diff options
| author | Rogério Brito <rbrito@ime.usp.br> | 2015-01-16 15:58:13 -0200 |
|---|---|---|
| committer | Rogério Brito <rbrito@ime.usp.br> | 2015-01-16 15:58:13 -0200 |
| commit | 453698570f26bebd37b39df8537d993b57d77b8b (patch) | |
| tree | 65e50343889ee152fe2d7b9bfe4aec647869ba95 | |
| parent | 0cf0312991a54458a07e903da2e47e9f3c8855ae (diff) | |
| download | youtube-dl-453698570f26bebd37b39df8537d993b57d77b8b.zip youtube-dl-453698570f26bebd37b39df8537d993b57d77b8b.tar.gz youtube-dl-453698570f26bebd37b39df8537d993b57d77b8b.tar.bz2 | |
Imported Upstream version 2015.01.16
290 files changed, 8562 insertions, 2418 deletions
@@ -1,7 +1,7 @@ -all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish +all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites clean: - rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part + rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json CONTRIBUTING.md.tmp cleanall: clean rm -f youtube-dl youtube-dl.exe @@ -35,13 +35,22 @@ install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtu install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish +codetest: + flake8 . + test: #nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test nosetests --verbose test + $(MAKE) codetest + +ot: offlinetest + +offlinetest: codetest + nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists tar: youtube-dl.tar.gz -.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion +.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish @@ -54,7 +63,13 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py chmod a+x youtube-dl README.md: youtube_dl/*.py youtube_dl/*/*.py - COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py + COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py + +CONTRIBUTING.md: README.md + python devscripts/make_contributing.py README.md CONTRIBUTING.md + +supportedsites: + python devscripts/make_supportedsites.py docs/supportedsites.md README.txt: README.md pandoc -f markdown -t plain README.md -o README.txt @@ -1,7 +1,15 @@ youtube-dl - download videos from youtube.com or other video platforms -# SYNOPSIS -**youtube-dl** [OPTIONS] URL [URL...] +- [INSTALLATION](#installation) +- [DESCRIPTION](#description) +- [OPTIONS](#options) +- [CONFIGURATION](#configuration) +- [OUTPUT TEMPLATE](#output-template) +- [VIDEO SELECTION](#video-selection) +- [FAQ](#faq) +- [DEVELOPER INSTRUCTIONS](#developer-instructions) +- [BUGS](#bugs) +- [COPYRIGHT](#copyright) # INSTALLATION @@ -34,6 +42,8 @@ YouTube.com and a few more sites. It requires the Python interpreter, version your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. + youtube-dl [OPTIONS] URL [URL...] + # OPTIONS -h, --help print this help text and exit --version print program version and exit @@ -50,10 +60,6 @@ which means you can modify it, redistribute it or use it however you like. they would handle --extractor-descriptions Output descriptions of all supported extractors - --proxy URL Use the specified HTTP/HTTPS proxy. Pass in - an empty string (--proxy "") for direct - connection - --socket-timeout None Time to wait before giving up, in seconds --default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large @@ -65,13 +71,25 @@ which means you can modify it, redistribute it or use it however you like. this is not possible instead of searching. --ignore-config Do not read configuration files. When given in the global configuration file /etc - /youtube-dl.conf: do not read the user - configuration in ~/.config/youtube-dl.conf - (%APPDATA%/youtube-dl/config.txt on - Windows) + /youtube-dl.conf: Do not read the user + configuration in ~/.config/youtube- + dl/config (%APPDATA%/youtube-dl/config.txt + on Windows) --flat-playlist Do not extract the videos of a playlist, only list them. +## Network Options: + --proxy URL Use the specified HTTP/HTTPS proxy. Pass in + an empty string (--proxy "") for direct + connection + --socket-timeout SECONDS Time to wait before giving up, in seconds + --source-address IP Client-side IP address to bind to + (experimental) + -4, --force-ipv4 Make all connections via IPv4 + (experimental) + -6, --force-ipv6 Make all connections via IPv6 + (experimental) + ## Video Selection: --playlist-start NUMBER playlist video to start at (default is 1) --playlist-end NUMBER playlist video to end at (default is last) @@ -113,12 +131,12 @@ which means you can modify it, redistribute it or use it however you like. size. By default, the buffer size is automatically resized from an initial value of SIZE. + --playlist-reverse Download playlist videos in reverse order ## Filesystem Options: -a, --batch-file FILE file containing URLs to download ('-' for stdin) --id use only video ID in file name - -A, --auto-number number downloaded files starting from 00000 -o, --output TEMPLATE output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the @@ -152,6 +170,9 @@ which means you can modify it, redistribute it or use it however you like. --restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames + -A, --auto-number [deprecated; use -o + "%(autonumber)s-%(title)s.%(ext)s" ] number + downloaded files starting from 00000 -t, --title [deprecated] use title in file name (default) -l, --literal [deprecated] alias of --title @@ -206,6 +227,8 @@ which means you can modify it, redistribute it or use it however you like. for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line. + --print-json Be quiet and print the video information as + JSON (video is still being downloaded). --newline output progress bar as new lines --no-progress do not print progress bar --console-title display progress in console titlebar @@ -216,6 +239,10 @@ which means you can modify it, redistribute it or use it however you like. files in the current directory to debug problems --print-traffic Display sent and read HTTP traffic + -C, --call-home Contact the youtube-dl server for + debugging. + --no-call-home Do NOT contact the youtube-dl server for + debugging. ## Workarounds: --encoding ENCODING Force the specified encoding (experimental) @@ -235,14 +262,15 @@ which means you can modify it, redistribute it or use it however you like. ## Video Format Options: -f, --format FORMAT video format code, specify the order of - preference using slashes: -f 22/17/18 . -f - mp4 , -f m4a and -f flv are also - supported. You can also use the special - names "best", "bestvideo", "bestaudio", - "worst", "worstvideo" and "worstaudio". By - default, youtube-dl will pick the best - quality. Use commas to download multiple - audio formats, such as -f + preference using slashes, as in -f 22/17/18 + . Instead of format codes, you can select + by extension for the extensions aac, m4a, + mp3, mp4, ogg, wav, webm. You can also use + the special names "best", "bestvideo", + "bestaudio", "worst". By default, youtube- + dl will pick the best quality. Use commas + to download multiple audio formats, such as + -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio of two formats into a single file using -f <video- @@ -256,6 +284,10 @@ which means you can modify it, redistribute it or use it however you like. -F, --list-formats list all available formats --youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos + --merge-output-format FORMAT If a merge is required (e.g. + bestvideo+bestaudio), output to given + container format. One of mkv, mp4, ogg, + webm, flv.Ignored if no merge is required ## Subtitle Options: --write-sub write subtitle file @@ -302,6 +334,11 @@ which means you can modify it, redistribute it or use it however you like. --add-metadata write metadata to the video file --xattrs write metadata to the video file's xattrs (using dublin core and xdg standards) + --fixup POLICY (experimental) Automatically correct known + faults of the file. One of never (do + nothing), warn (only emit a warning), + detect_or_warn(check whether we can do + anything about it, warn otherwise --prefer-avconv Prefer avconv over ffmpeg for running the postprocessors (default) --prefer-ffmpeg Prefer ffmpeg over avconv for running the @@ -313,7 +350,7 @@ which means you can modify it, redistribute it or use it however you like. # CONFIGURATION -You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`. +You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`. # OUTPUT TEMPLATE @@ -407,9 +444,15 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much. Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/). -### The links provided by youtube-dl -g are not working anymore +### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser. + +It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. + +It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule. -The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. +Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well. + +If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn. ### ERROR: no fmt_url_map or conn information found in video info @@ -436,6 +479,22 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29). +### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files? + +If you put youtube-dl and ffmpeg in the same directory that you're running the command from, it will work, but that's rather cumbersome. + +To make a different directory work - either for ffmpeg, or for youtube-dl, or for both - simply create the directory (say, `C:\bin`, or `C:\Users\<User name>\bin`), put all the executables directly in there, and then [set your PATH environment variable](https://www.java.com/en/download/help/path.xml) to include that directory. + +From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in. + +### How can I detect whether a given URL is supported by youtube-dl? + +For one, have a look at the [list of supported sites](docs/supportedsites). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug. + +It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor. + +If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program. + # DEVELOPER INSTRUCTIONS Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution. @@ -526,23 +585,61 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho From a Python program, you can embed youtube-dl in a more powerful fashion, like this: - import youtube_dl +```python +import youtube_dl - ydl_opts = {} - with youtube_dl.YoutubeDL(ydl_opts) as ydl: - ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) +ydl_opts = {} +with youtube_dl.YoutubeDL(ydl_opts) as ydl: + ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) +``` Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object. +Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file: + +```python +import youtube_dl + + +class MyLogger(object): + def debug(self, msg): + pass + + def warning(self, msg): + pass + + def error(self, msg): + print(msg) + + +def my_hook(d): + if d['status'] == 'finished': + print('Done downloading, now converting ...') + + +ydl_opts = { + 'format': 'bestaudio/best', + 'postprocessors': [{ + 'key': 'FFmpegExtractAudio', + 'preferredcodec': 'mp3', + 'preferredquality': '192', + }], + 'logger': MyLogger(), + 'progress_hooks': [my_hook], +} +with youtube_dl.YoutubeDL(ydl_opts) as ydl: + ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) +``` + # BUGS -Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. +Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode. -Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. +**Please include the full output of youtube-dl when run with `-v`**. -For discussions, join us in the irc channel #youtube-dl on freenode. +The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. -When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist): +Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist): ### Is the description of the issue itself sufficient? @@ -1,9 +1,15 @@ youtube-dl - download videos from youtube.com or other video platforms -SYNOPSIS -======== - -youtube-dl OPTIONS URL [URL...] +- INSTALLATION +- DESCRIPTION +- OPTIONS +- CONFIGURATION +- OUTPUT TEMPLATE +- VIDEO SELECTION +- FAQ +- DEVELOPER INSTRUCTIONS +- BUGS +- COPYRIGHT INSTALLATION ============ @@ -44,6 +50,8 @@ work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. + youtube-dl [OPTIONS] URL [URL...] + OPTIONS ======= @@ -62,10 +70,6 @@ OPTIONS they would handle --extractor-descriptions Output descriptions of all supported extractors - --proxy URL Use the specified HTTP/HTTPS proxy. Pass in - an empty string (--proxy "") for direct - connection - --socket-timeout None Time to wait before giving up, in seconds --default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large @@ -77,13 +81,27 @@ OPTIONS this is not possible instead of searching. --ignore-config Do not read configuration files. When given in the global configuration file /etc - /youtube-dl.conf: do not read the user - configuration in ~/.config/youtube-dl.conf - (%APPDATA%/youtube-dl/config.txt on - Windows) + /youtube-dl.conf: Do not read the user + configuration in ~/.config/youtube- + dl/config (%APPDATA%/youtube-dl/config.txt + on Windows) --flat-playlist Do not extract the videos of a playlist, only list them. +Network Options: +---------------- + + --proxy URL Use the specified HTTP/HTTPS proxy. Pass in + an empty string (--proxy "") for direct + connection + --socket-timeout SECONDS Time to wait before giving up, in seconds + --source-address IP Client-side IP address to bind to + (experimental) + -4, --force-ipv4 Make all connections via IPv4 + (experimental) + -6, --force-ipv6 Make all connections via IPv6 + (experimental) + Video Selection: ---------------- @@ -129,6 +147,7 @@ Download Options: size. By default, the buffer size is automatically resized from an initial value of SIZE. + --playlist-reverse Download playlist videos in reverse order Filesystem Options: ------------------- @@ -136,7 +155,6 @@ Filesystem Options: -a, --batch-file FILE file containing URLs to download ('-' for stdin) --id use only video ID in file name - -A, --auto-number number downloaded files starting from 00000 -o, --output TEMPLATE output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the @@ -170,6 +188,9 @@ Filesystem Options: --restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames + -A, --auto-number [deprecated; use -o + "%(autonumber)s-%(title)s.%(ext)s" ] number + downloaded files starting from 00000 -t, --title [deprecated] use title in file name (default) -l, --literal [deprecated] alias of --title @@ -226,6 +247,8 @@ Verbosity / Simulation Options: for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line. + --print-json Be quiet and print the video information as + JSON (video is still being downloaded). --newline output progress bar as new lines --no-progress do not print progress bar --console-title display progress in console titlebar @@ -236,6 +259,10 @@ Verbosity / Simulation Options: files in the current directory to debug problems --print-traffic Display sent and read HTTP traffic + -C, --call-home Contact the youtube-dl server for + debugging. + --no-call-home Do NOT contact the youtube-dl server for + debugging. Workarounds: ------------ @@ -259,14 +286,15 @@ Video Format Options: --------------------- -f, --format FORMAT video format code, specify the order of - preference using slashes: -f 22/17/18 . -f - mp4 , -f m4a and -f flv are also - supported. You can also use the special - names "best", "bestvideo", "bestaudio", - "worst", "worstvideo" and "worstaudio". By - default, youtube-dl will pick the best - quality. Use commas to download multiple - audio formats, such as -f + preference using slashes, as in -f 22/17/18 + . Instead of format codes, you can select + by extension for the extensions aac, m4a, + mp3, mp4, ogg, wav, webm. You can also use + the special names "best", "bestvideo", + "bestaudio", "worst". By default, youtube- + dl will pick the best quality. Use commas + to download multiple audio formats, such as + -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio of two formats into a single file using -f <video- @@ -280,6 +308,10 @@ Video Format Options: -F, --list-formats list all available formats --youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos + --merge-output-format FORMAT If a merge is required (e.g. + bestvideo+bestaudio), output to given + container format. One of mkv, mp4, ogg, + webm, flv.Ignored if no merge is required Subtitle Options: ----------------- @@ -332,6 +364,11 @@ Post-processing Options: --add-metadata write metadata to the video file --xattrs write metadata to the video file's xattrs (using dublin core and xdg standards) + --fixup POLICY (experimental) Automatically correct known + faults of the file. One of never (do + nothing), warn (only emit a warning), + detect_or_warn(check whether we can do + anything about it, warn otherwise --prefer-avconv Prefer avconv over ffmpeg for running the postprocessors (default) --prefer-ffmpeg Prefer ffmpeg over avconv for running the @@ -348,7 +385,8 @@ You can configure youtube-dl by placing default arguments (such as --extract-audio --no-mtime to always extract the audio and not copy the mtime) into /etc/youtube-dl.conf and/or ~/.config/youtube-dl/config. On Windows, the configuration file locations are -%APPDATA%\youtube-dl\config.txt and C:\Users\<Yourname>\youtube-dl.conf. +%APPDATA%\youtube-dl\config.txt and +C:\Users\<user name>\youtube-dl.conf. OUTPUT TEMPLATE =============== @@ -497,13 +535,29 @@ I have downloaded a video but how can I play it? Once the video is fully downloaded, use any video player, such as vlc or mplayer. -The links provided by youtube-dl -g are not working anymore +I extracted a video URL with -g, but it does not play on another machine / in my webbrowser. + +It depends a lot on the service. In many cases, requests for the video +(to download/play it) must come from the same IP address and with the +same cookies. Use the --cookies option to write the required cookies +into a file, and advise your downloader to read cookies from that file. +Some sites also require a common user agent to be used, use +--dump-user-agent to see the one in use by youtube-dl. + +It may be beneficial to use IPv6; in some cases, the restrictions are +only applied to IPv4. Some services (sometimes only for a subset of +videos) do not restrict the video URL by IP address, cookie, or +user-agent, but these are the exception rather than the rule. -The URLs youtube-dl outputs require the downloader to have the correct -cookies. Use the --cookies option to write the required cookies into a -file, and advise your downloader to read cookies from that file. Some -sites also require a common user agent to be used, use --dump-user-agent -to see the one in use by youtube-dl. +Please bear in mind that some URL protocols are not supported by +browsers out of the box, including RTMP. If you are using -g, your own +downloader must support these as well. + +If you want to play the video on a machine that is not running +youtube-dl, you can relay the video content from the machine that runs +youtube-dl. You can use -o - to let youtube-dl stream a video to stdout, +or simply allow the player to download the files written by youtube-dl +in turn. ERROR: no fmt_url_map or conn information found in video info @@ -540,6 +594,45 @@ The exe throws a Runtime error from Visual C++ To run the exe you need to install first the Microsoft Visual C++ 2008 Redistributable Package. +On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files? + +If you put youtube-dl and ffmpeg in the same directory that you're +running the command from, it will work, but that's rather cumbersome. + +To make a different directory work - either for ffmpeg, or for +youtube-dl, or for both - simply create the directory (say, C:\bin, or +C:\Users\<User name>\bin), put all the executables directly in there, +and then set your PATH environment variable to include that directory. + +From then on, after restarting your shell, you will be able to access +both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) +by simply typing youtube-dl or ffmpeg, no matter what directory you're +in. + +How can I detect whether a given URL is supported by youtube-dl? + +For one, have a look at the list of supported sites. Note that it can +sometimes happen that the site changes its URL scheme (say, from +http://example.com/v/1234567 to http://example.com/v/1234567 ) and +youtube-dl reports an URL of a service in that list as unsupported. In +that case, simply report a bug. + +It is not possible to detect whether a URL is supported or not. That's +because youtube-dl contains a generic extractor which matches all URLs. +You may be tempted to disable, exclude, or remove the generic extractor, +but the generic extractor not only allows users to extract videos from +lots of websites that embed a video from another service, but may also +be used to extract video from a service that it's hosting itself. +Therefore, we neither recommend nor support disabling, excluding, or +removing the generic extractor. + +If you want to find out whether a given URL is supported, simply call +youtube-dl with it. If you get no videos back, chances are the URL is +either not referring to a video or unsupported. You can find out which +by examining the output (if you run youtube-dl on the console) or +catching an UnsupportedError exception if you run it from a Python +program. + DEVELOPER INSTRUCTIONS ====================== @@ -654,32 +747,72 @@ any problems parsing its output, feel free to create a report. From a Python program, you can embed youtube-dl in a more powerful fashion, like this: - import youtube_dl +``` {.python} +import youtube_dl - ydl_opts = {} - with youtube_dl.YoutubeDL(ydl_opts) as ydl: - ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) +ydl_opts = {} +with youtube_dl.YoutubeDL(ydl_opts) as ydl: + ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) +``` Most likely, you'll want to use various options. For a list of what can be done, have a look at youtube_dl/YoutubeDL.py. For a start, if you want to intercept youtube-dl's output, set a logger object. +Here's a more complete example of a program that outputs only errors +(and a short message after the download is finished), and +downloads/converts the video to an mp3 file: + +``` {.python} +import youtube_dl + + +class MyLogger(object): + def debug(self, msg): + pass + + def warning(self, msg): + pass + + def error(self, msg): + print(msg) + + +def my_hook(d): + if d['status'] == 'finished': + print('Done downloading, now converting ...') + + +ydl_opts = { + 'format': 'bestaudio/best', + 'postprocessors': [{ + 'key': 'FFmpegExtractAudio', + 'preferredcodec': 'mp3', + 'preferredquality': '192', + }], + 'logger': MyLogger(), + 'progress_hooks': [my_hook], +} +with youtube_dl.YoutubeDL(ydl_opts) as ydl: + ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) +``` + BUGS ==== Bugs and suggestions should be reported at: https://github.com/rg3/youtube-dl/issues . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the -bug report), please do not send bug reports via personal email. +bug report), please do not send bug reports via personal email. For +discussions, join us in the irc channel #youtube-dl on freenode. + +Please include the full output of youtube-dl when run with -v. -Please include the full output of the command when run with --verbose. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. -For discussions, join us in the irc channel #youtube-dl on freenode. - -When you submit a request, please re-read it once to avoid a couple of +Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist): Is the description of the issue itself sufficient? diff --git a/devscripts/gh-pages/update-sites.py b/devscripts/gh-pages/update-sites.py index f0f0481..d3ef5f0 100755 --- a/devscripts/gh-pages/update-sites.py +++ b/devscripts/gh-pages/update-sites.py @@ -16,7 +16,7 @@ def main(): template = tmplf.read() ie_htmls = [] - for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()): + for ie in youtube_dl.list_extractors(age_limit=None): ie_html = '<b>{}</b>'.format(ie.IE_NAME) ie_desc = getattr(ie, 'IE_DESC', None) if ie_desc is False: diff --git a/devscripts/make_contributing.py b/devscripts/make_contributing.py new file mode 100755 index 0000000..5e454a4 --- /dev/null +++ b/devscripts/make_contributing.py @@ -0,0 +1,32 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + +import io +import optparse +import re + + +def main(): + parser = optparse.OptionParser(usage='%prog INFILE OUTFILE') + options, args = parser.parse_args() + if len(args) != 2: + parser.error('Expected an input and an output filename') + + infile, outfile = args + + with io.open(infile, encoding='utf-8') as inf: + readme = inf.read() + + bug_text = re.search( + r'(?s)#\s*BUGS\s*[^\n]*\s*(.*?)#\s*COPYRIGHT', readme).group(1) + dev_text = re.search( + r'(?s)(#\s*DEVELOPER INSTRUCTIONS.*?)#\s*EMBEDDING YOUTUBE-DL', + readme).group(1) + + out = bug_text + dev_text + + with io.open(outfile, 'w', encoding='utf-8') as outf: + outf.write(out) + +if __name__ == '__main__': + main() diff --git a/devscripts/make_supportedsites.py b/devscripts/make_supportedsites.py new file mode 100644 index 0000000..3df4385 --- /dev/null +++ b/devscripts/make_supportedsites.py @@ -0,0 +1,45 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + +import io +import optparse +import os +import sys + + +# Import youtube_dl +ROOT_DIR = os.path.join(os.path.dirname(__file__), '..') +sys.path.append(ROOT_DIR) +import youtube_dl + + +def main(): + parser = optparse.OptionParser(usage='%prog OUTFILE.md') + options, args = parser.parse_args() + if len(args) != 1: + parser.error('Expected an output filename') + + outfile, = args + + def gen_ies_md(ies): + for ie in ies: + ie_md = '**{0}**'.format(ie.IE_NAME) + ie_desc = getattr(ie, 'IE_DESC', None) + if ie_desc is False: + continue + if ie_desc is not None: + ie_md += ': {0}'.format(ie.IE_DESC) + if not ie.working(): + ie_md += ' (Currently broken)' + yield ie_md + + ies = sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()) + out = '# Supported sites\n' + ''.join( + ' - ' + md + '\n' + for md in gen_ies_md(ies)) + + with io.open(outfile, 'w', encoding='utf-8') as outf: + outf.write(out) + +if __name__ == '__main__': + main() diff --git a/devscripts/prepare_manpage.py b/devscripts/prepare_manpage.py index f66bebf..7ece377 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -11,8 +11,19 @@ README_FILE = os.path.join(ROOT_DIR, 'README.md') with io.open(README_FILE, encoding='utf-8') as f: readme = f.read() -PREFIX = '%YOUTUBE-DL(1)\n\n# NAME\n' -readme = re.sub(r'(?s)# INSTALLATION.*?(?=# DESCRIPTION)', '', readme) +PREFIX = '''%YOUTUBE-DL(1) + +# NAME + +youtube\-dl \- download videos from youtube.com or other video platforms + +# SYNOPSIS + +**youtube-dl** \[OPTIONS\] URL [URL...] + +''' +readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme) +readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme) readme = PREFIX + readme if sys.version_info < (3, 0): diff --git a/docs/supportedsites.md b/docs/supportedsites.md new file mode 100644 index 0000000..dbbf4a7 --- /dev/null +++ b/docs/supportedsites.md @@ -0,0 +1,500 @@ +# Supported sites + - **1up.com** + - **220.ro** + - **24video** + - **3sat** + - **4tube** + - **56.com** + - **5min** + - **8tracks** + - **9gag** + - **abc.net.au** + - **AcademicEarth:Course** + - **AddAnime** + - **AdobeTV** + - **AdultSwim** + - **Aftonbladet** + - **AlJazeera** + - **Allocine** + - **anitube.se** + - **AnySex** + - **Aparat** + - **AppleTrailers** + - **archive.org**: archive.org videos + - **ARD** + - **ARD:mediathek** + - **arte.tv** + - **arte.tv:+7** + - **arte.tv:concert** + - **arte.tv:creative** + - **arte.tv:ddc** + - **arte.tv:embed** + - **arte.tv:future** + - **audiomack** + - **AUEngine** + - **Azubu** + - **bambuser** + - **bambuser:channel** + - **Bandcamp** + - **Bandcamp:album** + - **bbc.co.uk**: BBC iPlayer + - **Beeg** + - **BehindKink** + - **Bet** + - **Bild**: Bild.de + - **BiliBili** + - **blinkx** + - **blip.tv:user** + - **BlipTV** + - **Bloomberg** + - **Bpb**: Bundeszentrale für politische Bildung + - **BR**: Bayerischer Rundfunk Mediathek + - **Break** + - **Brightcove** + - **BuzzFeed** + - **BYUtv** + - **Canal13cl** + - **canalc2.tv** + - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv + - **CBS** + - **CBSNews**: CBS News + - **CeskaTelevize** + - **channel9**: Channel 9 + - **Chilloutzone** + - **Cinchcast** + - **Cinemassacre** + - **clipfish** + - **cliphunter** + - **Clipsyndicate** + - **Cloudy** + - **Clubic** + - **cmt.com** + - **CNET** + - **CNN** + - **CNNBlogs** + - **CollegeHumor** + - **ComCarCoff** + - **ComedyCentral** + - **ComedyCentralShows**: The Daily Show / The Colbert Report + - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED + - **Cracked** + - **Criterion** + - **Crunchyroll** + - **crunchyroll:playlist** + - **CSpan**: C-SPAN + - **culturebox.francetvinfo.fr** + - **dailymotion** + - **dailymotion:playlist** + - **dailymotion:user** + - **daum.net** + - **DBTV** + - **DeezerPlaylist** + - **defense.gouv.fr** + - **Discovery** + - **divxstage**: DivxStage + - **Dotsub** + - **Dropbox** + - **DrTuber** + - **DRTV** + - **Dump** + - **dvtv**: http://video.aktualne.cz/ + - **EbaumsWorld** + - **eHow** + - **Einthusan** + - **eitb.tv** + - **EllenTV** + - **EllenTV:clips** + - **ElPais**: El País + - **EMPFlix** + - **Engadget** + - **Eporner** + - **Escapist** + - **EveryonesMixtape** + - **exfm**: ex.fm + - **ExpoTV** + - **ExtremeTube** + - **facebook** + - **faz.net** + - **fc2** + - **fernsehkritik.tv** + - **fernsehkritik.tv:postecke** + - **Firedrive** + - **Firstpost** + - **firsttv**: Видеоархив - Первый канал + - **Flickr** + - **Folketinget**: Folketinget (ft.dk; Danish parliament) + - **Foxgay** + - **FoxNews** + - **france2.fr:generation-quoi** + - **FranceCulture** + - **FranceInter** + - **francetv**: France 2, 3, 4, 5 and Ô + - **francetvinfo.fr** + - **Freesound** + - **freespeech.org** + - **FreeVideo** + - **FunnyOrDie** + - **Gamekings** + - **GameOne** + - **gameone:playlist** + - **GameSpot** + - **GameStar** + - **Gametrailers** + - **GDCVault** + - **generic**: Generic downloader that works on some sites + - **GiantBomb** + - **Glide**: Glide mobile video messages (glide.me) + - **Globo** + - **GodTube** + - **GoldenMoustache** + - **Golem** + - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in + - **Goshgay** + - **Grooveshark** + - **Groupon** + - **Hark** + - **Heise** + - **Helsinki**: helsinki.fi + - **HentaiStigma** + - **HornBunny** + - **HostingBulk** + - **HotNewHipHop** + - **Howcast** + - **HowStuffWorks** + - **HuffPost**: Huffington Post + - **Hypem** + - **Iconosquare** + - **ign.com** + - **imdb**: Internet Movie Database trailers + - **imdb:list**: Internet Movie Database lists + - **Ina** + - **InfoQ** + - **Instagram** + - **instagram:user**: Instagram user profile + - **InternetVideoArchive** + - **IPrima** + - **ivi**: ivi.ru + - **ivi:compilation**: ivi.ru compilations + - **Izlesene** + - **JadoreCettePub** + - **JeuxVideo** + - **Jove** + - **jpopsuki.tv** + - **Jukebox** + - **Kankan** + - **keek** + - **KeezMovies** + - **KhanAcademy** + - **KickStarter** + - **kontrtube**: KontrTube.ru - Труба зовёт + - **KrasView**: Красвью + - **Ku6** + - **la7.tv** + - **Laola1Tv** + - **lifenews**: LIFE | NEWS + - **LiveLeak** + - **livestream** + - **livestream:original** + - **lrt.lt** + - **lynda**: lynda.com videos + - **lynda:course**: lynda.com online courses + - **m6** + - **macgamestore**: MacGameStore trailers + - **mailru**: Видео@Mail.Ru + - **Malemotion** + - **MDR** + - **metacafe** + - **Metacritic** + - **Mgoon** + - **Minhateca** + - **MinistryGrid** + - **mitele.es** + - **mixcloud** + - **MLB** + - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net + - **Mofosex** + - **Mojvideo** + - **Moniker**: allmyvideos.net and vidspot.net + - **mooshare**: Mooshare.biz + - **Morningstar**: morningstar.com + - **Motherless** + - **Motorsport**: motorsport.com + - **MovieClips** + - **Moviezine** + - **movshare**: MovShare + - **MPORA** + - **MTV** + - **mtviggy.com** + - **mtvservices:embedded** + - **MuenchenTV**: münchen.tv + - **MusicPlayOn** + - **MusicVault** + - **muzu.tv** + - **MySpace** + - **MySpace:album** + - **MySpass** + - **myvideo** + - **MyVidster** + - **Naver** + - **NBA** + - **NBC** + - **NBCNews** + - **ndr**: NDR.de - Mediathek + - **NDTV** + - **NerdCubedFeed** + - **Newgrounds** + - **Newstube** + - **nfb**: National Film Board of Canada + - **nfl.com** + - **nhl.com** + - **nhl.com:videocenter**: NHL videocenter category + - **niconico**: ニコニコ動画 + - **NiconicoPlaylist** + - **Noco** + - **Normalboots** + - **NosVideo** + - **novamov**: NovaMov + - **Nowness** + - **nowvideo**: NowVideo + - **npo.nl** + - **NRK** + - **NRKTV** + - **NTV** + - **Nuvid** + - **NYTimes** + - **ocw.mit.edu** + - **OktoberfestTV** + - **on.aol.com** + - **Ooyala** + - **orf:oe1**: Radio Österreich 1 + - **orf:tvthek**: ORF TVthek + - **ORFFM4**: radio FM4 + - **parliamentlive.tv**: UK parliament videos + - **Patreon** + - **PBS** + - **Phoenix** + - **Photobucket** + - **PlanetaPlay** + - **play.fm** + - **played.to** + - **Playvid** + - **plus.google**: Google Plus + - **pluzz.francetv.fr** + - **podomatic** + - **PornHd** + - **PornHub** + - **Pornotube** + - **PornoXO** + - **PromptFile** + - **prosiebensat1**: ProSiebenSat.1 Digital + - **Pyvideo** + - **QuickVid** + - **radio.de** + - **radiofrance** + - **Rai** + - **RBMARadio** + - **RedTube** + - **Restudy** + - **ReverbNation** + - **RingTV** + - **RottenTomatoes** + - **Roxwel** + - **RTBF** + - **RTLnow** + - **rtlxl.nl** + - **RTP** + - **RTS**: RTS.ch + - **rtve.es:alacarta**: RTVE a la carta + - **rtve.es:live**: RTVE.es live streams + - **RUHD** + - **rutube**: Rutube videos + - **rutube:channel**: Rutube channels + - **rutube:movie**: Rutube movies + - **rutube:person**: Rutube person videos + - **RUTV**: RUTV.RU + - **Sapo**: SAPO Vídeos + - **savefrom.net** + - **SBS**: sbs.com.au + - **SciVee** + - **screen.yahoo:search**: Yahoo screen search + - **Screencast** + - **ScreencastOMatic** + - **ScreenwaveMedia** + - **ServingSys** + - **Sexu** + - **SexyKarma**: Sexy Karma and Watch Indian Porn + - **Shared** + - **ShareSix** + - **Sina** + - **Slideshare** + - **Slutload** + - **smotri**: Smotri.com + - **smotri:broadcast**: Smotri.com broadcasts + - **smotri:community**: Smotri.com community videos + - **smotri:user**: Smotri.com user videos + - **Snotr** + - **Sockshare** + - **Sohu** + - **soundcloud** + - **soundcloud:playlist** + - **soundcloud:set** + - **soundcloud:user** + - **Soundgasm** + - **southpark.cc.com** + - **southpark.de** + - **Space** + - **Spankwire** + - **Spiegel** + - **Spiegel:Article**: Articles on spiegel.de + - **Spiegeltv** + - **Spike** + - **Sport5** + - **SportBox** + - **SportDeutschland** + - **SRMediathek**: Süddeutscher Rundfunk + - **stanfordoc**: Stanford Open ClassRoom + - **Steam** + - **streamcloud.eu** + - **StreamCZ** + - **SunPorno** + - **SWRMediathek** + - **Syfy** + - **SztvHu** + - **Tagesschau** + - **Tapely** + - **Tass** + - **teachertube**: teachertube.com videos + - **teachertube:user:collection**: teachertube.com user and collection videos + - **TeachingChannel** + - **Teamcoco** + - **TeamFour** + - **TechTalks** + - **techtv.mit.edu** + - **TED** + - **tegenlicht.vpro.nl** + - **TeleBruxelles** + - **telecinco.es** + - **TeleMB** + - **TenPlay** + - **TF1** + - **TheOnion** + - **ThePlatform** + - **TheSixtyOne** + - **ThisAV** + - **THVideo** + - **THVideoPlaylist** + - **tinypic**: tinypic.com videos + - **tlc.com** + - **tlc.de** + - **TMZ** + - **TNAFlix** + - **tou.tv** + - **Toypics**: Toypics user profile + - **ToypicsUser**: Toypics user profile + - **TrailerAddict** (Currently broken) + - **Trilulilu** + - **TruTube** + - **Tube8** + - **Tudou** + - **Tumblr** + - **TuneIn** + - **Turbo** + - **Tutv** + - **tv.dfb.de** + - **tvigle**: Интернет-телевидение Tvigle.ru + - **tvp.pl** + - **TVPlay**: TV3Play and related services + - **Twitch** + - **Ubu** + - **udemy** + - **udemy:course** + - **Unistra** + - **Urort**: NRK P3 Urørt + - **ustream** + - **ustream:channel** + - **Vbox7** + - **VeeHD** + - **Veoh** + - **Vesti**: Вести.Ru + - **Vevo** + - **VGTV** + - **vh1.com** + - **Vice** + - **Viddler** + - **video.google:search**: Google Video search + - **video.mit.edu** + - **VideoBam** + - **VideoDetective** + - **videofy.me** + - **videolectures.net** + - **VideoMega** + - **VideoPremium** + - **VideoTt**: video.tt - Your True Tube + - **videoweed**: VideoWeed + - **Vidme** + - **Vidzi** + - **viki** + - **vimeo** + - **vimeo:album** + - **vimeo:channel** + - **vimeo:group** + - **vimeo:likes**: Vimeo user likes + - **vimeo:review**: Review pages on vimeo + - **vimeo:user** + - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication) + - **Vimple**: Vimple.ru + - **Vine** + - **vine:user** + - **vk.com** + - **vk.com:user-videos**: vk.com:All of a user's videos + - **Vodlocker** + - **Vporn** + - **VRT** + - **vube**: Vube.com + - **VuClip** + - **vulture.com** + - **Walla** + - **WashingtonPost** + - **wat.tv** + - **WayOfTheMaster** + - **WDR** + - **wdr:mobile** + - **WDRMaus**: Sendung mit der Maus + - **Weibo** + - **Wimp** + - **Wistia** + - **WorldStarHipHop** + - **wrzuta.pl** + - **XBef** + - **XboxClips** + - **XHamster** + - **XMinus** + - **XNXX** + - **XTube** + - **XTubeUser**: XTube user profile + - **XVideos** + - **Yahoo**: Yahoo screen and movies + - **YesJapan** + - **Ynet** + - **YouJizz** + - **Youku** + - **YouPorn** + - **YourUpload** + - **youtube**: YouTube.com + - **youtube:channel**: YouTube.com channels + - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication) + - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication) + - **youtube:playlist**: YouTube.com playlists + - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication) + - **youtube:search**: YouTube.com searches + - **youtube:search:date**: YouTube.com searches, newest videos first + - **youtube:search_url**: YouTube.com search URLs + - **youtube:show**: YouTube.com (multi-season) shows + - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication) + - **youtube:toplist**: YouTube.com top lists, "yttoplist:{channel}:{list title}" (Example: "yttoplist:music:Top Tracks") + - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword) + - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication) + - **ZDF** + - **ZDFChannel** + - **zingmp3:album**: mp3.zing.vn albums + - **zingmp3:song**: mp3.zing.vn songs diff --git a/test/helper.py b/test/helper.py index 9a7f074..c416f38 100644 --- a/test/helper.py +++ b/test/helper.py @@ -82,24 +82,14 @@ class FakeYDL(YoutubeDL): def gettestcases(include_onlymatching=False): for ie in youtube_dl.extractor.gen_extractors(): - t = getattr(ie, '_TEST', None) - if t: - assert not hasattr(ie, '_TESTS'), \ - '%s has _TEST and _TESTS' % type(ie).__name__ - tests = [t] - else: - tests = getattr(ie, '_TESTS', []) - for t in tests: - if not include_onlymatching and t.get('only_matching', False): - continue - t['name'] = type(ie).__name__[:-len('IE')] - yield t + for tc in ie.get_testcases(include_onlymatching): + yield tc md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() -def expect_info_dict(self, expected_dict, got_dict): +def expect_info_dict(self, got_dict, expected_dict): for info_field, expected in expected_dict.items(): if isinstance(expected, compat_str) and expected.startswith('re:'): got = got_dict.get(info_field) @@ -120,6 +110,20 @@ def expect_info_dict(self, expected_dict, got_dict): else: if isinstance(expected, compat_str) and expected.startswith('md5:'): got = 'md5:' + md5(got_dict.get(info_field)) + elif isinstance(expected, compat_str) and expected.startswith('mincount:'): + got = got_dict.get(info_field) + self.assertTrue( + isinstance(got, list), + 'Expected field %s to be a list, but it is of type %s' % ( + info_field, type(got).__name__)) + expected_num = int(expected.partition(':')[2]) + assertGreaterEqual( + self, len(got), expected_num, + 'Expected %d items in field %s, but only got %d' % ( + expected_num, info_field, len(got) + ) + ) + continue else: got = got_dict.get(info_field) self.assertEqual(expected, got, @@ -161,7 +165,9 @@ def assertRegexpMatches(self, text, regexp, msg=None): else: m = re.match(regexp, text) if not m: - note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text) + note = 'Regexp didn\'t match: %r not found' % (regexp) + if len(text) < 1000: + note += ' in %r' % text if msg is None: msg = note else: diff --git a/test/swftests/ArrayAccess.swf b/test/swftests/ArrayAccess.swf Binary files differindex 150b23d..240fd66 100644 --- a/test/swftests/ArrayAccess.swf +++ b/test/swftests/ArrayAccess.swf diff --git a/test/swftests/ClassCall.swf b/test/swftests/ClassCall.swf Binary files differindex 8a19460..8bdfe06 100644 --- a/test/swftests/ClassCall.swf +++ b/test/swftests/ClassCall.swf diff --git a/test/swftests/ClassConstruction.swf b/test/swftests/ClassConstruction.swf Binary files differindex 01b2141..576eb30 100644 --- a/test/swftests/ClassConstruction.swf +++ b/test/swftests/ClassConstruction.swf diff --git a/test/swftests/ConstArrayAccess.swf b/test/swftests/ConstArrayAccess.swf Binary files differindex 70c5a7c..0d902fd 100644 --- a/test/swftests/ConstArrayAccess.swf +++ b/test/swftests/ConstArrayAccess.swf diff --git a/test/swftests/ConstantInt.swf b/test/swftests/ConstantInt.swf Binary files differindex a81677c..b8bd0cb 100644 --- a/test/swftests/ConstantInt.swf +++ b/test/swftests/ConstantInt.swf diff --git a/test/swftests/DictCall.swf b/test/swftests/DictCall.swf Binary files differindex e786bce..3fa3559 100644 --- a/test/swftests/DictCall.swf +++ b/test/swftests/DictCall.swf diff --git a/test/swftests/EqualsOperator.swf b/test/swftests/EqualsOperator.swf Binary files differindex 63ad7d4..33487f0 100644 --- a/test/swftests/EqualsOperator.swf +++ b/test/swftests/EqualsOperator.swf diff --git a/test/swftests/LocalVars.swf b/test/swftests/LocalVars.swf Binary files differindex d003d4f..42102af 100644 --- a/test/swftests/LocalVars.swf +++ b/test/swftests/LocalVars.swf diff --git a/test/swftests/MemberAssignment.swf b/test/swftests/MemberAssignment.swf Binary files differindex ba89ef0..c3ec513 100644 --- a/test/swftests/MemberAssignment.swf +++ b/test/swftests/MemberAssignment.swf diff --git a/test/swftests/NeOperator.swf b/test/swftests/NeOperator.swf Binary files differindex ee2487c..a251f7a 100644 --- a/test/swftests/NeOperator.swf +++ b/test/swftests/NeOperator.swf diff --git a/test/swftests/PrivateCall.swf b/test/swftests/PrivateCall.swf Binary files differindex 7abbfec..7fa395a 100644 --- a/test/swftests/PrivateCall.swf +++ b/test/swftests/PrivateCall.swf diff --git a/test/swftests/PrivateVoidCall.swf b/test/swftests/PrivateVoidCall.swf Binary files differindex 89dbdd9..09a857e 100644 --- a/test/swftests/PrivateVoidCall.swf +++ b/test/swftests/PrivateVoidCall.swf diff --git a/test/swftests/StaticAssignment.swf b/test/swftests/StaticAssignment.swf Binary files differindex 9727589..dff661c 100644 --- a/test/swftests/StaticAssignment.swf +++ b/test/swftests/StaticAssignment.swf diff --git a/test/swftests/StaticRetrieval.swf b/test/swftests/StaticRetrieval.swf Binary files differindex 3b6366e..622c40d 100644 --- a/test/swftests/StaticRetrieval.swf +++ b/test/swftests/StaticRetrieval.swf diff --git a/test/swftests/StringBasics.swf b/test/swftests/StringBasics.swf Binary files differindex 6ade5f7..2784c2b 100644 --- a/test/swftests/StringBasics.swf +++ b/test/swftests/StringBasics.swf diff --git a/test/swftests/StringCharCodeAt.swf b/test/swftests/StringCharCodeAt.swf Binary files differindex d09b8be..e81fce1 100644 --- a/test/swftests/StringCharCodeAt.swf +++ b/test/swftests/StringCharCodeAt.swf diff --git a/test/swftests/StringConversion.swf b/test/swftests/StringConversion.swf Binary files differindex 28546c6..188d56e 100644 --- a/test/swftests/StringConversion.swf +++ b/test/swftests/StringConversion.swf diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 13c18ed..be8d129 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase): self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2') + def test_html_search_meta(self): + ie = self.ie + html = ''' + <meta name="a" content="1" /> + <meta name='b' content='2'> + <meta name="c" content='3'> + <meta name=d content='4'> + <meta property="e" content='5' > + <meta content="6" name="f"> + ''' + + self.assertEqual(ie._html_search_meta('a', html), '1') + self.assertEqual(ie._html_search_meta('b', html), '2') + self.assertEqual(ie._html_search_meta('c', html), '3') + self.assertEqual(ie._html_search_meta('d', html), '4') + self.assertEqual(ie._html_search_meta('e', html), '5') + self.assertEqual(ie._html_search_meta('f', html), '6') + if __name__ == '__main__': unittest.main() diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index f8e4f93..85d87f2 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -8,6 +8,8 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) +import copy + from test.helper import FakeYDL, assertRegexpMatches from youtube_dl import YoutubeDL from youtube_dl.extractor import YoutubeIE @@ -192,6 +194,37 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'vid-high') + def test_format_selection_audio_exts(self): + formats = [ + {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'}, + {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'}, + {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'}, + {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'}, + {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'}, + ] + + info_dict = _make_result(formats) + ydl = YDL({'format': 'best'}) + ie = YoutubeIE(ydl) + ie._sort_formats(info_dict['formats']) + ydl.process_ie_result(copy.deepcopy(info_dict)) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'aac-64') + + ydl = YDL({'format': 'mp3'}) + ie = YoutubeIE(ydl) + ie._sort_formats(info_dict['formats']) + ydl.process_ie_result(copy.deepcopy(info_dict)) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'mp3-64') + + ydl = YDL({'prefer_free_formats': True}) + ie = YoutubeIE(ydl) + ie._sort_formats(info_dict['formats']) + ydl.process_ie_result(copy.deepcopy(info_dict)) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'ogg-64') + def test_format_selection_video(self): formats = [ {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'}, @@ -218,7 +251,7 @@ class TestFormatSelection(unittest.TestCase): # 3D '85', '84', '102', '83', '101', '82', '100', # Dash video - '138', '137', '248', '136', '247', '135', '246', + '137', '248', '136', '247', '135', '246', '245', '244', '134', '243', '133', '242', '160', # Dash audio '141', '172', '140', '171', '139', diff --git a/test/test_age_restriction.py b/test/test_age_restriction.py index 5be065c..6f5513f 100644 --- a/test/test_age_restriction.py +++ b/test/test_age_restriction.py @@ -45,11 +45,6 @@ class TestAgeRestriction(unittest.TestCase): 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', '505835.mp4', 2, old_age=25) - def test_pornotube(self): - self._assert_restricted( - 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', - '1689755.flv', 13) - if __name__ == '__main__': unittest.main() diff --git a/test/test_download.py b/test/test_download.py index a009aa4..412f3db 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -155,7 +155,7 @@ def generator(test_case): if is_playlist: self.assertEqual(res_dict['_type'], 'playlist') self.assertTrue('entries' in res_dict) - expect_info_dict(self, test_case.get('info_dict', {}), res_dict) + expect_info_dict(self, res_dict, test_case.get('info_dict', {})) if 'playlist_mincount' in test_case: assertGreaterEqual( @@ -204,7 +204,7 @@ def generator(test_case): with io.open(info_json_fn, encoding='utf-8') as infof: info_dict = json.load(infof) - expect_info_dict(self, tc.get('info_dict', {}), info_dict) + expect_info_dict(self, info_dict, tc.get('info_dict', {})) finally: try_rm_tcs_files() if is_playlist and res_dict is not None and res_dict.get('entries'): diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 7c4cd82..6336dd3 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -17,6 +17,7 @@ from youtube_dl.extractor import ( TEDIE, VimeoIE, WallaIE, + CeskaTelevizeIE, ) @@ -88,6 +89,14 @@ class TestYoutubeSubtitles(BaseTestSubtitles): subtitles = self.getSubtitles() self.assertTrue(subtitles['it'] is not None) + def test_youtube_translated_subtitles(self): + # This video has a subtitles track, which can be translated + self.url = 'Ky9eprVWzlI' + self.DL.params['writeautomaticsub'] = True + self.DL.params['subtitleslangs'] = ['it'] + subtitles = self.getSubtitles() + self.assertTrue(subtitles['it'] is not None) + def test_youtube_nosubtitles(self): self.DL.expect_warning('video doesn\'t have subtitles') self.url = 'n5BB19UTcdA' @@ -309,5 +318,32 @@ class TestWallaSubtitles(BaseTestSubtitles): self.assertEqual(len(subtitles), 0) +class TestCeskaTelevizeSubtitles(BaseTestSubtitles): + url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky' + IE = CeskaTelevizeIE + + def test_list_subtitles(self): + self.DL.expect_warning('Automatic Captions not supported by this server') + self.DL.params['listsubtitles'] = True + info_dict = self.getInfoDict() + self.assertEqual(info_dict, None) + + def test_allsubtitles(self): + self.DL.expect_warning('Automatic Captions not supported by this server') + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['cs'])) + self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4') + + def test_nosubtitles(self): + self.DL.expect_warning('video doesn\'t have subtitles') + self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220' + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(len(subtitles), 0) + + if __name__ == '__main__': unittest.main() diff --git a/test/test_unicode_literals.py b/test/test_unicode_literals.py index 2cc431b..7f81669 100644 --- a/test/test_unicode_literals.py +++ b/test/test_unicode_literals.py @@ -1,9 +1,13 @@ from __future__ import unicode_literals -import io +# Allow direct execution import os -import re +import sys import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +import io +import re rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) @@ -14,6 +18,9 @@ IGNORED_FILES = [ ] +from test.helper import assertRegexpMatches + + class TestUnicodeLiterals(unittest.TestCase): def test_all_files(self): for dirpath, _, filenames in os.walk(rootDir): @@ -29,9 +36,10 @@ class TestUnicodeLiterals(unittest.TestCase): if "'" not in code and '"' not in code: continue - self.assertRegexpMatches( + assertRegexpMatches( + self, code, - r'(?:#.*\n*)?from __future__ import (?:[a-z_]+,\s*)*unicode_literals', + r'(?:(?:#.*?|\s*)\n)*from __future__ import (?:[a-z_]+,\s*)*unicode_literals', 'unicode_literals import missing in %s' % fn) m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code) diff --git a/test/test_utils.py b/test/test_utils.py index baa3a21..206760d 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -16,38 +16,41 @@ import json import xml.etree.ElementTree from youtube_dl.utils import ( + age_restricted, + args_to_str, clean_html, DateRange, + detect_exe_version, encodeFilename, + escape_rfc3986, + escape_url, find_xpath_attr, fix_xml_ampersands, - orderedSet, - OnDemandPagedList, InAdvancePagedList, + intlist_to_bytes, + js_to_json, + limit_length, + OnDemandPagedList, + orderedSet, parse_duration, + parse_filesize, + parse_iso8601, read_batch_urls, sanitize_filename, shell_quote, smuggle_url, str_to_int, + strip_jsonp, struct_unpack, timeconvert, unescapeHTML, unified_strdate, unsmuggle_url, + uppercase_escape, url_basename, urlencode_postdata, + version_tuple, xpath_with_ns, - parse_iso8601, - strip_jsonp, - uppercase_escape, - limit_length, - escape_rfc3986, - escape_url, - js_to_json, - intlist_to_bytes, - args_to_str, - parse_filesize, ) @@ -76,6 +79,10 @@ class TestUtil(unittest.TestCase): tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430' self.assertEqual(sanitize_filename(tests), tests) + self.assertEqual( + sanitize_filename('New World record at 0:12:34'), + 'New World record at 0_12_34') + forbidden = '"\0\\/' for fc in forbidden: for fbc in forbidden: @@ -141,8 +148,12 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_strdate('8/7/2009'), '20090708') self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214') self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011') + self.assertEqual(unified_strdate('1968 12 10'), '19681210') self.assertEqual(unified_strdate('1968-12-10'), '19681210') self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128') + self.assertEqual( + unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False), + '20141126') def test_find_xpath_attr(self): testxml = '''<root> @@ -202,6 +213,8 @@ class TestUtil(unittest.TestCase): def test_parse_duration(self): self.assertEqual(parse_duration(None), None) + self.assertEqual(parse_duration(False), None) + self.assertEqual(parse_duration('invalid'), None) self.assertEqual(parse_duration('1'), 1) self.assertEqual(parse_duration('1337:12'), 80232) self.assertEqual(parse_duration('9:12:43'), 33163) @@ -220,6 +233,9 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('0s'), 0) self.assertEqual(parse_duration('01:02:03.05'), 3723.05) self.assertEqual(parse_duration('T30M38S'), 1838) + self.assertEqual(parse_duration('5 s'), 5) + self.assertEqual(parse_duration('3 min'), 180) + self.assertEqual(parse_duration('2.5 hours'), 9000) def test_fix_xml_ampersands(self): self.assertEqual( @@ -376,6 +392,30 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_filesize('2 MiB'), 2097152) self.assertEqual(parse_filesize('5 GB'), 5000000000) self.assertEqual(parse_filesize('1.2Tb'), 1200000000000) + self.assertEqual(parse_filesize('1,24 KB'), 1240) + + def test_version_tuple(self): + self.assertEqual(version_tuple('1'), (1,)) + self.assertEqual(version_tuple('10.23.344'), (10, 23, 344)) + self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style + + def test_detect_exe_version(self): + self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1 +built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4) +configuration: --prefix=/usr --extra-'''), '1.2.1') + self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685 +built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685') + self.assertEqual(detect_exe_version('''X server found. dri2 connection failed! +Trying to open render node... +Success at /dev/dri/renderD128. +ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4') + + def test_age_restricted(self): + self.assertFalse(age_restricted(None, 10)) # unrestricted content + self.assertFalse(age_restricted(1, None)) # unrestricted policy + self.assertFalse(age_restricted(8, 10)) + self.assertTrue(age_restricted(18, 14)) + self.assertFalse(age_restricted(18, 18)) if __name__ == '__main__': unittest.main() diff --git a/test/test_write_info_json.py b/test/test_write_info_json.py deleted file mode 100644 index 0396ef2..0000000 --- a/test/test_write_info_json.py +++ /dev/null @@ -1,76 +0,0 @@ -#!/usr/bin/env python -# coding: utf-8 -from __future__ import unicode_literals - -# Allow direct execution -import os -import sys -import unittest -sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) - -from test.helper import get_params - - -import io -import json - -import youtube_dl.YoutubeDL -import youtube_dl.extractor - - -class YoutubeDL(youtube_dl.YoutubeDL): - def __init__(self, *args, **kwargs): - super(YoutubeDL, self).__init__(*args, **kwargs) - self.to_stderr = self.to_screen - -params = get_params({ - 'writeinfojson': True, - 'skip_download': True, - 'writedescription': True, -}) - - -TEST_ID = 'BaW_jenozKc' -INFO_JSON_FILE = TEST_ID + '.info.json' -DESCRIPTION_FILE = TEST_ID + '.mp4.description' -EXPECTED_DESCRIPTION = '''test chars: "'/\ä↭𝕐 -test URL: https://github.com/rg3/youtube-dl/issues/1892 - -This is a test video for youtube-dl. - -For more information, contact phihag@phihag.de .''' - - -class TestInfoJSON(unittest.TestCase): - def setUp(self): - # Clear old files - self.tearDown() - - def test_info_json(self): - ie = youtube_dl.extractor.YoutubeIE() - ydl = YoutubeDL(params) - ydl.add_info_extractor(ie) - ydl.download([TEST_ID]) - self.assertTrue(os.path.exists(INFO_JSON_FILE)) - with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf: - jd = json.load(jsonf) - self.assertEqual(jd['upload_date'], '20121002') - self.assertEqual(jd['description'], EXPECTED_DESCRIPTION) - self.assertEqual(jd['id'], TEST_ID) - self.assertEqual(jd['extractor'], 'youtube') - self.assertEqual(jd['title'], '''youtube-dl test video "'/\ä↭𝕐''') - self.assertEqual(jd['uploader'], 'Philipp Hagemeister') - - self.assertTrue(os.path.exists(DESCRIPTION_FILE)) - with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf: - descr = descf.read() - self.assertEqual(descr, EXPECTED_DESCRIPTION) - - def tearDown(self): - if os.path.exists(INFO_JSON_FILE): - os.remove(INFO_JSON_FILE) - if os.path.exists(DESCRIPTION_FILE): - os.remove(DESCRIPTION_FILE) - -if __name__ == '__main__': - unittest.main() Binary files differdiff --git a/youtube-dl.1 b/youtube-dl.1 index 08e2ae3..cb69dee 100644 --- a/youtube-dl.1 +++ b/youtube-dl.1 @@ -4,7 +4,7 @@ youtube\-dl \- download videos from youtube.com or other video platforms .SH SYNOPSIS .PP -\f[B]youtube\-dl\f[] OPTIONS (#options) URL [URL...] +\f[B]youtube\-dl\f[] [OPTIONS] URL [URL...] .SH DESCRIPTION .PP \f[B]youtube\-dl\f[] is a small command\-line program to download videos @@ -33,10 +33,6 @@ redistribute it or use it however you like. \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ they\ would\ handle \-\-extractor\-descriptions\ \ \ \ \ \ \ \ \ Output\ descriptions\ of\ all\ supported \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ extractors -\-\-proxy\ URL\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Use\ the\ specified\ HTTP/HTTPS\ proxy.\ Pass\ in -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ an\ empty\ string\ (\-\-proxy\ "")\ for\ direct -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ connection -\-\-socket\-timeout\ None\ \ \ \ \ \ \ \ \ \ \ \ Time\ to\ wait\ before\ giving\ up,\ in\ seconds \-\-default\-search\ PREFIX\ \ \ \ \ \ \ \ \ \ Use\ this\ prefix\ for\ unqualified\ URLs.\ For \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ example\ "gvsearch2:"\ downloads\ two\ videos \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ from\ google\ videos\ for\ \ youtube\-dl\ "large @@ -48,14 +44,30 @@ redistribute it or use it however you like. \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ this\ is\ not\ possible\ instead\ of\ searching. \-\-ignore\-config\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Do\ not\ read\ configuration\ files.\ When\ given \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ in\ the\ global\ configuration\ file\ /etc -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ /youtube\-dl.conf:\ do\ not\ read\ the\ user -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ configuration\ in\ ~/.config/youtube\-dl.conf -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (%APPDATA%/youtube\-dl/config.txt\ on -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Windows) +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ /youtube\-dl.conf:\ Do\ not\ read\ the\ user +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ configuration\ in\ ~/.config/youtube\- +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ dl/config\ (%APPDATA%/youtube\-dl/config.txt +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ on\ Windows) \-\-flat\-playlist\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Do\ not\ extract\ the\ videos\ of\ a\ playlist, \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ only\ list\ them. \f[] .fi +.SS Network Options: +.IP +.nf +\f[C] +\-\-proxy\ URL\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Use\ the\ specified\ HTTP/HTTPS\ proxy.\ Pass\ in +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ an\ empty\ string\ (\-\-proxy\ "")\ for\ direct +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ connection +\-\-socket\-timeout\ SECONDS\ \ \ \ \ \ \ \ \ Time\ to\ wait\ before\ giving\ up,\ in\ seconds +\-\-source\-address\ IP\ \ \ \ \ \ \ \ \ \ \ \ \ \ Client\-side\ IP\ address\ to\ bind\ to +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (experimental) +\-4,\ \-\-force\-ipv4\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Make\ all\ connections\ via\ IPv4 +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (experimental) +\-6,\ \-\-force\-ipv6\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Make\ all\ connections\ via\ IPv6 +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (experimental) +\f[] +.fi .SS Video Selection: .IP .nf @@ -104,6 +116,7 @@ redistribute it or use it however you like. \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ size.\ By\ default,\ the\ buffer\ size\ is \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ automatically\ resized\ from\ an\ initial\ value \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ of\ SIZE. +\-\-playlist\-reverse\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ playlist\ videos\ in\ reverse\ order \f[] .fi .SS Filesystem Options: @@ -113,7 +126,6 @@ redistribute it or use it however you like. \-a,\ \-\-batch\-file\ FILE\ \ \ \ \ \ \ \ \ \ \ \ file\ containing\ URLs\ to\ download\ (\[aq]\-\[aq]\ for \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ stdin) \-\-id\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ only\ video\ ID\ in\ file\ name -\-A,\ \-\-auto\-number\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ number\ downloaded\ files\ starting\ from\ 00000 \-o,\ \-\-output\ TEMPLATE\ \ \ \ \ \ \ \ \ \ \ \ output\ filename\ template.\ Use\ %(title)s\ to \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ get\ the\ title,\ %(uploader)s\ for\ the \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ uploader\ name,\ %(uploader_id)s\ for\ the @@ -147,6 +159,9 @@ redistribute it or use it however you like. \-\-restrict\-filenames\ \ \ \ \ \ \ \ \ \ \ \ \ Restrict\ filenames\ to\ only\ ASCII \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ characters,\ and\ avoid\ "&"\ and\ spaces\ in \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ filenames +\-A,\ \-\-auto\-number\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ [deprecated;\ use\ \ \-o +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ "%(autonumber)s\-%(title)s.%(ext)s"\ ]\ number +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ downloaded\ files\ starting\ from\ 00000 \-t,\ \-\-title\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ [deprecated]\ use\ title\ in\ file\ name \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (default) \-l,\ \-\-literal\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ [deprecated]\ alias\ of\ \-\-title @@ -205,6 +220,8 @@ redistribute it or use it however you like. \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ for\ each\ command\-line\ argument.\ If\ the\ URL \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ refers\ to\ a\ playlist,\ dump\ the\ whole \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ playlist\ information\ in\ a\ single\ line. +\-\-print\-json\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Be\ quiet\ and\ print\ the\ video\ information\ as +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ JSON\ (video\ is\ still\ being\ downloaded). \-\-newline\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ output\ progress\ bar\ as\ new\ lines \-\-no\-progress\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ print\ progress\ bar \-\-console\-title\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ display\ progress\ in\ console\ titlebar @@ -215,6 +232,10 @@ redistribute it or use it however you like. \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ files\ in\ the\ current\ directory\ to\ debug \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ problems \-\-print\-traffic\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Display\ sent\ and\ read\ HTTP\ traffic +\-C,\ \-\-call\-home\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Contact\ the\ youtube\-dl\ server\ for +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ debugging. +\-\-no\-call\-home\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Do\ NOT\ contact\ the\ youtube\-dl\ server\ for +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ debugging. \f[] .fi .SS Workarounds: @@ -242,14 +263,15 @@ redistribute it or use it however you like. .nf \f[C] \-f,\ \-\-format\ FORMAT\ \ \ \ \ \ \ \ \ \ \ \ \ \ video\ format\ code,\ specify\ the\ order\ of -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ preference\ using\ slashes:\ \-f\ 22/17/18\ .\ \ \-f -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ mp4\ ,\ \-f\ m4a\ and\ \ \-f\ flv\ \ are\ also -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ supported.\ You\ can\ also\ use\ the\ special -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ names\ "best",\ "bestvideo",\ "bestaudio", -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ "worst",\ "worstvideo"\ and\ "worstaudio".\ By -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ default,\ youtube\-dl\ will\ pick\ the\ best -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ quality.\ Use\ commas\ to\ download\ multiple -\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ audio\ formats,\ such\ as\ \-f +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ preference\ using\ slashes,\ as\ in\ \-f\ 22/17/18 +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ .\ \ Instead\ of\ format\ codes,\ you\ can\ select +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ by\ extension\ for\ the\ extensions\ aac,\ m4a, +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ mp3,\ mp4,\ ogg,\ wav,\ webm.\ You\ can\ also\ use +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ the\ special\ names\ "best",\ "bestvideo", +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ "bestaudio",\ "worst".\ \ By\ default,\ youtube\- +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ dl\ will\ pick\ the\ best\ quality.\ Use\ commas +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ to\ download\ multiple\ audio\ formats,\ such\ as +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \-f \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 136/137/mp4/bestvideo,140/m4a/bestaudio. \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ You\ can\ merge\ the\ video\ and\ audio\ of\ two \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ formats\ into\ a\ single\ file\ using\ \-f\ <video\- @@ -263,6 +285,10 @@ redistribute it or use it however you like. \-F,\ \-\-list\-formats\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ list\ all\ available\ formats \-\-youtube\-skip\-dash\-manifest\ \ \ \ \ Do\ not\ download\ the\ DASH\ manifest\ on \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ YouTube\ videos +\-\-merge\-output\-format\ FORMAT\ \ \ \ \ If\ a\ merge\ is\ required\ (e.g. +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ bestvideo+bestaudio),\ output\ to\ given +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ container\ format.\ One\ of\ mkv,\ mp4,\ ogg, +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ webm,\ flv.Ignored\ if\ no\ merge\ is\ required \f[] .fi .SS Subtitle Options: @@ -321,6 +347,11 @@ redistribute it or use it however you like. \-\-add\-metadata\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ metadata\ to\ the\ video\ file \-\-xattrs\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ metadata\ to\ the\ video\ file\[aq]s\ xattrs \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (using\ dublin\ core\ and\ xdg\ standards) +\-\-fixup\ POLICY\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (experimental)\ Automatically\ correct\ known +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ faults\ of\ the\ file.\ One\ of\ never\ (do +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ nothing),\ warn\ (only\ emit\ a\ warning), +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ detect_or_warn(check\ whether\ we\ can\ do +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ anything\ about\ it,\ warn\ otherwise \-\-prefer\-avconv\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ avconv\ over\ ffmpeg\ for\ running\ the \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ postprocessors\ (default) \-\-prefer\-ffmpeg\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ ffmpeg\ over\ avconv\ for\ running\ the @@ -339,7 +370,7 @@ and not copy the mtime) into \f[C]/etc/youtube\-dl.conf\f[] and/or \f[C]~/.config/youtube\-dl/config\f[]. On Windows, the configuration file locations are \f[C]%APPDATA%\\youtube\-dl\\config.txt\f[] and -\f[C]C:\\Users\\<Yourname>\\youtube\-dl.conf\f[]. +\f[C]C:\\Users\\<user\ name>\\youtube\-dl.conf\f[]. .SH OUTPUT TEMPLATE .PP The \f[C]\-o\f[] option allows users to indicate a template for the @@ -521,14 +552,33 @@ youtube URL, solving the CAPTCHA, and restart youtube\-dl. .PP Once the video is fully downloaded, use any video player, such as vlc (http://www.videolan.org) or mplayer (http://www.mplayerhq.hu/). -.SS The links provided by youtube\-dl \-g are not working anymore +.SS I extracted a video URL with \-g, but it does not play on another +machine / in my webbrowser. .PP -The URLs youtube\-dl outputs require the downloader to have the correct -cookies. +It depends a lot on the service. +In many cases, requests for the video (to download/play it) must come +from the same IP address and with the same cookies. Use the \f[C]\-\-cookies\f[] option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use \f[C]\-\-dump\-user\-agent\f[] to see the one in use by youtube\-dl. +.PP +It may be beneficial to use IPv6; in some cases, the restrictions are +only applied to IPv4. +Some services (sometimes only for a subset of videos) do not restrict +the video URL by IP address, cookie, or user\-agent, but these are the +exception rather than the rule. +.PP +Please bear in mind that some URL protocols are \f[B]not\f[] supported +by browsers out of the box, including RTMP. +If you are using \-g, your own downloader must support these as well. +.PP +If you want to play the video on a machine that is not running +youtube\-dl, you can relay the video content from the machine that runs +youtube\-dl. +You can use \f[C]\-o\ \-\f[] to let youtube\-dl stream a video to +stdout, or simply allow the player to download the files written by +youtube\-dl in turn. .SS ERROR: no fmt_url_map or conn information found in video info .PP youtube has switched to a new video info format in July 2011 which is @@ -565,6 +615,51 @@ To recompile the executable, run \f[C]make\ youtube\-dl\f[]. To run the exe you need to install first the Microsoft Visual C++ 2008 Redistributable Package (http://www.microsoft.com/en-us/download/details.aspx?id=29). +.SS On Windows, how should I set up ffmpeg and youtube\-dl? Where should +I put the exe files? +.PP +If you put youtube\-dl and ffmpeg in the same directory that you\[aq]re +running the command from, it will work, but that\[aq]s rather +cumbersome. +.PP +To make a different directory work \- either for ffmpeg, or for +youtube\-dl, or for both \- simply create the directory (say, +\f[C]C:\\bin\f[], or \f[C]C:\\Users\\<User\ name>\\bin\f[]), put all the +executables directly in there, and then set your PATH environment +variable (https://www.java.com/en/download/help/path.xml) to include +that directory. +.PP +From then on, after restarting your shell, you will be able to access +both youtube\-dl and ffmpeg (and youtube\-dl will be able to find +ffmpeg) by simply typing \f[C]youtube\-dl\f[] or \f[C]ffmpeg\f[], no +matter what directory you\[aq]re in. +.SS How can I detect whether a given URL is supported by youtube\-dl? +.PP +For one, have a look at the list of supported +sites (docs/supportedsites). +Note that it can sometimes happen that the site changes its URL scheme +(say, from http://example.com/v/1234567 to http://example.com/v/1234567 +) and youtube\-dl reports an URL of a service in that list as +unsupported. +In that case, simply report a bug. +.PP +It is \f[I]not\f[] possible to detect whether a URL is supported or not. +That\[aq]s because youtube\-dl contains a generic extractor which +matches \f[B]all\f[] URLs. +You may be tempted to disable, exclude, or remove the generic extractor, +but the generic extractor not only allows users to extract videos from +lots of websites that embed a video from another service, but may also +be used to extract video from a service that it\[aq]s hosting itself. +Therefore, we neither recommend nor support disabling, excluding, or +removing the generic extractor. +.PP +If you want to find out whether a given URL is supported, simply call +youtube\-dl with it. +If you get no videos back, chances are the URL is either not referring +to a video or unsupported. +You can find out which by examining the output (if you run youtube\-dl +on the console) or catching an \f[C]UnsupportedError\f[] exception if +you run it from a Python program. .SH DEVELOPER INSTRUCTIONS .PP Most users do not need to build youtube\-dl and can download the @@ -733,6 +828,46 @@ For a list of what can be done, have a look at youtube_dl/YoutubeDL.py (https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube\-dl\[aq]s output, set a \f[C]logger\f[] object. +.PP +Here\[aq]s a more complete example of a program that outputs only errors +(and a short message after the download is finished), and +downloads/converts the video to an mp3 file: +.IP +.nf +\f[C] +import\ youtube_dl + + +class\ MyLogger(object): +\ \ \ \ def\ debug(self,\ msg): +\ \ \ \ \ \ \ \ pass + +\ \ \ \ def\ warning(self,\ msg): +\ \ \ \ \ \ \ \ pass + +\ \ \ \ def\ error(self,\ msg): +\ \ \ \ \ \ \ \ print(msg) + + +def\ my_hook(d): +\ \ \ \ if\ d[\[aq]status\[aq]]\ ==\ \[aq]finished\[aq]: +\ \ \ \ \ \ \ \ print(\[aq]Done\ downloading,\ now\ converting\ ...\[aq]) + + +ydl_opts\ =\ { +\ \ \ \ \[aq]format\[aq]:\ \[aq]bestaudio/best\[aq], +\ \ \ \ \[aq]postprocessors\[aq]:\ [{ +\ \ \ \ \ \ \ \ \[aq]key\[aq]:\ \[aq]FFmpegExtractAudio\[aq], +\ \ \ \ \ \ \ \ \[aq]preferredcodec\[aq]:\ \[aq]mp3\[aq], +\ \ \ \ \ \ \ \ \[aq]preferredquality\[aq]:\ \[aq]192\[aq], +\ \ \ \ }], +\ \ \ \ \[aq]logger\[aq]:\ MyLogger(), +\ \ \ \ \[aq]progress_hooks\[aq]:\ [my_hook], +} +with\ youtube_dl.YoutubeDL(ydl_opts)\ as\ ydl: +\ \ \ \ ydl.download([\[aq]http://www.youtube.com/watch?v=BaW_jenozKc\[aq]]) +\f[] +.fi .SH BUGS .PP Bugs and suggestions should be reported at: @@ -740,17 +875,17 @@ Bugs and suggestions should be reported at: Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. +For discussions, join us in the irc channel #youtube\-dl on freenode. +.PP +\f[B]Please include the full output of youtube\-dl when run with +\f[C]\-v\f[]\f[]. .PP -Please include the full output of the command when run with -\f[C]\-\-verbose\f[]. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. .PP -For discussions, join us in the irc channel #youtube\-dl on freenode. -.PP -When you submit a request, please re\-read it once to avoid a couple of +Please re\-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist): .SS Is the description of the issue itself sufficient? .PP diff --git a/youtube-dl.bash-completion b/youtube-dl.bash-completion index 9ee1b7a..0bad8b6 100644 --- a/youtube-dl.bash-completion +++ b/youtube-dl.bash-completion @@ -4,7 +4,7 @@ __youtube_dl() COMPREPLY=() cur="${COMP_WORDS[COMP_CWORD]}" prev="${COMP_WORDS[COMP_CWORD-1]}" - opts="--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --proxy --socket-timeout --default-search --ignore-config --flat-playlist --playlist-start --playlist-end --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --batch-file --id --auto-number --output --autonumber-size --restrict-filenames --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --write-thumbnail --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --prefer-avconv --prefer-ffmpeg --exec" + opts="--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --playlist-start --playlist-end --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --write-thumbnail --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --fixup --prefer-avconv --prefer-ffmpeg --exec" keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory" fileopts="-a|--batch-file|--download-archive|--cookies|--load-info" diropts="--cache-dir" diff --git a/youtube-dl.fish b/youtube-dl.fish index 923fd60..76857d4 100644 --- a/youtube-dl.fish +++ b/youtube-dl.fish @@ -7,11 +7,14 @@ complete --command youtube-dl --long-option abort-on-error --description 'Abort complete --command youtube-dl --long-option dump-user-agent --description 'display the current browser identification' complete --command youtube-dl --long-option list-extractors --description 'List all supported extractors and the URLs they would handle' complete --command youtube-dl --long-option extractor-descriptions --description 'Output descriptions of all supported extractors' -complete --command youtube-dl --long-option proxy --description 'Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection' -complete --command youtube-dl --long-option socket-timeout --description 'Time to wait before giving up, in seconds' complete --command youtube-dl --long-option default-search --description 'Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.' -complete --command youtube-dl --long-option ignore-config --description 'Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)' +complete --command youtube-dl --long-option ignore-config --description 'Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)' complete --command youtube-dl --long-option flat-playlist --description 'Do not extract the videos of a playlist, only list them.' +complete --command youtube-dl --long-option proxy --description 'Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection' +complete --command youtube-dl --long-option socket-timeout --description 'Time to wait before giving up, in seconds' +complete --command youtube-dl --long-option source-address --description 'Client-side IP address to bind to (experimental)' +complete --command youtube-dl --long-option force-ipv4 --short-option 4 --description 'Make all connections via IPv4 (experimental)' +complete --command youtube-dl --long-option force-ipv6 --short-option 6 --description 'Make all connections via IPv6 (experimental)' complete --command youtube-dl --long-option playlist-start --description 'playlist video to start at (default is %default)' complete --command youtube-dl --long-option playlist-end --description 'playlist video to end at (default is last)' complete --command youtube-dl --long-option match-title --description 'download only matching titles (regex or caseless sub-string)' @@ -33,12 +36,13 @@ complete --command youtube-dl --long-option retries --short-option R --descripti complete --command youtube-dl --long-option buffer-size --description 'size of download buffer (e.g. 1024 or 16K) (default is %default)' complete --command youtube-dl --long-option no-resize-buffer --description 'do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.' complete --command youtube-dl --long-option test +complete --command youtube-dl --long-option playlist-reverse --description 'Download playlist videos in reverse order' complete --command youtube-dl --long-option batch-file --short-option a --description 'file containing URLs to download ('"'"'-'"'"' for stdin)' --require-parameter complete --command youtube-dl --long-option id --description 'use only video ID in file name' -complete --command youtube-dl --long-option auto-number --short-option A --description 'number downloaded files starting from 00000' complete --command youtube-dl --long-option output --short-option o --description 'output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube'"'"'s itags: "137"), %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id, %(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in, %(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format. %(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o '"'"'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s'"'"' .' complete --command youtube-dl --long-option autonumber-size --description 'Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given' complete --command youtube-dl --long-option restrict-filenames --description 'Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames' +complete --command youtube-dl --long-option auto-number --short-option A --description '[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000' complete --command youtube-dl --long-option title --short-option t --description '[deprecated] use title in file name (default)' complete --command youtube-dl --long-option literal --short-option l --description '[deprecated] alias of --title' complete --command youtube-dl --long-option no-overwrites --short-option w --description 'do not overwrite files' @@ -69,6 +73,7 @@ complete --command youtube-dl --long-option get-filename --description 'simulate complete --command youtube-dl --long-option get-format --description 'simulate, quiet but print output format' complete --command youtube-dl --long-option dump-json --short-option j --description 'simulate, quiet but print JSON information. See --output for a description of available keys.' complete --command youtube-dl --long-option dump-single-json --short-option J --description 'simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line.' +complete --command youtube-dl --long-option print-json --description 'Be quiet and print the video information as JSON (video is still being downloaded).' complete --command youtube-dl --long-option newline --description 'output progress bar as new lines' complete --command youtube-dl --long-option no-progress --description 'do not print progress bar' complete --command youtube-dl --long-option console-title --description 'display progress in console titlebar' @@ -77,6 +82,8 @@ complete --command youtube-dl --long-option dump-intermediate-pages --descriptio complete --command youtube-dl --long-option write-pages --description 'Write downloaded intermediary pages to files in the current directory to debug problems' complete --command youtube-dl --long-option youtube-print-sig-code complete --command youtube-dl --long-option print-traffic --description 'Display sent and read HTTP traffic' +complete --command youtube-dl --long-option call-home --short-option C --description 'Contact the youtube-dl server for debugging.' +complete --command youtube-dl --long-option no-call-home --description 'Do NOT contact the youtube-dl server for debugging.' complete --command youtube-dl --long-option encoding --description 'Force the specified encoding (experimental)' complete --command youtube-dl --long-option no-check-certificate --description 'Suppress HTTPS certificate validation.' complete --command youtube-dl --long-option prefer-insecure --description 'Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)' @@ -84,13 +91,14 @@ complete --command youtube-dl --long-option user-agent --description 'specify a complete --command youtube-dl --long-option referer --description 'specify a custom referer, use if the video access is restricted to one domain' complete --command youtube-dl --long-option add-header --description 'specify a custom HTTP header and its value, separated by a colon '"'"':'"'"'. You can use this option multiple times' complete --command youtube-dl --long-option bidi-workaround --description 'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH' -complete --command youtube-dl --long-option format --short-option f --description 'video format code, specify the order of preference using slashes: -f 22/17/18 . -f mp4 , -f m4a and -f flv are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality. Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f bestvideo+bestaudio.' +complete --command youtube-dl --long-option format --short-option f --description 'video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio", "worst". By default, youtube-dl will pick the best quality. Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f bestvideo+bestaudio.' complete --command youtube-dl --long-option all-formats --description 'download all available video formats' complete --command youtube-dl --long-option prefer-free-formats --description 'prefer free video formats unless a specific one is requested' complete --command youtube-dl --long-option max-quality --description 'highest quality format to download' complete --command youtube-dl --long-option list-formats --short-option F --description 'list all available formats' complete --command youtube-dl --long-option youtube-include-dash-manifest complete --command youtube-dl --long-option youtube-skip-dash-manifest --description 'Do not download the DASH manifest on YouTube videos' +complete --command youtube-dl --long-option merge-output-format --description 'If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no merge is required' complete --command youtube-dl --long-option write-sub --description 'write subtitle file' complete --command youtube-dl --long-option write-auto-sub --description 'write automatic subtitle file (youtube only)' complete --command youtube-dl --long-option all-subs --description 'downloads all the available subtitles of the video' @@ -112,6 +120,7 @@ complete --command youtube-dl --long-option embed-subs --description 'embed subt complete --command youtube-dl --long-option embed-thumbnail --description 'embed thumbnail in the audio as cover art' complete --command youtube-dl --long-option add-metadata --description 'write metadata to the video file' complete --command youtube-dl --long-option xattrs --description 'write metadata to the video file'"'"'s xattrs (using dublin core and xdg standards)' +complete --command youtube-dl --long-option fixup --description '(experimental) Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(check whether we can do anything about it, warn otherwise' complete --command youtube-dl --long-option prefer-avconv --description 'Prefer avconv over ffmpeg for running the postprocessors (default)' complete --command youtube-dl --long-option prefer-ffmpeg --description 'Prefer ffmpeg over avconv for running the postprocessors' complete --command youtube-dl --long-option exec --description 'Execute a command on the file after downloading, similar to find'"'"'s -exec syntax. Example: --exec '"'"'adb push {} /sdcard/Music/ && rm {}'"'"'' diff --git a/youtube-dl.zsh b/youtube-dl.zsh index af7a61a..b4cef18 100644 --- a/youtube-dl.zsh +++ b/youtube-dl.zsh @@ -19,7 +19,7 @@ __youtube_dl() { elif [[ ${prev} == "--recode-video" ]]; then _arguments '*: :(mp4 flv ogg webm mkv)' else - _arguments '*: :(--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --proxy --socket-timeout --default-search --ignore-config --flat-playlist --playlist-start --playlist-end --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --batch-file --id --auto-number --output --autonumber-size --restrict-filenames --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --write-thumbnail --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --prefer-avconv --prefer-ffmpeg --exec)' + _arguments '*: :(--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --playlist-start --playlist-end --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --write-thumbnail --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --fixup --prefer-avconv --prefer-ffmpeg --exec)' fi ;; esac diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 21c7c29..772fddd 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -7,6 +7,7 @@ import collections import datetime import errno import io +import itertools import json import locale import os @@ -26,6 +27,7 @@ from .compat import ( compat_cookiejar, compat_expanduser, compat_http_client, + compat_kwargs, compat_str, compat_urllib_error, compat_urllib_request, @@ -56,17 +58,24 @@ from .utils import ( takewhile_inclusive, UnavailableVideoError, url_basename, + version_tuple, write_json_file, write_string, YoutubeDLHandler, prepend_extension, args_to_str, + age_restricted, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractors from .downloader import get_suitable_downloader from .downloader.rtmp import rtmpdump_version -from .postprocessor import FFmpegMergerPP, FFmpegPostProcessor +from .postprocessor import ( + FFmpegFixupStretchedPP, + FFmpegMergerPP, + FFmpegPostProcessor, + get_postprocessor, +) from .version import __version__ @@ -115,7 +124,7 @@ class YoutubeDL(object): dump_single_json: Force printing the info_dict of the whole playlist (or video) as a single JSON line. simulate: Do not download the video files. - format: Video format code. + format: Video format code. See options.py for more information. format_limit: Highest quality format to try. outtmpl: Template for output names. restrictfilenames: Do not allow "&" and spaces in file names @@ -123,6 +132,7 @@ class YoutubeDL(object): nooverwrites: Prevent overwriting files. playliststart: Playlist item to start at. playlistend: Playlist item to end at. + playlistreverse: Download playlist items in reverse order. matchtitle: Download only matching titles. rejecttitle: Reject downloads for matching titles. logger: Log messages to a logging.Logger instance. @@ -174,6 +184,38 @@ class YoutubeDL(object): extract_flat: Do not resolve URLs, return the immediate result. Pass in 'in_playlist' to only show this behavior for playlist items. + postprocessors: A list of dictionaries, each with an entry + * key: The name of the postprocessor. See + youtube_dl/postprocessor/__init__.py for a list. + as well as any further keyword arguments for the + postprocessor. + progress_hooks: A list of functions that get called on download + progress, with a dictionary with the entries + * filename: The final filename + * status: One of "downloading" and "finished" + + The dict may also have some of the following entries: + + * downloaded_bytes: Bytes on disk + * total_bytes: Size of the whole file, None if unknown + * tmpfilename: The filename we're currently writing to + * eta: The estimated time in seconds, None if unknown + * speed: The download speed in bytes/second, None if + unknown + + Progress hooks are guaranteed to be called at least once + (with status "finished") if the download is successful. + merge_output_format: Extension to use when merging formats. + fixup: Automatically correct known faults of the file. + One of: + - "never": do nothing + - "warn": only emit a warning + - "detect_or_warn": check whether we can do anything + about it, warn otherwise + source_address: (Experimental) Client-side IP address to bind to. + call_home: Boolean, true iff we are allowed to contact the + youtube-dl servers for debugging. + The following parameters are not used by YoutubeDL itself, they are used by the FileDownloader: @@ -254,6 +296,16 @@ class YoutubeDL(object): self.print_debug_header() self.add_default_info_extractors() + for pp_def_raw in self.params.get('postprocessors', []): + pp_class = get_postprocessor(pp_def_raw['key']) + pp_def = dict(pp_def_raw) + del pp_def['key'] + pp = pp_class(self, **compat_kwargs(pp_def)) + self.add_post_processor(pp) + + for ph in self.params.get('progress_hooks', []): + self.add_progress_hook(ph) + def warn_if_short_id(self, argv): # short YouTube ID starting with dash? idxs = [ @@ -511,13 +563,8 @@ class YoutubeDL(object): max_views = self.params.get('max_views') if max_views is not None and view_count > max_views: return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) - age_limit = self.params.get('age_limit') - if age_limit is not None: - actual_age_limit = info_dict.get('age_limit') - if actual_age_limit is None: - actual_age_limit = 0 - if age_limit < actual_age_limit: - return 'Skipping "' + title + '" because it is age restricted' + if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')): + return 'Skipping "%s" because it is age restricted' % title if self.in_download_archive(info_dict): return '%s has already been recorded in archive' % video_title return None @@ -621,23 +668,15 @@ class YoutubeDL(object): ie_result['url'], ie_key=ie_result.get('ie_key'), extra_info=extra_info, download=False, process=False) - def make_result(embedded_info): - new_result = ie_result.copy() - for f in ('_type', 'url', 'ext', 'player_url', 'formats', - 'entries', 'ie_key', 'duration', - 'subtitles', 'annotations', 'format', - 'thumbnail', 'thumbnails'): - if f in new_result: - del new_result[f] - if f in embedded_info: - new_result[f] = embedded_info[f] - return new_result - new_result = make_result(info) + force_properties = dict( + (k, v) for k, v in ie_result.items() if v is not None) + for f in ('_type', 'url'): + if f in force_properties: + del force_properties[f] + new_result = info.copy() + new_result.update(force_properties) assert new_result.get('_type') != 'url_transparent' - if new_result.get('_type') == 'compat_list': - new_result['entries'] = [ - make_result(e) for e in new_result['entries']] return self.process_ie_result( new_result, download=download, extra_info=extra_info) @@ -654,24 +693,34 @@ class YoutubeDL(object): if playlistend == -1: playlistend = None - if isinstance(ie_result['entries'], list): - n_all_entries = len(ie_result['entries']) - entries = ie_result['entries'][playliststart:playlistend] + ie_entries = ie_result['entries'] + if isinstance(ie_entries, list): + n_all_entries = len(ie_entries) + entries = ie_entries[playliststart:playlistend] n_entries = len(entries) self.to_screen( "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % (ie_result['extractor'], playlist, n_all_entries, n_entries)) - else: - assert isinstance(ie_result['entries'], PagedList) - entries = ie_result['entries'].getslice( + elif isinstance(ie_entries, PagedList): + entries = ie_entries.getslice( playliststart, playlistend) n_entries = len(entries) self.to_screen( "[%s] playlist %s: Downloading %d videos" % (ie_result['extractor'], playlist, n_entries)) + else: # iterable + entries = list(itertools.islice( + ie_entries, playliststart, playlistend)) + n_entries = len(entries) + self.to_screen( + "[%s] playlist %s: Downloading %d videos" % + (ie_result['extractor'], playlist, n_entries)) + + if self.params.get('playlistreverse', False): + entries = entries[::-1] for i, entry in enumerate(entries, 1): - self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries)) + self.to_screen('[download] Downloading video %s of %s' % (i, n_entries)) extra = { 'n_entries': n_entries, 'playlist': playlist, @@ -749,7 +798,7 @@ class YoutubeDL(object): if video_formats: return video_formats[0] else: - extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a'] + extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav'] if format_spec in extensions: filter_f = lambda f: f['ext'] == format_spec else: @@ -787,6 +836,10 @@ class YoutubeDL(object): info_dict['display_id'] = info_dict['id'] if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: + # Working around negative timestamps in Windows + # (see http://bugs.python.org/issue1646728) + if info_dict['timestamp'] < 0 and os.name == 'nt': + info_dict['timestamp'] = 0 upload_date = datetime.datetime.utcfromtimestamp( info_dict['timestamp']) info_dict['upload_date'] = upload_date.strftime('%Y%m%d') @@ -868,10 +921,24 @@ class YoutubeDL(object): 'contain the video, try using ' '"-f %s+%s"' % (format_2, format_1)) return + output_ext = ( + formats_info[0]['ext'] + if self.params.get('merge_output_format') is None + else self.params['merge_output_format']) selected_format = { 'requested_formats': formats_info, 'format': rf, 'ext': formats_info[0]['ext'], + 'width': formats_info[0].get('width'), + 'height': formats_info[0].get('height'), + 'resolution': formats_info[0].get('resolution'), + 'fps': formats_info[0].get('fps'), + 'vcodec': formats_info[0].get('vcodec'), + 'vbr': formats_info[0].get('vbr'), + 'stretched_ratio': formats_info[0].get('stretched_ratio'), + 'acodec': formats_info[1].get('acodec'), + 'abr': formats_info[1].get('abr'), + 'ext': output_ext, } else: selected_format = None @@ -930,8 +997,12 @@ class YoutubeDL(object): if self.params.get('forceid', False): self.to_stdout(info_dict['id']) if self.params.get('forceurl', False): - # For RTMP URLs, also include the playpath - self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) + if info_dict.get('requested_formats') is not None: + for f in info_dict['requested_formats']: + self.to_stdout(f['url'] + f.get('play_path', '')) + else: + # For RTMP URLs, also include the playpath + self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: self.to_stdout(info_dict['thumbnail']) if self.params.get('forcedescription', False) and info_dict.get('description') is not None: @@ -967,13 +1038,13 @@ class YoutubeDL(object): descfn = filename + '.description' if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): self.to_screen('[info] Video description is already present') + elif info_dict.get('description') is None: + self.report_warning('There\'s no description to write.') else: try: self.to_screen('[info] Writing video description to: ' + descfn) with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: descfile.write(info_dict['description']) - except (KeyError, TypeError): - self.report_warning('There\'s no description to write.') except (OSError, IOError): self.report_error('Cannot write description file ' + descfn) return @@ -1050,58 +1121,75 @@ class YoutubeDL(object): (info_dict['thumbnail'], compat_str(err))) if not self.params.get('skip_download', False): - if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): - success = True - else: - try: - def dl(name, info): - fd = get_suitable_downloader(info)(self, self.params) - for ph in self._progress_hooks: - fd.add_progress_hook(ph) - if self.params.get('verbose'): - self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) - return fd.download(name, info) - if info_dict.get('requested_formats') is not None: - downloaded = [] - success = True - merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) - if not merger._executable: - postprocessors = [] - self.report_warning('You have requested multiple ' - 'formats but ffmpeg or avconv are not installed.' - ' The formats won\'t be merged') - else: - postprocessors = [merger] - for f in info_dict['requested_formats']: - new_info = dict(info_dict) - new_info.update(f) - fname = self.prepare_filename(new_info) - fname = prepend_extension(fname, 'f%s' % f['format_id']) - downloaded.append(fname) - partial_success = dl(fname, new_info) - success = success and partial_success - info_dict['__postprocessors'] = postprocessors - info_dict['__files_to_merge'] = downloaded + try: + def dl(name, info): + fd = get_suitable_downloader(info)(self, self.params) + for ph in self._progress_hooks: + fd.add_progress_hook(ph) + if self.params.get('verbose'): + self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) + return fd.download(name, info) + if info_dict.get('requested_formats') is not None: + downloaded = [] + success = True + merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) + if not merger._executable: + postprocessors = [] + self.report_warning('You have requested multiple ' + 'formats but ffmpeg or avconv are not installed.' + ' The formats won\'t be merged') else: - # Just a single file - success = dl(filename, info_dict) - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.report_error('unable to download video data: %s' % str(err)) - return - except (OSError, IOError) as err: - raise UnavailableVideoError(err) - except (ContentTooShortError, ) as err: - self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) - return + postprocessors = [merger] + for f in info_dict['requested_formats']: + new_info = dict(info_dict) + new_info.update(f) + fname = self.prepare_filename(new_info) + fname = prepend_extension(fname, 'f%s' % f['format_id']) + downloaded.append(fname) + partial_success = dl(fname, new_info) + success = success and partial_success + info_dict['__postprocessors'] = postprocessors + info_dict['__files_to_merge'] = downloaded + else: + # Just a single file + success = dl(filename, info_dict) + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.report_error('unable to download video data: %s' % str(err)) + return + except (OSError, IOError) as err: + raise UnavailableVideoError(err) + except (ContentTooShortError, ) as err: + self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return if success: + # Fixup content + stretched_ratio = info_dict.get('stretched_ratio') + if stretched_ratio is not None and stretched_ratio != 1: + fixup_policy = self.params.get('fixup') + if fixup_policy is None: + fixup_policy = 'detect_or_warn' + if fixup_policy == 'warn': + self.report_warning('%s: Non-uniform pixel ratio (%s)' % ( + info_dict['id'], stretched_ratio)) + elif fixup_policy == 'detect_or_warn': + stretched_pp = FFmpegFixupStretchedPP(self) + if stretched_pp.available: + info_dict.setdefault('__postprocessors', []) + info_dict['__postprocessors'].append(stretched_pp) + else: + self.report_warning( + '%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % ( + info_dict['id'], stretched_ratio)) + else: + assert fixup_policy == 'ignore' + try: self.post_process(filename, info_dict) except (PostProcessingError) as err: self.report_error('postprocessing: %s' % str(err)) return - - self.record_download_archive(info_dict) + self.record_download_archive(info_dict) def download(self, url_list): """Download a given list of URLs.""" @@ -1144,14 +1232,15 @@ class YoutubeDL(object): """Run all the postprocessors on the given file.""" info = dict(ie_info) info['filepath'] = filename - keep_video = None pps_chain = [] if ie_info.get('__postprocessors') is not None: pps_chain.extend(ie_info['__postprocessors']) pps_chain.extend(self._pps) for pp in pps_chain: + keep_video = None + old_filename = info['filepath'] try: - keep_video_wish, new_info = pp.run(info) + keep_video_wish, info = pp.run(info) if keep_video_wish is not None: if keep_video_wish: keep_video = keep_video_wish @@ -1160,12 +1249,12 @@ class YoutubeDL(object): keep_video = keep_video_wish except PostProcessingError as e: self.report_error(e.msg) - if keep_video is False and not self.params.get('keepvideo', False): - try: - self.to_screen('Deleting original file %s (pass -k to keep)' % filename) - os.remove(encodeFilename(filename)) - except (IOError, OSError): - self.report_warning('Unable to remove downloaded video file') + if keep_video is False and not self.params.get('keepvideo', False): + try: + self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename) + os.remove(encodeFilename(old_filename)) + except (IOError, OSError): + self.report_warning('Unable to remove downloaded video file') def _make_archive_id(self, info_dict): # Future-proof against any change in case @@ -1285,7 +1374,9 @@ class YoutubeDL(object): formats = info_dict.get('formats', [info_dict]) idlen = max(len('format code'), max(len(f['format_id']) for f in formats)) - formats_s = [line(f, idlen) for f in formats] + formats_s = [ + line(f, idlen) for f in formats + if f.get('preference') is None or f['preference'] >= -1000] if len(formats) > 1: formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)' formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)' @@ -1374,6 +1465,17 @@ class YoutubeDL(object): proxy_map.update(handler.proxies) self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') + if self.params.get('call_home', False): + ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8') + self._write_string('[debug] Public IP address: %s\n' % ipaddr) + latest_version = self.urlopen( + 'https://yt-dl.org/latest/version').read().decode('utf-8') + if version_tuple(latest_version) > version_tuple(__version__): + self.report_warning( + 'You are using an outdated version (newest version: %s)! ' + 'See https://yt-dl.org/update if you need help updating.' % + latest_version) + def _setup_opener(self): timeout_val = self.params.get('socket_timeout') self._socket_timeout = 600 if timeout_val is None else float(timeout_val) @@ -1404,9 +1506,8 @@ class YoutubeDL(object): proxy_handler = compat_urllib_request.ProxyHandler(proxies) debuglevel = 1 if self.params.get('debug_printtraffic') else 0 - https_handler = make_HTTPS_handler( - self.params.get('nocheckcertificate', False), debuglevel=debuglevel) - ydlh = YoutubeDLHandler(debuglevel=debuglevel) + https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) + ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) opener = compat_urllib_request.build_opener( https_handler, proxy_handler, cookie_processor, ydlh) # Delete the default user-agent header, which would otherwise apply in diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 77b3384..ddf6260 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -38,18 +38,8 @@ from .update import update_self from .downloader import ( FileDownloader, ) -from .extractor import gen_extractors +from .extractor import gen_extractors, list_extractors from .YoutubeDL import YoutubeDL -from .postprocessor import ( - AtomicParsleyPP, - FFmpegAudioFixPP, - FFmpegMetadataPP, - FFmpegVideoConvertor, - FFmpegExtractAudioPP, - FFmpegEmbedSubtitlePP, - XAttrMetadataPP, - ExecAfterDownloadPP, -) def _real_main(argv=None): @@ -105,24 +95,22 @@ def _real_main(argv=None): _enc = preferredencoding() all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls] - extractors = gen_extractors() - if opts.list_extractors: - for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): + for ie in list_extractors(opts.age_limit): compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) matchedUrls = [url for url in all_urls if ie.suitable(url)] for mu in matchedUrls: compat_print(' ' + mu) sys.exit(0) if opts.list_extractor_descriptions: - for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): + for ie in list_extractors(opts.age_limit): if not ie._WORKING: continue desc = getattr(ie, 'IE_DESC', ie.IE_NAME) if desc is False: continue if hasattr(ie, 'SEARCH_KEY'): - _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny') + _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow') _COUNTS = ('', '5', '10', 'all') desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) compat_print(desc) @@ -178,6 +166,7 @@ def _real_main(argv=None): if opts.recodevideo is not None: if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: parser.error('invalid video recode format specified') + if opts.date is not None: date = DateRange.day(opts.date) else: @@ -209,16 +198,54 @@ def _real_main(argv=None): ' file! Use "{0}.%(ext)s" instead of "{0}" as the output' ' template'.format(outtmpl)) - any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json + any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json + any_printing = opts.print_json download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive + # PostProcessors + postprocessors = [] + # Add the metadata pp first, the other pps will copy it + if opts.addmetadata: + postprocessors.append({'key': 'FFmpegMetadata'}) + if opts.extractaudio: + postprocessors.append({ + 'key': 'FFmpegExtractAudio', + 'preferredcodec': opts.audioformat, + 'preferredquality': opts.audioquality, + 'nopostoverwrites': opts.nopostoverwrites, + }) + if opts.recodevideo: + postprocessors.append({ + 'key': 'FFmpegVideoConvertor', + 'preferedformat': opts.recodevideo, + }) + if opts.embedsubtitles: + postprocessors.append({ + 'key': 'FFmpegEmbedSubtitle', + 'subtitlesformat': opts.subtitlesformat, + }) + if opts.xattrs: + postprocessors.append({'key': 'XAttrMetadata'}) + if opts.embedthumbnail: + if not opts.addmetadata: + postprocessors.append({'key': 'FFmpegAudioFix'}) + postprocessors.append({'key': 'AtomicParsley'}) + # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. + # So if the user is able to remove the file before your postprocessor runs it might cause a few problems. + if opts.exec_cmd: + postprocessors.append({ + 'key': 'ExecAfterDownload', + 'verboseOutput': opts.verbose, + 'exec_cmd': opts.exec_cmd, + }) + ydl_opts = { 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, 'twofactor': opts.twofactor, 'videopassword': opts.videopassword, - 'quiet': (opts.quiet or any_printing), + 'quiet': (opts.quiet or any_getting or any_printing), 'no_warnings': opts.no_warnings, 'forceurl': opts.geturl, 'forcetitle': opts.gettitle, @@ -228,9 +255,9 @@ def _real_main(argv=None): 'forceduration': opts.getduration, 'forcefilename': opts.getfilename, 'forceformat': opts.getformat, - 'forcejson': opts.dumpjson, + 'forcejson': opts.dumpjson or opts.print_json, 'dump_single_json': opts.dump_single_json, - 'simulate': opts.simulate or any_printing, + 'simulate': opts.simulate or any_getting, 'skip_download': opts.skip_download, 'format': opts.format, 'format_limit': opts.format_limit, @@ -249,6 +276,7 @@ def _real_main(argv=None): 'progress_with_newline': opts.progress_with_newline, 'playliststart': opts.playliststart, 'playlistend': opts.playlistend, + 'playlistreverse': opts.playlist_reverse, 'noplaylist': opts.noplaylist, 'logtostderr': opts.outtmpl == '-', 'consoletitle': opts.consoletitle, @@ -296,32 +324,14 @@ def _real_main(argv=None): 'encoding': opts.encoding, 'exec_cmd': opts.exec_cmd, 'extract_flat': opts.extract_flat, + 'merge_output_format': opts.merge_output_format, + 'postprocessors': postprocessors, + 'fixup': opts.fixup, + 'source_address': opts.source_address, + 'call_home': opts.call_home, } with YoutubeDL(ydl_opts) as ydl: - # PostProcessors - # Add the metadata pp first, the other pps will copy it - if opts.addmetadata: - ydl.add_post_processor(FFmpegMetadataPP()) - if opts.extractaudio: - ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites)) - if opts.recodevideo: - ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo)) - if opts.embedsubtitles: - ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat)) - if opts.xattrs: - ydl.add_post_processor(XAttrMetadataPP()) - if opts.embedthumbnail: - if not opts.addmetadata: - ydl.add_post_processor(FFmpegAudioFixPP()) - ydl.add_post_processor(AtomicParsleyPP()) - - # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. - # So if the user is able to remove the file before your postprocessor runs it might cause a few problems. - if opts.exec_cmd: - ydl.add_post_processor(ExecAfterDownloadPP( - verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd)) - # Update version if opts.update_self: update_self(ydl.to_screen, opts.verbose) @@ -359,3 +369,5 @@ def main(argv=None): sys.exit('ERROR: fixed output name but more than one file to download') except KeyboardInterrupt: sys.exit('\nERROR: Interrupted by user') + +__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors'] diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 2759668..4453b34 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -4,6 +4,7 @@ import getpass import optparse import os import re +import socket import subprocess import sys @@ -247,7 +248,7 @@ else: userhome = compat_getenv('HOME') elif 'USERPROFILE' in os.environ: userhome = compat_getenv('USERPROFILE') - elif not 'HOMEPATH' in os.environ: + elif 'HOMEPATH' not in os.environ: return path else: try: @@ -297,7 +298,9 @@ else: # Old 2.6 and 2.7 releases require kwargs to be bytes try: - (lambda x: x)(**{'x': 0}) + def _testfunc(x): + pass + _testfunc(**{'x': 0}) except TypeError: def compat_kwargs(kwargs): return dict((bytes(k), v) for k, v in kwargs.items()) @@ -305,6 +308,32 @@ else: compat_kwargs = lambda kwargs: kwargs +if sys.version_info < (2, 7): + def compat_socket_create_connection(address, timeout, source_address=None): + host, port = address + err = None + for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM): + af, socktype, proto, canonname, sa = res + sock = None + try: + sock = socket.socket(af, socktype, proto) + sock.settimeout(timeout) + if source_address: + sock.bind(source_address) + sock.connect(sa) + return sock + except socket.error as _: + err = _ + if sock is not None: + sock.close() + if err is not None: + raise err + else: + raise socket.error("getaddrinfo returns an empty list") +else: + compat_socket_create_connection = socket.create_connection + + # Fix https://github.com/rg3/youtube-dl/issues/4223 # See http://bugs.python.org/issue9161 for what is broken def workaround_optparse_bug9161(): @@ -340,6 +369,7 @@ __all__ = [ 'compat_ord', 'compat_parse_qs', 'compat_print', + 'compat_socket_create_connection', 'compat_str', 'compat_subprocess_get_DEVNULL', 'compat_urllib_error', diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index c0af50c..de6b931 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -5,8 +5,8 @@ import re import sys import time +from ..compat import compat_str from ..utils import ( - compat_str, encodeFilename, format_bytes, timeconvert, @@ -80,6 +80,8 @@ class FileDownloader(object): def calc_eta(start, now, total, current): if total is None: return None + if now is None: + now = time.time() dif = now - start if current == 0 or dif < 0.001: # One millisecond return None @@ -146,18 +148,19 @@ class FileDownloader(object): def report_error(self, *args, **kargs): self.ydl.report_error(*args, **kargs) - def slow_down(self, start_time, byte_counter): + def slow_down(self, start_time, now, byte_counter): """Sleep if the download speed is over the rate limit.""" rate_limit = self.params.get('ratelimit', None) if rate_limit is None or byte_counter == 0: return - now = time.time() + if now is None: + now = time.time() elapsed = now - start_time if elapsed <= 0.0: return speed = float(byte_counter) / elapsed if speed > rate_limit: - time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + time.sleep(max((byte_counter // rate_limit) - elapsed, 0)) def temp_name(self, filename): """Returns a temporary filename for the given filename.""" @@ -281,8 +284,19 @@ class FileDownloader(object): """Download to a filename using the info from info_dict Return True on success and False otherwise """ + nooverwrites_and_exists = ( + self.params.get('nooverwrites', False) + and os.path.exists(encodeFilename(filename)) + ) + + continuedl_and_exists = ( + self.params.get('continuedl', False) + and os.path.isfile(encodeFilename(filename)) + and not self.params.get('nopart', False) + ) + # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): + if filename != '-' and nooverwrites_and_exists or continuedl_and_exists: self.report_file_already_downloaded(filename) self._hook_progress({ 'filename': filename, @@ -302,19 +316,6 @@ class FileDownloader(object): ph(status) def add_progress_hook(self, ph): - """ ph gets called on download progress, with a dictionary with the entries - * filename: The final filename - * status: One of "downloading" and "finished" - - It can also have some of the following entries: - - * downloaded_bytes: Bytes on disks - * total_bytes: Total bytes, None if unknown - * tmpfilename: The filename we're currently writing to - * eta: The estimated time in seconds, None if unknown - * speed: The download speed in bytes/second, None if unknown - - Hooks are guaranteed to be called at least once (with status "finished") - if the download is successful. - """ + # See YoutubeDl.py (search for progress_hooks) for a description of + # this interface self._progress_hooks.append(ph) diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 7cd22c5..c460c16 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -9,10 +9,12 @@ import xml.etree.ElementTree as etree from .common import FileDownloader from .http import HttpFD +from ..compat import ( + compat_urlparse, +) from ..utils import ( struct_pack, struct_unpack, - compat_urlparse, format_bytes, encodeFilename, sanitize_open, @@ -185,24 +187,34 @@ def build_fragments_list(boot_info): return res -def write_flv_header(stream, metadata): - """Writes the FLV header and the metadata to stream""" +def write_unsigned_int(stream, val): + stream.write(struct_pack('!I', val)) + + +def write_unsigned_int_24(stream, val): + stream.write(struct_pack('!I', val)[1:]) + + +def write_flv_header(stream): + """Writes the FLV header to stream""" # FLV header stream.write(b'FLV\x01') stream.write(b'\x05') stream.write(b'\x00\x00\x00\x09') - # FLV File body stream.write(b'\x00\x00\x00\x00') - # FLVTAG - # Script data - stream.write(b'\x12') - # Size of the metadata with 3 bytes - stream.write(struct_pack('!L', len(metadata))[1:]) - stream.write(b'\x00\x00\x00\x00\x00\x00\x00') - stream.write(metadata) - # Magic numbers extracted from the output files produced by AdobeHDS.php - #(https://github.com/K-S-V/Scripts) - stream.write(b'\x00\x00\x01\x73') + + +def write_metadata_tag(stream, metadata): + """Writes optional metadata tag to stream""" + SCRIPT_TAG = b'\x12' + FLV_TAG_HEADER_LEN = 11 + + if metadata: + stream.write(SCRIPT_TAG) + write_unsigned_int_24(stream, len(metadata)) + stream.write(b'\x00\x00\x00\x00\x00\x00\x00') + stream.write(metadata) + write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata)) def _add_ns(prop): @@ -231,6 +243,7 @@ class F4mFD(FileDownloader): 'continuedl': True, 'quiet': True, 'noprogress': True, + 'ratelimit': self.params.get('ratelimit', None), 'test': self.params.get('test', False), } ) @@ -253,7 +266,11 @@ class F4mFD(FileDownloader): bootstrap = self.ydl.urlopen(bootstrap_url).read() else: bootstrap = base64.b64decode(bootstrap_node.text) - metadata = base64.b64decode(media.find(_add_ns('metadata')).text) + metadata_node = media.find(_add_ns('metadata')) + if metadata_node is not None: + metadata = base64.b64decode(metadata_node.text) + else: + metadata = None boot_info = read_bootstrap_info(bootstrap) fragments_list = build_fragments_list(boot_info) @@ -266,7 +283,8 @@ class F4mFD(FileDownloader): tmpfilename = self.temp_name(filename) (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb') - write_flv_header(dest_stream, metadata) + write_flv_header(dest_stream) + write_metadata_tag(dest_stream, metadata) # This dict stores the download progress, it's updated by the progress # hook diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 954beff..aa58b52 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -4,11 +4,13 @@ import os import re import subprocess +from ..postprocessor.ffmpeg import FFmpegPostProcessor from .common import FileDownloader -from ..utils import ( +from ..compat import ( compat_urlparse, compat_urllib_request, - check_executable, +) +from ..utils import ( encodeFilename, ) @@ -24,12 +26,12 @@ class HlsFD(FileDownloader): '-bsf:a', 'aac_adtstoasc', encodeFilename(tmpfilename, for_subprocess=True)] - for program in ['avconv', 'ffmpeg']: - if check_executable(program, ['-version']): - break - else: + ffpp = FFmpegPostProcessor(downloader=self) + program = ffpp._executable + if program is None: self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.') return False + ffpp.check_version() cmd = [program] + args retval = subprocess.call(cmd) diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 8491cee..e68f20c 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -4,11 +4,12 @@ import os import time from .common import FileDownloader -from ..utils import ( +from ..compat import ( compat_urllib_request, compat_urllib_error, +) +from ..utils import ( ContentTooShortError, - encodeFilename, sanitize_open, format_bytes, @@ -136,16 +137,21 @@ class HttpFD(FileDownloader): byte_counter = 0 + resume_len block_size = self.params.get('buffersize', 1024) start = time.time() + + # measure time over whole while-loop, so slow_down() and best_block_size() work together properly + now = None # needed for slow_down() in the first loop run + before = start # start measuring while True: + # Download and write - before = time.time() data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter)) - after = time.time() + byte_counter += len(data_block) + + # exit loop when download is finished if len(data_block) == 0: break - byte_counter += len(data_block) - # Open file just in time + # Open destination file just in time if stream is None: try: (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) @@ -161,11 +167,22 @@ class HttpFD(FileDownloader): self.to_stderr('\n') self.report_error('unable to write data: %s' % str(err)) return False + + # Apply rate limit + self.slow_down(start, now, byte_counter - resume_len) + + # end measuring of one loop run + now = time.time() + after = now + + # Adjust block size if not self.params.get('noresizebuffer', False): block_size = self.best_block_size(after - before, len(data_block)) + before = after + # Progress message - speed = self.calc_speed(start, time.time(), byte_counter - resume_len) + speed = self.calc_speed(start, now, byte_counter - resume_len) if data_len is None: eta = percent = None else: @@ -186,9 +203,6 @@ class HttpFD(FileDownloader): if is_test and byte_counter == data_len: break - # Apply rate limit - self.slow_down(start, byte_counter - resume_len) - if stream is None: self.to_stderr('\n') self.report_error('Did not get any data blocks') diff --git a/youtube_dl/downloader/mplayer.py b/youtube_dl/downloader/mplayer.py index c53195d..72cef30 100644 --- a/youtube_dl/downloader/mplayer.py +++ b/youtube_dl/downloader/mplayer.py @@ -4,8 +4,8 @@ import os import subprocess from .common import FileDownloader -from ..compat import compat_subprocess_get_DEVNULL from ..utils import ( + check_executable, encodeFilename, ) @@ -20,11 +20,7 @@ class MplayerFD(FileDownloader): 'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url] # Check for mplayer first - try: - subprocess.call( - ['mplayer', '-h'], - stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT) - except (OSError, IOError): + if not check_executable('mplayer', ['-h']): self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0]) return False diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 58ae200..5346cb9 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -7,9 +7,9 @@ import sys import time from .common import FileDownloader +from ..compat import compat_str from ..utils import ( check_executable, - compat_str, encodeFilename, format_bytes, get_exe_version, @@ -185,7 +185,7 @@ class RtmpFD(FileDownloader): cursize = os.path.getsize(encodeFilename(tmpfilename)) if prevsize == cursize and retval == RD_FAILED: break - # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024: self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.') retval = RD_SUCCESS diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0339d13..0902eb4 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -3,8 +3,11 @@ from __future__ import unicode_literals from .abc import ABCIE from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE +from .adobetv import AdobeTVIE from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE +from .aljazeera import AlJazeeraIE +from .alphaporno import AlphaPornoIE from .anitube import AnitubeIE from .anysex import AnySexIE from .aol import AolIE @@ -22,13 +25,17 @@ from .arte import ( ArteTVDDCIE, ArteTVEmbedIE, ) -from .audiomack import AudiomackIE +from .atresplayer import AtresPlayerIE +from .atttechchannel import ATTTechChannelIE +from .audiomack import AudiomackIE, AudiomackAlbumIE from .auengine import AUEngineIE +from .azubu import AzubuIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE from .bbccouk import BBCCoUkIE from .beeg import BeegIE from .behindkink import BehindKinkIE +from .bet import BetIE from .bild import BildIE from .bilibili import BiliBiliIE from .blinkx import BlinkxIE @@ -49,7 +56,7 @@ from .cbsnews import CBSNewsIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE -from .cinemassacre import CinemassacreIE +from .cinchcast import CinchcastIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE @@ -60,9 +67,13 @@ from .cnet import CNETIE from .cnn import ( CNNIE, CNNBlogsIE, + CNNArticleIE, ) from .collegehumor import CollegeHumorIE +from .collegerama import CollegeRamaIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE +from .comcarcoff import ComCarCoffIE +from .commonmistakes import CommonMistakesIE from .condenast import CondeNastIE from .cracked import CrackedIE from .criterion import CriterionIE @@ -82,14 +93,17 @@ from .deezer import DeezerPlaylistIE from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +from .drbonanza import DRBonanzaIE from .drtuber import DrTuberIE from .drtv import DRTVIE +from .dvtv import DVTVIE from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE +from .echomsk import EchoMskIE from .ehow import EHowIE from .eighttracks import EightTracksIE from .einthusan import EinthusanIE @@ -102,6 +116,7 @@ from .elpais import ElPaisIE from .empflix import EMPFlixIE from .engadget import EngadgetIE from .eporner import EpornerIE +from .eroprofile import EroProfileIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE @@ -121,6 +136,8 @@ from .fktv import ( from .flickr import FlickrIE from .folketinget import FolketingetIE from .fourtube import FourTubeIE +from .foxgay import FoxgayIE +from .foxnews import FoxNewsIE from .franceculture import FranceCultureIE from .franceinter import FranceInterIE from .francetv import ( @@ -144,6 +161,8 @@ from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE +from .giantbomb import GiantBombIE +from .giga import GigaIE from .glide import GlideIE from .globo import GloboIE from .godtube import GodTubeIE @@ -154,10 +173,13 @@ from .googlesearch import GoogleSearchIE from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE from .grooveshark import GroovesharkIE +from .groupon import GrouponIE from .hark import HarkIE from .heise import HeiseIE +from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .hitbox import HitboxIE, HitboxLiveIE from .hornbunny import HornBunnyIE from .hostingbulk import HostingBulkIE from .hotnewhiphop import HotNewHipHopIE @@ -187,6 +209,7 @@ from .jove import JoveIE from .jukebox import JukeboxIE from .jpopsukitv import JpopsukiIE from .kankan import KankanIE +from .karaoketv import KaraoketvIE from .keezmovies import KeezMoviesIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE @@ -203,6 +226,7 @@ from .livestream import ( LivestreamOriginalIE, LivestreamShortenerIE, ) +from .lnkgo import LnkGoIE from .lrt import LRTIE from .lynda import ( LyndaIE, @@ -216,6 +240,7 @@ from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE +from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE from .mitele import MiTeleIE @@ -245,6 +270,7 @@ from .muzu import MuzuTVIE from .myspace import MySpaceIE, MySpaceAlbumIE from .myspass import MySpassIE from .myvideo import MyVideoIE +from .myvidster import MyVidsterIE from .naver import NaverIE from .nba import NBAIE from .nbc import ( @@ -253,6 +279,8 @@ from .nbc import ( ) from .ndr import NDRIE from .ndtv import NDTVIE +from .netzkino import NetzkinoIE +from .nerdcubed import NerdCubedFeedIE from .newgrounds import NewgroundsIE from .newstube import NewstubeIE from .nfb import NFBIE @@ -268,6 +296,7 @@ from .nowness import NownessIE from .nowvideo import NowVideoIE from .npo import ( NPOIE, + NPOLiveIE, TegenlichtVproIE, ) from .nrk import ( @@ -279,6 +308,7 @@ from .nytimes import NYTimesIE from .nuvid import NuvidIE from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE +from .openfilm import OpenFilmIE from .orf import ( ORFTVthekIE, ORFOE1IE, @@ -302,24 +332,30 @@ from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE from .quickvid import QuickVidIE +from .radiode import RadioDeIE +from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE +from .restudy import RestudyIE from .reverbnation import ReverbNationIE from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rte import RteIE from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE +from .rtp import RTPIE from .rts import RTSIE from .rtve import RTVEALaCartaIE, RTVELiveIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, RutubeChannelIE, + RutubeEmbedIE, RutubeMovieIE, RutubePersonIE, ) @@ -329,6 +365,8 @@ from .savefrom import SaveFromIE from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE +from .screencastomatic import ScreencastOMaticIE +from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE from .servingsys import ServingSysIE from .sexu import SexuIE from .sexykarma import SexyKarmaIE @@ -388,6 +426,7 @@ from .ted import TEDIE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE from .telemb import TeleMBIE +from .teletask import TeleTaskIE from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE @@ -415,8 +454,9 @@ from .tunein import TuneInIE from .turbo import TurboIE from .tutv import TutvIE from .tvigle import TvigleIE -from .tvp import TvpIE +from .tvp import TvpIE, TvpSeriesIE from .tvplay import TVPlayIE +from .twentyfourvideo import TwentyFourVideoIE from .twitch import TwitchIE from .ubu import UbuIE from .udemy import ( @@ -445,6 +485,7 @@ from .videott import VideoTtIE from .videoweed import VideoWeedIE from .vidme import VidmeIE from .vidzi import VidziIE +from .vier import VierIE, VierVideosIE from .vimeo import ( VimeoIE, VimeoAlbumIE, @@ -480,6 +521,7 @@ from .wdr import ( WDRMobileIE, WDRMausIE, ) +from .webofstories import WebOfStoriesIE from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE @@ -492,10 +534,12 @@ from .xminus import XMinusIE from .xnxx import XNXXIE from .xvideos import XVideosIE from .xtube import XTubeUserIE, XTubeIE +from .xxxymovies import XXXYMoviesIE from .yahoo import ( YahooIE, YahooSearchIE, ) +from .yesjapan import YesJapanIE from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE @@ -513,12 +557,12 @@ from .youtube import ( YoutubeSearchURLIE, YoutubeShowIE, YoutubeSubscriptionsIE, - YoutubeTopListIE, + YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, YoutubeUserIE, YoutubeWatchLaterIE, ) -from .zdf import ZDFIE +from .zdf import ZDFIE, ZDFChannelIE from .zingmp3 import ( ZingMp3SongIE, ZingMp3AlbumIE, @@ -539,6 +583,17 @@ def gen_extractors(): return [klass() for klass in _ALL_CLASSES] +def list_extractors(age_limit): + """ + Return a list of extractors that are suitable for the given age, + sorted by extractor ID. + """ + + return sorted( + filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()), + key=lambda ie: ie.IE_NAME.lower()) + + def get_info_extractor(ie_name): """Returns the info extractor class with the given ie_name""" return globals()[ie_name + 'IE'] diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py new file mode 100644 index 0000000..28e07f8 --- /dev/null +++ b/youtube_dl/extractor/adobetv.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + unified_strdate, + str_to_int, +) + + +class AdobeTVIE(InfoExtractor): + _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)' + + _TEST = { + 'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/', + 'md5': '9bc5727bcdd55251f35ad311ca74fa1e', + 'info_dict': { + 'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop', + 'ext': 'mp4', + 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop', + 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311', + 'thumbnail': 're:https?://.*\.jpg$', + 'upload_date': '20110914', + 'duration': 60, + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + player = self._parse_json( + self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'), + video_id) + + title = player.get('title') or self._search_regex( + r'data-title="([^"]+)"', webpage, 'title') + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + upload_date = unified_strdate( + self._html_search_meta('datepublished', webpage, 'upload date')) + + duration = parse_duration( + self._html_search_meta('duration', webpage, 'duration') + or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration')) + + view_count = str_to_int(self._search_regex( + r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>', + webpage, 'view count')) + + formats = [{ + 'url': source['src'], + 'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None, + 'tbr': source.get('bitrate'), + } for source in player['sources']] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 0d05cbb..502a9c2 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -2,123 +2,150 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor +from ..utils import ( + ExtractorError, + xpath_text, + float_or_none, +) class AdultSwimIE(InfoExtractor): - _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' - _TEST = { - 'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', + _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?' + + _TESTS = [{ + 'url': 'http://adultswim.com/videos/rick-and-morty/pilot', 'playlist': [ { - 'md5': '4da359ec73b58df4575cd01a610ba5dc', - 'info_dict': { - 'id': '8a250ba1450996e901453d7f02ca02f5', - 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } - }, - { - 'md5': 'ffbdf55af9331c509d95350bd0cc1819', + 'md5': '247572debc75c7652f253c8daa51a14d', 'info_dict': { - 'id': '8a250ba1450996e901453d7f4bd102f6', + 'id': 'rQxZvXQ4ROaSOqq-or2Mow-0', 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } + 'title': 'Rick and Morty - Pilot Part 1', + 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " + }, }, { - 'md5': 'b92409635540304280b4b6c36bd14a0a', + 'md5': '77b0e037a4b20ec6b98671c4c379f48d', 'info_dict': { - 'id': '8a250ba1450996e901453d7fa73c02f7', + 'id': 'rQxZvXQ4ROaSOqq-or2Mow-3', 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } + 'title': 'Rick and Morty - Pilot Part 4', + 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " + }, }, + ], + 'info_dict': { + 'title': 'Rick and Morty - Pilot', + 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " + } + }, { + 'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/', + 'playlist': [ { - 'md5': 'e8818891d60e47b29cd89d7b0278156d', + 'md5': '2eb5c06d0f9a1539da3718d897f13ec5', 'info_dict': { - 'id': '8a250ba1450996e901453d7fc8ba02f8', + 'id': '-t8CamQlQ2aYZ49ItZCFog-0', 'ext': 'flv', - 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4', - 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', - 'uploader': 'Rick and Morty', - 'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg' - } + 'title': 'American Dad - Putting Francine Out of Business', + 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].' + }, } - ] - } - - _video_extensions = { - '3500': 'flv', - '640': 'mp4', - '150': 'mp4', - 'ipad': 'm3u8', - 'iphone': 'm3u8' - } - _video_dimensions = { - '3500': (1280, 720), - '640': (480, 270), - '150': (320, 180) - } + ], + 'info_dict': { + 'title': 'American Dad - Putting Francine Out of Business', + 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].' + }, + }] + + @staticmethod + def find_video_info(collection, slug): + for video in collection.get('videos'): + if video.get('slug') == slug: + return video + + @staticmethod + def find_collection_by_linkURL(collections, linkURL): + for collection in collections: + if collection.get('linkURL') == linkURL: + return collection + + @staticmethod + def find_collection_containing_video(collections, slug): + for collection in collections: + for video in collection.get('videos'): + if video.get('slug') == slug: + return collection, video def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_path = mobj.group('path') - - webpage = self._download_webpage(url, video_path) - episode_id = self._html_search_regex( - r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', - webpage, 'episode_id') - title = self._og_search_title(webpage) - - index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id - idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') - - episode_el = idoc.find('.//episode') - show_title = episode_el.attrib.get('collectionTitle') - episode_title = episode_el.attrib.get('title') - thumbnail = episode_el.attrib.get('thumbnailUrl') - description = episode_el.find('./description').text.strip() + show_path = mobj.group('show_path') + episode_path = mobj.group('episode_path') + is_playlist = True if mobj.group('is_playlist') else False + + webpage = self._download_webpage(url, episode_path) + + # Extract the value of `bootstrappedData` from the Javascript in the page. + bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path) + + try: + bootstrappedData = json.loads(bootstrappedDataJS) + except ValueError as ve: + errmsg = '%s: Failed to parse JSON ' % episode_path + raise ExtractorError(errmsg, cause=ve) + + # Downloading videos from a /videos/playlist/ URL needs to be handled differently. + # NOTE: We are only downloading one video (the current one) not the playlist + if is_playlist: + collections = bootstrappedData['playlists']['collections'] + collection = self.find_collection_by_linkURL(collections, show_path) + video_info = self.find_video_info(collection, episode_path) + + show_title = video_info['showTitle'] + segment_ids = [video_info['videoPlaybackID']] + else: + collections = bootstrappedData['show']['collections'] + collection, video_info = self.find_collection_containing_video(collections, episode_path) + + show = bootstrappedData['show'] + show_title = show['title'] + segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']] + + episode_id = video_info['id'] + episode_title = video_info['title'] + episode_description = video_info['description'] + episode_duration = video_info.get('duration') entries = [] - segment_els = episode_el.findall('./segments/segment') + for part_num, segment_id in enumerate(segment_ids): + segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id - for part_num, segment_el in enumerate(segment_els): - segment_id = segment_el.attrib.get('id') - segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) - thumbnail = segment_el.attrib.get('thumbnailUrl') - duration = segment_el.attrib.get('duration') + segment_title = '%s - %s' % (show_title, episode_title) + if len(segment_ids) > 1: + segment_title += ' Part %d' % (part_num + 1) - segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id idoc = self._download_xml( segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information') + segment_duration = float_or_none( + xpath_text(idoc, './/trt', 'segment duration').strip()) + formats = [] file_els = idoc.findall('.//files/file') for file_el in file_els: bitrate = file_el.attrib.get('bitrate') - type = file_el.attrib.get('type') - width, height = self._video_dimensions.get(bitrate, (None, None)) + ftype = file_el.attrib.get('type') + formats.append({ - 'format_id': '%s-%s' % (bitrate, type), - 'url': file_el.text, - 'ext': self._video_extensions.get(bitrate, 'mp4'), + 'format_id': '%s_%s' % (bitrate, ftype), + 'url': file_el.text.strip(), # The bitrate may not be a number (for example: 'iphone') 'tbr': int(bitrate) if bitrate.isdigit() else None, - 'height': height, - 'width': width + 'quality': 1 if ftype == 'hd' else -1 }) self._sort_formats(formats) @@ -127,18 +154,16 @@ class AdultSwimIE(InfoExtractor): 'id': segment_id, 'title': segment_title, 'formats': formats, - 'uploader': show_title, - 'thumbnail': thumbnail, - 'duration': duration, - 'description': description + 'duration': segment_duration, + 'description': episode_description }) return { '_type': 'playlist', 'id': episode_id, - 'display_id': video_path, + 'display_id': episode_path, 'entries': entries, - 'title': '%s %s' % (show_title, episode_title), - 'description': description, - 'thumbnail': thumbnail + 'title': '%s - %s' % (show_title, episode_title), + 'description': episode_description, + 'duration': episode_duration } diff --git a/youtube_dl/extractor/aljazeera.py b/youtube_dl/extractor/aljazeera.py new file mode 100644 index 0000000..612708e --- /dev/null +++ b/youtube_dl/extractor/aljazeera.py @@ -0,0 +1,35 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class AlJazeeraIE(InfoExtractor): + _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html' + + _TEST = { + 'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html', + 'info_dict': { + 'id': '3792260579001', + 'ext': 'mp4', + 'title': 'The Slum - Episode 1: Deliverance', + 'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.', + 'uploader': 'Al Jazeera English', + }, + 'add_ie': ['Brightcove'], + } + + def _real_extract(self, url): + program_name = self._match_id(url) + webpage = self._download_webpage(url, program_name) + brightcove_id = self._search_regex( + r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id') + + return { + '_type': 'url', + 'url': ( + 'brightcove:' + 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc' + '&%40videoPlayer={0}'.format(brightcove_id) + ), + 'ie_key': 'Brightcove', + } diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index 398e93b..7d65b81 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -5,15 +5,14 @@ import re import json from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_str, qualities, - determine_ext, ) class AllocineIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?' + _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?' _TESTS = [{ 'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html', @@ -45,6 +44,9 @@ class AllocineIE(InfoExtractor): 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac', 'thumbnail': 're:http://.*\.jpg', }, + }, { + 'url': 'http://www.allocine.fr/video/video-19550147/', + 'only_matching': True, }] def _real_extract(self, url): @@ -75,9 +77,7 @@ class AllocineIE(InfoExtractor): 'format_id': format_id, 'quality': quality(format_id), 'url': v, - 'ext': determine_ext(v), }) - self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/alphaporno.py b/youtube_dl/extractor/alphaporno.py new file mode 100644 index 0000000..c34719d --- /dev/null +++ b/youtube_dl/extractor/alphaporno.py @@ -0,0 +1,77 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + parse_duration, + parse_filesize, + int_or_none, +) + + +class AlphaPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/', + 'md5': 'feb6d3bba8848cd54467a87ad34bd38e', + 'info_dict': { + 'id': '258807', + 'display_id': 'sensual-striptease-porn-with-samantha-alexandra', + 'ext': 'mp4', + 'title': 'Sensual striptease porn with Samantha Alexandra', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1418694611, + 'upload_date': '20141216', + 'duration': 387, + 'filesize_approx': 54120000, + 'tbr': 1145, + 'categories': list, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None) + + video_url = self._search_regex( + r"video_url\s*:\s*'([^']+)'", webpage, 'video url') + ext = self._html_search_meta( + 'encodingFormat', webpage, 'ext', default='.mp4')[1:] + + title = self._search_regex( + [r'<meta content="([^"]+)" itemprop="description">', + r'class="title" itemprop="name">([^<]+)<'], + webpage, 'title') + thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date')) + duration = parse_duration(self._html_search_meta( + 'duration', webpage, 'duration')) + filesize_approx = parse_filesize(self._html_search_meta( + 'contentSize', webpage, 'file size')) + bitrate = int_or_none(self._html_search_meta( + 'bitrate', webpage, 'bitrate')) + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'filesize_approx': filesize_approx, + 'tbr': bitrate, + 'categories': categories, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index 47f8e41..b51eafc 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .fivemin import FiveMinIE class AolIE(InfoExtractor): @@ -42,31 +41,30 @@ class AolIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - playlist_id = mobj.group('playlist_id') - if playlist_id and not self._downloader.params.get('noplaylist'): - self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) + if not playlist_id or self._downloader.params.get('noplaylist'): + return self.url_result('5min:%s' % video_id) - webpage = self._download_webpage(url, playlist_id) - title = self._html_search_regex( - r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title') - playlist_html = self._search_regex( - r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage, - 'playlist HTML') - entries = [{ - '_type': 'url', - 'url': 'aol-video:%s' % m.group('id'), - 'ie_key': 'Aol', - } for m in re.finditer( - r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>", - playlist_html)] + self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': mobj.group('playlist_display_id'), - 'title': title, - 'entries': entries, - } + webpage = self._download_webpage(url, playlist_id) + title = self._html_search_regex( + r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title') + playlist_html = self._search_regex( + r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage, + 'playlist HTML') + entries = [{ + '_type': 'url', + 'url': 'aol-video:%s' % m.group('id'), + 'ie_key': 'Aol', + } for m in re.finditer( + r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>", + playlist_html)] - return FiveMinIE._build_result(video_id) + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': mobj.group('playlist_display_id'), + 'title': title, + 'entries': entries, + } diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 0c01fa1..7cd0482 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -4,8 +4,8 @@ import re import json from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( - compat_urlparse, int_or_none, ) diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 34ce842..9fc35a4 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -1,42 +1,48 @@ from __future__ import unicode_literals -import json -import re - from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' - _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' - _TEST = { - "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", - 'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv', + _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' + _TESTS = [{ + 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'md5': '8af1d4cf447933ed3c7f4871162602db', 'info_dict': { - "title": "1968 Demo - FJCC Conference Presentation Reel #1", - "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>", - "upload_date": "19681210", - "uploader": "SRI International" + 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect', + 'ext': 'ogv', + 'title': '1968 Demo - FJCC Conference Presentation Reel #1', + 'description': 'md5:1780b464abaca9991d8968c877bb53ed', + 'upload_date': '19681210', + 'uploader': 'SRI International' + } + }, { + 'url': 'https://archive.org/details/Cops1922', + 'md5': '18f2a19e6d89af8425671da1cf3d4e04', + 'info_dict': { + 'id': 'Cops1922', + 'ext': 'ogv', + 'title': 'Buster Keaton\'s "Cops" (1922)', + 'description': 'md5:70f72ee70882f713d4578725461ffcc3', } - } + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) json_url = url + ('?' if '?' in url else '&') + 'output=json' - json_data = self._download_webpage(json_url, video_id) - data = json.loads(json_data) + data = self._download_json(json_url, video_id) + + def get_optional(data_dict, field): + return data_dict['metadata'].get(field, [None])[0] - title = data['metadata']['title'][0] - description = data['metadata']['description'][0] - uploader = data['metadata']['creator'][0] - upload_date = unified_strdate(data['metadata']['date'][0]) + title = get_optional(data, 'title') + description = get_optional(data, 'description') + uploader = get_optional(data, 'creator') + upload_date = unified_strdate(get_optional(data, 'date')) formats = [ { diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 219631b..929dd3c 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -37,7 +37,7 @@ class ArteTvIE(InfoExtractor): config_xml_url, video_id, note='Downloading configuration') formats = [{ - 'forma_id': q.attrib['quality'], + 'format_id': q.attrib['quality'], # The playpath starts at 'mp4:', if we don't manually # split the url, rtmpdump will incorrectly parse them 'url': q.text.split('mp4:', 1)[0], @@ -133,7 +133,7 @@ class ArteTVPlus7IE(InfoExtractor): 'width': int_or_none(f.get('width')), 'height': int_or_none(f.get('height')), 'tbr': int_or_none(f.get('bitrate')), - 'quality': qfunc(f['quality']), + 'quality': qfunc(f.get('quality')), 'source_preference': source_pref, } diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py new file mode 100644 index 0000000..5db1941 --- /dev/null +++ b/youtube_dl/extractor/atresplayer.py @@ -0,0 +1,144 @@ +from __future__ import unicode_literals + +import time +import hmac + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + int_or_none, + float_or_none, + xpath_text, + ExtractorError, +) + + +class AtresPlayerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html' + _TESTS = [ + { + 'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html', + 'md5': 'efd56753cda1bb64df52a3074f62e38a', + 'info_dict': { + 'id': 'capitulo-10-especial-solidario-nochebuena', + 'ext': 'mp4', + 'title': 'Especial Solidario de Nochebuena', + 'description': 'md5:e2d52ff12214fa937107d21064075bf1', + 'duration': 5527.6, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', + 'only_matching': True, + }, + ] + + _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J' + _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)' + _TIMESTAMP_SHIFT = 30000 + + _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json' + _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json' + _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s' + _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s' + + _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check' + + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_form = { + 'j_username': username, + 'j_password': password, + } + + request = compat_urllib_request.Request( + self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + response = self._download_webpage( + request, None, 'Logging in as %s' % username) + + error = self._html_search_regex( + r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None) + if error: + raise ExtractorError( + 'Unable to login: %s' % error, expected=True) + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + episode_id = self._search_regex( + r'episode="([^"]+)"', webpage, 'episode id') + + timestamp = int_or_none(self._download_webpage( + self._TIME_API_URL, + video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) + timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) + token = hmac.new( + self._MAGIC.encode('ascii'), + (episode_id + timestamp_shifted).encode('utf-8') + ).hexdigest() + + formats = [] + for fmt in ['windows', 'android_tablet']: + request = compat_urllib_request.Request( + self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token)) + request.add_header('Youtubedl-user-agent', self._USER_AGENT) + + fmt_json = self._download_json( + request, video_id, 'Downloading %s video JSON' % fmt) + + result = fmt_json.get('resultDes') + if result.lower() != 'ok': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, result), expected=True) + + for _, video_url in fmt_json['resultObject'].items(): + if video_url.endswith('/Manifest'): + formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id)) + else: + formats.append({ + 'url': video_url, + 'format_id': 'android', + 'preference': 1, + }) + self._sort_formats(formats) + + player = self._download_json( + self._PLAYER_URL_TEMPLATE % episode_id, + episode_id) + + path_data = player.get('pathData') + + episode = self._download_xml( + self._EPISODE_URL_TEMPLATE % path_data, + video_id, 'Downloading episode XML') + + duration = float_or_none(xpath_text( + episode, './media/asset/info/technical/contentDuration', 'duration')) + + art = episode.find('./media/asset/info/art') + title = xpath_text(art, './name', 'title') + description = xpath_text(art, './description', 'description') + thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail') + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/atttechchannel.py b/youtube_dl/extractor/atttechchannel.py new file mode 100644 index 0000000..b01d35b --- /dev/null +++ b/youtube_dl/extractor/atttechchannel.py @@ -0,0 +1,55 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class ATTTechChannelIE(InfoExtractor): + _VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)' + _TEST = { + 'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use', + 'info_dict': { + 'id': '11316', + 'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use', + 'ext': 'flv', + 'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use', + 'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20140127', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r"url\s*:\s*'(rtmp://[^']+)'", + webpage, 'video URL') + + video_id = self._search_regex( + r'mediaid\s*=\s*(\d+)', + webpage, 'video id', fatal=False) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + upload_date = unified_strdate(self._search_regex( + r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})', + webpage, 'upload date', fatal=False), False) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'ext': 'flv', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index eeeec76..8bfe502 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -1,11 +1,15 @@ # coding: utf-8 from __future__ import unicode_literals +import itertools +import time + from .common import InfoExtractor from .soundcloud import SoundcloudIE -from ..utils import ExtractorError - -import time +from ..utils import ( + ExtractorError, + url_basename, +) class AudiomackIE(InfoExtractor): @@ -17,53 +21,119 @@ class AudiomackIE(InfoExtractor): 'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary', 'info_dict': { - 'id': 'roosh-williams/extraordinary', + 'id': '310086', 'ext': 'mp3', - 'title': 'Roosh Williams - Extraordinary' + 'uploader': 'Roosh Williams', + 'title': 'Extraordinary' } }, - # hosted on soundcloud via audiomack + # audiomack wrapper around soundcloud song { + 'add_ie': ['Soundcloud'], 'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare', - 'file': '172419696.mp3', - 'info_dict': - { + 'info_dict': { + 'id': '172419696', 'ext': 'mp3', + 'description': 'md5:1fc3272ed7a635cce5be1568c2822997', 'title': 'Young Thug ft Lil Wayne - Take Kare', - "upload_date": "20141016", - "description": "New track produced by London On Da Track called “Take Kare\"\n\nhttp://instagram.com/theyoungthugworld\nhttps://www.facebook.com/ThuggerThuggerCashMoney\n", - "uploader": "Young Thug World" + 'uploader': 'Young Thug World', + 'upload_date': '20141016', } - } + }, ] def _real_extract(self, url): - video_id = self._match_id(url) + # URLs end with [uploader name]/[uploader title] + # this title is whatever the user types in, and is rarely + # the proper song title. Real metadata is in the api response + album_url_tag = self._match_id(url) + # Request the extended version of the api for extra fields like artist and title api_response = self._download_json( - "http://www.audiomack.com/api/music/url/song/%s?_=%d" % ( - video_id, time.time()), - video_id) + 'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % ( + album_url_tag, time.time()), + album_url_tag) - if "url" not in api_response: - raise ExtractorError("Unable to deduce api url of song") - realurl = api_response["url"] + # API is inconsistent with errors + if 'url' not in api_response or not api_response['url'] or 'error' in api_response: + raise ExtractorError('Invalid url %s', url) # Audiomack wraps a lot of soundcloud tracks in their branded wrapper - # - if so, pass the work off to the soundcloud extractor - if SoundcloudIE.suitable(realurl): - return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'} - - webpage = self._download_webpage(url, video_id) - artist = self._html_search_regex( - r'<span class="artist">(.*?)</span>', webpage, "artist") - songtitle = self._html_search_regex( - r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>', - webpage, "title") - title = artist + " - " + songtitle + # if so, pass the work off to the soundcloud extractor + if SoundcloudIE.suitable(api_response['url']): + return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'} return { - 'id': video_id, - 'title': title, - 'url': realurl, + 'id': api_response.get('id', album_url_tag), + 'uploader': api_response.get('artist'), + 'title': api_response.get('title'), + 'url': api_response['url'], + } + + +class AudiomackAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)' + IE_NAME = 'audiomack:album' + _TESTS = [ + # Standard album playlist + { + 'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape', + 'playlist_count': 15, + 'info_dict': + { + 'id': '812251', + 'title': 'Tha Tour: Part 2 (Official Mixtape)' + } + }, + # Album playlist ripped from fakeshoredrive with no metadata + { + 'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project', + 'playlist': [{ + 'info_dict': { + 'title': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu', + 'id': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu', + 'ext': 'mp3', + } + }], + 'params': { + 'playliststart': 8, + 'playlistend': 8, + } } + ] + + def _real_extract(self, url): + # URLs end with [uploader name]/[uploader title] + # this title is whatever the user types in, and is rarely + # the proper song title. Real metadata is in the api response + album_url_tag = self._match_id(url) + result = {'_type': 'playlist', 'entries': []} + # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata + # Therefore we don't know how many songs the album has and must infi-loop until failure + for track_no in itertools.count(): + # Get song's metadata + api_response = self._download_json( + 'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d' + % (album_url_tag, track_no, time.time()), album_url_tag, + note='Querying song information (%d)' % (track_no + 1)) + + # Total failure, only occurs when url is totally wrong + # Won't happen in middle of valid playlist (next case) + if 'url' not in api_response or 'error' in api_response: + raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url)) + # URL is good but song id doesn't exist - usually means end of playlist + elif not api_response['url']: + break + else: + # Pull out the album metadata and add to result (if it exists) + for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]: + if apikey in api_response and resultkey not in result: + result[resultkey] = api_response[apikey] + song_id = url_basename(api_response['url']).rpartition('.')[0] + result['entries'].append({ + 'id': api_response.get('id', song_id), + 'uploader': api_response.get('artist'), + 'title': api_response.get('title', song_id), + 'url': api_response['url'], + }) + return result diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 1c76553..a1b666b 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -3,10 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( - compat_urllib_parse, determine_ext, ExtractorError, + remove_end, ) @@ -27,23 +28,18 @@ class AUEngineIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title') - title = title.strip() - links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage) - links = map(compat_urllib_parse.unquote, links) - - thumbnail = None - video_url = None - for link in links: - if link.endswith('.png'): - thumbnail = link - elif '/videos/' in link: - video_url = link + title = self._html_search_regex( + r'<title>\s*(?P<title>.+?)\s*</title>', webpage, 'title') + video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage) + video_url = compat_urllib_parse.unquote(video_urls[0]) + thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage) + thumbnail = compat_urllib_parse.unquote(thumbnails[0]) + if not video_url: raise ExtractorError('Could not find video URL') + ext = '.' + determine_ext(video_url) - if ext == title[-len(ext):]: - title = title[:-len(ext)] + title = remove_end(title, ext) return { 'id': video_id, diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py new file mode 100644 index 0000000..0961d33 --- /dev/null +++ b/youtube_dl/extractor/azubu.py @@ -0,0 +1,93 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import float_or_none + + +class AzubuIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1', + 'md5': 'a88b42fcf844f29ad6035054bd9ecaf4', + 'info_dict': { + 'id': '15575', + 'ext': 'mp4', + 'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1', + 'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01', + 'thumbnail': 're:^https?://.*\.jpe?g', + 'timestamp': 1417523507.334, + 'upload_date': '20141202', + 'duration': 9988.7, + 'uploader': 'GSL', + 'uploader_id': 414310, + 'view_count': int, + }, + }, + { + 'url': 'http://www.azubu.tv/FnaticTV#!/play/9344/-fnatic-at-worlds-2014:-toyz---%22i-love-rekkles,-he-has-amazing-mechanics%22-', + 'md5': 'b72a871fe1d9f70bd7673769cdb3b925', + 'info_dict': { + 'id': '9344', + 'ext': 'mp4', + 'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"', + 'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af', + 'thumbnail': 're:^https?://.*\.jpe?g', + 'timestamp': 1410530893.320, + 'upload_date': '20140912', + 'duration': 172.385, + 'uploader': 'FnaticTV', + 'uploader_id': 272749, + 'view_count': int, + }, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + data = self._download_json( + 'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data'] + + title = data['title'].strip() + description = data['description'] + thumbnail = data['thumbnail'] + view_count = data['view_count'] + uploader = data['user']['username'] + uploader_id = data['user']['id'] + + stream_params = json.loads(data['stream_params']) + + timestamp = float_or_none(stream_params['creationDate'], 1000) + duration = float_or_none(stream_params['length'], 1000) + + renditions = stream_params.get('renditions') or [] + video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength') + if video: + renditions.append(video) + + formats = [{ + 'url': fmt['url'], + 'width': fmt['frameWidth'], + 'height': fmt['frameHeight'], + 'vbr': float_or_none(fmt['encodingRate'], 1000), + 'filesize': fmt['size'], + 'vcodec': fmt['videoCodec'], + 'container': fmt['videoContainer'], + } for fmt in renditions if fmt['url']] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index 1ca0b7c..98e1443 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -5,7 +5,7 @@ import json import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, ) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index acddbc8..aea0263 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -4,9 +4,11 @@ import json import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urlparse, +) +from ..utils import ( ExtractorError, ) @@ -104,7 +106,7 @@ class BandcampIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' - _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' + _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+)|/?(?:$|[?#]))' _TESTS = [{ 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', @@ -139,6 +141,12 @@ class BandcampAlbumIE(InfoExtractor): 'title': 'Hierophany of the Open Grave', }, 'playlist_mincount': 9, + }, { + 'url': 'http://dotscale.bandcamp.com', + 'info_dict': { + 'title': 'Loom', + }, + 'playlist_mincount': 7, }] def _real_extract(self, url): @@ -153,7 +161,8 @@ class BandcampAlbumIE(InfoExtractor): entries = [ self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key()) for t_path in tracks_paths] - title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title') + title = self._search_regex( + r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False) return { '_type': 'playlist', 'id': playlist_id, diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index beb6cfc..1cf48fe 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import re import xml.etree.ElementTree from .subtitles import SubtitlesInfoExtractor @@ -11,7 +10,7 @@ from ..compat import compat_HTTPError class BBCCoUkIE(SubtitlesInfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' _TESTS = [ { @@ -19,8 +18,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope: Leonard Cohen', - 'description': 'md5:db4755d7a665ae72343779f7dacb402c', + 'title': 'Kaleidoscope, Leonard Cohen', + 'description': 'The Canadian poet and songwriter reflects on his musical career.', 'duration': 1740, }, 'params': { @@ -72,7 +71,54 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'skip_download': True, }, 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', - }, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', + 'info_dict': { + 'id': 'b04v209v', + 'ext': 'flv', + 'title': 'Pete Tong, The Essential New Tune Special', + 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", + 'duration': 10800, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', + 'note': 'Audio', + 'info_dict': { + 'id': 'p02frcch', + 'ext': 'flv', + 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', + 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', + 'duration': 3507, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', + 'note': 'Video', + 'info_dict': { + 'id': 'p025c103', + 'ext': 'flv', + 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', + 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', + 'duration': 226, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', + 'only_matching': True, + } ] def _extract_asx_playlist(self, connection, programme_id): @@ -204,13 +250,66 @@ class BBCCoUkIE(SubtitlesInfoExtractor): return formats, subtitles + def _download_playlist(self, playlist_id): + try: + playlist = self._download_json( + 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, + playlist_id, 'Downloading playlist JSON') + + version = playlist.get('defaultAvailableVersion') + if version: + smp_config = version['smpConfig'] + title = smp_config['title'] + description = smp_config['summary'] + for item in smp_config['items']: + kind = item['kind'] + if kind != 'programme' and kind != 'radioProgramme': + continue + programme_id = item.get('vpid') + duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) + return programme_id, title, description, duration, formats, subtitles + except ExtractorError as ee: + if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: + raise + + # fallback to legacy playlist + playlist = self._download_xml( + 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, + playlist_id, 'Downloading legacy playlist XML') + + no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') + if no_items is not None: + reason = no_items.get('reason') + if reason == 'preAvailability': + msg = 'Episode %s is not yet available' % playlist_id + elif reason == 'postAvailability': + msg = 'Episode %s is no longer available' % playlist_id + elif reason == 'noMedia': + msg = 'Episode %s is not currently available' % playlist_id + else: + msg = 'Episode %s is not available: %s' % (playlist_id, reason) + raise ExtractorError(msg, expected=True) + + for item in self._extract_items(playlist): + kind = item.get('kind') + if kind != 'programme' and kind != 'radioProgramme': + continue + title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text + description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text + programme_id = item.get('identifier') + duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) + + return programme_id, title, description, duration, formats, subtitles + def _real_extract(self, url): group_id = self._match_id(url) webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False) + r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) if programme_id: player = self._download_json( 'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id, @@ -220,32 +319,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor): duration = player['duration'] formats, subtitles = self._download_media_selector(programme_id) else: - playlist = self._download_xml( - 'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, - group_id, 'Downloading playlist XML') - - no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') - if no_items is not None: - reason = no_items.get('reason') - if reason == 'preAvailability': - msg = 'Episode %s is not yet available' % group_id - elif reason == 'postAvailability': - msg = 'Episode %s is no longer available' % group_id - elif reason == 'noMedia': - msg = 'Episode %s is not currently available' % group_id - else: - msg = 'Episode %s is not available: %s' % (group_id, reason) - raise ExtractorError(msg, expected=True) - - for item in self._extract_items(playlist): - kind = item.get('kind') - if kind != 'programme' and kind != 'radioProgramme': - continue - title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text - description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text - programme_id = item.get('identifier') - duration = int(item.get('duration')) - formats, subtitles = self._download_media_selector(programme_id) + programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) if self._downloader.params.get('listsubtitles', False): self._list_available_subtitles(programme_id, subtitles) diff --git a/youtube_dl/extractor/behindkink.py b/youtube_dl/extractor/behindkink.py index 31fdc0d..1bdc258 100644 --- a/youtube_dl/extractor/behindkink.py +++ b/youtube_dl/extractor/behindkink.py @@ -10,15 +10,15 @@ from ..utils import url_basename class BehindKinkIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)' _TEST = { - 'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/', - 'md5': '41ad01222b8442089a55528fec43ec01', + 'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/', + 'md5': '507b57d8fdcd75a41a9a7bdb7989c762', 'info_dict': { - 'id': '36370', + 'id': '37127', 'ext': 'mp4', - 'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!', - 'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...', - 'upload_date': '20140814', - 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg', + 'title': 'What are you passionate about – Marley Blaze', + 'description': 'md5:aee8e9611b4ff70186f752975d9b94b4', + 'upload_date': '20141205', + 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg', 'age_limit': 18, } } @@ -26,26 +26,19 @@ class BehindKinkIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') - year = mobj.group('year') - month = mobj.group('month') - day = mobj.group('day') - upload_date = year + month + day webpage = self._download_webpage(url, display_id) video_url = self._search_regex( - r"'file':\s*'([^']+)'", - webpage, 'URL base') - - video_id = url_basename(video_url) - video_id = video_id.split('_')[0] + r'<source src="([^"]+)"', webpage, 'video URL') + video_id = url_basename(video_url).split('_')[0] + upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day') return { 'id': video_id, + 'display_id': display_id, 'url': video_url, - 'ext': 'mp4', 'title': self._og_search_title(webpage), - 'display_id': display_id, 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), 'upload_date': upload_date, diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py new file mode 100644 index 0000000..d2abd4d --- /dev/null +++ b/youtube_dl/extractor/bet.py @@ -0,0 +1,107 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urllib_parse +from ..utils import ( + xpath_text, + xpath_with_ns, + int_or_none, + parse_iso8601, +) + + +class BetIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' + _TESTS = [ + { + 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html', + 'info_dict': { + 'id': '740ab250-bb94-4a8a-8787-fe0de7c74471', + 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism', + 'ext': 'flv', + 'title': 'BET News Presents: A Conversation With President Obama', + 'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6', + 'duration': 1534, + 'timestamp': 1418075340, + 'upload_date': '20141208', + 'uploader': 'admin', + 'thumbnail': 're:(?i)^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', + 'info_dict': { + 'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d', + 'display_id': 'justice-for-ferguson-a-community-reacts', + 'ext': 'flv', + 'title': 'Justice for Ferguson: A Community Reacts', + 'description': 'A BET News special.', + 'duration': 1696, + 'timestamp': 1416942360, + 'upload_date': '20141125', + 'uploader': 'admin', + 'thumbnail': 're:(?i)^https?://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + media_url = compat_urllib_parse.unquote(self._search_regex( + [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], + webpage, 'media URL')) + + mrss = self._download_xml(media_url, display_id) + + item = mrss.find('./channel/item') + + NS_MAP = { + 'dc': 'http://purl.org/dc/elements/1.1/', + 'media': 'http://search.yahoo.com/mrss/', + 'ka': 'http://kickapps.com/karss', + } + + title = xpath_text(item, './title', 'title') + description = xpath_text( + item, './description', 'description', fatal=False) + + video_id = xpath_text(item, './guid', 'video id', fatal=False) + + timestamp = parse_iso8601(xpath_text( + item, xpath_with_ns('./dc:date', NS_MAP), + 'upload date', fatal=False)) + uploader = xpath_text( + item, xpath_with_ns('./dc:creator', NS_MAP), + 'uploader', fatal=False) + + media_content = item.find( + xpath_with_ns('./media:content', NS_MAP)) + duration = int_or_none(media_content.get('duration')) + smil_url = media_content.get('url') + + thumbnail = media_content.find( + xpath_with_ns('./media:thumbnail', NS_MAP)).get('url') + + formats = self._extract_smil_formats(smil_url, display_id) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'uploader': uploader, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 0d5889f..75d7448 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -5,8 +5,6 @@ import re from .common import InfoExtractor from ..utils import ( - compat_parse_qs, - ExtractorError, int_or_none, unified_strdate, ) @@ -29,10 +27,9 @@ class BiliBiliIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + video_code = self._search_regex( r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code') @@ -55,45 +52,38 @@ class BiliBiliIE(InfoExtractor): thumbnail = self._html_search_meta( 'thumbnailUrl', video_code, 'thumbnail', fatal=False) - player_params = compat_parse_qs(self._html_search_regex( - r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"', - webpage, 'player params')) + cid = self._search_regex(r'cid=(\d+)', webpage, 'cid') - if 'cid' in player_params: - cid = player_params['cid'][0] + lq_doc = self._download_xml( + 'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid, + video_id, + note='Downloading LQ video info' + ) + lq_durl = lq_doc.find('./durl') + formats = [{ + 'format_id': 'lq', + 'quality': 1, + 'url': lq_durl.find('./url').text, + 'filesize': int_or_none( + lq_durl.find('./size'), get_attr='text'), + }] - lq_doc = self._download_xml( - 'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid, - video_id, - note='Downloading LQ video info' - ) - lq_durl = lq_doc.find('.//durl') - formats = [{ - 'format_id': 'lq', - 'quality': 1, - 'url': lq_durl.find('./url').text, + hq_doc = self._download_xml( + 'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid, + video_id, + note='Downloading HQ video info', + fatal=False, + ) + if hq_doc is not False: + hq_durl = hq_doc.find('./durl') + formats.append({ + 'format_id': 'hq', + 'quality': 2, + 'ext': 'flv', + 'url': hq_durl.find('./url').text, 'filesize': int_or_none( - lq_durl.find('./size'), get_attr='text'), - }] - - hq_doc = self._download_xml( - 'http://interface.bilibili.cn/playurl?cid=%s' % cid, - video_id, - note='Downloading HQ video info', - fatal=False, - ) - if hq_doc is not False: - hq_durl = hq_doc.find('.//durl') - formats.append({ - 'format_id': 'hq', - 'quality': 2, - 'ext': 'flv', - 'url': hq_durl.find('./url').text, - 'filesize': int_or_none( - hq_durl.find('./size'), get_attr='text'), - }) - else: - raise ExtractorError('Unsupported player parameters: %r' % (player_params,)) + hq_durl.find('./size'), get_attr='text'), + }) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index da47f27..14b8141 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -4,13 +4,17 @@ import re from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( + +from ..compat import ( + compat_str, compat_urllib_request, - unescapeHTML, - parse_iso8601, compat_urlparse, +) +from ..utils import ( clean_html, - compat_str, + int_or_none, + parse_iso8601, + unescapeHTML, ) @@ -78,7 +82,25 @@ class BlipTVIE(SubtitlesInfoExtractor): 'uploader': 'NostalgiaCritic', 'uploader_id': '246467', } - } + }, + { + # https://github.com/rg3/youtube-dl/pull/4404 + 'note': 'Audio only', + 'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982', + 'md5': '76c0a56f24e769ceaab21fbb6416a351', + 'info_dict': { + 'id': '7103299', + 'ext': 'flv', + 'title': 'Weekly Manga Recap: Kingdom', + 'description': 'And then Shin breaks the enemy line, and he's all like HWAH! And then he slices a guy and it's all like FWASHING! And... it's really hard to describe the best parts of this series without breaking down into sound effects, okay?', + 'timestamp': 1417660321, + 'upload_date': '20141204', + 'uploader': 'The Rollo T', + 'uploader_id': '407429', + 'duration': 7251, + 'vcodec': 'none', + } + }, ] def _real_extract(self, url): @@ -145,11 +167,11 @@ class BlipTVIE(SubtitlesInfoExtractor): 'url': real_url, 'format_id': role, 'format_note': media_type, - 'vcodec': media_content.get(blip('vcodec')), + 'vcodec': media_content.get(blip('vcodec')) or 'none', 'acodec': media_content.get(blip('acodec')), 'filesize': media_content.get('filesize'), - 'width': int(media_content.get('width')), - 'height': int(media_content.get('height')), + 'width': int_or_none(media_content.get('width')), + 'height': int_or_none(media_content.get('height')), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 2c0e5ee..4bcc897 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -14,7 +14,6 @@ class BreakIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056', - 'md5': '33aa4ff477ecd124d18d7b5d23b87ce5', 'info_dict': { 'id': '2468056', 'ext': 'mp4', diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 2db7f9f..003152c 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -6,25 +6,26 @@ import json import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse, - find_xpath_attr, - fix_xml_ampersands, - compat_urlparse, - compat_str, - compat_urllib_request, +from ..compat import ( compat_parse_qs, + compat_str, + compat_urllib_parse, compat_urllib_parse_urlparse, - + compat_urllib_request, + compat_urlparse, +) +from ..utils import ( determine_ext, ExtractorError, - unsmuggle_url, + find_xpath_attr, + fix_xml_ampersands, unescapeHTML, + unsmuggle_url, ) class BrightcoveIE(InfoExtractor): - _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P<query>.*)' + _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)' _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' _TESTS = [ @@ -265,6 +266,7 @@ class BrightcoveIE(InfoExtractor): url = rend['defaultURL'] if not url: continue + ext = None if rend['remote']: url_comp = compat_urllib_parse_urlparse(url) if url_comp.path.endswith('.m3u8'): @@ -276,7 +278,7 @@ class BrightcoveIE(InfoExtractor): # akamaihd.net, but they don't use f4m manifests url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB' ext = 'flv' - else: + if ext is None: ext = determine_ext(url) size = rend.get('size') formats.append({ diff --git a/youtube_dl/extractor/buzzfeed.py b/youtube_dl/extractor/buzzfeed.py index a40a1bb..a5d2af1 100644 --- a/youtube_dl/extractor/buzzfeed.py +++ b/youtube_dl/extractor/buzzfeed.py @@ -33,7 +33,7 @@ class BuzzFeedIE(InfoExtractor): 'skip_download': True, # Got enough YouTube download tests }, 'info_dict': { - 'description': 'Munchkin the Teddy Bear is back !', + 'description': 're:Munchkin the Teddy Bear is back ?!', 'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill', }, 'playlist': [{ @@ -42,9 +42,9 @@ class BuzzFeedIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20141124', 'uploader_id': 'CindysMunchkin', - 'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu', + 'description': 're:© 2014 Munchkin the Shih Tzu', 'uploader': 'Munchkin the Shih Tzu', - 'title': 'Munchkin the Teddy Bear gets her exercise', + 'title': 're:Munchkin the Teddy Bear gets her exercise', }, }] }] diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 9873728..11d18d7 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -5,6 +5,8 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, + HEADRequest, unified_strdate, url_basename, qualities, @@ -76,6 +78,16 @@ class CanalplusIE(InfoExtractor): preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']) + fmt_url = next(iter(media.find('VIDEOS'))).text + if '/geo' in fmt_url.lower(): + response = self._request_webpage( + HEADRequest(fmt_url), video_id, + 'Checking if the video is georestricted') + if '/blocage' in response.geturl(): + raise ExtractorError( + 'The video is not available in your country', + expected=True) + formats = [] for fmt in media.find('VIDEOS'): format_url = fmt.text diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 97feb67..f70e090 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -3,55 +3,50 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..utils import ( +from .subtitles import SubtitlesInfoExtractor +from ..compat import ( compat_urllib_request, compat_urllib_parse, compat_urllib_parse_urlparse, +) +from ..utils import ( ExtractorError, + float_or_none, ) -class CeskaTelevizeIE(InfoExtractor): +class CeskaTelevizeIE(SubtitlesInfoExtractor): _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)' _TESTS = [ { - 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka', - 'info_dict': { - 'id': '213512120230004', - 'ext': 'flv', - 'title': 'První republika: Španělská chřipka', - 'duration': 3107.4, - }, - 'params': { - 'skip_download': True, # requires rtmpdump - }, - 'skip': 'Works only from Czech Republic.', - }, - { - 'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt', + 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220', 'info_dict': { - 'id': '20138143440', - 'ext': 'flv', - 'title': 'Tsatsiki, maminka a policajt', - 'duration': 6754.1, + 'id': '214411058091220', + 'ext': 'mp4', + 'title': 'Hyde Park Civilizace', + 'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 3350, }, 'params': { - 'skip_download': True, # requires rtmpdump + # m3u8 download + 'skip_download': True, }, - 'skip': 'Works only from Czech Republic.', }, { 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina', 'info_dict': { 'id': '14716', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'První republika: Zpěvačka z Dupárny Bobina', - 'duration': 90, + 'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 88.4, }, 'params': { - 'skip_download': True, # requires rtmpdump + # m3u8 download + 'skip_download': True, }, }, ] @@ -78,8 +73,9 @@ class CeskaTelevizeIE(InfoExtractor): 'requestSource': 'iVysilani', } - req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url', - data=compat_urllib_parse.urlencode(data)) + req = compat_urllib_request.Request( + 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', + data=compat_urllib_parse.urlencode(data)) req.add_header('Content-type', 'application/x-www-form-urlencoded') req.add_header('x-addr', '127.0.0.1') @@ -88,39 +84,72 @@ class CeskaTelevizeIE(InfoExtractor): playlistpage = self._download_json(req, video_id) - req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url'])) + playlist_url = playlistpage['url'] + if playlist_url == 'error_region': + raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) + + req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url)) req.add_header('Referer', url) - playlist = self._download_xml(req, video_id) + playlist = self._download_json(req, video_id) + item = playlist['playlist'][0] formats = [] - for i in playlist.find('smilRoot/body'): - if 'AD' not in i.attrib['id']: - base_url = i.attrib['base'] - parsedurl = compat_urllib_parse_urlparse(base_url) - duration = i.attrib['duration'] - - for video in i.findall('video'): - if video.attrib['label'] != 'AD': - format_id = video.attrib['label'] - play_path = video.attrib['src'] - vbr = int(video.attrib['system-bitrate']) - - formats.append({ - 'format_id': format_id, - 'url': base_url, - 'vbr': vbr, - 'play_path': play_path, - 'app': parsedurl.path[1:] + '?' + parsedurl.query, - 'rtmp_live': True, - 'ext': 'flv', - }) - + for format_id, stream_url in item['streamUrls'].items(): + formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4')) self._sort_formats(formats) + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + duration = float_or_none(item.get('duration')) + thumbnail = item.get('previewImageUrl') + + subtitles = {} + subs = item.get('subtitles') + if subs: + subtitles['cs'] = subs[0]['url'] + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles)) + return { 'id': episode_id, - 'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'), - 'duration': float(duration), + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, 'formats': formats, + 'subtitles': subtitles, } + + @staticmethod + def _fix_subtitles(subtitles): + """ Convert millisecond-based subtitles to SRT """ + if subtitles is None: + return subtitles # subtitles not requested + + def _msectotimecode(msec): + """ Helper utility to convert milliseconds to timecode """ + components = [] + for divider in [1000, 60, 60, 100]: + components.append(msec % divider) + msec //= divider + return "{3:02}:{2:02}:{1:02},{0:03}".format(*components) + + def _fix_subtitle(subtitle): + for line in subtitle.splitlines(): + m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line) + if m: + yield m.group(1) + start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:]) + yield "{0} --> {1}".format(start, stop) + else: + yield line + + fixed_subtitles = {} + for k, v in subtitles.items(): + fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v)) + return fixed_subtitles diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index 2a05813..3dfc24f 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -236,16 +236,17 @@ class Channel9IE(InfoExtractor): if contents is None: return contents - session_meta = {'session_code': self._extract_session_code(html), - 'session_day': self._extract_session_day(html), - 'session_room': self._extract_session_room(html), - 'session_speakers': self._extract_session_speakers(html), - } + session_meta = { + 'session_code': self._extract_session_code(html), + 'session_day': self._extract_session_day(html), + 'session_room': self._extract_session_room(html), + 'session_speakers': self._extract_session_speakers(html), + } for content in contents: content.update(session_meta) - return contents + return self.playlist_result(contents) def _extract_list(self, content_path): rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS') diff --git a/youtube_dl/extractor/cinchcast.py b/youtube_dl/extractor/cinchcast.py new file mode 100644 index 0000000..0c9a24b --- /dev/null +++ b/youtube_dl/extractor/cinchcast.py @@ -0,0 +1,52 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + xpath_text, +) + + +class CinchcastIE(InfoExtractor): + _VALID_URL = r'https?://player\.cinchcast\.com/.*?assetId=(?P<id>[0-9]+)' + _TEST = { + # Actual test is run in generic, look for undergroundwellness + 'url': 'http://player.cinchcast.com/?platformId=1&assetType=single&assetId=7141703', + 'only_matching': True, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + doc = self._download_xml( + 'http://www.blogtalkradio.com/playerasset/mrss?assetType=single&assetId=%s' % video_id, + video_id) + + item = doc.find('.//item') + title = xpath_text(item, './title', fatal=True) + date_str = xpath_text( + item, './{http://developer.longtailvideo.com/trac/}date') + upload_date = unified_strdate(date_str, day_first=False) + # duration is present but wrong + formats = [] + formats.append({ + 'format_id': 'main', + 'url': item.find( + './{http://search.yahoo.com/mrss/}content').attrib['url'], + }) + backup_url = xpath_text( + item, './{http://developer.longtailvideo.com/trac/}backupContent') + if backup_url: + formats.append({ + 'preference': 2, # seems to be more reliable + 'format_id': 'backup', + 'url': backup_url, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'upload_date': upload_date, + 'formats': formats, + } diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 710d500..3145b30 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -2,12 +2,10 @@ from __future__ import unicode_literals import json -import re from .common import InfoExtractor from ..utils import ( ExtractorError, - int_or_none, ) @@ -15,23 +13,24 @@ class CNETIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' _TEST = { 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', - 'md5': '041233212a0d06b179c87cbcca1577b8', 'info_dict': { 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Hands-on with Microsoft Windows 8.1 Update', 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', 'thumbnail': 're:^http://.*/flmswindows8.jpg$', - 'uploader_id': 'sarah.mitroff@cbsinteractive.com', + 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861', 'uploader': 'Sarah Mitroff', + }, + 'params': { + 'skip_download': 'requires rtmpdump', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - + display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) + data_json = self._html_search_regex( r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'", webpage, 'data json') @@ -42,37 +41,31 @@ class CNETIE(InfoExtractor): if not vdata: raise ExtractorError('Cannot find video data') + mpx_account = data['config']['players']['default']['mpx_account'] + vid = vdata['files']['rtmp'] + tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid) + video_id = vdata['id'] title = vdata.get('headline') if title is None: title = vdata.get('title') if title is None: raise ExtractorError('Cannot find title!') - description = vdata.get('dek') thumbnail = vdata.get('image', {}).get('path') author = vdata.get('author') if author: uploader = '%s %s' % (author['firstName'], author['lastName']) - uploader_id = author.get('email') + uploader_id = author.get('id') else: uploader = None uploader_id = None - formats = [{ - 'format_id': '%s-%s-%s' % ( - f['type'], f['format'], - int_or_none(f.get('bitrate'), 1000, default='')), - 'url': f['uri'], - 'tbr': int_or_none(f.get('bitrate'), 1000), - } for f in vdata['files']['data']] - self._sort_formats(formats) - return { + '_type': 'url_transparent', + 'url': tp_link, 'id': video_id, 'display_id': display_id, 'title': title, - 'formats': formats, - 'description': description, 'uploader': uploader, 'uploader_id': uploader_id, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 81142ee..93e8d0d 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -11,14 +11,14 @@ from ..utils import ( class CNNIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/ - (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))''' + _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/ + (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))''' _TESTS = [{ 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', 'md5': '3e6121ea48df7e2259fe73a0628605c4', 'info_dict': { - 'id': 'sports_2013_06_09_nadal-1-on-1.cnn', + 'id': 'sports/2013/06/09/nadal-1-on-1.cnn', 'ext': 'mp4', 'title': 'Nadal wins 8th French Open title', 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', @@ -35,6 +35,16 @@ class CNNIE(InfoExtractor): "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", "upload_date": "20130821", } + }, { + 'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html', + 'md5': 'f14d02ebd264df951feb2400e2c25a1b', + 'info_dict': { + 'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln', + 'ext': 'mp4', + 'title': 'Nashville Ep. 1: Hand crafted skateboards', + 'description': 'md5:e7223a503315c9f150acac52e76de086', + 'upload_date': '20141222', + } }] def _real_extract(self, url): @@ -127,3 +137,28 @@ class CNNBlogsIE(InfoExtractor): 'url': cnn_url, 'ie_key': CNNIE.ie_key(), } + + +class CNNArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)' + _TEST = { + 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/', + 'md5': '275b326f85d80dff7592a9820f5dc887', + 'info_dict': { + 'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn', + 'ext': 'mp4', + 'title': 'Obama: We\'re not going to be intimidated', + 'description': 'md5:e735586f3dc936075fa654a4d91b21f9', + 'upload_date': '20141220', + }, + 'add_ie': ['CNN'], + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, url_basename(url)) + cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') + return { + '_type': 'url', + 'url': 'http://cnn.com/video/?/video/' + cnn_url, + 'ie_key': CNNIE.ie_key(), + } diff --git a/youtube_dl/extractor/collegerama.py b/youtube_dl/extractor/collegerama.py new file mode 100644 index 0000000..fedd484 --- /dev/null +++ b/youtube_dl/extractor/collegerama.py @@ -0,0 +1,92 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..compat import compat_urllib_request +from ..utils import ( + float_or_none, + int_or_none, +) + + +class CollegeRamaIE(InfoExtractor): + _VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)' + _TESTS = [ + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d', + 'md5': '481fda1c11f67588c0d9d8fbdced4e39', + 'info_dict': { + 'id': '585a43626e544bdd97aeb71a0ec907a01d', + 'ext': 'mp4', + 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.', + 'description': '', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 7713.088, + 'timestamp': 1413309600, + 'upload_date': '20141014', + }, + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4', + 'md5': 'ef1fdded95bdf19b12c5999949419c92', + 'info_dict': { + 'id': '86a9ea9f53e149079fbdb4202b521ed21d', + 'ext': 'wmv', + 'title': '64ste Vakantiecursus: Afvalwater', + 'description': 'md5:7fd774865cc69d972f542b157c328305', + 'duration': 10853, + 'timestamp': 1326446400, + 'upload_date': '20120113', + }, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + player_options_request = { + "getPlayerOptionsRequest": { + "ResourceId": video_id, + "QueryString": "", + } + } + + request = compat_urllib_request.Request( + 'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions', + json.dumps(player_options_request)) + request.add_header('Content-Type', 'application/json') + + player_options = self._download_json(request, video_id) + + presentation = player_options['d']['Presentation'] + title = presentation['Title'] + description = presentation.get('Description') + thumbnail = None + duration = float_or_none(presentation.get('Duration'), 1000) + timestamp = int_or_none(presentation.get('UnixTime'), 1000) + + formats = [] + for stream in presentation['Streams']: + for video in stream['VideoUrls']: + thumbnail_url = stream.get('ThumbnailUrl') + if thumbnail_url: + thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url + format_id = video['MediaType'] + if format_id == 'SS': + continue + formats.append({ + 'url': video['Location'], + 'format_id': format_id, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + } diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py new file mode 100644 index 0000000..9c25b22 --- /dev/null +++ b/youtube_dl/extractor/comcarcoff.py @@ -0,0 +1,57 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import parse_iso8601 + + +class ComCarCoffIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)' + _TESTS = [{ + 'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/', + 'info_dict': { + 'id': 'miranda-sings-happy-thanksgiving-miranda', + 'ext': 'mp4', + 'upload_date': '20141127', + 'timestamp': 1417107600, + 'title': 'Happy Thanksgiving Miranda', + 'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.', + 'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg', + }, + 'params': { + 'skip_download': 'requires ffmpeg', + } + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + if not display_id: + display_id = 'comediansincarsgettingcoffee.com' + webpage = self._download_webpage(url, display_id) + + full_data = json.loads(self._search_regex( + r'<script type="application/json" id="videoData">(?P<json>.+?)</script>', + webpage, 'full data json')) + + video_id = full_data['activeVideo']['video'] + video_data = full_data['videos'][video_id] + thumbnails = [{ + 'url': video_data['images']['thumb'], + }, { + 'url': video_data['images']['poster'], + }] + formats = self._extract_m3u8_formats( + video_data['mediaUrl'], video_id, ext='mp4') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': video_data['title'], + 'description': video_data.get('description'), + 'timestamp': parse_iso8601(video_data.get('pubDate')), + 'thumbnails': thumbnails, + 'formats': formats, + 'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))), + } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 2e3ef3f..8d27af5 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .mtv import MTVServicesInfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urllib_parse, +) +from ..utils import ( ExtractorError, float_or_none, unified_strdate, @@ -48,7 +50,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): )| (?P<interview> extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) - (?:[?#].*|$)''' + ''' _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', @@ -82,6 +84,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', 'only_matching': True, }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo', + 'only_matching': True, + }, { 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', 'only_matching': True, }, { diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e80a2da..03f3f18 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -21,6 +21,7 @@ from ..compat import ( compat_str, ) from ..utils import ( + age_restricted, clean_html, compiled_regex_type, ExtractorError, @@ -40,7 +41,7 @@ class InfoExtractor(object): information about the video (or videos) the URL refers to. This information includes the real video URL, the video title, author and others. The information is stored in a dictionary which is then - passed to the FileDownloader. The FileDownloader processes this + passed to the YoutubeDL. The YoutubeDL processes this information possibly downloading the video to the file system, among other possible outcomes. @@ -92,6 +93,8 @@ class InfoExtractor(object): by this field, regardless of all other values. -1 for default (order by other properties), -2 or smaller for less than default. + < -1000 to hide the format (if there is + another one which is strictly better) * language_preference Is this in the correct requested language? 10 if it's what the URL is about, @@ -111,6 +114,9 @@ class InfoExtractor(object): to add to the request. * http_post_data Additional data to send with a POST request. + * stretched_ratio If given and not 1, indicates that the + video's pixels are not square. + width : height ratio as float. url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) @@ -118,6 +124,7 @@ class InfoExtractor(object): The following fields are optional: + alt_title: A secondary title of the video. display_id An alternative identifier for the video, not necessarily unique, but available before title. Typically, id is something like "4234987", title "Dancing naked mole rats", @@ -129,7 +136,7 @@ class InfoExtractor(object): * "resolution" (optional, string "{width}x{height"}, deprecated) thumbnail: Full URL to a video thumbnail image. - description: One-line video description. + description: Full video description. uploader: Full name of the video uploader. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). @@ -143,6 +150,17 @@ class InfoExtractor(object): like_count: Number of positive ratings of the video dislike_count: Number of negative ratings of the video comment_count: Number of comments on the video + comments: A list of comments, each with one or more of the following + properties (all but one of text or html optional): + * "author" - human-readable name of the comment author + * "author_id" - user ID of the comment author + * "id" - Comment ID + * "html" - Comment as HTML + * "text" - Plain text of the comment + * "timestamp" - UNIX timestamp of comment + * "parent" - ID of the comment this one is replying to. + Set to "root" to indicate that this is a + comment to the original video. age_limit: Age restriction for the video, as an integer (years) webpage_url: The url to the video webpage, if given to youtube-dl it should allow to get the same result again. (It will be set @@ -158,8 +176,8 @@ class InfoExtractor(object): _type "playlist" indicates multiple videos. - There must be a key "entries", which is a list or a PagedList object, each - element of which is a valid dictionary under this specfication. + There must be a key "entries", which is a list, an iterable, or a PagedList + object, each element of which is a valid dictionary by this specification. Additionally, playlists can have "title" and "id" attributes with the same semantics as videos (see above). @@ -174,9 +192,10 @@ class InfoExtractor(object): _type "url" indicates that the video must be extracted from another location, possibly by a different extractor. Its only required key is: "url" - the next URL to extract. - - Additionally, it may have properties believed to be identical to the - resolved entity, for example "title" if the title of the referred video is + The key "ie_key" can be set to the class name (minus the trailing "IE", + e.g. "Youtube") if the extractor class is known in advance. + Additionally, the dictionary may have any properties of the resolved entity + known in advance, for example "title" if the title of the referred video is known ahead of time. @@ -360,9 +379,19 @@ class InfoExtractor(object): return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5): """ Returns the data of the page as a string """ - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + success = False + try_count = 0 + while success is False: + try: + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + success = True + except compat_http_client.IncompleteRead as e: + try_count += 1 + if try_count >= tries: + raise e + self._sleep(timeout, video_id) if res is False: return res else: @@ -390,6 +419,10 @@ class InfoExtractor(object): url_or_request, video_id, note, errnote, fatal=fatal) if (not fatal) and json_string is False: return None + return self._parse_json( + json_string, video_id, transform_source=transform_source, fatal=fatal) + + def _parse_json(self, json_string, video_id, transform_source=None, fatal=True): if transform_source: json_string = transform_source(json_string) try: @@ -439,7 +472,7 @@ class InfoExtractor(object): return video_info @staticmethod - def playlist_result(entries, playlist_id=None, playlist_title=None): + def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None): """Returns a playlist""" video_info = {'_type': 'playlist', 'entries': entries} @@ -447,6 +480,8 @@ class InfoExtractor(object): video_info['id'] = playlist_id if playlist_title: video_info['title'] = playlist_title + if playlist_description: + video_info['description'] = playlist_description return video_info def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): @@ -581,9 +616,9 @@ class InfoExtractor(object): if display_name is None: display_name = name return self._html_search_regex( - r'''(?ix)<meta + r'''(?isx)<meta (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1) - [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name), + [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name), html, display_name, fatal=fatal, group='content', **kwargs) def _dc_search_uploader(self, html): @@ -707,8 +742,14 @@ class InfoExtractor(object): 'Unable to download f4m manifest') formats = [] + manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') + if not media_nodes: + manifest_version = '2.0' + media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') for i, media_el in enumerate(media_nodes): + if manifest_version == '2.0': + manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href') tbr = int_or_none(media_el.attrib.get('bitrate')) format_id = 'f4m-%d' % (i if tbr is None else tbr) formats.append({ @@ -790,6 +831,49 @@ class InfoExtractor(object): self._sort_formats(formats) return formats + # TODO: improve extraction + def _extract_smil_formats(self, smil_url, video_id): + smil = self._download_xml( + smil_url, video_id, 'Downloading SMIL file', + 'Unable to download SMIL file') + + base = smil.find('./head/meta').get('base') + + formats = [] + rtmp_count = 0 + for video in smil.findall('./body/switch/video'): + src = video.get('src') + if not src: + continue + bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) + width = int_or_none(video.get('width')) + height = int_or_none(video.get('height')) + proto = video.get('proto') + if not proto: + if base: + if base.startswith('rtmp'): + proto = 'rtmp' + elif base.startswith('http'): + proto = 'http' + ext = video.get('ext') + if proto == 'm3u8': + formats.extend(self._extract_m3u8_formats(src, video_id, ext)) + elif proto == 'rtmp': + rtmp_count += 1 + streamer = video.get('streamer') or base + formats.append({ + 'url': streamer, + 'play_path': src, + 'ext': 'flv', + 'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate), + 'tbr': bitrate, + 'width': width, + 'height': height, + }) + self._sort_formats(formats) + + return formats + def _live_title(self, name): """ Generate the title for a live video """ now = datetime.datetime.now() @@ -819,10 +903,40 @@ class InfoExtractor(object): return res def _set_cookie(self, domain, name, value, expire_time=None): - cookie = compat_cookiejar.Cookie(0, name, value, None, None, domain, None, + cookie = compat_cookiejar.Cookie( + 0, name, value, None, None, domain, None, None, '/', True, False, expire_time, '', None, None, None) self._downloader.cookiejar.set_cookie(cookie) + def get_testcases(self, include_onlymatching=False): + t = getattr(self, '_TEST', None) + if t: + assert not hasattr(self, '_TESTS'), \ + '%s has _TEST and _TESTS' % type(self).__name__ + tests = [t] + else: + tests = getattr(self, '_TESTS', []) + for t in tests: + if not include_onlymatching and t.get('only_matching', False): + continue + t['name'] = type(self).__name__[:-len('IE')] + yield t + + def is_suitable(self, age_limit): + """ Test whether the extractor is generally suitable for the given + age limit (i.e. pornographic sites are not, all others usually are) """ + + any_restricted = False + for tc in self.get_testcases(include_onlymatching=False): + if 'playlist' in tc: + tc = tc['playlist'][0] + is_restricted = age_restricted( + tc.get('info_dict', {}).get('age_limit'), age_limit) + if not is_restricted: + return True + any_restricted = any_restricted or is_restricted + return not any_restricted + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/commonmistakes.py b/youtube_dl/extractor/commonmistakes.py new file mode 100644 index 0000000..75c0690 --- /dev/null +++ b/youtube_dl/extractor/commonmistakes.py @@ -0,0 +1,29 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class CommonMistakesIE(InfoExtractor): + IE_DESC = False # Do not list + _VALID_URL = r'''(?x) + (?:url|URL) + ''' + + _TESTS = [{ + 'url': 'url', + 'only_matching': True, + }, { + 'url': 'URL', + 'only_matching': True, + }] + + def _real_extract(self, url): + msg = ( + 'You\'ve asked youtube-dl to download the URL "%s". ' + 'That doesn\'t make any sense. ' + 'Simply remove the parameter in your command or configuration.' + ) % url + if self._downloader.params.get('verbose'): + msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.' + raise ExtractorError(msg, expected=True) diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index 7a7e793..3db4db4 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -5,12 +5,14 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - orderedSet, compat_urllib_parse_urlparse, compat_urlparse, ) +from ..utils import ( + orderedSet, +) class CondeNastIE(InfoExtractor): diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index d7e2b84..1680f53 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -10,10 +10,12 @@ import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( + ExtractorError, bytes_to_intlist, intlist_to_bytes, unified_strdate, @@ -27,10 +29,9 @@ from .common import InfoExtractor class CrunchyrollIE(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' - _TEST = { + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' + _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', - #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412', 'info_dict': { 'id': '645513', 'ext': 'flv', @@ -45,7 +46,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor): # rtmp 'skip_download': True, }, - } + }, { + 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', + 'only_matching': True, + }] _FORMAT_IDS = { '360': ('60', '106'), @@ -224,7 +228,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False) formats = [] - for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): + for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 5411066..955119d 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -27,7 +27,6 @@ class CSpanIE(InfoExtractor): 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', # For whatever reason, the served video alternates between # two different ones - #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c', 'info_dict': { 'id': '340723', 'ext': 'mp4', diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 936c13c..cf5841a 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -8,13 +8,15 @@ import itertools from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( - compat_urllib_request, +from ..compat import ( compat_str, + compat_urllib_request, +) +from ..utils import ( + ExtractorError, + int_or_none, orderedSet, str_to_int, - int_or_none, - ExtractorError, unescapeHTML, ) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 45d66e2..934da76 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -5,7 +5,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -38,7 +38,7 @@ class DaumIE(InfoExtractor): canonical_url = 'http://tvpot.daum.net/v/%s' % video_id webpage = self._download_webpage(canonical_url, video_id) full_id = self._search_regex( - r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]', + r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']', webpage, 'full id') query = compat_urllib_parse.urlencode({'vid': full_id}) info = self._download_xml( diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py index 1d3e2ff..2122176 100644 --- a/youtube_dl/extractor/dbtv.py +++ b/youtube_dl/extractor/dbtv.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( float_or_none, int_or_none, @@ -61,7 +62,7 @@ class DBTVIE(InfoExtractor): self._sort_formats(formats) return { - 'id': video['id'], + 'id': compat_str(video['id']), 'display_id': display_id, 'title': video['title'], 'description': clean_html(video['desc']), diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 52c2d7d..d3e6675 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -1,47 +1,45 @@ from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + int_or_none, +) class DiscoveryIE(InfoExtractor): - _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' + _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?' _TEST = { 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', - 'md5': 'e12614f9ee303a6ccef415cb0793eba2', + 'md5': '3c69d77d9b0d82bfd5e5932a60f26504', 'info_dict': { - 'id': '614784', - 'ext': 'mp4', - 'title': 'MythBusters: Mission Impossible Outtakes', + 'id': 'mission-impossible-outtakes', + 'ext': 'flv', + 'title': 'Mission Impossible Outtakes', 'description': ('Watch Jamie Hyneman and Adam Savage practice being' ' each other -- to the point of confusing Jamie\'s dog -- and ' 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' ' back.'), 'duration': 156, + 'timestamp': 1303099200, + 'upload_date': '20110418', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_list_json = self._search_regex(r'var videoListJSON = ({.*?});', - webpage, 'video list', flags=re.DOTALL) - video_list = json.loads(video_list_json) - info = video_list['clips'][0] - formats = [] - for f in info['mp4']: - formats.append( - {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])}) + info = self._parse_json(self._search_regex( + r'(?s)<script type="application/ld\+json">(.*?)</script>', + webpage, 'video info'), video_id) return { - 'id': info['contentId'], - 'title': video_list['name'], - 'formats': formats, - 'description': info['videoCaption'], - 'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'), - 'duration': info['duration'], + 'id': video_id, + 'title': info['name'], + 'url': info['contentURL'], + 'description': info.get('description'), + 'thumbnail': info.get('thumbnailUrl'), + 'timestamp': parse_iso8601(info.get('uploadDate')), + 'duration': int_or_none(info.get('duration')), } diff --git a/youtube_dl/extractor/drbonanza.py b/youtube_dl/extractor/drbonanza.py new file mode 100644 index 0000000..7626219 --- /dev/null +++ b/youtube_dl/extractor/drbonanza.py @@ -0,0 +1,131 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) + + +class DRBonanzaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)' + + _TESTS = [{ + 'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517', + 'md5': 'fe330252ddea607635cf2eb2c99a0af3', + 'info_dict': { + 'id': '65517', + 'ext': 'mp4', + 'title': 'Talkshowet - Leonard Cohen', + 'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + 'timestamp': 1295537932, + 'upload_date': '20110120', + 'duration': 3664, + }, + }, { + 'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410', + 'md5': '6dfe039417e76795fb783c52da3de11d', + 'info_dict': { + 'id': '59410', + 'ext': 'mp3', + 'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission', + 'description': 'md5:501e5a195749480552e214fbbed16c4e', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + 'timestamp': 1223274900, + 'upload_date': '20081006', + 'duration': 7369, + }, + }] + + def _real_extract(self, url): + url_id = self._match_id(url) + webpage = self._download_webpage(url, url_id) + + if url_id: + info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json')) + else: + # Just fetch the first video on that page + info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json')) + + asset_id = str(info['AssetId']) + title = info['Title'].rstrip(' \'\"-,.:;!?') + duration = int_or_none(info.get('Duration'), scale=1000) + # First published online. "FirstPublished" contains the date for original airing. + timestamp = parse_iso8601( + re.sub(r'\.\d+$', '', info['Created'])) + + def parse_filename_info(url): + match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url) + if match: + return { + 'width': int(match.group('width')), + 'height': int(match.group('height')), + 'vbr': int(match.group('bitrate')), + 'ext': match.group('ext') + } + match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url) + if match: + return { + 'vbr': int(match.group('bitrate')), + 'ext': match.group(2) + } + return {} + + video_types = ['VideoHigh', 'VideoMid', 'VideoLow'] + preferencemap = { + 'VideoHigh': -1, + 'VideoMid': -2, + 'VideoLow': -3, + 'Audio': -4, + } + + formats = [] + for file in info['Files']: + if info['Type'] == "Video": + if file['Type'] in video_types: + format = parse_filename_info(file['Location']) + format.update({ + 'url': file['Location'], + 'format_id': file['Type'].replace('Video', ''), + 'preference': preferencemap.get(file['Type'], -10), + }) + formats.append(format) + elif file['Type'] == "Thumb": + thumbnail = file['Location'] + elif info['Type'] == "Audio": + if file['Type'] == "Audio": + format = parse_filename_info(file['Location']) + format.update({ + 'url': file['Location'], + 'format_id': file['Type'], + 'vcodec': 'none', + }) + formats.append(format) + elif file['Type'] == "Thumb": + thumbnail = file['Location'] + + description = '%s\n%s\n%s\n' % ( + info['Description'], info['Actors'], info['Colophon']) + + for f in formats: + f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/') + f['url'] = f['url'].replace('mp4:bonanza', 'bonanza') + self._sort_formats(formats) + + display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id + display_id = re.sub(r'-+', '-', display_id) + + return { + 'id': asset_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + } diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index 93b3c9f..c44adb1 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -6,7 +6,7 @@ from ..utils import parse_iso8601 class DRTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)' + _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)' _TEST = { 'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8', diff --git a/youtube_dl/extractor/dvtv.py b/youtube_dl/extractor/dvtv.py new file mode 100644 index 0000000..c1a4bc7 --- /dev/null +++ b/youtube_dl/extractor/dvtv.py @@ -0,0 +1,125 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + unescapeHTML, + ExtractorError, +) + + +class DVTVIE(InfoExtractor): + IE_NAME = 'dvtv' + IE_DESC = 'http://video.aktualne.cz/' + + _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})' + + _TESTS = [{ + 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/', + 'md5': '67cb83e4a955d36e1b5d31993134a0c2', + 'info_dict': { + 'id': 'dc0768de855511e49e4b0025900fea04', + 'ext': 'mp4', + 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně', + } + }, { + 'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/', + 'md5': '6388f1941b48537dbd28791f712af8bf', + 'info_dict': { + 'id': '72c02230849211e49f60002590604f2e', + 'ext': 'mp4', + 'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala', + } + }, { + 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/', + 'info_dict': { + 'title': 'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci', + 'id': '973eb3bc854e11e498be002590604f2e', + }, + 'playlist': [{ + 'md5': 'da7ca6be4935532241fa9520b3ad91e4', + 'info_dict': { + 'id': 'b0b40906854d11e4bdad0025900fea04', + 'ext': 'mp4', + 'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne' + } + }, { + 'md5': '5f7652a08b05009c1292317b449ffea2', + 'info_dict': { + 'id': '420ad9ec854a11e4bdad0025900fea04', + 'ext': 'mp4', + 'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka' + } + }, { + 'md5': '498eb9dfa97169f409126c617e2a3d64', + 'info_dict': { + 'id': '95d35580846a11e4b6d20025900fea04', + 'ext': 'mp4', + 'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?' + } + }, { + 'md5': 'b8dc6b744844032dab6ba3781a7274b9', + 'info_dict': { + 'id': '6fe14d66853511e4833a0025900fea04', + 'ext': 'mp4', + 'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády' + } + }], + }, { + 'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/', + 'only_matching': True, + }] + + def _parse_video_metadata(self, js, video_id): + metadata = self._parse_json(js, video_id, transform_source=js_to_json) + + formats = [] + for video in metadata['sources']: + ext = video['type'][6:] + formats.append({ + 'url': video['file'], + 'ext': ext, + 'format_id': '%s-%s' % (ext, video['label']), + 'height': int(video['label'].rstrip('p')), + 'fps': 25, + }) + + self._sort_formats(formats) + + return { + 'id': metadata['mediaid'], + 'title': unescapeHTML(metadata['title']), + 'thumbnail': self._proto_relative_url(metadata['image'], 'http:'), + 'formats': formats + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + # single video + item = self._search_regex( + r"(?s)embedData[0-9a-f]{32}\['asset'\]\s*=\s*(\{.+?\});", + webpage, 'video', default=None, fatal=False) + + if item: + return self._parse_video_metadata(item, video_id) + + # playlist + items = re.findall( + r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);", + webpage) + + if items: + return { + '_type': 'playlist', + 'id': video_id, + 'title': self._og_search_title(webpage), + 'entries': [self._parse_video_metadata(i, video_id) for i in items] + } + + raise ExtractorError('Could not find neither video nor playlist') diff --git a/youtube_dl/extractor/ebaumsworld.py b/youtube_dl/extractor/ebaumsworld.py index 63c2549..b6bfd2b 100644 --- a/youtube_dl/extractor/ebaumsworld.py +++ b/youtube_dl/extractor/ebaumsworld.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -20,8 +18,7 @@ class EbaumsWorldIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) config = self._download_xml( 'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id) video_url = config.find('file').text diff --git a/youtube_dl/extractor/echomsk.py b/youtube_dl/extractor/echomsk.py new file mode 100644 index 0000000..d2d9404 --- /dev/null +++ b/youtube_dl/extractor/echomsk.py @@ -0,0 +1,46 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class EchoMskIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.echo.msk.ru/sounds/1464134.html', + 'md5': '2e44b3b78daff5b458e4dbc37f191f7c', + 'info_dict': { + 'id': '1464134', + 'ext': 'mp3', + 'title': 'Особое мнение - 29 декабря 2014, 19:08', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + audio_url = self._search_regex( + r'<a rel="mp3" href="([^"]+)">', webpage, 'audio URL') + + title = self._html_search_regex( + r'<a href="/programs/[^"]+" target="_blank">([^<]+)</a>', + webpage, 'title') + + air_date = self._html_search_regex( + r'(?s)<div class="date">(.+?)</div>', + webpage, 'date', fatal=False, default=None) + + if air_date: + air_date = re.sub(r'(\s)\1+', r'\1', air_date) + if air_date: + title = '%s - %s' % (title, air_date) + + return { + 'id': video_id, + 'url': audio_url, + 'title': title, + } diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index b766e17..9cb1bf3 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,8 +1,6 @@ from __future__ import unicode_literals -import re - -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) from .common import InfoExtractor @@ -24,11 +22,10 @@ class EHowIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', - webpage, 'video URL') + video_url = self._search_regex( + r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL') final_url = compat_urllib_parse.unquote(video_url) uploader = self._html_search_meta('uploader', webpage) title = self._og_search_title(webpage).replace(' | eHow', '') diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index f4c1e2a..fb5dbbe 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -6,9 +6,12 @@ import random import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, ) +from ..utils import ( + ExtractorError, +) class EightTracksIE(InfoExtractor): @@ -112,14 +115,29 @@ class EightTracksIE(InfoExtractor): session = str(random.randint(0, 1000000000)) mix_id = data['id'] track_count = data['tracks_count'] + duration = data['duration'] + avg_song_duration = float(duration) / track_count first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) next_url = first_url entries = [] + for i in range(track_count): - api_json = self._download_webpage( - next_url, playlist_id, - note='Downloading song information %d/%d' % (i + 1, track_count), - errnote='Failed to download song information') + api_json = None + download_tries = 0 + + while api_json is None: + try: + api_json = self._download_webpage( + next_url, playlist_id, + note='Downloading song information %d/%d' % (i + 1, track_count), + errnote='Failed to download song information') + except ExtractorError: + if download_tries > 3: + raise + else: + download_tries += 1 + self._sleep(avg_song_duration, playlist_id) + api_data = json.loads(api_json) track_data = api_data['set']['track'] info = { @@ -131,6 +149,7 @@ class EightTracksIE(InfoExtractor): 'ext': 'm4a', } entries.append(info) + next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % ( session, mix_id, track_data['id']) return { diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py index 3e79236..fc92ff8 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re import json from .common import InfoExtractor @@ -12,32 +11,49 @@ from ..utils import ( class EllenTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)' + _TESTS = [{ 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', 'md5': 'e4af06f3bf0d5f471921a18db5764642', 'info_dict': { 'id': '0-7jqrsr18', 'ext': 'mp4', 'title': 'What\'s Wrong with These Photos? A Whole Lot', + 'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6', 'timestamp': 1406876400, 'upload_date': '20140801', } - } + }, { + 'url': 'http://ellentube.com/videos/0-dvzmabd5/', + 'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb', + 'info_dict': { + 'id': '0-dvzmabd5', + 'ext': 'mp4', + 'title': '1 year old twin sister makes her brother laugh', + 'description': '1 year old twin sister makes her brother laugh', + 'timestamp': 1419542075, + 'upload_date': '20141225', + } + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + video_url = self._html_search_meta('VideoURL', webpage, 'url') + title = self._og_search_title(webpage, default=None) or self._search_regex( + r'pageName\s*=\s*"([^"]+)"', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') or self._og_search_description(webpage) timestamp = parse_iso8601(self._search_regex( r'<span class="publish-date"><time datetime="([^"]+)">', webpage, 'timestamp')) return { 'id': video_id, - 'title': self._og_search_title(webpage), - 'url': self._html_search_meta('VideoURL', webpage, 'url'), + 'url': video_url, + 'title': title, + 'description': description, 'timestamp': timestamp, } @@ -55,8 +71,7 @@ class EllenTVClipsIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) playlist = self._extract_playlist(webpage) diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py index 4277202..00a69e6 100644 --- a/youtube_dl/extractor/elpais.py +++ b/youtube_dl/extractor/elpais.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import unified_strdate @@ -24,9 +22,7 @@ class ElPaisIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) prefix = self._html_search_regex( diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py index 92ada81..4ea37eb 100644 --- a/youtube_dl/extractor/engadget.py +++ b/youtube_dl/extractor/engadget.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .fivemin import FiveMinIE from ..utils import ( url_basename, ) @@ -27,11 +26,10 @@ class EngadgetIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) if video_id is not None: - return FiveMinIE._build_result(video_id) + return self.url_result('5min:%s' % video_id) else: title = url_basename(url) webpage = self._download_webpage(url, title) @@ -39,5 +37,5 @@ class EngadgetIE(InfoExtractor): return { '_type': 'playlist', 'title': title, - 'entries': [FiveMinIE._build_result(id) for id in ids] + 'entries': [self.url_result('5min:%s' % vid) for vid in ids] } diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py new file mode 100644 index 0000000..79e2fbd --- /dev/null +++ b/youtube_dl/extractor/eroprofile.py @@ -0,0 +1,45 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class EroProfileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore', + 'md5': 'c26f351332edf23e1ea28ce9ec9de32f', + 'info_dict': { + 'id': '3733775', + 'display_id': 'sexy-babe-softcore', + 'ext': 'm4v', + 'title': 'sexy babe softcore', + 'thumbnail': 're:https?://.*\.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'], + webpage, 'video id', default=None) + + video_url = self._search_regex( + r'<source src="([^"]+)', webpage, 'video url') + title = self._html_search_regex( + r'Title:</th><td>([^<]+)</td>', webpage, 'title') + thumbnail = self._search_regex( + r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', + webpage, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 476fc22..e240cb8 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -3,9 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index d237a82..d872d82 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -3,8 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index aacbf14..36ba331 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -3,16 +3,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, +) +from ..utils import ( str_to_int, ) class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', @@ -31,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 2139f68..1ad4e77 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -13,9 +13,10 @@ from ..compat import ( compat_urllib_request, ) from ..utils import ( - urlencode_postdata, ExtractorError, + int_or_none, limit_length, + urlencode_postdata, ) @@ -36,7 +37,6 @@ class FacebookIE(InfoExtractor): 'info_dict': { 'id': '637842556329505', 'ext': 'mp4', - 'duration': 38, 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', } }, { @@ -107,9 +107,7 @@ class FacebookIE(InfoExtractor): self._login() def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'https://www.facebook.com/video/video.php?v=%s' % video_id webpage = self._download_webpage(url, video_id) @@ -149,6 +147,6 @@ class FacebookIE(InfoExtractor): 'id': video_id, 'title': video_title, 'url': video_url, - 'duration': int(video_data['video_duration']), - 'thumbnail': video_data['thumbnail_src'], + 'duration': int_or_none(video_data.get('video_duration')), + 'thumbnail': video_data.get('thumbnail_src'), } diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index 6f5d235..81ceace 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -1,19 +1,20 @@ #! -*- coding: utf-8 -*- from __future__ import unicode_literals -import re import hashlib from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_request, compat_urlparse, ) +from ..utils import ( + ExtractorError, +) class FC2IE(InfoExtractor): - _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)' + _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)' IE_NAME = 'fc2' _TEST = { 'url': 'http://video.fc2.com/en/content/20121103kUan1KHs', @@ -26,9 +27,7 @@ class FC2IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) self._downloader.cookiejar.clear_session_cookies() # must clear diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py index af439cc..3191116 100644 --- a/youtube_dl/extractor/firedrive.py +++ b/youtube_dl/extractor/firedrive.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) +from ..utils import ( + ExtractorError, +) class FiredriveIE(InfoExtractor): @@ -28,11 +30,8 @@ class FiredriveIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'http://firedrive.com/file/%s' % video_id - webpage = self._download_webpage(url, video_id) if re.search(self._FILE_DELETED_REGEX, webpage) is not None: diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index f9c127c..5b24b92 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -1,11 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urllib_parse, +) +from ..utils import ( ExtractorError, ) @@ -13,7 +13,7 @@ from ..utils import ( class FiveMinIE(InfoExtractor): IE_NAME = '5min' _VALID_URL = r'''(?x) - (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=| + (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=| 5min:) (?P<id>\d+) ''' @@ -41,13 +41,8 @@ class FiveMinIE(InfoExtractor): }, ] - @classmethod - def _build_result(cls, video_id): - return cls.url_result('5min:%s' % video_id, cls.ie_key()) - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id embed_page = self._download_webpage(embed_url, video_id, 'Downloading embed page') diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index d09d1c1..190d9f9 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -13,7 +13,7 @@ from ..utils import ( class FKTVIE(InfoExtractor): IE_NAME = 'fernsehkritik.tv' - _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' + _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?' _TEST = { 'url': 'http://fernsehkritik.tv/folge-1', @@ -26,29 +26,32 @@ class FKTVIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = int(mobj.group('ep')) + episode = int(self._match_id(url)) - server = random.randint(2, 4) - video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode - start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode, + video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode + start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode, episode) playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage, 'playlist', flags=re.DOTALL) files = json.loads(re.sub('{[^{}]*?}', '{}', playlist)) - # TODO: return a single multipart video + videos = [] for i, _ in enumerate(files, 1): video_id = '%04d%d' % (episode, i) - video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i) + video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i) videos.append({ + 'ext': 'flv', 'id': video_id, 'url': video_url, 'title': clean_html(get_element_by_id('eptitle', start_webpage)), 'description': clean_html(get_element_by_id('contentlist', start_webpage)), 'thumbnail': video_thumbnail }) - return videos + return { + '_type': 'multi_video', + 'entries': videos, + 'id': 'folge-%s' % episode, + } class FKTVPosteckeIE(InfoExtractor): diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index b22ce2a..b2284ab 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -3,12 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, - unified_strdate, - str_to_int, +) +from ..utils import ( parse_duration, - clean_html, + parse_iso8601, + str_to_int, ) @@ -26,70 +27,81 @@ class FourTubeIE(InfoExtractor): 'uploader': 'WCP Club', 'uploader_id': 'wcp-club', 'upload_date': '20131031', + 'timestamp': 1383263892, 'duration': 583, + 'view_count': int, + 'like_count': int, + 'categories': list, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - webpage_url = 'http://www.4tube.com/videos/' + video_id - webpage = self._download_webpage(webpage_url, video_id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) + title = self._html_search_meta('name', webpage) + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage)) + thumbnail = self._html_search_meta('thumbnailUrl', webpage) + uploader_id = self._html_search_regex( + r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">', + webpage, 'uploader id') + uploader = self._html_search_regex( + r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">', + webpage, 'uploader') - playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist') - media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id') - sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',') - title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title') - thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False) + categories_html = self._search_regex( + r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>', + webpage, 'categories', fatal=False) + categories = None + if categories_html: + categories = [ + c.strip() for c in re.findall( + r'(?s)<li><a.*?>(.*?)</a>', categories_html)] - uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False) - mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str) - (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None) + view_count = str_to_int(self._search_regex( + r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">', + webpage, 'view count', fatal=False)) + like_count = str_to_int(self._search_regex( + r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">', + webpage, 'like count', fatal=False)) + duration = parse_duration(self._html_search_meta('duration', webpage)) - upload_date = None - view_count = None - duration = None - description = self._html_search_meta('description', webpage, 'description') - if description: - upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date', - fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False)) + params_js = self._search_regex( + r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)', + webpage, 'initialization parameters' + ) + params = self._parse_json('[%s]' % params_js, video_id) + media_id = params[0] + sources = ['%s' % p for p in params[2]] - token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources)) + token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format( + media_id, '+'.join(sources)) headers = { b'Content-Type': b'application/x-www-form-urlencoded', b'Origin': b'http://www.4tube.com', } token_req = compat_urllib_request.Request(token_url, b'{}', headers) tokens = self._download_json(token_req, video_id) - formats = [{ 'url': tokens[format]['token'], 'format_id': format + 'p', 'resolution': format + 'p', 'quality': int(format), } for format in sources] - self._sort_formats(formats) return { 'id': video_id, 'title': title, 'formats': formats, - 'thumbnail': thumbnail_url, + 'categories': categories, + 'thumbnail': thumbnail, 'uploader': uploader, 'uploader_id': uploader_id, - 'upload_date': upload_date, + 'timestamp': timestamp, + 'like_count': like_count, 'view_count': view_count, 'duration': duration, 'age_limit': 18, - 'webpage_url': webpage_url, } diff --git a/youtube_dl/extractor/foxgay.py b/youtube_dl/extractor/foxgay.py new file mode 100644 index 0000000..08b8ea3 --- /dev/null +++ b/youtube_dl/extractor/foxgay.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class FoxgayIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml' + _TEST = { + 'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml', + 'md5': '80d72beab5d04e1655a56ad37afe6841', + 'info_dict': { + 'id': '2582', + 'ext': 'mp4', + 'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a', + 'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf', + 'age_limit': 18, + 'thumbnail': 're:https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<title>(?P<title>.*?)</title>', + webpage, 'title', fatal=False) + description = self._html_search_regex( + r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>', + webpage, 'description', fatal=False) + + # Find the URL for the iFrame which contains the actual video. + iframe = self._download_webpage( + self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'), + video_id) + video_url = self._html_search_regex( + r"v_path = '(?P<vid>http://.*?)'", iframe, 'url') + thumb_url = self._html_search_regex( + r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'description': description, + 'thumbnail': thumb_url, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py new file mode 100644 index 0000000..917f76b --- /dev/null +++ b/youtube_dl/extractor/foxnews.py @@ -0,0 +1,94 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + int_or_none, +) + + +class FoxNewsIE(InfoExtractor): + _VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips', + 'md5': '32aaded6ba3ef0d1c04e238d01031e5e', + 'info_dict': { + 'id': '3937480', + 'ext': 'flv', + 'title': 'Frozen in Time', + 'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler', + 'duration': 265, + 'timestamp': 1304411491, + 'upload_date': '20110503', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips', + 'md5': '5846c64a1ea05ec78175421b8323e2df', + 'info_dict': { + 'id': '3922535568001', + 'ext': 'mp4', + 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal", + 'description': "Congressman discusses the president's executive action", + 'duration': 292, + 'timestamp': 1417662047, + 'upload_date': '20141204', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % video_id, video_id) + + item = video['channel']['item'] + title = item['title'] + description = item['description'] + timestamp = parse_iso8601(item['dc-date']) + + media_group = item['media-group'] + duration = None + formats = [] + for media in media_group['media-content']: + attributes = media['@attributes'] + video_url = attributes['url'] + if video_url.endswith('.f4m'): + formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id)) + elif video_url.endswith('.m3u8'): + formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv')) + elif not video_url.endswith('.smil'): + duration = int_or_none(attributes.get('duration')) + formats.append({ + 'url': video_url, + 'format_id': media['media-category']['@attributes']['label'], + 'preference': 1, + 'vbr': int_or_none(attributes.get('bitrate')), + 'filesize': int_or_none(attributes.get('fileSize')) + }) + self._sort_formats(formats) + + media_thumbnail = media_group['media-thumbnail']['@attributes'] + thumbnails = [{ + 'url': media_thumbnail['url'], + 'width': int_or_none(media_thumbnail.get('width')), + 'height': int_or_none(media_thumbnail.get('height')), + }] if media_thumbnail else [] + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'thumbnails': thumbnails, + } diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index 898e0dd..0c29721 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -5,7 +5,7 @@ import json import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_parse_qs, compat_urlparse, ) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index e0420a4..bbc760a 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -6,13 +6,15 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse_urlparse, compat_urlparse, - ExtractorError, +) +from ..utils import ( clean_html, - parse_duration, - compat_urllib_parse_urlparse, + ExtractorError, int_or_none, + parse_duration, ) diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py index 3022f53..a07d698 100644 --- a/youtube_dl/extractor/gameone.py +++ b/youtube_dl/extractor/gameone.py @@ -6,7 +6,9 @@ import re from .common import InfoExtractor from ..utils import ( xpath_with_ns, - parse_iso8601 + parse_iso8601, + float_or_none, + int_or_none, ) NAMESPACE_MAP = { @@ -21,25 +23,41 @@ RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/' class GameOneIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)' - _TEST = { - 'url': 'http://www.gameone.de/tv/288', - 'md5': '136656b7fb4c9cb4a8e2d500651c499b', - 'info_dict': { - 'id': '288', - 'ext': 'mp4', - 'title': 'Game One - Folge 288', - 'duration': 1238, - 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', - 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', - 'age_limit': 16, - 'upload_date': '20140513', - 'timestamp': 1399980122, + _TESTS = [ + { + 'url': 'http://www.gameone.de/tv/288', + 'md5': '136656b7fb4c9cb4a8e2d500651c499b', + 'info_dict': { + 'id': '288', + 'ext': 'mp4', + 'title': 'Game One - Folge 288', + 'duration': 1238, + 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', + 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', + 'age_limit': 16, + 'upload_date': '20140513', + 'timestamp': 1399980122, + } + }, + { + 'url': 'http://gameone.de/tv/220', + 'md5': '5227ca74c4ae6b5f74c0510a7c48839e', + 'info_dict': { + 'id': '220', + 'ext': 'mp4', + 'upload_date': '20120918', + 'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker', + 'timestamp': 1347971451, + 'title': 'Game One - Folge 220', + 'duration': 896.62, + 'age_limit': 16, + } } - } + + ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) og_video = self._og_search_video_url(webpage, secure=False) @@ -66,13 +84,13 @@ class GameOneIE(InfoExtractor): video_id, 'Downloading media:content') rendition_items = content.findall('.//rendition') - duration = int(rendition_items[0].get('duration')) + duration = float_or_none(rendition_items[0].get('duration')) formats = [ { 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text), - 'width': int(r.get('width')), - 'height': int(r.get('height')), - 'tbr': int(r.get('bitrate')), + 'width': int_or_none(r.get('width')), + 'height': int_or_none(r.get('height')), + 'tbr': int_or_none(r.get('bitrate')), } for r in rendition_items ] @@ -105,7 +123,8 @@ class GameOnePlaylistIE(InfoExtractor): webpage = self._download_webpage('http://www.gameone.de/tv', 'TV') max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage))) entries = [ - self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne') + self.url_result('http://www.gameone.de/tv/%d' % + video_id, 'GameOne') for video_id in range(max_id, 0, -1)] return { diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index d570e3f..47373e2 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -4,9 +4,11 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, +) +from ..utils import ( unescapeHTML, ) diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index de14ae1..fed968f 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -39,7 +39,8 @@ class GDCVaultIE(InfoExtractor): 'id': '1015301', 'ext': 'flv', 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment', - } + }, + 'skip': 'Requires login', } ] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 328301d..7a5bf93 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -23,6 +23,7 @@ from ..utils import ( unescapeHTML, unified_strdate, unsmuggle_url, + UnsupportedError, url_basename, ) from .brightcove import BrightcoveIE @@ -130,12 +131,13 @@ class GenericIE(InfoExtractor): # ooyala video { 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', - 'md5': '5644c6ca5d5782c1d0d350dad9bd840c', + 'md5': '166dd577b433b4d4ebfee10b0824d8ff', 'info_dict': { 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'ext': 'mp4', 'title': '2cc213299525360.mov', # that's what we get }, + 'add_ie': ['Ooyala'], }, # google redirect { @@ -145,7 +147,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20130224', 'uploader_id': 'TheVerge', - 'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.', + 'description': 're:^Chris Ziegler takes a look at the\.*', 'uploader': 'The Verge', 'title': 'First Firefox OS phones side-by-side', }, @@ -180,6 +182,14 @@ class GenericIE(InfoExtractor): 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', }, }, + # BBC iPlayer embeds + { + 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER', + 'info_dict': { + 'title': 'BBC - Blogs - Adam Curtis - BUGGER', + }, + 'playlist_mincount': 18, + }, # RUTV embed { 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', @@ -467,8 +477,17 @@ class GenericIE(InfoExtractor): 'expected_warnings': [ 'URL could be a direct video link, returning it as such.' ] - } - + }, + # Cinchcast embed + { + 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/', + 'info_dict': { + 'id': '7141703', + 'ext': 'mp3', + 'upload_date': '20141126', + 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing', + } + }, ] def report_following_redirect(self, new_url): @@ -689,9 +708,9 @@ class GenericIE(InfoExtractor): r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') # Helper method - def _playlist_from_matches(matches, getter, ie=None): + def _playlist_from_matches(matches, getter=None, ie=None): urlrs = orderedSet( - self.url_result(self._proto_relative_url(getter(m)), ie) + self.url_result(self._proto_relative_url(getter(m) if getter else m), ie) for m in matches) return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) @@ -895,6 +914,11 @@ class GenericIE(InfoExtractor): return _playlist_from_matches( matches, getter=unescapeHTML, ie='FunnyOrDie') + # Look for BBC iPlayer embed + matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage) + if matches: + return _playlist_from_matches(matches, ie='BBCCoUk') + # Look for embedded RUTV player rutv_url = RUTVIE._extract_url(webpage) if rutv_url: @@ -902,7 +926,7 @@ class GenericIE(InfoExtractor): # Look for embedded TED player mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'TED') @@ -962,6 +986,13 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'SBS') + # Look for embedded Cinchcast player + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Cinchcast') + mobj = re.search( r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', webpage) @@ -1041,7 +1072,7 @@ class GenericIE(InfoExtractor): 'url': new_url, } if not found: - raise ExtractorError('Unsupported URL: %s' % url) + raise UnsupportedError(url) entries = [] for video_url in found: diff --git a/youtube_dl/extractor/giantbomb.py b/youtube_dl/extractor/giantbomb.py new file mode 100644 index 0000000..87cd191 --- /dev/null +++ b/youtube_dl/extractor/giantbomb.py @@ -0,0 +1,81 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + unescapeHTML, + qualities, + int_or_none, +) + + +class GiantBombIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)' + _TEST = { + 'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/', + 'md5': '57badeface303ecf6b98b812de1b9018', + 'info_dict': { + 'id': '2300-9782', + 'display_id': 'quick-look-destiny-the-dark-below', + 'ext': 'mp4', + 'title': 'Quick Look: Destiny: The Dark Below', + 'description': 'md5:0aa3aaf2772a41b91d44c63f30dfad24', + 'duration': 2399, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + video = json.loads(unescapeHTML(self._search_regex( + r'data-video="([^"]+)"', webpage, 'data-video'))) + + duration = int_or_none(video.get('lengthSeconds')) + + quality = qualities([ + 'f4m_low', 'progressive_low', 'f4m_high', + 'progressive_high', 'f4m_hd', 'progressive_hd']) + + formats = [] + for format_id, video_url in video['videoStreams'].items(): + if format_id == 'f4m_stream': + continue + if video_url.endswith('.f4m'): + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.3.1', display_id) + if f4m_formats: + f4m_formats[0]['quality'] = quality(format_id) + formats.extend(f4m_formats) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'quality': quality(format_id), + }) + + if not formats: + youtube_id = video.get('youtubeID') + if youtube_id: + return self.url_result(youtube_id, 'Youtube') + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/giga.py b/youtube_dl/extractor/giga.py new file mode 100644 index 0000000..7758901 --- /dev/null +++ b/youtube_dl/extractor/giga.py @@ -0,0 +1,101 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools + +from .common import InfoExtractor +from ..utils import ( + qualities, + compat_str, + parse_duration, + parse_iso8601, + str_to_int, +) + + +class GigaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/', + 'md5': '6bc5535e945e724640664632055a584f', + 'info_dict': { + 'id': '2622086', + 'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss', + 'ext': 'mp4', + 'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss', + 'description': 'md5:afdf5862241aded4718a30dff6a57baf', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 578, + 'timestamp': 1414749706, + 'upload_date': '20141031', + 'uploader': 'Robin Schweiger', + 'view_count': int, + }, + }, { + 'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/', + 'only_matching': True, + }, { + 'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/', + 'only_matching': True, + }, { + 'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + [r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'], + webpage, 'video id') + + playlist = self._download_json( + 'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/' + % video_id, video_id)[0] + + quality = qualities(['normal', 'hd720']) + + formats = [] + for format_id in itertools.count(0): + fmt = playlist.get(compat_str(format_id)) + if not fmt: + break + formats.append({ + 'url': fmt['src'], + 'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]), + 'quality': quality(fmt['quality']), + }) + self._sort_formats(formats) + + title = self._html_search_meta( + 'title', webpage, 'title', fatal=True) + description = self._html_search_meta( + 'description', webpage, 'description') + thumbnail = self._og_search_thumbnail(webpage) + + duration = parse_duration(self._search_regex( + r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id), + webpage, 'duration', fatal=False)) + + timestamp = parse_iso8601(self._search_regex( + r'datetime="([^"]+)"', webpage, 'upload date', fatal=False)) + uploader = self._search_regex( + r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False) + + view_count = str_to_int(self._search_regex( + r'<span class="views"><strong>([\d.]+)</strong>', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader': uploader, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/goldenmoustache.py b/youtube_dl/extractor/goldenmoustache.py index 10001d4..0fb5097 100644 --- a/youtube_dl/extractor/goldenmoustache.py +++ b/youtube_dl/extractor/goldenmoustache.py @@ -1,9 +1,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - int_or_none, -) class GoldenMoustacheIE(InfoExtractor): @@ -17,7 +14,6 @@ class GoldenMoustacheIE(InfoExtractor): 'title': 'Suricate - Le Poker', 'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9', 'thumbnail': 're:^https?://.*\.jpg$', - 'view_count': int, } }, { 'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/', @@ -28,7 +24,6 @@ class GoldenMoustacheIE(InfoExtractor): 'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)', 'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a', 'thumbnail': 're:^https?://.*\.(?:png|jpg)$', - 'view_count': int, } }] @@ -42,9 +37,6 @@ class GoldenMoustacheIE(InfoExtractor): r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title') thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage) - view_count = int_or_none(self._html_search_regex( - r'<strong>([0-9]+)</strong>\s*VUES</span>', - webpage, 'view count', fatal=False)) return { 'id': video_id, @@ -53,5 +45,4 @@ class GoldenMoustacheIE(InfoExtractor): 'title': title, 'description': description, 'thumbnail': thumbnail, - 'view_count': view_count, } diff --git a/youtube_dl/extractor/golem.py b/youtube_dl/extractor/golem.py index 53714f4..2bfb990 100644 --- a/youtube_dl/extractor/golem.py +++ b/youtube_dl/extractor/golem.py @@ -2,8 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, +) +from ..utils import ( determine_ext, ) diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index 469e1f9..498304c 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -4,7 +4,7 @@ import itertools import re from .common import SearchInfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py index 1ac1da8..ae24aff 100644 --- a/youtube_dl/extractor/gorillavid.py +++ b/youtube_dl/extractor/gorillavid.py @@ -4,11 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, - determine_ext, +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( + ExtractorError, int_or_none, ) @@ -106,7 +107,6 @@ class GorillaVidIE(InfoExtractor): formats = [{ 'format_id': 'sd', 'url': video_url, - 'ext': determine_ext(video_url), 'quality': 1, }] diff --git a/youtube_dl/extractor/goshgay.py b/youtube_dl/extractor/goshgay.py index 18474cb..b116d25 100644 --- a/youtube_dl/extractor/goshgay.py +++ b/youtube_dl/extractor/goshgay.py @@ -2,57 +2,52 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, +) from ..utils import ( - compat_urlparse, - ExtractorError, + parse_duration, ) class GoshgayIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)www.goshgay.com/video(?P<id>\d+?)($|/)' + _VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)' _TEST = { - 'url': 'http://www.goshgay.com/video4116282', - 'md5': '268b9f3c3229105c57859e166dd72b03', + 'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video', + 'md5': '027fcc54459dff0feb0bc06a7aeda680', 'info_dict': { - 'id': '4116282', + 'id': '299069', 'ext': 'flv', - 'title': 'md5:089833a4790b5e103285a07337f245bf', - 'thumbnail': 're:http://.*\.jpg', + 'title': 'DIESEL SFW XXX Video', + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 79, 'age_limit': 18, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage) - thumbnail = self._og_search_thumbnail(webpage) + + title = self._html_search_regex( + r'<h2>(.*?)<', webpage, 'title') + duration = parse_duration(self._html_search_regex( + r'<span class="duration">\s*-?\s*(.*?)</span>', + webpage, 'duration', fatal=False)) family_friendly = self._html_search_meta( 'isFamilyFriendly', webpage, default='false') - config_url = self._search_regex( - r"'config'\s*:\s*'([^']+)'", webpage, 'config URL') - - config = self._download_xml( - config_url, video_id, 'Downloading player config XML') - - if config is None: - raise ExtractorError('Missing config XML') - if config.tag != 'config': - raise ExtractorError('Missing config attribute') - fns = config.findall('file') - if len(fns) < 1: - raise ExtractorError('Missing media URI') - video_url = fns[0].text - url_comp = compat_urlparse.urlparse(url) - ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2]) + flashvars = compat_parse_qs(self._html_search_regex( + r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"', + webpage, 'flashvars')) + thumbnail = flashvars.get('url_bigthumb', [None])[0] + video_url = flashvars['flv_url'][0] return { 'id': video_id, 'url': video_url, 'title': title, 'thumbnail': thumbnail, - 'http_referer': ref, + 'duration': duration, 'age_limit': 0 if family_friendly == 'true' else 18, } diff --git a/youtube_dl/extractor/groupon.py b/youtube_dl/extractor/groupon.py new file mode 100644 index 0000000..8b9e0e2 --- /dev/null +++ b/youtube_dl/extractor/groupon.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class GrouponIE(InfoExtractor): + _VALID_URL = r'https?://www\.groupon\.com/deals/(?P<id>[^?#]+)' + + _TEST = { + 'url': 'https://www.groupon.com/deals/bikram-yoga-huntington-beach-2#ooid=tubGNycTo_9Uxg82uESj4i61EYX8nyuf', + 'info_dict': { + 'id': 'bikram-yoga-huntington-beach-2', + 'title': '$49 for 10 Yoga Classes or One Month of Unlimited Classes at Bikram Yoga Huntington Beach ($180 Value)', + 'description': 'Studio kept at 105 degrees and 40% humidity with anti-microbial and anti-slip Flotex flooring; certified instructors', + }, + 'playlist': [{ + 'info_dict': { + 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf', + 'ext': 'mp4', + 'title': 'Bikram Yoga Huntington Beach | Orange County', + }, + }], + 'params': { + 'skip_download': 'HLS', + } + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + payload = self._parse_json(self._search_regex( + r'var\s+payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id) + videos = payload['carousel'].get('dealVideos', []) + entries = [] + for v in videos: + if v.get('provider') != 'OOYALA': + self.report_warning( + '%s: Unsupported video provider %s, skipping video' % + (playlist_id, v.get('provider'))) + continue + entries.append(self.url_result('ooyala:%s' % v['media'])) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'entries': entries, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + } diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py new file mode 100644 index 0000000..7a1c75b --- /dev/null +++ b/youtube_dl/extractor/hellporno.py @@ -0,0 +1,71 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) + + +class HellPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', + 'md5': '1fee339c610d2049699ef2aa699439f1', + 'info_dict': { + 'id': '149116', + 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', + 'ext': 'mp4', + 'title': 'Dixie is posing with naked ass very erotic', + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + title = remove_end(self._html_search_regex( + r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno') + + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), + display_id, transform_source=js_to_json) + + video_id = flashvars.get('video_id') + thumbnail = flashvars.get('preview_url') + ext = flashvars.get('postfix', '.mp4')[1:] + + formats = [] + for video_url_key in ['video_url', 'video_alt_url']: + video_url = flashvars.get(video_url_key) + if not video_url: + continue + video_text = flashvars.get('%s_text' % video_url_key) + fmt = { + 'url': video_url, + 'ext': ext, + 'format_id': video_text, + } + m = re.search(r'^(?P<height>\d+)[pP]', video_text) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) + + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'thumbnail': thumbnail, + 'categories': categories, + 'age_limit': 18, + 'formats': formats, + } diff --git a/youtube_dl/extractor/helsinki.py b/youtube_dl/extractor/helsinki.py index 5268efa..93107b3 100644 --- a/youtube_dl/extractor/helsinki.py +++ b/youtube_dl/extractor/helsinki.py @@ -2,9 +2,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import js_to_json class HelsinkiIE(InfoExtractor): @@ -24,39 +23,21 @@ class HelsinkiIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - formats = [] - - mobj = re.search(r'file=((\w+):[^&]+)', webpage) - if mobj: - formats.append({ - 'ext': mobj.group(2), - 'play_path': mobj.group(1), - 'url': 'rtmp://flashvideo.it.helsinki.fi/vod/', - 'player_url': 'http://video.helsinki.fi/player.swf', - 'format_note': 'sd', - 'quality': 0, - }) - - mobj = re.search(r'hd\.file=((\w+):[^&]+)', webpage) - if mobj: - formats.append({ - 'ext': mobj.group(2), - 'play_path': mobj.group(1), - 'url': 'rtmp://flashvideo.it.helsinki.fi/vod/', - 'player_url': 'http://video.helsinki.fi/player.swf', - 'format_note': 'hd', - 'quality': 1, - }) + params = self._parse_json(self._html_search_regex( + r'(?s)jwplayer\("player"\).setup\((\{.*?\})\);', + webpage, 'player code'), video_id, transform_source=js_to_json) + formats = [{ + 'url': s['file'], + 'ext': 'mp4', + } for s in params['sources']] self._sort_formats(formats) return { 'id': video_id, 'title': self._og_search_title(webpage).replace('Video: ', ''), 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, } diff --git a/youtube_dl/extractor/hitbox.py b/youtube_dl/extractor/hitbox.py new file mode 100644 index 0000000..84bd7c0 --- /dev/null +++ b/youtube_dl/extractor/hitbox.py @@ -0,0 +1,166 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + parse_iso8601, + float_or_none, + int_or_none, + compat_str, +) + + +class HitboxIE(InfoExtractor): + IE_NAME = 'hitbox' + _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/video/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.hitbox.tv/video/203213', + 'info_dict': { + 'id': '203213', + 'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy', + 'alt_title': 'hitboxlive - Aug 9th #6', + 'description': '', + 'ext': 'mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 215.1666, + 'resolution': 'HD 720p', + 'uploader': 'hitboxlive', + 'view_count': int, + 'timestamp': 1407576133, + 'upload_date': '20140809', + 'categories': ['Live Show'], + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _extract_metadata(self, url, video_id): + thumb_base = 'https://edge.sf.hitbox.tv' + metadata = self._download_json( + '%s/%s' % (url, video_id), video_id) + + date = 'media_live_since' + media_type = 'livestream' + if metadata.get('media_type') == 'video': + media_type = 'video' + date = 'media_date_added' + + video_meta = metadata.get(media_type, [])[0] + title = video_meta.get('media_status') + alt_title = video_meta.get('media_title') + description = clean_html( + video_meta.get('media_description') or + video_meta.get('media_description_md')) + duration = float_or_none(video_meta.get('media_duration')) + uploader = video_meta.get('media_user_name') + views = int_or_none(video_meta.get('media_views')) + timestamp = parse_iso8601(video_meta.get(date), ' ') + categories = [video_meta.get('category_name')] + thumbs = [ + {'url': thumb_base + video_meta.get('media_thumbnail'), + 'width': 320, + 'height': 180}, + {'url': thumb_base + video_meta.get('media_thumbnail_large'), + 'width': 768, + 'height': 432}, + ] + + return { + 'id': video_id, + 'title': title, + 'alt_title': alt_title, + 'description': description, + 'ext': 'mp4', + 'thumbnails': thumbs, + 'duration': duration, + 'uploader': uploader, + 'view_count': views, + 'timestamp': timestamp, + 'categories': categories, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + metadata = self._extract_metadata( + 'https://www.hitbox.tv/api/media/video', + video_id) + + player_config = self._download_json( + 'https://www.hitbox.tv/api/player/config/video/%s' % video_id, + video_id) + + clip = player_config.get('clip') + video_url = clip.get('url') + res = clip.get('bitrates', [])[0].get('label') + + metadata['resolution'] = res + metadata['url'] = video_url + metadata['protocol'] = 'm3u8' + + return metadata + + +class HitboxLiveIE(HitboxIE): + IE_NAME = 'hitbox:live' + _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/(?!video)(?P<id>.+)' + _TEST = { + 'url': 'http://www.hitbox.tv/dimak', + 'info_dict': { + 'id': 'dimak', + 'ext': 'mp4', + 'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e', + 'timestamp': int, + 'upload_date': compat_str, + 'title': compat_str, + 'uploader': 'Dimak', + }, + 'params': { + # live + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + metadata = self._extract_metadata( + 'https://www.hitbox.tv/api/media/live', + video_id) + + player_config = self._download_json( + 'https://www.hitbox.tv/api/player/config/live/%s' % video_id, + video_id) + + formats = [] + cdns = player_config.get('cdns') + servers = [] + for cdn in cdns: + base_url = cdn.get('netConnectionUrl') + host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1) + if base_url not in servers: + servers.append(base_url) + for stream in cdn.get('bitrates'): + label = stream.get('label') + if label != 'Auto': + formats.append({ + 'url': '%s/%s' % (base_url, stream.get('url')), + 'ext': 'mp4', + 'vbr': stream.get('bitrate'), + 'resolution': label, + 'rtmp_live': True, + 'format_note': host, + 'page_url': url, + 'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf', + }) + + self._sort_formats(formats) + metadata['formats'] = formats + metadata['is_live'] = True + metadata['title'] = self._live_title(metadata.get('title')) + return metadata diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py index 8e812b6..704d028 100644 --- a/youtube_dl/extractor/hostingbulk.py +++ b/youtube_dl/extractor/hostingbulk.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, int_or_none, urlencode_postdata, ) @@ -30,9 +32,7 @@ class HostingBulkIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'http://hostingbulk.com/{0:}.html'.format(video_id) # Custom request with cookie to set language to English, so our file diff --git a/youtube_dl/extractor/howstuffworks.py b/youtube_dl/extractor/howstuffworks.py index fccc238..e973391 100644 --- a/youtube_dl/extractor/howstuffworks.py +++ b/youtube_dl/extractor/howstuffworks.py @@ -1,12 +1,12 @@ from __future__ import unicode_literals -import re -import json -import random -import string - from .common import InfoExtractor -from ..utils import find_xpath_attr +from ..utils import ( + find_xpath_attr, + int_or_none, + js_to_json, + unescapeHTML, +) class HowStuffWorksIE(InfoExtractor): @@ -16,98 +16,74 @@ class HowStuffWorksIE(InfoExtractor): 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm', 'info_dict': { 'id': '450221', - 'display_id': 'cool-jobs-iditarod-musher', 'ext': 'flv', 'title': 'Cool Jobs - Iditarod Musher', - 'description': 'md5:82bb58438a88027b8186a1fccb365f90', + 'description': 'Cold sleds, freezing temps and warm dog breath... an Iditarod musher\'s dream. Kasey-Dee Gardner jumps on a sled to find out what the big deal is.', + 'display_id': 'cool-jobs-iditarod-musher', 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 161, }, - 'params': { - # md5 is not consistent - 'skip_download': True - } }, { 'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm', 'info_dict': { 'id': '453464', - 'display_id': 'survival-zone-food-and-water-in-the-savanna', 'ext': 'mp4', 'title': 'Survival Zone: Food and Water In the Savanna', - 'description': 'md5:7e1c89f6411434970c15fa094170c371', + 'description': 'Learn how to find both food and water while trekking in the African savannah. In this video from the Discovery Channel.', + 'display_id': 'survival-zone-food-and-water-in-the-savanna', 'thumbnail': 're:^https?://.*\.jpg$', }, - 'params': { - # md5 is not consistent - 'skip_download': True - } }, { 'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm', 'info_dict': { 'id': '440011', - 'display_id': 'sword-swallowing-1-by-dan-meyer', 'ext': 'flv', 'title': 'Sword Swallowing #1 by Dan Meyer', - 'description': 'md5:b2409e88172913e2e7d3d1159b0ef735', + 'description': 'Video footage (1 of 3) used by permission of the owner Dan Meyer through Sword Swallowers Association International <www.swordswallow.org>', + 'display_id': 'sword-swallowing-1-by-dan-meyer', 'thumbnail': 're:^https?://.*\.jpg$', }, - 'params': { - # md5 is not consistent - 'skip_download': True - } }, ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') + display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) + clip_js = self._search_regex( + r'(?s)var clip = ({.*?});', webpage, 'clip info') + clip_info = self._parse_json( + clip_js, display_id, transform_source=js_to_json) - content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id') - - mp4 = self._search_regex( - r'''(?xs)var\s+clip\s*=\s*{\s* - .+?\s* - content_id\s*:\s*%s\s*,\s* - .+?\s* - mp4\s*:\s*\[(.*?),?\]\s* - };\s* - videoData\.push\(clip\);''' % content_id, - webpage, 'mp4', fatal=False, default=None) - - smil = self._download_xml( - 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id, - content_id, 'Downloading video SMIL') - - http_base = find_xpath_attr( - smil, - './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'), - 'name', - 'httpBase').get('content') - - def random_string(str_len=0): - return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)]) - - URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12)) - + video_id = clip_info['content_id'] formats = [] + m3u8_url = clip_info.get('m3u8') + if m3u8_url: + formats += self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') + for video in clip_info.get('mp4', []): + formats.append({ + 'url': video['src'], + 'format_id': video['bitrate'], + 'vbr': int(video['bitrate'].rstrip('k')), + }) + + if not formats: + smil = self._download_xml( + 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % video_id, + video_id, 'Downloading video SMIL') + + http_base = find_xpath_attr( + smil, + './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'), + 'name', + 'httpBase').get('content') + + URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=A&g=A' - if mp4: - for video in json.loads('[%s]' % mp4): - bitrate = video['bitrate'] - fmt = { - 'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX, - 'format_id': bitrate, - } - m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate) - if m: - fmt['vbr'] = int(m.group('vbr')) - formats.append(fmt) - else: for video in smil.findall( - './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')): - vbr = int(video.attrib['system-bitrate']) / 1000 + './{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')): + vbr = int_or_none(video.attrib['system-bitrate'], scale=1000) formats.append({ 'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX), 'format_id': '%dk' % vbr, @@ -116,19 +92,12 @@ class HowStuffWorksIE(InfoExtractor): self._sort_formats(formats) - title = self._og_search_title(webpage) - TITLE_SUFFIX = ' : HowStuffWorks' - if title.endswith(TITLE_SUFFIX): - title = title[:-len(TITLE_SUFFIX)] - - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - return { - 'id': content_id, + 'id': '%s' % video_id, 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, + 'title': unescapeHTML(clip_info['clip_title']), + 'description': unescapeHTML(clip_info.get('caption')), + 'thumbnail': clip_info.get('video_still_url'), + 'duration': clip_info.get('duration'), 'formats': formats, } diff --git a/youtube_dl/extractor/huffpost.py b/youtube_dl/extractor/huffpost.py index 4ccf6b9..a38eae4 100644 --- a/youtube_dl/extractor/huffpost.py +++ b/youtube_dl/extractor/huffpost.py @@ -39,8 +39,9 @@ class HuffPostIE(InfoExtractor): data = self._download_json(api_url, video_id)['data'] video_title = data['title'] - duration = parse_duration(data['running_time']) - upload_date = unified_strdate(data['schedule']['starts_at']) + duration = parse_duration(data.get('running_time')) + upload_date = unified_strdate( + data.get('schedule', {}).get('starts_at') or data.get('segment_start_date_time')) description = data.get('description') thumbnails = [] @@ -59,16 +60,11 @@ class HuffPostIE(InfoExtractor): 'ext': 'mp4', 'url': url, 'vcodec': 'none' if key.startswith('audio/') else None, - } for key, url in data['sources']['live'].items()] - if data.get('fivemin_id'): - fid = data['fivemin_id'] - fcat = str(int(fid) // 100 + 1) - furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4' - formats.append({ - 'format': 'fivemin', - 'url': furl, - 'preference': 1, - }) + } for key, url in data.get('sources', {}).get('live', {}).items()] + + if not formats and data.get('fivemin_id'): + return self.url_result('5min:%s' % data['fivemin_id']) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index 6d0d847..aa0724a 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -1,20 +1,20 @@ from __future__ import unicode_literals import json -import re import time from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, ) class HypemIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' + _VALID_URL = r'http://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/' _TEST = { 'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', 'md5': 'b9cc91b5af8995e9f0c1cee04c575828', @@ -27,8 +27,7 @@ class HypemIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - track_id = mobj.group(1) + track_id = self._match_id(url) data = {'ax': 1, 'ts': time.time()} data_encoded = compat_urllib_parse.urlencode(data) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index f2c1c10..f29df36 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -4,7 +4,7 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, ) @@ -16,7 +16,6 @@ class ImdbIE(InfoExtractor): _TEST = { 'url': 'http://www.imdb.com/video/imdb/vi2524815897', - 'md5': '9f34fa777ade3a6e57a054fdbcb3a068', 'info_dict': { 'id': '2524815897', 'ext': 'mp4', diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index e76dd22..f25f436 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -1,10 +1,9 @@ from __future__ import unicode_literals import base64 -import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -24,9 +23,7 @@ class InfoQIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 1e47991..483cc6f 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, compat_urllib_parse, +) +from ..utils import ( xpath_with_ns, ) @@ -20,7 +22,7 @@ class InternetVideoArchiveIE(InfoExtractor): 'ext': 'mp4', 'title': 'SKYFALL', 'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.', - 'duration': 149, + 'duration': 152, }, } diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 4247d63..8529bed 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -6,8 +6,10 @@ from random import random from math import floor from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index f0fba1a..7a40032 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -5,8 +5,10 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/karaoketv.py b/youtube_dl/extractor/karaoketv.py new file mode 100644 index 0000000..e3b43ff --- /dev/null +++ b/youtube_dl/extractor/karaoketv.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urllib_parse +from ..utils import ( + js_to_json, +) + + +class KaraoketvIE(InfoExtractor): + _VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://karaoketv.co.il/?container=songs&id=171568', + 'info_dict': { + 'id': '171568', + 'ext': 'mp4', + 'title': 'אל העולם שלך - רותם כהן - שרים קריוקי', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + page_video_url = self._og_search_video_url(webpage, video_id) + config_json = compat_urllib_parse.unquote_plus(self._search_regex( + r'config=(.*)', page_video_url, 'configuration')) + + urls_info_json = self._download_json( + config_json, video_id, 'Downloading configuration', + transform_source=js_to_json) + + url = urls_info_json['playlist'][0]['url'] + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'url': url, + } diff --git a/youtube_dl/extractor/keek.py b/youtube_dl/extractor/keek.py index 5d679e8..c0956ba 100644 --- a/youtube_dl/extractor/keek.py +++ b/youtube_dl/extractor/keek.py @@ -1,34 +1,39 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class KeekIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)' + _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<id>\w+)' IE_NAME = 'keek' _TEST = { 'url': 'https://www.keek.com/ytdl/keeks/NODfbab', - 'file': 'NODfbab.mp4', - 'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83', + 'md5': '09c5c109067536c1cec8bac8c21fea05', 'info_dict': { - 'uploader': 'ytdl', + 'id': 'NODfbab', + 'ext': 'mp4', + 'uploader': 'youtube-dl project', + 'uploader_id': 'ytdl', 'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .', }, } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') + video_id = self._match_id(url) video_url = 'http://cdn.keek.com/keek/video/%s' % video_id thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id webpage = self._download_webpage(url, video_id) - uploader = self._html_search_regex( - r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', - webpage, 'uploader', fatal=False) + raw_desc = self._html_search_meta('description', webpage) + if raw_desc: + uploader = self._html_search_regex( + r'Watch (.*?)\s+\(', raw_desc, 'uploader', fatal=False) + uploader_id = self._html_search_regex( + r'Watch .*?\(@(.+?)\)', raw_desc, 'uploader_id', fatal=False) + else: + uploader = None + uploader_id = None return { 'id': video_id, @@ -36,5 +41,6 @@ class KeekIE(InfoExtractor): 'ext': 'mp4', 'title': self._og_search_title(webpage), 'thumbnail': thumbnail, - 'uploader': uploader + 'uploader': uploader, + 'uploader_id': uploader_id, } diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 75b63cf..97dcb51 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -4,7 +4,7 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, @@ -15,7 +15,7 @@ from ..aes import ( class KeezMoviesIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)' _TEST = { 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', 'file': '1214711.mp4', @@ -27,8 +27,7 @@ class KeezMoviesIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 408d009..08a671f 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -22,8 +22,10 @@ class KhanAcademyIE(InfoExtractor): 'description': 'The perfect cipher', 'duration': 176, 'uploader': 'Brit Cruise', + 'uploader_id': 'khanacademy', 'upload_date': '20120411', - } + }, + 'add_ie': ['Youtube'], }, { 'url': 'https://www.khanacademy.org/math/applied-math/cryptography', 'info_dict': { diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py index 41fd620..720bc93 100644 --- a/youtube_dl/extractor/kontrtube.py +++ b/youtube_dl/extractor/kontrtube.py @@ -10,13 +10,14 @@ from ..utils import int_or_none class KontrTubeIE(InfoExtractor): IE_NAME = 'kontrtube' IE_DESC = 'KontrTube.ru - Труба зовёт' - _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+' + _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/' _TEST = { 'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/', 'md5': '975a991a4926c9a85f383a736a2e6b80', 'info_dict': { 'id': '2678', + 'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag', 'ext': 'mp4', 'title': 'Над олимпийской деревней в Сочи поднят российский флаг', 'description': 'md5:80edc4c613d5887ae8ccf1d59432be41', @@ -28,21 +29,28 @@ class KontrTubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + display_id = mobj.group('display_id') - webpage = self._download_webpage(url, video_id, 'Downloading page') + webpage = self._download_webpage( + url, display_id, 'Downloading page') - video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL') - thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False) + video_url = self._html_search_regex( + r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL') + thumbnail = self._html_search_regex( + r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False) title = self._html_search_regex( r'<title>(.+?)</title>', webpage, 'video title') - description = self._html_search_meta('description', webpage, 'video description') + description = self._html_search_meta( + 'description', webpage, 'video description') mobj = re.search( - r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage) + r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', + webpage) duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None view_count = self._html_search_regex( - r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False) + r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', + webpage, 'view count', fatal=False) comment_count = None comment_str = self._html_search_regex( @@ -56,6 +64,7 @@ class KontrTubeIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'url': video_url, 'thumbnail': thumbnail, 'title': title, diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 03c4691..5247c6f 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -4,10 +4,12 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urllib_parse_urlparse, compat_urlparse, +) +from ..utils import ( ExtractorError, find_xpath_attr, int_or_none, diff --git a/youtube_dl/extractor/lnkgo.py b/youtube_dl/extractor/lnkgo.py new file mode 100644 index 0000000..a8e3578 --- /dev/null +++ b/youtube_dl/extractor/lnkgo.py @@ -0,0 +1,124 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + js_to_json, + unified_strdate, +) + + +class LnkGoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi\-video/(?P<show>[^/]+)/ziurek\-(?P<display_id>[A-Za-z0-9\-]+)' + _TESTS = [{ + 'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162', + 'info_dict': { + 'id': '46712', + 'ext': 'mp4', + 'title': 'Yra kaip yra', + 'upload_date': '20150107', + 'description': 'md5:d82a5e36b775b7048617f263a0e3475e', + 'age_limit': 7, + 'duration': 3019, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + 'params': { + 'skip_download': True, # HLS download + }, + }, { + 'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2', + 'info_dict': { + 'id': '47289', + 'ext': 'mp4', + 'title': 'Nėrdas: Kompiuterio Valymas', + 'upload_date': '20150113', + 'description': 'md5:7352d113a242a808676ff17e69db6a69', + 'age_limit': 18, + 'duration': 346, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + 'params': { + 'skip_download': True, # HLS download + }, + }] + _AGE_LIMITS = { + 'N-7': 7, + 'N-14': 14, + 'S': 18, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + webpage = self._download_webpage( + url, display_id, 'Downloading player webpage') + + video_id = self._search_regex( + r'data-ep="([^"]+)"', webpage, 'video ID') + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + + thumbnail_w = int_or_none( + self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False)) + thumbnail_h = int_or_none( + self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False)) + thumbnail = { + 'url': self._og_search_thumbnail(webpage), + } + if thumbnail_w and thumbnail_h: + thumbnail.update({ + 'width': thumbnail_w, + 'height': thumbnail_h, + }) + + upload_date = unified_strdate(self._search_regex( + r'class="meta-item\sair-time">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False)) + duration = int_or_none(self._search_regex( + r'VideoDuration = "([^"]+)"', webpage, 'duration', fatal=False)) + + pg_rating = self._search_regex( + r'pgrating="([^"]+)"', webpage, 'PG rating', fatal=False, default='') + age_limit = self._AGE_LIMITS.get(pg_rating.upper(), 0) + + sources_js = self._search_regex( + r'(?s)sources:\s(\[.*?\]),', webpage, 'sources') + sources = self._parse_json( + sources_js, video_id, transform_source=js_to_json) + + formats = [] + for source in sources: + if source.get('provider') == 'rtmp': + m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', source['file']) + if not m: + continue + formats.append({ + 'format_id': 'rtmp', + 'ext': 'flv', + 'url': m.group('url'), + 'play_path': m.group('play_path'), + 'page_url': url, + }) + elif source.get('file').endswith('.m3u8'): + formats.append({ + 'format_id': 'hls', + 'ext': source.get('type', 'mp4'), + 'url': source['file'], + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'thumbnails': [thumbnail], + 'duration': duration, + 'description': description, + 'age_limit': age_limit, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py index d72d470..9c2fbdd 100644 --- a/youtube_dl/extractor/lrt.py +++ b/youtube_dl/extractor/lrt.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( @@ -28,7 +27,6 @@ class LRTIE(InfoExtractor): 'params': { 'skip_download': True, # HLS download }, - } def _real_extract(self, url): @@ -44,7 +42,9 @@ class LRTIE(InfoExtractor): formats = [] for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage): - data = json.loads(js_to_json(js)) + data = self._parse_json(js, video_id, transform_source=js_to_json) + if 'provider' not in data: + continue if data['provider'] == 'rtmp': formats.append({ 'format_id': 'rtmp', diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 2160d6c..26e8497 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -5,12 +5,14 @@ import json from .subtitles import SubtitlesInfoExtractor from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_str, compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, int_or_none, - compat_str, ) diff --git a/youtube_dl/extractor/malemotion.py b/youtube_dl/extractor/malemotion.py index 1abf6e4..0b85a59 100644 --- a/youtube_dl/extractor/malemotion.py +++ b/youtube_dl/extractor/malemotion.py @@ -1,43 +1,33 @@ +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) class MalemotionIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' + _VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' _TEST = { - 'url': 'http://malemotion.com/video/bien-dur.10ew', - 'file': '10ew.mp4', - 'md5': 'b3cc49f953b107e4a363cdff07d100ce', + 'url': 'http://malemotion.com/video/bete-de-concours.ltc', + 'md5': '3013e53a0afbde2878bc39998c33e8a5', 'info_dict': { - "title": "Bien dur", - "age_limit": 18, + 'id': 'ltc', + 'ext': 'mp4', + 'title': 'Bête de Concours', + 'age_limit': 18, }, - 'skip': 'This video has been deleted.' } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group("id") - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - - # Extract video URL - video_url = compat_urllib_parse.unquote( - self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL')) - - # Extract title + video_url = compat_urllib_parse.unquote(self._search_regex( + r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL')) video_title = self._html_search_regex( r'<title>(.*?)</title', webpage, 'title') - - # Extract video thumbnail video_thumbnail = self._search_regex( r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False) @@ -47,14 +37,12 @@ class MalemotionIE(InfoExtractor): 'format_id': 'mp4', 'preference': 1, }] + self._sort_formats(formats) return { 'id': video_id, 'formats': formats, - 'uploader': None, - 'upload_date': None, 'title': video_title, 'thumbnail': video_thumbnail, - 'description': None, 'age_limit': 18, } diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 858c1c0..8bc333b 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -3,10 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_parse_qs, compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( determine_ext, ExtractorError, int_or_none, diff --git a/youtube_dl/extractor/minhateca.py b/youtube_dl/extractor/minhateca.py new file mode 100644 index 0000000..14934b7 --- /dev/null +++ b/youtube_dl/extractor/minhateca.py @@ -0,0 +1,72 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + int_or_none, + parse_duration, + parse_filesize, +) + + +class MinhatecaIE(InfoExtractor): + _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.' + _TEST = { + 'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)', + 'info_dict': { + 'id': '125848331', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + 'thumbnail': 're:^https?://.*\.jpg$', + 'filesize_approx': 1530000, + 'duration': 9, + 'view_count': int, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + token = self._html_search_regex( + r'<input name="__RequestVerificationToken".*?value="([^"]+)"', + webpage, 'request token') + token_data = [ + ('fileId', video_id), + ('__RequestVerificationToken', token), + ] + req = compat_urllib_request.Request( + 'http://minhateca.com.br/action/License/Download', + data=compat_urllib_parse.urlencode(token_data)) + req.add_header('Content-Type', 'application/x-www-form-urlencoded') + data = self._download_json( + req, video_id, note='Downloading metadata') + + video_url = data['redirectUrl'] + title_str = self._html_search_regex( + r'<h1.*?>(.*?)</h1>', webpage, 'title') + title, _, ext = title_str.rpartition('.') + filesize_approx = parse_filesize(self._html_search_regex( + r'<p class="fileSize">(.*?)</p>', + webpage, 'file size approximation', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'(?s)<p class="fileLeng[ht][th]">.*?class="bold">(.*?)<', + webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'<p class="downloadsCounter">([0-9]+)</p>', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': ext, + 'filesize_approx': filesize_approx, + 'duration': duration, + 'view_count': view_count, + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 807b1dc..3c61a85 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -5,8 +5,10 @@ import json from .common import InfoExtractor from .youtube import YoutubeIE -from ..utils import ( +from ..compat import ( compat_urlparse, +) +from ..utils import ( clean_html, ExtractorError, get_element_by_id, @@ -15,7 +17,7 @@ from ..utils import ( class TechTVMITIE(InfoExtractor): IE_NAME = 'techtv.mit.edu' - _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)' + _VALID_URL = r'https?://techtv\.mit\.edu/(?:videos|embeds)/(?P<id>\d+)' _TEST = { 'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set', @@ -29,8 +31,7 @@ class TechTVMITIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) raw_page = self._download_webpage( 'http://techtv.mit.edu/videos/%s' % video_id, video_id) clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page) @@ -104,7 +105,10 @@ class OCWMITIE(InfoExtractor): 'ext': 'mp4', 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence', 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.', - #'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt' + 'upload_date': '20121109', + 'uploader_id': 'MIT', + 'uploader': 'MIT OpenCourseWare', + # 'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt' } }, { @@ -113,8 +117,11 @@ class OCWMITIE(InfoExtractor): 'id': '7K1sB05pE0A', 'ext': 'mp4', 'title': 'Session 1: Introduction to Derivatives', + 'upload_date': '20090818', + 'uploader_id': 'MIT', + 'uploader': 'MIT OpenCourseWare', 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.', - #'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT' + # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT' } } ] diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 6691521..2567583 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,12 +1,13 @@ from __future__ import unicode_literals -import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, +) +from ..utils import ( get_element_by_attribute, parse_duration, strip_jsonp, @@ -15,7 +16,7 @@ from ..utils import ( class MiTeleIE(InfoExtractor): IE_NAME = 'mitele.es' - _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/' _TEST = { 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', @@ -31,12 +32,10 @@ class MiTeleIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = mobj.group('episode') + episode = self._match_id(url) webpage = self._download_webpage(url, episode) embed_data_json = self._search_regex( - r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', - flags=re.DOTALL + r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', ).replace('\'', '"') embed_data = json.loads(embed_data_json) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index bb8937c..07d1945 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -3,8 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( ExtractorError, HEADRequest, int_or_none, @@ -70,7 +72,7 @@ class MixcloudIE(InfoExtractor): raise ExtractorError('Unable to extract track url') PREFIX = ( - r'<div class="cloudcast-play-button-container[^"]*?"' + r'<span class="play-button[^"]*?"' r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+') title = self._html_search_regex( PREFIX + r'm-title="([^"]+)"', webpage, 'title') diff --git a/youtube_dl/extractor/moevideo.py b/youtube_dl/extractor/moevideo.py index 2ff79b9..5a66302 100644 --- a/youtube_dl/extractor/moevideo.py +++ b/youtube_dl/extractor/moevideo.py @@ -5,10 +5,12 @@ import json import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( + ExtractorError, int_or_none, ) @@ -50,7 +52,8 @@ class MoeVideoIE(InfoExtractor): 'height': 296, 'duration': 6027, 'filesize': 588257923, - } + }, + 'skip': 'Video has been removed', }, ] diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index d658647..2cec12d 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -4,7 +4,7 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, @@ -12,7 +12,7 @@ from ..utils import ( class MofosexIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' + _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)' _TEST = { 'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', 'md5': '1b2eb47ac33cc75d4a80e3026b613c5a', @@ -26,7 +26,7 @@ class MofosexIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py index 1c4f589..5de719b 100644 --- a/youtube_dl/extractor/moniker.py +++ b/youtube_dl/extractor/moniker.py @@ -5,7 +5,7 @@ import os.path import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -37,10 +37,9 @@ class MonikerIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) orig_webpage = self._download_webpage(url, video_id) + fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) data = dict(fields) diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index 34a4bec..7603af5 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -1,14 +1,15 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_request, compat_urllib_parse, ) +from ..utils import ( + ExtractorError, +) class MooshareIE(InfoExtractor): @@ -43,9 +44,7 @@ class MooshareIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) page = self._download_webpage(url, video_id, 'Downloading page') if re.search(r'>Video Not Found or Deleted<', page) is not None: @@ -64,8 +63,7 @@ class MooshareIE(InfoExtractor): 'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - self.to_screen('%s: Waiting for timeout' % video_id) - time.sleep(5) + self._sleep(5, video_id) video_page = self._download_webpage(request, video_id, 'Downloading video page') diff --git a/youtube_dl/extractor/motorsport.py b/youtube_dl/extractor/motorsport.py index 7c0ec6a..c1a482d 100644 --- a/youtube_dl/extractor/motorsport.py +++ b/youtube_dl/extractor/motorsport.py @@ -1,63 +1,49 @@ # coding: utf-8 from __future__ import unicode_literals -import hashlib -import json -import re -import time - from .common import InfoExtractor -from ..utils import ( - compat_parse_qs, - compat_str, - int_or_none, +from ..compat import ( + compat_urlparse, ) class MotorsportIE(InfoExtractor): IE_DESC = 'motorsport.com' - _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])' + _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])' _TEST = { 'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/', - 'md5': '5592cb7c5005d9b2c163df5ac3dc04e4', 'info_dict': { - 'id': '7063', + 'id': '2-T3WuR-KMM', 'ext': 'mp4', 'title': 'Red Bull Racing: 2014 Rules Explained', - 'duration': 207, + 'duration': 208, 'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.', - 'uploader': 'rainiere', - 'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$' - } + 'uploader': 'mcomstaff', + 'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ', + 'upload_date': '20140903', + 'thumbnail': r're:^https?://.+\.jpg$' + }, + 'add_ie': ['Youtube'], + 'params': { + 'skip_download': True, + }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - + display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - flashvars_code = self._html_search_regex( - r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars') - flashvars = compat_parse_qs(flashvars_code) - params = json.loads(flashvars['parameters'][0]) - - e = compat_str(int(time.time()) + 24 * 60 * 60) - base_video_url = params['location'] + '?e=' + e - s = 'h3hg713fh32' - h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest() - video_url = base_video_url + '&h=' + h - uploader = self._html_search_regex( - r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage, - 'uploader', fatal=False) + iframe_path = self._html_search_regex( + r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage, + 'iframe path') + iframe = self._download_webpage( + compat_urlparse.urljoin(url, iframe_path), display_id, + 'Downloading iframe') + youtube_id = self._search_regex( + r'www.youtube.com/embed/(.{11})', iframe, 'youtube id') return { - 'id': params['video_id'], + '_type': 'url_transparent', 'display_id': display_id, - 'title': params['title'], - 'url': video_url, - 'description': params.get('description'), - 'thumbnail': params.get('main_thumb'), - 'duration': int_or_none(params.get('duration')), - 'uploader': uploader, + 'url': 'https://youtube.com/watch?v=%s' % youtube_id, } diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py index 456807d..04e17d0 100644 --- a/youtube_dl/extractor/movieclips.py +++ b/youtube_dl/extractor/movieclips.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, +) from ..utils import ( ExtractorError, - compat_str, clean_html, ) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index b482d6d..5ebc780 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py index e626146..83414a2 100644 --- a/youtube_dl/extractor/myspace.py +++ b/youtube_dl/extractor/myspace.py @@ -88,6 +88,7 @@ class MySpaceIE(InfoExtractor): self.report_warning( '%s: No downloadable song on this page' % video_id) return + def search_data(name): return self._search_regex( r'''data-%s=([\'"])(?P<data>.*?)\1''' % name, diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py index 51e5408..5b9b9fb 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -2,9 +2,10 @@ from __future__ import unicode_literals import os.path from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, - +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/myvidster.py b/youtube_dl/extractor/myvidster.py new file mode 100644 index 0000000..a94ab83 --- /dev/null +++ b/youtube_dl/extractor/myvidster.py @@ -0,0 +1,29 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class MyVidsterIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?myvidster\.com/video/(?P<id>\d+)/' + + _TEST = { + 'url': 'http://www.myvidster.com/video/32059805/Hot_chemistry_with_raw_love_making', + 'md5': '95296d0231c1363222c3441af62dc4ca', + 'info_dict': { + 'id': '3685814', + 'title': 'md5:7d8427d6d02c4fbcef50fe269980c749', + 'upload_date': '20141027', + 'uploader_id': 'utkualp', + 'ext': 'mp4', + 'age_limit': 18, + }, + 'add_ie': ['XHamster'], + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + return self.url_result(self._html_search_regex( + r'rel="videolink" href="(?P<real_url>.*)">', + webpage, 'real video url')) diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index fbe34de..c10405f 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -4,8 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( ExtractorError, clean_html, ) @@ -26,9 +28,9 @@ class NaverIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"', webpage) if m_id is None: diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index f69fe09..862b706 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( remove_end, @@ -10,8 +8,8 @@ from ..utils import ( class NBAIE(InfoExtractor): - _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$' - _TEST = { + _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$' + _TESTS = [{ 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', 'md5': 'c0edcfc37607344e2ff8f13c378c88a4', 'info_dict': { @@ -21,12 +19,13 @@ class NBAIE(InfoExtractor): 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'duration': 181, }, - } + }, { + 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' @@ -37,7 +36,7 @@ class NBAIE(InfoExtractor): description = self._og_search_description(webpage) duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration', fatal=False)) + self._html_search_meta('duration', webpage, 'duration')) return { 'id': shortened_video_id, diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 7b54490..690c46b 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -4,31 +4,47 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, +) +from ..utils import ( ExtractorError, find_xpath_attr, ) class NBCIE(InfoExtractor): - _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)' - - _TEST = { - 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', - # md5 checksum is not stable - 'info_dict': { - 'id': 'bTmnLCvIbaaH', - 'ext': 'flv', - 'title': 'I Am a Firefighter', - 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', + _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)' + + _TESTS = [ + { + 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', + # md5 checksum is not stable + 'info_dict': { + 'id': 'bTmnLCvIbaaH', + 'ext': 'flv', + 'title': 'I Am a Firefighter', + 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', + }, }, - } + { + 'url': 'http://www.nbc.com/the-tonight-show/episodes/176', + 'info_dict': { + 'id': 'XwU9KZkp98TH', + 'ext': 'flv', + 'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen', + 'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.', + }, + 'skip': 'Only works from US', + }, + ] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url') + theplatform_url = self._search_regex( + '(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"', + webpage, 'theplatform url').replace('_no_endcard', '') if theplatform_url.startswith('//'): theplatform_url = 'http:' + theplatform_url return self.url_result(theplatform_url) diff --git a/youtube_dl/extractor/nerdcubed.py b/youtube_dl/extractor/nerdcubed.py new file mode 100644 index 0000000..efc903a --- /dev/null +++ b/youtube_dl/extractor/nerdcubed.py @@ -0,0 +1,35 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import datetime + +from .common import InfoExtractor + + +class NerdCubedFeedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nerdcubed\.co\.uk/feed\.json' + _TEST = { + 'url': 'http://www.nerdcubed.co.uk/feed.json', + 'info_dict': { + 'title': 'nerdcubed.co.uk feed', + }, + 'playlist_mincount': 1300, + } + + def _real_extract(self, url): + feed = self._download_json(url, url, "Downloading NerdCubed JSON feed") + + entries = [{ + '_type': 'url', + 'title': feed_entry['title'], + 'uploader': feed_entry['source']['name'] if feed_entry['source'] else None, + 'upload_date': datetime.datetime.strptime(feed_entry['date'], '%Y-%m-%d').strftime('%Y%m%d'), + 'url': "http://www.youtube.com/watch?v=" + feed_entry['youtube_id'], + } for feed_entry in feed] + + return { + '_type': 'playlist', + 'title': 'nerdcubed.co.uk feed', + 'id': 'nerdcubed-feed', + 'entries': entries, + } diff --git a/youtube_dl/extractor/netzkino.py b/youtube_dl/extractor/netzkino.py new file mode 100644 index 0000000..93567d1 --- /dev/null +++ b/youtube_dl/extractor/netzkino.py @@ -0,0 +1,86 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + int_or_none, + js_to_json, + parse_iso8601, +) + + +class NetzkinoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/(?P<category>[^/]+)/(?P<id>[^/]+)' + + _TEST = { + 'url': 'http://www.netzkino.de/#!/scifikino/rakete-zum-mond', + 'md5': '92a3f8b76f8d7220acce5377ea5d4873', + 'info_dict': { + 'id': 'rakete-zum-mond', + 'ext': 'mp4', + 'title': 'Rakete zum Mond (Endstation Mond, Destination Moon)', + 'comments': 'mincount:3', + 'description': 'md5:1eddeacc7e62d5a25a2d1a7290c64a28', + 'upload_date': '20120813', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1344858571, + 'age_limit': 12, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + category_id = mobj.group('category') + video_id = mobj.group('id') + + api_url = 'http://api.netzkino.de.simplecache.net/capi-2.0a/categories/%s.json?d=www' % category_id + api_info = self._download_json(api_url, video_id) + info = next( + p for p in api_info['posts'] if p['slug'] == video_id) + custom_fields = info['custom_fields'] + + production_js = self._download_webpage( + 'http://www.netzkino.de/beta/dist/production.min.js', video_id, + note='Downloading player code') + avo_js = self._search_regex( + r'window\.avoCore\s*=.*?urlTemplate:\s*(\{.*?"\})', + production_js, 'URL templates') + templates = self._parse_json( + avo_js, video_id, transform_source=js_to_json) + + suffix = { + 'hds': '.mp4/manifest.f4m', + 'hls': '.mp4/master.m3u8', + 'pmd': '.mp4', + } + film_fn = custom_fields['Streaming'][0] + formats = [{ + 'format_id': key, + 'ext': 'mp4', + 'url': tpl.replace('{}', film_fn) + suffix[key], + } for key, tpl in templates.items()] + self._sort_formats(formats) + + comments = [{ + 'timestamp': parse_iso8601(c.get('date'), delimiter=' '), + 'id': c['id'], + 'author': c['name'], + 'html': c['content'], + 'parent': 'root' if c.get('parent', 0) == 0 else c['parent'], + } for c in info.get('comments', [])] + + return { + 'id': video_id, + 'formats': formats, + 'comments': comments, + 'title': info['title'], + 'age_limit': int_or_none(custom_fields.get('FSK')[0]), + 'timestamp': parse_iso8601(info.get('date'), delimiter=' '), + 'description': clean_html(info.get('content')), + 'thumbnail': info.get('thumbnail'), + 'playlist_title': api_info.get('title'), + 'playlist_id': category_id, + } diff --git a/youtube_dl/extractor/nfb.py b/youtube_dl/extractor/nfb.py index 7ce1d48..ea07725 100644 --- a/youtube_dl/extractor/nfb.py +++ b/youtube_dl/extractor/nfb.py @@ -1,9 +1,7 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, compat_urllib_parse, ) @@ -12,7 +10,7 @@ from ..utils import ( class NFBIE(InfoExtractor): IE_NAME = 'nfb' IE_DESC = 'National Film Board of Canada' - _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)' + _VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)' _TEST = { 'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny', @@ -32,10 +30,10 @@ class NFBIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page') + video_id = self._match_id(url) + page = self._download_webpage( + 'https://www.nfb.ca/film/%s' % video_id, video_id, + 'Downloading film page') uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"', page, 'director id', fatal=False) diff --git a/youtube_dl/extractor/nfl.py b/youtube_dl/extractor/nfl.py index cc7c921..606e229 100644 --- a/youtube_dl/extractor/nfl.py +++ b/youtube_dl/extractor/nfl.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, - compat_urllib_parse_urlparse, int_or_none, remove_end, ) diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index bdcf7e2..d3a4fc5 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -2,11 +2,13 @@ from __future__ import unicode_literals import re import json +import os from .common import InfoExtractor from ..compat import ( compat_urlparse, compat_urllib_parse, + compat_urllib_parse_urlparse ) from ..utils import ( unified_strdate, @@ -24,9 +26,12 @@ class NHLBaseInfoExtractor(InfoExtractor): initial_video_url = info['publishPoint'] if info['formats'] == '1': + parsed_url = compat_urllib_parse_urlparse(initial_video_url) + filename, ext = os.path.splitext(parsed_url.path) + path = '%s_sd%s' % (filename, ext) data = compat_urllib_parse.urlencode({ 'type': 'fvod', - 'path': initial_video_url.replace('.mp4', '_sd.mp4'), + 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:]) }) path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data path_doc = self._download_xml( @@ -49,7 +54,7 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): IE_NAME = 'nhl.com' - _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9a-z-]+)' + _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', @@ -74,6 +79,17 @@ class NHLIE(NHLBaseInfoExtractor): 'upload_date': '20141011', }, }, { + 'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802', + 'md5': 'c78fc64ea01777e426cfc202b746c825', + 'info_dict': { + 'id': '58665', + 'ext': 'flv', + 'title': 'Classic Game In Six - April 22, 1979', + 'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.', + 'duration': 400, + 'upload_date': '20100129' + }, + }, { 'url': 'http://video.flames.nhl.com/videocenter/console?id=630616', 'only_matching': True, }] @@ -90,7 +106,7 @@ class NHLIE(NHLBaseInfoExtractor): class NHLVideocenterIE(NHLBaseInfoExtractor): IE_NAME = 'nhl.com:videocenter' IE_DESC = 'NHL videocenter category' - _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' + _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$' _TEST = { 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999', 'info_dict': { diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 1d9c1a0..4c18904 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -5,14 +5,16 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, compat_urlparse, - unified_strdate, - parse_duration, - int_or_none, +) +from ..utils import ( ExtractorError, + int_or_none, + parse_duration, + unified_strdate, ) diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py index 16a02ad..7f842b5 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -23,6 +23,9 @@ class NineGagIE(InfoExtractor): "ext": "mp4", "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)", "title": "\"People Are Awesome 2013\" Is Absolutely Awesome", + 'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA', + 'uploader': 'CompilationChannel', + 'upload_date': '20131110', "view_count": int, "thumbnail": "re:^https?://", }, @@ -35,6 +38,9 @@ class NineGagIE(InfoExtractor): 'display_id': 'alternate-banned-opening-scene-of-gravity', "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.", 'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie", + 'uploader': 'Krishna Shenoi', + 'upload_date': '20140401', + 'uploader_id': 'krishnashenoi93', }, }] diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index 7d2ff7b..251e6da 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -6,13 +6,15 @@ import time import hashlib from .common import InfoExtractor -from ..utils import ( - compat_urllib_request, +from ..compat import ( + compat_str, compat_urllib_parse, - ExtractorError, + compat_urllib_request, +) +from ..utils import ( clean_html, + ExtractorError, unified_strdate, - compat_str, ) diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py index 3d35b11..c13ff0d 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -22,7 +22,11 @@ class NormalbootsIE(InfoExtractor): 'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/', 'uploader': 'JonTron', 'upload_date': '20140125', - } + }, + 'params': { + # rtmp download + 'skip_download': True, + }, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py index f3be8f5..f5ef856 100644 --- a/youtube_dl/extractor/nosvideo.py +++ b/youtube_dl/extractor/nosvideo.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, urlencode_postdata, xpath_text, xpath_with_ns, @@ -32,8 +34,7 @@ class NosVideoIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) fields = { 'id': video_id, diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 38d05e4..04d7798 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urlparse, +) from ..utils import ( ExtractorError, - compat_urlparse ) diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index ecb38de..dec09cd 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE): IE_NAME = 'nowvideo' IE_DESC = 'NowVideo' - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co|li)'} _HOST = 'www.nowvideo.ch' diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index ce31694..175b145 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -1,18 +1,26 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - unified_strdate, + fix_xml_ampersands, parse_duration, qualities, strip_jsonp, + unified_strdate, url_basename, ) -class NPOIE(InfoExtractor): +class NPOBaseIE(InfoExtractor): + def _get_token(self, video_id): + token_page = self._download_webpage( + 'http://ida.omroep.nl/npoplayer/i.js', + video_id, note='Downloading token') + return self._search_regex( + r'npoplayer\.token = "(.+?)"', token_page, 'token') + + +class NPOIE(NPOBaseIE): IE_NAME = 'npo.nl' _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)' @@ -51,12 +59,35 @@ class NPOIE(InfoExtractor): 'upload_date': '20130225', 'duration': 3000, }, - } + }, + { + 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', + 'info_dict': { + 'id': 'WO_VPRO_043706', + 'ext': 'wmv', + 'title': 'De nieuwe mens - Deel 1', + 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', + 'duration': 4680, + }, + 'params': { + # mplayer mms download + 'skip_download': True, + } + }, + # non asf in streams + { + 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771', + 'md5': 'b3da13de374cbe2d5332a7e910bef97f', + 'info_dict': { + 'id': 'WO_NOS_762771', + 'ext': 'mp4', + 'title': 'Hoe gaat Europa verder na Parijs?', + }, + }, ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) return self._get_info(video_id) def _get_info(self, video_id): @@ -66,39 +97,68 @@ class NPOIE(InfoExtractor): # We have to remove the javascript callback transform_source=strip_jsonp, ) - token_page = self._download_webpage( - 'http://ida.omroep.nl/npoplayer/i.js', - video_id, - note='Downloading token' - ) - token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token') + + token = self._get_token(video_id) formats = [] - quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) - for format_id in metadata['pubopties']: - format_info = self._download_json( - 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token), - video_id, 'Downloading %s JSON' % format_id) - if format_info.get('error_code', 0) or format_info.get('errorcode', 0): - continue - streams = format_info.get('streams') - if streams: - video_info = self._download_json( - streams[0] + '&type=json', - video_id, 'Downloading %s stream JSON' % format_id) - else: - video_info = format_info - video_url = video_info.get('url') - if not video_url: - continue - if format_id == 'adaptive': - formats.extend(self._extract_m3u8_formats(video_url, video_id)) - else: + + pubopties = metadata.get('pubopties') + if pubopties: + quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) + for format_id in pubopties: + format_info = self._download_json( + 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' + % (video_id, format_id, token), + video_id, 'Downloading %s JSON' % format_id) + if format_info.get('error_code', 0) or format_info.get('errorcode', 0): + continue + streams = format_info.get('streams') + if streams: + video_info = self._download_json( + streams[0] + '&type=json', + video_id, 'Downloading %s stream JSON' % format_id) + else: + video_info = format_info + video_url = video_info.get('url') + if not video_url: + continue + if format_id == 'adaptive': + formats.extend(self._extract_m3u8_formats(video_url, video_id)) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'quality': quality(format_id), + }) + + streams = metadata.get('streams') + if streams: + for i, stream in enumerate(streams): + stream_url = stream.get('url') + if not stream_url: + continue + if '.asf' not in stream_url: + formats.append({ + 'url': stream_url, + 'quality': stream.get('kwaliteit'), + }) + continue + asx = self._download_xml( + stream_url, video_id, + 'Downloading stream %d ASX playlist' % i, + transform_source=fix_xml_ampersands) + ref = asx.find('./ENTRY/Ref') + if ref is None: + continue + video_url = ref.get('href') + if not video_url: + continue formats.append({ 'url': video_url, - 'format_id': format_id, - 'quality': quality(format_id), + 'ext': stream.get('formaat', 'asf'), + 'quality': stream.get('kwaliteit'), }) + self._sort_formats(formats) return { @@ -112,6 +172,83 @@ class NPOIE(InfoExtractor): } +class NPOLiveIE(NPOBaseIE): + IE_NAME = 'npo.nl:live' + _VALID_URL = r'https?://www\.npo\.nl/live/(?P<id>.+)' + + _TEST = { + 'url': 'http://www.npo.nl/live/npo-1', + 'info_dict': { + 'id': 'LI_NEDERLAND1_136692', + 'display_id': 'npo-1', + 'ext': 'mp4', + 'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'Livestream', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + live_id = self._search_regex( + r'data-prid="([^"]+)"', webpage, 'live id') + + metadata = self._download_json( + 'http://e.omroep.nl/metadata/%s' % live_id, + display_id, transform_source=strip_jsonp) + + token = self._get_token(display_id) + + formats = [] + + streams = metadata.get('streams') + if streams: + for stream in streams: + stream_type = stream.get('type').lower() + if stream_type == 'ss': + continue + stream_info = self._download_json( + 'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp' + % (stream.get('url'), token), + display_id, 'Downloading %s JSON' % stream_type) + if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0): + continue + stream_url = self._download_json( + stream_info['stream'], display_id, + 'Downloading %s URL' % stream_type, + transform_source=strip_jsonp) + if stream_type == 'hds': + f4m_formats = self._extract_f4m_formats(stream_url, display_id) + # f4m downloader downloads only piece of live stream + for f4m_format in f4m_formats: + f4m_format['preference'] = -1 + formats.extend(f4m_formats) + elif stream_type == 'hls': + formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4')) + else: + formats.append({ + 'url': stream_url, + }) + + self._sort_formats(formats) + + return { + 'id': live_id, + 'display_id': display_id, + 'title': self._live_title(metadata['titel']), + 'description': metadata['info'], + 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], + 'formats': formats, + 'is_live': True, + } + + class TegenlichtVproIE(NPOIE): IE_NAME = 'tegenlicht.vpro.nl' _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?' diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 96f0ae1..f6de260 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -7,8 +7,10 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, float_or_none, + parse_duration, unified_strdate, ) +from .subtitles import SubtitlesInfoExtractor class NRKIE(InfoExtractor): @@ -71,13 +73,13 @@ class NRKIE(InfoExtractor): } -class NRKTVIE(InfoExtractor): - _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})' +class NRKTVIE(SubtitlesInfoExtractor): + _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?' _TESTS = [ { 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'md5': '7b96112fbae1faf09a6f9ae1aff6cb84', + 'md5': 'adf2c5454fa2bf032f47a9f8fb351342', 'info_dict': { 'id': 'MUHH48000314', 'ext': 'flv', @@ -85,11 +87,11 @@ class NRKTVIE(InfoExtractor): 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'upload_date': '20140523', 'duration': 1741.52, - } + }, }, { 'url': 'http://tv.nrk.no/program/mdfp15000514', - 'md5': 'af01795a31f1cf7265c8657534d8077b', + 'md5': '383650ece2b25ecec996ad7b5bb2a384', 'info_dict': { 'id': 'mdfp15000514', 'ext': 'flv', @@ -97,42 +99,155 @@ class NRKTVIE(InfoExtractor): 'description': 'md5:654c12511f035aed1e42bdf5db3b206a', 'upload_date': '20140524', 'duration': 4605.0, - } + }, + }, + { + # single playlist video + 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + 'skip': 'Only works from Norway', }, + { + 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', + 'playlist': [ + { + 'md5': '9480285eff92d64f06e02a5367970a7a', + 'info_dict': { + 'id': 'MSPO40010515-part1', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + }, + { + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + }, + ], + 'info_dict': { + 'id': 'MSPO40010515', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + 'duration': 6947.5199999999995, + }, + 'skip': 'Only works from Norway', + } ] + def _seconds2str(self, s): + return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000) + + def _debug_print(self, txt): + if self._downloader.params.get('verbose', False): + self.to_screen('[debug] %s' % txt) + + def _extract_captions(self, subtitlesurl, video_id, baseurl): + url = "%s%s" % (baseurl, subtitlesurl) + self._debug_print('%s: Subtitle url: %s' % (video_id, url)) + captions = self._download_xml(url, video_id, 'Downloading subtitles') + lang = captions.get('lang', 'no') + ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}')) + srt = '' + for pos, p in enumerate(ps): + begin = parse_duration(p.get('begin')) + duration = parse_duration(p.get('dur')) + starttime = self._seconds2str(begin) + endtime = self._seconds2str(begin + duration) + text = '\n'.join(p.itertext()) + srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text) + return {lang: srt} + + def _extract_f4m(self, manifest_url, video_id): + return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + part_id = mobj.group('part_id') + baseurl = mobj.group('baseurl') - page = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_meta( + 'title', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') - title = self._html_search_meta('title', page, 'title') - description = self._html_search_meta('description', page, 'description') - thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False) - upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False)) - duration = float_or_none( - self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)) + thumbnail = self._html_search_regex( + r'data-posterimage="([^"]+)"', + webpage, 'thumbnail', fatal=False) + upload_date = unified_strdate(self._html_search_meta( + 'rightsfrom', webpage, 'upload date', fatal=False)) + duration = float_or_none(self._html_search_regex( + r'data-duration="([^"]+)"', + webpage, 'duration', fatal=False)) + + # playlist + parts = re.findall( + r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage) + if parts: + entries = [] + for current_part_id, stream_url, part_title in parts: + if part_id and current_part_id != part_id: + continue + video_part_id = '%s-part%s' % (video_id, current_part_id) + formats = self._extract_f4m(stream_url, video_part_id) + entries.append({ + 'id': video_part_id, + 'title': part_title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + }) + if part_id: + if entries: + return entries[0] + else: + playlist = self.playlist_result(entries, video_id, title, description) + playlist.update({ + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + }) + return playlist formats = [] - f4m_url = re.search(r'data-media="([^"]+)"', page) + f4m_url = re.search(r'data-media="([^"]+)"', webpage) if f4m_url: - formats.append({ - 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', - 'format_id': 'f4m', - 'ext': 'flv', - }) + formats.extend(self._extract_f4m(f4m_url.group(1), video_id)) - m3u8_url = re.search(r'data-hls-media="([^"]+)"', page) + m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage) if m3u8_url: - formats.append({ - 'url': m3u8_url.group(1), - 'format_id': 'm3u8', - }) - + formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4')) self._sort_formats(formats) + subtitles_url = self._html_search_regex( + r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"', + webpage, 'subtitle URL', default=None) + subtitles = None + if subtitles_url: + subtitles = self._extract_captions(subtitles_url, video_id, baseurl) + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + return { 'id': video_id, 'title': title, @@ -141,4 +256,5 @@ class NRKTVIE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/ntv.py b/youtube_dl/extractor/ntv.py index 13c8d79..ee740cd 100644 --- a/youtube_dl/extractor/ntv.py +++ b/youtube_dl/extractor/ntv.py @@ -130,7 +130,7 @@ class NTVIE(InfoExtractor): 'rtmp_conn': 'B:1', 'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128', 'page_url': 'http://www.ntv.ru', - 'flash_ver': 'LNX 11,2,202,341', + 'flash_version': 'LNX 11,2,202,341', 'rtmp_live': True, 'ext': 'flv', 'filesize': int(size.text), diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 449c8a6..57928f2 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -3,15 +3,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( parse_duration, unified_strdate, - compat_urllib_request, ) class NuvidIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)' _TEST = { 'url': 'http://m.nuvid.com/video/1310741/', 'md5': 'eab207b7ac4fccfb4e23c86201f11277', @@ -26,8 +28,7 @@ class NuvidIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) formats = [] diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index f17a528..d5b05c1 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -16,7 +16,6 @@ class OoyalaIE(InfoExtractor): { # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c', 'info_dict': { 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', 'ext': 'mp4', @@ -26,7 +25,6 @@ class OoyalaIE(InfoExtractor): }, { # Only available for ipad 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', - 'md5': '4b9754921fddb68106e48c142e2a01e6', 'info_dict': { 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', 'ext': 'mp4', diff --git a/youtube_dl/extractor/openfilm.py b/youtube_dl/extractor/openfilm.py new file mode 100644 index 0000000..2249657 --- /dev/null +++ b/youtube_dl/extractor/openfilm.py @@ -0,0 +1,70 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + compat_urllib_parse, + parse_age_limit, + int_or_none, +) + + +class OpenFilmIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)openfilm\.com/videos/(?P<id>.+)' + _TEST = { + 'url': 'http://www.openfilm.com/videos/human-resources-remastered', + 'md5': '42bcd88c2f3ec13b65edf0f8ad1cac37', + 'info_dict': { + 'id': '32736', + 'display_id': 'human-resources-remastered', + 'ext': 'mp4', + 'title': 'Human Resources (Remastered)', + 'description': 'Social Engineering in the 20th Century.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 7164, + 'timestamp': 1334756988, + 'upload_date': '20120418', + 'uploader_id': '41117', + 'view_count': int, + 'age_limit': 0, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + player = compat_urllib_parse.unquote_plus( + self._og_search_video_url(webpage)) + + video = json.loads(self._search_regex( + r'\bp=({.+?})(?:&|$)', player, 'video JSON')) + + video_url = '%s1.mp4' % video['location'] + video_id = video.get('video_id') + display_id = video.get('alias') or display_id + title = video.get('title') + description = video.get('description') + thumbnail = video.get('main_thumb') + duration = int_or_none(video.get('duration')) + timestamp = parse_iso8601(video.get('dt_published'), ' ') + uploader_id = video.get('user_id') + view_count = int_or_none(video.get('views_count')) + age_limit = parse_age_limit(video.get('age_limit')) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 572a234..4e29339 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -17,24 +17,39 @@ from ..utils import ( class ORFTVthekIE(InfoExtractor): IE_NAME = 'orf:tvthek' IE_DESC = 'ORF TVthek' - _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)' - - _TEST = { - 'url': 'http://tvthek.orf.at/program/matinee-Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7317210/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319746/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319747', - 'file': '7319747.mp4', - 'md5': 'bd803c5d8c32d3c64a0ea4b4eeddf375', - 'info_dict': { - 'title': 'Was Sie schon immer über Klassik wissen wollten', - 'description': 'md5:0ddf0d5f0060bd53f744edaa5c2e04a4', - 'duration': 3508, - 'upload_date': '20140105', - }, - 'skip': 'Blocked outside of Austria', - } + _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389', + 'playlist': [{ + 'md5': '2942210346ed779588f428a92db88712', + 'info_dict': { + 'id': '8896777', + 'ext': 'mp4', + 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde', + 'description': 'md5:c1272f0245537812d4e36419c207b67d', + 'duration': 2668, + 'upload_date': '20141208', + }, + }], + 'skip': 'Blocked outside of Austria / Germany', + }, { + 'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256', + 'playlist': [{ + 'md5': '68f543909aea49d621dfc7703a11cfaf', + 'info_dict': { + 'id': '7982259', + 'ext': 'mp4', + 'title': 'Best of Ingrid Thurnher', + 'upload_date': '20140527', + 'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".', + } + }], + '_skip': 'Blocked outside of Austria / Germany', + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) data_json = self._search_regex( @@ -43,7 +58,9 @@ class ORFTVthekIE(InfoExtractor): def get_segments(all_data): for data in all_data: - if data['name'] == 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM': + if data['name'] in ( + 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM', + 'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'): return data['values']['segments'] sdata = get_segments(all_data) @@ -111,18 +128,19 @@ class ORFTVthekIE(InfoExtractor): } -# Audios on ORF radio are only available for 7 days, so we can't add tests. - - class ORFOE1IE(InfoExtractor): IE_NAME = 'orf:oe1' IE_DESC = 'Radio Österreich 1' - _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + _VALID_URL = r'http://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)' - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') + # Audios on ORF radio are only available for 7 days, so we can't add tests. + _TEST = { + 'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211', + 'only_matching': True, + } + def _real_extract(self, url): + show_id = self._match_id(url) data = self._download_json( 'http://oe1.orf.at/programm/%s/konsole' % show_id, show_id @@ -145,7 +163,7 @@ class ORFOE1IE(InfoExtractor): class ORFFM4IE(InfoExtractor): - IE_DESC = 'orf:fm4' + IE_NAME = 'orf:fm4' IE_DESC = 'radio FM4' _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 6118ed5..afce732 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, unified_strdate, US_RATINGS, ) @@ -151,6 +152,19 @@ class PBSIE(InfoExtractor): info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) + redirect_url = info['alternate_encoding']['url'] + redirect_info = self._download_json( + redirect_url + '?format=json', display_id, + 'Downloading video url info') + if redirect_info['status'] == 'error': + if redirect_info['http_code'] == 403: + message = ( + 'The video is not available in your region due to ' + 'right restrictions') + else: + message = redirect_info['message'] + raise ExtractorError(message, expected=True) + rating_str = info.get('rating') if rating_str is not None: rating_str = rating_str.rpartition('-')[2] @@ -160,7 +174,7 @@ class PBSIE(InfoExtractor): 'id': video_id, 'display_id': display_id, 'title': info['title'], - 'url': info['alternate_encoding']['url'], + 'url': redirect_info['url'], 'ext': 'mp4', 'description': info['program'].get('description'), 'thumbnail': info.get('image_url'), diff --git a/youtube_dl/extractor/photobucket.py b/youtube_dl/extractor/photobucket.py index b4389e0..c66db3c 100644 --- a/youtube_dl/extractor/photobucket.py +++ b/youtube_dl/extractor/photobucket.py @@ -4,16 +4,17 @@ import json import re from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..compat import compat_urllib_parse class PhotobucketIE(InfoExtractor): _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))' _TEST = { 'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0', - 'file': 'zpsc0c3b9fa.mp4', 'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99', 'info_dict': { + 'id': 'zpsc0c3b9fa', + 'ext': 'mp4', 'timestamp': 1367669341, 'upload_date': '20130504', 'uploader': 'rachaneronas', diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py index 1788047..45716c7 100644 --- a/youtube_dl/extractor/played.py +++ b/youtube_dl/extractor/played.py @@ -5,11 +5,13 @@ import re import os.path from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) +from ..utils import ( + ExtractorError, +) class PlayedIE(InfoExtractor): @@ -24,11 +26,11 @@ class PlayedIE(InfoExtractor): 'ext': 'flv', 'title': 'youtube-dl_test_video.mp4', }, + 'skip': 'Removed for copyright infringement.', # oh wow } def _real_extract(self, url): video_id = self._match_id(url) - orig_webpage = self._download_webpage(url, video_id) m_error = re.search( diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py index ebc0468..9576aed 100644 --- a/youtube_dl/extractor/playfm.py +++ b/youtube_dl/extractor/playfm.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, float_or_none, int_or_none, diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py index cd3905a..c3e667e 100644 --- a/youtube_dl/extractor/playvid.py +++ b/youtube_dl/extractor/playvid.py @@ -3,31 +3,31 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, +) from ..utils import ( - ExtractorError, clean_html, - compat_urllib_parse, + ExtractorError, ) class PlayvidIE(InfoExtractor): - _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)' + _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)' _TEST = { - 'url': 'http://www.playvid.com/watch/agbDDi7WZTV', - 'md5': '44930f8afa616efdf9482daf4fe53e1e', + 'url': 'http://www.playvid.com/watch/RnmBNgtrrJu', + 'md5': 'ffa2f6b2119af359f544388d8c01eb6c', 'info_dict': { - 'id': 'agbDDi7WZTV', + 'id': 'RnmBNgtrrJu', 'ext': 'mp4', - 'title': 'Michelle Lewin in Miami Beach', - 'duration': 240, + 'title': 'md5:9256d01c6317e3f703848b5906880dc8', + 'duration': 82, 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) m_error = re.search( diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index bac484c..954dfcc 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -8,7 +8,6 @@ from ..utils import ( int_or_none, js_to_json, qualities, - determine_ext, ) @@ -45,13 +44,18 @@ class PornHdIE(InfoExtractor): thumbnail = self._search_regex( r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False) - quality = qualities(['SD', 'HD']) - formats = [{ - 'url': source['file'], - 'format_id': '%s-%s' % (source['label'], determine_ext(source['file'])), - 'quality': quality(source['label']), - } for source in json.loads(js_to_json(self._search_regex( - r"(?s)'sources'\s*:\s*(\[.+?\])", webpage, 'sources')))] + quality = qualities(['sd', 'hd']) + sources = json.loads(js_to_json(self._search_regex( + r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}\);", webpage, 'sources'))) + formats = [] + for container, s in sources.items(): + for qname, video_url in s.items(): + formats.append({ + 'url': video_url, + 'container': container, + 'format_id': '%s-%s' % (container, qname), + 'quality': quality(qname), + }) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 2ca15b7..634142d 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -4,10 +4,12 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse, compat_urllib_parse_urlparse, compat_urllib_request, - compat_urllib_parse, +) +from ..utils import ( str_to_int, ) from ..aes import ( @@ -16,7 +18,7 @@ from ..aes import ( class PornHubIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)' + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)' _TEST = { 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', 'md5': '882f488fa1f0026f023f33576004a2ed', diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py index 5253aa3..34735c5 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -1,56 +1,94 @@ from __future__ import unicode_literals -import re +import json from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( - compat_urllib_parse, - - unified_strdate, + int_or_none, ) class PornotubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)' _TEST = { - 'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', - 'md5': '374dd6dcedd24234453b295209aa69b6', + 'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science', + 'md5': '60fc5a4f0d93a97968fc7999d98260c9', 'info_dict': { - 'id': '1689755', - 'ext': 'flv', - 'upload_date': '20090708', - 'title': 'Marilyn-Monroe-Bathing', - 'age_limit': 18 + 'id': '4964', + 'ext': 'mp4', + 'upload_date': '20141203', + 'title': 'Weird Hot and Wet Science', + 'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0', + 'categories': ['Adult Humor', 'Blondes'], + 'uploader': 'Alpha Blue Archives', + 'thumbnail': 're:^https?://.*\\.jpg$', + 'timestamp': 1417582800, + 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + video_id = self._match_id(url) - video_id = mobj.group('videoid') - video_title = mobj.group('title') + # Fetch origin token + js_config = self._download_webpage( + 'http://www.pornotube.com/assets/src/app/config.js', video_id, + note='Download JS config') + originAuthenticationSpaceKey = self._search_regex( + r"constant\('originAuthenticationSpaceKey',\s*'([^']+)'", + js_config, 'originAuthenticationSpaceKey') + + # Fetch actual token + token_req_data = { + 'authenticationSpaceKey': originAuthenticationSpaceKey, + 'credentials': 'Clip Application', + } + token_req = compat_urllib_request.Request( + 'https://api.aebn.net/auth/v1/token/primal', + data=json.dumps(token_req_data).encode('utf-8')) + token_req.add_header('Content-Type', 'application/json') + token_req.add_header('Origin', 'http://www.pornotube.com') + token_answer = self._download_json( + token_req, video_id, note='Requesting primal token') + token = token_answer['tokenKey'] - # Get webpage content - webpage = self._download_webpage(url, video_id) + # Get video URL + delivery_req = compat_urllib_request.Request( + 'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id) + delivery_req.add_header('Authorization', token) + delivery_info = self._download_json( + delivery_req, video_id, note='Downloading delivery information') + video_url = delivery_info['mediaUrl'] - # Get the video URL - VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') - video_url = compat_urllib_parse.unquote(video_url) + # Get additional info (title etc.) + info_req = compat_urllib_request.Request( + 'https://api.aebn.net/content/v1/clips/%s?expand=' + 'title,description,primaryImageNumber,startSecond,endSecond,' + 'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,' + 'movie.studios,stars.name,studios.name,categories.name,' + 'clipActive,movieActive,publishDate,orientations' % video_id) + info_req.add_header('Authorization', token) + info = self._download_json( + info_req, video_id, note='Downloading metadata') - # Get the uploaded date - VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - age_limit = self._rta_search(webpage) + timestamp = int_or_none(info.get('publishDate'), scale=1000) + uploader = info.get('studios', [{}])[0].get('name') + movie_id = info['movie']['movieId'] + thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % ( + movie_id, movie_id, info['primaryImageNumber']) + categories = [c['name'] for c in info.get('categories')] return { 'id': video_id, 'url': video_url, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'age_limit': age_limit, + 'title': info['title'], + 'description': info.get('description'), + 'timestamp': timestamp, + 'uploader': uploader, + 'thumbnail': thumbnail, + 'categories': categories, + 'age_limit': 18, } diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py index 7fcde08..f536e6e 100644 --- a/youtube_dl/extractor/promptfile.py +++ b/youtube_dl/extractor/promptfile.py @@ -4,12 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, - determine_ext, +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) +from ..utils import ( + determine_ext, + ExtractorError, +) class PromptFileIE(InfoExtractor): diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 32d747e..385681d 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -5,8 +5,10 @@ import re from hashlib import sha1 from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( unified_strdate, ) @@ -85,7 +87,7 @@ class ProSiebenSat1IE(InfoExtractor): 'ext': 'mp4', 'title': 'Im Interview: Kai Wiesinger', 'description': 'md5:e4e5370652ec63b95023e914190b4eb9', - 'upload_date': '20140225', + 'upload_date': '20140203', 'duration': 522.56, }, 'params': { @@ -100,7 +102,7 @@ class ProSiebenSat1IE(InfoExtractor): 'ext': 'mp4', 'title': 'Jagd auf Fertigkost im Elsthal - Teil 2', 'description': 'md5:2669cde3febe9bce13904f701e774eb6', - 'upload_date': '20140225', + 'upload_date': '20141014', 'duration': 2410.44, }, 'params': { @@ -152,12 +154,22 @@ class ProSiebenSat1IE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.prosieben.de/tv/joko-gegen-klaas/videos/playlists/episode-8-ganze-folge-playlist', + 'info_dict': { + 'id': '439664', + 'title': 'Episode 8 - Ganze Folge - Playlist', + 'description': 'md5:63b8963e71f481782aeea877658dec84', + }, + 'playlist_count': 2, + }, ] _CLIPID_REGEXES = [ r'"clip_id"\s*:\s+"(\d+)"', r'clipid: "(\d+)"', r'clip[iI]d=(\d+)', + r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)", ] _TITLE_REGEXES = [ r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', @@ -178,11 +190,19 @@ class ProSiebenSat1IE(InfoExtractor): r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>', r'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>', ] + _PAGE_TYPE_REGEXES = [ + r'<meta name="page_type" content="([^"]+)">', + r"'itemType'\s*:\s*'([^']*)'", + ] + _PLAYLIST_ID_REGEXES = [ + r'content[iI]d=(\d+)', + r"'itemId'\s*:\s*'([^']*)'", + ] + _PLAYLIST_CLIP_REGEXES = [ + r'(?s)data-qvt=.+?<a href="([^"]+)"', + ] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - + def _extract_clip(self, url, webpage): clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id') access_token = 'testclient' @@ -281,3 +301,31 @@ class ProSiebenSat1IE(InfoExtractor): 'duration': duration, 'formats': formats, } + + def _extract_playlist(self, url, webpage): + playlist_id = self._html_search_regex( + self._PLAYLIST_ID_REGEXES, webpage, 'playlist id') + for regex in self._PLAYLIST_CLIP_REGEXES: + playlist_clips = re.findall(regex, webpage) + if playlist_clips: + title = self._html_search_regex( + self._TITLE_REGEXES, webpage, 'title') + description = self._html_search_regex( + self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False) + entries = [ + self.url_result( + re.match('(.+?//.+?)/', url).group(1) + clip_path, + 'ProSiebenSat1') + for clip_path in playlist_clips] + return self.playlist_result(entries, playlist_id, title, description) + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + page_type = self._search_regex( + self._PAGE_TYPE_REGEXES, webpage, + 'page type', default='clip').lower() + if page_type == 'clip': + return self._extract_clip(url, webpage) + elif page_type == 'playlist': + return self._extract_playlist(url, webpage) diff --git a/youtube_dl/extractor/quickvid.py b/youtube_dl/extractor/quickvid.py index 3bc7806..af7d76c 100644 --- a/youtube_dl/extractor/quickvid.py +++ b/youtube_dl/extractor/quickvid.py @@ -3,8 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, +) +from ..utils import ( determine_ext, int_or_none, ) diff --git a/youtube_dl/extractor/radiobremen.py b/youtube_dl/extractor/radiobremen.py new file mode 100644 index 0000000..0d70631 --- /dev/null +++ b/youtube_dl/extractor/radiobremen.py @@ -0,0 +1,63 @@ +# -*- coding: utf-8 -*- + +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class RadioBremenIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(?:index\.html)?\?id=(?P<id>[0-9]+)' + IE_NAME = 'radiobremen' + + _TEST = { + 'url': 'http://www.radiobremen.de/mediathek/index.html?id=114720', + 'info_dict': { + 'id': '114720', + 'ext': 'mp4', + 'duration': 1685, + 'width': 512, + 'title': 'buten un binnen vom 22. Dezember', + 'thumbnail': 're:https?://.*\.jpg$', + 'description': 'Unter anderem mit diesen Themen: 45 Flüchtlinge sind in Worpswede angekommen +++ Freies Internet für alle: Bremer arbeiten an einem flächendeckenden W-Lan-Netzwerk +++ Aktivisten kämpfen für das Unibad +++ So war das Wetter 2014 +++', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + meta_url = "http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s" % video_id + meta_doc = self._download_webpage( + meta_url, video_id, 'Downloading metadata') + title = self._html_search_regex( + r"<h1.*>(?P<title>.+)</h1>", meta_doc, "title") + description = self._html_search_regex( + r"<p>(?P<description>.*)</p>", meta_doc, "description", fatal=False) + duration = parse_duration(self._html_search_regex( + r"Länge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>", + meta_doc, "duration", fatal=False)) + + page_doc = self._download_webpage( + url, video_id, 'Downloading video information') + mobj = re.search( + r"ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)", + page_doc) + video_url = ( + "http://dl-ondemand.radiobremen.de/mediabase/%s/%s_%s_%s.mp4" % + (video_id, video_id, mobj.group("secret"), mobj.group('width'))) + + formats = [{ + 'url': video_url, + 'ext': 'mp4', + 'width': int(mobj.group("width")), + }] + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'formats': formats, + 'thumbnail': mobj.group('thumbnail'), + } diff --git a/youtube_dl/extractor/radiode.py b/youtube_dl/extractor/radiode.py new file mode 100644 index 0000000..f95bc94 --- /dev/null +++ b/youtube_dl/extractor/radiode.py @@ -0,0 +1,55 @@ +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor + + +class RadioDeIE(InfoExtractor): + IE_NAME = 'radio.de' + _VALID_URL = r'https?://(?P<id>.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)' + _TEST = { + 'url': 'http://ndr2.radio.de/', + 'md5': '3b4cdd011bc59174596b6145cda474a4', + 'info_dict': { + 'id': 'ndr2', + 'ext': 'mp3', + 'title': 're:^NDR 2 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:591c49c702db1a33751625ebfb67f273', + 'thumbnail': 're:^https?://.*\.png', + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + radio_id = self._match_id(url) + + webpage = self._download_webpage(url, radio_id) + + broadcast = json.loads(self._search_regex( + r'_getBroadcast\s*=\s*function\(\s*\)\s*{\s*return\s+({.+?})\s*;\s*}', + webpage, 'broadcast')) + + title = self._live_title(broadcast['name']) + description = broadcast.get('description') or broadcast.get('shortDescription') + thumbnail = broadcast.get('picture4Url') or broadcast.get('picture4TransUrl') + + formats = [{ + 'url': stream['streamUrl'], + 'ext': stream['streamContentFormat'].lower(), + 'acodec': stream['streamContentFormat'], + 'abr': stream['bitRate'], + 'asr': stream['sampleRate'] + } for stream in broadcast['streamUrls']] + self._sort_formats(formats) + + return { + 'id': radio_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'is_live': True, + 'formats': formats, + } diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 2d39ecf..aa26b7e 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -3,10 +3,12 @@ from __future__ import unicode_literals import re from .subtitles import SubtitlesInfoExtractor +from ..compat import ( + compat_urllib_parse, +) from ..utils import ( parse_duration, unified_strdate, - compat_urllib_parse, ) diff --git a/youtube_dl/extractor/restudy.py b/youtube_dl/extractor/restudy.py new file mode 100644 index 0000000..b17c2bf --- /dev/null +++ b/youtube_dl/extractor/restudy.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class RestudyIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://www.restudy.dk/video/play/id/1637', + 'info_dict': { + 'id': '1637', + 'ext': 'flv', + 'title': 'Leiden-frosteffekt', + 'description': 'Denne video er et eksperiment med flydende kvælstof.', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage).strip() + description = self._og_search_description(webpage).strip() + + formats = self._extract_smil_formats( + 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id, + video_id) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'formats': formats, + } diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py new file mode 100644 index 0000000..04158b9 --- /dev/null +++ b/youtube_dl/extractor/rte.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + float_or_none, +) + + +class RteIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P<id>[0-9]+)/' + _TEST = { + 'url': 'http://www.rte.ie/player/de/show/10363114/', + 'info_dict': { + 'id': '10363114', + 'ext': 'mp4', + 'title': 'One News', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'The One O\'Clock News followed by Weather.', + 'duration': 436.844, + }, + 'params': { + 'skip_download': 'f4m fails with --test atm' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._html_search_meta('description', webpage, 'description') + duration = float_or_none(self._html_search_meta( + 'duration', webpage, 'duration', fatal=False), 1000) + + thumbnail_id = self._search_regex( + r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail') + thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' + + feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id + json_string = self._download_json(feeds_url, video_id) + + # f4m_url = server + relative_url + f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url'] + f4m_formats = self._extract_f4m_formats(f4m_url, video_id) + f4m_formats = [{ + 'format_id': f['format_id'], + 'url': f['url'], + 'ext': 'mp4', + 'width': f['width'], + 'height': f['height'], + } for f in f4m_formats] + + return { + 'id': video_id, + 'title': title, + 'formats': f4m_formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + } diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py index d029b0e..a3ca79f 100644 --- a/youtube_dl/extractor/rtlnl.py +++ b/youtube_dl/extractor/rtlnl.py @@ -8,7 +8,7 @@ from ..utils import parse_duration class RtlXlIE(InfoExtractor): IE_NAME = 'rtlxl.nl' - _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' + _VALID_URL = r'https?://(www\.)?rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)' _TEST = { 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', diff --git a/youtube_dl/extractor/rtp.py b/youtube_dl/extractor/rtp.py new file mode 100644 index 0000000..7736cab --- /dev/null +++ b/youtube_dl/extractor/rtp.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import js_to_json + + +class RTPIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?' + _TESTS = [{ + 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas', + 'info_dict': { + 'id': 'e174042', + 'ext': 'mp3', + 'title': 'Paixões Cruzadas', + 'description': 'As paixões musicais de António Cartaxo e António Macedo', + 'thumbnail': 're:^https?://.*\.jpg', + }, + 'params': { + 'skip_download': True, # RTMP download + }, + }, { + 'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._html_search_meta( + 'twitter:title', webpage, display_name='title', fatal=True) + description = self._html_search_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + player_config = self._search_regex( + r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config') + config = json.loads(js_to_json(player_config)) + + path, ext = config.get('file').rsplit('.', 1) + formats = [{ + 'app': config.get('application'), + 'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path), + 'page_url': url, + 'url': 'rtmp://{streamer:s}/{application:s}'.format(**config), + 'rtmp_live': config.get('live', False), + 'ext': ext, + 'vcodec': config.get('type') == 'audio' and 'none' or None, + 'player_url': 'http://programas.rtp.pt/play/player.swf?v3', + }] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index e8199b1..5e84c10 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -4,18 +4,20 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, +) from ..utils import ( int_or_none, parse_duration, parse_iso8601, unescapeHTML, - compat_str, ) class RTSIE(InfoExtractor): IE_DESC = 'RTS.ch' - _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html' + _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))' _TESTS = [ { @@ -23,6 +25,7 @@ class RTSIE(InfoExtractor): 'md5': '753b877968ad8afaeddccc374d4256a5', 'info_dict': { 'id': '3449373', + 'display_id': 'les-enfants-terribles', 'ext': 'mp4', 'duration': 1488, 'title': 'Les Enfants Terribles', @@ -30,7 +33,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Divers', 'upload_date': '19680921', 'timestamp': -40280400, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -38,6 +42,7 @@ class RTSIE(InfoExtractor): 'md5': 'c148457a27bdc9e5b1ffe081a7a8337b', 'info_dict': { 'id': '5624067', + 'display_id': 'entre-ciel-et-mer', 'ext': 'mp4', 'duration': 3720, 'title': 'Les yeux dans les cieux - Mon homard au Canada', @@ -45,7 +50,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Passe-moi les jumelles', 'upload_date': '20140404', 'timestamp': 1396635300, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -53,6 +59,7 @@ class RTSIE(InfoExtractor): 'md5': 'b4326fecd3eb64a458ba73c73e91299d', 'info_dict': { 'id': '5745975', + 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski', 'ext': 'mp4', 'duration': 48, 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski', @@ -60,7 +67,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Hockey', 'upload_date': '20140403', 'timestamp': 1396556882, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, 'skip': 'Blocked outside Switzerland', }, @@ -69,6 +77,7 @@ class RTSIE(InfoExtractor): 'md5': '9bb06503773c07ce83d3cbd793cebb91', 'info_dict': { 'id': '5745356', + 'display_id': 'londres-cachee-par-un-epais-smog', 'ext': 'mp4', 'duration': 33, 'title': 'Londres cachée par un épais smog', @@ -76,7 +85,8 @@ class RTSIE(InfoExtractor): 'uploader': 'Le Journal en continu', 'upload_date': '20140403', 'timestamp': 1396537322, - 'thumbnail': 're:^https?://.*\.image' + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, }, }, { @@ -84,6 +94,7 @@ class RTSIE(InfoExtractor): 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae', 'info_dict': { 'id': '5706148', + 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014', 'ext': 'mp3', 'duration': 123, 'title': '"Urban Hippie", de Damien Krisl', @@ -92,22 +103,44 @@ class RTSIE(InfoExtractor): 'timestamp': 1396551600, }, }, + { + 'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260', + 'md5': '968777c8779e5aa2434be96c54e19743', + 'info_dict': { + 'id': '6348260', + 'display_id': 'le-19h30', + 'ext': 'mp4', + 'duration': 1796, + 'title': 'Le 19h30', + 'description': '', + 'uploader': 'Le 19h30', + 'upload_date': '20141201', + 'timestamp': 1417458600, + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, + }, + }, + { + 'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280', + 'only_matching': True, + } ] def _real_extract(self, url): m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = m.group('id') or m.group('id_new') + display_id = m.group('display_id') or m.group('display_id_new') def download_json(internal_id): return self._download_json( 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id, - video_id) + display_id) all_info = download_json(video_id) # video_id extracted out of URL is not always a real id if 'video' not in all_info and 'audio' not in all_info: - page = self._download_webpage(url, video_id) + page = self._download_webpage(url, display_id) internal_id = self._html_search_regex( r'<(?:video|audio) data-id="([0-9]+)"', page, 'internal video id') @@ -143,6 +176,7 @@ class RTSIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'formats': formats, 'title': info['title'], 'description': info.get('intro'), diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 0c8790d..5b1c357 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -5,10 +5,12 @@ import re import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, - unified_strdate, +) +from ..utils import ( ExtractorError, + unified_strdate, ) @@ -36,9 +38,7 @@ class RutubeIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) video = self._download_json( 'http://rutube.ru/api/video/%s/?format=json' % video_id, video_id, 'Downloading video JSON') @@ -53,6 +53,7 @@ class RutubeIE(InfoExtractor): m3u8_url = options['video_balancer'].get('m3u8') if m3u8_url is None: raise ExtractorError('Couldn\'t find m3u8 manifest url') + formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') return { 'id': video['id'], @@ -60,8 +61,7 @@ class RutubeIE(InfoExtractor): 'description': video['description'], 'duration': video['duration'], 'view_count': video['hits'], - 'url': m3u8_url, - 'ext': 'mp4', + 'formats': formats, 'thumbnail': video['thumbnail_url'], 'uploader': author.get('name'), 'uploader_id': compat_str(author['id']) if author else None, @@ -70,6 +70,37 @@ class RutubeIE(InfoExtractor): } +class RutubeEmbedIE(InfoExtractor): + IE_NAME = 'rutube:embed' + IE_DESC = 'Rutube embedded videos' + _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)' + + _TEST = { + 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', + 'info_dict': { + 'id': 'a10e53b86e8f349080f718582ce4c661', + 'ext': 'mp4', + 'upload_date': '20131223', + 'uploader_id': '297833', + 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89', + 'uploader': 'subziro89 ILya', + 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', + }, + 'params': { + 'skip_download': 'Requires ffmpeg', + }, + } + + def _real_extract(self, url): + embed_id = self._match_id(url) + webpage = self._download_webpage(url, embed_id) + + canonical_url = self._html_search_regex( + r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage, + 'Canonical URL') + return self.url_result(canonical_url, 'Rutube') + + class RutubeChannelIE(InfoExtractor): IE_NAME = 'rutube:channel' IE_DESC = 'Rutube channels' @@ -114,8 +145,7 @@ class RutubeMovieIE(RutubeChannelIE): _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - movie_id = mobj.group('id') + movie_id = self._match_id(url) movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index c145f6f..dfd897b 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -1,14 +1,14 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_parse_qs, compat_urllib_request, ) +from ..utils import ( + ExtractorError, +) class ScreencastIE(InfoExtractor): @@ -57,8 +57,7 @@ class ScreencastIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = self._html_search_regex( diff --git a/youtube_dl/extractor/screencastomatic.py b/youtube_dl/extractor/screencastomatic.py new file mode 100644 index 0000000..0533742 --- /dev/null +++ b/youtube_dl/extractor/screencastomatic.py @@ -0,0 +1,49 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + ExtractorError, + js_to_json, +) + + +class ScreencastOMaticIE(InfoExtractor): + _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)' + _TEST = { + 'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl', + 'md5': '483583cb80d92588f15ccbedd90f0c18', + 'info_dict': { + 'id': 'c2lD3BeOPl', + 'ext': 'mp4', + 'title': 'Welcome to 3-4 Philosophy @ DECV!', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + setup_js = self._search_regex( + r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", + webpage, 'setup code') + data = self._parse_json(setup_js, video_id, transform_source=js_to_json) + try: + video_data = next( + m for m in data['modes'] if m.get('type') == 'html5') + except StopIteration: + raise ExtractorError('Could not find any video entries!') + video_url = compat_urlparse.urljoin(url, video_data['config']['file']) + thumbnail = data.get('image') + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'url': video_url, + 'ext': 'mp4', + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/screenwavemedia.py index b7fa73c..6c9fdb7 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -5,61 +5,27 @@ import re from .common import InfoExtractor from ..utils import ( - ExtractorError, int_or_none, + unified_strdate, ) -class CinemassacreIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': '19911', - 'ext': 'mp4', - 'upload_date': '20121110', - 'title': '“Angry Video Game Nerd: The Movie” – Trailer', - 'description': 'md5:fb87405fcb42a331742a0dce2708560b', - }, - }, - { - 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'md5': 'd72f10cd39eac4215048f62ab477a511', - 'info_dict': { - 'id': '521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - } - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - - webpage = self._download_webpage(url, display_id) - video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') - mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage) - if not mobj: - raise ExtractorError('Can\'t extract embed url and video id') - playerdata_url = mobj.group('embed_url') - video_id = mobj.group('video_id') - full_video_id = mobj.group('full_video_id') +class ScreenwaveMediaIE(InfoExtractor): + _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)' - video_title = self._html_search_regex( - r'<title>(?P<title>.+?)\|', webpage, 'title') - video_description = self._html_search_regex( - r'<div class="entry-content">(?P<description>.+?)</div>', - webpage, 'description', flags=re.DOTALL, fatal=False) - video_thumbnail = self._og_search_thumbnail(webpage) + _TESTS = [{ + 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911', + 'only_matching': True, + }] - playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') + def _real_extract(self, url): + video_id = self._match_id(url) + playerdata = self._download_webpage(url, video_id, 'Downloading player webpage') + vidtitle = self._search_regex( + r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/') vidurl = self._search_regex( - r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/') + r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/') videolist_url = None @@ -67,7 +33,7 @@ class CinemassacreIE(InfoExtractor): if mobj: videoserver = mobj.group('videoserver') mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata) - vidid = mobj.group('vidid') if mobj else full_video_id + vidid = mobj.group('vidid') if mobj else video_id videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid) else: mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata) @@ -85,34 +51,128 @@ class CinemassacreIE(InfoExtractor): file_ = src.partition(':')[-1] width = int_or_none(video.get('width')) height = int_or_none(video.get('height')) - bitrate = int_or_none(video.get('system-bitrate')) + bitrate = int_or_none(video.get('system-bitrate'), scale=1000) format = { 'url': baseurl + file_, 'format_id': src.rpartition('.')[0].rpartition('_')[-1], } if width or height: format.update({ - 'tbr': bitrate // 1000 if bitrate else None, + 'tbr': bitrate, 'width': width, 'height': height, }) else: format.update({ - 'abr': bitrate // 1000 if bitrate else None, + 'abr': bitrate, 'vcodec': 'none', }) formats.append(format) - self._sort_formats(formats) else: formats = [{ 'url': vidurl, }] + self._sort_formats(formats) return { 'id': video_id, - 'title': video_title, + 'title': vidtitle, 'formats': formats, + } + + +class CinemassacreIE(InfoExtractor): + _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' + _TESTS = [ + { + 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', + 'md5': 'fde81fbafaee331785f58cd6c0d46190', + 'info_dict': { + 'id': 'Cinemassacre-19911', + 'ext': 'mp4', + 'upload_date': '20121110', + 'title': '“Angry Video Game Nerd: The Movie” – Trailer', + 'description': 'md5:fb87405fcb42a331742a0dce2708560b', + }, + }, + { + 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', + 'md5': 'd72f10cd39eac4215048f62ab477a511', + 'info_dict': { + 'id': 'Cinemassacre-521be8ef82b16', + 'ext': 'mp4', + 'upload_date': '20131002', + 'title': 'The Mummy’s Hand (1940)', + }, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') + + webpage = self._download_webpage(url, display_id) + + playerdata_url = self._search_regex( + r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + webpage, 'player data URL') + video_title = self._html_search_regex( + r'<title>(?P<title>.+?)\|', webpage, 'title') + video_description = self._html_search_regex( + r'<div class="entry-content">(?P<description>.+?)</div>', + webpage, 'description', flags=re.DOTALL, fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + 'url': playerdata_url, + } + + +class TeamFourIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?' + _TEST = { + 'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/', + 'info_dict': { + 'id': 'TeamFourStar-5292a02f20bfa', + 'ext': 'mp4', + 'upload_date': '20130401', + 'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar', + 'title': 'A Moment With TFS Episode 4', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + playerdata_url = self._search_regex( + r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + webpage, 'player data URL') + + video_title = self._html_search_regex( + r'<div class="heroheadingtitle">(?P<title>.+?)</div>', + webpage, 'title') + video_date = unified_strdate(self._html_search_regex( + r'<div class="heroheadingdate">(?P<date>.+?)</div>', + webpage, 'date', fatal=False)) + video_description = self._html_search_regex( + r'(?s)<div class="postcontent">(?P<description>.+?)</div>', + webpage, 'description', fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'title': video_title, 'description': video_description, 'upload_date': video_date, 'thumbnail': video_thumbnail, + 'url': playerdata_url, } diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py index c833fc8..6446d26 100644 --- a/youtube_dl/extractor/sexykarma.py +++ b/youtube_dl/extractor/sexykarma.py @@ -24,7 +24,7 @@ class SexyKarmaIE(InfoExtractor): 'title': 'Taking a quick pee.', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'wildginger7', - 'upload_date': '20141007', + 'upload_date': '20141008', 'duration': 22, 'view_count': int, 'comment_count': int, @@ -45,6 +45,7 @@ class SexyKarmaIE(InfoExtractor): 'view_count': int, 'comment_count': int, 'categories': list, + 'age_limit': 18, } }, { 'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html', @@ -61,6 +62,7 @@ class SexyKarmaIE(InfoExtractor): 'view_count': int, 'comment_count': int, 'categories': list, + 'age_limit': 18, } }] @@ -114,4 +116,5 @@ class SexyKarmaIE(InfoExtractor): 'view_count': view_count, 'comment_count': comment_count, 'categories': categories, + 'age_limit': 18, } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index fdc3160..26ced71 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -4,10 +4,12 @@ import re import base64 from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, - compat_urllib_parse, int_or_none, ) @@ -26,26 +28,30 @@ class SharedIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage(url, video_id) - - if re.search(r'>File does not exist<', page) is not None: - raise ExtractorError('Video %s does not exist' % video_id, expected=True) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page)) + if '>File does not exist<' in webpage: + raise ExtractorError( + 'Video %s does not exist' % video_id, expected=True) - request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form)) + download_form = dict(re.findall( + r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage)) + request = compat_urllib_request.Request( + url, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - video_page = self._download_webpage(request, video_id, 'Downloading video page') + video_page = self._download_webpage( + request, video_id, 'Downloading video page') - video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL') - title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8') - filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False)) + video_url = self._html_search_regex( + r'data-url="([^"]+)"', video_page, 'video URL') + title = base64.b64decode(self._html_search_meta( + 'full:title', webpage, 'title')).decode('utf-8') + filesize = int_or_none(self._html_search_meta( + 'full:size', webpage, 'file size', fatal=False)) thumbnail = self._html_search_regex( - r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None) + r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None) return { 'id': video_id, diff --git a/youtube_dl/extractor/sharesix.py b/youtube_dl/extractor/sharesix.py index 7531e83..ac3e3ad 100644 --- a/youtube_dl/extractor/sharesix.py +++ b/youtube_dl/extractor/sharesix.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( parse_duration, ) diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index 5eadbb7..a63d126 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -4,7 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, compat_urllib_parse, ) diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py index 5864b99..9f79ff5 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -4,8 +4,10 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, +) +from ..utils import ( ExtractorError, ) @@ -28,7 +30,7 @@ class SlideshareIE(InfoExtractor): page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) slideshare_obj = self._search_regex( - r'var slideshare_object = ({.*?}); var user_info =', + r'var\s+slideshare_object\s*=\s*({.*?});\s*var\s+user_info\s*=', webpage, 'slideshare object') info = json.loads(slideshare_obj) if info['slideshow']['type'] != 'video': @@ -39,7 +41,7 @@ class SlideshareIE(InfoExtractor): ext = info['jsplayer']['video_extension'] video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext) description = self._html_search_regex( - r'<p\s+(?:style="[^"]*"\s+)?class=".*?description.*?"[^>]*>(.*?)</p>', webpage, + r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage, 'description', fatal=False) return { diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 0751efc..26f361c 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -7,9 +7,11 @@ import hashlib import uuid from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, int_or_none, unified_strdate, @@ -67,6 +69,7 @@ class SmotriIE(InfoExtractor): 'params': { 'videopassword': 'qwerty', }, + 'skip': 'Video is not approved by moderator', }, # age limit + video-password { @@ -84,7 +87,22 @@ class SmotriIE(InfoExtractor): }, 'params': { 'videopassword': '333' - } + }, + 'skip': 'Video is not approved by moderator', + }, + # not approved by moderator, but available + { + 'url': 'http://smotri.com/video/view/?id=v28888533b73', + 'md5': 'f44bc7adac90af518ef1ecf04893bb34', + 'info_dict': { + 'id': 'v28888533b73', + 'ext': 'mp4', + 'title': 'Russian Spies Killed By ISIL Child Soldier', + 'uploader': 'Mopeder', + 'uploader_id': 'mopeder', + 'duration': 71, + 'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg', + }, }, # swf player { @@ -142,13 +160,16 @@ class SmotriIE(InfoExtractor): video = self._download_json(request, video_id, 'Downloading video JSON') - if video.get('_moderate_no') or not video.get('moderated'): - raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True) + video_url = video.get('_vidURL') or video.get('_vidURL_mp4') - if video.get('error'): - raise ExtractorError('Video %s does not exist' % video_id, expected=True) + if not video_url: + if video.get('_moderate_no') or not video.get('moderated'): + raise ExtractorError( + 'Video %s has not been approved by moderator' % video_id, expected=True) + + if video.get('error'): + raise ExtractorError('Video %s does not exist' % video_id, expected=True) - video_url = video.get('_vidURL') or video.get('_vidURL_mp4') title = video['title'] thumbnail = video['_imgURL'] upload_date = unified_strdate(video['added']) @@ -274,15 +295,18 @@ class SmotriBroadcastIE(InfoExtractor): broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page') if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None: - raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True) + raise ExtractorError( + 'Broadcast %s does not exist' % broadcast_id, expected=True) # Adult content if re.search('EroConfirmText">', broadcast_page) is not None: (username, password) = self._get_login_info() if username is None: - raise ExtractorError('Erotic broadcasts allowed only for registered users, ' - 'use --username and --password options to provide account credentials.', expected=True) + raise ExtractorError( + 'Erotic broadcasts allowed only for registered users, ' + 'use --username and --password options to provide account credentials.', + expected=True) login_form = { 'login-hint53': '1', @@ -291,9 +315,11 @@ class SmotriBroadcastIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form)) + request = compat_urllib_request.Request( + broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age') + broadcast_page = self._download_webpage( + request, broadcast_id, 'Logging in and confirming age') if re.search('>Неверный логин или пароль<', broadcast_page) is not None: raise ExtractorError('Unable to log in: bad username or password', expected=True) @@ -303,7 +329,7 @@ class SmotriBroadcastIE(InfoExtractor): adult_content = False ticket = self._html_search_regex( - 'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);', + r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)", broadcast_page, 'broadcast ticket') url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket @@ -312,26 +338,31 @@ class SmotriBroadcastIE(InfoExtractor): if broadcast_password: url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest() - broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON') + broadcast_json_page = self._download_webpage( + url, broadcast_id, 'Downloading broadcast JSON') try: broadcast_json = json.loads(broadcast_json_page) protected_broadcast = broadcast_json['_pass_protected'] == 1 if protected_broadcast and not broadcast_password: - raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True) + raise ExtractorError( + 'This broadcast is protected by a password, use the --video-password option', + expected=True) broadcast_offline = broadcast_json['is_play'] == 0 if broadcast_offline: raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True) rtmp_url = broadcast_json['_server'] - if not rtmp_url.startswith('rtmp://'): + mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url) + if not mobj: raise ExtractorError('Unexpected broadcast rtmp URL') broadcast_playpath = broadcast_json['_streamName'] + broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL']) broadcast_thumbnail = broadcast_json['_imgURL'] - broadcast_title = broadcast_json['title'] + broadcast_title = self._live_title(broadcast_json['title']) broadcast_description = broadcast_json['description'] broadcaster_nick = broadcast_json['nick'] broadcaster_login = broadcast_json['login'] @@ -352,6 +383,9 @@ class SmotriBroadcastIE(InfoExtractor): 'age_limit': 18 if adult_content else 0, 'ext': 'flv', 'play_path': broadcast_playpath, + 'player_url': 'http://pics.smotri.com/broadcast_play.swf', + 'app': broadcast_app, 'rtmp_live': True, - 'rtmp_conn': rtmp_conn + 'rtmp_conn': rtmp_conn, + 'is_live': True, } diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py index c663e56..7d3c0e9 100644 --- a/youtube_dl/extractor/sockshare.py +++ b/youtube_dl/extractor/sockshare.py @@ -1,13 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals -from ..utils import ( - ExtractorError, +import re + +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( determine_ext, + ExtractorError, ) -import re from .common import InfoExtractor @@ -27,9 +30,7 @@ class SockshareIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'http://sockshare.com/file/%s' % video_id webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 07f514a..c047919 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -1,11 +1,10 @@ # encoding: utf-8 from __future__ import unicode_literals -import json import re from .common import InfoExtractor -from ..utils import ExtractorError +from .common import compat_str class SohuIE(InfoExtractor): @@ -29,60 +28,73 @@ class SohuIE(InfoExtractor): base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' else: base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' - data_url = base_data_url + str(vid_id) - data_json = self._download_webpage( - data_url, video_id, - note='Downloading JSON data for ' + str(vid_id)) - return json.loads(data_json) + + return self._download_json( + base_data_url + vid_id, video_id, + 'Downloading JSON data for %s' % vid_id) mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') mytv = mobj.group('mytv') is not None webpage = self._download_webpage(url, video_id) - raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>', - webpage, 'video title') + raw_title = self._html_search_regex( + r'(?s)<title>(.+?)</title>', + webpage, 'video title') title = raw_title.partition('-')[0].strip() - vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage, - 'video path') - data = _fetch_data(vid, mytv) - - QUALITIES = ('ori', 'super', 'high', 'nor') - vid_ids = [data['data'][q + 'Vid'] - for q in QUALITIES - if data['data'][q + 'Vid'] != 0] - if not vid_ids: - raise ExtractorError('No formats available for this video') + vid = self._html_search_regex( + r'var vid ?= ?["\'](\d+)["\']', + webpage, 'video path') + vid_data = _fetch_data(vid, mytv) - # For now, we just pick the highest available quality - vid_id = vid_ids[-1] + formats_json = {} + for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'): + vid_id = vid_data['data'].get('%sVid' % format_id) + if not vid_id: + continue + vid_id = compat_str(vid_id) + formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv) - format_data = data if vid == vid_id else _fetch_data(vid_id, mytv) - part_count = format_data['data']['totalBlocks'] - allot = format_data['allot'] - prot = format_data['prot'] - clipsURL = format_data['data']['clipsURL'] - su = format_data['data']['su'] + part_count = vid_data['data']['totalBlocks'] playlist = [] for i in range(part_count): - part_url = ('http://%s/?prot=%s&file=%s&new=%s' % - (allot, prot, clipsURL[i], su[i])) - part_str = self._download_webpage( - part_url, video_id, - note='Downloading part %d of %d' % (i + 1, part_count)) - - part_info = part_str.split('|') - video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) - - video_info = { - 'id': '%s_part%02d' % (video_id, i + 1), + formats = [] + for format_id, format_data in formats_json.items(): + allot = format_data['allot'] + prot = format_data['prot'] + + data = format_data['data'] + clips_url = data['clipsURL'] + su = data['su'] + + part_str = self._download_webpage( + 'http://%s/?prot=%s&file=%s&new=%s' % + (allot, prot, clips_url[i], su[i]), + video_id, + 'Downloading %s video URL part %d of %d' + % (format_id, i + 1, part_count)) + + part_info = part_str.split('|') + video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) + + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'filesize': data['clipsBytes'][i], + 'width': data['width'], + 'height': data['height'], + 'fps': data['fps'], + }) + self._sort_formats(formats) + + playlist.append({ + 'id': '%s_part%d' % (video_id, i + 1), 'title': title, - 'url': video_url, - 'ext': 'mp4', - } - playlist.append(video_info) + 'duration': vid_data['data']['clipsDuration'][i], + 'formats': formats, + }) if len(playlist) == 1: info = playlist[0] diff --git a/youtube_dl/extractor/soulanime.py b/youtube_dl/extractor/soulanime.py new file mode 100644 index 0000000..feef33e --- /dev/null +++ b/youtube_dl/extractor/soulanime.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + HEADRequest, + urlhandle_detect_ext, +) + + +class SoulAnimeWatchingIE(InfoExtractor): + IE_NAME = "soulanime:watching" + IE_DESC = "SoulAnime video" + _TEST = { + 'url': 'http://www.soul-anime.net/watching/seirei-tsukai-no-blade-dance-episode-9/', + 'md5': '05fae04abf72298098b528e98abf4298', + 'info_dict': { + 'id': 'seirei-tsukai-no-blade-dance-episode-9', + 'ext': 'mp4', + 'title': 'seirei-tsukai-no-blade-dance-episode-9', + 'description': 'seirei-tsukai-no-blade-dance-episode-9' + } + } + _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/watch[^/]*/(?P<id>[^/]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + domain = mobj.group('domain') + + page = self._download_webpage(url, video_id) + + video_url_encoded = self._html_search_regex( + r'<div id="download">[^<]*<a href="(?P<url>[^"]+)"', page, 'url') + video_url = "http://www.soul-anime." + domain + video_url_encoded + + ext_req = HEADRequest(video_url) + ext_handle = self._request_webpage( + ext_req, video_id, note='Determining extension') + ext = urlhandle_detect_ext(ext_handle) + + return { + 'id': video_id, + 'url': video_url, + 'ext': ext, + 'title': video_id, + 'description': video_id + } + + +class SoulAnimeSeriesIE(InfoExtractor): + IE_NAME = "soulanime:series" + IE_DESC = "SoulAnime Series" + + _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/anime./(?P<id>[^/]+)' + + _EPISODE_REGEX = r'<option value="(/watch[^/]*/[^"]+)">[^<]*</option>' + + _TEST = { + 'url': 'http://www.soul-anime.net/anime1/black-rock-shooter-tv/', + 'info_dict': { + 'id': 'black-rock-shooter-tv' + }, + 'playlist_count': 8 + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + series_id = mobj.group('id') + domain = mobj.group('domain') + + pattern = re.compile(self._EPISODE_REGEX) + + page = self._download_webpage(url, series_id, "Downloading series page") + mobj = pattern.findall(page) + + entries = [self.url_result("http://www.soul-anime." + domain + obj) for obj in mobj] + + return self.playlist_result(entries, series_id) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 3c1d058..5d60c49 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -5,11 +5,12 @@ import re import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, compat_urlparse, compat_urllib_parse, - +) +from ..utils import ( ExtractorError, int_or_none, unified_strdate, @@ -32,7 +33,7 @@ class SoundcloudIE(InfoExtractor): (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) - (?:/?\?secret_token=(?P<secret_token>[^&]+?))?$) + (?:/?\?secret_token=(?P<secret_token>[^&]+))?) |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 94602e8..b936202 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -3,12 +3,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse, compat_urllib_parse_urlparse, compat_urllib_request, - compat_urllib_parse, - unified_strdate, +) +from ..utils import ( str_to_int, + unified_strdate, ) from ..aes import aes_decrypt_text diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 1e55a9f..f345883 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -4,7 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_HTTPError, +) +from ..utils import ( + HEADRequest, + ExtractorError, +) from .spiegeltv import SpiegeltvIE @@ -60,21 +67,31 @@ class SpiegelIE(InfoExtractor): xml_url = base_url + video_id + '.xml' idoc = self._download_xml(xml_url, video_id) - formats = [ - { - 'format_id': n.tag.rpartition('type')[2], - 'url': base_url + n.find('./filename').text, - 'width': int(n.find('./width').text), - 'height': int(n.find('./height').text), - 'abr': int(n.find('./audiobitrate').text), - 'vbr': int(n.find('./videobitrate').text), - 'vcodec': n.find('./codec').text, - 'acodec': 'MP4A', - } - for n in list(idoc) - # Blacklist type 6, it's extremely LQ and not available on the same server - if n.tag.startswith('type') and n.tag != 'type6' - ] + formats = [] + for n in list(idoc): + if n.tag.startswith('type') and n.tag != 'type6': + format_id = n.tag.rpartition('type')[2] + video_url = base_url + n.find('./filename').text + # Test video URLs beforehand as some of them are invalid + try: + self._request_webpage( + HEADRequest(video_url), video_id, + 'Checking %s video URL' % format_id) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: + self.report_warning( + '%s video URL is invalid, skipping' % format_id, video_id) + continue + formats.append({ + 'format_id': format_id, + 'url': video_url, + 'width': int(n.find('./width').text), + 'height': int(n.find('./height').text), + 'abr': int(n.find('./audiobitrate').text), + 'vbr': int(n.find('./videobitrate').text), + 'vcodec': n.find('./codec').text, + 'acodec': 'MP4A', + }) duration = float(idoc[0].findall('./duration')[0].text) self._sort_formats(formats) diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py index 057ef52..1a57aeb 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -4,8 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( parse_iso8601, ) @@ -58,9 +60,10 @@ class SportDeutschlandIE(InfoExtractor): categories = list(data.get('section', {}).get('tags', {}).values()) asset = data['asset'] + assets_info = self._download_json(asset['url'], video_id) formats = [] - smil_url = asset['video'] + smil_url = assets_info['video'] if '.smil' in smil_url: m3u8_url = smil_url.replace('.smil', '.m3u8') formats.extend( diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index c1178f2..d4e1340 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -2,10 +2,9 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -40,8 +39,7 @@ class StreamcloudIE(InfoExtractor): ''', orig_webpage) post = compat_urllib_parse.urlencode(fields) - self.to_screen('%s: Waiting for timeout' % video_id) - time.sleep(12) + self._sleep(12, video_id) headers = { b'Content-Type': b'application/x-www-form-urlencoded', } diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py index 73efe95..c3ceb5f 100644 --- a/youtube_dl/extractor/streamcz.py +++ b/youtube_dl/extractor/streamcz.py @@ -1,18 +1,14 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor from ..utils import ( int_or_none, - compat_str, ) class StreamCZIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)' + _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)' _TESTS = [{ 'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti', @@ -21,61 +17,63 @@ class StreamCZIE(InfoExtractor): 'id': '765767', 'ext': 'mp4', 'title': 'Peklo na talíři: Éčka pro děti', - 'description': 'md5:49ace0df986e95e331d0fe239d421519', - 'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100', + 'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE', + 'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100', 'duration': 256, }, }, { 'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka', - 'md5': '246272e753e26bbace7fcd9deca0650c', + 'md5': 'e54a254fb8b871968fd8403255f28589', 'info_dict': { 'id': '10002447', 'ext': 'mp4', 'title': 'Kancelář Blaník: Tři roky pro Mazánka', - 'description': 'md5:9177695a8b756a0a8ab160de4043b392', - 'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000', + 'description': 'md5:3862a00ba7bf0b3e44806b544032c859', + 'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000', 'duration': 368, }, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - - webpage = self._download_webpage(url, video_id) - - data = self._html_search_regex(r'Stream\.Data\.Episode\((.+?)\);', webpage, 'stream data') - - jsonData = json.loads(data) + video_id = self._match_id(url) + data = self._download_json( + 'http://www.stream.cz/API/episode/%s' % video_id, video_id) formats = [] - for video in jsonData['instances']: - for video_format in video['instances']: - format_id = video_format['quality'] - - if format_id == '240p': - quality = 0 - elif format_id == '360p': - quality = 1 - elif format_id == '480p': - quality = 2 - elif format_id == '720p': - quality = 3 - + for quality, video in enumerate(data['video_qualities']): + for f in video['formats']: + typ = f['type'].partition('/')[2] + qlabel = video.get('quality_label') formats.append({ - 'format_id': '%s-%s' % (video_format['type'].split('/')[1], format_id), - 'url': video_format['source'], + 'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ, + 'format_id': '%s-%s' % (typ, f['quality']), + 'url': f['source'], + 'height': int_or_none(f['quality'].rstrip('p')), 'quality': quality, }) - self._sort_formats(formats) + image = data.get('image') + if image: + thumbnail = self._proto_relative_url( + image.replace('{width}', '1240').replace('{height}', '697'), + scheme='http:', + ) + else: + thumbnail = None + + stream = data.get('_embedded', {}).get('stream:show', {}).get('name') + if stream: + title = '%s: %s' % (stream, data['name']) + else: + title = data['name'] + return { - 'id': compat_str(jsonData['episode_id']), - 'title': self._og_search_title(webpage), - 'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'), + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, 'formats': formats, - 'description': self._og_search_description(webpage), - 'duration': int_or_none(jsonData['duration']), - 'view_count': int_or_none(jsonData['stats_total']), + 'description': data.get('web_site_text'), + 'duration': int_or_none(data.get('duration')), + 'view_count': int_or_none(data.get('views')), } diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py index 263f09b..8a333f1 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -28,23 +28,27 @@ class SunPornoIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title') - description = self._html_search_meta('description', webpage, 'description') + title = self._html_search_regex( + r'<title>([^<]+)</title>', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') thumbnail = self._html_search_regex( r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._search_regex( - r'Duration:\s*(\d+:\d+)\s*<', webpage, 'duration', fatal=False)) + r'itemprop="duration">\s*(\d+:\d+)\s*<', + webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( - r'class="views">\s*(\d+)\s*<', webpage, 'view count', fatal=False)) + r'class="views">\s*(\d+)\s*<', + webpage, 'view count', fatal=False)) comment_count = int_or_none(self._html_search_regex( - r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) + r'(\d+)</b> Comments?', + webpage, 'comment count', fatal=False)) formats = [] quality = qualities(['mp4', 'flv']) diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py index b870474..bfe07b0 100644 --- a/youtube_dl/extractor/tagesschau.py +++ b/youtube_dl/extractor/tagesschau.py @@ -4,10 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import parse_filesize class TagesschauIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html' + _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/ts|video/video)(?P<id>-?[0-9]+)\.html' _TESTS = [{ 'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html', @@ -19,6 +20,16 @@ class TagesschauIE(InfoExtractor): 'description': 'md5:69da3c61275b426426d711bde96463ab', 'thumbnail': 're:^http:.*\.jpg$', }, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html', + 'md5': '3c54c1f6243d279b706bde660ceec633', + 'info_dict': { + 'id': '5727', + 'ext': 'mp4', + 'description': 'md5:695c01bfd98b7e313c501386327aea59', + 'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr', + 'thumbnail': 're:^http:.*\.jpg$', + } }] _FORMATS = { @@ -28,42 +39,82 @@ class TagesschauIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - if video_id.startswith('-'): - display_id = video_id.strip('-') - else: - display_id = video_id - + video_id = self._match_id(url) + display_id = video_id.lstrip('-') webpage = self._download_webpage(url, display_id) - playerpage = self._download_webpage( - 'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id, - display_id, 'Downloading player page') - - medias = re.findall( - r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"', - playerpage) + player_url = self._html_search_meta( + 'twitter:player', webpage, 'player URL', default=None) + if player_url: + playerpage = self._download_webpage( + player_url, display_id, 'Downloading player page') - formats = [] - for url, ext, res in medias: - f = { - 'format_id': res + '_' + ext, - 'url': url, - 'ext': ext, - } - f.update(self._FORMATS.get(res, {})) - formats.append(f) + medias = re.findall( + r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"', + playerpage) + formats = [] + for url, ext, res in medias: + f = { + 'format_id': res + '_' + ext, + 'url': url, + 'ext': ext, + } + f.update(self._FORMATS.get(res, {})) + formats.append(f) + thumbnail_fn = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1] + title = self._og_search_title(webpage).strip() + description = self._og_search_description(webpage).strip() + else: + download_text = self._search_regex( + r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>', + webpage, 'download links') + links = re.finditer( + r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>', + download_text) + formats = [] + for l in links: + format_id = self._search_regex( + r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID') + format = { + 'format_id': format_id, + 'url': l.group('url'), + 'format_name': l.group('name'), + } + m = re.match( + r'''(?x) + Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10; + (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10; + (?P<vbr>[0-9]+)kbps&\#10; + Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10; + Größe:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''', + l.group('title')) + if m: + format.update({ + 'format_note': m.group('audio_desc'), + 'vcodec': m.group('vcodec'), + 'width': int(m.group('width')), + 'height': int(m.group('height')), + 'abr': int(m.group('abr')), + 'vbr': int(m.group('vbr')), + 'filesize_approx': parse_filesize(m.group('filesize_approx')), + }) + formats.append(format) + thumbnail_fn = self._search_regex( + r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"', + webpage, 'thumbnail', fatal=False) + description = self._html_search_regex( + r'(?s)<p class="teasertext">(.*?)</p>', + webpage, 'description', fatal=False) + title = self._html_search_regex( + r'<span class="headline".*?>(.*?)</span>', webpage, 'title') self._sort_formats(formats) - - thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1] + thumbnail = 'http://www.tagesschau.de' + thumbnail_fn return { 'id': display_id, - 'title': self._og_search_title(webpage).strip(), - 'thumbnail': 'http://www.tagesschau.de' + thumbnail, + 'title': title, + 'thumbnail': thumbnail, 'formats': formats, - 'description': self._og_search_description(webpage).strip(), + 'description': description, } diff --git a/youtube_dl/extractor/tapely.py b/youtube_dl/extractor/tapely.py index 283e113..f1f43d0 100644 --- a/youtube_dl/extractor/tapely.py +++ b/youtube_dl/extractor/tapely.py @@ -4,10 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, +) from ..utils import ( - ExtractorError, clean_html, - compat_urllib_request, + ExtractorError, float_or_none, parse_iso8601, ) diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 6c3445d..8267543 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -57,9 +57,7 @@ class TeacherTubeIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_meta('title', webpage, 'title', fatal=True) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index f8a87af..10b3b70 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -5,7 +5,7 @@ import re from .subtitles import SubtitlesInfoExtractor -from ..utils import ( +from ..compat import ( compat_str, ) @@ -13,7 +13,7 @@ from ..utils import ( class TEDIE(SubtitlesInfoExtractor): _VALID_URL = r'''(?x) (?P<proto>https?://) - (?P<type>www|embed)(?P<urlmain>\.ted\.com/ + (?P<type>www|embed(?:-ssl)?)(?P<urlmain>\.ted\.com/ ( (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist | @@ -98,7 +98,7 @@ class TEDIE(SubtitlesInfoExtractor): def _real_extract(self, url): m = re.match(self._VALID_URL, url, re.VERBOSE) - if m.group('type') == 'embed': + if m.group('type').startswith('embed'): desktop_url = m.group('proto') + 'www' + m.group('urlmain') return self.url_result(desktop_url, 'TED') name = m.group('name') @@ -199,8 +199,9 @@ class TEDIE(SubtitlesInfoExtractor): webpage = self._download_webpage(url, name) config_json = self._html_search_regex( - r"data-config='([^']+)", webpage, 'config') - config = json.loads(config_json) + r'"pages\.jwplayer"\s*,\s*({.+?})\s*\)\s*</script>', + webpage, 'config') + config = json.loads(config_json)['config'] video_url = config['video']['url'] thumbnail = config.get('image', {}).get('url') diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index 2a2fff5..be3f72d 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -6,7 +6,7 @@ from .mitele import MiTeleIE class TelecincoIE(MiTeleIE): IE_NAME = 'telecinco.es' - _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<episode>.*?)\.html' + _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<id>.*?)\.html' _TEST = { 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html', diff --git a/youtube_dl/extractor/teletask.py b/youtube_dl/extractor/teletask.py new file mode 100644 index 0000000..e541451 --- /dev/null +++ b/youtube_dl/extractor/teletask.py @@ -0,0 +1,53 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class TeleTaskIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.tele-task.de/archive/video/html5/26168/', + 'info_dict': { + 'title': 'Duplicate Detection', + }, + 'playlist': [{ + 'md5': '290ef69fb2792e481169c3958dbfbd57', + 'info_dict': { + 'id': '26168-speaker', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + } + }, { + 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4', + 'info_dict': { + 'id': '26168-slides', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + } + }] + } + + def _real_extract(self, url): + lecture_id = self._match_id(url) + + webpage = self._download_webpage(url, lecture_id) + + title = self._html_search_regex( + r'itemprop="name">([^<]+)</a>', webpage, 'title') + upload_date = unified_strdate(self._html_search_regex( + r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False)) + + entries = [{ + 'id': '%s-%s' % (lecture_id, format_id), + 'url': video_url, + 'title': title, + 'upload_date': upload_date, + } for format_id, video_url in re.findall( + r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)] + + return self.playlist_result(entries, lecture_id, title) diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py index 81ba169..466155e 100644 --- a/youtube_dl/extractor/tenplay.py +++ b/youtube_dl/extractor/tenplay.py @@ -8,7 +8,6 @@ class TenPlayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?ten(play)?\.com\.au/.+' _TEST = { 'url': 'http://tenplay.com.au/ten-insider/extra/season-2013/tenplay-tv-your-way', - #'md5': 'd68703d9f73dc8fccf3320ab34202590', 'info_dict': { 'id': '2695695426001', 'ext': 'flv', diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 6e61cc9..025d087 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -1,15 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html' - _TEST = { + _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html' + _TESTS = { 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 'info_dict': { 'id': '10635995', @@ -21,14 +19,26 @@ class TF1IE(InfoExtractor): # Sometimes wat serves the whole file with the --test option 'skip_download': True, }, + }, { + 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', + 'info_dict': { + 'id': '12043945', + 'ext': 'mp4', + 'title': 'Le grand Mystérioso - Chuggington', + 'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.', + 'upload_date': '20150103', + }, + 'params': { + # Sometimes wat serves the whole file with the --test option + 'skip_download': True, + }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) embed_url = self._html_search_regex( - r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') + r'["\'](https?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url') embed_page = self._download_webpage(embed_url, video_id, 'Downloading embed player page') wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index e2653d6..110ed97 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re import json -from .common import InfoExtractor -from ..utils import ( +from .subtitles import SubtitlesInfoExtractor +from ..compat import ( compat_str, +) +from ..utils import ( determine_ext, ExtractorError, xpath_with_ns, @@ -14,7 +16,7 @@ from ..utils import ( _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'}) -class ThePlatformIE(InfoExtractor): +class ThePlatformIE(SubtitlesInfoExtractor): _VALID_URL = r'''(?x) (?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/ (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)? @@ -64,6 +66,20 @@ class ThePlatformIE(InfoExtractor): info_json = self._download_webpage(info_url, video_id) info = json.loads(info_json) + subtitles = {} + captions = info.get('captions') + if isinstance(captions, list): + for caption in captions: + lang, src = caption.get('lang'), caption.get('src') + if lang and src: + subtitles[lang] = src + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self.extract_subtitles(video_id, subtitles) + head = meta.find(_x('smil:head')) body = meta.find(_x('smil:body')) @@ -115,6 +131,7 @@ class ThePlatformIE(InfoExtractor): return { 'id': video_id, 'title': info['title'], + 'subtitles': subtitles, 'formats': formats, 'description': info['description'], 'thumbnail': info['defaultThumbnailUrl'], diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py index 66d159e..9f9e388 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -5,7 +5,7 @@ import re from .common import InfoExtractor from .brightcove import BrightcoveIE from .discovery import DiscoveryIE -from ..utils import compat_urlparse +from ..compat import compat_urlparse class TlcIE(DiscoveryIE): diff --git a/youtube_dl/extractor/tmz.py b/youtube_dl/extractor/tmz.py index 827aa08..c5c6fdc 100644 --- a/youtube_dl/extractor/tmz.py +++ b/youtube_dl/extractor/tmz.py @@ -15,7 +15,7 @@ class TMZIE(InfoExtractor): 'ext': 'mp4', 'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!', 'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie??? Or is she just showing off her amazing boobs?', - 'thumbnail': 'http://cdnbakmi.kaltura.com/p/591531/sp/59153100/thumbnail/entry_id/0_okj015ty/version/100002/acv/182/width/640', + 'thumbnail': r're:http://cdnbakmi\.kaltura\.com/.*thumbnail.*', } } diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 0ecd695..d48cbbf 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -12,7 +12,7 @@ from ..utils import ( class TNAFlixIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)' - _TITLE_REGEX = None + _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>' _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' @@ -49,8 +49,8 @@ class TNAFlixIE(InfoExtractor): if duration: duration = parse_duration(duration[1:]) - cfg_url = self._html_search_regex( - self._CONFIG_REGEX, webpage, 'flashvars.config') + cfg_url = self._proto_relative_url(self._html_search_regex( + self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:') cfg_xml = self._download_xml( cfg_url, display_id, note='Downloading metadata', diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 64a1e90..d73ad37 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -4,9 +4,11 @@ import json import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, +) +from ..utils import ( int_or_none, str_to_int, ) diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 161e476..c89de5b 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -9,7 +9,7 @@ from .common import InfoExtractor class TudouIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])' _TESTS = [{ 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', 'md5': '140a49ed444bd22f93330985d8475fcb', @@ -27,13 +27,6 @@ class TudouIE(InfoExtractor): 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', 'thumbnail': 're:^https?://.*\.jpg$', } - }, { - 'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', - 'info_dict': { - 'title': 'todo.mp4', - }, - 'add_ie': ['Youku'], - 'skip': 'Only works from China' }] def _url_for_id(self, id, quality=None): @@ -45,8 +38,7 @@ class TudouIE(InfoExtractor): return final_url def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(2) + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) @@ -87,4 +79,9 @@ class TudouIE(InfoExtractor): } result.append(part_info) - return result + return { + '_type': 'multi_video', + 'entries': result, + 'id': video_id, + 'title': title, + } diff --git a/youtube_dl/extractor/tunein.py b/youtube_dl/extractor/tunein.py index 4ce5aee..b6b1f25 100644 --- a/youtube_dl/extractor/tunein.py +++ b/youtube_dl/extractor/tunein.py @@ -24,7 +24,7 @@ class TuneInIE(InfoExtractor): _INFO_DICT = { 'id': '34682', 'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2', - 'ext': 'AAC', + 'ext': 'aac', 'thumbnail': 're:^https?://.*\.png$', 'location': 'Tacoma, WA', } @@ -78,14 +78,21 @@ class TuneInIE(InfoExtractor): for stream in streams: if stream.get('Type') == 'Live': is_live = True + reliability = stream.get('Reliability') + format_note = ( + 'Reliability: %d%%' % reliability + if reliability is not None else None) formats.append({ + 'preference': ( + 0 if reliability is None or reliability > 90 + else 1), 'abr': stream.get('Bandwidth'), - 'ext': stream.get('MediaType'), + 'ext': stream.get('MediaType').lower(), 'acodec': stream.get('MediaType'), 'vcodec': 'none', 'url': stream.get('Url'), - # Sometimes streams with the highest quality do not exist - 'preference': stream.get('Reliability'), + 'source_preference': reliability, + 'format_note': format_note, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py index d516b64..4de0aac 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -1,10 +1,9 @@ from __future__ import unicode_literals import base64 -import re from .common import InfoExtractor -from ..utils import compat_parse_qs +from ..compat import compat_parse_qs class TutvIE(InfoExtractor): @@ -20,10 +19,9 @@ class TutvIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') data_content = self._download_webpage( diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index d81d1d1..ba65996 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -1,32 +1,30 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( float_or_none, - str_to_int, + parse_age_limit, ) class TvigleIE(InfoExtractor): IE_NAME = 'tvigle' IE_DESC = 'Интернет-телевидение Tvigle.ru' - _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$' + _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<id>[^/]+)/$' _TESTS = [ { - 'url': 'http://www.tvigle.ru/video/brat/', - 'md5': 'ff4344a4894b0524441fb6f8218dc716', + 'url': 'http://www.tvigle.ru/video/sokrat/', + 'md5': '36514aed3657d4f70b4b2cef8eb520cd', 'info_dict': { - 'id': '5118490', - 'display_id': 'brat', - 'ext': 'mp4', - 'title': 'Брат', - 'description': 'md5:d16ac7c0b47052ea51fddb92c4e413eb', - 'duration': 5722.6, - 'age_limit': 16, + 'id': '1848932', + 'display_id': 'sokrat', + 'ext': 'flv', + 'title': 'Сократ', + 'description': 'md5:a05bd01be310074d5833efc6743be95e', + 'duration': 6586, + 'age_limit': 0, }, }, { @@ -44,8 +42,7 @@ class TvigleIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') + display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) @@ -60,8 +57,8 @@ class TvigleIE(InfoExtractor): title = item['title'] description = item['description'] thumbnail = item['thumbnail'] - duration = float_or_none(item['durationMilliseconds'], 1000) - age_limit = str_to_int(item['ageRestrictions']) + duration = float_or_none(item.get('durationMilliseconds'), 1000) + age_limit = parse_age_limit(item.get('ageRestrictions')) formats = [] for vcodec, fmts in item['videos'].items(): diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index a645800..cc26f41 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,37 +1,142 @@ +# -*- coding: utf-8 -*- from __future__ import unicode_literals +import re + from .common import InfoExtractor class TvpIE(InfoExtractor): IE_NAME = 'tvp.pl' - _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:vod|www)\.tvp\.pl/.*/(?P<id>\d+)$' - _TEST = { - 'url': 'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', - 'md5': '148408967a6a468953c0a75cbdaf0d7a', + _TESTS = [{ + 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem/wideo/odc-2/4278035', 'info_dict': { - 'id': '12878238', + 'id': '4278035', 'ext': 'wmv', - 'title': '31.10.2013 - Odcinek 2', - 'description': '31.10.2013 - Odcinek 2', + 'title': 'Ogniem i mieczem, odc. 2', + 'description': 'Bohun dowiaduje się o złamaniu przez kniahinię danego mu słowa i wyrusza do Rozłogów. Helenie w ostatniej chwili udaje się uciec dzięki pomocy Zagłoby.', + }, + }, { + 'url': 'http://vod.tvp.pl/seriale/obyczajowe/czas-honoru/sezon-1-1-13/i-seria-odc-13/194536', + 'info_dict': { + 'id': '194536', + 'ext': 'mp4', + 'title': 'Czas honoru, I seria – odc. 13', + # 'description': 'WŁADEK\nCzesław prosi Marię o dostarczenie Władkowi zarazki tyfusu. Jeśli zachoruje zostanie przewieziony do szpitala skąd łatwiej będzie go odbić. Czy matka zdecyduje się zarazić syna? Karol odwiedza Wandę przyznaje się, że ją oszukiwał, ale ostrzega też, że grozi jej aresztowanie i nalega, żeby wyjechała z Warszawy. Czy dziewczyna zdecyduje się znów oddalić od ukochanego? Rozpoczyna się akcja odbicia Władka.', + }, + }, { + 'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176', + 'info_dict': { + 'id': '17916176', + 'ext': 'mp4', + 'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata', + }, + 'params': { + # m3u8 download + 'skip_download': 'true', + }, + }, { + 'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272', + 'info_dict': { + 'id': '17834272', + 'ext': 'mp4', + 'title': 'Na sygnale, odc. 39', + 'description': 'Ekipa Wiktora ratuje młodą matkę, która spadła ze schodów trzymając na rękach noworodka. Okazuje się, że dziewczyna jest surogatką, a biologiczni rodzice dziecka próbują zmusić ją do oddania synka…', + }, + 'params': { + # m3u8 download + 'skip_download': 'true', }, - 'skip': 'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' - } + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id - params = self._download_json( - json_url, video_id, "Downloading video metadata") - video_url = params['video_url'] + webpage = self._download_webpage( + 'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id) + + title = self._og_search_title(webpage) + series = self._search_regex( + r'{name:\s*([\'"])SeriesTitle\1,\s*value:\s*\1(?P<series>.*?)\1},', + webpage, 'series', group='series', default=None) + if series is not None and series not in title: + title = '%s, %s' % (series, title) + description = self._og_search_description(webpage, default=None) + + video_url = self._search_regex( + r'0:{src:([\'"])(?P<url>.*?)\1', webpage, 'formats', group='url', default=None) + if video_url is None: + video_url = self._download_json( + 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id, + video_id)['video_url'] + + ext = video_url.rsplit('.', 1)[-1] + if ext != 'ism/manifest': + if '/' in ext: + ext = 'mp4' + formats = [{ + 'format_id': 'direct', + 'url': video_url, + 'ext': ext, + }] + else: + m3u8_url = re.sub('([^/]*)\.ism/manifest', r'\1.ism/\1.m3u8', video_url) + formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') + + self._sort_formats(formats) return { 'id': video_id, - 'title': self._og_search_title(webpage), - 'ext': 'wmv', - 'url': video_url, - 'description': self._og_search_description(webpage), + 'title': title, 'thumbnail': self._og_search_thumbnail(webpage), + 'description': description, + 'formats': formats, + } + + +class TvpSeriesIE(InfoExtractor): + IE_NAME = 'tvp.pl:Series' + _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$' + + _TESTS = [{ + 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', + 'info_dict': { + 'title': 'Ogniem i mieczem', + 'id': '4278026', + }, + 'playlist_count': 4, + }, { + 'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat', + 'info_dict': { + 'title': 'Boso przez świat', + 'id': '9329207', + }, + 'playlist_count': 86, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id, tries=5) + + title = self._html_search_regex( + r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series') + playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') + playlist = self._download_webpage( + 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' + 'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5, + note='Downloading playlist') + + videos_paths = re.findall( + '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist) + entries = [ + self.url_result('http://vod.tvp.pl%s' % v_path, ie=TvpIE.ie_key()) + for v_path in videos_paths] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': display_id, + 'title': title, + 'entries': entries, } diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index eb94737..9a53a3c 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -6,7 +6,6 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - ExtractorError, parse_iso8601, qualities, ) @@ -182,8 +181,8 @@ class TVPlayIE(InfoExtractor): 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON') if video['is_geo_blocked']: - raise ExtractorError( - 'This content is not available in your country due to copyright reasons', expected=True) + self.report_warning( + 'This content might not be available in your country due to copyright reasons') streams = self._download_json( 'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON') diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py new file mode 100644 index 0000000..67e8bfe --- /dev/null +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -0,0 +1,109 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + int_or_none, +) + + +class TwentyFourVideoIE(InfoExtractor): + IE_NAME = '24video' + _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)' + + _TESTS = [ + { + 'url': 'http://www.24video.net/video/view/1044982', + 'md5': '48dd7646775690a80447a8dca6a2df76', + 'info_dict': { + 'id': '1044982', + 'ext': 'mp4', + 'title': 'Эротика каменного века', + 'description': 'Как смотрели порно в каменном веке.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'SUPERTELO', + 'duration': 31, + 'timestamp': 1275937857, + 'upload_date': '20100607', + 'age_limit': 18, + 'like_count': int, + 'dislike_count': int, + }, + }, + { + 'url': 'http://www.24video.net/player/new24_play.swf?id=1044982', + 'only_matching': True, + } + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'http://www.24video.net/video/view/%s' % video_id, video_id) + + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'<span itemprop="description">([^<]+)</span>', webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + duration = int_or_none(self._og_search_property( + 'duration', webpage, 'duration', fatal=False)) + timestamp = parse_iso8601(self._search_regex( + r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">', + webpage, 'upload date')) + + uploader = self._html_search_regex( + r'Загрузил\s*<a href="/jsecUser/movies/[^"]+" class="link">([^<]+)</a>', + webpage, 'uploader', fatal=False) + + view_count = int_or_none(self._html_search_regex( + r'<span class="video-views">(\d+) просмотр', + webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'<div class="comments-title" id="comments-count">(\d+) комментари', + webpage, 'comment count', fatal=False)) + + formats = [] + + pc_video = self._download_xml( + 'http://www.24video.net/video/xml/%s?mode=play' % video_id, + video_id, 'Downloading PC video URL').find('.//video') + + formats.append({ + 'url': pc_video.attrib['url'], + 'format_id': 'pc', + 'quality': 1, + }) + + like_count = int_or_none(pc_video.get('ratingPlus')) + dislike_count = int_or_none(pc_video.get('ratingMinus')) + age_limit = 18 if pc_video.get('adult') == 'true' else 0 + + mobile_video = self._download_xml( + 'http://www.24video.net/video/xml/%s' % video_id, + video_id, 'Downloading mobile video URL').find('.//video') + + formats.append({ + 'url': mobile_video.attrib['url'], + 'format_id': 'mobile', + 'quality': 0, + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'duration': duration, + 'timestamp': timestamp, + 'view_count': view_count, + 'comment_count': comment_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 36aa1ad..b11a1d5 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -1,9 +1,14 @@ +# coding: utf-8 from __future__ import unicode_literals import itertools import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( ExtractorError, parse_iso8601, @@ -17,6 +22,7 @@ class TwitchIE(InfoExtractor): _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?twitch\.tv/ (?: (?P<channelid>[^/]+)| + (?:(?:[^/]+)/v/(?P<vodid>[^/]+))| (?:(?:[^/]+)/b/(?P<videoid>[^/]+))| (?:(?:[^/]+)/c/(?P<chapterid>[^/]+)) ) @@ -24,6 +30,7 @@ class TwitchIE(InfoExtractor): """ _PAGE_LIMIT = 100 _API_BASE = 'https://api.twitch.tv' + _LOGIN_URL = 'https://secure.twitch.tv/user/login' _TESTS = [{ 'url': 'http://www.twitch.tv/riotgames/b/577357806', 'info_dict': { @@ -64,11 +71,24 @@ class TwitchIE(InfoExtractor): def _extract_media(self, item, item_id): ITEMS = { 'a': 'video', + 'v': 'vod', 'c': 'chapter', } info = self._extract_info(self._download_json( '%s/kraken/videos/%s%s' % (self._API_BASE, item, item_id), item_id, 'Downloading %s info JSON' % ITEMS[item])) + + if item == 'v': + access_token = self._download_json( + '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id, + 'Downloading %s access token' % ITEMS[item]) + formats = self._extract_m3u8_formats( + 'http://usher.twitch.tv/vod/%s?nauth=%s&nauthsig=%s' + % (item_id, access_token['token'], access_token['sig']), + item_id, 'mp4') + info['formats'] = formats + return info + response = self._download_json( '%s/api/videos/%s%s' % (self._API_BASE, item, item_id), item_id, 'Downloading %s playlist JSON' % ITEMS[item]) @@ -109,6 +129,44 @@ class TwitchIE(InfoExtractor): 'view_count': info['views'], } + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + authenticity_token = self._search_regex( + r'<input name="authenticity_token" type="hidden" value="([^"]+)"', + login_page, 'authenticity token') + + login_form = { + 'utf8': '✓'.encode('utf-8'), + 'authenticity_token': authenticity_token, + 'redirect_on_login': '', + 'embed_form': 'false', + 'mp_source_action': '', + 'follow': '', + 'user[login]': username, + 'user[password]': password, + } + + request = compat_urllib_request.Request( + self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) + request.add_header('Referer', self._LOGIN_URL) + response = self._download_webpage( + request, None, 'Logging in as %s' % username) + + m = re.search( + r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response) + if m: + raise ExtractorError( + 'Unable to login: %s' % m.group('msg').strip(), expected=True) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj.group('chapterid'): @@ -165,6 +223,8 @@ class TwitchIE(InfoExtractor): """ elif mobj.group('videoid'): return self._extract_media('a', mobj.group('videoid')) + elif mobj.group('vodid'): + return self._extract_media('v', mobj.group('vodid')) elif mobj.group('channelid'): channel_id = mobj.group('channelid') info = self._download_json( diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 0e4d386..4667ed8 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, ) @@ -97,11 +99,8 @@ class UdemyIE(InfoExtractor): if 'returnUrl' not in response: raise ExtractorError('Unable to log in') - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - lecture_id = mobj.group('id') + lecture_id = self._match_id(url) lecture = self._download_json( 'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id, diff --git a/youtube_dl/extractor/urort.py b/youtube_dl/extractor/urort.py index 5d06fcc..8872cfc 100644 --- a/youtube_dl/extractor/urort.py +++ b/youtube_dl/extractor/urort.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( unified_strdate, ) @@ -18,11 +18,10 @@ class UrortIE(InfoExtractor): 'url': 'https://urort.p3.no/#!/Band/Gerilja', 'md5': '5ed31a924be8a05e47812678a86e127b', 'info_dict': { - 'id': '33124-4', + 'id': '33124-24', 'ext': 'mp3', 'title': 'The Bomb', 'thumbnail': 're:^https?://.+\.jpg', - 'like_count': int, 'uploader': 'Gerilja', 'uploader_id': 'Gerilja', 'upload_date': '20100323', @@ -33,25 +32,31 @@ class UrortIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) fstr = compat_urllib_parse.quote("InternalBandUrl eq '%s'" % playlist_id) - json_url = 'http://urort.p3.no/breeze/urort/TrackDtos?$filter=' + fstr + json_url = 'http://urort.p3.no/breeze/urort/TrackDTOViews?$filter=%s&$orderby=Released%%20desc&$expand=Tags%%2CFiles' % fstr songs = self._download_json(json_url, playlist_id) - print(songs[0]) - - entries = [{ - 'id': '%d-%s' % (s['BandId'], s['$id']), - 'title': s['Title'], - 'url': s['TrackUrl'], - 'ext': 'mp3', - 'uploader_id': playlist_id, - 'uploader': s.get('BandName', playlist_id), - 'like_count': s.get('LikeCount'), - 'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'], - 'upload_date': unified_strdate(s.get('Released')), - } for s in songs] + entries = [] + for s in songs: + formats = [{ + 'tbr': f.get('Quality'), + 'ext': f['FileType'], + 'format_id': '%s-%s' % (f['FileType'], f.get('Quality', '')), + 'url': 'http://p3urort.blob.core.windows.net/tracks/%s' % f['FileRef'], + 'preference': 3 if f['FileType'] == 'mp3' else 2, + } for f in s['Files']] + self._sort_formats(formats) + e = { + 'id': '%d-%s' % (s['BandId'], s['$id']), + 'title': s['Title'], + 'uploader_id': playlist_id, + 'uploader': s.get('BandName', playlist_id), + 'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'], + 'upload_date': unified_strdate(s.get('Released')), + 'formats': formats, + } + entries.append(e) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 53dc3a4..68d03b9 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, ) diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index 455b6d9..dd02674 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -1,19 +1,18 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, ) class Vbox7IE(InfoExtractor): - _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)' + _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)' _TEST = { 'url': 'http://vbox7.com/play:249bb972c2', 'md5': '99f65c0c9ef9b682b97313e052734c3f', @@ -25,8 +24,7 @@ class Vbox7IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) redirect_page, urlh = self._download_webpage_handle(url, video_id) new_location = self._search_regex(r'window\.location = \'(.*)\';', diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index 94647d1..96353f5 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -4,10 +4,13 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, - get_element_by_id, +) +from ..utils import ( + ExtractorError, clean_html, + get_element_by_id, ) @@ -15,24 +18,27 @@ class VeeHDIE(InfoExtractor): _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)' _TEST = { - 'url': 'http://veehd.com/video/4686958', + 'url': 'http://veehd.com/video/4639434_Solar-Sinter', 'info_dict': { - 'id': '4686958', + 'id': '4639434', 'ext': 'mp4', - 'title': 'Time Lapse View from Space ( ISS)', - 'uploader_id': 'spotted', - 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7', + 'title': 'Solar Sinter', + 'uploader_id': 'VideoEyes', + 'description': 'md5:46a840e8692ddbaffb5f81d9885cb457', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) # VeeHD seems to send garbage on the first request. # See https://github.com/rg3/youtube-dl/issues/2102 self._download_webpage(url, video_id, 'Requesting webpage') webpage = self._download_webpage(url, video_id) + + if 'This video has been removed<' in webpage: + raise ExtractorError('Video %s has been removed' % video_id, expected=True) + player_path = self._search_regex( r'\$\("#playeriframe"\).attr\({src : "(.+?)"', webpage, 'player path') @@ -41,18 +47,35 @@ class VeeHDIE(InfoExtractor): self._download_webpage(player_url, video_id, 'Requesting player page') player_page = self._download_webpage( player_url, video_id, 'Downloading player page') + config_json = self._search_regex( - r'value=\'config=({.+?})\'', player_page, 'config json') - config = json.loads(config_json) + r'value=\'config=({.+?})\'', player_page, 'config json', default=None) + + if config_json: + config = json.loads(config_json) + video_url = compat_urlparse.unquote(config['clip']['url']) + else: + iframe_src = self._search_regex( + r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url') + iframe_url = 'http://veehd.com/%s' % iframe_src + + self._download_webpage(iframe_url, video_id, 'Requesting iframe page') + iframe_page = self._download_webpage( + iframe_url, video_id, 'Downloading iframe page') + + video_url = self._search_regex( + r"file\s*:\s*'([^']+)'", iframe_page, 'video url') - video_url = compat_urlparse.unquote(config['clip']['url']) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) - uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>', - webpage, 'uploader') - thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"', - webpage, 'thumbnail') - description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul', - webpage, 'description', flags=re.DOTALL) + uploader_id = self._html_search_regex( + r'<a href="/profile/\d+">(.+?)</a>', + webpage, 'uploader') + thumbnail = self._search_regex( + r'<img id="veehdpreview" src="(.+?)"', + webpage, 'thumbnail') + description = self._html_search_regex( + r'<td class="infodropdown".*?<div>(.*?)<ul', + webpage, 'description', flags=re.DOTALL) return { '_type': 'video', diff --git a/youtube_dl/extractor/veoh.py b/youtube_dl/extractor/veoh.py index a7953a7..01e258e 100644 --- a/youtube_dl/extractor/veoh.py +++ b/youtube_dl/extractor/veoh.py @@ -4,8 +4,10 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( int_or_none, ExtractorError, ) diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index c912c3c..43f6b02 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -4,8 +4,10 @@ import re import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, +) +from ..utils import ( ExtractorError, ) diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 70578a4..2f111bf 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -17,7 +17,7 @@ class VGTVIE(InfoExtractor): 'info_dict': { 'id': '84196', 'ext': 'mp4', - 'title': 'Hevnen er søt episode 1:10 - Abu', + 'title': 'Hevnen er søt: Episode 10 - Abu', 'description': 'md5:e25e4badb5f544b04341e14abdc72234', 'thumbnail': 're:^https?://.*\.jpg', 'duration': 648.000, @@ -35,7 +35,7 @@ class VGTVIE(InfoExtractor): 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen', 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3', 'thumbnail': 're:^https?://.*\.jpg', - 'duration': 9056.000, + 'duration': 9103.0, 'timestamp': 1410113864, 'upload_date': '20140907', 'view_count': int, diff --git a/youtube_dl/extractor/videodetective.py b/youtube_dl/extractor/videodetective.py index ac6c255..0ffc7ff 100644 --- a/youtube_dl/extractor/videodetective.py +++ b/youtube_dl/extractor/videodetective.py @@ -1,10 +1,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urlparse from .internetvideoarchive import InternetVideoArchiveIE -from ..utils import compat_urlparse class VideoDetectiveIE(InfoExtractor): @@ -17,13 +15,12 @@ class VideoDetectiveIE(InfoExtractor): 'ext': 'mp4', 'title': 'KICK-ASS 2', 'description': 'md5:65ba37ad619165afac7d432eaded6013', - 'duration': 135, + 'duration': 138, }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) og_video = self._og_search_video_url(webpage) query = compat_urlparse.urlparse(og_video).query diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py index 29c4e01..9fc64d1 100644 --- a/youtube_dl/extractor/videomega.py +++ b/youtube_dl/extractor/videomega.py @@ -1,11 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( remove_start, ) @@ -16,22 +17,23 @@ class VideoMegaIE(InfoExtractor): (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+) ''' _TEST = { - 'url': 'http://videomega.tv/?ref=GKeGPVedBe', - 'md5': '240fb5bcf9199961f48eb17839b084d6', + 'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ', + 'md5': 'bf5c2f95c4c917536e80936af7bc51e1', 'info_dict': { - 'id': 'GKeGPVedBe', + 'id': 'QR0HCUHI1661IHUCH0RQ', 'ext': 'mp4', - 'title': 'XXL - All Sports United', + 'title': 'Big Buck Bunny', 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) - webpage = self._download_webpage(url, video_id) + iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) + req = compat_urllib_request.Request(iframe_url) + req.add_header('Referer', url) + webpage = self._download_webpage(req, video_id) escaped_data = self._search_regex( r'unescape\("([^"]+)"\)', webpage, 'escaped data') @@ -39,13 +41,13 @@ class VideoMegaIE(InfoExtractor): thumbnail = self._search_regex( r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False) - url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') + video_url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') title = remove_start(self._html_search_regex( r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ') formats = [{ 'format_id': 'sd', - 'url': url, + 'url': video_url, }] self._sort_formats(formats) @@ -54,4 +56,5 @@ class VideoMegaIE(InfoExtractor): 'title': title, 'formats': formats, 'thumbnail': thumbnail, + 'http_referer': iframe_url, } diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py new file mode 100644 index 0000000..619039e --- /dev/null +++ b/youtube_dl/extractor/vier.py @@ -0,0 +1,118 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class VierIE(InfoExtractor): + IE_NAME = 'vier' + _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))' + _TESTS = [{ + 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', + 'info_dict': { + 'id': '16129', + 'display_id': 'het-wordt-warm-de-moestuin', + 'ext': 'mp4', + 'title': 'Het wordt warm in De Moestuin', + 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen', + 'only_matching': True, + }, { + 'url': 'http://www.vier.be/video/v3/embed/16129', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + embed_id = mobj.group('embed_id') + display_id = mobj.group('display_id') or embed_id + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'"nid"\s*:\s*"(\d+)"', webpage, 'video id') + application = self._search_regex( + r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod') + filename = self._search_regex( + r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename') + + playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename) + formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4') + + title = self._og_search_title(webpage, default=display_id) + description = self._og_search_description(webpage, default=None) + thumbnail = self._og_search_thumbnail(webpage, default=None) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } + + +class VierVideosIE(InfoExtractor): + IE_NAME = 'vier:videos' + _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)' + _TESTS = [{ + 'url': 'http://www.vier.be/demoestuin/videos', + 'info_dict': { + 'id': 'demoestuin', + }, + 'playlist_mincount': 153, + }, { + 'url': 'http://www.vier.be/demoestuin/videos?page=6', + 'info_dict': { + 'id': 'demoestuin-page6', + }, + 'playlist_mincount': 20, + }, { + 'url': 'http://www.vier.be/demoestuin/videos?page=7', + 'info_dict': { + 'id': 'demoestuin-page7', + }, + 'playlist_mincount': 13, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + program = mobj.group('program') + + webpage = self._download_webpage(url, program) + + page_id = mobj.group('page') + if page_id: + page_id = int(page_id) + start_page = page_id + last_page = start_page + 1 + playlist_id = '%s-page%d' % (program, page_id) + else: + start_page = 0 + last_page = int(self._search_regex( + r'videos\?page=(\d+)">laatste</a>', + webpage, 'last page', default=0)) + 1 + playlist_id = program + + entries = [] + for current_page_id in range(start_page, last_page): + current_page = self._download_webpage( + 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id), + program, + 'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage + page_entries = [ + self.url_result('http://www.vier.be' + video_url, 'Vier') + for video_url in re.findall( + r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)] + entries.extend(page_entries) + + return self.playlist_result(entries, playlist_id) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 15f3152..944901e 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -17,7 +17,6 @@ class VikiIE(SubtitlesInfoExtractor): _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)' _TEST = { 'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14', - 'md5': 'a21454021c2646f5433514177e2caa5f', 'info_dict': { 'id': '1023585v', 'ext': 'mp4', @@ -31,8 +30,7 @@ class VikiIE(SubtitlesInfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._og_search_title(webpage) diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py index 33d370e..ee3d861 100644 --- a/youtube_dl/extractor/vimple.py +++ b/youtube_dl/extractor/vimple.py @@ -14,28 +14,17 @@ class VimpleIE(InfoExtractor): IE_DESC = 'Vimple.ru' _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})' _TESTS = [ - # Quality: Large, from iframe { - 'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c', + 'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf', + 'md5': '2e750a330ed211d3fd41821c6ad9a279', 'info_dict': { - 'id': 'b132bdfd71b546d3972f9ab9a25f201c', - 'title': 'great-escape-minecraft.flv', + 'id': 'c0f6b1687dcd4000a97ebe70068039cf', 'ext': 'mp4', - 'duration': 352, - 'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c', + 'title': 'Sunset', + 'duration': 20, + 'thumbnail': 're:https?://.*?\.jpg', }, }, - # Quality: Medium, from mainpage - { - 'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', - 'info_dict': { - 'id': 'a15950562888453b8e6f9572dc8600cd', - 'title': 'DB 01', - 'ext': 'flv', - 'duration': 1484, - 'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', - } - }, ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 4299522..0b58fe0 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -17,6 +17,7 @@ class VineIE(InfoExtractor): 'id': 'b9KOOWX7HUx', 'ext': 'mp4', 'title': 'Chicken.', + 'alt_title': 'Vine by Jack Dorsey', 'description': 'Chicken.', 'upload_date': '20130519', 'uploader': 'Jack Dorsey', @@ -25,30 +26,26 @@ class VineIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id) data = json.loads(self._html_search_regex( r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data')) - formats = [ - { - 'url': data['videoLowURL'], - 'ext': 'mp4', - 'format_id': 'low', - }, - { - 'url': data['videoUrl'], - 'ext': 'mp4', - 'format_id': 'standard', - } - ] + formats = [{ + 'url': data['videoLowURL'], + 'ext': 'mp4', + 'format_id': 'low', + }, { + 'url': data['videoUrl'], + 'ext': 'mp4', + 'format_id': 'standard', + }] return { 'id': video_id, 'title': self._og_search_title(webpage), + 'alt_title': self._og_search_description(webpage), 'description': data['description'], 'thumbnail': data['thumbnailUrl'], 'upload_date': unified_strdate(data['created']), @@ -63,29 +60,36 @@ class VineIE(InfoExtractor): class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' - _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$' + _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$' _VINE_BASE_URL = "https://vine.co/" - _TEST = { - 'url': 'https://vine.co/Visa', - 'info_dict': { - 'id': 'Visa', + _TESTS = [ + { + 'url': 'https://vine.co/Visa', + 'info_dict': { + 'id': 'Visa', + }, + 'playlist_mincount': 46, }, - 'playlist_mincount': 46, - } + { + 'url': 'https://vine.co/u/941705360593584128', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user = mobj.group('user') + u = mobj.group('u') - profile_url = "%sapi/users/profiles/vanity/%s" % ( - self._VINE_BASE_URL, user) + profile_url = "%sapi/users/profiles/%s%s" % ( + self._VINE_BASE_URL, 'vanity/' if not u else '', user) profile_data = self._download_json( profile_url, user, note='Downloading user profile data') user_id = profile_data['data']['userId'] timeline_data = [] for pagenum in itertools.count(1): - timeline_url = "%sapi/timelines/users/%s?page=%s" % ( + timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % ( self._VINE_BASE_URL, user_id, pagenum) timeline_page = self._download_json( timeline_url, user, note='Downloading page %d' % pagenum) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index ca6b0d5..81e02a6 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -5,14 +5,17 @@ import re import json from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, - compat_urllib_parse, - compat_str, + orderedSet, unescapeHTML, unified_strdate, - orderedSet) +) class VKIE(InfoExtractor): @@ -161,6 +164,14 @@ class VKIE(InfoExtractor): self.to_screen('Youtube video detected') return self.url_result(m_yt.group(1), 'Youtube') + m_rutube = re.search( + r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) + if m_rutube is not None: + self.to_screen('rutube video detected') + rutube_url = self._proto_relative_url( + m_rutube.group(1).replace('\\', '')) + return self.url_result(rutube_url) + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page) if m_opts: m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1)) diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index affef65..1c0966a 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -2,8 +2,9 @@ from __future__ import unicode_literals import re + from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, ) @@ -24,8 +25,7 @@ class VodlockerIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) fields = dict(re.findall(r'''(?x)<input\s+ diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index 1b2f731..405cb9d 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -3,9 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, +) from ..utils import ( int_or_none, - compat_str, ExtractorError, ) diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py index ec3c010..c3fde53 100644 --- a/youtube_dl/extractor/vuclip.py +++ b/youtube_dl/extractor/vuclip.py @@ -3,8 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, +) +from ..utils import ( ExtractorError, parse_duration, qualities, @@ -25,10 +27,9 @@ class VuClipIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + ad_m = re.search( r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage) if ad_m: diff --git a/youtube_dl/extractor/washingtonpost.py b/youtube_dl/extractor/washingtonpost.py index 88bbbb2..c17bebd 100644 --- a/youtube_dl/extractor/washingtonpost.py +++ b/youtube_dl/extractor/washingtonpost.py @@ -10,14 +10,14 @@ from ..utils import ( class WashingtonPostIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' + _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _TEST = { 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', 'info_dict': { 'title': 'Sinkhole of bureaucracy', }, 'playlist': [{ - 'md5': 'c3f4b4922ffa259243f68e928db2db8c', + 'md5': '79132cc09ec5309fa590ae46e4cc31bc', 'info_dict': { 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f', 'ext': 'mp4', @@ -29,7 +29,7 @@ class WashingtonPostIE(InfoExtractor): 'upload_date': '20140322', }, }, { - 'md5': 'f645a07652c2950cd9134bb852c5f5eb', + 'md5': 'e1d5734c06865cc504ad99dc2de0d443', 'info_dict': { 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f', 'ext': 'mp4', @@ -44,10 +44,9 @@ class WashingtonPostIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - + page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) + title = self._og_search_title(webpage) uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage) entries = [] diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 93a6e64..45466e3 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -1,12 +1,15 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_parse_qs, compat_urlparse, +) +from ..utils import ( determine_ext, unified_strdate, ) @@ -65,6 +68,10 @@ class WDRIE(InfoExtractor): 'upload_date': '20140717', }, }, + { + 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html', + 'playlist_mincount': 146, + } ] def _real_extract(self, url): @@ -79,6 +86,27 @@ class WDRIE(InfoExtractor): self.url_result(page_url + href, 'WDR') for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage) ] + + if entries: # Playlist page + return self.playlist_result(entries, page_id) + + # Overview page + entries = [] + for page_num in itertools.count(2): + hrefs = re.findall( + r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"', + webpage) + entries.extend( + self.url_result(page_url + href, 'WDR') + for href in hrefs) + next_url_m = re.search( + r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage) + if not next_url_m: + break + next_url = page_url + next_url_m.group(1) + webpage = self._download_webpage( + next_url, page_id, + note='Downloading playlist page %d' % page_num) return self.playlist_result(entries, page_id) flashvars = compat_parse_qs( @@ -141,7 +169,6 @@ class WDRMobileIE(InfoExtractor): 'title': mobj.group('title'), 'age_limit': int(mobj.group('age_limit')), 'url': url, - 'ext': determine_ext(url), 'user_agent': 'mobile', } @@ -171,8 +198,7 @@ class WDRMausIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) param_code = self._html_search_regex( @@ -223,5 +249,3 @@ class WDRMausIE(InfoExtractor): 'thumbnail': thumbnail, 'upload_date': upload_date, } - -# TODO test _1 diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py new file mode 100644 index 0000000..396cf4e --- /dev/null +++ b/youtube_dl/extractor/webofstories.py @@ -0,0 +1,102 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class WebOfStoriesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)' + _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/' + _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/' + _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/' + _TESTS = [ + { + 'url': 'http://www.webofstories.com/play/hans.bethe/71', + 'md5': '373e4dd915f60cfe3116322642ddf364', + 'info_dict': { + 'id': '4536', + 'ext': 'mp4', + 'title': 'The temperature of the sun', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Hans Bethe talks about calculating the temperature of the sun', + 'duration': 238, + } + }, + { + 'url': 'http://www.webofstories.com/play/55908', + 'md5': '2985a698e1fe3211022422c4b5ed962c', + 'info_dict': { + 'id': '55908', + 'ext': 'mp4', + 'title': 'The story of Gemmata obscuriglobus', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus', + 'duration': 169, + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + description = self._html_search_meta('description', webpage) + thumbnail = self._og_search_thumbnail(webpage) + + story_filename = self._search_regex( + r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename') + speaker_id = self._search_regex( + r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID') + story_id = self._search_regex( + r'\.storyId\((\d+)\)', webpage, 'story ID') + speaker_type = self._search_regex( + r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type') + great_life = self._search_regex( + r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story') + is_great_life_series = great_life == 'true' + duration = int_or_none(self._search_regex( + r'\.duration\((\d+)\)', webpage, 'duration', fatal=False)) + + # URL building, see: http://www.webofstories.com/scripts/player.js + ms_prefix = '' + if speaker_type.lower() == 'ms': + ms_prefix = 'mini_sites/' + + if is_great_life_series: + mp4_url = '{0:}lives/{1:}/{2:}.mp4'.format( + self._VIDEO_DOMAIN, speaker_id, story_filename) + rtmp_ext = 'flv' + streamer = self._GREAT_LIFE_STREAMER + play_path = 'stories/{0:}/{1:}'.format( + speaker_id, story_filename) + else: + mp4_url = '{0:}{1:}{2:}/{3:}.mp4'.format( + self._VIDEO_DOMAIN, ms_prefix, speaker_id, story_filename) + rtmp_ext = 'mp4' + streamer = self._USER_STREAMER + play_path = 'mp4:{0:}{1:}/{2}.mp4'.format( + ms_prefix, speaker_id, story_filename) + + formats = [{ + 'format_id': 'mp4_sd', + 'url': mp4_url, + }, { + 'format_id': 'rtmp_sd', + 'page_url': url, + 'url': streamer, + 'ext': rtmp_ext, + 'play_path': play_path, + }] + + self._sort_formats(formats) + + return { + 'id': story_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + } diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 748443f..13a0791 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,9 +1,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ExtractorError, compat_urllib_request +from ..compat import compat_urllib_request +from ..utils import ExtractorError class WistiaIE(InfoExtractor): @@ -22,8 +21,7 @@ class WistiaIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) request = compat_urllib_request.Request(self._API_URL.format(video_id)) request.add_header('Referer', url) # Some videos require this. diff --git a/youtube_dl/extractor/xbef.py b/youtube_dl/extractor/xbef.py index 1b4e883..80c48c3 100644 --- a/youtube_dl/extractor/xbef.py +++ b/youtube_dl/extractor/xbef.py @@ -1,9 +1,7 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -23,10 +21,9 @@ class XBefIE(InfoExtractor): } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( r'<h1[^>]*>(.*?)</h1>', webpage, 'title') diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py index a9aa72e..236ff40 100644 --- a/youtube_dl/extractor/xboxclips.py +++ b/youtube_dl/extractor/xboxclips.py @@ -1,46 +1,42 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - parse_iso8601, - float_or_none, int_or_none, + parse_filesize, + unified_strdate, ) class XboxClipsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' + _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\w-]{36})' _TEST = { 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', 'info_dict': { 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', 'ext': 'mp4', - 'title': 'Iabdulelah playing Upload Studio', - 'filesize_approx': 28101836.8, - 'timestamp': 1407388500, + 'title': 'Iabdulelah playing Titanfall', + 'filesize_approx': 26800000, 'upload_date': '20140807', 'duration': 56, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = self._html_search_regex( - r'>Link: <a href="([^"]+)">', webpage, 'video URL') + r'>(?:Link|Download): <a[^>]+href="([^"]+)"', webpage, 'video URL') title = self._html_search_regex( r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title') - timestamp = parse_iso8601(self._html_search_regex( + upload_date = unified_strdate(self._html_search_regex( r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False)) - filesize = float_or_none(self._html_search_regex( - r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024) + filesize = parse_filesize(self._html_search_regex( + r'>Size: ([^<]+)<', webpage, 'file size', fatal=False)) duration = int_or_none(self._html_search_regex( r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( @@ -50,7 +46,7 @@ class XboxClipsIE(InfoExtractor): 'id': video_id, 'url': video_url, 'title': title, - 'timestamp': timestamp, + 'upload_date': upload_date, 'filesize_approx': filesize, 'duration': duration, 'view_count': view_count, diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 6b37bcb..4527567 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -14,7 +14,7 @@ from ..utils import ( class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" - _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' + _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' _TESTS = [ { 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', @@ -39,7 +39,11 @@ class XHamsterIE(InfoExtractor): 'duration': 200, 'age_limit': 18, } - } + }, + { + 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', + 'only_matching': True, + }, ] def _real_extract(self, url): @@ -57,7 +61,8 @@ class XHamsterIE(InfoExtractor): video_id = mobj.group('id') seo = mobj.group('seo') - mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo) + proto = mobj.group('proto') + mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo) webpage = self._download_webpage(mrss_url, video_id) title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title') diff --git a/youtube_dl/extractor/xminus.py b/youtube_dl/extractor/xminus.py index f7e2e8a..8c6241a 100644 --- a/youtube_dl/extractor/xminus.py +++ b/youtube_dl/extractor/xminus.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_chr, @@ -25,6 +27,7 @@ class XMinusIE(InfoExtractor): 'tbr': 320, 'filesize_approx': 5900000, 'view_count': int, + 'description': 'md5:03238c5b663810bc79cf42ef3c03e371', } } @@ -48,6 +51,11 @@ class XMinusIE(InfoExtractor): view_count = int_or_none(self._html_search_regex( r'<div class="quality.*?► ([0-9]+)', webpage, 'view count', fatal=False)) + description = self._html_search_regex( + r'(?s)<div id="song_texts">(.*?)</div><br', + webpage, 'song lyrics', fatal=False) + if description: + description = re.sub(' *\r *', '\n', description) enc_token = self._html_search_regex( r'minus_track\.tkn="(.+?)"', webpage, 'enc_token') @@ -64,4 +72,5 @@ class XMinusIE(InfoExtractor): 'filesize_approx': filesize_approx, 'tbr': tbr, 'view_count': view_count, + 'description': description, } diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py index 53ed7ef..79ed6c7 100644 --- a/youtube_dl/extractor/xnxx.py +++ b/youtube_dl/extractor/xnxx.py @@ -1,10 +1,8 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) @@ -23,10 +21,7 @@ class XNXXIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - # Get webpage content + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = self._search_regex(r'flv_url=(.*?)&', diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 38448e7..e8490b0 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -1,18 +1,20 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_request, + compat_urllib_parse, +) +from ..utils import ( parse_duration, str_to_int, ) class XTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))' + _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))' _TEST = { 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', @@ -28,41 +30,49 @@ class XTubeIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title') + video_title = self._html_search_regex( + r'<p class="title">([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False) + [r"var\s+contentOwnerId\s*=\s*'([^']+)", + r'By:\s*<a href="/community/profile\.php\?user=([^"]+)'], + webpage, 'uploader', fatal=False) video_description = self._html_search_regex( - r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False) + r'<p class="fieldsDesc">([^<]+)', + webpage, 'description', fatal=False) duration = parse_duration(self._html_search_regex( - r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False)) - view_count = self._html_search_regex( - r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = self._html_search_regex( - r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False) - if comment_count: - comment_count = str_to_int(comment_count) - - player_quality_option = json.loads(self._html_search_regex( - r'playerQualityOption = ({.+?});', webpage, 'player quality option')) - - QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080'] - formats = [ - { - 'url': furl, + r'<span class="bold">Runtime:</span> ([^<]+)</p>', + webpage, 'duration', fatal=False)) + view_count = str_to_int(self._html_search_regex( + r'<span class="bold">Views:</span> ([\d,\.]+)</p>', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'<div id="commentBar">([\d,\.]+) Comments</div>', + webpage, 'comment count', fatal=False)) + + formats = [] + for format_id, video_url in re.findall( + r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage): + fmt = { + 'url': compat_urllib_parse.unquote(video_url), 'format_id': format_id, - 'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1, - } for format_id, furl in player_quality_option.items() - ] + } + m = re.search(r'^(?P<height>\d+)[pP]', format_id) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + + if not formats: + video_url = compat_urllib_parse.unquote(self._search_regex( + r'flashvars\.video_url\s*=\s*"([^"]+)"', + webpage, 'video URL')) + formats.append({'url': video_url}) + self._sort_formats(formats) return { @@ -85,6 +95,7 @@ class XTubeUserIE(InfoExtractor): 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers', 'info_dict': { 'id': 'greenshowers', + 'age_limit': 18, }, 'playlist_mincount': 155, } @@ -114,6 +125,7 @@ class XTubeUserIE(InfoExtractor): return { '_type': 'playlist', 'id': username, + 'age_limit': 18, 'entries': [{ '_type': 'url', 'url': eurl, diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 7e00448..2a45dc5 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -3,15 +3,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - ExtractorError, +) +from ..utils import ( clean_html, + ExtractorError, ) class XVideosIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)' _TEST = { 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl', 'md5': '4b46ae6ea5e6e9086e714d883313c0c9', @@ -24,37 +26,25 @@ class XVideosIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage) if mobj: raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) - # Extract video URL video_url = compat_urllib_parse.unquote( self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL')) - - # Extract title video_title = self._html_search_regex( r'<title>(.*?)\s+-\s+XVID', webpage, 'title') - - # Extract video thumbnail video_thumbnail = self._search_regex( r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False) return { 'id': video_id, 'url': video_url, - 'uploader': None, - 'upload_date': None, 'title': video_title, 'ext': 'flv', 'thumbnail': video_thumbnail, - 'description': None, 'age_limit': 18, } diff --git a/youtube_dl/extractor/xxxymovies.py b/youtube_dl/extractor/xxxymovies.py new file mode 100644 index 0000000..5c8f17e --- /dev/null +++ b/youtube_dl/extractor/xxxymovies.py @@ -0,0 +1,81 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class XXXYMoviesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)' + _TEST = { + 'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/', + 'md5': '810b1bdbbffff89dd13bdb369fe7be4b', + 'info_dict': { + 'id': '138669', + 'display_id': 'ecstatic-orgasm-sofcore', + 'ext': 'mp4', + 'title': 'Ecstatic Orgasm Sofcore', + 'duration': 931, + 'categories': list, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') + + title = self._html_search_regex( + [r'<div class="block_header">\s*<h1>([^<]+)</h1>', + r'<title>(.*?)\s*-\s*XXXYMovies\.com</title>'], + webpage, 'title') + + thumbnail = self._search_regex( + r"preview_url\s*:\s*'([^']+)'", + webpage, 'thumbnail', fatal=False) + + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + duration = parse_duration(self._search_regex( + r'<span>Duration:</span>\s*(\d+:\d+)', + webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'<div class="video_views">\s*(\d+)', + webpage, 'view count', fatal=False)) + like_count = int_or_none(self._search_regex( + r'>\s*Likes? <b>\((\d+)\)', + webpage, 'like count', fatal=False)) + dislike_count = int_or_none(self._search_regex( + r'>\s*Dislike <b>\((\d+)\)</b>', + webpage, 'dislike count', fatal=False)) + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 0fdb122..f8e7041 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -6,11 +6,14 @@ import json import re from .common import InfoExtractor, SearchInfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( compat_urllib_parse, compat_urlparse, +) +from ..utils import ( clean_html, + unescapeHTML, + ExtractorError, int_or_none, ) @@ -53,14 +56,14 @@ class YahooIE(InfoExtractor): } }, { - 'url': 'https://tw.screen.yahoo.com/taipei-opinion-poll/選情站報-街頭民調-台北市篇-102823042.html', - 'md5': '92a7fdd8a08783c68a174d7aa067dde8', + 'url': 'https://tw.screen.yahoo.com/election-2014-askmayor/敢問市長-黃秀霜批賴清德-非常高傲-033009720.html', + 'md5': '3a09cf59349cfaddae1797acc3c087fc', 'info_dict': { - 'id': '7a23b569-7bea-36cb-85b9-bd5301a0a1fb', + 'id': 'cac903b3-fcf4-3c14-b632-643ab541712f', 'ext': 'mp4', - 'title': '選情站報 街頭民調 台北市篇', - 'description': '選情站報 街頭民調 台北市篇', - 'duration': 429, + 'title': '敢問市長／黃秀霜批賴清德「非常高傲」', + 'description': '直言台南沒捷運 交通居五都之末', + 'duration': 396, } }, { @@ -85,14 +88,14 @@ class YahooIE(InfoExtractor): 'duration': 121, } }, { - 'url': 'https://ca.finance.yahoo.com/news/20-most-valuable-brands-world-112600775.html', - 'md5': '3e401e4eed6325aa29d9b96125fd5b4f', + 'url': 'https://ca.finance.yahoo.com/news/hackers-sony-more-trouble-well-154609075.html', + 'md5': '226a895aae7e21b0129e2a2006fe9690', 'info_dict': { - 'id': 'c1b4c09c-8ed8-3b65-8b05-169c55358a83', + 'id': 'e624c4bc-3389-34de-9dfc-025f74943409', 'ext': 'mp4', - 'title': "Apple Is The World's Most Valuable Brand", - 'description': 'md5:73eabc1a11c6f59752593b2ceefa1262', - 'duration': 21, + 'title': '\'The Interview\' TV Spot: War', + 'description': 'The Interview', + 'duration': 30, } }, { 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', @@ -115,6 +118,16 @@ class YahooIE(InfoExtractor): 'duration': 201, } }, { + 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', + 'md5': '989396ae73d20c6f057746fb226aa215', + 'info_dict': { + 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', + 'ext': 'mp4', + 'title': '\'True Story\' Trailer', + 'description': 'True Story', + 'duration': 150, + }, + }, { 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', 'only_matching': True, } @@ -123,6 +136,7 @@ class YahooIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('display_id') + page_id = mobj.group('id') url = mobj.group('url') host = mobj.group('host') webpage = self._download_webpage(url, display_id) @@ -147,6 +161,7 @@ class YahooIE(InfoExtractor): r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', r'"first_videoid"\s*:\s*"([^"]+)"', + r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), ] video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') else: @@ -161,17 +176,15 @@ class YahooIE(InfoExtractor): region = self._search_regex( r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', webpage, 'region', fatal=False, default='US') - query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' - ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="%s"' - ' AND protocol="http"' % (video_id, region)) data = compat_urllib_parse.urlencode({ - 'q': query, - 'env': 'prod', - 'format': 'json', + 'protocol': 'http', + 'region': region, }) + query_url = ( + 'https://video.media.yql.yahoo.com/v1/video/sapi/streams/' + '{id}?{data}'.format(id=video_id, data=data)) query_result = self._download_json( - 'http://video.query.yahoo.com/v1/public/yql?' + data, - display_id, 'Downloading video info') + query_url, display_id, 'Downloading video info') info = query_result['query']['results']['mediaObj'][0] meta = info.get('meta') @@ -209,7 +222,7 @@ class YahooIE(InfoExtractor): return { 'id': video_id, 'display_id': display_id, - 'title': meta['title'], + 'title': unescapeHTML(meta['title']), 'formats': formats, 'description': clean_html(meta['description']), 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), diff --git a/youtube_dl/extractor/yesjapan.py b/youtube_dl/extractor/yesjapan.py new file mode 100644 index 0000000..112a6c0 --- /dev/null +++ b/youtube_dl/extractor/yesjapan.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + HEADRequest, + get_element_by_attribute, + parse_iso8601, +) + + +class YesJapanIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yesjapan\.com/video/(?P<slug>[A-Za-z0-9\-]*)_(?P<id>[A-Za-z0-9]+)\.html' + _TEST = { + 'url': 'http://www.yesjapan.com/video/japanese-in-5-20-wa-and-ga-particle-usages_726497834.html', + 'md5': 'f0be416314e5be21a12b499b330c21cf', + 'info_dict': { + 'id': '726497834', + 'title': 'Japanese in 5! #20 - WA And GA Particle Usages', + 'description': 'This should clear up some issues most students of Japanese encounter with WA and GA....', + 'ext': 'mp4', + 'timestamp': 1416391590, + 'upload_date': '20141119', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + video_url = self._og_search_video_url(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + timestamp = None + submit_info = get_element_by_attribute('class', 'pm-submit-data', webpage) + if submit_info: + timestamp = parse_iso8601(self._search_regex( + r'datetime="([^"]+)"', submit_info, 'upload date', fatal=False, default=None)) + + # attempt to resolve the final URL in order to get a proper extension + redirect_req = HEADRequest(video_url) + req = self._request_webpage( + redirect_req, video_id, note='Resolving final URL', errnote='Could not resolve final URL', fatal=False) + if req: + video_url = req.geturl() + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + }] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'timestamp': timestamp, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py index 7b621a9..894678a 100644 --- a/youtube_dl/extractor/ynet.py +++ b/youtube_dl/extractor/ynet.py @@ -5,7 +5,7 @@ import re import json from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..compat import compat_urllib_parse class YnetIE(InfoExtractor): diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 8123928..107c9ac 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -6,10 +6,11 @@ import re import sys from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, unescapeHTML, unified_strdate, @@ -45,7 +46,9 @@ class YouPornIE(InfoExtractor): age_limit = self._rta_search(webpage) # Get JSON parameters - json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters') + json_params = self._search_regex( + r'var currentVideo = new Video\((.*)\)[,;]', + webpage, 'JSON parameters') try: params = json.loads(json_params) except: diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 2642ecf..2a1f8be 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -14,23 +14,24 @@ from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor from ..jsinterp import JSInterpreter from ..swfinterp import SWFInterpreter -from ..utils import ( +from ..compat import ( compat_chr, compat_parse_qs, compat_urllib_parse, compat_urllib_request, compat_urlparse, compat_str, - +) +from ..utils import ( clean_html, - get_element_by_id, - get_element_by_attribute, ExtractorError, + get_element_by_attribute, + get_element_by_id, int_or_none, OnDemandPagedList, + orderedSet, unescapeHTML, unified_strdate, - orderedSet, uppercase_escape, ) @@ -44,9 +45,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor): _LOGIN_REQUIRED = False def _set_language(self): - self._set_cookie('.youtube.com', 'PREF', 'f1=50000000&hl=en', + self._set_cookie( + '.youtube.com', 'PREF', 'f1=50000000&hl=en', # YouTube sets the expire time to about two months - expire_time=time.time() + 60*24*3600) + expire_time=time.time() + 2 * 30 * 24 * 3600) def _login(self): """ @@ -254,7 +256,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, - '138': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, @@ -262,9 +264,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, # Dash mp4 audio - '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50}, - '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 128, 'preference': -50}, - '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 256, 'preference': -50}, + '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50}, + '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50}, + '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50}, # Dash webm '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, @@ -285,7 +287,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, + '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'}, + '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, # Dash webm audio '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, @@ -390,6 +394,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'format': '141', }, }, + # JS player signature function name containing $ + { + 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', + 'info_dict': { + 'id': 'nfWlot6h_JM', + 'ext': 'm4a', + 'title': 'Taylor Swift - Shake It Off', + 'description': 'md5:2acfda1b285bdd478ccec22f9918199d', + 'uploader': 'TaylorSwiftVEVO', + 'uploader_id': 'TaylorSwiftVEVO', + 'upload_date': '20140818', + }, + 'params': { + 'youtube_include_dash_manifest': True, + 'format': '141', + }, + }, # Controversy video { 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', @@ -410,12 +431,71 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'id': 'HtVdAasjOgU', 'ext': 'mp4', 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', - 'description': 'md5:eca57043abae25130f58f655ad9a7771', + 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', 'uploader': 'The Witcher', 'uploader_id': 'WitcherGame', 'upload_date': '20140605', }, }, + # Age-gate video with encrypted signature + { + 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', + 'info_dict': { + 'id': '6kLq3WMV1nU', + 'ext': 'mp4', + 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', + 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', + 'uploader': 'LloydVEVO', + 'uploader_id': 'LloydVEVO', + 'upload_date': '20110629', + }, + }, + # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) + { + 'url': '__2ABJjxzNo', + 'info_dict': { + 'id': '__2ABJjxzNo', + 'ext': 'mp4', + 'upload_date': '20100430', + 'uploader_id': 'deadmau5', + 'description': 'md5:12c56784b8032162bb936a5f76d55360', + 'uploader': 'deadmau5', + 'title': 'Deadmau5 - Some Chords (HD)', + }, + 'expected_warnings': [ + 'DASH manifest missing', + ] + }, + # Olympics (https://github.com/rg3/youtube-dl/issues/4431) + { + 'url': 'lqQg6PlCWgI', + 'info_dict': { + 'id': 'lqQg6PlCWgI', + 'ext': 'mp4', + 'upload_date': '20120731', + 'uploader_id': 'olympic', + 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', + 'uploader': 'Olympics', + 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', + }, + 'params': { + 'skip_download': 'requires avconv', + } + }, + # Non-square pixels + { + 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', + 'info_dict': { + 'id': '_b-2C3KPAM0', + 'ext': 'mp4', + 'stretched_ratio': 16 / 9., + 'upload_date': '20110310', + 'uploader_id': 'AllenMeow', + 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', + 'uploader': '孫艾倫', + 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', + }, + } ] def __init__(self, *args, **kwargs): @@ -444,7 +524,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', + r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -493,8 +573,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return 's[%s%s%s]' % (starts, ends, steps) step = None - start = '(Never used)' # Quelch pyflakes warnings - start will be - # set as soon as step is set + # Quelch pyflakes warnings - start will be set when step is set + start = '(Never used)' for i, prev in zip(idxs[1:], idxs[:-1]): if step is not None: if i - prev == step: @@ -525,7 +605,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _parse_sig_js(self, jscode): funcname = self._search_regex( - r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode, + r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode, 'Initial JS player signature function name') jsi = JSInterpreter(jscode) @@ -565,24 +645,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _get_available_subtitles(self, video_id, webpage): try: - sub_list = self._download_webpage( + subs_doc = self._download_xml( 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, video_id, note=False) except ExtractorError as err: self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) return {} - lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) sub_lang_list = {} - for l in lang_list: - lang = l[1] + for track in subs_doc.findall('track'): + lang = track.attrib['lang_code'] if lang in sub_lang_list: continue params = compat_urllib_parse.urlencode({ 'lang': lang, 'v': video_id, 'fmt': self._downloader.params.get('subtitlesformat', 'srt'), - 'name': unescapeHTML(l[0]).encode('utf-8'), + 'name': track.attrib['name'].encode('utf-8'), }) url = 'https://www.youtube.com/api/timedtext?' + params sub_lang_list[lang] = url @@ -615,10 +694,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): list_url = caption_url + '&' + list_params caption_list = self._download_xml(list_url, video_id) original_lang_node = caption_list.find('track') - if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr': + if original_lang_node is None: self._downloader.report_warning('Video doesn\'t have automatic captions') return {} original_lang = original_lang_node.attrib['lang_code'] + caption_kind = original_lang_node.attrib.get('kind', '') sub_lang_list = {} for lang_node in caption_list.findall('target'): @@ -628,7 +708,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'tlang': sub_lang, 'fmt': sub_format, 'ts': timestamp, - 'kind': 'asr', + 'kind': caption_kind, }) sub_lang_list[sub_lang] = caption_url + '&' + params return sub_lang_list @@ -665,6 +745,47 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') + def _parse_dash_manifest( + self, video_id, dash_manifest_url, player_url, age_gate): + def decrypt_sig(mobj): + s = mobj.group(1) + dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) + return '/signature/%s' % dec_s + dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) + dash_doc = self._download_xml( + dash_manifest_url, video_id, + note='Downloading DASH manifest', + errnote='Could not download DASH manifest') + + formats = [] + for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): + url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') + if url_el is None: + continue + format_id = r.attrib['id'] + video_url = url_el.text + filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) + f = { + 'format_id': format_id, + 'url': video_url, + 'width': int_or_none(r.attrib.get('width')), + 'height': int_or_none(r.attrib.get('height')), + 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), + 'asr': int_or_none(r.attrib.get('audioSamplingRate')), + 'filesize': filesize, + 'fps': int_or_none(r.attrib.get('frameRate')), + } + try: + existing_format = next( + fo for fo in formats + if fo['format_id'] == format_id) + except StopIteration: + f.update(self._formats.get(format_id, {}).items()) + formats.append(f) + else: + existing_format.update(f) + return formats + def _real_extract(self, url): proto = ( 'http' if self._downloader.params.get('prefer_insecure', False) @@ -692,11 +813,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube + url = proto + '://www.youtube.com/embed/%s' % video_id + embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') data = compat_urllib_parse.urlencode({ 'video_id': video_id, 'eurl': 'https://youtube.googleapis.com/v/' + video_id, 'sts': self._search_regex( - r'"sts"\s*:\s*(\d+)', video_webpage, 'sts', default=''), + r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data video_info_webpage = self._download_webpage( @@ -722,9 +845,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # We fallback to the get_video_info pages (used by the embed page) self.report_video_info_webpage_download(video_id) for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = (proto + '://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) - video_info_webpage = self._download_webpage(video_info_url, + video_info_url = ( + '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (proto, video_id, el_type)) + video_info_webpage = self._download_webpage( + video_info_url, video_id, note=False, errnote='unable to download video info webpage') video_info = compat_parse_qs(video_info_webpage) @@ -797,7 +922,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): m_cat_container = self._search_regex( r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', - video_webpage, 'categories', fatal=False) + video_webpage, 'categories', default=None) if m_cat_container: category = self._html_search_regex( r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', @@ -875,7 +1000,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'url': video_info['conn'][0], 'player_url': player_url, }] - elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1: + elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) @@ -892,11 +1017,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): elif 's' in url_data: encrypted_sig = url_data['s'][0] - if not age_gate: - jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - video_webpage, 'JS player URL') - player_url = json.loads(jsplayer_url_json) + jsplayer_url_json = self._search_regex( + r'"assets":.+?"js":\s*("[^"]+")', + embed_webpage if age_gate else video_webpage, 'JS player URL') + player_url = json.loads(jsplayer_url_json) if player_url is None: player_url_json = self._search_regex( r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', @@ -940,50 +1064,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # Look for the DASH manifest if self._downloader.params.get('youtube_include_dash_manifest', True): - try: - # The DASH manifest used needs to be the one from the original video_webpage. - # The one found in get_video_info seems to be using different signatures. - # However, in the case of an age restriction there won't be any embedded dashmpd in the video_webpage. - # Luckily, it seems, this case uses some kind of default signature (len == 86), so the - # combination of get_video_info and the _static_decrypt_signature() decryption fallback will work here. - dash_manifest_url = video_info.get('dashmpd')[0] - - def decrypt_sig(mobj): - s = mobj.group(1) - dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) - return '/signature/%s' % dec_s - dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) - dash_doc = self._download_xml( - dash_manifest_url, video_id, - note='Downloading DASH manifest', - errnote='Could not download DASH manifest') - for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): - url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') - if url_el is None: - continue - format_id = r.attrib['id'] - video_url = url_el.text - filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) - f = { - 'format_id': format_id, - 'url': video_url, - 'width': int_or_none(r.attrib.get('width')), - 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), - 'asr': int_or_none(r.attrib.get('audioSamplingRate')), - 'filesize': filesize, - } - try: - existing_format = next( - fo for fo in formats - if fo['format_id'] == format_id) - except StopIteration: - f.update(self._formats.get(format_id, {})) - formats.append(f) - else: - existing_format.update(f) - - except (ExtractorError, KeyError) as e: - self.report_warning('Skipping DASH manifest: %r' % e, video_id) + dash_mpd = video_info.get('dashmpd') + if dash_mpd: + dash_manifest_url = dash_mpd[0] + try: + dash_formats = self._parse_dash_manifest( + video_id, dash_manifest_url, player_url, age_gate) + except (ExtractorError, KeyError) as e: + self.report_warning( + 'Skipping DASH manifest: %r' % e, video_id) + else: + # Hide the formats we found through non-DASH + dash_keys = set(df['format_id'] for df in dash_formats) + for f in formats: + if f['format_id'] in dash_keys: + f['format_id'] = 'nondash-%s' % f['format_id'] + f['preference'] = f.get('preference', 0) - 10000 + formats.extend(dash_formats) + + # Check for malformed aspect ratio + stretched_m = re.search( + r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', + video_webpage) + if stretched_m: + ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) + for f in formats: + if f.get('vcodec') != 'none': + f['stretched_ratio'] = ratio self._sort_formats(formats) @@ -1029,7 +1136,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): ((?:PL|LL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,}) )""" _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' - _MORE_PAGES_INDICATOR = r'data-link-type="next"' _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' IE_NAME = 'youtube:playlist' _TESTS = [{ @@ -1086,6 +1192,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'info_dict': { 'title': 'JODA7', } + }, { + 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', + 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', + 'info_dict': { + 'title': 'Uploads from Interstellar Movie', + }, + 'playlist_mincout': 21, }] def _real_initialize(self): @@ -1136,9 +1249,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): if playlist_id.startswith('RD'): # Mixes require a custom extraction process return self._extract_mix(playlist_id) - if playlist_id.startswith('TL'): - raise ExtractorError('For downloading YouTube.com top lists, use ' - 'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True) url = self._TEMPLATE_URL % playlist_id page = self._download_webpage(url, playlist_id) @@ -1170,6 +1280,10 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'Downloading page #%s' % page_num, transform_source=uppercase_escape) content_html = more['content_html'] + if not content_html.strip(): + # Some webpages show a "Load more" button but they don't + # have more videos + break more_widget_html = more['load_more_widget_html'] playlist_title = self._html_search_regex( @@ -1180,54 +1294,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): return self.playlist_result(url_results, playlist_id, playlist_title) -class YoutubeTopListIE(YoutubePlaylistIE): - IE_NAME = 'youtube:toplist' - IE_DESC = ('YouTube.com top lists, "yttoplist:{channel}:{list title}"' - ' (Example: "yttoplist:music:Top Tracks")') - _VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$' - _TESTS = [{ - 'url': 'yttoplist:music:Trending', - 'playlist_mincount': 5, - 'skip': 'Only works for logged-in users', - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel = mobj.group('chann') - title = mobj.group('title') - query = compat_urllib_parse.urlencode({'title': title}) - channel_page = self._download_webpage( - 'https://www.youtube.com/%s' % channel, title) - link = self._html_search_regex( - r'''(?x) - <a\s+href="([^"]+)".*?>\s* - <span\s+class="branded-page-module-title-text">\s* - <span[^>]*>.*?%s.*?</span>''' % re.escape(query), - channel_page, 'list') - url = compat_urlparse.urljoin('https://www.youtube.com/', link) - - video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"' - ids = [] - # sometimes the webpage doesn't contain the videos - # retry until we get them - for i in itertools.count(0): - msg = 'Downloading Youtube mix' - if i > 0: - msg += ', retry #%d' % i - - webpage = self._download_webpage(url, title, msg) - ids = orderedSet(re.findall(video_re, webpage)) - if ids: - break - url_results = self._ids_to_results(ids) - return self.playlist_result(url_results, playlist_title=title) - - class YoutubeChannelIE(InfoExtractor): IE_DESC = 'YouTube.com channels' - _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)" - _MORE_PAGES_INDICATOR = 'yt-uix-load-more' - _MORE_PAGES_URL = 'https://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s' + _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' IE_NAME = 'youtube:channel' _TESTS = [{ 'note': 'paginated channel', @@ -1243,13 +1312,8 @@ class YoutubeChannelIE(InfoExtractor): return ids_in_page def _real_extract(self, url): - # Extract channel id - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) + channel_id = self._match_id(url) - # Download channel page - channel_id = mobj.group(1) video_ids = [] url = 'https://www.youtube.com/channel/%s/videos' % channel_id channel_page = self._download_webpage(url, channel_id) @@ -1263,30 +1327,39 @@ class YoutubeChannelIE(InfoExtractor): # The videos are contained in a single page # the ajax pages can't be used, they are empty video_ids = self.extract_videos_from_page(channel_page) - else: - # Download all channel pages using the json-based channel_ajax query + entries = [ + self.url_result(video_id, 'Youtube', video_id=video_id) + for video_id in video_ids] + return self.playlist_result(entries, channel_id) + + def _entries(): + more_widget_html = content_html = channel_page for pagenum in itertools.count(1): - url = self._MORE_PAGES_URL % (pagenum, channel_id) - page = self._download_json( - url, channel_id, note='Downloading page #%s' % pagenum, - transform_source=uppercase_escape) - ids_in_page = self.extract_videos_from_page(page['content_html']) - video_ids.extend(ids_in_page) + ids_in_page = self.extract_videos_from_page(content_html) + for video_id in ids_in_page: + yield self.url_result( + video_id, 'Youtube', video_id=video_id) - if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: + mobj = re.search( + r'data-uix-load-more-href="/?(?P<more>[^"]+)"', + more_widget_html) + if not mobj: break - self._downloader.to_screen('[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), channel_id, + 'Downloading page #%s' % (pagenum + 1), + transform_source=uppercase_escape) + content_html = more['content_html'] + more_widget_html = more['load_more_widget_html'] - url_entries = [self.url_result(video_id, 'Youtube', video_id=video_id) - for video_id in video_ids] - return self.playlist_result(url_entries, channel_id) + return self.playlist_result(_entries(), channel_id) class YoutubeUserIE(InfoExtractor): IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)([A-Za-z0-9_-]+)' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/users/%s' _GDATA_PAGE_SIZE = 50 _GDATA_URL = 'https://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json' @@ -1314,12 +1387,7 @@ class YoutubeUserIE(InfoExtractor): return super(YoutubeUserIE, cls).suitable(url) def _real_extract(self, url): - # Extract username - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) - - username = mobj.group(1) + username = self._match_id(url) # Download video ids using YouTube Data API. Result size per # query is limited (currently to 50 videos) so we need to query @@ -1516,9 +1584,11 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): feed_entries = [] paging = 0 for i in itertools.count(1): - info = self._download_json(self._FEED_TEMPLATE % paging, - '%s feed' % self._FEED_NAME, - 'Downloading page %s' % i) + info = self._download_json( + self._FEED_TEMPLATE % paging, + '%s feed' % self._FEED_NAME, + 'Downloading page %s' % i, + transform_source=uppercase_escape) feed_html = info.get('feed_html') or info.get('content_html') load_more_widget_html = info.get('load_more_widget_html') or feed_html m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) @@ -1635,3 +1705,20 @@ class YoutubeTruncatedURLIE(InfoExtractor): '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' ' or simply youtube-dl BaW_jenozKc .', expected=True) + + +class YoutubeTruncatedIDIE(InfoExtractor): + IE_NAME = 'youtube:truncated_id' + IE_DESC = False # Do not list + _VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' + + _TESTS = [{ + 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + raise ExtractorError( + 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), + expected=True) diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 9ff00e2..98f1517 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -1,12 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals +import functools import re from .common import InfoExtractor from ..utils import ( int_or_none, unified_strdate, + OnDemandPagedList, ) @@ -87,7 +89,7 @@ def extract_from_xml_url(ie, video_id, xml_url): class ZDFIE(InfoExtractor): - _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' + _VALID_URL = r'(?:zdf:|zdf:video:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/(.*beitrag/(?:video/)?))(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' _TEST = { 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt', @@ -106,6 +108,52 @@ class ZDFIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id return extract_from_xml_url(self, video_id, xml_url) + + +class ZDFChannelIE(InfoExtractor): + _VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/)(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic', + 'info_dict': { + 'id': '1586442', + }, + 'playlist_count': 3, + } + _PAGE_SIZE = 50 + + def _fetch_page(self, channel_id, page): + offset = page * self._PAGE_SIZE + xml_url = ( + 'http://www.zdf.de/ZDFmediathek/xmlservice/web/aktuellste?ak=web&offset=%d&maxLength=%d&id=%s' + % (offset, self._PAGE_SIZE, channel_id)) + doc = self._download_xml( + xml_url, channel_id, + note='Downloading channel info', + errnote='Failed to download channel info') + + title = doc.find('.//information/title').text + description = doc.find('.//information/detail').text + for asset in doc.findall('.//teasers/teaser'): + a_type = asset.find('./type').text + a_id = asset.find('./details/assetId').text + if a_type not in ('video', 'topic'): + continue + yield { + '_type': 'url', + 'playlist_title': title, + 'playlist_description': description, + 'url': 'zdf:%s:%s' % (a_type, a_id), + } + + def _real_extract(self, url): + channel_id = self._match_id(url) + entries = OnDemandPagedList( + functools.partial(self._fetch_page, channel_id), self._PAGE_SIZE) + + return { + '_type': 'playlist', + 'id': channel_id, + 'entries': entries, + } diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 2e8c715..a30974e 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -109,7 +109,7 @@ def parseOpts(overrideArguments=None): kw = { 'version': __version__, 'formatter': fmt, - 'usage': '%prog [options] url [url...]', + 'usage': '%prog [OPTIONS] URL [URL...]', 'conflict_handler': 'resolve', } @@ -149,27 +149,47 @@ def parseOpts(overrideArguments=None): action='store_true', dest='list_extractor_descriptions', default=False, help='Output descriptions of all supported extractors') general.add_option( - '--proxy', dest='proxy', - default=None, metavar='URL', - help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection') - general.add_option( - '--socket-timeout', - dest='socket_timeout', type=float, default=None, - help='Time to wait before giving up, in seconds') - general.add_option( '--default-search', dest='default_search', metavar='PREFIX', help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.') general.add_option( '--ignore-config', action='store_true', - help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)') + help='Do not read configuration files. ' + 'When given in the global configuration file /etc/youtube-dl.conf: ' + 'Do not read the user configuration in ~/.config/youtube-dl/config ' + '(%APPDATA%/youtube-dl/config.txt on Windows)') general.add_option( '--flat-playlist', action='store_const', dest='extract_flat', const='in_playlist', default=False, help='Do not extract the videos of a playlist, only list them.') + network = optparse.OptionGroup(parser, 'Network Options') + network.add_option( + '--proxy', dest='proxy', + default=None, metavar='URL', + help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection') + network.add_option( + '--socket-timeout', + dest='socket_timeout', type=float, default=None, metavar='SECONDS', + help='Time to wait before giving up, in seconds') + network.add_option( + '--source-address', + metavar='IP', dest='source_address', default=None, + help='Client-side IP address to bind to (experimental)', + ) + network.add_option( + '-4', '--force-ipv4', + action='store_const', const='0.0.0.0', dest='source_address', + help='Make all connections via IPv4 (experimental)', + ) + network.add_option( + '-6', '--force-ipv6', + action='store_const', const='::', dest='source_address', + help='Make all connections via IPv6 (experimental)', + ) + selection = optparse.OptionGroup(parser, 'Video Selection') selection.add_option( '--playlist-start', @@ -264,10 +284,12 @@ def parseOpts(overrideArguments=None): action='store', dest='format', metavar='FORMAT', default=None, help=( 'video format code, specify the order of preference using' - ' slashes: -f 22/17/18 . -f mp4 , -f m4a and -f flv are also' - ' supported. You can also use the special names "best",' - ' "bestvideo", "bestaudio", "worst", "worstvideo" and' - ' "worstaudio". By default, youtube-dl will pick the best quality.' + ' slashes, as in -f 22/17/18 . ' + ' Instead of format codes, you can select by extension for the ' + 'extensions aac, m4a, mp3, mp4, ogg, wav, webm. ' + 'You can also use the special names "best",' + ' "bestvideo", "bestaudio", "worst". ' + ' By default, youtube-dl will pick the best quality.' ' Use commas to download multiple audio formats, such as' ' -f 136/137/mp4/bestvideo,140/m4a/bestaudio.' ' You can merge the video and audio of two formats into a single' @@ -297,6 +319,12 @@ def parseOpts(overrideArguments=None): '--youtube-skip-dash-manifest', action='store_false', dest='youtube_include_dash_manifest', help='Do not download the DASH manifest on YouTube videos') + video_format.add_option( + '--merge-output-format', + action='store', dest='merge_output_format', metavar='FORMAT', default=None, + help=( + 'If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.' + 'Ignored if no merge is required')) subtitles = optparse.OptionGroup(parser, 'Subtitle Options') subtitles.add_option( @@ -346,6 +374,10 @@ def parseOpts(overrideArguments=None): '--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP) + downloader.add_option( + '--playlist-reverse', + action='store_true', + help='Download playlist videos in reverse order') workarounds = optparse.OptionGroup(parser, 'Workarounds') workarounds.add_option( @@ -437,6 +469,11 @@ def parseOpts(overrideArguments=None): action='store_true', dest='dump_single_json', default=False, help='simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line.') verbosity.add_option( + '--print-json', + action='store_true', dest='print_json', default=False, + help='Be quiet and print the video information as JSON (video is still being downloaded).', + ) + verbosity.add_option( '--newline', action='store_true', dest='progress_with_newline', default=False, help='output progress bar as new lines') @@ -468,6 +505,14 @@ def parseOpts(overrideArguments=None): '--print-traffic', dest='debug_printtraffic', action='store_true', default=False, help='Display sent and read HTTP traffic') + verbosity.add_option( + '-C', '--call-home', + dest='call_home', action='store_true', default=False, + help='Contact the youtube-dl server for debugging.') + verbosity.add_option( + '--no-call-home', + dest='call_home', action='store_false', default=False, + help='Do NOT contact the youtube-dl server for debugging.') filesystem = optparse.OptionGroup(parser, 'Filesystem Options') filesystem.add_option( @@ -478,10 +523,6 @@ def parseOpts(overrideArguments=None): '--id', default=False, action='store_true', dest='useid', help='use only video ID in file name') filesystem.add_option( - '-A', '--auto-number', - action='store_true', dest='autonumber', default=False, - help='number downloaded files starting from 00000') - filesystem.add_option( '-o', '--output', dest='outtmpl', metavar='TEMPLATE', help=('output filename template. Use %(title)s to get the title, ' @@ -509,6 +550,10 @@ def parseOpts(overrideArguments=None): action='store_true', dest='restrictfilenames', default=False, help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames') filesystem.add_option( + '-A', '--auto-number', + action='store_true', dest='autonumber', default=False, + help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000') + filesystem.add_option( '-t', '--title', action='store_true', dest='usetitle', default=False, help='[deprecated] use title in file name (default)') @@ -612,6 +657,13 @@ def parseOpts(overrideArguments=None): action='store_true', dest='xattrs', default=False, help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)') postproc.add_option( + '--fixup', + metavar='POLICY', dest='fixup', default='detect_or_warn', + help='(experimental) Automatically correct known faults of the file. ' + 'One of never (do nothing), warn (only emit a warning), ' + 'detect_or_warn(check whether we can do anything about it, warn ' + 'otherwise') + postproc.add_option( '--prefer-avconv', action='store_false', dest='prefer_ffmpeg', help='Prefer avconv over ffmpeg for running the postprocessors (default)') @@ -625,6 +677,7 @@ def parseOpts(overrideArguments=None): help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'') parser.add_option_group(general) + parser.add_option_group(network) parser.add_option_group(selection) parser.add_option_group(downloader) parser.add_option_group(filesystem) diff --git a/youtube_dl/postprocessor/__init__.py b/youtube_dl/postprocessor/__init__.py index fb367eb..f850795 100644 --- a/youtube_dl/postprocessor/__init__.py +++ b/youtube_dl/postprocessor/__init__.py @@ -6,22 +6,29 @@ from .ffmpeg import ( FFmpegAudioFixPP, FFmpegEmbedSubtitlePP, FFmpegExtractAudioPP, + FFmpegFixupStretchedPP, FFmpegMergerPP, FFmpegMetadataPP, - FFmpegVideoConvertor, + FFmpegVideoConvertorPP, ) from .xattrpp import XAttrMetadataPP from .execafterdownload import ExecAfterDownloadPP + +def get_postprocessor(key): + return globals()[key + 'PP'] + + __all__ = [ 'AtomicParsleyPP', 'ExecAfterDownloadPP', 'FFmpegAudioFixPP', 'FFmpegEmbedSubtitlePP', 'FFmpegExtractAudioPP', + 'FFmpegFixupStretchedPP', 'FFmpegMergerPP', 'FFmpegMetadataPP', 'FFmpegPostProcessor', - 'FFmpegVideoConvertor', + 'FFmpegVideoConvertorPP', 'XAttrMetadataPP', ] diff --git a/youtube_dl/postprocessor/execafterdownload.py b/youtube_dl/postprocessor/execafterdownload.py index 09db436..75c0f7b 100644 --- a/youtube_dl/postprocessor/execafterdownload.py +++ b/youtube_dl/postprocessor/execafterdownload.py @@ -14,7 +14,7 @@ class ExecAfterDownloadPP(PostProcessor): def run(self, information): cmd = self.exec_cmd - if not '{}' in cmd: + if '{}' not in cmd: cmd += ' {}' cmd = cmd.replace('{}', shlex_quote(information['filepath'])) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 9303b83..5b0ff32 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -37,11 +37,11 @@ class FFmpegPostProcessor(PostProcessor): if not self._executable: raise FFmpegPostProcessorError('ffmpeg or avconv not found. Please install one.') - REQUIRED_VERSION = '1.0' + required_version = '10-0' if self._uses_avconv() else '1.0' if is_outdated_version( - self._versions[self._executable], REQUIRED_VERSION): + self._versions[self._executable], required_version): warning = 'Your copy of %s is outdated, update %s to version %s or newer if you encounter any errors.' % ( - self._executable, self._executable, REQUIRED_VERSION) + self._executable, self._executable, required_version) if self._downloader: self._downloader.report_warning(warning) @@ -51,6 +51,10 @@ class FFmpegPostProcessor(PostProcessor): return dict((p, get_exe_version(p, args=['-version'])) for p in programs) @property + def available(self): + return self._executable is not None + + @property def _executable(self): if self._downloader.params.get('prefer_ffmpeg', False): prefs = ('ffmpeg', 'avconv') @@ -78,11 +82,15 @@ class FFmpegPostProcessor(PostProcessor): def run_ffmpeg_multiple_files(self, input_paths, out_path, opts): self.check_version() + oldest_mtime = min( + os.stat(encodeFilename(path)).st_mtime for path in input_paths) + files_cmd = [] for path in input_paths: - files_cmd.extend(['-i', encodeFilename(path, True)]) - cmd = ([self._executable, '-y'] + files_cmd - + [encodeArgument(o) for o in opts] + + files_cmd.extend([encodeArgument('-i'), encodeFilename(path, True)]) + cmd = ([encodeFilename(self._executable, True), encodeArgument('-y')] + + files_cmd + + [encodeArgument(o) for o in opts] + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) if self._downloader.params.get('verbose', False): @@ -93,6 +101,7 @@ class FFmpegPostProcessor(PostProcessor): stderr = stderr.decode('utf-8', 'replace') msg = stderr.strip().split('\n')[-1] raise FFmpegPostProcessorError(msg) + os.utime(encodeFilename(out_path), (oldest_mtime, oldest_mtime)) if self._deletetempfiles: for ipath in input_paths: os.remove(ipath) @@ -122,8 +131,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): raise PostProcessingError('ffprobe or avprobe not found. Please install one.') try: cmd = [ - self._probe_executable, - '-show_streams', + encodeFilename(self._probe_executable, True), + encodeArgument('-show_streams'), encodeFilename(self._ffmpeg_filename_argument(path), True)] handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE) output = handle.communicate()[0] @@ -236,9 +245,9 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): return self._nopostoverwrites, information -class FFmpegVideoConvertor(FFmpegPostProcessor): +class FFmpegVideoConvertorPP(FFmpegPostProcessor): def __init__(self, downloader=None, preferedformat=None): - super(FFmpegVideoConvertor, self).__init__(downloader) + super(FFmpegVideoConvertorPP, self).__init__(downloader) self._preferedformat = preferedformat def run(self, information): @@ -466,15 +475,21 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): filename = information['filepath'] input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs] - opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy'] + opts = [ + '-map', '0', + '-c', 'copy', + # Don't copy the existing subtitles, we may be running the + # postprocessor a second time + '-map', '-0:s', + '-c:s', 'mov_text', + ] for (i, lang) in enumerate(sub_langs): - opts.extend(['-map', '%d:0' % (i + 1), '-c:s:%d' % i, 'mov_text']) + opts.extend(['-map', '%d:0' % (i + 1)]) lang_code = self._conver_lang_code(lang) if lang_code is not None: opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) - opts.extend(['-f', 'mp4']) - temp_filename = filename + '.temp' + temp_filename = prepend_extension(filename, 'temp') self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename) self.run_ffmpeg_multiple_files(input_files, temp_filename, opts) os.remove(encodeFilename(filename)) @@ -520,7 +535,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor): class FFmpegMergerPP(FFmpegPostProcessor): def run(self, info): filename = info['filepath'] - args = ['-c', 'copy', '-map', '0:v:0', '-map', '1:a:0', '-shortest'] + args = ['-c', 'copy', '-map', '0:v:0', '-map', '1:a:0'] self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename) self.run_ffmpeg_multiple_files(info['__files_to_merge'], filename, args) return True, info @@ -539,3 +554,22 @@ class FFmpegAudioFixPP(FFmpegPostProcessor): os.rename(encodeFilename(temp_filename), encodeFilename(filename)) return True, info + + +class FFmpegFixupStretchedPP(FFmpegPostProcessor): + def run(self, info): + stretched_ratio = info.get('stretched_ratio') + if stretched_ratio is None or stretched_ratio == 1: + return + + filename = info['filepath'] + temp_filename = prepend_extension(filename, 'temp') + + options = ['-c', 'copy', '-aspect', '%f' % stretched_ratio] + self._downloader.to_screen('[ffmpeg] Fixing aspect ratio in "%s"' % filename) + self.run_ffmpeg(filename, temp_filename, options) + + os.remove(encodeFilename(filename)) + os.rename(encodeFilename(temp_filename), encodeFilename(filename)) + + return True, info diff --git a/youtube_dl/swfinterp.py b/youtube_dl/swfinterp.py index 2bd264b..e60505a 100644 --- a/youtube_dl/swfinterp.py +++ b/youtube_dl/swfinterp.py @@ -4,8 +4,8 @@ import collections import io import zlib +from .compat import compat_str from .utils import ( - compat_str, ExtractorError, struct_unpack, ) diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 4c07a55..d8be404 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -13,6 +13,7 @@ from .compat import ( compat_str, compat_urllib_request, ) +from .utils import make_HTTPS_handler from .version import __version__ @@ -58,9 +59,12 @@ def update_self(to_screen, verbose): to_screen('It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.') return + https_handler = make_HTTPS_handler({}) + opener = compat_urllib_request.build_opener(https_handler) + # Check if there is a new version try: - newversion = compat_urllib_request.urlopen(VERSION_URL).read().decode('utf-8').strip() + newversion = opener.open(VERSION_URL).read().decode('utf-8').strip() except: if verbose: to_screen(compat_str(traceback.format_exc())) @@ -72,14 +76,14 @@ def update_self(to_screen, verbose): # Download and check versions info try: - versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8') + versions_info = opener.open(JSON_URL).read().decode('utf-8') versions_info = json.loads(versions_info) except: if verbose: to_screen(compat_str(traceback.format_exc())) to_screen('ERROR: can\'t obtain versions info. Please try again later.') return - if not 'signature' in versions_info: + if 'signature' not in versions_info: to_screen('ERROR: the versions file is not signed or corrupted. Aborting.') return signature = versions_info['signature'] @@ -120,7 +124,7 @@ def update_self(to_screen, verbose): return try: - urlh = compat_urllib_request.urlopen(version['exe'][0]) + urlh = opener.open(version['exe'][0]) newcontent = urlh.read() urlh.close() except (IOError, OSError): @@ -166,7 +170,7 @@ start /b "" cmd /c del "%%~f0"&exit /b" # Zip unix package elif isinstance(globals().get('__loader__'), zipimporter): try: - urlh = compat_urllib_request.urlopen(version['bin'][0]) + urlh = opener.open(version['bin'][0]) newcontent = urlh.read() urlh.close() except (IOError, OSError): diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 4d3cbac..7832ed8 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -10,6 +10,7 @@ import ctypes import datetime import email.utils import errno +import functools import gzip import itertools import io @@ -34,7 +35,9 @@ from .compat import ( compat_chr, compat_getenv, compat_html_entities, + compat_http_client, compat_parse_qs, + compat_socket_create_connection, compat_str, compat_urllib_error, compat_urllib_parse, @@ -166,7 +169,7 @@ def xpath_text(node, xpath, name=None, fatal=False): xpath = xpath.encode('ascii') n = node.find(xpath) - if n is None: + if n is None or n.text is None: if fatal: name = xpath if name is None else name raise ExtractorError('Could not find XML element %s' % name) @@ -205,6 +208,10 @@ def get_element_by_attribute(attribute, value, html): def clean_html(html): """Clean an HTML snippet into a readable string""" + + if html is None: # Convenience for sanitizing descriptions etc. + return html + # Newline vs <br /> html = html.replace('\n', ' ') html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html) @@ -280,6 +287,8 @@ def sanitize_filename(s, restricted=False, is_id=False): return '_' return char + # Handle timestamps + s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s) result = ''.join(map(replace_insane, s)) if not is_id: while '__' in result: @@ -363,7 +372,7 @@ def encodeArgument(s): if not isinstance(s, compat_str): # Legacy code that uses byte strings # Uncomment the following line after fixing all post processors - #assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s)) + # assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s)) s = s.decode('ascii') return encodeFilename(s, True) @@ -387,7 +396,20 @@ def formatSeconds(secs): return '%d' % secs -def make_HTTPS_handler(opts_no_check_certificate, **kwargs): +def make_HTTPS_handler(params, **kwargs): + opts_no_check_certificate = params.get('nocheckcertificate', False) + if hasattr(ssl, 'create_default_context'): # Python >= 3.4 or 2.7.9 + context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH) + if opts_no_check_certificate: + context.check_hostname = False + context.verify_mode = ssl.CERT_NONE + try: + return YoutubeDLHTTPSHandler(params, context=context, **kwargs) + except TypeError: + # Python 2.7.8 + # (create_default_context present but HTTPSHandler has no context=) + pass + if sys.version_info < (3, 2): import httplib @@ -405,27 +427,14 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs): except ssl.SSLError: self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23) - class HTTPSHandlerV3(compat_urllib_request.HTTPSHandler): - def https_open(self, req): - return self.do_open(HTTPSConnectionV3, req) - return HTTPSHandlerV3(**kwargs) - elif hasattr(ssl, 'create_default_context'): # Python >= 3.4 - context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH) - context.options &= ~ssl.OP_NO_SSLv3 # Allow older, not-as-secure SSLv3 - if opts_no_check_certificate: - context.verify_mode = ssl.CERT_NONE - return compat_urllib_request.HTTPSHandler(context=context, **kwargs) + return YoutubeDLHTTPSHandler(params, https_conn_class=HTTPSConnectionV3, **kwargs) else: # Python < 3.4 context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) context.verify_mode = (ssl.CERT_NONE if opts_no_check_certificate else ssl.CERT_REQUIRED) context.set_default_verify_paths() - try: - context.load_default_certs() - except AttributeError: - pass # Python < 3.4 - return compat_urllib_request.HTTPSHandler(context=context, **kwargs) + return YoutubeDLHTTPSHandler(params, context=context, **kwargs) class ExtractorError(Exception): @@ -463,6 +472,13 @@ class ExtractorError(Exception): return ''.join(traceback.format_tb(self.traceback)) +class UnsupportedError(ExtractorError): + def __init__(self, url): + super(UnsupportedError, self).__init__( + 'Unsupported URL: %s' % url, expected=True) + self.url = url + + class RegexNotFoundError(ExtractorError): """Error when a regex didn't match""" pass @@ -532,6 +548,26 @@ class ContentTooShortError(Exception): self.expected = expected +def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): + hc = http_class(*args, **kwargs) + source_address = ydl_handler._params.get('source_address') + if source_address is not None: + sa = (source_address, 0) + if hasattr(hc, 'source_address'): # Python 2.7+ + hc.source_address = sa + else: # Python 2.6 + def _hc_connect(self, *args, **kwargs): + sock = compat_socket_create_connection( + (self.host, self.port), self.timeout, sa) + if is_https: + self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file) + else: + self.sock = sock + hc.connect = functools.partial(_hc_connect, hc) + + return hc + + class YoutubeDLHandler(compat_urllib_request.HTTPHandler): """Handler for HTTP requests and responses. @@ -550,6 +586,15 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): public domain. """ + def __init__(self, params, *args, **kwargs): + compat_urllib_request.HTTPHandler.__init__(self, *args, **kwargs) + self._params = params + + def http_open(self, req): + return self.do_open(functools.partial( + _create_http_connection, self, compat_http_client.HTTPConnection, False), + req) + @staticmethod def deflate(data): try: @@ -619,6 +664,18 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): https_response = http_response +class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): + def __init__(self, params, https_conn_class=None, *args, **kwargs): + compat_urllib_request.HTTPSHandler.__init__(self, *args, **kwargs) + self._https_conn_class = https_conn_class or compat_http_client.HTTPSConnection + self._params = params + + def https_open(self, req): + return self.do_open(functools.partial( + _create_http_connection, self, self._https_conn_class, True), + req) + + def parse_iso8601(date_str, delimiter='T'): """ Return a UNIX timestamp from the given date """ @@ -644,17 +701,19 @@ def parse_iso8601(date_str, delimiter='T'): return calendar.timegm(dt.timetuple()) -def unified_strdate(date_str): +def unified_strdate(date_str, day_first=True): """Return a string with the date in the format YYYYMMDD""" if date_str is None: return None - upload_date = None # Replace commas date_str = date_str.replace(',', ' ') # %z (UTC offset) is only supported in python>=3.2 date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str) + # Remove AM/PM + timezone + date_str = re.sub(r'(?i)\s*(?:AM|PM)\s+[A-Z]+', '', date_str) + format_expressions = [ '%d %B %Y', '%d %b %Y', @@ -663,13 +722,10 @@ def unified_strdate(date_str): '%b %dst %Y %I:%M%p', '%b %dnd %Y %I:%M%p', '%b %dth %Y %I:%M%p', + '%Y %m %d', '%Y-%m-%d', '%Y/%m/%d', - '%d.%m.%Y', - '%d/%m/%Y', - '%d/%m/%y', '%Y/%m/%d %H:%M:%S', - '%d/%m/%Y %H:%M:%S', '%Y-%m-%d %H:%M:%S', '%Y-%m-%d %H:%M:%S.%f', '%d.%m.%Y %H:%M', @@ -681,6 +737,20 @@ def unified_strdate(date_str): '%Y-%m-%dT%H:%M:%S.%f', '%Y-%m-%dT%H:%M', ] + if day_first: + format_expressions.extend([ + '%d.%m.%Y', + '%d/%m/%Y', + '%d/%m/%y', + '%d/%m/%Y %H:%M:%S', + ]) + else: + format_expressions.extend([ + '%m.%d.%Y', + '%m/%d/%Y', + '%m/%d/%y', + '%m/%d/%Y %H:%M:%S', + ]) for expression in format_expressions: try: upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') @@ -712,8 +782,10 @@ def date_from_str(date_str): Return a datetime object from a string in the format YYYYMMDD or (now|today)[+-][0-9](day|week|month|year)(s)?""" today = datetime.date.today() - if date_str == 'now'or date_str == 'today': + if date_str in ('now', 'today'): return today + if date_str == 'yesterday': + return today - datetime.timedelta(days=1) match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str) if match is not None: sign = match.group('sign') @@ -808,22 +880,22 @@ def _windows_write_string(s, out): GetStdHandle = ctypes.WINFUNCTYPE( ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)( - ("GetStdHandle", ctypes.windll.kernel32)) + (b"GetStdHandle", ctypes.windll.kernel32)) h = GetStdHandle(WIN_OUTPUT_IDS[fileno]) WriteConsoleW = ctypes.WINFUNCTYPE( ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR, ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD), - ctypes.wintypes.LPVOID)(("WriteConsoleW", ctypes.windll.kernel32)) + ctypes.wintypes.LPVOID)((b"WriteConsoleW", ctypes.windll.kernel32)) written = ctypes.wintypes.DWORD(0) - GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(("GetFileType", ctypes.windll.kernel32)) + GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)((b"GetFileType", ctypes.windll.kernel32)) FILE_TYPE_CHAR = 0x0002 FILE_TYPE_REMOTE = 0x8000 GetConsoleMode = ctypes.WINFUNCTYPE( ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.POINTER(ctypes.wintypes.DWORD))( - ("GetConsoleMode", ctypes.windll.kernel32)) + (b"GetConsoleMode", ctypes.windll.kernel32)) INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value def not_a_console(handle): @@ -1024,7 +1096,7 @@ def smuggle_url(url, data): def unsmuggle_url(smug_url, default=None): - if not '#__youtubedl_smuggle' in smug_url: + if '#__youtubedl_smuggle' not in smug_url: return smug_url, default url, _, sdata = smug_url.rpartition('#') jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0] @@ -1090,11 +1162,14 @@ def parse_filesize(s): } units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE) - m = re.match(r'(?P<num>[0-9]+(?:\.[0-9]*)?)\s*(?P<unit>%s)' % units_re, s) + m = re.match( + r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)' % units_re, s) if not m: return None - return int(float(m.group('num')) * _UNIT_TABLE[m.group('unit')]) + num_str = m.group('num').replace(',', '.') + mult = _UNIT_TABLE[m.group('unit')] + return int(float(num_str) * mult) def get_term_width(): @@ -1196,25 +1271,36 @@ def float_or_none(v, scale=1, invscale=1, default=None): def parse_duration(s): - if s is None: + if not isinstance(s, basestring if sys.version_info < (3, 0) else compat_str): return None s = s.strip() m = re.match( - r'''(?ix)T? + r'''(?ix)(?:P?T)? + (?: + (?P<only_mins>[0-9.]+)\s*(?:mins?|minutes?)\s*| + (?P<only_hours>[0-9.]+)\s*(?:hours?)| + (?: (?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)? (?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s* )? - (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$''', s) + (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)? + )$''', s) if not m: return None - res = int(m.group('secs')) + res = 0 + if m.group('only_mins'): + return float_or_none(m.group('only_mins'), invscale=60) + if m.group('only_hours'): + return float_or_none(m.group('only_hours'), invscale=60 * 60) + if m.group('secs'): + res += int(m.group('secs')) if m.group('mins'): res += int(m.group('mins')) * 60 - if m.group('hours'): - res += int(m.group('hours')) * 60 * 60 + if m.group('hours'): + res += int(m.group('hours')) * 60 * 60 if m.group('ms'): res += float(m.group('ms')) return res @@ -1236,18 +1322,25 @@ def check_executable(exe, args=[]): def get_exe_version(exe, args=['--version'], - version_re=r'version\s+([0-9._-a-zA-Z]+)', - unrecognized='present'): + version_re=None, unrecognized='present'): """ Returns the version of the specified executable, or False if the executable is not present """ try: - out, err = subprocess.Popen( + out, _ = subprocess.Popen( [exe] + args, stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate() except OSError: return False - firstline = out.partition(b'\n')[0].decode('ascii', 'ignore') - m = re.search(version_re, firstline) + if isinstance(out, bytes): # Python 2.x + out = out.decode('ascii', 'ignore') + return detect_exe_version(out, version_re, unrecognized) + + +def detect_exe_version(output, version_re=None, unrecognized='present'): + assert isinstance(output, compat_str) + if version_re is None: + version_re = r'version\s+([-0-9._a-zA-Z]+)' + m = re.search(version_re, output) if m: return m.group(1) else: @@ -1488,7 +1581,7 @@ def limit_length(s, length): def version_tuple(v): - return [int(e) for e in v.split('.')] + return tuple(int(e) for e in re.split(r'[-.]', v)) def is_outdated_version(version, limit, assume_new=True): @@ -1510,3 +1603,23 @@ def ytdl_is_updateable(): def args_to_str(args): # Get a short string representation for a subprocess command return ' '.join(shlex_quote(a) for a in args) + + +def urlhandle_detect_ext(url_handle): + try: + url_handle.headers + getheader = lambda h: url_handle.headers[h] + except AttributeError: # Python < 3 + getheader = url_handle.info().getheader + + return getheader('Content-Type').split("/")[1] + + +def age_restricted(content_limit, age_limit): + """ Returns True iff the content should be blocked """ + + if age_limit is None: # No limit set + return False + if content_limit is None: + return False # Content available for everyone + return age_limit < content_limit diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 847a47c..63a79a7 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2014.12.01' +__version__ = '2015.01.16' |