diff options
| author | Wolfgang Wiedmeyer <wolfgit@wiedmeyer.de> | 2016-12-03 21:10:24 +0100 |
|---|---|---|
| committer | Wolfgang Wiedmeyer <wolfgit@wiedmeyer.de> | 2016-12-03 21:10:24 +0100 |
| commit | 0b9ee148f5234d4e9fef6110e512dd7e95a5641b (patch) | |
| tree | c2a48510636f461b9f74cee7612f72336d0ea19d | |
| parent | b624dcf2b031a55102993dbff90c1c1d0c80fae2 (diff) | |
| parent | 83442966194640d9bc00e7f3086aa5e8b25c4ae3 (diff) | |
| download | youtube-dl-0b9ee148f5234d4e9fef6110e512dd7e95a5641b.zip youtube-dl-0b9ee148f5234d4e9fef6110e512dd7e95a5641b.tar.gz youtube-dl-0b9ee148f5234d4e9fef6110e512dd7e95a5641b.tar.bz2 | |
Merge branch 'upstream'
127 files changed, 2796 insertions, 802 deletions
diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 0a051ad..36559dd 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.21.1*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.10.21.1** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.12.01*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.12.01** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ $ youtube-dl -v <your command line> [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2016.10.21.1 +[debug] youtube-dl version 2016.12.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} @@ -30,6 +30,10 @@ updates_key.pem *.m4v *.mp3 *.3gp +*.wav +*.ape +*.mkv +*.swf *.part *.swp test/testdata @@ -188,3 +188,5 @@ Xie Yanbo Philip Xu John Hawkinson Rich Leeper +Zhong Jianxin +Thor77 diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 29f52cb..495955b 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -92,7 +92,7 @@ If you want to create a build of youtube-dl yourself, you'll need ### Adding support for a new site -If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**. +If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**. After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): @@ -245,7 +245,7 @@ Say `meta` from the previous example has a `title` and you are about to extract title = meta['title'] ``` -If `title` disappeares from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected. +If `title` disappears from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected. Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario: @@ -1,3 +1,170 @@ +version <unreleased> + +Extractors ++ [thisoldhouse] Recognize /tv-episode/ URLs (#11271) + +version 2016.12.01 + +Extractors +* [soundcloud] Update client id (#11327) +* [ruutu] Detect DRM protected videos ++ [liveleak] Add support for youtube embeds (#10688) +* [spike] Fix full episodes support (#11312) +* [comedycentral] Fix full episodes support +* [normalboots] Rewrite in terms of JWPlatform (#11184) +* [teamfourstar] Rewrite in terms of JWPlatform (#11184) +- [screenwavemedia] Remove extractor (#11184) + + +version 2016.11.27 + +Extractors ++ [webcaster] Add support for webcaster.pro ++ [azubu] Add support for azubu.uol.com.br (#11305) +* [viki] Prefer hls formats +* [viki] Fix rtmp formats extraction (#11255) +* [puls4] Relax URL regular expression (#11267) +* [vevo] Improve artist extraction (#10911) +* [mitele] Relax URL regular expression and extract more metadata (#11244) ++ [cbslocal] Recognize New York site (#11285) ++ [youtube:playlist] Pass disable_polymer in URL query (#11193) + + +version 2016.11.22 + +Extractors +* [hellporno] Fix video extension extraction (#11247) ++ [hellporno] Add support for hellporno.net (#11247) ++ [amcnetworks] Recognize more BBC America URLs (#11263) +* [funnyordie] Improve extraction (#11208) +* [extractor/generic] Improve limelight embeds support +- [crunchyroll] Remove ScaledBorderAndShadow from ASS subtitles (#8207, #9028) +* [bandcamp] Fix free downloads extraction and extract all formats (#11067) +* [twitter:card] Relax URL regular expression (#11225) ++ [tvanouvelles] Add support for tvanouvelles.ca (#10616) + + +version 2016.11.18 + +Extractors +* [youtube:live] Relax URL regular expression (#11164) +* [openload] Fix extraction (#10408, #11122) +* [vlive] Prefer locale over language for subtitles id (#11203) + + +version 2016.11.14.1 + +Core ++ [downoader/fragment,f4m,hls] Respect HTTP headers from info dict +* [extractor/common] Fix media templates with Bandwidth substitution pattern in + MPD manifests (#11175) +* [extractor/common] Improve thumbnail extraction from JSON-LD + +Extractors ++ [nrk] Workaround geo restriction ++ [nrk] Improve error detection and messages ++ [afreecatv] Add support for vod.afreecatv.com (#11174) +* [cda] Fix and improve extraction (#10929, #10936) +* [plays] Fix extraction (#11165) +* [eagleplatform] Fix extraction (#11160) ++ [audioboom] Recognize /posts/ URLs (#11149) + + +version 2016.11.08.1 + +Extractors +* [espn:article] Fix support for espn.com articles +* [franceculture] Fix extraction (#11140) + + +version 2016.11.08 + +Extractors +* [tmz:article] Fix extraction (#11052) +* [espn] Fix extraction (#11041) +* [mitele] Fix extraction after website redesign (#10824) +- [ard] Remove age restriction check (#11129) +* [generic] Improve support for pornhub.com embeds (#11100) ++ [generic] Add support for redtube.com embeds (#11099) ++ [generic] Add support for drtuber.com embeds (#11098) ++ [redtube] Add support for embed URLs ++ [drtuber] Add support for embed URLs ++ [yahoo] Improve content id extraction (#11088) +* [toutv] Relax URL regular expression (#11121) + + +version 2016.11.04 + +Core +* [extractor/common] Tolerate malformed RESOLUTION attribute in m3u8 + manifests (#11113) +* [downloader/ism] Fix AVC Decoder Configuration Record + +Extractors ++ [fox9] Add support for fox9.com (#11110) ++ [anvato] Extract more metadata and improve formats extraction +* [vodlocker] Improve removed videos detection (#11106) ++ [vzaar] Add support for vzaar.com (#11093) ++ [vice] Add support for uplynk preplay videos (#11101) +* [tubitv] Fix extraction (#11061) ++ [shahid] Add support for authentication (#11091) ++ [radiocanada] Add subtitles support (#11096) ++ [generic] Add support for ISM manifests + + +version 2016.11.02 + +Core ++ Add basic support for Smooth Streaming protocol (#8118, #10969) +* Improve MPD manifest base URL extraction (#10909, #11079) +* Fix --match-filter for int-like strings (#11082) + +Extractors ++ [mva] Add support for ISM formats ++ [msn] Add support for ISM formats ++ [onet] Add support for ISM formats ++ [tvp] Add support for ISM formats ++ [nicknight] Add support for nicknight sites (#10769) + + +version 2016.10.30 + +Extractors +* [facebook] Improve 1080P video detection (#11073) +* [imgur] Recognize /r/ URLs (#11071) +* [beeg] Fix extraction (#11069) +* [openload] Fix extraction (#10408) +* [gvsearch] Modernize and fix search request (#11051) +* [adultswim] Fix extraction (#10979) ++ [nobelprize] Add support for nobelprize.org (#9999) +* [hornbunny] Fix extraction (#10981) +* [tvp] Improve video id extraction (#10585) + + +version 2016.10.26 + +Extractors ++ [rentv] Add support for ren.tv (#10620) ++ [ard] Detect unavailable videos (#11018) +* [vk] Fix extraction (#11022) + + +version 2016.10.25 + +Core +* Running youtube-dl in the background is fixed (#10996, #10706, #955) + +Extractors ++ [jamendo] Add support for jamendo.com (#10132, #10736) ++ [pandatv] Add support for panda.tv (#10736) ++ [dotsub] Support Vimeo embed (#10964) +* [litv] Fix extraction ++ [vimeo] Delegate ondemand redirects to ondemand extractor (#10994) +* [vivo] Fix extraction (#11003) ++ [twitch:stream] Add support for rebroadcasts (#10995) +* [pluralsight] Fix subtitles conversion (#10990) + + version 2016.10.21.1 Extractors @@ -1,7 +1,7 @@ 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 youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe + 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 youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe find . -name "*.pyc" -delete find . -name "*.class" -delete @@ -664,7 +664,7 @@ $ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best' # Download best format available but not better that 480p $ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]' -# Download best video only format but no bigger that 50 MB +# Download best video only format but no bigger than 50 MB $ youtube-dl -f 'best[filesize<50M]' # Download best format available via direct link over HTTP/HTTPS protocol @@ -758,7 +758,7 @@ Once the video is fully downloaded, use any video player, such as [mpv](https:// ### 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 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 and/or HTTP headers. 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. You can also get necessary cookies and HTTP headers from JSON output obtained with `--dump-json`. 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. @@ -930,7 +930,7 @@ If you want to create a build of youtube-dl yourself, you'll need ### Adding support for a new site -If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**. +If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**. After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): @@ -1083,7 +1083,7 @@ Say `meta` from the previous example has a `title` and you are about to extract title = meta['title'] ``` -If `title` disappeares from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected. +If `title` disappears from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected. Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario: diff --git a/devscripts/bash-completion.py b/devscripts/bash-completion.py index ce68f26..3d13913 100755 --- a/devscripts/bash-completion.py +++ b/devscripts/bash-completion.py @@ -25,5 +25,6 @@ def build_completion(opt_parser): filled_template = template.replace("{{flags}}", " ".join(opts_flag)) f.write(filled_template) + parser = youtube_dl.parseOpts()[0] build_completion(parser) diff --git a/devscripts/create-github-release.py b/devscripts/create-github-release.py index 3b8021e..30716ad 100644 --- a/devscripts/create-github-release.py +++ b/devscripts/create-github-release.py @@ -2,11 +2,13 @@ from __future__ import unicode_literals import base64 +import io import json import mimetypes import netrc import optparse import os +import re import sys sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) @@ -90,16 +92,23 @@ class GitHubReleaser(object): def main(): - parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH') + parser = optparse.OptionParser(usage='%prog CHANGELOG VERSION BUILDPATH') options, args = parser.parse_args() - if len(args) != 2: + if len(args) != 3: parser.error('Expected a version and a build directory') - version, build_path = args + changelog_file, version, build_path = args + + with io.open(changelog_file, encoding='utf-8') as inf: + changelog = inf.read() + + mobj = re.search(r'(?s)version %s\n{2}(.+?)\n{3}' % version, changelog) + body = mobj.group(1) if mobj else '' releaser = GitHubReleaser() - new_release = releaser.create_release(version, name='youtube-dl %s' % version) + new_release = releaser.create_release( + version, name='youtube-dl %s' % version, body=body) release_id = new_release['id'] for asset in os.listdir(build_path): diff --git a/devscripts/fish-completion.py b/devscripts/fish-completion.py index 41629d8..51d19dd 100755 --- a/devscripts/fish-completion.py +++ b/devscripts/fish-completion.py @@ -44,5 +44,6 @@ def build_completion(opt_parser): with open(FISH_COMPLETION_FILE, 'w') as f: f.write(filled_template) + parser = youtube_dl.parseOpts()[0] build_completion(parser) diff --git a/devscripts/generate_aes_testdata.py b/devscripts/generate_aes_testdata.py index 2e389fc..e3df42c 100644 --- a/devscripts/generate_aes_testdata.py +++ b/devscripts/generate_aes_testdata.py @@ -23,6 +23,7 @@ def openssl_encode(algo, key, iv): out, _ = prog.communicate(secret_msg) return out + iv = key = [0x20, 0x15] + 14 * [0] r = openssl_encode('aes-128-cbc', key, iv) diff --git a/devscripts/gh-pages/update-sites.py b/devscripts/gh-pages/update-sites.py index 503c137..531c93c 100755 --- a/devscripts/gh-pages/update-sites.py +++ b/devscripts/gh-pages/update-sites.py @@ -32,5 +32,6 @@ def main(): with open('supportedsites.html', 'w', encoding='utf-8') as sitesf: sitesf.write(template) + if __name__ == '__main__': main() diff --git a/devscripts/make_contributing.py b/devscripts/make_contributing.py index 5e454a4..226d1a5 100755 --- a/devscripts/make_contributing.py +++ b/devscripts/make_contributing.py @@ -28,5 +28,6 @@ def main(): with io.open(outfile, 'w', encoding='utf-8') as outf: outf.write(out) + if __name__ == '__main__': main() diff --git a/devscripts/make_lazy_extractors.py b/devscripts/make_lazy_extractors.py index 9a79c2b..19114d3 100644 --- a/devscripts/make_lazy_extractors.py +++ b/devscripts/make_lazy_extractors.py @@ -59,6 +59,7 @@ def build_lazy_ie(ie, name): s += make_valid_template.format(valid_url=ie._make_valid_url()) return s + # find the correct sorting and add the required base classes so that sublcasses # can be correctly created classes = _ALL_CLASSES[:-1] diff --git a/devscripts/make_supportedsites.py b/devscripts/make_supportedsites.py index 8cb4a46..764795b 100644 --- a/devscripts/make_supportedsites.py +++ b/devscripts/make_supportedsites.py @@ -41,5 +41,6 @@ def main(): 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 ce54873..f9fe63f 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -74,5 +74,6 @@ def filter_options(readme): return ret + if __name__ == '__main__': main() diff --git a/devscripts/release.sh b/devscripts/release.sh index 1af61aa..4db5def 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -110,7 +110,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz" for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done ROOT=$(pwd) -python devscripts/create-github-release.py $version "$ROOT/build/$version" +python devscripts/create-github-release.py ChangeLog $version "$ROOT/build/$version" ssh ytdl@yt-dl.org "sh html/update_latest.sh $version" diff --git a/devscripts/zsh-completion.py b/devscripts/zsh-completion.py index 04728e8..60aaf76 100755 --- a/devscripts/zsh-completion.py +++ b/devscripts/zsh-completion.py @@ -44,5 +44,6 @@ def build_completion(opt_parser): with open(ZSH_COMPLETION_FILE, "w") as f: f.write(template) + parser = youtube_dl.parseOpts()[0] build_completion(parser) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 0a51888..edb76d9 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -158,6 +158,7 @@ - **CollegeRama** - **ComCarCoff** - **ComedyCentral** + - **ComedyCentralFullEpisodes** - **ComedyCentralShortname** - **ComedyCentralTV** - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED @@ -225,6 +226,7 @@ - **EroProfile** - **Escapist** - **ESPN** + - **ESPNArticle** - **EsriVideo** - **Europa** - **EveryonesMixtape** @@ -247,6 +249,7 @@ - **FootyRoom** - **Formula1** - **FOX** + - **FOX9** - **Foxgay** - **foxnews**: Fox News and Fox Business Video - **foxnews:article** @@ -332,6 +335,8 @@ - **ivideon**: Ivideon TV - **Iwara** - **Izlesene** + - **Jamendo** + - **JamendoAlbum** - **JeuxVideo** - **Jove** - **jpopsuki.tv** @@ -481,11 +486,13 @@ - **nhl.com:videocenter:category**: NHL videocenter category - **nick.com** - **nick.de** + - **nicknight** - **niconico**: ニコニコ動画 - **NiconicoPlaylist** - **Nintendo** - **njoy**: N-JOY - **njoy:embed** + - **NobelPrize** - **Noco** - **Normalboots** - **NosVideo** @@ -527,6 +534,7 @@ - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek + - **PandaTV**: 熊猫TV - **pandora.tv**: 판도라TV - **parliamentlive.tv**: UK parliament videos - **Patreon** @@ -586,6 +594,8 @@ - **RDS**: RDS.ca - **RedTube** - **RegioTV** + - **RENTV** + - **RENTVArticle** - **Restudy** - **Reuters** - **ReverbNation** @@ -634,14 +644,13 @@ - **Screencast** - **ScreencastOMatic** - **ScreenJunkies** - - **ScreenwaveMedia** - **Seeker** - **SenateISVP** - **SendtoNews** - **ServingSys** - **Sexu** - **Shahid** - - **Shared**: shared.sx and vivo.sx + - **Shared**: shared.sx - **ShareSix** - **Sina** - **SixPlay** @@ -706,7 +715,7 @@ - **teachertube:user:collection**: teachertube.com user and collection videos - **TeachingChannel** - **Teamcoco** - - **TeamFour** + - **TeamFourStar** - **TechTalks** - **techtv.mit.edu** - **ted** @@ -762,6 +771,8 @@ - **TV2Article** - **TV3** - **TV4**: tv4.se and tv4play.se + - **TVANouvelles** + - **TVANouvellesArticle** - **TVC** - **TVCArticle** - **tvigle**: Интернет-телевидение Tvigle.ru @@ -848,6 +859,7 @@ - **Vimple**: Vimple - one-click video hosting - **Vine** - **vine:user** + - **Vivo**: vivo.sx - **vk**: VK - **vk:uservideos**: VK - User's Videos - **vk:wallpost** @@ -862,6 +874,7 @@ - **vube**: Vube.com - **VuClip** - **VyboryMos** + - **Vzaar** - **Walla** - **washingtonpost** - **washingtonpost:article** @@ -869,6 +882,8 @@ - **WatchIndianPorn**: Watch Indian Porn - **WDR** - **wdr:mobile** + - **Webcaster** + - **WebcasterFeed** - **WebOfStories** - **WebOfStoriesPlaylist** - **WeiqiTV**: WQTV diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index a98305c..437c727 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -84,5 +84,6 @@ class TestInfoExtractor(unittest.TestCase): self.assertRaises(ExtractorError, self.ie._download_json, uri, None) self.assertEqual(self.ie._download_json(uri, None, fatal=False), None) + if __name__ == '__main__': unittest.main() diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 0dfe25c..8bf00be 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -605,6 +605,7 @@ class TestYoutubeDL(unittest.TestCase): 'extractor': 'TEST', 'duration': 30, 'filesize': 10 * 1024, + 'playlist_id': '42', } second = { 'id': '2', @@ -614,6 +615,7 @@ class TestYoutubeDL(unittest.TestCase): 'duration': 10, 'description': 'foo', 'filesize': 5 * 1024, + 'playlist_id': '43', } videos = [first, second] @@ -650,6 +652,10 @@ class TestYoutubeDL(unittest.TestCase): res = get_videos(f) self.assertEqual(res, ['1']) + f = match_filter_func('playlist_id = 42') + res = get_videos(f) + self.assertEqual(res, ['1']) + def test_playlist_items_selection(self): entries = [{ 'id': compat_str(i), diff --git a/test/test_aes.py b/test/test_aes.py index 315a3f5..54078a6 100644 --- a/test/test_aes.py +++ b/test/test_aes.py @@ -51,5 +51,6 @@ class TestAES(unittest.TestCase): decrypted = (aes_decrypt_text(encrypted, password, 32)) self.assertEqual(decrypted, self.secret_msg) + if __name__ == '__main__': unittest.main() diff --git a/test/test_download.py b/test/test_download.py index a3f1c06..4639529 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -60,6 +60,7 @@ def _file_md5(fn): with open(fn, 'rb') as f: return hashlib.md5(f.read()).hexdigest() + defs = gettestcases() @@ -217,6 +218,7 @@ def generator(test_case): return test_template + # And add them to TestDownload for n, test_case in enumerate(defs): test_method = generator(test_case) diff --git a/test/test_execution.py b/test/test_execution.py index 620db08..11661bb 100644 --- a/test/test_execution.py +++ b/test/test_execution.py @@ -39,5 +39,6 @@ class TestExecution(unittest.TestCase): _, stderr = p.communicate() self.assertFalse(stderr) + if __name__ == '__main__': unittest.main() diff --git a/test/test_http.py b/test/test_http.py index bb0a098..7a7a351 100644 --- a/test/test_http.py +++ b/test/test_http.py @@ -169,5 +169,6 @@ class TestProxy(unittest.TestCase): # b'xn--fiq228c' is '中文'.encode('idna') self.assertEqual(response, 'normal: http://xn--fiq228c.tw/') + if __name__ == '__main__': unittest.main() diff --git a/test/test_iqiyi_sdk_interpreter.py b/test/test_iqiyi_sdk_interpreter.py index 9d95cb6..789059d 100644 --- a/test/test_iqiyi_sdk_interpreter.py +++ b/test/test_iqiyi_sdk_interpreter.py @@ -43,5 +43,6 @@ class TestIqiyiSDKInterpreter(unittest.TestCase): ie._login() self.assertTrue('unable to log in:' in logger.messages[0]) + if __name__ == '__main__': unittest.main() diff --git a/test/test_jsinterp.py b/test/test_jsinterp.py index 63c350b..c24b8ca 100644 --- a/test/test_jsinterp.py +++ b/test/test_jsinterp.py @@ -104,6 +104,14 @@ class TestJSInterpreter(unittest.TestCase): }''') self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50]) + def test_call(self): + jsi = JSInterpreter(''' + function x() { return 2; } + function y(a) { return x() + a; } + function z() { return y(3); } + ''') + self.assertEqual(jsi.call_function('z'), 5) + if __name__ == '__main__': unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index b1b2eff..2e3cd01 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -69,6 +69,7 @@ from youtube_dl.utils import ( uppercase_escape, lowercase_escape, url_basename, + base_url, urlencode_postdata, urshift, update_url_query, @@ -437,6 +438,13 @@ class TestUtil(unittest.TestCase): url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'), 'trailer.mp4') + def test_base_url(self): + self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/') + self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/') + self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/') + self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/') + self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/') + def test_parse_age_limit(self): self.assertEqual(parse_age_limit(None), None) self.assertEqual(parse_age_limit(False), None) @@ -1067,5 +1075,6 @@ The first line self.assertEqual(get_element_by_class('foo', html), 'nice') self.assertEqual(get_element_by_class('no-such-class', html), None) + if __name__ == '__main__': unittest.main() diff --git a/test/test_verbose_output.py b/test/test_verbose_output.py index 96a66f7..c1465fe 100644 --- a/test/test_verbose_output.py +++ b/test/test_verbose_output.py @@ -66,5 +66,6 @@ class TestVerboseOutput(unittest.TestCase): self.assertTrue(b'-p' in serr) self.assertTrue(b'secret' not in serr) + if __name__ == '__main__': unittest.main() diff --git a/test/test_write_annotations.py b/test/test_write_annotations.py index 8de08f2..41abdfe 100644 --- a/test/test_write_annotations.py +++ b/test/test_write_annotations.py @@ -24,6 +24,7 @@ class YoutubeDL(youtube_dl.YoutubeDL): super(YoutubeDL, self).__init__(*args, **kwargs) self.to_stderr = self.to_screen + params = get_params({ 'writeannotations': True, 'skip_download': True, @@ -74,5 +75,6 @@ class TestAnnotations(unittest.TestCase): def tearDown(self): try_rm(ANNOTATIONS_FILE) + if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index af1c454..7a33dbf 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -66,5 +66,6 @@ class TestYoutubeLists(unittest.TestCase): for entry in result['entries']: self.assertTrue(entry.get('title')) + if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index 0608644..f0c370e 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -114,6 +114,7 @@ def make_tfunc(url, stype, sig_input, expected_sig): test_func.__name__ = str('test_signature_' + stype + '_' + test_id) setattr(TestSignature, test_func.__name__, test_func) + for test_spec in _TESTS: make_tfunc(*test_spec) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 99825e3..53f20ac 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1658,7 +1658,7 @@ class YoutubeDL(object): video_ext, audio_ext = audio.get('ext'), video.get('ext') if video_ext and audio_ext: COMPATIBLE_EXTS = ( - ('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v'), + ('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma'), ('webm') ) for exts in COMPATIBLE_EXTS: diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 6433935..6850d95 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -95,8 +95,7 @@ def _real_main(argv=None): write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n') except IOError: sys.exit('ERROR: batch file could not be read') - all_urls = batch_urls + args - all_urls = [url.strip() for url in all_urls] + all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls _enc = preferredencoding() all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls] @@ -450,4 +449,5 @@ def main(argv=None): except KeyboardInterrupt: sys.exit('\nERROR: Interrupted by user') + __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors'] diff --git a/youtube_dl/aes.py b/youtube_dl/aes.py index a01c367..b8ff454 100644 --- a/youtube_dl/aes.py +++ b/youtube_dl/aes.py @@ -174,6 +174,7 @@ def aes_decrypt_text(data, password, key_size_bytes): return plaintext + RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36) SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76, 0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0, @@ -328,4 +329,5 @@ def inc(data): break return data + __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text'] diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index b8aaf5a..83ee7e2 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2491,6 +2491,7 @@ class _TreeBuilder(etree.TreeBuilder): def doctype(self, name, pubid, system): pass + if sys.version_info[0] >= 3: def compat_etree_fromstring(text): return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder())) @@ -2787,6 +2788,7 @@ def workaround_optparse_bug9161(): return real_add_option(self, *bargs, **bkwargs) optparse.OptionGroup.add_option = _compat_add_option + if hasattr(shutil, 'get_terminal_size'): # Python >= 3.3 compat_get_terminal_size = shutil.get_terminal_size else: diff --git a/youtube_dl/downloader/__init__.py b/youtube_dl/downloader/__init__.py index 817591d..16952e3 100644 --- a/youtube_dl/downloader/__init__.py +++ b/youtube_dl/downloader/__init__.py @@ -7,6 +7,7 @@ from .http import HttpFD from .rtmp import RtmpFD from .dash import DashSegmentsFD from .rtsp import RtspFD +from .ism import IsmFD from .external import ( get_external_downloader, FFmpegFD, @@ -24,6 +25,7 @@ PROTOCOL_MAP = { 'rtsp': RtspFD, 'f4m': F4mFD, 'http_dash_segments': DashSegmentsFD, + 'ism': IsmFD, } diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 0aeae3b..5d3e5d8 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -293,6 +293,7 @@ class FFmpegFD(ExternalFD): class AVconvFD(FFmpegFD): pass + _BY_NAME = dict( (klass.get_basename(), klass) for name, klass in globals().items() diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 80c21d4..688e086 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -314,7 +314,8 @@ class F4mFD(FragmentFD): man_url = info_dict['url'] requested_bitrate = info_dict.get('tbr') self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) - urlh = self.ydl.urlopen(man_url) + + urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url)) man_url = urlh.geturl() # Some manifests may be malformed, e.g. prosiebensat1 generated manifests # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244 @@ -387,7 +388,10 @@ class F4mFD(FragmentFD): url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query)) frag_filename = '%s-%s' % (ctx['tmpfilename'], name) try: - success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()}) + success = ctx['dl'].download(frag_filename, { + 'url': url_parsed.geturl(), + 'http_headers': info_dict.get('http_headers'), + }) if not success: return False (down, frag_sanitized) = sanitize_open(frag_filename, 'rb') diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index 84aacf7..60df627 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -9,6 +9,7 @@ from ..utils import ( error_to_compat_str, encodeFilename, sanitize_open, + sanitized_Request, ) @@ -37,6 +38,10 @@ class FragmentFD(FileDownloader): def report_skip_fragment(self, fragment_name): self.to_screen('[download] Skipping fragment %s...' % fragment_name) + def _prepare_url(self, info_dict, url): + headers = info_dict.get('http_headers') + return sanitized_Request(url, None, headers) if headers else url + def _prepare_and_start_frag_download(self, ctx): self._prepare_frag_download(ctx) self._start_frag_download(ctx) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 541b92e..7373ec0 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -59,7 +59,8 @@ class HlsFD(FragmentFD): def real_download(self, filename, info_dict): man_url = info_dict['url'] self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME) - manifest = self.ydl.urlopen(man_url).read() + + manifest = self.ydl.urlopen(self._prepare_url(info_dict, man_url)).read() s = manifest.decode('utf-8', 'ignore') @@ -112,7 +113,10 @@ class HlsFD(FragmentFD): count = 0 while count <= fragment_retries: try: - success = ctx['dl'].download(frag_filename, {'url': frag_url}) + success = ctx['dl'].download(frag_filename, { + 'url': frag_url, + 'http_headers': info_dict.get('http_headers'), + }) if not success: return False down, frag_sanitized = sanitize_open(frag_filename, 'rb') diff --git a/youtube_dl/downloader/ism.py b/youtube_dl/downloader/ism.py new file mode 100644 index 0000000..93cac5e --- /dev/null +++ b/youtube_dl/downloader/ism.py @@ -0,0 +1,271 @@ +from __future__ import unicode_literals + +import os +import time +import struct +import binascii +import io + +from .fragment import FragmentFD +from ..compat import compat_urllib_error +from ..utils import ( + sanitize_open, + encodeFilename, +) + + +u8 = struct.Struct(b'>B') +u88 = struct.Struct(b'>Bx') +u16 = struct.Struct(b'>H') +u1616 = struct.Struct(b'>Hxx') +u32 = struct.Struct(b'>I') +u64 = struct.Struct(b'>Q') + +s88 = struct.Struct(b'>bx') +s16 = struct.Struct(b'>h') +s1616 = struct.Struct(b'>hxx') +s32 = struct.Struct(b'>i') + +unity_matrix = (s32.pack(0x10000) + s32.pack(0) * 3) * 2 + s32.pack(0x40000000) + +TRACK_ENABLED = 0x1 +TRACK_IN_MOVIE = 0x2 +TRACK_IN_PREVIEW = 0x4 + +SELF_CONTAINED = 0x1 + + +def box(box_type, payload): + return u32.pack(8 + len(payload)) + box_type + payload + + +def full_box(box_type, version, flags, payload): + return box(box_type, u8.pack(version) + u32.pack(flags)[1:] + payload) + + +def write_piff_header(stream, params): + track_id = params['track_id'] + fourcc = params['fourcc'] + duration = params['duration'] + timescale = params.get('timescale', 10000000) + language = params.get('language', 'und') + height = params.get('height', 0) + width = params.get('width', 0) + is_audio = width == 0 and height == 0 + creation_time = modification_time = int(time.time()) + + ftyp_payload = b'isml' # major brand + ftyp_payload += u32.pack(1) # minor version + ftyp_payload += b'piff' + b'iso2' # compatible brands + stream.write(box(b'ftyp', ftyp_payload)) # File Type Box + + mvhd_payload = u64.pack(creation_time) + mvhd_payload += u64.pack(modification_time) + mvhd_payload += u32.pack(timescale) + mvhd_payload += u64.pack(duration) + mvhd_payload += s1616.pack(1) # rate + mvhd_payload += s88.pack(1) # volume + mvhd_payload += u16.pack(0) # reserved + mvhd_payload += u32.pack(0) * 2 # reserved + mvhd_payload += unity_matrix + mvhd_payload += u32.pack(0) * 6 # pre defined + mvhd_payload += u32.pack(0xffffffff) # next track id + moov_payload = full_box(b'mvhd', 1, 0, mvhd_payload) # Movie Header Box + + tkhd_payload = u64.pack(creation_time) + tkhd_payload += u64.pack(modification_time) + tkhd_payload += u32.pack(track_id) # track id + tkhd_payload += u32.pack(0) # reserved + tkhd_payload += u64.pack(duration) + tkhd_payload += u32.pack(0) * 2 # reserved + tkhd_payload += s16.pack(0) # layer + tkhd_payload += s16.pack(0) # alternate group + tkhd_payload += s88.pack(1 if is_audio else 0) # volume + tkhd_payload += u16.pack(0) # reserved + tkhd_payload += unity_matrix + tkhd_payload += u1616.pack(width) + tkhd_payload += u1616.pack(height) + trak_payload = full_box(b'tkhd', 1, TRACK_ENABLED | TRACK_IN_MOVIE | TRACK_IN_PREVIEW, tkhd_payload) # Track Header Box + + mdhd_payload = u64.pack(creation_time) + mdhd_payload += u64.pack(modification_time) + mdhd_payload += u32.pack(timescale) + mdhd_payload += u64.pack(duration) + mdhd_payload += u16.pack(((ord(language[0]) - 0x60) << 10) | ((ord(language[1]) - 0x60) << 5) | (ord(language[2]) - 0x60)) + mdhd_payload += u16.pack(0) # pre defined + mdia_payload = full_box(b'mdhd', 1, 0, mdhd_payload) # Media Header Box + + hdlr_payload = u32.pack(0) # pre defined + hdlr_payload += b'soun' if is_audio else b'vide' # handler type + hdlr_payload += u32.pack(0) * 3 # reserved + hdlr_payload += (b'Sound' if is_audio else b'Video') + b'Handler\0' # name + mdia_payload += full_box(b'hdlr', 0, 0, hdlr_payload) # Handler Reference Box + + if is_audio: + smhd_payload = s88.pack(0) # balance + smhd_payload = u16.pack(0) # reserved + media_header_box = full_box(b'smhd', 0, 0, smhd_payload) # Sound Media Header + else: + vmhd_payload = u16.pack(0) # graphics mode + vmhd_payload += u16.pack(0) * 3 # opcolor + media_header_box = full_box(b'vmhd', 0, 1, vmhd_payload) # Video Media Header + minf_payload = media_header_box + + dref_payload = u32.pack(1) # entry count + dref_payload += full_box(b'url ', 0, SELF_CONTAINED, b'') # Data Entry URL Box + dinf_payload = full_box(b'dref', 0, 0, dref_payload) # Data Reference Box + minf_payload += box(b'dinf', dinf_payload) # Data Information Box + + stsd_payload = u32.pack(1) # entry count + + sample_entry_payload = u8.pack(0) * 6 # reserved + sample_entry_payload += u16.pack(1) # data reference index + if is_audio: + sample_entry_payload += u32.pack(0) * 2 # reserved + sample_entry_payload += u16.pack(params.get('channels', 2)) + sample_entry_payload += u16.pack(params.get('bits_per_sample', 16)) + sample_entry_payload += u16.pack(0) # pre defined + sample_entry_payload += u16.pack(0) # reserved + sample_entry_payload += u1616.pack(params['sampling_rate']) + + if fourcc == 'AACL': + sample_entry_box = box(b'mp4a', sample_entry_payload) + else: + sample_entry_payload = sample_entry_payload + sample_entry_payload += u16.pack(0) # pre defined + sample_entry_payload += u16.pack(0) # reserved + sample_entry_payload += u32.pack(0) * 3 # pre defined + sample_entry_payload += u16.pack(width) + sample_entry_payload += u16.pack(height) + sample_entry_payload += u1616.pack(0x48) # horiz resolution 72 dpi + sample_entry_payload += u1616.pack(0x48) # vert resolution 72 dpi + sample_entry_payload += u32.pack(0) # reserved + sample_entry_payload += u16.pack(1) # frame count + sample_entry_payload += u8.pack(0) * 32 # compressor name + sample_entry_payload += u16.pack(0x18) # depth + sample_entry_payload += s16.pack(-1) # pre defined + + codec_private_data = binascii.unhexlify(params['codec_private_data']) + if fourcc in ('H264', 'AVC1'): + sps, pps = codec_private_data.split(u32.pack(1))[1:] + avcc_payload = u8.pack(1) # configuration version + avcc_payload += sps[1:4] # avc profile indication + profile compatibility + avc level indication + avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete represenation (1) + reserved (11111) + length size minus one + avcc_payload += u8.pack(1) # reserved (0) + number of sps (0000001) + avcc_payload += u16.pack(len(sps)) + avcc_payload += sps + avcc_payload += u8.pack(1) # number of pps + avcc_payload += u16.pack(len(pps)) + avcc_payload += pps + sample_entry_payload += box(b'avcC', avcc_payload) # AVC Decoder Configuration Record + sample_entry_box = box(b'avc1', sample_entry_payload) # AVC Simple Entry + stsd_payload += sample_entry_box + + stbl_payload = full_box(b'stsd', 0, 0, stsd_payload) # Sample Description Box + + stts_payload = u32.pack(0) # entry count + stbl_payload += full_box(b'stts', 0, 0, stts_payload) # Decoding Time to Sample Box + + stsc_payload = u32.pack(0) # entry count + stbl_payload += full_box(b'stsc', 0, 0, stsc_payload) # Sample To Chunk Box + + stco_payload = u32.pack(0) # entry count + stbl_payload += full_box(b'stco', 0, 0, stco_payload) # Chunk Offset Box + + minf_payload += box(b'stbl', stbl_payload) # Sample Table Box + + mdia_payload += box(b'minf', minf_payload) # Media Information Box + + trak_payload += box(b'mdia', mdia_payload) # Media Box + + moov_payload += box(b'trak', trak_payload) # Track Box + + mehd_payload = u64.pack(duration) + mvex_payload = full_box(b'mehd', 1, 0, mehd_payload) # Movie Extends Header Box + + trex_payload = u32.pack(track_id) # track id + trex_payload += u32.pack(1) # default sample description index + trex_payload += u32.pack(0) # default sample duration + trex_payload += u32.pack(0) # default sample size + trex_payload += u32.pack(0) # default sample flags + mvex_payload += full_box(b'trex', 0, 0, trex_payload) # Track Extends Box + + moov_payload += box(b'mvex', mvex_payload) # Movie Extends Box + stream.write(box(b'moov', moov_payload)) # Movie Box + + +def extract_box_data(data, box_sequence): + data_reader = io.BytesIO(data) + while True: + box_size = u32.unpack(data_reader.read(4))[0] + box_type = data_reader.read(4) + if box_type == box_sequence[0]: + box_data = data_reader.read(box_size - 8) + if len(box_sequence) == 1: + return box_data + return extract_box_data(box_data, box_sequence[1:]) + data_reader.seek(box_size - 8, 1) + + +class IsmFD(FragmentFD): + """ + Download segments in a ISM manifest + """ + + FD_NAME = 'ism' + + def real_download(self, filename, info_dict): + segments = info_dict['fragments'][:1] if self.params.get( + 'test', False) else info_dict['fragments'] + + ctx = { + 'filename': filename, + 'total_frags': len(segments), + } + + self._prepare_and_start_frag_download(ctx) + + segments_filenames = [] + + fragment_retries = self.params.get('fragment_retries', 0) + skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True) + + track_written = False + for i, segment in enumerate(segments): + segment_url = segment['url'] + segment_name = 'Frag%d' % i + target_filename = '%s-%s' % (ctx['tmpfilename'], segment_name) + count = 0 + while count <= fragment_retries: + try: + success = ctx['dl'].download(target_filename, {'url': segment_url}) + if not success: + return False + down, target_sanitized = sanitize_open(target_filename, 'rb') + down_data = down.read() + if not track_written: + tfhd_data = extract_box_data(down_data, [b'moof', b'traf', b'tfhd']) + info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0] + write_piff_header(ctx['dest_stream'], info_dict['_download_params']) + track_written = True + ctx['dest_stream'].write(down_data) + down.close() + segments_filenames.append(target_sanitized) + break + except compat_urllib_error.HTTPError as err: + count += 1 + if count <= fragment_retries: + self.report_retry_fragment(err, segment_name, count, fragment_retries) + if count > fragment_retries: + if skip_unavailable_fragments: + self.report_skip_fragment(segment_name) + continue + self.report_error('giving up after %s fragment retries' % fragment_retries) + return False + + self._finish_frag_download(ctx) + + for segment_file in segments_filenames: + os.remove(encodeFilename(segment_file)) + + return True diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 5d0bf5a..989505c 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -96,6 +96,27 @@ class AdultSwimIE(TurnerBaseIE): 'skip_download': True, }, 'expected_warnings': ['Unable to download f4m manifest'], + }, { + 'url': 'http://www.adultswim.com/videos/toonami/friday-october-14th-2016/', + 'info_dict': { + 'id': 'eYiLsKVgQ6qTC6agD67Sig', + 'title': 'Toonami - Friday, October 14th, 2016', + 'description': 'md5:99892c96ffc85e159a428de85c30acde', + }, + 'playlist': [{ + 'md5': '', + 'info_dict': { + 'id': 'eYiLsKVgQ6qTC6agD67Sig', + 'ext': 'mp4', + 'title': 'Toonami - Friday, October 14th, 2016', + 'description': 'md5:99892c96ffc85e159a428de85c30acde', + }, + }], + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'expected_warnings': ['Unable to download f4m manifest'], }] @staticmethod @@ -163,6 +184,8 @@ class AdultSwimIE(TurnerBaseIE): segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']] elif video_info.get('videoPlaybackID'): segment_ids = [video_info['videoPlaybackID']] + elif video_info.get('id'): + segment_ids = [video_info['id']] else: if video_info.get('auth') is True: raise ExtractorError( diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 6adb6d8..c5e079a 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -26,7 +26,7 @@ class AENetworksIE(AENetworksBaseIE): _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)' _TESTS = [{ 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', - 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7', + 'md5': 'a97a65f7e823ae10e9244bc5433d5fe6', 'info_dict': { 'id': '22253814', 'ext': 'mp4', @@ -99,7 +99,7 @@ class AENetworksIE(AENetworksBaseIE): query = { 'mbr': 'true', - 'assetTypes': 'medium_video_s3' + 'assetTypes': 'high_video_s3' } video_id = self._html_search_meta('aetn:VideoID', webpage) media_url = self._search_regex( @@ -155,7 +155,7 @@ class HistoryTopicIE(AENetworksBaseIE): 'id': 'world-war-i-history', 'title': 'World War I History', }, - 'playlist_mincount': 24, + 'playlist_mincount': 23, }, { 'url': 'http://www.history.com/topics/world-war-i-history/videos', 'only_matching': True, @@ -193,7 +193,8 @@ class HistoryTopicIE(AENetworksBaseIE): return self.theplatform_url_result( release_url, video_id, { 'mbr': 'true', - 'switch': 'hls' + 'switch': 'hls', + 'assetTypes': 'high_video_ak', }) else: webpage = self._download_webpage(url, topic_id) @@ -203,6 +204,7 @@ class HistoryTopicIE(AENetworksBaseIE): entries.append(self.theplatform_url_result( video_attributes['data-release-url'], video_attributes['data-id'], { 'mbr': 'true', - 'switch': 'hls' + 'switch': 'hls', + 'assetTypes': 'high_video_ak', })) return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage)) diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py index 518c61f..75b3669 100644 --- a/youtube_dl/extractor/afreecatv.py +++ b/youtube_dl/extractor/afreecatv.py @@ -11,6 +11,7 @@ from ..compat import ( from ..utils import ( ExtractorError, int_or_none, + update_url_query, xpath_element, xpath_text, ) @@ -18,12 +19,18 @@ from ..utils import ( class AfreecaTVIE(InfoExtractor): IE_DESC = 'afreecatv.com' - _VALID_URL = r'''(?x)^ - https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)? - (?: - /app/(?:index|read_ucc_bbs)\.cgi| - /player/[Pp]layer\.(?:swf|html)) - \?.*?\bnTitleNo=(?P<id>\d+)''' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)? + (?: + /app/(?:index|read_ucc_bbs)\.cgi| + /player/[Pp]layer\.(?:swf|html) + )\?.*?\bnTitleNo=| + vod\.afreecatv\.com/PLAYER/STATION/ + ) + (?P<id>\d+) + ''' _TESTS = [{ 'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=', 'md5': 'f72c89fe7ecc14c1b5ce506c4996046e', @@ -66,6 +73,9 @@ class AfreecaTVIE(InfoExtractor): }, { 'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652', 'only_matching': True, + }, { + 'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030', + 'only_matching': True, }] @staticmethod @@ -83,7 +93,9 @@ class AfreecaTVIE(InfoExtractor): info_url = compat_urlparse.urlunparse(parsed_url._replace( netloc='afbbs.afreecatv.com:8080', path='/api/video/get_video_info.php')) - video_xml = self._download_xml(info_url, video_id) + + video_xml = self._download_xml( + update_url_query(info_url, {'nTitleNo': video_id}), video_id) if xpath_element(video_xml, './track/video/file') is None: raise ExtractorError('Specified AfreecaTV video does not exist', diff --git a/youtube_dl/extractor/amcnetworks.py b/youtube_dl/extractor/amcnetworks.py index d2b03b1..87c803e 100644 --- a/youtube_dl/extractor/amcnetworks.py +++ b/youtube_dl/extractor/amcnetworks.py @@ -10,7 +10,7 @@ from ..utils import ( class AMCNetworksIE(ThePlatformIE): - _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?[^/]+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)' _TESTS = [{ 'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1', 'md5': '', @@ -41,6 +41,9 @@ class AMCNetworksIE(ThePlatformIE): }, { 'url': 'http://www.ifc.com/movies/chaos', 'only_matching': True, + }, { + 'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/anvato.py b/youtube_dl/extractor/anvato.py index cb29cf1..623f44d 100644 --- a/youtube_dl/extractor/anvato.py +++ b/youtube_dl/extractor/anvato.py @@ -157,22 +157,16 @@ class AnvatoIE(InfoExtractor): video_data_url, video_id, transform_source=strip_jsonp, data=json.dumps(payload).encode('utf-8')) - def _extract_anvato_videos(self, webpage, video_id): - anvplayer_data = self._parse_json(self._html_search_regex( - r'<script[^>]+data-anvp=\'([^\']+)\'', webpage, - 'Anvato player data'), video_id) - - video_id = anvplayer_data['video'] - access_key = anvplayer_data['accessKey'] - + def _get_anvato_videos(self, access_key, video_id): video_data = self._get_video_json(access_key, video_id) formats = [] for published_url in video_data['published_urls']: video_url = published_url['embed_url'] + media_format = published_url.get('format') ext = determine_ext(video_url) - if ext == 'smil': + if ext == 'smil' or media_format == 'smil': formats.extend(self._extract_smil_formats(video_url, video_id)) continue @@ -183,7 +177,7 @@ class AnvatoIE(InfoExtractor): 'tbr': tbr if tbr != 0 else None, } - if ext == 'm3u8': + if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'): # Not using _extract_m3u8_formats here as individual media # playlists are also included in published_urls. if tbr is None: @@ -194,7 +188,7 @@ class AnvatoIE(InfoExtractor): 'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])), 'ext': 'mp4', }) - elif ext == 'mp3': + elif ext == 'mp3' or media_format == 'mp3': a_format['vcodec'] = 'none' else: a_format.update({ @@ -218,7 +212,19 @@ class AnvatoIE(InfoExtractor): 'formats': formats, 'title': video_data.get('def_title'), 'description': video_data.get('def_description'), + 'tags': video_data.get('def_tags', '').split(','), 'categories': video_data.get('categories'), 'thumbnail': video_data.get('thumbnail'), + 'timestamp': int_or_none(video_data.get( + 'ts_published') or video_data.get('ts_added')), + 'uploader': video_data.get('mcp_id'), + 'duration': int_or_none(video_data.get('duration')), 'subtitles': subtitles, } + + def _extract_anvato_videos(self, webpage, video_id): + anvplayer_data = self._parse_json(self._html_search_regex( + r'<script[^>]+data-anvp=\'([^\']+)\'', webpage, + 'Anvato player data'), video_id) + return self._get_anvato_videos( + anvplayer_data['accessKey'], anvplayer_data['video']) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 3a806a6..35f3656 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -174,11 +174,15 @@ class ARDMediathekIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: - raise ExtractorError('Video %s is no longer available' % video_id, expected=True) + ERRORS = ( + ('>Leider liegt eine Störung vor.', 'Video %s is unavailable'), + ('>Der gewünschte Beitrag ist nicht mehr verfügbar.<', + 'Video %s is no longer available'), + ) - if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage: - raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True) + for pattern, message in ERRORS: + if pattern in webpage: + raise ExtractorError(message % video_id, expected=True) if re.search(r'[\?&]rss($|[=&])', url): doc = compat_etree_fromstring(webpage.encode('utf-8')) diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py index 2ec2d70..d7d1c63 100644 --- a/youtube_dl/extractor/audioboom.py +++ b/youtube_dl/extractor/audioboom.py @@ -6,8 +6,8 @@ from ..utils import float_or_none class AudioBoomIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', 'info_dict': { @@ -19,7 +19,10 @@ class AudioBoomIE(InfoExtractor): 'uploader': 'Steve Czaban', 'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', } - } + }, { + 'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py index 72e1bd5..1eebf5d 100644 --- a/youtube_dl/extractor/azubu.py +++ b/youtube_dl/extractor/azubu.py @@ -11,7 +11,7 @@ from ..utils import ( class AzubuIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/[^/]+#!/play/(?P<id>\d+)' _TESTS = [ { 'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1', @@ -103,12 +103,15 @@ class AzubuIE(InfoExtractor): class AzubuLiveIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$' + _VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/(?P<id>[^/]+)$' - _TEST = { + _TESTS = [{ 'url': 'http://www.azubu.tv/MarsTVMDLen', 'only_matching': True, - } + }, { + 'url': 'http://azubu.uol.com.br/adolfz', + 'only_matching': True, + }] def _real_extract(self, url): user = self._match_id(url) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index 249c3d9..88c590e 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -1,7 +1,9 @@ from __future__ import unicode_literals import json +import random import re +import time from .common import InfoExtractor from ..compat import ( @@ -12,6 +14,9 @@ from ..utils import ( ExtractorError, float_or_none, int_or_none, + parse_filesize, + unescapeHTML, + update_url_query, ) @@ -81,35 +86,68 @@ class BandcampIE(InfoExtractor): r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$', webpage, 'video id') - download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page') - # We get the dictionary of the track from some javascript code - all_info = self._parse_json(self._search_regex( - r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id) - info = all_info[0] - # We pick mp3-320 for now, until format selection can be easily implemented. - mp3_info = info['downloads']['mp3-320'] - # If we try to use this url it says the link has expired - initial_url = mp3_info['url'] - m_url = re.match( - r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$', - initial_url) - # We build the url we will use to get the final track url - # This url is build in Bandcamp in the script download_bunde_*.js - request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts')) - final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') - # If we could correctly generate the .rand field the url would be - # in the "download_url" key - final_url = self._proto_relative_url(self._search_regex( - r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:') + download_webpage = self._download_webpage( + download_link, video_id, 'Downloading free downloads page') + + blob = self._parse_json( + self._search_regex( + r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage, + 'blob', group='blob'), + video_id, transform_source=unescapeHTML) + + info = blob['digital_items'][0] + + downloads = info['downloads'] + track = info['title'] + + artist = info.get('artist') + title = '%s - %s' % (artist, track) if artist else track + + download_formats = {} + for f in blob['download_formats']: + name, ext = f.get('name'), f.get('file_extension') + if all(isinstance(x, compat_str) for x in (name, ext)): + download_formats[name] = ext.strip('.') + + formats = [] + for format_id, f in downloads.items(): + format_url = f.get('url') + if not format_url: + continue + # Stat URL generation algorithm is reverse engineered from + # download_*_bundle_*.js + stat_url = update_url_query( + format_url.replace('/download/', '/statdownload/'), { + '.rand': int(time.time() * 1000 * random.random()), + }) + format_id = f.get('encoding_name') or format_id + stat = self._download_json( + stat_url, video_id, 'Downloading %s JSON' % format_id, + transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1], + fatal=False) + if not stat: + continue + retry_url = stat.get('retry_url') + if not isinstance(retry_url, compat_str): + continue + formats.append({ + 'url': self._proto_relative_url(retry_url, 'http:'), + 'ext': download_formats.get(format_id), + 'format_id': format_id, + 'format_note': f.get('description'), + 'filesize': parse_filesize(f.get('size_mb')), + 'vcodec': 'none', + }) + self._sort_formats(formats) return { 'id': video_id, - 'title': info['title'], - 'ext': 'mp3', - 'vcodec': 'none', - 'url': final_url, + 'title': title, 'thumbnail': info.get('thumb_url'), 'uploader': info.get('artist'), + 'artist': artist, + 'track': track, + 'formats': formats, } diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index 956c768..b0b7914 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -46,19 +46,19 @@ class BeegIE(InfoExtractor): self._proto_relative_url(cpl_url), video_id, 'Downloading cpl JS', fatal=False) if cpl: - beeg_version = self._search_regex( - r'beeg_version\s*=\s*(\d+)', cpl, - 'beeg version', default=None) or self._search_regex( + beeg_version = int_or_none(self._search_regex( + r'beeg_version\s*=\s*([^\b]+)', cpl, + 'beeg version', default=None)) or self._search_regex( r'/(\d+)\.js', cpl_url, 'beeg version', default=None) beeg_salt = self._search_regex( - r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg beeg_salt', + r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt', default=None, group='beeg_salt') - beeg_version = beeg_version or '1750' - beeg_salt = beeg_salt or 'MIDtGaw96f0N1kMMAM1DE46EC9pmFr' + beeg_version = beeg_version or '2000' + beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H' video = self._download_json( - 'http://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id), + 'https://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id), video_id) def split(o, e): diff --git a/youtube_dl/extractor/cbslocal.py b/youtube_dl/extractor/cbslocal.py index 4bcd104..8d5f11d 100644 --- a/youtube_dl/extractor/cbslocal.py +++ b/youtube_dl/extractor/cbslocal.py @@ -4,11 +4,14 @@ from __future__ import unicode_literals from .anvato import AnvatoIE from .sendtonews import SendtoNewsIE from ..compat import compat_urlparse -from ..utils import unified_timestamp +from ..utils import ( + parse_iso8601, + unified_timestamp, +) class CBSLocalIE(AnvatoIE): - _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)' + _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/(?:\d+/\d+/\d+|video)/(?P<id>[0-9a-z-]+)' _TESTS = [{ # Anvato backend @@ -22,6 +25,7 @@ class CBSLocalIE(AnvatoIE): 'thumbnail': 're:^https?://.*', 'timestamp': 1463440500, 'upload_date': '20160516', + 'uploader': 'CBS', 'subtitles': { 'en': 'mincount:5', }, @@ -35,6 +39,7 @@ class CBSLocalIE(AnvatoIE): 'Syndication\\Curb.tv', 'Content\\News' ], + 'tags': ['CBS 2 News Evening'], }, }, { # SendtoNews embed @@ -47,6 +52,31 @@ class CBSLocalIE(AnvatoIE): # m3u8 download 'skip_download': True, }, + }, { + 'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/', + 'info_dict': { + 'id': '3580809', + 'ext': 'mp4', + 'title': 'A Very Blue Anniversary', + 'description': 'CBS2’s Cindy Hsu has more.', + 'thumbnail': 're:^https?://.*', + 'timestamp': 1479962220, + 'upload_date': '20161124', + 'uploader': 'CBS', + 'subtitles': { + 'en': 'mincount:5', + }, + 'categories': [ + 'Stations\\Spoken Word\\WCBSTV', + 'Syndication\\AOL', + 'Syndication\\MSN', + 'Syndication\\NDN', + 'Syndication\\Yahoo', + 'Content\\News', + 'Content\\News\\Local News', + ], + 'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'], + }, }] def _real_extract(self, url): @@ -62,8 +92,11 @@ class CBSLocalIE(AnvatoIE): info_dict = self._extract_anvato_videos(webpage, display_id) time_str = self._html_search_regex( - r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False) - timestamp = unified_timestamp(time_str) + r'class="entry-date">([^<]+)<', webpage, 'released date', default=None) + if time_str: + timestamp = unified_timestamp(time_str) + else: + timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage)) info_dict.update({ 'display_id': display_id, diff --git a/youtube_dl/extractor/cda.py b/youtube_dl/extractor/cda.py index 8af3187..e00bdaf 100755 --- a/youtube_dl/extractor/cda.py +++ b/youtube_dl/extractor/cda.py @@ -5,14 +5,16 @@ import re from .common import InfoExtractor from ..utils import ( - decode_packed_codes, ExtractorError, - parse_duration + float_or_none, + int_or_none, + parse_duration, ) class CDAIE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)' + _BASE_URL = 'http://www.cda.pl/' _TESTS = [{ 'url': 'http://www.cda.pl/video/5749950c', 'md5': '6f844bf51b15f31fae165365707ae970', @@ -21,6 +23,9 @@ class CDAIE(InfoExtractor): 'ext': 'mp4', 'height': 720, 'title': 'Oto dlaczego przed zakrętem należy zwolnić.', + 'description': 'md5:269ccd135d550da90d1662651fcb9772', + 'thumbnail': 're:^https?://.*\.jpg$', + 'average_rating': float, 'duration': 39 } }, { @@ -30,6 +35,11 @@ class CDAIE(InfoExtractor): 'id': '57413289', 'ext': 'mp4', 'title': 'Lądowanie na lotnisku na Maderze', + 'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'crash404', + 'view_count': int, + 'average_rating': float, 'duration': 137 } }, { @@ -39,31 +49,55 @@ class CDAIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id) + self._set_cookie('cda.pl', 'cda.player', 'html5') + webpage = self._download_webpage( + self._BASE_URL + '/video/' + video_id, video_id) if 'Ten film jest dostępny dla użytkowników premium' in webpage: raise ExtractorError('This video is only available for premium users.', expected=True) - title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title') - formats = [] + uploader = self._search_regex(r'''(?x) + <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*> + (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*? + <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3> + ''', webpage, 'uploader', default=None, group='uploader') + view_count = self._search_regex( + r'Odsłony:(?:\s| )*([0-9]+)', webpage, + 'view_count', default=None) + average_rating = self._search_regex( + r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)', + webpage, 'rating', fatal=False, group='rating_value') + info_dict = { 'id': video_id, - 'title': title, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'uploader': uploader, + 'view_count': int_or_none(view_count), + 'average_rating': float_or_none(average_rating), + 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, 'duration': None, } def extract_format(page, version): - unpacked = decode_packed_codes(page) - format_url = self._search_regex( - r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked, - '%s url' % version, fatal=False, group='url') - if not format_url: + json_str = self._search_regex( + r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page, + '%s player_json' % version, fatal=False, group='player_data') + if not json_str: + return + player_data = self._parse_json( + json_str, '%s player_data' % version, fatal=False) + if not player_data: + return + video = player_data.get('video') + if not video or 'file' not in video: + self.report_warning('Unable to extract %s version information' % version) return f = { - 'url': format_url, + 'url': video['file'], } m = re.search( r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p', @@ -75,9 +109,7 @@ class CDAIE(InfoExtractor): }) info_dict['formats'].append(f) if not info_dict['duration']: - info_dict['duration'] = parse_duration(self._search_regex( - r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1", - unpacked, 'duration', fatal=False, group='duration')) + info_dict['duration'] = parse_duration(video.get('duration')) extract_format(webpage, 'default') @@ -85,7 +117,8 @@ class CDAIE(InfoExtractor): r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)', webpage): webpage = self._download_webpage( - href, video_id, 'Downloading %s version information' % resolution, fatal=False) + self._BASE_URL + href, video_id, + 'Downloading %s version information' % resolution, fatal=False) if not webpage: # Manually report warning because empty page is returned when # invalid version is requested. diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 88346dd..0239dfd 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class ComedyCentralIE(MTVServicesInfoExtractor): _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ - (video-clips|episodes|cc-studios|video-collections|full-episodes|shows) + (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes))) /(?P<title>.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' @@ -27,6 +27,40 @@ class ComedyCentralIE(MTVServicesInfoExtractor): }] +class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ + (?:full-episodes|shows(?=/[^/]+/full-episodes)) + /(?P<id>[^?]+)''' + _FEED_URL = 'http://comedycentral.com/feeds/mrss/' + + _TESTS = [{ + 'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028', + 'info_dict': { + 'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."', + 'title': 'November 28, 2016 - Ryan Speedo Green', + }, + 'playlist_count': 4, + }, { + 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed') + feed = self._parse_json(feed_json, playlist_id) + zones = feed['manifest']['zones'] + + video_zone = zones['t2_lc_promo1'] + feed = self._download_json(video_zone['feed'], playlist_id) + mgid = feed['result']['data']['id'] + + videos_info = self._get_videos_info(mgid) + return videos_info + + class ToshIE(MTVServicesInfoExtractor): IE_DESC = 'Tosh.0' _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)' diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 415dc84..05c51fa 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -30,6 +30,7 @@ from ..downloader.f4m import remove_encrypted_media from ..utils import ( NO_DEFAULT, age_restricted, + base_url, bug_reports_message, clean_html, compiled_regex_type, @@ -885,7 +886,7 @@ class InfoExtractor(object): 'url': e.get('contentUrl'), 'title': unescapeHTML(e.get('name')), 'description': unescapeHTML(e.get('description')), - 'thumbnail': e.get('thumbnailUrl'), + 'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'), 'duration': parse_duration(e.get('duration')), 'timestamp': unified_timestamp(e.get('uploadDate')), 'filesize': float_or_none(e.get('contentSize')), @@ -1279,9 +1280,10 @@ class InfoExtractor(object): } resolution = last_info.get('RESOLUTION') if resolution: - width_str, height_str = resolution.split('x') - f['width'] = int(width_str) - f['height'] = int(height_str) + mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution) + if mobj: + f['width'] = int(mobj.group('width')) + f['height'] = int(mobj.group('height')) # Unified Streaming Platform mobj = re.search( r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url']) @@ -1539,7 +1541,7 @@ class InfoExtractor(object): if res is False: return [] mpd, urlh = res - mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group() + mpd_base_url = base_url(urlh.geturl()) return self._parse_mpd_formats( compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, @@ -1701,7 +1703,7 @@ class InfoExtractor(object): representation_ms_info['fragments'] = [{ 'url': media_template % { 'Number': segment_number, - 'Bandwidth': representation_attrib.get('bandwidth'), + 'Bandwidth': int_or_none(representation_attrib.get('bandwidth')), }, 'duration': segment_duration, } for segment_number in range( @@ -1719,7 +1721,7 @@ class InfoExtractor(object): def add_segment_url(): segment_url = media_template % { 'Time': segment_time, - 'Bandwidth': representation_attrib.get('bandwidth'), + 'Bandwidth': int_or_none(representation_attrib.get('bandwidth')), 'Number': segment_number, } representation_ms_info['fragments'].append({ @@ -1780,6 +1782,105 @@ class InfoExtractor(object): self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) return formats + def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True): + res = self._download_webpage_handle( + ism_url, video_id, + note=note or 'Downloading ISM manifest', + errnote=errnote or 'Failed to download ISM manifest', + fatal=fatal) + if res is False: + return [] + ism, urlh = res + + return self._parse_ism_formats( + compat_etree_fromstring(ism.encode('utf-8')), urlh.geturl(), ism_id) + + def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None): + if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None: + return [] + + duration = int(ism_doc.attrib['Duration']) + timescale = int_or_none(ism_doc.get('TimeScale')) or 10000000 + + formats = [] + for stream in ism_doc.findall('StreamIndex'): + stream_type = stream.get('Type') + if stream_type not in ('video', 'audio'): + continue + url_pattern = stream.attrib['Url'] + stream_timescale = int_or_none(stream.get('TimeScale')) or timescale + stream_name = stream.get('Name') + for track in stream.findall('QualityLevel'): + fourcc = track.get('FourCC') + # TODO: add support for WVC1 and WMAP + if fourcc not in ('H264', 'AVC1', 'AACL'): + self.report_warning('%s is not a supported codec' % fourcc) + continue + tbr = int(track.attrib['Bitrate']) // 1000 + width = int_or_none(track.get('MaxWidth')) + height = int_or_none(track.get('MaxHeight')) + sampling_rate = int_or_none(track.get('SamplingRate')) + + track_url_pattern = re.sub(r'{[Bb]itrate}', track.attrib['Bitrate'], url_pattern) + track_url_pattern = compat_urlparse.urljoin(ism_url, track_url_pattern) + + fragments = [] + fragment_ctx = { + 'time': 0, + } + stream_fragments = stream.findall('c') + for stream_fragment_index, stream_fragment in enumerate(stream_fragments): + fragment_ctx['time'] = int_or_none(stream_fragment.get('t')) or fragment_ctx['time'] + fragment_repeat = int_or_none(stream_fragment.get('r')) or 1 + fragment_ctx['duration'] = int_or_none(stream_fragment.get('d')) + if not fragment_ctx['duration']: + try: + next_fragment_time = int(stream_fragment[stream_fragment_index + 1].attrib['t']) + except IndexError: + next_fragment_time = duration + fragment_ctx['duration'] = (next_fragment_time - fragment_ctx['time']) / fragment_repeat + for _ in range(fragment_repeat): + fragments.append({ + 'url': re.sub(r'{start[ _]time}', compat_str(fragment_ctx['time']), track_url_pattern), + 'duration': fragment_ctx['duration'] / stream_timescale, + }) + fragment_ctx['time'] += fragment_ctx['duration'] + + format_id = [] + if ism_id: + format_id.append(ism_id) + if stream_name: + format_id.append(stream_name) + format_id.append(compat_str(tbr)) + + formats.append({ + 'format_id': '-'.join(format_id), + 'url': ism_url, + 'manifest_url': ism_url, + 'ext': 'ismv' if stream_type == 'video' else 'isma', + 'width': width, + 'height': height, + 'tbr': tbr, + 'asr': sampling_rate, + 'vcodec': 'none' if stream_type == 'audio' else fourcc, + 'acodec': 'none' if stream_type == 'video' else fourcc, + 'protocol': 'ism', + 'fragments': fragments, + '_download_params': { + 'duration': duration, + 'timescale': stream_timescale, + 'width': width or 0, + 'height': height or 0, + 'fourcc': fourcc, + 'codec_private_data': track.get('CodecPrivateData'), + 'sampling_rate': sampling_rate, + 'channels': int_or_none(track.get('Channels', 2)), + 'bits_per_sample': int_or_none(track.get('BitsPerSample', 16)), + 'nal_unit_length_field': int_or_none(track.get('NALUnitLengthField', 4)), + }, + }) + return formats + def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'): def absolute_url(video_url): return compat_urlparse.urljoin(base_url, video_url) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index cc141f6..8d5b69f 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -236,7 +236,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style'] output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x'] output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y'] - output += """ScaledBorderAndShadow: yes + output += """ScaledBorderAndShadow: no [V4+ Styles] Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding diff --git a/youtube_dl/extractor/dotsub.py b/youtube_dl/extractor/dotsub.py index fd64d1a..1f75352 100644 --- a/youtube_dl/extractor/dotsub.py +++ b/youtube_dl/extractor/dotsub.py @@ -9,7 +9,7 @@ from ..utils import ( class DotsubIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)' - _TEST = { + _TESTS = [{ 'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09', 'md5': '21c7ff600f545358134fea762a6d42b6', 'info_dict': { @@ -24,7 +24,24 @@ class DotsubIE(InfoExtractor): 'upload_date': '20131130', 'view_count': int, } - } + }, { + 'url': 'https://dotsub.com/view/747bcf58-bd59-45b7-8c8c-ac312d084ee6', + 'md5': '2bb4a83896434d5c26be868c609429a3', + 'info_dict': { + 'id': '168006778', + 'ext': 'mp4', + 'title': 'Apartments and flats in Raipur the white symphony', + 'description': 'md5:784d0639e6b7d1bc29530878508e38fe', + 'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p', + 'duration': 290, + 'timestamp': 1476767794.2809999, + 'upload_date': '20160525', + 'uploader': 'parthivi001', + 'uploader_id': 'user52596202', + 'view_count': int, + }, + 'add_ie': ['Vimeo'], + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -37,12 +54,23 @@ class DotsubIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'], - webpage, 'video url') + webpage, 'video url', default=None) + info_dict = { + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + } - return { - 'id': video_id, - 'url': video_url, - 'ext': 'flv', + if not video_url: + setup_data = self._parse_json(self._html_search_regex( + r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1', + webpage, 'setup data', group='content'), video_id) + info_dict = { + '_type': 'url_transparent', + 'url': setup_data['src'], + } + + info_dict.update({ 'title': info['title'], 'description': info.get('description'), 'thumbnail': info.get('screenshotURI'), @@ -50,4 +78,6 @@ class DotsubIE(InfoExtractor): 'uploader': info.get('user'), 'timestamp': float_or_none(info.get('dateCreated'), 1000), 'view_count': int_or_none(info.get('numberOfViews')), - } + }) + + return info_dict diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index e8870c4..22da8e4 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -10,8 +10,8 @@ from ..utils import ( class DrTuberIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?' + _TESTS = [{ 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', 'md5': '93e680cf2536ad0dfb7e74d94a89facd', 'info_dict': { @@ -25,20 +25,30 @@ class DrTuberIE(InfoExtractor): 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } - } + }, { + 'url': 'http://www.drtuber.com/embed/489939', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)', + webpage) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id - webpage = self._download_webpage(url, display_id) + webpage = self._download_webpage( + 'http://www.drtuber.com/video/%s' % video_id, display_id) video_url = self._html_search_regex( r'<source src="([^"]+)"', webpage, 'video URL') title = self._html_search_regex( - (r'class="title_watch"[^>]*><p>([^<]+)<', + (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<', r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'), webpage, 'title') diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py index d4dfda8..c2f593e 100644 --- a/youtube_dl/extractor/eagleplatform.py +++ b/youtube_dl/extractor/eagleplatform.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..compat import ( + compat_HTTPError, + compat_str, +) from ..utils import ( ExtractorError, int_or_none, - url_basename, ) @@ -77,7 +79,7 @@ class EaglePlatformIE(InfoExtractor): if status != 200: raise ExtractorError(' '.join(response['errors']), expected=True) - def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'): + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs): try: response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note) except ExtractorError as ee: @@ -116,29 +118,38 @@ class EaglePlatformIE(InfoExtractor): m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON') m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, - 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False) formats.extend(m3u8_formats) - mp4_url = self._get_video_url( + m3u8_formats_dict = {} + for f in m3u8_formats: + if f.get('height') is not None: + m3u8_formats_dict[f['height']] = f + + mp4_data = self._download_json( # Secure mp4 URL is constructed according to Player.prototype.mp4 from # http://lentaru.media.eagleplatform.com/player/player.js - re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8), - video_id, 'Downloading mp4 JSON') - mp4_url_basename = url_basename(mp4_url) - for m3u8_format in m3u8_formats: - mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url']) - if mobj: - http_format = m3u8_format.copy() - video_url = mp4_url.replace(mp4_url_basename, mobj.group(1)) - if not self._is_valid_url(video_url, video_id): + re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8), + video_id, 'Downloading mp4 JSON', fatal=False) + if mp4_data: + for format_id, format_url in mp4_data.get('data', {}).items(): + if not isinstance(format_url, compat_str): continue - http_format.update({ - 'url': video_url, - 'format_id': m3u8_format['format_id'].replace('hls', 'http'), - 'protocol': 'http', - }) - formats.append(http_format) + height = int_or_none(format_id) + if height is not None and m3u8_formats_dict.get(height): + f = m3u8_formats_dict[height].copy() + f.update({ + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + }) + else: + f = { + 'format_id': 'http-%s' % format_id, + 'height': int_or_none(format_id), + } + f['url'] = format_url + formats.append(f) self._sort_formats(formats) diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 6d10f8e..8795e0d 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -1,38 +1,117 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import remove_end +from ..compat import compat_str +from ..utils import ( + determine_ext, + int_or_none, + unified_timestamp, +) class ESPNIE(InfoExtractor): - _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)' + _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/video/clip(?:\?.*?\bid=|/_/id/)(?P<id>\d+)' _TESTS = [{ 'url': 'http://espn.go.com/video/clip?id=10365079', - 'md5': '60e5d097a523e767d06479335d1bdc58', 'info_dict': { - 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', + 'id': '10365079', 'ext': 'mp4', 'title': '30 for 30 Shorts: Judging Jewell', - 'description': None, + 'description': 'md5:39370c2e016cb4ecf498ffe75bef7f0f', + 'timestamp': 1390936111, + 'upload_date': '20140128', }, 'params': { 'skip_download': True, }, - 'add_ie': ['OoyalaExternal'], }, { # intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season 'url': 'http://espn.go.com/video/clip?id=2743663', - 'md5': 'f4ac89b59afc7e2d7dbb049523df6768', 'info_dict': { - 'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg', + 'id': '2743663', 'ext': 'mp4', 'title': 'Must-See Moments: Best of the MLS season', + 'description': 'md5:4c2d7232beaea572632bec41004f0aeb', + 'timestamp': 1449446454, + 'upload_date': '20151207', }, 'params': { 'skip_download': True, }, - 'add_ie': ['OoyalaExternal'], + 'expected_warnings': ['Unable to download f4m manifest'], }, { + 'url': 'http://www.espn.com/video/clip?id=10365079', + 'only_matching': True, + }, { + 'url': 'http://www.espn.com/video/clip/_/id/17989860', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + clip = self._download_json( + 'http://api-app.espn.com/v1/video/clips/%s' % video_id, + video_id)['videos'][0] + + title = clip['headline'] + + format_urls = set() + formats = [] + + def traverse_source(source, base_source_id=None): + for source_id, source in source.items(): + if isinstance(source, compat_str): + extract_source(source, base_source_id) + elif isinstance(source, dict): + traverse_source( + source, + '%s-%s' % (base_source_id, source_id) + if base_source_id else source_id) + + def extract_source(source_url, source_id=None): + if source_url in format_urls: + return + format_urls.add(source_url) + ext = determine_ext(source_url) + if ext == 'smil': + formats.extend(self._extract_smil_formats( + source_url, video_id, fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + source_url, video_id, f4m_id=source_id, fatal=False)) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + source_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id=source_id, fatal=False)) + else: + formats.append({ + 'url': source_url, + 'format_id': source_id, + }) + + traverse_source(clip['links']['source']) + self._sort_formats(formats) + + description = clip.get('caption') or clip.get('description') + thumbnail = clip.get('thumbnail') + duration = int_or_none(clip.get('duration')) + timestamp = unified_timestamp(clip.get('originalPublishDate')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } + + +class ESPNArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)' + _TESTS = [{ 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', 'only_matching': True, }, { @@ -47,11 +126,12 @@ class ESPNIE(InfoExtractor): }, { 'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return', 'only_matching': True, - }, { - 'url': 'http://www.espn.com/video/clip?id=10365079', - 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if ESPNIE.suitable(url) else super(ESPNArticleIE, cls).suitable(url) + def _real_extract(self, url): video_id = self._match_id(url) @@ -61,23 +141,5 @@ class ESPNIE(InfoExtractor): r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)', webpage, 'video id', group='id') - cms = 'espn' - if 'data-source="intl"' in webpage: - cms = 'intl' - player_url = 'https://espn.go.com/video/iframe/twitter/?id=%s&cms=%s' % (video_id, cms) - player = self._download_webpage( - player_url, video_id) - - pcode = self._search_regex( - r'["\']pcode=([^"\']+)["\']', player, 'pcode') - - title = remove_end( - self._og_search_title(webpage), - '- ESPN Video').strip() - - return { - '_type': 'url_transparent', - 'url': 'ooyalaexternal:%s:%s:%s' % (cms, video_id, pcode), - 'ie_key': 'OoyalaExternal', - 'title': title, - } + return self.url_result( + 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a693f8c..46d007b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -180,6 +180,7 @@ from .cnn import ( from .coub import CoubIE from .collegerama import CollegeRamaIE from .comedycentral import ( + ComedyCentralFullEpisodesIE, ComedyCentralIE, ComedyCentralShortnameIE, ComedyCentralTVIE, @@ -267,7 +268,10 @@ from .engadget import EngadgetIE from .eporner import EpornerIE from .eroprofile import EroProfileIE from .escapist import EscapistIE -from .espn import ESPNIE +from .espn import ( + ESPNIE, + ESPNArticleIE, +) from .esri import EsriVideoIE from .europa import EuropaIE from .everyonesmixtape import EveryonesMixtapeIE @@ -296,6 +300,7 @@ from .footyroom import FootyRoomIE from .formula1 import Formula1IE from .fourtube import FourTubeIE from .fox import FOXIE +from .fox9 import FOX9IE from .foxgay import FoxgayIE from .foxnews import ( FoxNewsIE, @@ -408,6 +413,10 @@ from .ivi import ( from .ivideon import IvideonIE from .iwara import IwaraIE from .izlesene import IzleseneIE +from .jamendo import ( + JamendoIE, + JamendoAlbumIE, +) from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .jwplatform import JWPlatformIE @@ -592,6 +601,7 @@ from .nhl import ( from .nick import ( NickIE, NickDeIE, + NickNightIE, ) from .niconico import NiconicoIE, NiconicoPlaylistIE from .ninecninemedia import ( @@ -601,6 +611,7 @@ from .ninecninemedia import ( from .ninegag import NineGagIE from .ninenow import NineNowIE from .nintendo import NintendoIE +from .nobelprize import NobelPrizeIE from .noco import NocoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE @@ -667,6 +678,7 @@ from .orf import ( ORFFM4IE, ORFIPTVIE, ) +from .pandatv import PandaTVIE from .pandoratv import PandoraTVIE from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE @@ -740,6 +752,10 @@ from .rbmaradio import RBMARadioIE from .rds import RDSIE from .redtube import RedTubeIE from .regiotv import RegioTVIE +from .rentv import ( + RENTVIE, + RENTVArticleIE, +) from .restudy import RestudyIE from .reuters import ReutersIE from .reverbnation import ReverbNationIE @@ -789,14 +805,16 @@ from .scivee import SciVeeIE from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE from .screenjunkies import ScreenJunkiesIE -from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE from .seeker import SeekerIE from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE from .servingsys import ServingSysIE from .sexu import SexuIE from .shahid import ShahidIE -from .shared import SharedIE +from .shared import ( + SharedIE, + VivoIE, +) from .sharesix import ShareSixIE from .sina import SinaIE from .sixplay import SixPlayIE @@ -879,6 +897,7 @@ from .teachertube import ( ) from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE +from .teamfourstar import TeamFourStarIE from .techtalks import TechTalksIE from .ted import TEDIE from .tele13 import Tele13IE @@ -947,6 +966,10 @@ from .tv2 import ( ) from .tv3 import TV3IE from .tv4 import TV4IE +from .tvanouvelles import ( + TVANouvellesIE, + TVANouvellesArticleIE, +) from .tvc import ( TVCIE, TVCArticleIE, @@ -1087,6 +1110,7 @@ from .vrt import VRTIE from .vube import VubeIE from .vuclip import VuClipIE from .vyborymos import VyboryMosIE +from .vzaar import VzaarIE from .walla import WallaIE from .washingtonpost import ( WashingtonPostIE, @@ -1098,6 +1122,10 @@ from .wdr import ( WDRIE, WDRMobileIE, ) +from .webcaster import ( + WebcasterIE, + WebcasterFeedIE, +) from .webofstories import ( WebOfStoriesIE, WebOfStoriesPlaylistIE, diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 8015734..b4d38e5 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import json import re import socket @@ -100,7 +99,8 @@ class FacebookIE(InfoExtractor): 'ext': 'mp4', 'title': '"What are you doing running in the snow?"', 'uploader': 'FailArmy', - } + }, + 'skip': 'Video gone', }, { 'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903', 'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3', @@ -110,6 +110,7 @@ class FacebookIE(InfoExtractor): 'title': 'What the Flock Is Going On In New Zealand Credit: ViralHog', 'uploader': 'S. Saint', }, + 'skip': 'Video gone', }, { 'note': 'swf params escaped', 'url': 'https://www.facebook.com/barackobama/posts/10153664894881749', @@ -120,6 +121,18 @@ class FacebookIE(InfoExtractor): 'title': 'Facebook video #10153664894881749', }, }, { + # have 1080P, but only up to 720p in swf params + 'url': 'https://www.facebook.com/cnn/videos/10155529876156509/', + 'md5': '0d9813160b146b3bc8744e006027fcc6', + 'info_dict': { + 'id': '10155529876156509', + 'ext': 'mp4', + 'title': 'Holocaust survivor becomes US citizen', + 'timestamp': 1477818095, + 'upload_date': '20161030', + 'uploader': 'CNN', + }, + }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, }, { @@ -227,43 +240,13 @@ class FacebookIE(InfoExtractor): video_data = None - BEFORE = '{swf.addParam(param[0], param[1]);});' - AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' - PATTERN = re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER) - - for m in re.findall(PATTERN, webpage): - swf_params = m.replace('\\\\', '\\').replace('\\"', '"') - data = dict(json.loads(swf_params)) - params_raw = compat_urllib_parse_unquote(data['params']) - video_data_candidate = json.loads(params_raw)['video_data'] - for _, f in video_data_candidate.items(): - if not f: - continue - if isinstance(f, dict): - f = [f] - if not isinstance(f, list): - continue - if f[0].get('video_id') == video_id: - video_data = video_data_candidate - break - if video_data: + server_js_data = self._parse_json(self._search_regex( + r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id) + for item in server_js_data.get('instances', []): + if item[1][0] == 'VideoConfig': + video_data = item[2][0]['videoData'] break - def video_data_list2dict(video_data): - ret = {} - for item in video_data: - format_id = item['stream_type'] - ret.setdefault(format_id, []).append(item) - return ret - - if not video_data: - server_js_data = self._parse_json(self._search_regex( - r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id) - for item in server_js_data.get('instances', []): - if item[1][0] == 'VideoConfig': - video_data = video_data_list2dict(item[2][0]['videoData']) - break - if not video_data: if not fatal_if_no_video: return webpage, False @@ -276,7 +259,8 @@ class FacebookIE(InfoExtractor): raise ExtractorError('Cannot parse data') formats = [] - for format_id, f in video_data.items(): + for f in video_data: + format_id = f['stream_type'] if f and isinstance(f, dict): f = [f] if not f or not isinstance(f, list): diff --git a/youtube_dl/extractor/fox9.py b/youtube_dl/extractor/fox9.py new file mode 100644 index 0000000..56d9975 --- /dev/null +++ b/youtube_dl/extractor/fox9.py @@ -0,0 +1,43 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .anvato import AnvatoIE +from ..utils import js_to_json + + +class FOX9IE(AnvatoIE): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story' + _TESTS = [{ + 'url': 'http://www.fox9.com/news/215123287-story', + 'md5': 'd6e1b2572c3bab8a849c9103615dd243', + 'info_dict': { + 'id': '314473', + 'ext': 'mp4', + 'title': 'Bear climbs tree in downtown Duluth', + 'description': 'md5:6a36bfb5073a411758a752455408ac90', + 'duration': 51, + 'timestamp': 1478123580, + 'upload_date': '20161102', + 'uploader': 'EPFOX', + 'categories': ['News', 'Sports'], + 'tags': ['news', 'video'], + }, + }, { + 'url': 'http://www.fox9.com/news/investigators/214070684-story', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._parse_json( + self._search_regex( + r'AnvatoPlaylist\s*\(\s*(\[.+?\])\s*\)\s*;', + webpage, 'anvato playlist'), + video_id, transform_source=js_to_json)[0]['video'] + + return self._get_anvato_videos( + 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b', + video_id) diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index 186da0d..56048ff 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -29,7 +29,7 @@ class FranceCultureIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_url = self._search_regex( - r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"', + r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<button[^>]+data-asset-source="([^"]+)"', webpage, 'video path') title = self._og_search_title(webpage) @@ -38,7 +38,7 @@ class FranceCultureIE(InfoExtractor): '(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<', webpage, 'upload date', fatal=False)) thumbnail = self._search_regex( - r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"', + r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-dejavu-src="([^"]+)"', webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( r'(?s)<div id="emission".*?<span class="author">(.*?)</span>', diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 8c5ffc9..f2928b5 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -28,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor): 'description': 'Please use this to sell something. www.jonlajoie.com', 'thumbnail': 're:^http:.*\.jpg$', }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man', 'only_matching': True, @@ -51,19 +54,45 @@ class FunnyOrDieIE(InfoExtractor): formats = [] - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + source_formats = list(filter( + lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', + m3u8_formats)) - bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)] + bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)] bitrates.sort() - for bitrate in bitrates: - for link in links: - formats.append({ - 'url': self._proto_relative_url('%s%d.%s' % (link[0], bitrate, link[1])), - 'format_id': '%s-%d' % (link[1], bitrate), - 'vbr': bitrate, - }) + if source_formats: + self._sort_formats(source_formats) + + for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)): + for path, ext in links: + ff = f.copy() + if ff: + if ext != 'mp4': + ff = dict( + [(k, v) for k, v in ff.items() + if k in ('height', 'width', 'format_id')]) + ff.update({ + 'format_id': ff['format_id'].replace('hls', ext), + 'ext': ext, + 'protocol': 'http', + }) + else: + ff.update({ + 'format_id': '%s-%d' % (ext, bitrate), + 'vbr': bitrate, + }) + ff['url'] = self._proto_relative_url( + '%s%d.%s' % (path, bitrate, ext)) + formats.append(ff) + self._check_formats(formats, video_id) + + formats.extend(m3u8_formats) + self._sort_formats( + formats, field_preference=('height', 'width', 'tbr', 'format_id')) subtitles = {} for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage): diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 7b8a9cf..3949c8b 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -47,6 +47,8 @@ from .svt import SVTIE from .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE from .tnaflix import TNAFlixNetworkEmbedIE +from .drtuber import DrTuberIE +from .redtube import RedTubeIE from .vimeo import VimeoIE from .dailymotion import ( DailymotionIE, @@ -54,10 +56,10 @@ from .dailymotion import ( ) from .onionstudios import OnionStudiosIE from .viewlift import ViewLiftEmbedIE -from .screenwavemedia import ScreenwaveMediaIE from .mtv import MTVServicesEmbeddedIE from .pladform import PladformIE from .videomore import VideomoreIE +from .webcaster import WebcasterFeedIE from .googledrive import GoogleDriveIE from .jwplatform import JWPlatformIE from .digiteka import DigitekaIE @@ -1187,16 +1189,6 @@ class GenericIE(InfoExtractor): 'duration': 248.667, }, }, - # ScreenwaveMedia embed - { - 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1', - 'md5': '24ace5baba0d35d55c6810b51f34e9e0', - 'info_dict': { - 'id': 'cinemasnob-55d26273809dd', - 'ext': 'mp4', - 'title': 'cinemasnob', - }, - }, # BrightcoveInPageEmbed embed { 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/', @@ -1208,20 +1200,6 @@ class GenericIE(InfoExtractor): 'duration': 51690, }, }, - # JWPlayer with M3U8 - { - 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video', - 'info_dict': { - 'id': 'playlist', - 'ext': 'mp4', - 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ', - 'uploader': 'ren.tv', - }, - 'params': { - # m3u8 downloads - 'skip_download': True, - } - }, # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions' # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm { @@ -1648,6 +1626,10 @@ class GenericIE(InfoExtractor): doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return self._extract_rss(url, video_id, doc) + elif doc.tag == 'SmoothStreamingMedia': + info_dict['formats'] = self._parse_ism_formats(doc, url) + self._sort_formats(info_dict['formats']) + return info_dict elif re.match(r'^(?:{[^}]+})?smil$', doc.tag): smil = self._parse_smil(doc, url, video_id) self._sort_formats(smil['formats']) @@ -1991,11 +1973,6 @@ class GenericIE(InfoExtractor): if sportbox_urls: return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed') - # Look for embedded PornHub player - pornhub_url = PornHubIE._extract_url(webpage) - if pornhub_url: - return self.url_result(pornhub_url, 'PornHub') - # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) if xhamster_urls: @@ -2006,6 +1983,21 @@ class GenericIE(InfoExtractor): if tnaflix_urls: return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key()) + # Look for embedded PornHub player + pornhub_urls = PornHubIE._extract_urls(webpage) + if pornhub_urls: + return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key()) + + # Look for embedded DrTuber player + drtuber_urls = DrTuberIE._extract_urls(webpage) + if drtuber_urls: + return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key()) + + # Look for embedded RedTube player + redtube_urls = RedTubeIE._extract_urls(webpage) + if redtube_urls: + return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) @@ -2138,6 +2130,11 @@ class GenericIE(InfoExtractor): if videomore_url: return self.url_result(videomore_url) + # Look for Webcaster embeds + webcaster_url = WebcasterFeedIE._extract_url(self, webpage) + if webcaster_url: + return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key()) + # Look for Playwire embeds mobj = re.search( r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage) @@ -2204,11 +2201,6 @@ class GenericIE(InfoExtractor): if jwplatform_url: return self.url_result(jwplatform_url, 'JWPlatform') - # Look for ScreenwaveMedia embeds - mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage) - if mobj is not None: - return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia') - # Look for Digiteka embeds digiteka_url = DigitekaIE._extract_url(webpage) if digiteka_url: @@ -2230,6 +2222,16 @@ class GenericIE(InfoExtractor): return self.url_result('limelight:%s:%s' % ( lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) + mobj = re.search( + r'''(?sx) + <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*? + <param[^>]+ + name=(["\'])flashVars\2[^>]+ + value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32}) + ''', webpage) + if mobj: + return self.url_result('limelight:media:%s' % mobj.group('id')) + # Look for AdobeTVVideo embeds mobj = re.search( r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', @@ -2463,6 +2465,21 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) elif ext == 'f4m': entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) + elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url: + # Just matching .ism/manifest is not enough to be reliably sure + # whether it's actually an ISM manifest or some other streaming + # manifest since there are various streaming URL formats + # possible (see [1]) as well as some other shenanigans like + # .smil/manifest URLs that actually serve an ISM (see [2]) and + # so on. + # Thus the most reasonable way to solve this is to delegate + # to generic extractor in order to look into the contents of + # the manifest itself. + # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats + # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest + entry_info_dict = self.url_result( + smuggle_url(video_url, {'to_generic': True}), + GenericIE.ie_key()) else: entry_info_dict['url'] = video_url diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index 498304c..5279fa8 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -4,9 +4,6 @@ import itertools import re from .common import SearchInfoExtractor -from ..compat import ( - compat_urllib_parse, -) class GoogleSearchIE(SearchInfoExtractor): @@ -34,13 +31,16 @@ class GoogleSearchIE(SearchInfoExtractor): } for pagenum in itertools.count(): - result_url = ( - 'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' - % (compat_urllib_parse.quote_plus(query), pagenum * 10)) - webpage = self._download_webpage( - result_url, 'gvsearch:' + query, - note='Downloading result page ' + str(pagenum + 1)) + 'http://www.google.com/search', + 'gvsearch:' + query, + note='Downloading result page %s' % (pagenum + 1), + query={ + 'tbm': 'vid', + 'q': query, + 'start': pagenum * 10, + 'hl': 'en', + }) for hit_idx, mobj in enumerate(re.finditer( r'<h3 class="r"><a href="([^"]+)"', webpage)): diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 7a1c75b..10da140 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -6,12 +6,13 @@ from .common import InfoExtractor from ..utils import ( js_to_json, remove_end, + determine_ext, ) class HellPornoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)' + _TESTS = [{ 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', 'md5': '1fee339c610d2049699ef2aa699439f1', 'info_dict': { @@ -22,7 +23,10 @@ class HellPornoIE(InfoExtractor): 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } - } + }, { + 'url': 'http://hellporno.net/v/186271/', + 'only_matching': True, + }] def _real_extract(self, url): display_id = self._match_id(url) @@ -38,7 +42,7 @@ class HellPornoIE(InfoExtractor): video_id = flashvars.get('video_id') thumbnail = flashvars.get('preview_url') - ext = flashvars.get('postfix', '.mp4')[1:] + ext = determine_ext(flashvars.get('postfix'), 'mp4') formats = [] for video_url_key in ['video_url', 'video_alt_url']: diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py index 5b6efb2..0615f06 100644 --- a/youtube_dl/extractor/hornbunny.py +++ b/youtube_dl/extractor/hornbunny.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( int_or_none, @@ -14,29 +12,24 @@ class HornBunnyIE(InfoExtractor): _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html' _TEST = { 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html', - 'md5': '95e40865aedd08eff60272b704852ad7', + 'md5': 'e20fd862d1894b67564c96f180f43924', 'info_dict': { 'id': '5227', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'panty slut jerk off instruction', 'duration': 550, 'age_limit': 18, + 'view_count': int, + 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage( - url, video_id, note='Downloading initial webpage') - title = self._html_search_regex( - r'class="title">(.*?)</h2>', webpage, 'title') - redirect_url = self._html_search_regex( - r'pg&settings=(.*?)\|0"\);', webpage, 'title') - webpage2 = self._download_webpage(redirect_url, video_id) - video_url = self._html_search_regex( - r'flvMask:(.*?);', webpage2, 'video_url') + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0] duration = parse_duration(self._search_regex( r'<strong>Runtime:</strong>\s*([0-9:]+)</div>', @@ -45,12 +38,12 @@ class HornBunnyIE(InfoExtractor): r'<strong>Views:</strong>\s*(\d+)</div>', webpage, 'view count', fatal=False)) - return { + info_dict.update({ 'id': video_id, - 'url': video_url, 'title': title, - 'ext': 'flv', 'duration': duration, 'view_count': view_count, 'age_limit': 18, - } + }) + + return info_dict diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index d23489d..67c24a5 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -13,7 +13,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -43,6 +43,9 @@ class ImgurIE(InfoExtractor): }, { 'url': 'http://imgur.com/topic/Funny/N8rOudd', 'only_matching': True, + }, { + 'url': 'http://imgur.com/r/aww/VQcQPhM', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py new file mode 100644 index 0000000..ee9acac --- /dev/null +++ b/youtube_dl/extractor/jamendo.py @@ -0,0 +1,107 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from ..compat import compat_urlparse +from .common import InfoExtractor + + +class JamendoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)' + _TEST = { + 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i', + 'md5': '6e9e82ed6db98678f171c25a8ed09ffd', + 'info_dict': { + 'id': '196219', + 'display_id': 'stories-from-emona-i', + 'ext': 'flac', + 'title': 'Stories from Emona I', + 'thumbnail': 're:^https?://.*\.jpg' + } + } + + def _real_extract(self, url): + mobj = self._VALID_URL_RE.match(url) + track_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_meta('name', webpage, 'title') + + formats = [{ + 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294' + % (sub_domain, track_id, format_id), + 'format_id': format_id, + 'ext': ext, + 'quality': quality, + } for quality, (format_id, sub_domain, ext) in enumerate(( + ('mp31', 'mp3l', 'mp3'), + ('mp32', 'mp3d', 'mp3'), + ('ogg1', 'ogg', 'ogg'), + ('flac', 'flac', 'flac'), + ))] + self._sort_formats(formats) + + thumbnail = self._html_search_meta( + 'image', webpage, 'thumbnail', fatal=False) + + return { + 'id': track_id, + 'display_id': display_id, + 'thumbnail': thumbnail, + 'title': title, + 'formats': formats + } + + +class JamendoAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)' + _TEST = { + 'url': 'https://www.jamendo.com/album/121486/duck-on-cover', + 'info_dict': { + 'id': '121486', + 'title': 'Duck On Cover' + }, + 'playlist': [{ + 'md5': 'e1a2fcb42bda30dfac990212924149a8', + 'info_dict': { + 'id': '1032333', + 'ext': 'flac', + 'title': 'Warmachine' + } + }, { + 'md5': '1f358d7b2f98edfe90fd55dac0799d50', + 'info_dict': { + 'id': '1032330', + 'ext': 'flac', + 'title': 'Without Your Ghost' + } + }], + 'params': { + 'playlistend': 2 + } + } + + def _real_extract(self, url): + mobj = self._VALID_URL_RE.match(url) + album_id = mobj.group('id') + + webpage = self._download_webpage(url, mobj.group('display_id')) + + title = self._html_search_meta('name', webpage, 'title') + + entries = [ + self.url_result( + compat_urlparse.urljoin(url, m.group('path')), + ie=JamendoIE.ie_key(), + video_id=self._search_regex( + r'/track/(\d+)', m.group('path'), + 'track id', default=None)) + for m in re.finditer( + r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link', + webpage) + ] + + return self.playlist_result(entries, album_id, title) diff --git a/youtube_dl/extractor/litv.py b/youtube_dl/extractor/litv.py index a3784e6..ded717c 100644 --- a/youtube_dl/extractor/litv.py +++ b/youtube_dl/extractor/litv.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import json -import re from .common import InfoExtractor from ..utils import ( @@ -52,8 +51,8 @@ class LiTVIE(InfoExtractor): 'skip': 'Georestricted to Taiwan', }] - def _extract_playlist(self, season_list, video_id, vod_data, view_data, prompt=True): - episode_title = view_data['title'] + def _extract_playlist(self, season_list, video_id, program_info, prompt=True): + episode_title = program_info['title'] content_id = season_list['contentId'] if prompt: @@ -61,7 +60,7 @@ class LiTVIE(InfoExtractor): all_episodes = [ self.url_result(smuggle_url( - self._URL_TEMPLATE % (view_data['contentType'], episode['contentId']), + self._URL_TEMPLATE % (program_info['contentType'], episode['contentId']), {'force_noplaylist': True})) # To prevent infinite recursion for episode in season_list['episode']] @@ -80,19 +79,15 @@ class LiTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - view_data = dict(map(lambda t: (t[0], t[2]), re.findall( - r'viewData\.([a-zA-Z]+)\s*=\s*(["\'])([^"\']+)\2', - webpage))) - - vod_data = self._parse_json(self._search_regex( - 'var\s+vod\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'), + program_info = self._parse_json(self._search_regex( + 'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'), video_id) - season_list = list(vod_data.get('seasonList', {}).values()) + season_list = list(program_info.get('seasonList', {}).values()) if season_list: if not noplaylist: return self._extract_playlist( - season_list[0], video_id, vod_data, view_data, + season_list[0], video_id, program_info, prompt=noplaylist_prompt) if noplaylist_prompt: @@ -102,8 +97,8 @@ class LiTVIE(InfoExtractor): # endpoint gives the same result as the data embedded in the webpage. # If georestricted, there are no embedded data, so an extra request is # necessary to get the error code - if 'assetId' not in view_data: - view_data = self._download_json( + if 'assetId' not in program_info: + program_info = self._download_json( 'https://www.litv.tv/vod/ajax/getProgramInfo', video_id, query={'contentId': video_id}, headers={'Accept': 'application/json'}) @@ -112,9 +107,9 @@ class LiTVIE(InfoExtractor): webpage, 'video data', default='{}'), video_id) if not video_data: payload = { - 'assetId': view_data['assetId'], - 'watchDevices': view_data['watchDevices'], - 'contentType': view_data['contentType'], + 'assetId': program_info['assetId'], + 'watchDevices': program_info['watchDevices'], + 'contentType': program_info['contentType'], } video_data = self._download_json( 'https://www.litv.tv/vod/getMainUrl', video_id, @@ -136,11 +131,11 @@ class LiTVIE(InfoExtractor): # LiTV HLS segments doesn't like compressions a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = True - title = view_data['title'] + view_data.get('secondaryMark', '') - description = view_data.get('description') - thumbnail = view_data.get('imageFile') - categories = [item['name'] for item in vod_data.get('category', [])] - episode = int_or_none(view_data.get('episode')) + title = program_info['title'] + program_info.get('secondaryMark', '') + description = program_info.get('description') + thumbnail = program_info.get('imageFile') + categories = [item['name'] for item in program_info.get('category', [])] + episode = int_or_none(program_info.get('episode')) return { 'id': video_id, diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index ea0565a..b84e4dd 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -54,6 +54,22 @@ class LiveLeakIE(InfoExtractor): 'title': 'Crazy Hungarian tourist films close call waterspout in Croatia', 'thumbnail': 're:^https?://.*\.jpg$' } + }, { + # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521 + 'url': 'http://m.liveleak.com/view?i=763_1473349649', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': '763_1473349649', + 'ext': 'mp4', + 'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty', + 'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.', + 'uploader': 'Ziz', + 'upload_date': '20160908', + 'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw' + }, + 'params': { + 'skip_download': True, + }, }] @staticmethod @@ -87,7 +103,7 @@ class LiveLeakIE(InfoExtractor): else: # Maybe an embed? embed_url = self._search_regex( - r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"', + r'<iframe[^>]+src="(https?://(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"', webpage, 'embed URL') return { '_type': 'url_transparent', @@ -107,6 +123,7 @@ class LiveLeakIE(InfoExtractor): 'format_note': s.get('label'), 'url': s['file'], } for i, s in enumerate(sources)] + for i, s in enumerate(sources): # Removing '.h264_*.mp4' gives the raw video, which is essentially # the same video without the LiveLeak logo at the top (see diff --git a/youtube_dl/extractor/microsoftvirtualacademy.py b/youtube_dl/extractor/microsoftvirtualacademy.py index afd3e98..8e0aee0 100644 --- a/youtube_dl/extractor/microsoftvirtualacademy.py +++ b/youtube_dl/extractor/microsoftvirtualacademy.py @@ -71,12 +71,15 @@ class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE): formats = [] for sources in settings.findall(compat_xpath('.//MediaSources')): - if sources.get('videoType') == 'smoothstreaming': - continue + sources_type = sources.get('videoType') for source in sources.findall(compat_xpath('./MediaSource')): video_url = source.text if not video_url or not video_url.startswith('http'): continue + if sources_type == 'smoothstreaming': + formats.extend(self._extract_ism_formats( + video_url, video_id, 'mss', fatal=False)) + continue video_mode = source.get('videoMode') height = int_or_none(self._search_regex( r'^(\d+)[pP]$', video_mode or '', 'height', default=None)) diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 2294745..f577836 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,19 +1,20 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import uuid from .common import InfoExtractor from ..compat import ( + compat_str, compat_urllib_parse_urlencode, compat_urlparse, ) from ..utils import ( - get_element_by_attribute, int_or_none, - remove_start, extract_attributes, determine_ext, + smuggle_url, + parse_duration, ) @@ -72,76 +73,133 @@ class MiTeleBaseIE(InfoExtractor): } -class MiTeleIE(MiTeleBaseIE): +class MiTeleIE(InfoExtractor): IE_DESC = 'mitele.es' - _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/' + _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player' _TESTS = [{ - 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', - # MD5 is unstable + 'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player', 'info_dict': { - 'id': '0NF1jJnxS1Wu3pHrmvFyw2', - 'display_id': 'programa-144', + 'id': '57b0dfb9c715da65618b4afa', 'ext': 'mp4', 'title': 'Tor, la web invisible', 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', 'series': 'Diario de', 'season': 'La redacción', + 'season_number': 14, + 'season_id': 'diario_de_t14_11981', 'episode': 'Programa 144', + 'episode_number': 3, 'thumbnail': 're:(?i)^https?://.*\.jpg$', 'duration': 2913, }, + 'add_ie': ['Ooyala'], }, { # no explicit title - 'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/', + 'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player', 'info_dict': { - 'id': 'eLZSwoEd1S3pVyUm8lc6F', - 'display_id': 'programa-226', + 'id': '57b0de3dc915da14058b4876', 'ext': 'mp4', - 'title': 'Cuarto Milenio - Temporada 6 - Programa 226', - 'description': 'md5:50daf9fadefa4e62d9fc866d0c015701', + 'title': 'Cuarto Milenio Temporada 6 Programa 226', + 'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f', 'series': 'Cuarto Milenio', 'season': 'Temporada 6', + 'season_number': 6, + 'season_id': 'cuarto_milenio_t06_12715', 'episode': 'Programa 226', + 'episode_number': 24, 'thumbnail': 're:(?i)^https?://.*\.jpg$', - 'duration': 7312, + 'duration': 7313, }, 'params': { 'skip_download': True, }, + 'add_ie': ['Ooyala'], + }, { + 'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player', + 'only_matching': True, }] def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - info = self._get_player_info(url, webpage) - - title = self._search_regex( - r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', - webpage, 'title', default=None) - - mobj = re.search(r'''(?sx) - class="Destacado-text"[^>]*>.*?<h1>\s* - <span>(?P<series>[^<]+)</span>\s* - <span>(?P<season>[^<]+)</span>\s* - <span>(?P<episode>[^<]+)</span>''', webpage) - series, season, episode = mobj.groups() if mobj else [None] * 3 + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + gigya_url = self._search_regex( + r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>', + webpage, 'gigya', default=None) + gigya_sc = self._download_webpage( + compat_urlparse.urljoin('http://www.mitele.es/', gigya_url), + video_id, 'Downloading gigya script') + + # Get a appKey/uuid for getting the session key + appKey_var = self._search_regex( + r'value\s*\(\s*["\']appGridApplicationKey["\']\s*,\s*([0-9a-f]+)', + gigya_sc, 'appKey variable') + appKey = self._search_regex( + r'var\s+%s\s*=\s*["\']([0-9a-f]+)' % appKey_var, gigya_sc, 'appKey') + + session_json = self._download_json( + 'https://appgrid-api.cloud.accedo.tv/session', + video_id, 'Downloading session keys', query={ + 'appKey': appKey, + 'uuid': compat_str(uuid.uuid4()), + }) + + paths = self._download_json( + 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration', + video_id, 'Downloading paths JSON', + query={'sessionKey': compat_str(session_json['sessionKey'])}) + + ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search'] + source = self._download_json( + 'http://%s%s%s/docs/%s' % ( + ooyala_s['base_url'], ooyala_s['full_path'], + ooyala_s['provider_id'], video_id), + video_id, 'Downloading data JSON', query={ + 'include_titles': 'Series,Season', + 'product_name': 'test', + 'format': 'full', + })['hits']['hits'][0]['_source'] + + embedCode = source['offers'][0]['embed_codes'][0] + titles = source['localizable_titles'][0] + + title = titles.get('title_medium') or titles['title_long'] + + description = titles.get('summary_long') or titles.get('summary_medium') + + def get(key1, key2): + value1 = source.get(key1) + if not value1 or not isinstance(value1, list): + return + if not isinstance(value1[0], dict): + return + return value1[0].get(key2) + + series = get('localizable_titles_series', 'title_medium') + + season = get('localizable_titles_season', 'title_medium') + season_number = int_or_none(source.get('season_number')) + season_id = source.get('season_id') + + episode = titles.get('title_sort_name') + episode_number = int_or_none(source.get('episode_number')) + + duration = parse_duration(get('videos', 'duration')) - if not title: - if mobj: - title = '%s - %s - %s' % (series, season, episode) - else: - title = remove_start(self._search_regex( - r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ') - - info.update({ - 'display_id': display_id, + return { + '_type': 'url_transparent', + # for some reason only HLS is supported + 'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}), + 'id': video_id, 'title': title, - 'description': get_element_by_attribute('class', 'text', webpage), + 'description': description, 'series': series, 'season': season, + 'season_number': season_number, + 'season_id': season_id, 'episode': episode, - }) - return info + 'episode_number': episode_number, + 'duration': duration, + 'thumbnail': get('images', 'url'), + } diff --git a/youtube_dl/extractor/movieclips.py b/youtube_dl/extractor/movieclips.py index d0cb827..30c206f 100644 --- a/youtube_dl/extractor/movieclips.py +++ b/youtube_dl/extractor/movieclips.py @@ -11,7 +11,7 @@ from ..utils import ( class MovieClipsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/.+-(?P<id>\d+)(?:\?|$)' + _VALID_URL = r'https?://(?:www\.)?movieclips\.com/videos/.+-(?P<id>\d+)(?:\?|$)' _TEST = { 'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597', 'md5': '42b5a0352d4933a7bd54f2104f481244', diff --git a/youtube_dl/extractor/msn.py b/youtube_dl/extractor/msn.py index 1ec8e0f..d75ce8b 100644 --- a/youtube_dl/extractor/msn.py +++ b/youtube_dl/extractor/msn.py @@ -69,10 +69,9 @@ class MSNIE(InfoExtractor): if not format_url: continue ext = determine_ext(format_url) - # .ism is not yet supported (see - # https://github.com/rg3/youtube-dl/issues/8118) if ext == 'ism': - continue + formats.extend(self._extract_ism_formats( + format_url + '/Manifest', display_id, 'mss', fatal=False)) if 'm3u8' in format_url: # m3u8_native should not be used here until # https://github.com/rg3/youtube-dl/issues/9913 is fixed diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 74a3a03..0335191 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -13,6 +13,7 @@ from ..utils import ( fix_xml_ampersands, float_or_none, HEADRequest, + NO_DEFAULT, RegexNotFoundError, sanitized_Request, strip_or_none, @@ -201,7 +202,7 @@ class MTVServicesInfoExtractor(InfoExtractor): [self._get_video_info(item) for item in idoc.findall('.//item')], playlist_title=title, playlist_description=description) - def _extract_mgid(self, webpage): + def _extract_mgid(self, webpage, default=NO_DEFAULT): try: # the url can be http://media.mtvnservices.com/fb/{mgid}.swf # or http://media.mtvnservices.com/{mgid} @@ -221,7 +222,7 @@ class MTVServicesInfoExtractor(InfoExtractor): sm4_embed = self._html_search_meta( 'sm4:video:embed', webpage, 'sm4 embed', default='') mgid = self._search_regex( - r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid') + r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default) return mgid def _real_extract(self, url): diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index 57cf1ce..7672845 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .mtv import MTVServicesInfoExtractor from ..utils import update_url_query @@ -69,7 +71,7 @@ class NickIE(MTVServicesInfoExtractor): class NickDeIE(MTVServicesInfoExtractor): IE_NAME = 'nick.de' - _VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.nl)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?P<host>nick\.de|nickelodeon\.(?:nl|at))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse', 'only_matching': True, @@ -79,15 +81,43 @@ class NickDeIE(MTVServicesInfoExtractor): }, { 'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit', 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.at/playlist/3773-top-videos/videos/episode/77993-das-letzte-gefecht', + 'only_matching': True, }] + def _extract_mrss_url(self, webpage, host): + return update_url_query(self._search_regex( + r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'), + {'siteKey': host}) + def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') webpage = self._download_webpage(url, video_id) - mrss_url = update_url_query(self._search_regex( - r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'), - {'siteKey': 'nick.de'}) + mrss_url = self._extract_mrss_url(webpage, host) return self._get_videos_info_from_url(mrss_url, video_id) + + +class NickNightIE(NickDeIE): + IE_NAME = 'nicknight' + _VALID_URL = r'https?://(?:www\.)(?P<host>nicknight\.(?:de|at|tv))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.nicknight.at/shows/977-awkward/videos/85987-nimmer-beste-freunde', + 'only_matching': True, + }, { + 'url': 'http://www.nicknight.at/shows/977-awkward', + 'only_matching': True, + }, { + 'url': 'http://www.nicknight.at/shows/1900-faking-it', + 'only_matching': True, + }] + + def _extract_mrss_url(self, webpage, *args): + return self._search_regex( + r'mrss\s*:\s*(["\'])(?P<url>http.+?)\1', webpage, + 'mrss url', group='url') diff --git a/youtube_dl/extractor/nobelprize.py b/youtube_dl/extractor/nobelprize.py new file mode 100644 index 0000000..4dfdb09 --- /dev/null +++ b/youtube_dl/extractor/nobelprize.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + mimetype2ext, + determine_ext, + update_url_query, + get_element_by_attribute, + int_or_none, +) + + +class NobelPrizeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)' + _TEST = { + 'url': 'http://www.nobelprize.org/mediaplayer/?id=2636', + 'md5': '04c81e5714bb36cc4e2232fee1d8157f', + 'info_dict': { + 'id': '2636', + 'ext': 'mp4', + 'title': 'Announcement of the 2016 Nobel Prize in Physics', + 'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + media = self._parse_json(self._search_regex( + r'(?s)var\s*config\s*=\s*({.+?});', webpage, + 'config'), video_id, js_to_json)['media'] + title = media['title'] + + formats = [] + for source in media.get('source', []): + source_src = source.get('src') + if not source_src: + continue + ext = mimetype2ext(source.get('type')) or determine_ext(source_src) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + source_src, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + update_url_query(source_src, {'hdcore': '3.7.0'}), + video_id, f4m_id='hds', fatal=False)) + else: + formats.append({ + 'url': source_src, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': get_element_by_attribute('itemprop', 'description', webpage), + 'duration': int_or_none(media.get('duration')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py index 6aa0895..61fe571 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -2,7 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from .screenwavemedia import ScreenwaveMediaIE +from .jwplatform import JWPlatformIE from ..utils import ( unified_strdate, @@ -25,7 +25,7 @@ class NormalbootsIE(InfoExtractor): # m3u8 download 'skip_download': True, }, - 'add_ie': ['ScreenwaveMedia'], + 'add_ie': ['JWPlatform'], } def _real_extract(self, url): @@ -39,15 +39,13 @@ class NormalbootsIE(InfoExtractor): r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', webpage, 'date', fatal=False)) - screenwavemedia_url = self._html_search_regex( - ScreenwaveMediaIE.EMBED_PATTERN, webpage, 'screenwave URL', - group='url') + jwplatform_url = JWPlatformIE._extract_url(webpage) return { '_type': 'url_transparent', 'id': video_id, - 'url': screenwavemedia_url, - 'ie_key': ScreenwaveMediaIE.ie_key(), + 'url': jwplatform_url, + 'ie_key': JWPlatformIE.ie_key(), 'title': self._og_search_title(webpage), 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 3700b7a..c89aac6 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import random import re from .common import InfoExtractor @@ -14,6 +15,25 @@ from ..utils import ( class NRKBaseIE(InfoExtractor): + _faked_ip = None + + def _download_webpage_handle(self, *args, **kwargs): + # NRK checks X-Forwarded-For HTTP header in order to figure out the + # origin of the client behind proxy. This allows to bypass geo + # restriction by faking this header's value to some Norway IP. + # We will do so once we encounter any geo restriction error. + if self._faked_ip: + # NB: str is intentional + kwargs.setdefault(str('headers'), {})['X-Forwarded-For'] = self._faked_ip + return super(NRKBaseIE, self)._download_webpage_handle(*args, **kwargs) + + def _fake_ip(self): + # Use fake IP from 37.191.128.0/17 in order to workaround geo + # restriction + def octet(lb=0, ub=255): + return random.randint(lb, ub) + self._faked_ip = '37.191.%d.%d' % (octet(128), octet()) + def _real_extract(self, url): video_id = self._match_id(url) @@ -24,6 +44,8 @@ class NRKBaseIE(InfoExtractor): title = data.get('fullTitle') or data.get('mainTitle') or data['title'] video_id = data.get('id') or video_id + http_headers = {'X-Forwarded-For': self._faked_ip} if self._faked_ip else {} + entries = [] media_assets = data.get('mediaAssets') @@ -54,6 +76,7 @@ class NRKBaseIE(InfoExtractor): 'duration': duration, 'subtitles': subtitles, 'formats': formats, + 'http_headers': http_headers, }) if not entries: @@ -70,10 +93,23 @@ class NRKBaseIE(InfoExtractor): }] if not entries: - if data.get('usageRights', {}).get('isGeoBlocked'): - raise ExtractorError( - 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', - expected=True) + message_type = data.get('messageType', '') + # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked* + if 'IsGeoBlocked' in message_type and not self._faked_ip: + self.report_warning( + 'Video is geo restricted, trying to fake IP') + self._fake_ip() + return self._real_extract(url) + + MESSAGES = { + 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', + 'ProgramRightsHasExpired': 'Programmet har gått ut', + 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', + } + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, MESSAGES.get( + message_type, message_type)), + expected=True) conviva = data.get('convivaStatistics') or {} series = conviva.get('seriesName') or data.get('seriesTitle') diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py index 9cbc7c2..0a501b3 100644 --- a/youtube_dl/extractor/onet.py +++ b/youtube_dl/extractor/onet.py @@ -56,8 +56,8 @@ class OnetBaseIE(InfoExtractor): continue ext = determine_ext(video_url) if format_id == 'ism': - # TODO: Support Microsoft Smooth Streaming - continue + formats.extend(self._extract_ism_formats( + video_url, video_id, 'mss', fatal=False)) elif ext == 'mpd': formats.extend(self._extract_mpd_formats( video_url, video_id, mpd_id='dash', fatal=False)) diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 72ec209..c2807d0 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor): _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/' _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?' - def _extract(self, content_tree_url, video_id, domain='example.org'): + def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None): content_tree = self._download_json(content_tree_url, video_id)['content_tree'] metadata = content_tree[list(content_tree)[0]] embed_code = metadata['embed_code'] @@ -29,7 +29,7 @@ class OoyalaBaseIE(InfoExtractor): self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) + compat_urllib_parse_urlencode({ 'domain': domain, - 'supportedFormats': 'mp4,rtmp,m3u8,hds', + 'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds', }), video_id) cur_auth_data = auth_data['authorization_data'][embed_code] @@ -145,8 +145,9 @@ class OoyalaIE(OoyalaBaseIE): url, smuggled_data = unsmuggle_url(url, {}) embed_code = self._match_id(url) domain = smuggled_data.get('domain') + supportedformats = smuggled_data.get('supportedformats') content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code) - return self._extract(content_tree_url, embed_code, domain) + return self._extract(content_tree_url, embed_code, domain, supportedformats) class OoyalaExternalIE(OoyalaBaseIE): diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 6cf7e4a..7f19b1b 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals, division +import re + from .common import InfoExtractor from ..compat import ( compat_chr, @@ -10,6 +12,10 @@ from ..utils import ( determine_ext, ExtractorError, ) +from ..jsinterp import ( + JSInterpreter, + _NAME_RE +) class OpenloadIE(InfoExtractor): @@ -56,6 +62,44 @@ class OpenloadIE(InfoExtractor): 'only_matching': True, }] + def openload_decode(self, txt): + symbol_dict = { + '(ﾟДﾟ) [ﾟΘﾟ]': '_', + '(ﾟДﾟ) [ﾟωﾟﾉ]': 'a', + '(ﾟДﾟ) [ﾟΘﾟﾉ]': 'b', + '(ﾟДﾟ) [\'c\']': 'c', + '(ﾟДﾟ) [ﾟｰﾟﾉ]': 'd', + '(ﾟДﾟ) [ﾟДﾟﾉ]': 'e', + '(ﾟДﾟ) [1]': 'f', + '(ﾟДﾟ) [\'o\']': 'o', + '(oﾟｰﾟo)': 'u', + '(ﾟДﾟ) [\'c\']': 'c', + '((ﾟｰﾟ) + (o^_^o))': '7', + '((o^_^o) +(o^_^o) +(c^_^o))': '6', + '((ﾟｰﾟ) + (ﾟΘﾟ))': '5', + '(-~3)': '4', + '(-~-~1)': '3', + '(-~1)': '2', + '(-~0)': '1', + '((c^_^o)-(c^_^o))': '0', + } + delim = '(ﾟДﾟ)[ﾟεﾟ]+' + end_token = '(ﾟДﾟ)[ﾟoﾟ]' + symbols = '|'.join(map(re.escape, symbol_dict.keys())) + txt = re.sub('(%s)\+\s?' % symbols, lambda m: symbol_dict[m.group(1)], txt) + ret = '' + for aacode in re.findall(r'{0}\+\s?{1}(.*?){0}'.format(re.escape(end_token), re.escape(delim)), txt): + for aachar in aacode.split(delim): + if aachar.isdigit(): + ret += compat_chr(int(aachar, 8)) + else: + m = re.match(r'^u([\da-f]{4})$', aachar) + if m: + ret += compat_chr(int(m.group(1), 16)) + else: + self.report_warning("Cannot decode: %s" % aachar) + return ret + def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id) @@ -70,19 +114,26 @@ class OpenloadIE(InfoExtractor): r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"', webpage, 'encrypted data') - magic = compat_ord(enc_data[-1]) + enc_code = self._html_search_regex(r'<script[^>]+>(ﾟωﾟ[^<]+)</script>', + webpage, 'encrypted code') + + js_code = self.openload_decode(enc_code) + jsi = JSInterpreter(js_code) + + m_offset_fun = self._search_regex(r'slice\(0\s*-\s*(%s)\(\)' % _NAME_RE, js_code, 'javascript offset function') + m_diff_fun = self._search_regex(r'charCodeAt\(0\)\s*\+\s*(%s)\(\)' % _NAME_RE, js_code, 'javascript diff function') + + offset = jsi.call_function(m_offset_fun) + diff = jsi.call_function(m_diff_fun) + video_url_chars = [] for idx, c in enumerate(enc_data): j = compat_ord(c) - if j == magic: - j -= 1 - elif j == magic - 1: - j += 1 if j >= 33 and j <= 126: j = ((j + 14) % 94) + 33 - if idx == len(enc_data) - 1: - j += 2 + if idx == len(enc_data) - offset: + j += diff video_url_chars += compat_chr(j) video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars) diff --git a/youtube_dl/extractor/pandatv.py b/youtube_dl/extractor/pandatv.py new file mode 100644 index 0000000..133cc9b --- /dev/null +++ b/youtube_dl/extractor/pandatv.py @@ -0,0 +1,91 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + qualities, +) + + +class PandaTVIE(InfoExtractor): + IE_DESC = '熊猫TV' + _VALID_URL = r'http://(?:www\.)?panda\.tv/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.panda.tv/10091', + 'info_dict': { + 'id': '10091', + 'title': 're:.+', + 'uploader': '囚徒', + 'ext': 'flv', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Live stream is offline', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + config = self._download_json( + 'http://www.panda.tv/api_room?roomid=%s' % video_id, video_id) + + error_code = config.get('errno', 0) + if error_code is not 0: + raise ExtractorError( + '%s returned error %s: %s' + % (self.IE_NAME, error_code, config['errmsg']), + expected=True) + + data = config['data'] + video_info = data['videoinfo'] + + # 2 = live, 3 = offline + if video_info.get('status') != '2': + raise ExtractorError( + 'Live stream is offline', expected=True) + + title = data['roominfo']['name'] + uploader = data.get('hostinfo', {}).get('name') + room_key = video_info['room_key'] + stream_addr = video_info.get( + 'stream_addr', {'OD': '1', 'HD': '1', 'SD': '1'}) + + # Reverse engineered from web player swf + # (http://s6.pdim.gs/static/07153e425f581151.swf at the moment of + # writing). + plflag0, plflag1 = video_info['plflag'].split('_') + plflag0 = int(plflag0) - 1 + if plflag1 == '21': + plflag0 = 10 + plflag1 = '4' + live_panda = 'live_panda' if plflag0 < 1 else '' + + quality_key = qualities(['OD', 'HD', 'SD']) + suffix = ['_small', '_mid', ''] + formats = [] + for k, v in stream_addr.items(): + if v != '1': + continue + quality = quality_key(k) + if quality <= 0: + continue + for pref, (ext, pl) in enumerate((('m3u8', '-hls'), ('flv', ''))): + formats.append({ + 'url': 'http://pl%s%s.live.panda.tv/live_panda/%s%s%s.%s' + % (pl, plflag1, room_key, live_panda, suffix[quality], ext), + 'format_id': '%s-%s' % (k, ext), + 'quality': quality, + 'source_preference': pref, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._live_title(title), + 'uploader': uploader, + 'formats': formats, + 'is_live': True, + } diff --git a/youtube_dl/extractor/plays.py b/youtube_dl/extractor/plays.py index c3c38cf..ddfc6f1 100644 --- a/youtube_dl/extractor/plays.py +++ b/youtube_dl/extractor/plays.py @@ -8,30 +8,31 @@ from ..utils import int_or_none class PlaysTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})' - _TEST = { - 'url': 'http://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall', + _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P<id>[0-9a-f]{18})' + _TESTS = [{ + 'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall', 'md5': 'dfeac1198506652b5257a62762cec7bc', 'info_dict': { 'id': '56af17f56c95335490', 'ext': 'mp4', - 'title': 'When you outplay the Azir wall', + 'title': 'Bjergsen - When you outplay the Azir wall', 'description': 'Posted by Bjergsen', } - } + }, { + 'url': 'https://plays.tv/embeds/56af17f56c95335490', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'https://plays.tv/video/%s' % video_id, video_id) + + info = self._search_json_ld(webpage, video_id,) - title = self._og_search_title(webpage) - content = self._parse_json( - self._search_regex( - r'R\.bindContent\(({.+?})\);', webpage, - 'content'), video_id)['content'] mpd_url, sources = re.search( r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>', - content).groups() + webpage).groups() formats = self._extract_mpd_formats( self._proto_relative_url(mpd_url), video_id, mpd_id='DASH') for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources): @@ -42,10 +43,11 @@ class PlaysTVIE(InfoExtractor): }) self._sort_formats(formats) - return { + info.update({ 'id': video_id, - 'title': title, 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': info.get('thumbnail') or self._og_search_thumbnail(webpage), 'formats': formats, - } + }) + + return info diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 2683c0a..0ffd41e 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -11,6 +11,7 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( + dict_get, ExtractorError, float_or_none, int_or_none, @@ -119,14 +120,17 @@ class PluralsightIE(PluralsightBaseIE): @staticmethod def _convert_subtitles(duration, subs): srt = '' + TIME_OFFSET_KEYS = ('displayTimeOffset', 'DisplayTimeOffset') + TEXT_KEYS = ('text', 'Text') for num, current in enumerate(subs): current = subs[num] - start, text = float_or_none( - current.get('DisplayTimeOffset')), current.get('Text') + start, text = ( + float_or_none(dict_get(current, TIME_OFFSET_KEYS)), + dict_get(current, TEXT_KEYS)) if start is None or text is None: continue end = duration if num == len(subs) - 1 else float_or_none( - subs[num + 1].get('DisplayTimeOffset')) + dict_get(subs[num + 1], TIME_OFFSET_KEYS)) if end is None: continue srt += os.linesep.join( diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 0724efc..40dbe69 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor): (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) - (?P<id>[0-9a-z]+) + (?P<id>[\da-z]+) ''' _TESTS = [{ 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', @@ -96,12 +96,11 @@ class PornHubIE(InfoExtractor): 'only_matching': True, }] - @classmethod - def _extract_url(cls, webpage): - mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage) - if mobj: - return mobj.group('url') + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)', + webpage) def _extract_count(self, pattern, webpage, name): return str_to_int(self._search_regex( diff --git a/youtube_dl/extractor/puls4.py b/youtube_dl/extractor/puls4.py index 1c54af0..80091b8 100644 --- a/youtube_dl/extractor/puls4.py +++ b/youtube_dl/extractor/puls4.py @@ -10,7 +10,7 @@ from ..utils import ( class Puls4IE(ProSiebenSat1BaseIE): - _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)' + _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)' _TESTS = [{ 'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118', 'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03', @@ -22,6 +22,12 @@ class Puls4IE(ProSiebenSat1BaseIE): 'upload_date': '20160830', 'uploader': 'PULS_4', }, + }, { + 'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer', + 'only_matching': True, + }, { + 'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598', + 'only_matching': True, }] _TOKEN = 'puls4' _SALT = '01!kaNgaiNgah1Ie4AeSha' diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 6751270..321917a 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -125,6 +125,14 @@ class RadioCanadaIE(InfoExtractor): f4m_id='hds', fatal=False)) self._sort_formats(formats) + subtitles = {} + closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5') + if closed_caption_url: + subtitles['fr'] = [{ + 'url': closed_caption_url, + 'ext': determine_ext(closed_caption_url, 'vtt'), + }] + return { 'id': video_id, 'title': get_meta('Title'), @@ -135,6 +143,7 @@ class RadioCanadaIE(InfoExtractor): 'season_number': int_or_none('SrcSaison'), 'episode_number': int_or_none('SrcEpisode'), 'upload_date': unified_strdate(get_meta('Date')), + 'subtitles': subtitles, 'formats': formats, } diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 721fc3a..c367a6a 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( ExtractorError, @@ -10,8 +12,8 @@ from ..utils import ( class RedTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'http://www.redtube.com/66418', 'md5': '7b8c22b5e7098a3e1c09709df1126d2d', 'info_dict': { @@ -23,11 +25,21 @@ class RedTubeIE(InfoExtractor): 'view_count': int, 'age_limit': 18, } - } + }, { + 'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)', + webpage) def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'http://www.redtube.com/%s' % video_id, video_id) if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']): raise ExtractorError('Video %s has been removed' % video_id, expected=True) diff --git a/youtube_dl/extractor/rentv.py b/youtube_dl/extractor/rentv.py new file mode 100644 index 0000000..422c02c --- /dev/null +++ b/youtube_dl/extractor/rentv.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .jwplatform import JWPlatformBaseIE +from ..compat import compat_str + + +class RENTVIE(JWPlatformBaseIE): + _VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://ren.tv/video/epizod/118577', + 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb', + 'info_dict': { + 'id': '118577', + 'ext': 'mp4', + 'title': 'Документальный спецпроект: "Промывка мозгов. Технологии XXI века"' + } + }, { + 'url': 'http://ren.tv/player/118577', + 'only_matching': True, + }, { + 'url': 'rentv:118577', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage('http://ren.tv/player/' + video_id, video_id) + jw_config = self._parse_json(self._search_regex( + r'config\s*=\s*({.+});', webpage, 'jw config'), video_id) + return self._parse_jwplayer_data(jw_config, video_id, m3u8_id='hls') + + +class RENTVArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ren\.tv/novosti/\d{4}-\d{2}-\d{2}/(?P<id>[^/?#]+)' + _TESTS = [{ + 'url': 'http://ren.tv/novosti/2016-10-26/video-mikroavtobus-popavshiy-v-dtp-s-gruzovikami-v-podmoskove-prevratilsya-v', + 'md5': 'ebd63c4680b167693745ab91343df1d6', + 'info_dict': { + 'id': '136472', + 'ext': 'mp4', + 'title': 'Видео: микроавтобус, попавший в ДТП с грузовиками в Подмосковье, превратился в груду металла', + 'description': 'Жертвами столкновения двух фур и микроавтобуса, по последним данным, стали семь человек.', + } + }, { + # TODO: invalid m3u8 + 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video', + 'info_dict': { + 'id': 'playlist', + 'ext': 'mp4', + 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ', + 'uploader': 'ren.tv', + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + }, + 'skip': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + drupal_settings = self._parse_json(self._search_regex( + r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', + webpage, 'drupal settings'), display_id) + + entries = [] + for config_profile in drupal_settings.get('ren_jwplayer', {}).values(): + media_id = config_profile.get('mediaid') + if not media_id: + continue + media_id = compat_str(media_id) + entries.append(self.url_result('rentv:' + media_id, 'RENTV', media_id)) + return self.playlist_result(entries, display_id) diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index 2fce4e8..6db3e3e 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_urlparse from ..utils import ( determine_ext, + ExtractorError, int_or_none, xpath_attr, xpath_text, @@ -101,6 +102,11 @@ class RuutuIE(InfoExtractor): }) extract_formats(video_xml.find('./Clip')) + + drm = xpath_text(video_xml, './Clip/DRM', default=None) + if not formats and drm: + raise ExtractorError('This video is DRM protected.', expected=True) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py deleted file mode 100644 index 7d77e88..0000000 --- a/youtube_dl/extractor/screenwavemedia.py +++ /dev/null @@ -1,146 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - unified_strdate, - js_to_json, -) - - -class ScreenwaveMediaIE(InfoExtractor): - _VALID_URL = r'(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)' - EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1' - _TESTS = [{ - 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - playerdata = self._download_webpage( - 'http://player.screenwavemedia.com/player.php?id=%s' % video_id, - video_id, 'Downloading player webpage') - - vidtitle = self._search_regex( - r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/') - - playerconfig = self._download_webpage( - 'http://player.screenwavemedia.com/player.js', - video_id, 'Downloading playerconfig webpage') - - videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver') - - sources = self._parse_json( - js_to_json( - re.sub( - r'(?s)/\*.*?\*/', '', - self._search_regex( - r'sources\s*:\s*(\[[^\]]+?\])', playerconfig, - 'sources', - ).replace( - "' + thisObj.options.videoserver + '", - videoserver - ).replace( - "' + playerVidId + '", - video_id - ) - ) - ), - video_id, fatal=False - ) - - # Fallback to hardcoded sources if JS changes again - if not sources: - self.report_warning('Falling back to a hardcoded list of streams') - sources = [{ - 'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id), - 'type': 'mp4', - 'label': format_label, - } for format_id, format_label in ( - ('low', '144p Low'), ('med', '160p Med'), ('high', '360p High'), ('hd1', '720p HD1'))] - sources.append({ - 'file': 'http://%s/vod/smil:%s.smil/playlist.m3u8' % (videoserver, video_id), - 'type': 'hls', - }) - - formats = [] - for source in sources: - file_ = source.get('file') - if not file_: - continue - if source.get('type') == 'hls': - formats.extend(self._extract_m3u8_formats(file_, video_id, ext='mp4')) - else: - format_id = self._search_regex( - r'_(.+?)\.[^.]+$', file_, 'format id', default=None) - if not self._is_valid_url(file_, video_id, format_id or 'video'): - continue - format_label = source.get('label') - height = int_or_none(self._search_regex( - r'^(\d+)[pP]', format_label, 'height', default=None)) - formats.append({ - 'url': file_, - 'format_id': format_id, - 'format': format_label, - 'ext': source.get('type'), - 'height': height, - }) - self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id')) - - return { - 'id': video_id, - 'title': vidtitle, - 'formats': formats, - } - - -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', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - - 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\d?\.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/shahid.py b/youtube_dl/extractor/shahid.py index ca286ab..62d41e8 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -1,17 +1,24 @@ # coding: utf-8 from __future__ import unicode_literals +import re +import json + from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, int_or_none, parse_iso8601, str_or_none, + urlencode_postdata, + clean_html, ) class ShahidIE(InfoExtractor): - _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?' + _NETRC_MACHINE = 'shahid' + _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?P<type>episode|movie)/(?P<id>\d+)' _TESTS = [{ 'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html', 'info_dict': { @@ -28,17 +35,53 @@ class ShahidIE(InfoExtractor): 'skip_download': True, } }, { + 'url': 'https://shahid.mbc.net/ar/movie/151746/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9.html', + 'only_matching': True + }, { # shahid plus subscriber only 'url': 'https://shahid.mbc.net/ar/episode/90511/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html', 'only_matching': True }] - def _call_api(self, path, video_id, note): - data = self._download_json( - 'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={ - 'apiKey': 'sh@hid0nlin3', - 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', - }).get('data', {}) + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + return + + try: + user_data = self._download_json( + 'https://shahid.mbc.net/wd/service/users/login', + None, 'Logging in', data=json.dumps({ + 'email': email, + 'password': password, + 'basic': 'false', + }).encode('utf-8'), headers={ + 'Content-Type': 'application/json; charset=UTF-8', + })['user'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + fail_data = self._parse_json( + e.cause.read().decode('utf-8'), None, fatal=False) + if fail_data: + faults = fail_data.get('faults', []) + faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')]) + if faults_message: + raise ExtractorError(faults_message, expected=True) + raise + + self._download_webpage( + 'https://shahid.mbc.net/populateContext', + None, 'Populate Context', data=urlencode_postdata({ + 'firstName': user_data['firstName'], + 'lastName': user_data['lastName'], + 'userName': user_data['email'], + 'csg_user_name': user_data['email'], + 'subscriberId': user_data['id'], + 'sessionId': user_data['sessionId'], + })) + + def _get_api_data(self, response): + data = response.get('data', {}) error = data.get('error') if error: @@ -49,11 +92,11 @@ class ShahidIE(InfoExtractor): return data def _real_extract(self, url): - video_id = self._match_id(url) + page_type, video_id = re.match(self._VALID_URL, url).groups() - player = self._call_api( - 'Content/Episode/%s' % video_id, - video_id, 'Downloading player JSON') + player = self._get_api_data(self._download_json( + 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-player.html' % video_id, + video_id, 'Downloading player JSON')) if player.get('drm'): raise ExtractorError('This video is DRM protected.', expected=True) @@ -61,9 +104,12 @@ class ShahidIE(InfoExtractor): formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4') self._sort_formats(formats) - video = self._call_api( - 'episode/%s' % video_id, video_id, - 'Downloading video JSON')['episode'] + video = self._get_api_data(self._download_json( + 'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id), + video_id, 'Downloading video JSON', query={ + 'apiKey': 'sh@hid0nlin3', + 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', + }))[page_type] title = video['title'] categories = [ diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index d592dfe..89e19e9 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -10,11 +10,38 @@ from ..utils import ( ) -class SharedIE(InfoExtractor): - IE_DESC = 'shared.sx and vivo.sx' - _VALID_URL = r'https?://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})' +class SharedBaseIE(InfoExtractor): + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage, urlh = self._download_webpage_handle(url, video_id) + + if self._FILE_NOT_FOUND in webpage: + raise ExtractorError( + 'Video %s does not exist' % video_id, expected=True) + + video_url = self._extract_video_url(webpage, video_id, url) + + title = base64.b64decode(self._html_search_meta( + 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') + filesize = int_or_none(self._html_search_meta( + 'full:size', webpage, 'file size', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'filesize': filesize, + 'title': title, + } + + +class SharedIE(SharedBaseIE): + IE_DESC = 'shared.sx' + _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})' + _FILE_NOT_FOUND = '>File does not exist<' - _TESTS = [{ + _TEST = { 'url': 'http://shared.sx/0060718775', 'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'info_dict': { @@ -23,52 +50,47 @@ class SharedIE(InfoExtractor): 'title': 'Bmp4', 'filesize': 1720110, }, - }, { - 'url': 'http://vivo.sx/d7ddda0e78', - 'md5': '15b3af41be0b4fe01f4df075c2678b2c', - 'info_dict': { - 'id': 'd7ddda0e78', - 'ext': 'mp4', - 'title': 'Chicken', - 'filesize': 528031, - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage, urlh = self._download_webpage_handle(url, video_id) - - if '>File does not exist<' in webpage: - raise ExtractorError( - 'Video %s does not exist' % video_id, expected=True) + } + def _extract_video_url(self, webpage, video_id, url): download_form = self._hidden_inputs(webpage) video_page = self._download_webpage( - urlh.geturl(), video_id, 'Downloading video page', + url, video_id, 'Downloading video page', data=urlencode_postdata(download_form), headers={ 'Content-Type': 'application/x-www-form-urlencoded', - 'Referer': urlh.geturl(), + 'Referer': url, }) video_url = self._html_search_regex( r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1', video_page, 'video URL', group='url') - title = base64.b64decode(self._html_search_meta( - 'full:title', webpage, 'title').encode('utf-8')).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=(["\'])(?P<url>(?:(?!\1).)+)\1', - video_page, 'thumbnail', default=None, group='url') - return { - 'id': video_id, - 'url': video_url, + return video_url + + +class VivoIE(SharedBaseIE): + IE_DESC = 'vivo.sx' + _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})' + _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed' + + _TEST = { + 'url': 'http://vivo.sx/d7ddda0e78', + 'md5': '15b3af41be0b4fe01f4df075c2678b2c', + 'info_dict': { + 'id': 'd7ddda0e78', 'ext': 'mp4', - 'filesize': filesize, - 'title': title, - 'thumbnail': thumbnail, - } + 'title': 'Chicken', + 'filesize': 528031, + }, + } + + def _extract_video_url(self, webpage, video_id, *args): + return self._parse_json( + self._search_regex( + r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage, 'stream', group='url'), + video_id, + transform_source=lambda x: base64.b64decode( + x.encode('ascii')).decode('utf-8'))[0] diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 3b7ecb3..5a201ea 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -121,7 +121,7 @@ class SoundcloudIE(InfoExtractor): }, ] - _CLIENT_ID = '02gUJC0hH2ct1EGOcYXQIzRFU91c72Ea' + _CLIENT_ID = 'fDoItMDbsbZz8dY16ZzARCZmzgHBPotA' _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf' @staticmethod diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py index 218785e..abfee3e 100644 --- a/youtube_dl/extractor/spike.py +++ b/youtube_dl/extractor/spike.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .mtv import MTVServicesInfoExtractor @@ -17,6 +19,15 @@ class SpikeIE(MTVServicesInfoExtractor): 'upload_date': '20131227', }, }, { + 'url': 'http://www.spike.com/full-episodes/j830qm/lip-sync-battle-joel-mchale-vs-jim-rash-season-2-ep-209', + 'md5': 'b25c6f16418aefb9ad5a6cae2559321f', + 'info_dict': { + 'id': '37ace3a8-1df6-48be-85b8-38df8229e241', + 'ext': 'mp4', + 'title': 'Lip Sync Battle|April 28, 2016|2|209|Joel McHale Vs. Jim Rash|Act 1', + 'description': 'md5:a739ca8f978a7802f67f8016d27ce114', + }, + }, { 'url': 'http://www.spike.com/video-clips/lhtu8m/', 'only_matching': True, }, { @@ -32,3 +43,12 @@ class SpikeIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.spike.com/feeds/mrss/' _MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s' + _CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)') + + def _extract_mgid(self, webpage): + mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None) + if mgid is None: + url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id') + video_type, episode_id = url_parts.split('/', 1) + mgid = 'mgid:arc:{0}:spike.com:{1}'.format(video_type, episode_id) + return mgid diff --git a/youtube_dl/extractor/teamfourstar.py b/youtube_dl/extractor/teamfourstar.py new file mode 100644 index 0000000..a8c6ed7 --- /dev/null +++ b/youtube_dl/extractor/teamfourstar.py @@ -0,0 +1,48 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .jwplatform import JWPlatformIE +from ..utils import unified_strdate + + +class TeamFourStarIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/(?P<id>[a-z0-9\-]+)' + _TEST = { + 'url': 'http://teamfourstar.com/tfs-abridged-parody-episode-1-2/', + 'info_dict': { + 'id': '0WdZO31W', + 'title': 'TFS Abridged Parody Episode 1', + 'description': 'md5:d60bc389588ebab2ee7ad432bda953ae', + 'ext': 'mp4', + 'timestamp': 1394168400, + 'upload_date': '20080508', + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + jwplatform_url = JWPlatformIE._extract_url(webpage) + + video_title = self._html_search_regex( + r'<h1[^>]+class="entry-title"[^>]*>(?P<title>.+?)</h1>', + webpage, 'title') + video_date = unified_strdate(self._html_search_regex( + r'<span[^>]+class="meta-date date updated"[^>]*>(?P<date>.+?)</span>', + webpage, 'date', fatal=False)) + video_description = self._html_search_regex( + r'(?s)<div[^>]+class="content-inner"[^>]*>.*?(?P<description><p>.+?)</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': jwplatform_url, + } diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 7629f0d..197258d 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -5,10 +5,10 @@ from .common import InfoExtractor class ThisOldHouseIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to)/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)' _TESTS = [{ 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', - 'md5': '568acf9ca25a639f0c4ff905826b662f', + 'md5': '946f05bbaa12a33f9ae35580d2dfcfe3', 'info_dict': { 'id': '2REGtUDQ', 'ext': 'mp4', @@ -20,6 +20,9 @@ class ThisOldHouseIE(InfoExtractor): }, { 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/tmz.py b/youtube_dl/extractor/tmz.py index 979856e..419f9d9 100644 --- a/youtube_dl/extractor/tmz.py +++ b/youtube_dl/extractor/tmz.py @@ -32,12 +32,15 @@ class TMZArticleIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?' _TEST = { 'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert', - 'md5': 'e482a414a38db73087450e3a6ce69d00', + 'md5': '3316ff838ae5bb7f642537825e1e90d2', 'info_dict': { 'id': '0_6snoelag', - 'ext': 'mp4', + 'ext': 'mov', 'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake', 'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."', + 'timestamp': 1429467813, + 'upload_date': '20150419', + 'uploader_id': 'batchUser', } } @@ -45,12 +48,9 @@ class TMZArticleIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - embedded_video_info_str = self._html_search_regex( - r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info') - - embedded_video_info = self._parse_json( - embedded_video_info_str, video_id, - transform_source=lambda s: s.replace('\\', '')) + embedded_video_info = self._parse_json(self._html_search_regex( + r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'), + video_id) return self.url_result( 'http://www.tmz.com/videos/%s/' % embedded_video_info['id']) diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index d2d5c11..26d7709 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -15,11 +15,11 @@ from ..utils import ( class TouTvIE(InfoExtractor): _NETRC_MACHINE = 'toutv' IE_NAME = 'tou.tv' - _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+/S[0-9]+E[0-9]+)' + _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+E[0-9]+)?)' _access_token = None _claims = None - _TEST = { + _TESTS = [{ 'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17', 'info_dict': { 'id': '122017', @@ -33,7 +33,10 @@ class TouTvIE(InfoExtractor): 'skip_download': True, }, 'skip': '404 Not Found', - } + }, { + 'url': 'http://ici.tou.tv/hackers', + 'only_matching': True, + }] def _real_initialize(self): email, password = self._get_login_info() @@ -53,7 +56,7 @@ class TouTvIE(InfoExtractor): 'state': state, }) login_form = self._search_regex( - r'(?s)(<form[^>]+id="Form-login".+?</form>)', login_webpage, 'login form') + r'(?s)(<form[^>]+(?:id|name)="Form-login".+?</form>)', login_webpage, 'login form') form_data = self._hidden_inputs(login_form) form_data.update({ 'login-email': email, diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py index c6572de..3a37df2 100644 --- a/youtube_dl/extractor/tubitv.py +++ b/youtube_dl/extractor/tubitv.py @@ -9,7 +9,6 @@ from ..utils import ( int_or_none, sanitized_Request, urlencode_postdata, - parse_iso8601, ) @@ -19,17 +18,13 @@ class TubiTvIE(InfoExtractor): _NETRC_MACHINE = 'tubitv' _TEST = { 'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday', + 'md5': '43ac06be9326f41912dc64ccf7a80320', 'info_dict': { 'id': '283829', 'ext': 'mp4', 'title': 'The Comedian at The Friday', 'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.', - 'uploader': 'Indie Rights Films', - 'upload_date': '20160111', - 'timestamp': 1452555979, - }, - 'params': { - 'skip_download': 'HLS download', + 'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434', }, } @@ -58,19 +53,28 @@ class TubiTvIE(InfoExtractor): video_id = self._match_id(url) video_data = self._download_json( 'http://tubitv.com/oz/videos/%s/content' % video_id, video_id) - title = video_data['n'] + title = video_data['title'] formats = self._extract_m3u8_formats( - video_data['mh'], video_id, 'mp4', 'm3u8_native') + self._proto_relative_url(video_data['url']), + video_id, 'mp4', 'm3u8_native') self._sort_formats(formats) + thumbnails = [] + for thumbnail_url in video_data.get('thumbnails', []): + if not thumbnail_url: + continue + thumbnails.append({ + 'url': self._proto_relative_url(thumbnail_url), + }) + subtitles = {} - for sub in video_data.get('sb', []): - sub_url = sub.get('u') + for sub in video_data.get('subtitles', []): + sub_url = sub.get('url') if not sub_url: continue - subtitles.setdefault(sub.get('l', 'en'), []).append({ - 'url': sub_url, + subtitles.setdefault(sub.get('lang', 'English'), []).append({ + 'url': self._proto_relative_url(sub_url), }) return { @@ -78,9 +82,8 @@ class TubiTvIE(InfoExtractor): 'title': title, 'formats': formats, 'subtitles': subtitles, - 'thumbnail': video_data.get('ph'), - 'description': video_data.get('d'), - 'duration': int_or_none(video_data.get('s')), - 'timestamp': parse_iso8601(video_data.get('u')), - 'uploader': video_data.get('on'), + 'thumbnails': thumbnails, + 'description': video_data.get('description'), + 'duration': int_or_none(video_data.get('duration')), + 'uploader_id': video_data.get('publisher_id'), } diff --git a/youtube_dl/extractor/tvanouvelles.py b/youtube_dl/extractor/tvanouvelles.py new file mode 100644 index 0000000..1086176 --- /dev/null +++ b/youtube_dl/extractor/tvanouvelles.py @@ -0,0 +1,65 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from .brightcove import BrightcoveNewIE + + +class TVANouvellesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tvanouvelles\.ca/videos/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.tvanouvelles.ca/videos/5117035533001', + 'info_dict': { + 'id': '5117035533001', + 'ext': 'mp4', + 'title': 'L’industrie du taxi dénonce l’entente entre Québec et Uber: explications', + 'description': 'md5:479653b7c8cf115747bf5118066bd8b3', + 'uploader_id': '1741764581', + 'timestamp': 1473352030, + 'upload_date': '20160908', + }, + 'add_ie': ['BrightcoveNew'], + } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1741764581/default_default/index.html?videoId=%s' + + def _real_extract(self, url): + brightcove_id = self._match_id(url) + return self.url_result( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + BrightcoveNewIE.ie_key(), brightcove_id) + + +class TVANouvellesArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tvanouvelles\.ca/(?:[^/]+/)+(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'http://www.tvanouvelles.ca/2016/11/17/des-policiers-qui-ont-la-meche-un-peu-courte', + 'info_dict': { + 'id': 'des-policiers-qui-ont-la-meche-un-peu-courte', + 'title': 'Des policiers qui ont «la mèche un peu courte»?', + 'description': 'md5:92d363c8eb0f0f030de9a4a84a90a3a0', + }, + 'playlist_mincount': 4, + } + + @classmethod + def suitable(cls, url): + return False if TVANouvellesIE.suitable(url) else super(TVANouvellesArticleIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [ + self.url_result( + 'http://www.tvanouvelles.ca/videos/%s' % mobj.group('id'), + ie=TVANouvellesIE.ie_key(), video_id=mobj.group('id')) + for mobj in re.finditer( + r'data-video-id=(["\'])?(?P<id>\d+)', webpage)] + + title = self._og_search_title(webpage, fatal=False) + description = self._og_search_description(webpage) + + return self.playlist_result(entries, display_id, title, description) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 2abfb78..06ea2b4 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -69,7 +69,8 @@ class TVPIE(InfoExtractor): webpage = self._download_webpage(url, page_id) video_id = self._search_regex([ r'<iframe[^>]+src="[^"]*?object_id=(\d+)', - "object_id\s*:\s*'(\d+)'"], webpage, 'video id') + r"object_id\s*:\s*'(\d+)'", + r'data-video-id="(\d+)"'], webpage, 'video id', default=page_id) return { '_type': 'url_transparent', 'url': 'tvp:' + video_id, @@ -138,6 +139,9 @@ class TVPEmbedIE(InfoExtractor): # formats.extend(self._extract_mpd_formats( # video_url_base + '.ism/video.mpd', # video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_ism_formats( + video_url_base + '.ism/Manifest', + video_id, 'mss', fatal=False)) formats.extend(self._extract_f4m_formats( video_url_base + '.ism/video.f4m', video_id, f4m_id='hds', fatal=False)) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 46c2cfe..77414a2 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -398,7 +398,7 @@ class TwitchStreamIE(TwitchBaseIE): channel_id = self._match_id(url) stream = self._call_api( - 'kraken/streams/%s' % channel_id, channel_id, + 'kraken/streams/%s?stream_type=all' % channel_id, channel_id, 'Downloading stream JSON').get('stream') if not stream: @@ -417,6 +417,7 @@ class TwitchStreamIE(TwitchBaseIE): query = { 'allow_source': 'true', 'allow_audio_only': 'true', + 'allow_spectre': 'true', 'p': random.randint(1000000, 10000000), 'player': 'twitchweb', 'segment_preference': '4', diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 3411fcf..ac0b221 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -25,7 +25,7 @@ class TwitterBaseIE(InfoExtractor): class TwitterCardIE(TwitterBaseIE): IE_NAME = 'twitter:card' - _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos/tweet)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', @@ -84,6 +84,9 @@ class TwitterCardIE(TwitterBaseIE): 'title': 'Twitter web player', 'thumbnail': 're:^https?://.*\.jpg', }, + }, { + 'url': 'https://twitter.com/i/videos/752274308186120192', + 'only_matching': True, }, ] diff --git a/youtube_dl/extractor/vessel.py b/youtube_dl/extractor/vessel.py index 2cd617b..6b9c227 100644 --- a/youtube_dl/extractor/vessel.py +++ b/youtube_dl/extractor/vessel.py @@ -13,7 +13,7 @@ from ..utils import ( class VesselIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)' + _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)' _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s' _LOGIN_URL = 'https://www.vessel.com/api/account/login' _NETRC_MACHINE = 'vessel' @@ -32,12 +32,18 @@ class VesselIE(InfoExtractor): }, { 'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346', 'only_matching': True, + }, { + 'url': 'https://www.vessel.com/videos/F01_dsLj1', + 'only_matching': True, + }, { + 'url': 'https://www.vessel.com/videos/RRX-sir-J', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return [url for _, url in re.findall( - r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z]+.*?)\1', + r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z-_]+.*?)\1', webpage)] @staticmethod diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index 783efda..d82261e 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -51,7 +51,7 @@ class VevoIE(VevoBaseIE): 'artist': 'Hurts', 'genre': 'Pop', }, - 'expected_warnings': ['Unable to download SMIL file'], + 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'], }, { 'note': 'v3 SMIL format', 'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923', @@ -67,7 +67,7 @@ class VevoIE(VevoBaseIE): 'artist': 'Cassadee Pope', 'genre': 'Country', }, - 'expected_warnings': ['Unable to download SMIL file'], + 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'], }, { 'note': 'Age-limited video', 'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282', @@ -83,7 +83,7 @@ class VevoIE(VevoBaseIE): 'artist': 'Justin Timberlake', 'genre': 'Pop', }, - 'expected_warnings': ['Unable to download SMIL file'], + 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'], }, { 'note': 'No video_info', 'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000', @@ -91,15 +91,33 @@ class VevoIE(VevoBaseIE): 'info_dict': { 'id': 'USUV71503000', 'ext': 'mp4', - 'title': 'K Camp - Till I Die', + 'title': 'K Camp ft. T.I. - Till I Die', 'age_limit': 18, 'timestamp': 1449468000, 'upload_date': '20151207', 'uploader': 'K Camp', 'track': 'Till I Die', 'artist': 'K Camp', - 'genre': 'Rap/Hip-Hop', + 'genre': 'Hip-Hop', }, + 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'], + }, { + 'note': 'Featured test', + 'url': 'https://www.vevo.com/watch/lemaitre/Wait/USUV71402190', + 'md5': 'd28675e5e8805035d949dc5cf161071d', + 'info_dict': { + 'id': 'USUV71402190', + 'ext': 'mp4', + 'title': 'Lemaitre ft. LoLo - Wait', + 'age_limit': 0, + 'timestamp': 1413432000, + 'upload_date': '20141016', + 'uploader': 'Lemaitre', + 'track': 'Wait', + 'artist': 'Lemaitre', + 'genre': 'Electronic', + }, + 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'], }, { 'note': 'Only available via webpage', 'url': 'http://www.vevo.com/watch/GBUV71600656', @@ -242,8 +260,11 @@ class VevoIE(VevoBaseIE): timestamp = parse_iso8601(video_info.get('releaseDate')) artists = video_info.get('artists') - if artists: - artist = uploader = artists[0]['name'] + for curr_artist in artists: + if curr_artist.get('role') == 'Featured': + featured_artist = curr_artist['name'] + else: + artist = uploader = curr_artist['name'] view_count = int_or_none(video_info.get('views', {}).get('total')) for video_version in video_versions: diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index e2b2ce0..8a00c8f 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,12 +1,93 @@ +# coding: utf-8 from __future__ import unicode_literals import re +import time +import hashlib +import json +from .adobepass import AdobePassIE from .common import InfoExtractor -from ..utils import ExtractorError +from ..compat import compat_HTTPError +from ..utils import ( + int_or_none, + parse_age_limit, + str_or_none, + parse_duration, + ExtractorError, + extract_attributes, +) -class ViceIE(InfoExtractor): +class ViceBaseIE(AdobePassIE): + def _extract_preplay_video(self, url, webpage): + watch_hub_data = extract_attributes(self._search_regex( + r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub')) + video_id = watch_hub_data['vms-id'] + title = watch_hub_data['video-title'] + + query = {} + is_locked = watch_hub_data.get('video-locked') == '1' + if is_locked: + resource = self._get_mvpd_resource( + 'VICELAND', title, video_id, + watch_hub_data.get('video-rating')) + query['tvetoken'] = self._extract_mvpd_auth(url, video_id, 'VICELAND', resource) + + # signature generation algorithm is reverse engineered from signatureGenerator in + # webpack:///../shared/~/vice-player/dist/js/vice-player.js in + # https://www.viceland.com/assets/common/js/web.vendor.bundle.js + exp = int(time.time()) + 14400 + query.update({ + 'exp': exp, + 'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(), + }) + + try: + host = 'www.viceland' if is_locked else self._PREPLAY_HOST + preplay = self._download_json('https://%s.com/en_us/preplay/%s' % (host, video_id), video_id, query=query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + error = json.loads(e.cause.read().decode()) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error['details']), expected=True) + raise + + video_data = preplay['video'] + base = video_data['base'] + uplynk_preplay_url = preplay['preplayURL'] + episode = video_data.get('episode', {}) + channel = video_data.get('channel', {}) + + subtitles = {} + cc_url = preplay.get('ccURL') + if cc_url: + subtitles['en'] = [{ + 'url': cc_url, + }] + + return { + '_type': 'url_transparent', + 'url': uplynk_preplay_url, + 'id': video_id, + 'title': title, + 'description': base.get('body'), + 'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'), + 'duration': parse_duration(video_data.get('video_duration') or watch_hub_data.get('video-duration')), + 'timestamp': int_or_none(video_data.get('created_at')), + 'age_limit': parse_age_limit(video_data.get('video_rating')), + 'series': video_data.get('show_title') or watch_hub_data.get('show-title'), + 'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')), + 'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')), + 'season_number': int_or_none(watch_hub_data.get('season')), + 'season_id': str_or_none(episode.get('season_id')), + 'uploader': channel.get('base', {}).get('title') or watch_hub_data.get('channel-title'), + 'uploader_id': str_or_none(channel.get('id')), + 'subtitles': subtitles, + 'ie_key': 'UplynkPreplay', + } + + +class ViceIE(ViceBaseIE): _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)' _TESTS = [{ @@ -21,7 +102,7 @@ class ViceIE(InfoExtractor): 'add_ie': ['Ooyala'], }, { 'url': 'http://www.vice.com/video/how-to-hack-a-car', - 'md5': '6fb2989a3fed069fb8eab3401fc2d3c9', + 'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2', 'info_dict': { 'id': '3jstaBeXgAs', 'ext': 'mp4', @@ -33,6 +114,22 @@ class ViceIE(InfoExtractor): }, 'add_ie': ['Youtube'], }, { + 'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56', + 'md5': '', + 'info_dict': { + 'id': '5816510690b70e6c5fd39a56', + 'ext': 'mp4', + 'uploader': 'Waypoint', + 'title': 'The Signal From Tölva', + 'uploader_id': '57f7d621e05ca860fa9ccaf9', + 'timestamp': 1477941983938, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'add_ie': ['UplynkPreplay'], + }, { 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', 'only_matching': True, }, { @@ -42,21 +139,21 @@ class ViceIE(InfoExtractor): 'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show', 'only_matching': True, }] + _PREPLAY_HOST = 'video.vice' def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - try: - embed_code = self._search_regex( - r'embedCode=([^&\'"]+)', webpage, - 'ooyala embed code', default=None) - if embed_code: - return self.url_result('ooyala:%s' % embed_code, 'Ooyala') - youtube_id = self._search_regex( - r'data-youtube-id="([^"]+)"', webpage, 'youtube id') + webpage, urlh = self._download_webpage_handle(url, video_id) + embed_code = self._search_regex( + r'embedCode=([^&\'"]+)', webpage, + 'ooyala embed code', default=None) + if embed_code: + return self.url_result('ooyala:%s' % embed_code, 'Ooyala') + youtube_id = self._search_regex( + r'data-youtube-id="([^"]+)"', webpage, 'youtube id', default=None) + if youtube_id: return self.url_result(youtube_id, 'Youtube') - except ExtractorError: - raise ExtractorError('The page doesn\'t contain a video', expected=True) + return self._extract_preplay_video(urlh.geturl(), webpage) class ViceShowIE(InfoExtractor): diff --git a/youtube_dl/extractor/viceland.py b/youtube_dl/extractor/viceland.py index 8742b60..0eff055 100644 --- a/youtube_dl/extractor/viceland.py +++ b/youtube_dl/extractor/viceland.py @@ -1,23 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -import time -import hashlib -import json +from .vice import ViceBaseIE -from .adobepass import AdobePassIE -from ..compat import compat_HTTPError -from ..utils import ( - int_or_none, - parse_age_limit, - str_or_none, - parse_duration, - ExtractorError, - extract_attributes, -) - -class VicelandIE(AdobePassIE): +class VicelandIE(ViceBaseIE): _VALID_URL = r'https?://(?:www\.)?viceland\.com/[^/]+/video/[^/]+/(?P<id>[a-f0-9]+)' _TEST = { 'url': 'https://www.viceland.com/en_us/video/cyberwar-trailer/57608447973ee7705f6fbd4e', @@ -38,70 +25,9 @@ class VicelandIE(AdobePassIE): }, 'add_ie': ['UplynkPreplay'], } + _PREPLAY_HOST = 'www.viceland' def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - watch_hub_data = extract_attributes(self._search_regex( - r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub')) - video_id = watch_hub_data['vms-id'] - title = watch_hub_data['video-title'] - - query = {} - if watch_hub_data.get('video-locked') == '1': - resource = self._get_mvpd_resource( - 'VICELAND', title, video_id, - watch_hub_data.get('video-rating')) - query['tvetoken'] = self._extract_mvpd_auth(url, video_id, 'VICELAND', resource) - - # signature generation algorithm is reverse engineered from signatureGenerator in - # webpack:///../shared/~/vice-player/dist/js/vice-player.js in - # https://www.viceland.com/assets/common/js/web.vendor.bundle.js - exp = int(time.time()) + 14400 - query.update({ - 'exp': exp, - 'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(), - }) - - try: - preplay = self._download_json('https://www.viceland.com/en_us/preplay/%s' % video_id, video_id, query=query) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: - error = json.loads(e.cause.read().decode()) - raise ExtractorError('%s said: %s' % (self.IE_NAME, error['details']), expected=True) - raise - - video_data = preplay['video'] - base = video_data['base'] - uplynk_preplay_url = preplay['preplayURL'] - episode = video_data.get('episode', {}) - channel = video_data.get('channel', {}) - - subtitles = {} - cc_url = preplay.get('ccURL') - if cc_url: - subtitles['en'] = [{ - 'url': cc_url, - }] - - return { - '_type': 'url_transparent', - 'url': uplynk_preplay_url, - 'id': video_id, - 'title': title, - 'description': base.get('body'), - 'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'), - 'duration': parse_duration(video_data.get('video_duration') or watch_hub_data.get('video-duration')), - 'timestamp': int_or_none(video_data.get('created_at')), - 'age_limit': parse_age_limit(video_data.get('video_rating')), - 'series': video_data.get('show_title') or watch_hub_data.get('show-title'), - 'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')), - 'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')), - 'season_number': int_or_none(watch_hub_data.get('season')), - 'season_id': str_or_none(episode.get('season_id')), - 'uploader': channel.get('base', {}).get('title') or watch_hub_data.get('channel-title'), - 'uploader_id': str_or_none(channel.get('id')), - 'subtitles': subtitles, - 'ie_key': 'UplynkPreplay', - } + return self._extract_preplay_video(url, webpage) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 4351ac4..9c48701 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -1,11 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import json -import time -import hmac import hashlib +import hmac import itertools +import json +import re +import time from .common import InfoExtractor from ..utils import ( @@ -276,10 +277,14 @@ class VikiIE(VikiBaseIE): height = int_or_none(self._search_regex( r'^(\d+)[pP]$', format_id, 'height', default=None)) for protocol, format_dict in stream_dict.items(): + # rtmps URLs does not seem to work + if protocol == 'rtmps': + continue + format_url = format_dict['url'] if format_id == 'm3u8': m3u8_formats = self._extract_m3u8_formats( - format_dict['url'], video_id, 'mp4', - entry_protocol='m3u8_native', preference=-1, + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='m3u8-%s' % protocol, fatal=False) # Despite CODECS metadata in m3u8 all video-only formats # are actually video+audio @@ -287,9 +292,23 @@ class VikiIE(VikiBaseIE): if f.get('acodec') == 'none' and f.get('vcodec') != 'none': f['acodec'] = None formats.extend(m3u8_formats) + elif format_url.startswith('rtmp'): + mobj = re.search( + r'^(?P<url>rtmp://[^/]+/(?P<app>.+?))/(?P<playpath>mp4:.+)$', + format_url) + if not mobj: + continue + formats.append({ + 'format_id': 'rtmp-%s' % format_id, + 'ext': 'flv', + 'url': mobj.group('url'), + 'play_path': mobj.group('playpath'), + 'app': mobj.group('app'), + 'page_url': url, + }) else: formats.append({ - 'url': format_dict['url'], + 'url': format_url, 'format_id': '%s-%s' % (format_id, protocol), 'height': height, }) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index b566241..51c69a8 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -323,6 +323,22 @@ class VimeoIE(VimeoBaseInfoExtractor): 'expected_warnings': ['Unable to download JSON metadata'], }, { + # redirects to ondemand extractor and should be passed throught it + # for successful extraction + 'url': 'https://vimeo.com/73445910', + 'info_dict': { + 'id': '73445910', + 'ext': 'mp4', + 'title': 'The Reluctant Revolutionary', + 'uploader': '10Ft Films', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/tenfootfilms', + 'uploader_id': 'tenfootfilms', + }, + 'params': { + 'skip_download': True, + }, + }, + { 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', 'only_matching': True, }, @@ -414,7 +430,12 @@ class VimeoIE(VimeoBaseInfoExtractor): # Retrieve video webpage to extract further information request = sanitized_Request(url, headers=headers) try: - webpage = self._download_webpage(request, video_id) + webpage, urlh = self._download_webpage_handle(request, video_id) + # Some URLs redirect to ondemand can't be extracted with + # this extractor right away thus should be passed through + # ondemand extractor (e.g. https://vimeo.com/73445910) + if VimeoOndemandIE.suitable(urlh.geturl()): + return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key()) except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index df43ba8..1990e70 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import collections import re -import json import sys from .common import InfoExtractor @@ -369,8 +368,18 @@ class VKIE(VKBaseIE): opts_url = 'http:' + opts_url return self.url_result(opts_url) - data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars') - data = json.loads(data_json) + # vars does not look to be served anymore since 24.10.2016 + data = self._parse_json( + self._search_regex( + r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'), + video_id, fatal=False) + + # <!json> is served instead + if not data: + data = self._parse_json( + self._search_regex( + r'<!json>\s*({.+?})\s*<!>', info_page, 'json'), + video_id)['player']['params'][0] title = unescapeHTML(data['md_title']) diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index 8d671cc..acf9fda 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -17,7 +17,7 @@ from ..compat import compat_urllib_parse_urlencode class VLiveIE(InfoExtractor): IE_NAME = 'vlive' _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.vlive.tv/video/1326', 'md5': 'cc7314812855ce56de70a06a27314983', 'info_dict': { @@ -27,7 +27,20 @@ class VLiveIE(InfoExtractor): 'creator': "Girl's Day", 'view_count': int, }, - } + }, { + 'url': 'http://www.vlive.tv/video/16937', + 'info_dict': { + 'id': '16937', + 'ext': 'mp4', + 'title': '[V LIVE] 첸백시 걍방', + 'creator': 'EXO', + 'view_count': int, + 'subtitles': 'mincount:12', + }, + 'params': { + 'skip_download': True, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -116,7 +129,7 @@ class VLiveIE(InfoExtractor): subtitles = {} for caption in playinfo.get('captions', {}).get('list', []): - lang = dict_get(caption, ('language', 'locale', 'country', 'label')) + lang = dict_get(caption, ('locale', 'language', 'country', 'label')) if lang and caption.get('source'): subtitles[lang] = [{ 'ext': 'vtt', diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index c85b474..bbfa6e5 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -31,7 +31,8 @@ class VodlockerIE(InfoExtractor): if any(p in webpage for p in ( '>THIS FILE WAS DELETED<', '>File Not Found<', - 'The file you were looking for could not be found, sorry for any inconvenience.<')): + 'The file you were looking for could not be found, sorry for any inconvenience.<', + '>The file was removed')): raise ExtractorError('Video %s does not exist' % video_id, expected=True) fields = self._hidden_inputs(webpage) diff --git a/youtube_dl/extractor/vzaar.py b/youtube_dl/extractor/vzaar.py new file mode 100644 index 0000000..b270f08 --- /dev/null +++ b/youtube_dl/extractor/vzaar.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, +) + + +class VzaarIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://vzaar.com/videos/1152805', + 'md5': 'bde5ddfeb104a6c56a93a06b04901dbf', + 'info_dict': { + 'id': '1152805', + 'ext': 'mp4', + 'title': 'sample video (public)', + }, + }, { + 'url': 'https://view.vzaar.com/27272/player', + 'md5': '3b50012ac9bbce7f445550d54e0508f2', + 'info_dict': { + 'id': '27272', + 'ext': 'mp3', + 'title': 'MP3', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_json( + 'http://view.vzaar.com/v2/%s/video' % video_id, video_id) + source_url = video_data['sourceUrl'] + + info = { + 'id': video_id, + 'title': video_data['videoTitle'], + 'url': source_url, + 'thumbnail': self._proto_relative_url(video_data.get('poster')), + 'duration': float_or_none(video_data.get('videoDuration')), + } + if 'audio' in source_url: + info.update({ + 'vcodec': 'none', + 'ext': 'mp3', + }) + else: + info.update({ + 'width': int_or_none(video_data.get('width')), + 'height': int_or_none(video_data.get('height')), + 'ext': 'mp4', + }) + return info diff --git a/youtube_dl/extractor/webcaster.py b/youtube_dl/extractor/webcaster.py new file mode 100644 index 0000000..7486cb3 --- /dev/null +++ b/youtube_dl/extractor/webcaster.py @@ -0,0 +1,102 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + xpath_text, +) + + +class WebcasterIE(InfoExtractor): + _VALID_URL = r'https?://bl\.webcaster\.pro/(?:quote|media)/start/free_(?P<id>[^/]+)' + _TESTS = [{ + # http://video.khl.ru/quotes/393859 + 'url': 'http://bl.webcaster.pro/quote/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104?sr%3D105%26fa%3D1%26type_id%3D18', + 'md5': '0c162f67443f30916ff1c89425dcd4cd', + 'info_dict': { + 'id': 'c8cefd240aa593681c8d068cff59f407_hd', + 'ext': 'mp4', + 'title': 'Сибирь - Нефтехимик. Лучшие моменты первого периода', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, { + 'url': 'http://bl.webcaster.pro/media/start/free_6246c7a4453ac4c42b4398f840d13100_hd/2_2991109016/e8d0d82587ef435480118f9f9c41db41/4635726126', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_xml(url, video_id) + + title = xpath_text(video, './/event_name', 'event name', fatal=True) + + def make_id(parts, separator): + return separator.join(filter(None, parts)) + + formats = [] + for format_id in (None, 'noise'): + track_tag = make_id(('track', format_id), '_') + for track in video.findall('.//iphone/%s' % track_tag): + track_url = track.text + if not track_url: + continue + if determine_ext(track_url) == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + track_url, video_id, 'mp4', + entry_protocol='m3u8_native', + m3u8_id=make_id(('hls', format_id), '-'), fatal=False) + for f in m3u8_formats: + f.update({ + 'source_preference': 0 if format_id == 'noise' else 1, + 'format_note': track.get('title'), + }) + formats.extend(m3u8_formats) + self._sort_formats(formats) + + thumbnail = xpath_text(video, './/image', 'thumbnail') + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } + + +class WebcasterFeedIE(InfoExtractor): + _VALID_URL = r'https?://bl\.webcaster\.pro/feed/start/free_(?P<id>[^/]+)' + _TEST = { + 'url': 'http://bl.webcaster.pro/feed/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104', + 'only_matching': True, + } + + @staticmethod + def _extract_url(ie, webpage): + mobj = re.search( + r'<(?:object|a[^>]+class=["\']webcaster-player["\'])[^>]+data(?:-config)?=(["\']).*?config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_.*?)(?:[?&]|\1)', + webpage) + if mobj: + return mobj.group('url') + for secure in (True, False): + video_url = ie._og_search_video_url( + webpage, secure=secure, default=None) + if video_url: + mobj = re.search( + r'config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_[^?&=]+)', + video_url) + if mobj: + return mobj.group('url') + + def _real_extract(self, url): + video_id = self._match_id(url) + + feed = self._download_xml(url, video_id) + + video_url = xpath_text( + feed, ('video_hd', 'video'), 'video url', fatal=True) + + return self.url_result(video_url, WebcasterIE.ie_key()) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 91f0a0d..4951414 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -201,6 +201,32 @@ class YahooIE(InfoExtractor): }, 'skip': 'redirect to https://www.yahoo.com/music', }, + { + # yahoo://article/ + 'url': 'https://www.yahoo.com/movies/video/true-story-trailer-173000497.html', + 'info_dict': { + 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', + 'ext': 'mp4', + 'title': "'True Story' Trailer", + 'description': 'True Story', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # ytwnews://cavideo/ + 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', + 'info_dict': { + 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', + 'ext': 'mp4', + 'title': '單車天使 - 中文版預', + 'description': '中文版預', + }, + 'params': { + 'skip_download': True, + }, + }, ] def _real_extract(self, url): @@ -269,7 +295,8 @@ class YahooIE(InfoExtractor): r'"first_videoid"\s*:\s*"([^"]+)"', r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), r'<article[^>]data-uuid=["\']([^"\']+)', - r'yahoo://article/view\?.*\buuid=([^&"\']+)', + r'<meta[^<>]+yahoo://article/view\?.*\buuid=([^&"\']+)', + r'<meta[^<>]+["\']ytwnews://cavideo/(?:[^/]+/)+([\da-fA-F-]+)[&"\']', ] video_id = self._search_regex( CONTENT_ID_REGEXES, webpage, 'content ID') diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 545246b..bd24a28 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1796,7 +1796,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): | ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) )""" - _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' + _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true' _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' IE_NAME = 'youtube:playlist' _TESTS = [{ @@ -2175,7 +2175,7 @@ class YoutubeUserIE(YoutubeChannelIE): class YoutubeLiveIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com live streams' - _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+))/live' + _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live' IE_NAME = 'youtube:live' _TESTS = [{ @@ -2204,6 +2204,9 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor): }, { 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/TheYoungTurks/live', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py index 9737f70..a8df4ae 100644 --- a/youtube_dl/jsinterp.py +++ b/youtube_dl/jsinterp.py @@ -198,12 +198,12 @@ class JSInterpreter(object): return opfunc(x, y) m = re.match( - r'^(?P<func>%s)\((?P<args>[a-zA-Z0-9_$,]+)\)$' % _NAME_RE, expr) + r'^(?P<func>%s)\((?P<args>[a-zA-Z0-9_$,]*)\)$' % _NAME_RE, expr) if m: fname = m.group('func') argvals = tuple([ int(v) if v.isdigit() else local_vars[v] - for v in m.group('args').split(',')]) + for v in m.group('args').split(',')]) if len(m.group('args')) > 0 else tuple() if fname not in self._functions: self._functions[fname] = self.extract_function(fname) return self._functions[fname](argvals) diff --git a/youtube_dl/socks.py b/youtube_dl/socks.py index 1048072..fece280 100644 --- a/youtube_dl/socks.py +++ b/youtube_dl/socks.py @@ -60,7 +60,7 @@ class ProxyError(IOError): def __init__(self, code=None, msg=None): if code is not None and msg is None: - msg = self.CODES.get(code) and 'unknown error' + msg = self.CODES.get(code) or 'unknown error' super(ProxyError, self).__init__(code, msg) @@ -103,6 +103,7 @@ class ProxyType(object): SOCKS4A = 1 SOCKS5 = 2 + Proxy = collections.namedtuple('Proxy', ( 'type', 'host', 'port', 'username', 'password', 'remote_dns')) diff --git a/youtube_dl/swfinterp.py b/youtube_dl/swfinterp.py index 7cf490a..0c71585 100644 --- a/youtube_dl/swfinterp.py +++ b/youtube_dl/swfinterp.py @@ -115,6 +115,8 @@ def _u30(reader): res = _read_int(reader) assert res & 0xf0000000 == 0 return res + + _u32 = _read_int @@ -176,6 +178,7 @@ class _Undefined(object): return 'undefined' __repr__ = __str__ + undefined = _Undefined() diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2894167..9595bcf 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1691,6 +1691,10 @@ def url_basename(url): return path.strip('/').split('/')[-1] +def base_url(url): + return re.match(r'https?://[^?#&]+/', url).group() + + class HEADRequest(compat_urllib_request.Request): def get_method(self): return 'HEAD' @@ -1818,8 +1822,12 @@ def get_exe_version(exe, args=['--version'], """ Returns the version of the specified executable, or False if the executable is not present """ try: + # STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers + # SIGTTOU if youtube-dl is run in the background. + # See https://github.com/rg3/youtube-dl/issues/955#issuecomment-209789656 out, _ = subprocess.Popen( [encodeArgument(exe)] + args, + stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate() except OSError: return False @@ -2341,11 +2349,18 @@ def _match_one(filter_part, dct): m = operator_rex.search(filter_part) if m: op = COMPARISON_OPERATORS[m.group('op')] - if m.group('strval') is not None: + actual_value = dct.get(m.group('key')) + if (m.group('strval') is not None or + # If the original field is a string and matching comparisonvalue is + # a number we should respect the origin of the original field + # and process comparison value as a string (see + # https://github.com/rg3/youtube-dl/issues/11082). + actual_value is not None and m.group('intval') is not None and + isinstance(actual_value, compat_str)): if m.group('op') not in ('=', '!='): raise ValueError( 'Operator %s does not support string values!' % m.group('op')) - comparison_value = m.group('strval') + comparison_value = m.group('strval') or m.group('intval') else: try: comparison_value = int(m.group('intval')) @@ -2357,7 +2372,6 @@ def _match_one(filter_part, dct): raise ValueError( 'Invalid integer value %r in filter part %r' % ( m.group('intval'), filter_part)) - actual_value = dct.get(m.group('key')) if actual_value is None: return m.group('none_inclusive') return op(actual_value, comparison_value) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 583c829..1acb630 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2016.10.21.1' +__version__ = '2016.12.01' |