diff options
author | Rogério Brito <rbrito@ime.usp.br> | 2017-02-24 21:07:40 -0300 |
---|---|---|
committer | Rogério Brito <rbrito@ime.usp.br> | 2017-02-24 21:07:40 -0300 |
commit | 4e090bc3ceacc4e3cd464d12ea97700e3acad37d (patch) | |
tree | 899b82420538d865e697fb071a03db254653e7c6 /youtube_dl/extractor | |
parent | 575f75429e2e479957d006a26940f4a5a51347ce (diff) | |
download | youtube-dl-4e090bc3ceacc4e3cd464d12ea97700e3acad37d.zip youtube-dl-4e090bc3ceacc4e3cd464d12ea97700e3acad37d.tar.gz youtube-dl-4e090bc3ceacc4e3cd464d12ea97700e3acad37d.tar.bz2 |
New upstream version 2017.02.24.1
Diffstat (limited to 'youtube_dl/extractor')
88 files changed, 1863 insertions, 772 deletions
diff --git a/youtube_dl/extractor/adobepass.py b/youtube_dl/extractor/adobepass.py index 12eeab2..4d655bd 100644 --- a/youtube_dl/extractor/adobepass.py +++ b/youtube_dl/extractor/adobepass.py @@ -31,6 +31,11 @@ MSO_INFO = { 'username_field': 'user', 'password_field': 'passwd', }, + 'TWC': { + 'name': 'Time Warner Cable | Spectrum', + 'username_field': 'Ecom_User_ID', + 'password_field': 'Ecom_Password', + }, 'thr030': { 'name': '3 Rivers Communications' }, diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index c973174..dd96a47 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -23,7 +23,7 @@ class AENetworksBaseIE(ThePlatformIE): class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' - _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)' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime|lifetimemovieclub)\.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': 'a97a65f7e823ae10e9244bc5433d5fe6', @@ -62,11 +62,15 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie', 'only_matching': True + }, { + 'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', 'aetv.com': 'AETV', 'mylifetime.com': 'LIFETIME', + 'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB', 'fyi.tv': 'FYI', } diff --git a/youtube_dl/extractor/amcnetworks.py b/youtube_dl/extractor/amcnetworks.py index 87c803e..b71d1a0 100644 --- a/youtube_dl/extractor/amcnetworks.py +++ b/youtube_dl/extractor/amcnetworks.py @@ -53,20 +53,30 @@ class AMCNetworksIE(ThePlatformIE): 'mbr': 'true', 'manifest': 'm3u', } - media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url') + media_url = self._search_regex( + r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', + webpage, 'media url') theplatform_metadata = self._download_theplatform_metadata(self._search_regex( - r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id) + r'link\.theplatform\.com/s/([^?]+)', + media_url, 'theplatform_path'), display_id) info = self._parse_theplatform_metadata(theplatform_metadata) video_id = theplatform_metadata['pid'] title = theplatform_metadata['title'] rating = theplatform_metadata['ratings'][0]['rating'] - auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required') + auth_required = self._search_regex( + r'window\.authRequired\s*=\s*(true|false);', + webpage, 'auth required') if auth_required == 'true': - requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id') - resource = self._get_mvpd_resource(requestor_id, title, video_id, rating) - query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource) + requestor_id = self._search_regex( + r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', + webpage, 'requestor id') + resource = self._get_mvpd_resource( + requestor_id, title, video_id, rating) + query['auth'] = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) media_url = update_url_query(media_url, query) - formats, subtitles = self._extract_theplatform_smil(media_url, video_id) + formats, subtitles = self._extract_theplatform_smil( + media_url, video_id) self._sort_formats(formats) info.update({ 'id': video_id, @@ -78,9 +88,11 @@ class AMCNetworksIE(ThePlatformIE): if ns_keys: ns = list(ns_keys)[0] series = theplatform_metadata.get(ns + '$show') - season_number = int_or_none(theplatform_metadata.get(ns + '$season')) + season_number = int_or_none( + theplatform_metadata.get(ns + '$season')) episode = theplatform_metadata.get(ns + '$episodeTitle') - episode_number = int_or_none(theplatform_metadata.get(ns + '$episode')) + episode_number = int_or_none( + theplatform_metadata.get(ns + '$episode')) if season_number: title = 'Season %d - %s' % (season_number, title) if series: diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 486dff8..e21045b 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -1,13 +1,13 @@ from __future__ import unicode_literals -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( unified_strdate, clean_html, ) -class ArchiveOrgIE(JWPlatformBaseIE): +class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$' diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index b179161..8a2ed0a 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -225,6 +225,8 @@ class BBCCoUkIE(InfoExtractor): } ] + _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8' + class MediaSelectionError(Exception): def __init__(self, id): self.id = id @@ -336,6 +338,15 @@ class BBCCoUkIE(InfoExtractor): formats.extend(self._extract_m3u8_formats( href, programme_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)) + if re.search(self._USP_RE, href): + usp_formats = self._extract_m3u8_formats( + re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href), + programme_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id=format_id, fatal=False) + for f in usp_formats: + if f.get('height') and f['height'] > 720: + continue + formats.append(f) elif transfer_format == 'hds': formats.extend(self._extract_f4m_formats( href, programme_id, f4m_id=format_id, fatal=False)) diff --git a/youtube_dl/extractor/bellmedia.py b/youtube_dl/extractor/bellmedia.py index 32326ed..1f5b6ed 100644 --- a/youtube_dl/extractor/bellmedia.py +++ b/youtube_dl/extractor/bellmedia.py @@ -24,7 +24,7 @@ class BellMediaIE(InfoExtractor): space )\.ca| much\.com - )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})''' + )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})''' _TESTS = [{ 'url': 'http://www.ctv.ca/video/player?vid=706966', 'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0', @@ -55,6 +55,9 @@ class BellMediaIE(InfoExtractor): }, { 'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6', 'only_matching': True, + }, { + 'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430', + 'only_matching': True, }] _DOMAINS = { 'thecomedynetwork': 'comedy', diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index c5e11e8..2fbfad1 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -34,6 +34,10 @@ class BloombergIE(InfoExtractor): 'format': 'best[format_id^=hds]', }, }, { + # data-bmmrid= + 'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money', + 'only_matching': True, + }, { 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', 'only_matching': True, }, { @@ -45,9 +49,10 @@ class BloombergIE(InfoExtractor): name = self._match_id(url) webpage = self._download_webpage(url, name) video_id = self._search_regex( - (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', - r'videoId\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1'), - webpage, 'id', group='url', default=None) + (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', + r'videoId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', + r'data-bmmrid=(["\'])(?P<id>(?:(?!\1).)+)\1'), + webpage, 'id', group='id', default=None) if not video_id: bplayer_data = self._parse_json(self._search_regex( r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 5c6e99d..27685ee 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -191,6 +191,10 @@ class BrightcoveLegacyIE(InfoExtractor): # These fields hold the id of the video videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList') if videoPlayer is not None: + if isinstance(videoPlayer, list): + videoPlayer = videoPlayer[0] + if not (videoPlayer.isdigit() or videoPlayer.startswith('ref:')): + return None params['@videoPlayer'] = videoPlayer linkBase = find_param('linkBaseURL') if linkBase is not None: diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 4f88c31..b1dfacf 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -13,6 +13,7 @@ from ..utils import ( float_or_none, sanitized_Request, urlencode_postdata, + USER_AGENTS, ) @@ -21,10 +22,10 @@ class CeskaTelevizeIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220', 'info_dict': { - 'id': '61924494876951776', + 'id': '61924494877246241', 'ext': 'mp4', - 'title': 'Hyde Park Civilizace', - 'description': 'md5:fe93f6eda372d150759d11644ebbfb4a', + 'title': 'Hyde Park Civilizace: Život v Grónsku', + 'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 3350, }, @@ -114,70 +115,100 @@ class CeskaTelevizeIE(InfoExtractor): 'requestSource': 'iVysilani', } - req = sanitized_Request( - 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', - data=urlencode_postdata(data)) - - req.add_header('Content-type', 'application/x-www-form-urlencoded') - req.add_header('x-addr', '127.0.0.1') - req.add_header('X-Requested-With', 'XMLHttpRequest') - req.add_header('Referer', url) - - playlistpage = self._download_json(req, playlist_id) - - playlist_url = playlistpage['url'] - if playlist_url == 'error_region': - raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) - - req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) - req.add_header('Referer', url) - - playlist_title = self._og_search_title(webpage, default=None) - playlist_description = self._og_search_description(webpage, default=None) - - playlist = self._download_json(req, playlist_id)['playlist'] - playlist_len = len(playlist) - entries = [] - for item in playlist: - is_live = item.get('type') == 'LIVE' - formats = [] - for format_id, stream_url in item['streamUrls'].items(): - formats.extend(self._extract_m3u8_formats( - stream_url, playlist_id, 'mp4', - entry_protocol='m3u8' if is_live else 'm3u8_native', - fatal=False)) - self._sort_formats(formats) - - item_id = item.get('id') or item['assetId'] - title = item['title'] - - duration = float_or_none(item.get('duration')) - thumbnail = item.get('previewImageUrl') - - subtitles = {} - if item.get('type') == 'VOD': - subs = item.get('subtitles') - if subs: - subtitles = self.extract_subtitles(episode_id, subs) - - if playlist_len == 1: - final_title = playlist_title or title - if is_live: - final_title = self._live_title(final_title) - else: - final_title = '%s (%s)' % (playlist_title, title) - - entries.append({ - 'id': item_id, - 'title': final_title, - 'description': playlist_description if playlist_len == 1 else None, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - 'is_live': is_live, - }) + + for user_agent in (None, USER_AGENTS['Safari']): + req = sanitized_Request( + 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', + data=urlencode_postdata(data)) + + req.add_header('Content-type', 'application/x-www-form-urlencoded') + req.add_header('x-addr', '127.0.0.1') + req.add_header('X-Requested-With', 'XMLHttpRequest') + if user_agent: + req.add_header('User-Agent', user_agent) + req.add_header('Referer', url) + + playlistpage = self._download_json(req, playlist_id, fatal=False) + + if not playlistpage: + continue + + playlist_url = playlistpage['url'] + if playlist_url == 'error_region': + raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) + + req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) + req.add_header('Referer', url) + + playlist_title = self._og_search_title(webpage, default=None) + playlist_description = self._og_search_description(webpage, default=None) + + playlist = self._download_json(req, playlist_id, fatal=False) + if not playlist: + continue + + playlist = playlist.get('playlist') + if not isinstance(playlist, list): + continue + + playlist_len = len(playlist) + + for num, item in enumerate(playlist): + is_live = item.get('type') == 'LIVE' + formats = [] + for format_id, stream_url in item.get('streamUrls', {}).items(): + if 'playerType=flash' in stream_url: + stream_formats = self._extract_m3u8_formats( + stream_url, playlist_id, 'mp4', + entry_protocol='m3u8' if is_live else 'm3u8_native', + m3u8_id='hls-%s' % format_id, fatal=False) + else: + stream_formats = self._extract_mpd_formats( + stream_url, playlist_id, + mpd_id='dash-%s' % format_id, fatal=False) + # See https://github.com/rg3/youtube-dl/issues/12119#issuecomment-280037031 + if format_id == 'audioDescription': + for f in stream_formats: + f['source_preference'] = -10 + formats.extend(stream_formats) + + if user_agent and len(entries) == playlist_len: + entries[num]['formats'].extend(formats) + continue + + item_id = item.get('id') or item['assetId'] + title = item['title'] + + duration = float_or_none(item.get('duration')) + thumbnail = item.get('previewImageUrl') + + subtitles = {} + if item.get('type') == 'VOD': + subs = item.get('subtitles') + if subs: + subtitles = self.extract_subtitles(episode_id, subs) + + if playlist_len == 1: + final_title = playlist_title or title + if is_live: + final_title = self._live_title(final_title) + else: + final_title = '%s (%s)' % (playlist_title, title) + + entries.append({ + 'id': item_id, + 'title': final_title, + 'description': playlist_description if playlist_len == 1 else None, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + 'is_live': is_live, + }) + + for e in entries: + self._sort_formats(e['formats']) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 0b4e2ac..4252d68 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -6,6 +6,7 @@ import hashlib import json import netrc import os +import random import re import socket import sys @@ -39,7 +40,10 @@ from ..utils import ( ExtractorError, fix_xml_ampersands, float_or_none, + GeoRestrictedError, + GeoUtils, int_or_none, + js_to_json, parse_iso8601, RegexNotFoundError, sanitize_filename, @@ -319,17 +323,34 @@ class InfoExtractor(object): _real_extract() methods and define a _VALID_URL regexp. Probably, they should also be added to the list of extractors. + _GEO_BYPASS attribute may be set to False in order to disable + geo restriction bypass mechanisms for a particular extractor. + Though it won't disable explicit geo restriction bypass based on + country code provided with geo_bypass_country. (experimental) + + _GEO_COUNTRIES attribute may contain a list of presumably geo unrestricted + countries for this extractor. One of these countries will be used by + geo restriction bypass mechanism right away in order to bypass + geo restriction, of course, if the mechanism is not disabled. (experimental) + + NB: both these geo attributes are experimental and may change in future + or be completely removed. + Finally, the _WORKING attribute should be set to False for broken IEs in order to warn the users and skip the tests. """ _ready = False _downloader = None + _x_forwarded_for_ip = None + _GEO_BYPASS = True + _GEO_COUNTRIES = None _WORKING = True def __init__(self, downloader=None): """Constructor. Receives an optional downloader.""" self._ready = False + self._x_forwarded_for_ip = None self.set_downloader(downloader) @classmethod @@ -358,15 +379,59 @@ class InfoExtractor(object): def initialize(self): """Initializes an instance (authentication, etc).""" + self._initialize_geo_bypass(self._GEO_COUNTRIES) if not self._ready: self._real_initialize() self._ready = True + def _initialize_geo_bypass(self, countries): + """ + Initialize geo restriction bypass mechanism. + + This method is used to initialize geo bypass mechanism based on faking + X-Forwarded-For HTTP header. A random country from provided country list + is selected and a random IP belonging to this country is generated. This + IP will be passed as X-Forwarded-For HTTP header in all subsequent + HTTP requests. + + This method will be used for initial geo bypass mechanism initialization + during the instance initialization with _GEO_COUNTRIES. + + You may also manually call it from extractor's code if geo countries + information is not available beforehand (e.g. obtained during + extraction) or due to some another reason. + """ + if not self._x_forwarded_for_ip: + country_code = self._downloader.params.get('geo_bypass_country', None) + # If there is no explicit country for geo bypass specified and + # the extractor is known to be geo restricted let's fake IP + # as X-Forwarded-For right away. + if (not country_code and + self._GEO_BYPASS and + self._downloader.params.get('geo_bypass', True) and + countries): + country_code = random.choice(countries) + if country_code: + self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code) + if self._downloader.params.get('verbose', False): + self._downloader.to_stdout( + '[debug] Using fake IP %s (%s) as X-Forwarded-For.' + % (self._x_forwarded_for_ip, country_code.upper())) + def extract(self, url): """Extracts URL information and returns it in list of dicts.""" try: - self.initialize() - return self._real_extract(url) + for _ in range(2): + try: + self.initialize() + ie_result = self._real_extract(url) + if self._x_forwarded_for_ip: + ie_result['__x_forwarded_for_ip'] = self._x_forwarded_for_ip + return ie_result + except GeoRestrictedError as e: + if self.__maybe_fake_ip_and_retry(e.countries): + continue + raise except ExtractorError: raise except compat_http_client.IncompleteRead as e: @@ -374,6 +439,21 @@ class InfoExtractor(object): except (KeyError, StopIteration) as e: raise ExtractorError('An extractor error has occurred.', cause=e) + def __maybe_fake_ip_and_retry(self, countries): + if (not self._downloader.params.get('geo_bypass_country', None) and + self._GEO_BYPASS and + self._downloader.params.get('geo_bypass', True) and + not self._x_forwarded_for_ip and + countries): + country_code = random.choice(countries) + self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code) + if self._x_forwarded_for_ip: + self.report_warning( + 'Video is geo restricted. Retrying extraction with fake IP %s (%s) as X-Forwarded-For.' + % (self._x_forwarded_for_ip, country_code.upper())) + return True + return False + def set_downloader(self, downloader): """Sets the downloader for this IE.""" self._downloader = downloader @@ -433,6 +513,15 @@ class InfoExtractor(object): if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] + # Some sites check X-Forwarded-For HTTP header in order to figure out + # the origin of the client behind proxy. This allows bypassing geo + # restriction by faking this header's value to IP that belongs to some + # geo unrestricted country. We will do so once we encounter any + # geo restriction error. + if self._x_forwarded_for_ip: + if 'X-Forwarded-For' not in headers: + headers['X-Forwarded-For'] = self._x_forwarded_for_ip + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal @@ -608,10 +697,8 @@ class InfoExtractor(object): expected=True) @staticmethod - def raise_geo_restricted(msg='This video is not available from your location due to geo restriction'): - raise ExtractorError( - '%s. You might want to use --proxy to workaround.' % msg, - expected=True) + def raise_geo_restricted(msg='This video is not available from your location due to geo restriction', countries=None): + raise GeoRestrictedError(msg, countries=countries) # Methods for following #608 @staticmethod @@ -1208,6 +1295,9 @@ class InfoExtractor(object): m3u8_doc, urlh = res m3u8_url = urlh.geturl() + if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access + return [] + formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)] format_url = lambda u: ( @@ -2070,6 +2160,123 @@ class InfoExtractor(object): }) return formats + @staticmethod + def _find_jwplayer_data(webpage): + mobj = re.search( + r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)', + webpage) + if mobj: + return mobj.group('options') + + def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs): + jwplayer_data = self._parse_json( + self._find_jwplayer_data(webpage), video_id, + transform_source=js_to_json) + return self._parse_jwplayer_data( + jwplayer_data, video_id, *args, **kwargs) + + def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, + m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None): + # JWPlayer backward compatibility: flattened playlists + # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96 + if 'playlist' not in jwplayer_data: + jwplayer_data = {'playlist': [jwplayer_data]} + + entries = [] + + # JWPlayer backward compatibility: single playlist item + # https://github.com/jwplayer/jwplayer/blob/v7.7.0/src/js/playlist/playlist.js#L10 + if not isinstance(jwplayer_data['playlist'], list): + jwplayer_data['playlist'] = [jwplayer_data['playlist']] + + for video_data in jwplayer_data['playlist']: + # JWPlayer backward compatibility: flattened sources + # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35 + if 'sources' not in video_data: + video_data['sources'] = [video_data] + + this_video_id = video_id or video_data['mediaid'] + + formats = [] + for source in video_data['sources']: + source_url = self._proto_relative_url(source['file']) + if base_url: + source_url = compat_urlparse.urljoin(base_url, source_url) + source_type = source.get('type') or '' + ext = mimetype2ext(source_type) or determine_ext(source_url) + if source_type == 'hls' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False)) + elif ext == 'mpd': + formats.extend(self._extract_mpd_formats( + source_url, this_video_id, mpd_id=mpd_id, fatal=False)) + # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67 + elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'): + formats.append({ + 'url': source_url, + 'vcodec': 'none', + 'ext': ext, + }) + else: + height = int_or_none(source.get('height')) + if height is None: + # Often no height is provided but there is a label in + # format like 1080p. + height = int_or_none(self._search_regex( + r'^(\d{3,})[pP]$', source.get('label') or '', + 'height', default=None)) + a_format = { + 'url': source_url, + 'width': int_or_none(source.get('width')), + 'height': height, + 'ext': ext, + } + if source_url.startswith('rtmp'): + a_format['ext'] = 'flv' + + # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as + # of jwplayer.flash.swf + rtmp_url_parts = re.split( + r'((?:mp4|mp3|flv):)', source_url, 1) + if len(rtmp_url_parts) == 3: + rtmp_url, prefix, play_path = rtmp_url_parts + a_format.update({ + 'url': rtmp_url, + 'play_path': prefix + play_path, + }) + if rtmp_params: + a_format.update(rtmp_params) + formats.append(a_format) + self._sort_formats(formats) + + subtitles = {} + tracks = video_data.get('tracks') + if tracks and isinstance(tracks, list): + for track in tracks: + if track.get('kind') != 'captions': + continue + track_url = urljoin(base_url, track.get('file')) + if not track_url: + continue + subtitles.setdefault(track.get('label') or 'en', []).append({ + 'url': self._proto_relative_url(track_url) + }) + + entries.append({ + 'id': this_video_id, + 'title': video_data['title'] if require_title else video_data.get('title'), + 'description': video_data.get('description'), + 'thumbnail': self._proto_relative_url(video_data.get('image')), + 'timestamp': int_or_none(video_data.get('pubdate')), + 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), + 'subtitles': subtitles, + 'formats': formats, + }) + if len(entries) == 1: + return entries[0] + else: + return self.playlist_result(entries) + def _live_title(self, name): """ Generate the title for a live video """ now = datetime.datetime.now() diff --git a/youtube_dl/extractor/commonmistakes.py b/youtube_dl/extractor/commonmistakes.py index 2f86e23..79f7a9c 100644 --- a/youtube_dl/extractor/commonmistakes.py +++ b/youtube_dl/extractor/commonmistakes.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import sys + from .common import InfoExtractor from ..utils import ExtractorError @@ -7,7 +9,7 @@ from ..utils import ExtractorError class CommonMistakesIE(InfoExtractor): IE_DESC = False # Do not list _VALID_URL = r'''(?x) - (?:url|URL) + (?:url|URL)$ ''' _TESTS = [{ @@ -33,7 +35,9 @@ class UnicodeBOMIE(InfoExtractor): IE_DESC = False _VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$' - _TESTS = [{ + # Disable test for python 3.2 since BOM is broken in re in this version + # (see https://github.com/rg3/youtube-dl/issues/9751) + _TESTS = [] if (3, 0) < sys.version_info <= (3, 3) else [{ 'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc', 'only_matching': True, }] diff --git a/youtube_dl/extractor/corus.py b/youtube_dl/extractor/corus.py new file mode 100644 index 0000000..7b2f500 --- /dev/null +++ b/youtube_dl/extractor/corus.py @@ -0,0 +1,72 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .theplatform import ThePlatformFeedIE +from ..utils import int_or_none + + +class CorusIE(ThePlatformFeedIE): + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:globaltv|etcanada)\.com|(?:hgtv|foodnetwork|slice)\.ca)/(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/', + 'md5': '05dcbca777bf1e58c2acbb57168ad3a6', + 'info_dict': { + 'id': '870923331648', + 'ext': 'mp4', + 'title': 'Movie Night Popcorn with Bryan', + 'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.', + 'uploader': 'SHWM-NEW', + 'upload_date': '20170206', + 'timestamp': 1486392197, + }, + }, { + 'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753', + 'only_matching': True, + }, { + 'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/', + 'only_matching': True, + }] + + _TP_FEEDS = { + 'globaltv': { + 'feed_id': 'ChQqrem0lNUp', + 'account_id': 2269680845, + }, + 'etcanada': { + 'feed_id': 'ChQqrem0lNUp', + 'account_id': 2269680845, + }, + 'hgtv': { + 'feed_id': 'L0BMHXi2no43', + 'account_id': 2414428465, + }, + 'foodnetwork': { + 'feed_id': 'ukK8o58zbRmJ', + 'account_id': 2414429569, + }, + 'slice': { + 'feed_id': '5tUJLgV2YNJ5', + 'account_id': 2414427935, + }, + } + + def _real_extract(self, url): + domain, video_id = re.match(self._VALID_URL, url).groups() + feed_info = self._TP_FEEDS[domain.split('.')[0]] + return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: { + 'episode_number': int_or_none(e.get('pl1$episode')), + 'season_number': int_or_none(e.get('pl1$season')), + 'series': e.get('pl1$show'), + }, { + 'HLS': { + 'manifest': 'm3u', + }, + 'DesktopHLS Default': { + 'manifest': 'm3u', + }, + 'MP4 MBR': { + 'manifest': 'm3u', + }, + }, feed_info['account_id']) diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index 377fb45..f919ed2 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -6,6 +6,7 @@ from ..utils import int_or_none class CrackleIE(InfoExtractor): + _GEO_COUNTRIES = ['US'] _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)' _TEST = { 'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934', diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 109d1c5..a1fc6a7 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -123,7 +123,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { 'id': '645513', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!', 'description': 'md5:2d17137920c64f2f49981a7797d275ef', 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', @@ -192,6 +192,21 @@ class CrunchyrollIE(CrunchyrollBaseIE): # geo-restricted (US), 18+ maturity wall, non-premium available 'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617', 'only_matching': True, + }, { + # A description with double quotes + 'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080', + 'info_dict': { + 'id': '535080', + 'ext': 'mp4', + 'title': '11eyes Episode 1 – Piros éjszaka - Red Night', + 'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".', + 'uploader': 'Marvelous AQL Inc.', + 'upload_date': '20091021', + }, + 'params': { + # Just test metadata extraction + 'skip_download': True, + }, }] _FORMAT_IDS = { @@ -362,9 +377,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>', webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) - video_description = self._html_search_regex( - r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id, - webpage, 'description', default=None) + video_description = self._parse_json(self._html_search_regex( + r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id, + webpage, 'description', default='{}'), video_id).get('description') if video_description: video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_upload_date = self._html_search_regex( @@ -519,11 +534,11 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>', webpage, 'title') episode_paths = re.findall( - r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"', + r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"', webpage) entries = [ - self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll') - for ep in episode_paths + self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id) + for ep_id, ep in episode_paths ] entries.reverse() diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 31bf5fa..b312401 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -66,7 +66,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'uploader_id': 'xijv66', 'age_limit': 0, 'view_count': int, - 'comment_count': int, } }, # Vevo video @@ -140,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): view_count = str_to_int(view_count_str) comment_count = int_or_none(self._search_regex( r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"', - webpage, 'comment count', fatal=False)) + webpage, 'comment count', default=None)) player_v5 = self._search_regex( [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826 diff --git a/youtube_dl/extractor/disney.py b/youtube_dl/extractor/disney.py index 396873c..939d133 100644 --- a/youtube_dl/extractor/disney.py +++ b/youtube_dl/extractor/disney.py @@ -9,13 +9,15 @@ from ..utils import ( unified_strdate, compat_str, determine_ext, + ExtractorError, ) class DisneyIE(InfoExtractor): _VALID_URL = r'''(?x) - https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})''' + https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})|(?:[^/]+/)?(?P<display_id>[^/?#]+))''' _TESTS = [{ + # Disney.EmbedVideo 'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977', 'info_dict': { 'id': '545ed1857afee5a0ec239977', @@ -29,6 +31,20 @@ class DisneyIE(InfoExtractor): 'skip_download': True, } }, { + # Grill.burger + 'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette', + 'info_dict': { + 'id': '5454e9f4e9804a552e3524c8', + 'ext': 'mp4', + 'title': '"Intro" Featurette: Rogue One: A Star Wars Story', + 'upload_date': '20170104', + 'description': 'Go behind-the-scenes of Rogue One: A Star Wars Story in this featurette with Director Gareth Edwards and the cast of the film.', + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + }, { 'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2', 'only_matching': True, }, { @@ -43,31 +59,55 @@ class DisneyIE(InfoExtractor): }, { 'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097', 'only_matching': True, + }, { + 'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677', + 'only_matching': True, + }, { + 'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1', + 'only_matching': True, + }, { + 'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo', + 'only_matching': True, + }, { + 'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue', + 'only_matching': True, }] def _real_extract(self, url): - domain, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage( - 'http://%s/embed/%s' % (domain, video_id), video_id) - video_data = self._parse_json(self._search_regex( - r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video'] + domain, video_id, display_id = re.match(self._VALID_URL, url).groups() + if not video_id: + webpage = self._download_webpage(url, display_id) + grill = re.sub(r'"\s*\+\s*"', '', self._search_regex( + r'Grill\.burger\s*=\s*({.+})\s*:', + webpage, 'grill data')) + page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video') + video_data = page_data['data'][0] + else: + webpage = self._download_webpage( + 'http://%s/embed/%s' % (domain, video_id), video_id) + page_data = self._parse_json(self._search_regex( + r'Disney\.EmbedVideo\s*=\s*({.+});', + webpage, 'embed data'), video_id) + video_data = page_data['video'] for external in video_data.get('externals', []): if external.get('source') == 'vevo': return self.url_result('vevo:' + external['data_id'], 'Vevo') + video_id = video_data['id'] title = video_data['title'] formats = [] for flavor in video_data.get('flavors', []): flavor_format = flavor.get('format') flavor_url = flavor.get('url') - if not flavor_url or not re.match(r'https?://', flavor_url): + if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access': continue tbr = int_or_none(flavor.get('bitrate')) if tbr == 99999: formats.extend(self._extract_m3u8_formats( - flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False)) + flavor_url, video_id, 'mp4', + m3u8_id=flavor_format, fatal=False)) continue format_id = [] if flavor_format: @@ -88,6 +128,10 @@ class DisneyIE(InfoExtractor): 'ext': ext, 'vcodec': 'none' if (width == 0 and height == 0) else None, }) + if not formats and video_data.get('expired'): + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']), + expected=True) self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index bcd9fe2..e7abc88 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -20,6 +20,7 @@ from ..utils import ( class DramaFeverBaseIE(AMPIE): _LOGIN_URL = 'https://www.dramafever.com/accounts/login/' _NETRC_MACHINE = 'dramafever' + _GEO_COUNTRIES = ['US', 'CA'] _CONSUMER_SECRET = 'DA59dtVXYLxajktV' @@ -116,8 +117,9 @@ class DramaFeverIE(DramaFeverBaseIE): 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError): - raise ExtractorError( - 'Currently unavailable in your country.', expected=True) + self.raise_geo_restricted( + msg='Currently unavailable in your country', + countries=self._GEO_COUNTRIES) raise series_id, episode_number = video_id.split('.') diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py index 6ca07a1..3f62686 100644 --- a/youtube_dl/extractor/einthusan.py +++ b/youtube_dl/extractor/einthusan.py @@ -1,67 +1,97 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 +import json + from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_str, +) from ..utils import ( - remove_start, - sanitized_Request, + extract_attributes, + ExtractorError, + get_elements_by_class, + urlencode_postdata, ) class EinthusanIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)' - _TESTS = [ - { - 'url': 'http://www.einthusan.com/movies/watch.php?id=2447', - 'md5': 'd71379996ff5b7f217eca034c34e3461', - 'info_dict': { - 'id': '2447', - 'ext': 'mp4', - 'title': 'Ek Villain', - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': 'md5:9d29fc91a7abadd4591fb862fa560d93', - } - }, - { - 'url': 'http://www.einthusan.com/movies/watch.php?id=1671', - 'md5': 'b16a6fd3c67c06eb7c79c8a8615f4213', - 'info_dict': { - 'id': '1671', - 'ext': 'mp4', - 'title': 'Soodhu Kavvuum', - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': 'md5:b40f2bf7320b4f9414f3780817b2af8c', - } - }, - ] + _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://einthusan.tv/movie/watch/9097/', + 'md5': 'ff0f7f2065031b8a2cf13a933731c035', + 'info_dict': { + 'id': '9097', + 'ext': 'mp4', + 'title': 'Ae Dil Hai Mushkil', + 'description': 'md5:33ef934c82a671a94652a9b4e54d931b', + 'thumbnail': r're:^https?://.*\.jpg$', + } + }, { + 'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi', + 'only_matching': True, + }] + + # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js + def _decrypt(self, encrypted_data, video_id): + return self._parse_json(base64.b64decode(( + encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1] + ).encode('ascii')).decode('utf-8'), video_id) def _real_extract(self, url): video_id = self._match_id(url) - request = sanitized_Request(url) - request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0') - webpage = self._download_webpage(request, video_id) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title') + + player_params = extract_attributes(self._search_regex( + r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters')) + + page_id = self._html_search_regex( + '<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID') + video_data = self._download_json( + 'https://einthusan.tv/ajax/movie/watch/%s/' % video_id, video_id, + data=urlencode_postdata({ + 'xEvent': 'UIVideoPlayer.PingOutcome', + 'xJson': json.dumps({ + 'EJOutcomes': player_params['data-ejpingables'], + 'NativeHLS': False + }), + 'arcVersion': 3, + 'appVersion': 59, + 'gorilla.csrf.Token': page_id, + }))['Data'] + + if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'): + raise ExtractorError( + 'Download rate reached. Please try again later.', expected=True) + + ej_links = self._decrypt(video_data['EJLinks'], video_id) + + formats = [] - title = self._html_search_regex( - r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>', - webpage, 'title') + m3u8_url = ej_links.get('HLSLink') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native')) - video_id = self._search_regex( - r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id) + mp4_url = ej_links.get('MP4Link') + if mp4_url: + formats.append({ + 'url': mp4_url, + }) - m3u8_url = self._download_webpage( - 'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/' - % video_id, video_id, headers={'Referer': url}) - formats = self._extract_m3u8_formats( - m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native') + self._sort_formats(formats) - description = self._html_search_meta('description', webpage) + description = get_elements_by_class('synopsis', webpage)[0] thumbnail = self._html_search_regex( - r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', - webpage, "thumbnail url", fatal=False) + r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''', + webpage, 'thumbnail url', fatal=False, group='url') if thumbnail is not None: - thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..')) + thumbnail = compat_urlparse.urljoin(url, thumbnail) return { 'id': video_id, diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py index 74bbc5c..e0a13dd 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -1,13 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import json - from .common import InfoExtractor -from ..utils import ( - ExtractorError, - NO_DEFAULT, -) +from .kaltura import KalturaIE +from ..utils import NO_DEFAULT class EllenTVIE(InfoExtractor): @@ -65,7 +61,7 @@ class EllenTVIE(InfoExtractor): if partner_id and kaltura_id: break - return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura') + return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key()) class EllenTVClipsIE(InfoExtractor): @@ -77,14 +73,14 @@ class EllenTVClipsIE(InfoExtractor): 'id': 'meryl-streep-vanessa-hudgens', 'title': 'Meryl Streep, Vanessa Hudgens', }, - 'playlist_mincount': 7, + 'playlist_mincount': 5, } def _real_extract(self, url): playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) - playlist = self._extract_playlist(webpage) + playlist = self._extract_playlist(webpage, playlist_id) return { '_type': 'playlist', @@ -93,16 +89,13 @@ class EllenTVClipsIE(InfoExtractor): 'entries': self._extract_entries(playlist) } - def _extract_playlist(self, webpage): + def _extract_playlist(self, webpage, playlist_id): json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') - try: - return json.loads('[{' + json_string + '}]') - except ValueError as ve: - raise ExtractorError('Failed to download JSON', cause=ve) + return self._parse_json('[{' + json_string + '}]', playlist_id) def _extract_entries(self, playlist): return [ self.url_result( 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']), - 'Kaltura') + KalturaIE.ie_key(), video_id=item['kaltura_entry_id']) for item in playlist] diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py index 99e00cf..b89f6db 100644 --- a/youtube_dl/extractor/elpais.py +++ b/youtube_dl/extractor/elpais.py @@ -39,6 +39,18 @@ class ElPaisIE(InfoExtractor): 'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas', 'upload_date': '20170127', }, + }, { + 'url': 'http://epv.elpais.com/epv/2017/02/14/programa_la_voz_de_inaki/1487062137_075943.html', + 'info_dict': { + 'id': '1487062137_075943', + 'ext': 'mp4', + 'title': 'Disyuntivas', + 'description': 'md5:a0fb1485c4a6a8a917e6f93878e66218', + 'upload_date': '20170214', + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -59,14 +71,15 @@ class ElPaisIE(InfoExtractor): video_url = prefix + video_suffix thumbnail_suffix = self._search_regex( r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", - webpage, 'thumbnail URL', fatal=False) + webpage, 'thumbnail URL', default=None) thumbnail = ( None if thumbnail_suffix is None - else prefix + thumbnail_suffix) + else prefix + thumbnail_suffix) or self._og_search_thumbnail(webpage) title = self._html_search_regex( - (r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title', - r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'), - webpage, 'title') + (r"tituloVideo\s*=\s*'([^']+)'", + r'<h2 class="entry-header entry-title.*?>(.*?)</h2>', + r'<h1[^>]+class="titulo"[^>]*>([^<]+)'), + webpage, 'title', default=None) or self._og_search_title(webpage) upload_date = unified_strdate(self._search_regex( r'<p class="date-header date-int updated"\s+title="([^"]+)">', webpage, 'upload date', default=None) or self._html_search_meta( diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 12cda36..83a170f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -202,6 +202,7 @@ from .commonprotocols import ( RtmpIE, ) from .condenast import CondeNastIE +from .corus import CorusIE from .cracked import CrackedIE from .crackle import CrackleIE from .criterion import CriterionIE @@ -381,10 +382,7 @@ from .heise import HeiseIE from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE -from .hgtv import ( - HGTVIE, - HGTVComShowIE, -) +from .hgtv import HGTVComShowIE from .historicfilms import HistoricFilmsIE from .hitbox import HitboxIE, HitboxLiveIE from .hitrecord import HitRecordIE @@ -696,6 +694,8 @@ from .ondemandkorea import OnDemandKoreaIE from .onet import ( OnetIE, OnetChannelIE, + OnetMVPIE, + OnetPlIE, ) from .onionstudios import OnionStudiosIE from .ooyala import ( @@ -838,6 +838,7 @@ from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE +from .scrippsnetworks import ScrippsNetworksWatchIE from .seeker import SeekerIE from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE @@ -851,6 +852,7 @@ from .shared import ( from .showroomlive import ShowRoomLiveIE from .sina import SinaIE from .sixplay import SixPlayIE +from .skylinewebcams import SkylineWebcamsIE from .skynewsarabia import ( SkyNewsArabiaIE, SkyNewsArabiaArticleIE, @@ -895,6 +897,7 @@ from .sport5 import Sport5IE from .sportbox import SportBoxEmbedIE from .sportdeutschland import SportDeutschlandIE from .sportschau import SportschauIE +from .sprout import SproutIE from .srgssr import ( SRGSSRIE, SRGSSRPlayIE, @@ -1007,6 +1010,7 @@ from .tvc import ( ) from .tvigle import TvigleIE from .tvland import TVLandIE +from .tvn24 import TVN24IE from .tvnoe import TVNoeIE from .tvp import ( TVPEmbedIE, @@ -1017,6 +1021,7 @@ from .tvplay import ( TVPlayIE, ViafreeIE, ) +from .tvplayer import TVPlayerIE from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twentymin import TwentyMinutenIE @@ -1146,6 +1151,7 @@ from .vlive import ( VLiveChannelIE ) from .vodlocker import VodlockerIE +from .vodpl import VODPlIE from .vodplatform import VODPlatformIE from .voicerepublic import VoiceRepublicIE from .voxmedia import VoxMediaIE diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index b325c82..70b8c95 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -135,6 +136,46 @@ class FacebookIE(InfoExtractor): 'uploader': 'CNN', }, }, { + # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall + 'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/', + 'info_dict': { + 'id': '1417995061575415', + 'ext': 'mp4', + 'title': 'md5:a7b86ca673f51800cd54687b7f4012fe', + 'timestamp': 1486648217, + 'upload_date': '20170209', + 'uploader': 'Yaroslav Korpan', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471', + 'info_dict': { + 'id': '1072691702860471', + 'ext': 'mp4', + 'title': 'md5:ae2d22a93fbb12dad20dc393a869739d', + 'timestamp': 1477305000, + 'upload_date': '20161024', + 'uploader': 'La Guía Del Varón', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/', + 'info_dict': { + 'id': '1396382447100162', + 'ext': 'mp4', + 'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3', + 'timestamp': 1486035494, + 'upload_date': '20170202', + 'uploader': 'Elisabeth Ahtn', + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, }, { @@ -249,7 +290,7 @@ class FacebookIE(InfoExtractor): for item in instances: if item[1][0] == 'VideoConfig': video_item = item[2][0] - if video_item.get('video_id') == video_id: + if video_item.get('video_id'): return video_item['videoData'] server_js_data = self._parse_json(self._search_regex( @@ -262,7 +303,7 @@ class FacebookIE(InfoExtractor): if not video_data: server_js_data = self._parse_json( self._search_regex( - r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet', + r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall)', webpage, 'js data', default='{}'), video_id, transform_source=js_to_json, fatal=False) if server_js_data: diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 1c233f0..9868ca6 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -20,6 +20,7 @@ from ..utils import ( float_or_none, HEADRequest, is_html, + js_to_json, orderedSet, sanitized_Request, smuggle_url, @@ -961,6 +962,16 @@ class GenericIE(InfoExtractor): 'skip_download': True, } }, + # Complex jwplayer + { + 'url': 'http://www.indiedb.com/games/king-machine/videos', + 'info_dict': { + 'id': 'videos', + 'ext': 'mp4', + 'title': 'king machine trailer 1', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + }, # rtl.nl embed { 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen', @@ -991,19 +1002,6 @@ class GenericIE(InfoExtractor): 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', }, }, - # Kaltura embed protected with referrer - { - 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero', - 'info_dict': { - 'id': '1_g4fbemnq', - 'ext': 'mp4', - 'title': 'Violetta - Achter De Schermen - Ruggero', - 'description': 'Achter de schermen met Ruggero', - 'timestamp': 1435133761, - 'upload_date': '20150624', - 'uploader_id': 'echojecka', - }, - }, # Kaltura embed with single quotes { 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY', @@ -1503,7 +1501,12 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, 'add_ie': [VideoPressIE.ie_key()], - } + }, + { + # ThePlatform embedded with whitespaces in URLs + 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm', + 'only_matching': True, + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -2350,8 +2353,9 @@ class GenericIE(InfoExtractor): 'Channel': 'channel', 'ChannelList': 'channel_list', } - return self.url_result('limelight:%s:%s' % ( - lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) + return self.url_result(smuggle_url('limelight:%s:%s' % ( + lm[mobj.group(1)], mobj.group(2)), {'source_url': url}), + 'Limelight%s' % mobj.group(1), mobj.group(2)) mobj = re.search( r'''(?sx) @@ -2361,7 +2365,9 @@ class GenericIE(InfoExtractor): value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32}) ''', webpage) if mobj: - return self.url_result('limelight:media:%s' % mobj.group('id')) + return self.url_result(smuggle_url( + 'limelight:media:%s' % mobj.group('id'), + {'source_url': url}), 'LimelightMedia', mobj.group('id')) # Look for AdobeTVVideo embeds mobj = re.search( @@ -2498,6 +2504,15 @@ class GenericIE(InfoExtractor): self._sort_formats(entry['formats']) return self.playlist_result(entries) + jwplayer_data_str = self._find_jwplayer_data(webpage) + if jwplayer_data_str: + try: + jwplayer_data = self._parse_json( + jwplayer_data_str, video_id, transform_source=js_to_json) + return self._parse_jwplayer_data(jwplayer_data, video_id) + except ExtractorError: + pass + def check_video(vurl): if YoutubeIE.suitable(vurl): return True diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index a34779b..21ed846 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .adobepass import AdobePassIE from ..utils import ( int_or_none, determine_ext, @@ -13,15 +13,30 @@ from ..utils import ( ) -class GoIE(InfoExtractor): - _BRANDS = { - 'abc': '001', - 'freeform': '002', - 'watchdisneychannel': '004', - 'watchdisneyjunior': '008', - 'watchdisneyxd': '009', +class GoIE(AdobePassIE): + _SITE_INFO = { + 'abc': { + 'brand': '001', + 'requestor_id': 'ABC', + }, + 'freeform': { + 'brand': '002', + 'requestor_id': 'ABCFamily', + }, + 'watchdisneychannel': { + 'brand': '004', + 'requestor_id': 'Disney', + }, + 'watchdisneyjunior': { + 'brand': '008', + 'requestor_id': 'DisneyJunior', + }, + 'watchdisneyxd': { + 'brand': '009', + 'requestor_id': 'DisneyXD', + } } - _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys()) + _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys()) _TESTS = [{ 'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx', 'info_dict': { @@ -47,7 +62,8 @@ class GoIE(InfoExtractor): # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id') - brand = self._BRANDS[sub_domain] + site_info = self._SITE_INFO[sub_domain] + brand = site_info['brand'] video_data = self._download_json( 'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id), video_id)['video'][0] @@ -62,28 +78,60 @@ class GoIE(InfoExtractor): ext = determine_ext(asset_url) if ext == 'm3u8': video_type = video_data.get('type') - if video_type == 'lf': - entitlement = self._download_json( - 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json', - video_id, data=urlencode_postdata({ - 'video_id': video_data['id'], - 'video_type': video_type, - 'brand': brand, - 'device': '001', - })) - errors = entitlement.get('errors', {}).get('errors', []) - if errors: - error_message = ', '.join([error['message'] for error in errors]) - raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) - asset_url += '?' + entitlement['uplynkData']['sessionKey'] + data = { + 'video_id': video_data['id'], + 'video_type': video_type, + 'brand': brand, + 'device': '001', + } + if video_data.get('accesslevel') == '1': + requestor_id = site_info['requestor_id'] + resource = self._get_mvpd_resource( + requestor_id, title, video_id, None) + auth = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) + data.update({ + 'token': auth, + 'token_type': 'ap', + 'adobe_requestor_id': requestor_id, + }) + else: + self._initialize_geo_bypass(['US']) + entitlement = self._download_json( + 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json', + video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers()) + errors = entitlement.get('errors', {}).get('errors', []) + if errors: + for error in errors: + if error.get('code') == 1002: + self.raise_geo_restricted( + error['message'], countries=['US']) + error_message = ', '.join([error['message'] for error in errors]) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) + asset_url += '?' + entitlement['uplynkData']['sessionKey'] formats.extend(self._extract_m3u8_formats( asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)) else: - formats.append({ + f = { 'format_id': format_id, 'url': asset_url, 'ext': ext, - }) + } + if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url): + f.update({ + 'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE', + 'preference': 1, + }) + else: + mobj = re.search(r'/(\d+)x(\d+)/', asset_url) + if mobj: + height = int(mobj.group(2)) + f.update({ + 'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height, + 'width': int(mobj.group(1)), + 'height': height, + }) + formats.append(f) self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py index 1629cdb..382f327 100644 --- a/youtube_dl/extractor/heise.py +++ b/youtube_dl/extractor/heise.py @@ -6,59 +6,58 @@ from ..utils import ( determine_ext, int_or_none, parse_iso8601, + xpath_text, ) class HeiseIE(InfoExtractor): - _VALID_URL = r'''(?x) - https?://(?:www\.)?heise\.de/video/artikel/ - .+?(?P<id>[0-9]+)\.html(?:$|[?#]) - ''' - _TEST = { - 'url': ( - 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html' - ), + _VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html' + _TESTS = [{ + 'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html', 'md5': 'ffed432483e922e88545ad9f2f15d30e', 'info_dict': { 'id': '2404147', 'ext': 'mp4', - 'title': ( - "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone" - ), + 'title': "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone", 'format_id': 'mp4_720p', 'timestamp': 1411812600, 'upload_date': '20140927', - 'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.', - 'thumbnail': r're:^https?://.*\.jpe?g$', + 'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20', + 'thumbnail': r're:^https?://.*/gallery/$', } - } + }, { + 'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html', + 'only_matching': True, + }, { + 'url': 'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom', + 'only_matching': True, + }, { + 'url': 'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) container_id = self._search_regex( - r'<div class="videoplayerjw".*?data-container="([0-9]+)"', + r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"', webpage, 'container ID') sequenz_id = self._search_regex( - r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"', + r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"', webpage, 'sequenz ID') - data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id) - doc = self._download_xml(data_url, video_id) - info = { - 'id': video_id, - 'thumbnail': self._og_search_thumbnail(webpage), - 'timestamp': parse_iso8601( - self._html_search_meta('date', webpage)), - 'description': self._og_search_description(webpage), - } + title = self._html_search_meta('fulltitle', webpage, default=None) + if not title or title == "c't": + title = self._search_regex( + r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"', + webpage, 'title') - title = self._html_search_meta('fulltitle', webpage) - if title: - info['title'] = title - else: - info['title'] = self._og_search_title(webpage) + doc = self._download_xml( + 'http://www.heise.de/videout/feed', video_id, query={ + 'container': container_id, + 'sequenz': sequenz_id, + }) formats = [] for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'): @@ -74,6 +73,18 @@ class HeiseIE(InfoExtractor): 'height': height, }) self._sort_formats(formats) - info['formats'] = formats - return info + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'description', webpage) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or + self._og_search_thumbnail(webpage)), + 'timestamp': parse_iso8601( + self._html_search_meta('date', webpage)), + 'formats': formats, + } diff --git a/youtube_dl/extractor/hgtv.py b/youtube_dl/extractor/hgtv.py index 69543bf..e854300 100644 --- a/youtube_dl/extractor/hgtv.py +++ b/youtube_dl/extractor/hgtv.py @@ -2,50 +2,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - int_or_none, - js_to_json, - smuggle_url, -) - - -class HGTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html' - _TEST = { - 'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video', - 'md5': '', - 'info_dict': { - 'id': 'aFH__I_5FBOX', - 'ext': 'mp4', - 'title': 'Overnight Success', - 'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.', - 'uploader': 'SHWM-NEW', - 'timestamp': 1470320034, - 'upload_date': '20160804', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - embed_vars = self._parse_json(self._search_regex( - r'(?s)embed_vars\s*=\s*({.*?});', - webpage, 'embed vars'), display_id, js_to_json) - return { - '_type': 'url_transparent', - 'url': smuggle_url( - 'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], { - 'force_smil_url': True - }), - 'series': embed_vars.get('show'), - 'season_number': int_or_none(embed_vars.get('season')), - 'episode_number': int_or_none(embed_vars.get('episode')), - 'ie_key': 'ThePlatform', - } class HGTVComShowIE(InfoExtractor): diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index f05d765..3a7a66a 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -34,11 +34,9 @@ class HotStarIE(InfoExtractor): 'only_matching': True, }] - _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s' - _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s' - - def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True): - json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal) + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True, query=None): + json_data = super(HotStarIE, self)._download_json( + url_or_request, video_id, note, fatal=fatal, query=query) if json_data['resultCode'] != 'OK': if fatal: raise ExtractorError(json_data['errorDescription']) @@ -48,20 +46,37 @@ class HotStarIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) video_data = self._download_json( - self._GET_CONTENT_TEMPLATE % video_id, - video_id)['contentInfo'][0] + 'http://account.hotstar.com/AVS/besc', video_id, query={ + 'action': 'GetAggregatedContentDetails', + 'channel': 'PCTV', + 'contentId': video_id, + })['contentInfo'][0] + title = video_data['episodeTitle'] + + if video_data.get('encrypted') == 'Y': + raise ExtractorError('This video is DRM protected.', expected=True) formats = [] - # PCTV for extracting f4m manifest - for f in ('TABLET',): + for f in ('JIO',): format_data = self._download_json( - self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'), - video_id, 'Downloading %s JSON metadata' % f, fatal=False) + 'http://getcdn.hotstar.com/AVS/besc', + video_id, 'Downloading %s JSON metadata' % f, + fatal=False, query={ + 'action': 'GetCDN', + 'asJson': 'Y', + 'channel': f, + 'id': video_id, + 'type': 'VOD', + }) if format_data: - format_url = format_data['src'] + format_url = format_data.get('src') + if not format_url: + continue ext = determine_ext(format_url) if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', + m3u8_id='hls', fatal=False)) elif ext == 'f4m': # produce broken files continue @@ -75,9 +90,12 @@ class HotStarIE(InfoExtractor): return { 'id': video_id, - 'title': video_data['episodeTitle'], + 'title': title, 'description': video_data.get('description'), 'duration': int_or_none(video_data.get('duration')), 'timestamp': int_or_none(video_data.get('broadcastDate')), 'formats': formats, + 'episode': title, + 'episode_number': int_or_none(video_data.get('episodeNumber')), + 'series': video_data.get('contentTitle'), } diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 98f408c..c1921cb 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( get_element_by_attribute, int_or_none, @@ -51,6 +52,33 @@ class InstagramIE(InfoExtractor): 'skip_download': True, }, }, { + # multi video post + 'url': 'https://www.instagram.com/p/BQ0eAlwhDrw/', + 'playlist': [{ + 'info_dict': { + 'id': 'BQ0dSaohpPW', + 'ext': 'mp4', + 'title': 'Video 1', + }, + }, { + 'info_dict': { + 'id': 'BQ0dTpOhuHT', + 'ext': 'mp4', + 'title': 'Video 2', + }, + }, { + 'info_dict': { + 'id': 'BQ0dT7RBFeF', + 'ext': 'mp4', + 'title': 'Video 3', + }, + }], + 'info_dict': { + 'id': 'BQ0eAlwhDrw', + 'title': 'Post by instagram', + 'description': 'md5:0f9203fc6a2ce4d228da5754bcf54957', + }, + }, { 'url': 'https://instagram.com/p/-Cmh1cukG2/', 'only_matching': True, }, { @@ -113,6 +141,32 @@ class InstagramIE(InfoExtractor): 'timestamp': int_or_none(comment.get('created_at')), } for comment in media.get( 'comments', {}).get('nodes', []) if comment.get('text')] + if not video_url: + edges = try_get( + media, lambda x: x['edge_sidecar_to_children']['edges'], + list) or [] + if edges: + entries = [] + for edge_num, edge in enumerate(edges, start=1): + node = try_get(edge, lambda x: x['node'], dict) + if not node: + continue + node_video_url = try_get(node, lambda x: x['video_url'], compat_str) + if not node_video_url: + continue + entries.append({ + 'id': node.get('shortcode') or node['id'], + 'title': 'Video %d' % edge_num, + 'url': node_video_url, + 'thumbnail': node.get('display_url'), + 'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])), + 'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])), + 'view_count': int_or_none(node.get('video_view_count')), + }) + return self.playlist_result( + entries, video_id, + 'Post by %s' % uploader_id if uploader_id else None, + description) if not video_url: video_url = self._og_search_video_url(webpage, secure=False) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 0fe5768..a29e6a5 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -8,12 +8,12 @@ from .common import InfoExtractor from ..utils import ( determine_ext, js_to_json, - sanitized_Request, ) class IPrimaIE(InfoExtractor): _VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)' + _GEO_BYPASS = False _TESTS = [{ 'url': 'http://play.iprima.cz/gondici-s-r-o-33', @@ -29,6 +29,10 @@ class IPrimaIE(InfoExtractor): }, { 'url': 'http://play.iprima.cz/particka/particka-92', 'only_matching': True, + }, { + # geo restricted + 'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1', + 'only_matching': True, }] def _real_extract(self, url): @@ -38,11 +42,13 @@ class IPrimaIE(InfoExtractor): video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id') - req = sanitized_Request( - 'http://play.iprima.cz/prehravac/init?_infuse=1' - '&_ts=%s&productId=%s' % (round(time.time()), video_id)) - req.add_header('Referer', url) - playerpage = self._download_webpage(req, video_id, note='Downloading player') + playerpage = self._download_webpage( + 'http://play.iprima.cz/prehravac/init', + video_id, note='Downloading player', query={ + '_infuse': 1, + '_ts': round(time.time()), + 'productId': video_id, + }, headers={'Referer': url}) formats = [] @@ -82,7 +88,7 @@ class IPrimaIE(InfoExtractor): extract_formats(src) if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage: - self.raise_geo_restricted() + self.raise_geo_restricted(countries=['CZ']) self._sort_formats(formats) diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index 01c7b30..2af6a6d 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -173,11 +173,12 @@ class IqiyiIE(InfoExtractor): } }, { 'url': 'http://www.iqiyi.com/v_19rrhnnclk.html', - 'md5': '667171934041350c5de3f5015f7f1152', + 'md5': 'b7dc800a4004b1b57749d9abae0472da', 'info_dict': { 'id': 'e3f585b550a280af23c98b6cb2be19fb', 'ext': 'mp4', - 'title': '名侦探柯南 国语版:第752集 迫近灰原秘密的黑影 下篇', + # This can be either Simplified Chinese or Traditional Chinese + 'title': r're:^(?:名侦探柯南 国语版:第752集 迫近灰原秘密的黑影 下篇|名偵探柯南 國語版:第752集 迫近灰原秘密的黑影 下篇)$', }, 'skip': 'Geo-restricted to China', }, { diff --git a/youtube_dl/extractor/itv.py b/youtube_dl/extractor/itv.py index b0d8604..021c6b2 100644 --- a/youtube_dl/extractor/itv.py +++ b/youtube_dl/extractor/itv.py @@ -24,6 +24,7 @@ from ..utils import ( class ITVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)' + _GEO_COUNTRIES = ['GB'] _TEST = { 'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053', 'info_dict': { @@ -98,7 +99,11 @@ class ITVIE(InfoExtractor): headers=headers, data=etree.tostring(req_env)) playlist = xpath_element(resp_env, './/Playlist') if playlist is None: + fault_code = xpath_text(resp_env, './/faultcode') fault_string = xpath_text(resp_env, './/faultstring') + if fault_code == 'InvalidGeoRegion': + self.raise_geo_restricted( + msg=fault_string, countries=self._GEO_COUNTRIES) raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string)) title = xpath_text(playlist, 'EpisodeTitle', fatal=True) video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 3d3c150..cb51cef 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -16,6 +16,8 @@ class IviIE(InfoExtractor): IE_DESC = 'ivi.ru' IE_NAME = 'ivi' _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' + _GEO_BYPASS = False + _GEO_COUNTRIES = ['RU'] _TESTS = [ # Single movie @@ -91,7 +93,11 @@ class IviIE(InfoExtractor): if 'error' in video_json: error = video_json['error'] - if error['origin'] == 'NoRedisValidData': + origin = error['origin'] + if origin == 'NotAllowedForLocation': + self.raise_geo_restricted( + msg=error['message'], countries=self._GEO_COUNTRIES) + elif origin == 'NoRedisValidData': raise ExtractorError('Video %s does not exist' % video_id, expected=True) raise ExtractorError( 'Unable to download video %s: %s' % (video_id, error['message']), diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index aff7ab4..33d55f7 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -4,139 +4,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse -from ..utils import ( - determine_ext, - float_or_none, - int_or_none, - js_to_json, - mimetype2ext, - urljoin, -) -class JWPlatformBaseIE(InfoExtractor): - @staticmethod - def _find_jwplayer_data(webpage): - # TODO: Merge this with JWPlayer-related codes in generic.py - - mobj = re.search( - r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)', - webpage) - if mobj: - return mobj.group('options') - - def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs): - jwplayer_data = self._parse_json( - self._find_jwplayer_data(webpage), video_id, - transform_source=js_to_json) - return self._parse_jwplayer_data( - jwplayer_data, video_id, *args, **kwargs) - - def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, - m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None): - # JWPlayer backward compatibility: flattened playlists - # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96 - if 'playlist' not in jwplayer_data: - jwplayer_data = {'playlist': [jwplayer_data]} - - entries = [] - - # JWPlayer backward compatibility: single playlist item - # https://github.com/jwplayer/jwplayer/blob/v7.7.0/src/js/playlist/playlist.js#L10 - if not isinstance(jwplayer_data['playlist'], list): - jwplayer_data['playlist'] = [jwplayer_data['playlist']] - - for video_data in jwplayer_data['playlist']: - # JWPlayer backward compatibility: flattened sources - # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35 - if 'sources' not in video_data: - video_data['sources'] = [video_data] - - this_video_id = video_id or video_data['mediaid'] - - formats = [] - for source in video_data['sources']: - source_url = self._proto_relative_url(source['file']) - if base_url: - source_url = compat_urlparse.urljoin(base_url, source_url) - source_type = source.get('type') or '' - ext = mimetype2ext(source_type) or determine_ext(source_url) - if source_type == 'hls' or ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False)) - elif ext == 'mpd': - formats.extend(self._extract_mpd_formats( - source_url, this_video_id, mpd_id=mpd_id, fatal=False)) - # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67 - elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'): - formats.append({ - 'url': source_url, - 'vcodec': 'none', - 'ext': ext, - }) - else: - height = int_or_none(source.get('height')) - if height is None: - # Often no height is provided but there is a label in - # format like 1080p. - height = int_or_none(self._search_regex( - r'^(\d{3,})[pP]$', source.get('label') or '', - 'height', default=None)) - a_format = { - 'url': source_url, - 'width': int_or_none(source.get('width')), - 'height': height, - 'ext': ext, - } - if source_url.startswith('rtmp'): - a_format['ext'] = 'flv' - - # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as - # of jwplayer.flash.swf - rtmp_url_parts = re.split( - r'((?:mp4|mp3|flv):)', source_url, 1) - if len(rtmp_url_parts) == 3: - rtmp_url, prefix, play_path = rtmp_url_parts - a_format.update({ - 'url': rtmp_url, - 'play_path': prefix + play_path, - }) - if rtmp_params: - a_format.update(rtmp_params) - formats.append(a_format) - self._sort_formats(formats) - - subtitles = {} - tracks = video_data.get('tracks') - if tracks and isinstance(tracks, list): - for track in tracks: - if track.get('kind') != 'captions': - continue - track_url = urljoin(base_url, track.get('file')) - if not track_url: - continue - subtitles.setdefault(track.get('label') or 'en', []).append({ - 'url': self._proto_relative_url(track_url) - }) - - entries.append({ - 'id': this_video_id, - 'title': video_data['title'] if require_title else video_data.get('title'), - 'description': video_data.get('description'), - 'thumbnail': self._proto_relative_url(video_data.get('image')), - 'timestamp': int_or_none(video_data.get('pubdate')), - 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), - 'subtitles': subtitles, - 'formats': formats, - }) - if len(entries) == 1: - return entries[0] - else: - return self.playlist_result(entries) - - -class JWPlatformIE(JWPlatformBaseIE): +class JWPlatformIE(InfoExtractor): _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' _TEST = { 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 5ef382f..54374ea 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -23,11 +23,11 @@ class KalturaIE(InfoExtractor): (?: kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)| https?:// - (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/ + (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/ (?: (?: # flash player - index\.php/kwidget| + index\.php/(?:kwidget|extwidget/preview)| # html5 player html5/html5lib/[^/]+/mwEmbedFrame\.php ) @@ -94,6 +94,14 @@ class KalturaIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, + { + 'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto', + 'only_matching': True, + }, + { + 'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto', + 'only_matching': True, } ] @@ -112,7 +120,7 @@ class KalturaIE(InfoExtractor): re.search( r'''(?xs) (?P<q1>["\']) - (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/(?:(?!(?P=q1)).)*(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)* + (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)* (?P=q1).*? (?: entry_?[Ii]d| @@ -209,6 +217,8 @@ class KalturaIE(InfoExtractor): partner_id = params['wid'][0][1:] elif 'p' in params: partner_id = params['p'][0] + elif 'partner_id' in params: + partner_id = params['partner_id'][0] else: raise ExtractorError('Invalid URL', expected=True) if 'entry_id' in params: diff --git a/youtube_dl/extractor/leeco.py b/youtube_dl/extractor/leeco.py index 4321f90..9eda956 100644 --- a/youtube_dl/extractor/leeco.py +++ b/youtube_dl/extractor/leeco.py @@ -30,7 +30,7 @@ from ..utils import ( class LeIE(InfoExtractor): IE_DESC = '乐视网' _VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|(?:sports\.le|(?:www\.)?lesports)\.com/(?:match|video))/(?P<id>\d+)\.html' - + _GEO_COUNTRIES = ['CN'] _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html' _TESTS = [{ @@ -126,10 +126,9 @@ class LeIE(InfoExtractor): if playstatus['status'] == 0: flag = playstatus['flag'] if flag == 1: - msg = 'Country %s auth error' % playstatus['country'] + self.raise_geo_restricted() else: - msg = 'Generic error. flag = %d' % flag - raise ExtractorError(msg, expected=True) + raise ExtractorError('Generic error. flag = %d' % flag, expected=True) def _real_extract(self, url): media_id = self._match_id(url) diff --git a/youtube_dl/extractor/lemonde.py b/youtube_dl/extractor/lemonde.py index 42568f3..3306892 100644 --- a/youtube_dl/extractor/lemonde.py +++ b/youtube_dl/extractor/lemonde.py @@ -7,20 +7,40 @@ class LemondeIE(InfoExtractor): _VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P<id>[^/]+)\.html' _TESTS = [{ 'url': 'http://www.lemonde.fr/police-justice/video/2016/01/19/comprendre-l-affaire-bygmalion-en-cinq-minutes_4849702_1653578.html', - 'md5': '01fb3c92de4c12c573343d63e163d302', + 'md5': 'da120c8722d8632eec6ced937536cc98', 'info_dict': { 'id': 'lqm3kl', 'ext': 'mp4', 'title': "Comprendre l'affaire Bygmalion en 5 minutes", 'thumbnail': r're:^https?://.*\.jpg', - 'duration': 320, + 'duration': 309, 'upload_date': '20160119', 'timestamp': 1453194778, 'uploader_id': '3pmkp', }, }, { + # standard iframe embed + 'url': 'http://www.lemonde.fr/les-decodeurs/article/2016/10/18/tout-comprendre-du-ceta-le-petit-cousin-du-traite-transatlantique_5015920_4355770.html', + 'info_dict': { + 'id': 'uzsxms', + 'ext': 'mp4', + 'title': "CETA : quelles suites pour l'accord commercial entre l'Europe et le Canada ?", + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 325, + 'upload_date': '20161021', + 'timestamp': 1477044540, + 'uploader_id': '3pmkp', + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html', 'only_matching': True, + }, { + # YouTube embeds + 'url': 'http://www.lemonde.fr/pixels/article/2016/12/09/pourquoi-pewdiepie-superstar-de-youtube-a-menace-de-fermer-sa-chaine_5046649_4408996.html', + 'only_matching': True, }] def _real_extract(self, url): @@ -30,5 +50,9 @@ class LemondeIE(InfoExtractor): digiteka_url = self._proto_relative_url(self._search_regex( r'url\s*:\s*(["\'])(?P<url>(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1', - webpage, 'digiteka url', group='url')) - return self.url_result(digiteka_url, 'Digiteka') + webpage, 'digiteka url', group='url', default=None)) + + if digiteka_url: + return self.url_result(digiteka_url, 'Digiteka') + + return self.url_result(url, 'Generic') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index e635f3c..422be25 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -4,10 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, float_or_none, int_or_none, + unsmuggle_url, + ExtractorError, ) @@ -15,20 +18,31 @@ class LimelightBaseIE(InfoExtractor): _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' - def _call_playlist_service(self, item_id, method, fatal=True): - return self._download_json( - self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal) + def _call_playlist_service(self, item_id, method, fatal=True, referer=None): + headers = {} + if referer: + headers['Referer'] = referer + try: + return self._download_json( + self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), + item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] + if error == 'CountryDisabled': + self.raise_geo_restricted() + raise ExtractorError(error, expected=True) + raise def _call_api(self, organization_id, item_id, method): return self._download_json( self._API_URL % (organization_id, self._API_PATH, item_id, method), item_id, 'Downloading API %s JSON' % method) - def _extract(self, item_id, pc_method, mobile_method, meta_method): - pc = self._call_playlist_service(item_id, pc_method) + def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None): + pc = self._call_playlist_service(item_id, pc_method, referer=referer) metadata = self._call_api(pc['orgId'], item_id, meta_method) - mobile = self._call_playlist_service(item_id, mobile_method, fatal=False) + mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) return pc, mobile, metadata def _extract_info(self, streams, mobile_urls, properties): @@ -207,10 +221,14 @@ class LimelightMediaIE(LimelightBaseIE): _API_PATH = 'media' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) + self._initialize_geo_bypass(smuggled_data.get('geo_countries')) pc, mobile, metadata = self._extract( - video_id, 'getPlaylistByMediaId', 'getMobilePlaylistByMediaId', 'properties') + video_id, 'getPlaylistByMediaId', + 'getMobilePlaylistByMediaId', 'properties', + smuggled_data.get('source_url')) return self._extract_info( pc['playlistItems'][0].get('streams', []), @@ -247,11 +265,13 @@ class LimelightChannelIE(LimelightBaseIE): _API_PATH = 'channels' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) channel_id = self._match_id(url) pc, mobile, medias = self._extract( channel_id, 'getPlaylistByChannelId', - 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'media') + 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', + 'media', smuggled_data.get('source_url')) entries = [ self._extract_info( diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index da94eab..d2f7529 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -260,9 +260,24 @@ class LyndaCourseIE(LyndaBaseIE): course_path = mobj.group('coursepath') course_id = mobj.group('courseid') + item_template = 'https://www.lynda.com/%s/%%s-4.html' % course_path + course = self._download_json( 'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id, - course_id, 'Downloading course JSON') + course_id, 'Downloading course JSON', fatal=False) + + if not course: + webpage = self._download_webpage(url, course_id) + entries = [ + self.url_result( + item_template % video_id, ie=LyndaIE.ie_key(), + video_id=video_id) + for video_id in re.findall( + r'data-video-id=["\'](\d+)', webpage)] + return self.playlist_result( + entries, course_id, + self._og_search_title(webpage, fatal=False), + self._og_search_description(webpage)) if course.get('Status') == 'NotFound': raise ExtractorError( @@ -283,7 +298,7 @@ class LyndaCourseIE(LyndaBaseIE): if video_id: entries.append({ '_type': 'url_transparent', - 'url': 'https://www.lynda.com/%s/%s-4.html' % (course_path, video_id), + 'url': item_template % video_id, 'ie_key': LyndaIE.ie_key(), 'chapter': chapter.get('Title'), 'chapter_number': int_or_none(chapter.get('ChapterIndex')), diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 9880924..28f59f6 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -6,12 +6,12 @@ from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urllib_parse_unquote, + compat_urllib_parse_urlencode, ) from ..utils import ( determine_ext, ExtractorError, int_or_none, - urlencode_postdata, get_element_by_attribute, mimetype2ext, ) @@ -50,6 +50,21 @@ class MetacafeIE(InfoExtractor): }, 'skip': 'Page is temporarily unavailable.', }, + # metacafe video with family filter + { + 'url': 'http://www.metacafe.com/watch/2155630/adult_art_by_david_hart_156/', + 'md5': 'b06082c5079bbdcde677a6291fbdf376', + 'info_dict': { + 'id': '2155630', + 'ext': 'mp4', + 'title': 'Adult Art By David Hart 156', + 'uploader': '63346', + 'description': 'md5:9afac8fc885252201ad14563694040fc', + }, + 'params': { + 'skip_download': True, + }, + }, # AnyClip video { 'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/', @@ -112,22 +127,6 @@ class MetacafeIE(InfoExtractor): def report_disclaimer(self): self.to_screen('Retrieving disclaimer') - def _confirm_age(self): - # Retrieve disclaimer - self.report_disclaimer() - self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer') - - # Confirm age - self.report_age_confirmation() - self._download_webpage( - self._FILTER_POST, None, False, 'Unable to confirm age', - data=urlencode_postdata({ - 'filters': '0', - 'submit': "Continue - I'm over 18", - }), headers={ - 'Content-Type': 'application/x-www-form-urlencoded', - }) - def _real_extract(self, url): # Extract id and simplified title from URL video_id, display_id = re.match(self._VALID_URL, url).groups() @@ -143,13 +142,15 @@ class MetacafeIE(InfoExtractor): if prefix == 'cb': return self.url_result('theplatform:%s' % ext_id, 'ThePlatform') - # self._confirm_age() + headers = { + # Disable family filter + 'Cookie': 'user=%s; ' % compat_urllib_parse_urlencode({'ffilter': False}) + } # AnyClip videos require the flashversion cookie so that we get the link # to the mp4 file - headers = {} if video_id.startswith('an-'): - headers['Cookie'] = 'flashVersion=0;' + headers['Cookie'] += 'flashVersion=0; ' # Retrieve video webpage to extract further information webpage = self._download_webpage(url, video_id, headers=headers) diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py index 659ede8..d53d96a 100644 --- a/youtube_dl/extractor/mgtv.py +++ b/youtube_dl/extractor/mgtv.py @@ -2,16 +2,17 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import int_or_none class MGTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html' + _VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html' IE_DESC = '芒果TV' _TESTS = [{ 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html', - 'md5': '1bdadcf760a0b90946ca68ee9a2db41a', + 'md5': 'b1ffc0fc163152acf6beaa81832c9ee7', 'info_dict': { 'id': '3116640', 'ext': 'mp4', @@ -21,48 +22,45 @@ class MGTVIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', }, }, { - # no tbr extracted from stream_url - 'url': 'http://www.mgtv.com/v/1/1/f/3324755.html', + 'url': 'http://www.mgtv.com/b/301817/3826653.html', 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) api_data = self._download_json( - 'http://v.api.mgtv.com/player/video', video_id, + 'http://pcweb.api.mgtv.com/player/video', video_id, query={'video_id': video_id}, headers=self.geo_verification_headers())['data'] info = api_data['info'] + title = info['title'].strip() + stream_domain = api_data['stream_domain'][0] formats = [] for idx, stream in enumerate(api_data['stream']): - stream_url = stream.get('url') - if not stream_url: + stream_path = stream.get('url') + if not stream_path: + continue + format_data = self._download_json( + stream_domain + stream_path, video_id, + note='Download video info for format #%d' % idx) + format_url = format_data.get('info') + if not format_url: continue tbr = int_or_none(self._search_regex( - r'(\d+)\.mp4', stream_url, 'tbr', default=None)) - - def extract_format(stream_url, format_id, idx, query={}): - format_info = self._download_json( - stream_url, video_id, - note='Download video info for format %s' % (format_id or '#%d' % idx), - query=query) - return { - 'format_id': format_id, - 'url': format_info['info'], - 'ext': 'mp4', - 'tbr': tbr, - } - - formats.append(extract_format( - stream_url, 'hls-%d' % tbr if tbr else None, idx * 2)) - formats.append(extract_format(stream_url.replace( - '/playlist.m3u8', ''), 'http-%d' % tbr if tbr else None, idx * 2 + 1, {'pno': 1031})) + r'_(\d+)_mp4/', format_url, 'tbr', default=None)) + formats.append({ + 'format_id': compat_str(tbr or idx), + 'url': format_url, + 'ext': 'mp4', + 'tbr': tbr, + 'protocol': 'm3u8_native', + }) self._sort_formats(formats) return { 'id': video_id, - 'title': info['title'].strip(), + 'title': title, 'formats': formats, 'description': info.get('desc'), 'duration': int_or_none(info.get('duration')), diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 434a94d..d2a44d0 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -4,23 +4,26 @@ import re from .common import InfoExtractor from .theplatform import ThePlatformIE +from .adobepass import AdobePassIE +from ..compat import compat_urllib_parse_urlparse from ..utils import ( find_xpath_attr, lowercase_escape, smuggle_url, unescapeHTML, update_url_query, + int_or_none, ) -class NBCIE(InfoExtractor): +class NBCIE(AdobePassIE): _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)' _TESTS = [ { - 'url': 'http://www.nbc.com/the-tonight-show/segments/112966', + 'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237', 'info_dict': { - 'id': '112966', + 'id': '2848237', 'ext': 'mp4', 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s', 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.', @@ -69,7 +72,7 @@ class NBCIE(InfoExtractor): # HLS streams requires the 'hdnea3' cookie 'url': 'http://www.nbc.com/Kings/video/goliath/n1806', 'info_dict': { - 'id': 'n1806', + 'id': '101528f5a9e8127b107e98c5e6ce4638', 'ext': 'mp4', 'title': 'Goliath', 'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.', @@ -87,21 +90,57 @@ class NBCIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex( - [ - r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"', - r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"', - r'"embedURL"\s*:\s*"([^"]+)"' - ], - webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/'))) - if theplatform_url.startswith('//'): - theplatform_url = 'http:' + theplatform_url - return { + info = { '_type': 'url_transparent', 'ie_key': 'ThePlatform', - 'url': smuggle_url(theplatform_url, {'source_url': url}), 'id': video_id, } + video_data = None + preload = self._search_regex( + r'PRELOAD\s*=\s*({.+})', webpage, 'preload data', default=None) + if preload: + preload_data = self._parse_json(preload, video_id) + path = compat_urllib_parse_urlparse(url).path.rstrip('/') + entity_id = preload_data.get('xref', {}).get(path) + video_data = preload_data.get('entities', {}).get(entity_id) + if video_data: + query = { + 'mbr': 'true', + 'manifest': 'm3u', + } + video_id = video_data['guid'] + title = video_data['title'] + if video_data.get('entitlement') == 'auth': + resource = self._get_mvpd_resource( + 'nbcentertainment', title, video_id, + video_data.get('vChipRating')) + query['auth'] = self._extract_mvpd_auth( + url, video_id, 'nbcentertainment', resource) + theplatform_url = smuggle_url(update_url_query( + 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id, + query), {'force_smil_url': True}) + info.update({ + 'id': video_id, + 'title': title, + 'url': theplatform_url, + 'description': video_data.get('description'), + 'keywords': video_data.get('keywords'), + 'season_number': int_or_none(video_data.get('seasonNumber')), + 'episode_number': int_or_none(video_data.get('episodeNumber')), + 'series': video_data.get('showName'), + }) + else: + theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex( + [ + r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"', + r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"', + r'"embedURL"\s*:\s*"([^"]+)"' + ], + webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/'))) + if theplatform_url.startswith('//'): + theplatform_url = 'http:' + theplatform_url + info['url'] = smuggle_url(theplatform_url, {'source_url': url}) + return info class NBCSportsVPlayerIE(InfoExtractor): diff --git a/youtube_dl/extractor/ninecninemedia.py b/youtube_dl/extractor/ninecninemedia.py index ec4d675..d9943fc 100644 --- a/youtube_dl/extractor/ninecninemedia.py +++ b/youtube_dl/extractor/ninecninemedia.py @@ -19,6 +19,7 @@ class NineCNineMediaBaseIE(InfoExtractor): class NineCNineMediaStackIE(NineCNineMediaBaseIE): IE_NAME = '9c9media:stack' + _GEO_COUNTRIES = ['CA'] _VALID_URL = r'9c9media:stack:(?P<destination_code>[^:]+):(?P<content_id>\d+):(?P<content_package>\d+):(?P<id>\d+)' def _real_extract(self, url): diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index 70ff2ab..8b83e1f 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -23,7 +23,7 @@ from ..utils import ( class NocoIE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)' - _LOGIN_URL = 'http://noco.tv/do.php' + _LOGIN_URL = 'https://noco.tv/do.php' _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s' _SUB_LANG_TEMPLATE = '&sub_lang=%s' _NETRC_MACHINE = 'noco' @@ -69,16 +69,17 @@ class NocoIE(InfoExtractor): if username is None: return - login_form = { - 'a': 'login', - 'cookie': '1', - 'username': username, - 'password': password, - } - request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8') - - login = self._download_json(request, None, 'Logging in as %s' % username) + login = self._download_json( + self._LOGIN_URL, None, 'Logging in as %s' % username, + data=urlencode_postdata({ + 'a': 'login', + 'cookie': '1', + 'username': username, + 'password': password, + }), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + }) if 'erreur' in login: raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index fc3c0cd..7fe79cb 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import random import re from .common import InfoExtractor @@ -15,24 +14,7 @@ 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()) + _GEO_COUNTRIES = ['NO'] def _real_extract(self, url): video_id = self._match_id(url) @@ -44,8 +26,6 @@ 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 = [] conviva = data.get('convivaStatistics') or {} @@ -90,7 +70,6 @@ class NRKBaseIE(InfoExtractor): 'duration': duration, 'subtitles': subtitles, 'formats': formats, - 'http_headers': http_headers, }) if not entries: @@ -107,19 +86,17 @@ class NRKBaseIE(InfoExtractor): }] if not entries: - 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', } + message_type = data.get('messageType', '') + # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked* + if 'IsGeoBlocked' in message_type: + self.raise_geo_restricted( + msg=MESSAGES.get('ProgramIsGeoBlocked'), + countries=self._GEO_COUNTRIES) raise ExtractorError( '%s said: %s' % (self.IE_NAME, MESSAGES.get( message_type, message_type)), @@ -188,12 +165,12 @@ class NRKIE(NRKBaseIE): https?:// (?: (?:www\.)?nrk\.no/video/PS\*| - v8-psapi\.nrk\.no/mediaelement/ + v8[-.]psapi\.nrk\.no/mediaelement/ ) ) - (?P<id>[^/?#&]+) + (?P<id>[^?#&]+) ''' - _API_HOST = 'v8.psapi.nrk.no' + _API_HOST = 'v8-psapi.nrk.no' _TESTS = [{ # video 'url': 'http://www.nrk.no/video/PS*150533', @@ -220,6 +197,9 @@ class NRKIE(NRKBaseIE): 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9', 'only_matching': True, }, { + 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70', + 'only_matching': True, + }, { 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9', 'only_matching': True, }] diff --git a/youtube_dl/extractor/ondemandkorea.py b/youtube_dl/extractor/ondemandkorea.py index de1d6b0..df1ce3c 100644 --- a/youtube_dl/extractor/ondemandkorea.py +++ b/youtube_dl/extractor/ondemandkorea.py @@ -1,15 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( ExtractorError, js_to_json, ) -class OnDemandKoreaIE(JWPlatformBaseIE): +class OnDemandKoreaIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html' + _GEO_COUNTRIES = ['US', 'CA'] _TEST = { 'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html', 'info_dict': { @@ -35,7 +36,8 @@ class OnDemandKoreaIE(JWPlatformBaseIE): if 'msg_block_01.png' in webpage: self.raise_geo_restricted( - 'This content is not available in your region') + msg='This content is not available in your region', + countries=self._GEO_COUNTRIES) if 'This video is only available to ODK PLUS members.' in webpage: raise ExtractorError( diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py index 0a501b3..94f5799 100644 --- a/youtube_dl/extractor/onet.py +++ b/youtube_dl/extractor/onet.py @@ -23,7 +23,7 @@ class OnetBaseIE(InfoExtractor): return self._search_regex( r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id') - def _extract_from_id(self, video_id, webpage): + def _extract_from_id(self, video_id, webpage=None): response = self._download_json( 'http://qi.ckm.onetapi.pl/', video_id, query={ @@ -74,8 +74,10 @@ class OnetBaseIE(InfoExtractor): meta = video.get('meta', {}) - title = self._og_search_title(webpage, default=None) or meta['title'] - description = self._og_search_description(webpage, default=None) or meta.get('description') + title = (self._og_search_title( + webpage, default=None) if webpage else None) or meta['title'] + description = (self._og_search_description( + webpage, default=None) if webpage else None) or meta.get('description') duration = meta.get('length') or meta.get('lenght') timestamp = parse_iso8601(meta.get('addDate'), ' ') @@ -89,6 +91,18 @@ class OnetBaseIE(InfoExtractor): } +class OnetMVPIE(OnetBaseIE): + _VALID_URL = r'onetmvp:(?P<id>\d+\.\d+)' + + _TEST = { + 'url': 'onetmvp:381027.1509591944', + 'only_matching': True, + } + + def _real_extract(self, url): + return self._extract_from_id(self._match_id(url)) + + class OnetIE(OnetBaseIE): _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)' IE_NAME = 'onet.tv' @@ -167,3 +181,44 @@ class OnetChannelIE(OnetBaseIE): channel_title = strip_or_none(get_element_by_class('o_channelName', webpage)) channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage)) return self.playlist_result(entries, channel_id, channel_title, channel_description) + + +class OnetPlIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?(?:onet|businessinsider\.com|plejada)\.pl/(?:[^/]+/)+(?P<id>[0-9a-z]+)' + IE_NAME = 'onet.pl' + + _TESTS = [{ + 'url': 'http://eurosport.onet.pl/zimowe/skoki-narciarskie/ziobro-wygral-kwalifikacje-w-pjongczangu/9ckrly', + 'md5': 'b94021eb56214c3969380388b6e73cb0', + 'info_dict': { + 'id': '1561707.1685479', + 'ext': 'mp4', + 'title': 'Ziobro wygrał kwalifikacje w Pjongczangu', + 'description': 'md5:61fb0740084d2d702ea96512a03585b4', + 'upload_date': '20170214', + 'timestamp': 1487078046, + }, + }, { + 'url': 'http://film.onet.pl/zwiastuny/ghost-in-the-shell-drugi-zwiastun-pl/5q6yl3', + 'only_matching': True, + }, { + 'url': 'http://moto.onet.pl/jak-wybierane-sa-miejsca-na-fotoradary/6rs04e', + 'only_matching': True, + }, { + 'url': 'http://businessinsider.com.pl/wideo/scenariusz-na-koniec-swiata-wedlug-nasa/dwnqptk', + 'only_matching': True, + }, { + 'url': 'http://plejada.pl/weronika-rosati-o-swoim-domniemanym-slubie/n2bq89', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + mvp_id = self._search_regex( + r'data-params-mvp=["\'](\d+\.\d+)', webpage, 'mvp id') + + return self.url_result( + 'onetmvp:%s' % mvp_id, OnetMVPIE.ie_key(), video_id=mvp_id) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 32289d8..fc7ff43 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -72,20 +72,25 @@ class OpenloadIE(InfoExtractor): raise ExtractorError('File not found', expected=True) ol_id = self._search_regex( - '<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>', + '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>', webpage, 'openload ID') - first_three_chars = int(float(ol_id[0:][:3])) - fifth_char = int(float(ol_id[3:5])) - urlcode = '' - num = 5 + first_char = int(ol_id[0]) + urlcode = [] + num = 1 while num < len(ol_id): - urlcode += compat_chr(int(float(ol_id[num:][:3])) + - first_three_chars - fifth_char * int(float(ol_id[num + 3:][:2]))) + i = ord(ol_id[num]) + key = 0 + if i <= 90: + key = i - 65 + elif i >= 97: + key = 25 + i - 97 + urlcode.append((key, compat_chr(int(ol_id[num + 2:num + 5]) // int(ol_id[num + 1]) - first_char))) num += 5 - video_url = 'https://openload.co/stream/' + urlcode + video_url = 'https://openload.co/stream/' + ''.join( + [value for _, value in sorted(urlcode, key=lambda x: x[0])]) title = self._og_search_title(webpage, default=None) or self._search_regex( r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage, diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 6baed77..3e51b4d 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -193,6 +193,8 @@ class PBSIE(InfoExtractor): ) ''' % '|'.join(list(zip(*_STATIONS))[0]) + _GEO_COUNTRIES = ['US'] + _TESTS = [ { 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', @@ -489,11 +491,13 @@ class PBSIE(InfoExtractor): headers=self.geo_verification_headers()) if redirect_info['status'] == 'error': + message = self._ERRORS.get( + redirect_info['http_code'], redirect_info['message']) + if redirect_info['http_code'] == 403: + self.raise_geo_restricted( + msg=message, countries=self._GEO_COUNTRIES) raise ExtractorError( - '%s said: %s' % ( - self.IE_NAME, - self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])), - expected=True) + '%s said: %s' % (self.IE_NAME, message), expected=True) format_url = redirect_info.get('url') if not format_url: diff --git a/youtube_dl/extractor/pinkbike.py b/youtube_dl/extractor/pinkbike.py index 6a4580d..9f3501f 100644 --- a/youtube_dl/extractor/pinkbike.py +++ b/youtube_dl/extractor/pinkbike.py @@ -64,7 +64,8 @@ class PinkbikeIE(InfoExtractor): 'video:duration', webpage, 'duration')) uploader = self._search_regex( - r'un:\s*"([^"]+)"', webpage, 'uploader', fatal=False) + r'<a[^>]+\brel=["\']author[^>]+>([^<]+)', webpage, + 'uploader', fatal=False) upload_date = unified_strdate(self._search_regex( r'class="fullTime"[^>]+title="([^"]+)"', webpage, 'upload date', fatal=False)) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 5c798e8..e0cbd04 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -18,6 +18,7 @@ from ..utils import ( parse_duration, qualities, srt_subtitles_timecode, + update_url_query, urlencode_postdata, ) @@ -92,6 +93,10 @@ class PluralsightIE(PluralsightBaseIE): raise ExtractorError('Unable to login: %s' % error, expected=True) if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')): + BLOCKED = 'Your account has been blocked due to suspicious activity' + if BLOCKED in response: + raise ExtractorError( + 'Unable to login: %s' % BLOCKED, expected=True) raise ExtractorError('Unable to log in') def _get_subtitles(self, author, clip_id, lang, name, duration, video_id): @@ -327,25 +332,44 @@ class PluralsightCourseIE(PluralsightBaseIE): # TODO: PSM cookie course = self._download_json( - '%s/data/course/%s' % (self._API_BASE, course_id), - course_id, 'Downloading course JSON') + '%s/player/functions/rpc' % self._API_BASE, course_id, + 'Downloading course JSON', + data=json.dumps({ + 'fn': 'bootstrapPlayer', + 'payload': { + 'courseId': course_id, + } + }).encode('utf-8'), + headers={ + 'Content-Type': 'application/json;charset=utf-8' + })['payload']['course'] title = course['title'] + course_name = course['name'] + course_data = course['modules'] description = course.get('description') or course.get('shortDescription') - course_data = self._download_json( - '%s/data/course/content/%s' % (self._API_BASE, course_id), - course_id, 'Downloading course data JSON') - entries = [] for num, module in enumerate(course_data, 1): + author = module.get('author') + module_name = module.get('name') + if not author or not module_name: + continue for clip in module.get('clips', []): - player_parameters = clip.get('playerParameters') - if not player_parameters: + clip_index = int_or_none(clip.get('index')) + if clip_index is None: continue + clip_url = update_url_query( + '%s/player' % self._API_BASE, query={ + 'mode': 'live', + 'course': course_name, + 'author': author, + 'name': module_name, + 'clip': clip_index, + }) entries.append({ '_type': 'url_transparent', - 'url': '%s/training/player?%s' % (self._API_BASE, player_parameters), + 'url': clip_url, 'ie_key': PluralsightIE.ie_key(), 'chapter': module.get('title'), 'chapter_number': num, diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 017f6c5..9b41359 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -2,27 +2,27 @@ from __future__ import unicode_literals import itertools -import os +# import os import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_urllib_parse_unquote, - compat_urllib_parse_unquote_plus, - compat_urllib_parse_urlparse, + # compat_urllib_parse_unquote, + # compat_urllib_parse_unquote_plus, + # compat_urllib_parse_urlparse, ) from ..utils import ( ExtractorError, int_or_none, js_to_json, orderedSet, - sanitized_Request, + # sanitized_Request, str_to_int, ) -from ..aes import ( - aes_decrypt_text -) +# from ..aes import ( +# aes_decrypt_text +# ) class PornHubIE(InfoExtractor): @@ -109,10 +109,14 @@ class PornHubIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - req = sanitized_Request( - 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + def dl_webpage(platform): + return self._download_webpage( + 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, + video_id, headers={ + 'Cookie': 'age_verified=1; platform=%s' % platform, + }) + + webpage = dl_webpage('pc') error_msg = self._html_search_regex( r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>', @@ -123,10 +127,19 @@ class PornHubIE(InfoExtractor): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) + tv_webpage = dl_webpage('tv') + + video_url = self._search_regex( + r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage, + 'video url', group='url') + + title = self._search_regex( + r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None) + # video_title from flashvars contains whitespace instead of non-ASCII (see # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. - title = self._html_search_meta( + title = title or self._html_search_meta( 'twitter:title', webpage, default=None) or self._search_regex( (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', @@ -156,42 +169,6 @@ class PornHubIE(InfoExtractor): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - video_urls = [] - for quote, video_url in re.findall( - r'player_quality_[0-9]{3,4}p\s*=\s*(["\'])(.+?)\1;', webpage): - video_urls.append(compat_urllib_parse_unquote(re.sub( - r'{0}\s*\+\s*{0}'.format(quote), '', video_url))) - - if webpage.find('"encrypted":true') != -1: - password = compat_urllib_parse_unquote_plus( - self._search_regex(r'"video_title":"([^"]+)', webpage, 'password')) - video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) - - formats = [] - for video_url in video_urls: - path = compat_urllib_parse_urlparse(video_url).path - extension = os.path.splitext(path)[1][1:] - format = path.split('/')[5].split('_')[:2] - format = '-'.join(format) - - m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format) - if m is None: - height = None - tbr = None - else: - height = int(m.group('height')) - tbr = int(m.group('tbr')) - - formats.append({ - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, - 'tbr': tbr, - 'height': height, - }) - self._sort_formats(formats) - page_params = self._parse_json(self._search_regex( r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', webpage, 'page parameters', group='data', default='{}'), @@ -203,6 +180,7 @@ class PornHubIE(InfoExtractor): return { 'id': video_id, + 'url': video_url, 'uploader': video_uploader, 'title': title, 'thumbnail': thumbnail, @@ -211,7 +189,7 @@ class PornHubIE(InfoExtractor): 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, - 'formats': formats, + # 'formats': formats, 'age_limit': 18, 'tags': tags, 'categories': categories, diff --git a/youtube_dl/extractor/pornoxo.py b/youtube_dl/extractor/pornoxo.py index 1a0cce7..2831368 100644 --- a/youtube_dl/extractor/pornoxo.py +++ b/youtube_dl/extractor/pornoxo.py @@ -2,13 +2,13 @@ from __future__ import unicode_literals import re -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( str_to_int, ) -class PornoXOIE(JWPlatformBaseIE): +class PornoXOIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html' _TEST = { 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html', diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 5091d84..1245309 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -424,3 +424,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): return self._extract_clip(url, webpage) elif page_type == 'playlist': return self._extract_playlist(url, webpage) + else: + raise ExtractorError( + 'Unsupported page type %s' % page_type, expected=True) diff --git a/youtube_dl/extractor/rentv.py b/youtube_dl/extractor/rentv.py index 422c02c..d338b3a 100644 --- a/youtube_dl/extractor/rentv.py +++ b/youtube_dl/extractor/rentv.py @@ -2,11 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from .jwplatform import JWPlatformBaseIE from ..compat import compat_str -class RENTVIE(JWPlatformBaseIE): +class RENTVIE(InfoExtractor): _VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P<id>\d+)' _TESTS = [{ 'url': 'http://ren.tv/video/epizod/118577', diff --git a/youtube_dl/extractor/rudo.py b/youtube_dl/extractor/rudo.py index 3bfe934..5164401 100644 --- a/youtube_dl/extractor/rudo.py +++ b/youtube_dl/extractor/rudo.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( js_to_json, get_element_by_class, @@ -11,7 +11,7 @@ from ..utils import ( ) -class RudoIE(JWPlatformBaseIE): +class RudoIE(InfoExtractor): _VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)' _TEST = { diff --git a/youtube_dl/extractor/screencastomatic.py b/youtube_dl/extractor/screencastomatic.py index 94a2a37..b5e76c9 100644 --- a/youtube_dl/extractor/screencastomatic.py +++ b/youtube_dl/extractor/screencastomatic.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import js_to_json -class ScreencastOMaticIE(JWPlatformBaseIE): +class ScreencastOMaticIE(InfoExtractor): _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)' _TEST = { 'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl', diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py new file mode 100644 index 0000000..597d6f5 --- /dev/null +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .adobepass import AdobePassIE +from ..utils import ( + int_or_none, + smuggle_url, + update_url_query, +) + + +class ScrippsNetworksWatchIE(AdobePassIE): + IE_NAME = 'scrippsnetworks:watch' + _VALID_URL = r'https?://watch\.(?:hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv)\.com/player\.[A-Z0-9]+\.html#(?P<id>\d+)' + _TEST = { + 'url': 'http://watch.hgtv.com/player.HNT.html#0256538', + 'md5': '26545fd676d939954c6808274bdb905a', + 'info_dict': { + 'id': '0256538', + 'ext': 'mp4', + 'title': 'Seeking a Wow House', + 'description': 'Buyers retiring in Palm Springs, California, want a modern house with major wow factor. They\'re also looking for a pool and a large, open floorplan with tall windows looking out at the views.', + 'uploader': 'SCNI', + 'upload_date': '20170207', + 'timestamp': 1486450493, + }, + 'skip': 'requires TV provider authentication', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + channel = self._parse_json(self._search_regex( + r'"channels"\s*:\s*(\[.+\])', + webpage, 'channels'), video_id)[0] + video_data = next(v for v in channel['videos'] if v.get('nlvid') == video_id) + title = video_data['title'] + release_url = video_data['releaseUrl'] + if video_data.get('restricted'): + requestor_id = self._search_regex( + r'requestorId\s*=\s*"([^"]+)";', webpage, 'requestor id') + resource = self._get_mvpd_resource( + requestor_id, title, video_id, + video_data.get('ratings', [{}])[0].get('rating')) + auth = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) + release_url = update_url_query(release_url, {'auth': auth}) + + return { + '_type': 'url_transparent', + 'id': video_id, + 'title': title, + 'url': smuggle_url(release_url, {'force_smil_url': True}), + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnailUrl'), + 'series': video_data.get('showTitle'), + 'season_number': int_or_none(video_data.get('season')), + 'episode_number': int_or_none(video_data.get('episodeNumber')), + 'ie_key': 'ThePlatform', + } diff --git a/youtube_dl/extractor/sendtonews.py b/youtube_dl/extractor/sendtonews.py index 9880a5a..9d96529 100644 --- a/youtube_dl/extractor/sendtonews.py +++ b/youtube_dl/extractor/sendtonews.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( float_or_none, parse_iso8601, @@ -14,7 +14,7 @@ from ..utils import ( ) -class SendtoNewsIE(JWPlatformBaseIE): +class SendtoNewsIE(InfoExtractor): _VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)' _TEST = { diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index d3aba58..547be8f 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -1,64 +1,101 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - qualities, - int_or_none, - mimetype2ext, determine_ext, + int_or_none, + try_get, + qualities, ) class SixPlayIE(InfoExtractor): + IE_NAME = '6play' _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)' _TEST = { - 'url': 'http://www.6play.fr/jamel-et-ses-amis-au-marrakech-du-rire-p_1316/jamel-et-ses-amis-au-marrakech-du-rire-2015-c_11495320', + 'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450', 'md5': '42310bffe4ba3982db112b9cd3467328', 'info_dict': { - 'id': '11495320', + 'id': '11638450', 'ext': 'mp4', - 'title': 'Jamel et ses amis au Marrakech du rire 2015', - 'description': 'md5:ba2149d5c321d5201b78070ee839d872', + 'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6', + 'description': 'md5:308853f6a5f9e2d55a30fc0654de415f', + 'duration': 39, + 'series': 'Le meilleur pâtissier', + }, + 'params': { + 'skip_download': True, }, } def _real_extract(self, url): video_id = self._match_id(url) - clip_data = self._download_json( - 'https://player.m6web.fr/v2/video/config/6play-auth/FR/%s.json' % video_id, - video_id) - video_data = clip_data['videoInfo'] + data = self._download_json( + 'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id, + video_id, query={ + 'csa': 5, + 'with': 'clips', + }) + + clip_data = data['clips'][0] + title = clip_data['title'] + + urls = [] quality_key = qualities(['lq', 'sd', 'hq', 'hd']) formats = [] - for source in clip_data['sources']: - source_type, source_url = source.get('type'), source.get('src') - if not source_url or source_type == 'hls/primetime': + for asset in clip_data['assets']: + asset_url = asset.get('full_physical_path') + protocol = asset.get('protocol') + if not asset_url or protocol == 'primetime' or asset_url in urls: continue - ext = mimetype2ext(source_type) or determine_ext(source_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - source_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - source_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - elif ext == 'mp4': - quality = source.get('quality') + urls.append(asset_url) + container = asset.get('video_container') + ext = determine_ext(asset_url) + if container == 'm3u8' or ext == 'm3u8': + if protocol == 'usp': + asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url) + formats.extend(self._extract_m3u8_formats( + asset_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + formats.extend(self._extract_f4m_formats( + asset_url.replace('.m3u8', '.f4m'), + video_id, f4m_id='hds', fatal=False)) + formats.extend(self._extract_mpd_formats( + asset_url.replace('.m3u8', '.mpd'), + video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_ism_formats( + re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url), + video_id, ism_id='mss', fatal=False)) + else: + formats.extend(self._extract_m3u8_formats( + asset_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif container == 'mp4' or ext == 'mp4': + quality = asset.get('video_quality') formats.append({ - 'url': source_url, + 'url': asset_url, 'format_id': quality, 'quality': quality_key(quality), 'ext': ext, }) self._sort_formats(formats) + def get(getter): + for src in (data, clip_data): + v = try_get(src, getter, compat_str) + if v: + return v + return { 'id': video_id, - 'title': video_data['title'].strip(), - 'description': video_data.get('description'), - 'duration': int_or_none(video_data.get('duration')), - 'series': video_data.get('titlePgm'), + 'title': title, + 'description': get(lambda x: x['description']), + 'duration': int_or_none(clip_data.get('duration')), + 'series': get(lambda x: x['program']['title']), 'formats': formats, } diff --git a/youtube_dl/extractor/skylinewebcams.py b/youtube_dl/extractor/skylinewebcams.py new file mode 100644 index 0000000..5b4aaac --- /dev/null +++ b/youtube_dl/extractor/skylinewebcams.py @@ -0,0 +1,42 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class SkylineWebcamsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?skylinewebcams\.com/[^/]+/webcam/(?:[^/]+/)+(?P<id>[^/]+)\.html' + _TEST = { + 'url': 'https://www.skylinewebcams.com/it/webcam/italia/lazio/roma/scalinata-piazza-di-spagna-barcaccia.html', + 'info_dict': { + 'id': 'scalinata-piazza-di-spagna-barcaccia', + 'ext': 'mp4', + 'title': 're:^Live Webcam Scalinata di Piazza di Spagna - La Barcaccia [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'Roma, veduta sulla Scalinata di Piazza di Spagna e sulla Barcaccia', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + stream_url = self._search_regex( + r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, + 'stream url', group='url') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + + return { + 'id': video_id, + 'url': stream_url, + 'ext': 'mp4', + 'title': self._live_title(title), + 'description': description, + 'is_live': True, + } diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 30760ca..7da12ce 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -108,12 +108,11 @@ class SohuIE(InfoExtractor): if vid_data['play'] != 1: if vid_data.get('status') == 12: raise ExtractorError( - 'Sohu said: There\'s something wrong in the video.', + '%s said: There\'s something wrong in the video.' % self.IE_NAME, expected=True) else: - raise ExtractorError( - 'Sohu said: The video is only licensed to users in Mainland China.', - expected=True) + self.raise_geo_restricted( + '%s said: The video is only licensed to users in Mainland China.' % self.IE_NAME) formats_json = {} for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'): diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index 123c33a..3394c7e 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -23,6 +23,10 @@ class SpankBangIE(InfoExtractor): # 480p only 'url': 'http://spankbang.com/1vt0/video/solvane+gangbang', 'only_matching': True, + }, { + # no uploader + 'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2', + 'only_matching': True, }] def _real_extract(self, url): @@ -48,7 +52,7 @@ class SpankBangIE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) uploader = self._search_regex( r'class="user"[^>]*><img[^>]+>([^<]+)', - webpage, 'uploader', fatal=False) + webpage, 'uploader', default=None) age_limit = self._rta_search(webpage) diff --git a/youtube_dl/extractor/sprout.py b/youtube_dl/extractor/sprout.py new file mode 100644 index 0000000..8467bf4 --- /dev/null +++ b/youtube_dl/extractor/sprout.py @@ -0,0 +1,52 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .adobepass import AdobePassIE +from ..utils import ( + extract_attributes, + update_url_query, + smuggle_url, +) + + +class SproutIE(AdobePassIE): + _VALID_URL = r'https?://(?:www\.)?sproutonline\.com/watch/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'http://www.sproutonline.com/watch/cowboy-adventure', + 'md5': '74bf14128578d1e040c3ebc82088f45f', + 'info_dict': { + 'id': '9dexnwtmh8_X', + 'ext': 'mp4', + 'title': 'A Cowboy Adventure', + 'description': 'Ruff-Ruff, Tweet and Dave get to be cowboys for the day at Six Cow Corral.', + 'timestamp': 1437758640, + 'upload_date': '20150724', + 'uploader': 'NBCU-SPROUT-NEW', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_component = self._search_regex( + r'(?s)(<div[^>]+data-component="video"[^>]*?>)', + webpage, 'video component', default=None) + if video_component: + options = self._parse_json(extract_attributes( + video_component)['data-options'], video_id) + theplatform_url = options['video'] + query = { + 'mbr': 'true', + 'manifest': 'm3u', + } + if options.get('protected'): + query['auth'] = self._extract_mvpd_auth(url, options['pid'], 'sprout', 'sprout') + theplatform_url = smuggle_url(update_url_query( + theplatform_url, query), {'force_smil_url': True}) + else: + iframe = self._search_regex( + r'(<iframe[^>]+id="sproutVideoIframe"[^>]*?>)', + webpage, 'iframe') + theplatform_url = extract_attributes(iframe)['src'] + + return self.url_result(theplatform_url, 'ThePlatform') diff --git a/youtube_dl/extractor/srgssr.py b/youtube_dl/extractor/srgssr.py index 319a48a..bb73eb1 100644 --- a/youtube_dl/extractor/srgssr.py +++ b/youtube_dl/extractor/srgssr.py @@ -14,6 +14,8 @@ from ..utils import ( class SRGSSRIE(InfoExtractor): _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)' + _GEO_BYPASS = False + _GEO_COUNTRIES = ['CH'] _ERRORS = { 'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.', @@ -40,8 +42,12 @@ class SRGSSRIE(InfoExtractor): media_id)[media_type.capitalize()] if media_data.get('block') and media_data['block'] in self._ERRORS: - raise ExtractorError('%s said: %s' % ( - self.IE_NAME, self._ERRORS[media_data['block']]), expected=True) + message = self._ERRORS[media_data['block']] + if media_data['block'] == 'GEOBLOCK': + self.raise_geo_restricted( + msg=message, countries=self._GEO_COUNTRIES) + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, message), expected=True) return media_data diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index 10cf808..1b5afb7 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -13,6 +13,8 @@ from ..utils import ( class SVTBaseIE(InfoExtractor): + _GEO_COUNTRIES = ['SE'] + def _extract_video(self, video_info, video_id): formats = [] for vr in video_info['videoReferences']: @@ -38,7 +40,9 @@ class SVTBaseIE(InfoExtractor): 'url': vurl, }) if not formats and video_info.get('rights', {}).get('geoBlockedSweden'): - self.raise_geo_restricted('This video is only available in Sweden') + self.raise_geo_restricted( + 'This video is only available in Sweden', + countries=self._GEO_COUNTRIES) self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/telequebec.py b/youtube_dl/extractor/telequebec.py index 4043fcb..82d73c3 100644 --- a/youtube_dl/extractor/telequebec.py +++ b/youtube_dl/extractor/telequebec.py @@ -2,7 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + smuggle_url, +) class TeleQuebecIE(InfoExtractor): @@ -28,7 +31,7 @@ class TeleQuebecIE(InfoExtractor): return { '_type': 'url_transparent', 'id': media_id, - 'url': 'limelight:media:' + media_data['streamInfo']['sourceId'], + 'url': smuggle_url('limelight:media:' + media_data['streamInfo']['sourceId'], {'geo_countries': ['CA']}), 'title': media_data['title'], 'description': media_data.get('descriptions', [{'text': None}])[0].get('text'), 'duration': int_or_none(media_data.get('durationInMilliseconds'), 1000), diff --git a/youtube_dl/extractor/tfo.py b/youtube_dl/extractor/tfo.py index 6f1eeac..0e2370c 100644 --- a/youtube_dl/extractor/tfo.py +++ b/youtube_dl/extractor/tfo.py @@ -8,10 +8,12 @@ from ..utils import ( HEADRequest, ExtractorError, int_or_none, + clean_html, ) class TFOIE(InfoExtractor): + _GEO_COUNTRIES = ['CA'] _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)' _TEST = { 'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon', @@ -36,7 +38,9 @@ class TFOIE(InfoExtractor): 'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value, }) if infos.get('success') == 0: - raise ExtractorError('%s said: %s' % (self.IE_NAME, infos['msg']), expected=True) + if infos.get('code') == 'ErrGeoBlocked': + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) + raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True) video_data = infos['data'] return { diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 192d8fa..9a424b1 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -179,10 +179,12 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): if m: return [m.group('url')] + # Are whitesapces ignored in URLs? + # https://github.com/rg3/youtube-dl/issues/12044 matches = re.findall( - r'<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage) + r'(?s)<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage) if matches: - return list(zip(*matches))[1] + return [re.sub(r'\s', '', list(zip(*matches))[1][0])] @staticmethod def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False): @@ -306,9 +308,10 @@ class ThePlatformFeedIE(ThePlatformBaseIE): }, }] - def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}): + def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None): real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query) entry = self._download_json(real_url, video_id)['entries'][0] + main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None formats = [] subtitles = {} @@ -333,7 +336,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if asset_type in asset_types_query: query.update(asset_types_query[asset_type]) cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query( - smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type) + main_smil_url or smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type) formats.extend(cur_formats) subtitles = self._merge_subtitles(subtitles, cur_subtitles) diff --git a/youtube_dl/extractor/thescene.py b/youtube_dl/extractor/thescene.py index ce1326c..b8504f0 100644 --- a/youtube_dl/extractor/thescene.py +++ b/youtube_dl/extractor/thescene.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import compat_urlparse -from ..utils import qualities +from ..utils import ( + int_or_none, + qualities, +) class TheSceneIE(InfoExtractor): @@ -16,6 +19,11 @@ class TheSceneIE(InfoExtractor): 'ext': 'mp4', 'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear', 'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear', + 'duration': 127, + 'series': 'Style.com Fashion Shows', + 'season': 'Ready To Wear Spring 2013', + 'tags': list, + 'categories': list, }, } @@ -32,21 +40,29 @@ class TheSceneIE(InfoExtractor): player = self._download_webpage(player_url, display_id) info = self._parse_json( self._search_regex( - r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'), + r'(?m)video\s*:\s*({.+?}),$', player, 'info json'), display_id) + video_id = info['id'] + title = info['title'] + qualities_order = qualities(('low', 'high')) formats = [{ 'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']), 'url': f['src'], 'quality': qualities_order(f['quality']), - } for f in info['sources'][0]] + } for f in info['sources']] self._sort_formats(formats) return { - 'id': info['id'], + 'id': video_id, 'display_id': display_id, - 'title': info['title'], + 'title': title, 'formats': formats, 'thumbnail': info.get('poster_frame'), + 'duration': int_or_none(info.get('duration')), + 'series': info.get('series_title'), + 'season': info.get('season_title'), + 'tags': info.get('tags'), + 'categories': info.get('categories'), } diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py index 4473a3c..33683b1 100644 --- a/youtube_dl/extractor/thisav.py +++ b/youtube_dl/extractor/thisav.py @@ -3,13 +3,14 @@ from __future__ import unicode_literals import re -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import remove_end -class ThisAVIE(JWPlatformBaseIE): +class ThisAVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*' _TESTS = [{ + # jwplayer 'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html', 'md5': '0480f1ef3932d901f0e0e719f188f19b', 'info_dict': { @@ -20,6 +21,7 @@ class ThisAVIE(JWPlatformBaseIE): 'uploader_id': 'dj7970' } }, { + # html5 media 'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html', 'md5': 'ba90c076bd0f80203679e5b60bf523ee', 'info_dict': { @@ -48,8 +50,12 @@ class ThisAVIE(JWPlatformBaseIE): }], } else: - info_dict = self._extract_jwplayer_data( - webpage, video_id, require_title=False) + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info_dict = entries[0] + else: + info_dict = self._extract_jwplayer_data( + webpage, video_id, require_title=False) uploader = self._html_search_regex( r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>', webpage, 'uploader name', fatal=False) diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py index 3a37df2..c44018a 100644 --- a/youtube_dl/extractor/tubitv.py +++ b/youtube_dl/extractor/tubitv.py @@ -16,6 +16,7 @@ class TubiTvIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video/(?P<id>[0-9]+)' _LOGIN_URL = 'http://tubitv.com/login' _NETRC_MACHINE = 'tubitv' + _GEO_COUNTRIES = ['US'] _TEST = { 'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday', 'md5': '43ac06be9326f41912dc64ccf7a80320', diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py index ad79db9..7aeb2c6 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -24,6 +24,7 @@ class TV4IE(InfoExtractor): sport/| ) )(?P<id>[0-9]+)''' + _GEO_COUNTRIES = ['SE'] _TESTS = [ { 'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650', @@ -71,16 +72,12 @@ class TV4IE(InfoExtractor): 'http://www.tv4play.se/player/assets/%s.json' % video_id, video_id, 'Downloading video info JSON') - # If is_geo_restricted is true, it doesn't necessarily mean we can't download it - if info.get('is_geo_restricted'): - self.report_warning('This content might not be available in your country due to licensing restrictions.') - title = info['title'] subtitles = {} formats = [] # http formats are linked with unresolvable host - for kind in ('hls', ''): + for kind in ('hls3', ''): data = self._download_json( 'https://prima.tv4play.se/api/web/asset/%s/play.json' % video_id, video_id, 'Downloading sources JSON', query={ @@ -113,6 +110,10 @@ class TV4IE(InfoExtractor): 'url': manifest_url, 'ext': 'vtt', }]}) + + if not formats and info.get('is_geo_restricted'): + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py new file mode 100644 index 0000000..12ed603 --- /dev/null +++ b/youtube_dl/extractor/tvn24.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unescapeHTML, +) + + +class TVN24IE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)\.html' + _TESTS = [{ + 'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html', + 'md5': 'fbdec753d7bc29d96036808275f2130c', + 'info_dict': { + 'id': '1584444', + 'ext': 'mp4', + 'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"', + 'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości "Szkła kontaktowego".', + 'thumbnail': 're:http://.*[.]jpeg', + } + }, { + 'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html', + 'only_matching': True, + }, { + 'url': 'http://sport.tvn24.pl/pilka-nozna,105/ligue-1-kamil-glik-rozcial-glowe-monaco-tylko-remisuje-z-bastia,716522.html', + 'only_matching': True, + }, { + 'url': 'http://tvn24bis.pl/poranek,146,m/gen-koziej-w-tvn24-bis-wracamy-do-czasow-zimnej-wojny,715660.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + + def extract_json(attr, name, fatal=True): + return self._parse_json( + self._search_regex( + r'\b%s=(["\'])(?P<json>(?!\1).+?)\1' % attr, webpage, + name, group='json', fatal=fatal) or '{}', + video_id, transform_source=unescapeHTML, fatal=fatal) + + quality_data = extract_json('data-quality', 'formats') + + formats = [] + for format_id, url in quality_data.items(): + formats.append({ + 'url': url, + 'format_id': format_id, + 'height': int_or_none(format_id.rstrip('p')), + }) + self._sort_formats(formats) + + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail( + webpage, default=None) or self._html_search_regex( + r'\bdata-poster=(["\'])(?P<url>(?!\1).+?)\1', webpage, + 'thumbnail', group='url') + + share_params = extract_json( + 'data-share-params', 'share params', fatal=False) + if isinstance(share_params, dict): + video_id = share_params.get('id') or video_id + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tvnoe.py b/youtube_dl/extractor/tvnoe.py index 6d5c748..1a5b76b 100644 --- a/youtube_dl/extractor/tvnoe.py +++ b/youtube_dl/extractor/tvnoe.py @@ -1,7 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( clean_html, get_element_by_class, @@ -9,7 +9,7 @@ from ..utils import ( ) -class TVNoeIE(JWPlatformBaseIE): +class TVNoeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)' _TEST = { 'url': 'http://www.tvnoe.cz/video/10362', diff --git a/youtube_dl/extractor/tvplayer.py b/youtube_dl/extractor/tvplayer.py new file mode 100644 index 0000000..b653714 --- /dev/null +++ b/youtube_dl/extractor/tvplayer.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + extract_attributes, + urlencode_postdata, + ExtractorError, +) + + +class TVPlayerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tvplayer\.com/watch/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'http://tvplayer.com/watch/bbcone', + 'info_dict': { + 'id': '89', + 'ext': 'mp4', + 'title': r're:^BBC One [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + current_channel = extract_attributes(self._search_regex( + r'(<div[^>]+class="[^"]*current-channel[^"]*"[^>]*>)', + webpage, 'channel element')) + title = current_channel['data-name'] + + resource_id = self._search_regex( + r'resourceId\s*=\s*"(\d+)"', webpage, 'resource id') + platform = self._search_regex( + r'platform\s*=\s*"([^"]+)"', webpage, 'platform') + token = self._search_regex( + r'token\s*=\s*"([^"]+)"', webpage, 'token', default='null') + validate = self._search_regex( + r'validate\s*=\s*"([^"]+)"', webpage, 'validate', default='null') + + try: + response = self._download_json( + 'http://api.tvplayer.com/api/v2/stream/live', + resource_id, headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + }, data=urlencode_postdata({ + 'service': 1, + 'platform': platform, + 'id': resource_id, + 'token': token, + 'validate': validate, + }))['tvplayer']['response'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + response = self._parse_json( + e.cause.read().decode(), resource_id)['tvplayer']['response'] + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, response['error']), expected=True) + raise + + formats = self._extract_m3u8_formats(response['stream'], resource_id, 'mp4') + self._sort_formats(formats) + + return { + 'id': resource_id, + 'display_id': display_id, + 'title': self._live_title(title), + 'formats': formats, + 'is_live': True, + } diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index a983ebf..f3541b6 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -12,7 +12,7 @@ from ..utils import ( class TwentyFourVideoIE(InfoExtractor): IE_NAME = '24video' - _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex|tube)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.24video.net/video/view/1044982', @@ -37,6 +37,9 @@ class TwentyFourVideoIE(InfoExtractor): }, { 'url': 'http://www.24video.me/video/view/1044982', 'only_matching': True, + }, { + 'url': 'http://www.24video.tube/video/view/2363750', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index bef6394..8152ace 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -20,6 +20,7 @@ class Vbox7IE(InfoExtractor): ) (?P<id>[\da-fA-F]+) ''' + _GEO_COUNTRIES = ['BG'] _TESTS = [{ 'url': 'http://vbox7.com/play:0946fff23c', 'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf', @@ -78,7 +79,7 @@ class Vbox7IE(InfoExtractor): video_url = video['src'] if '/na.mp4' in video_url: - self.raise_geo_restricted() + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) uploader = video.get('uploader') diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 8a574bc..0f8c156 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -14,6 +14,7 @@ from ..utils import ( class VGTVIE(XstreamIE): IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet' + _GEO_BYPASS = False _HOST_TO_APPNAME = { 'vgtv.no': 'vgtv', @@ -217,7 +218,8 @@ class VGTVIE(XstreamIE): properties = try_get( data, lambda x: x['streamConfiguration']['properties'], list) if properties and 'geoblocked' in properties: - raise self.raise_geo_restricted() + raise self.raise_geo_restricted( + countries=[host.rpartition('.')[-1].partition('/')[0].upper()]) self._sort_formats(info['formats']) diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 8a00c8f..f0a7fd7 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -70,10 +70,10 @@ class ViceBaseIE(AdobePassIE): 'url': uplynk_preplay_url, 'id': video_id, 'title': title, - 'description': base.get('body'), + 'description': base.get('body') or base.get('display_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')), + 'duration': int_or_none(video_data.get('video_duration')) or parse_duration(watch_hub_data.get('video-duration')), + 'timestamp': int_or_none(video_data.get('created_at'), 1000), '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')), diff --git a/youtube_dl/extractor/viceland.py b/youtube_dl/extractor/viceland.py index 0eff055..87f9216 100644 --- a/youtube_dl/extractor/viceland.py +++ b/youtube_dl/extractor/viceland.py @@ -7,16 +7,16 @@ from .vice import ViceBaseIE 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', + 'url': 'https://www.viceland.com/en_us/video/trapped/588a70d0dba8a16007de7316', 'info_dict': { - 'id': '57608447973ee7705f6fbd4e', + 'id': '588a70d0dba8a16007de7316', 'ext': 'mp4', - 'title': 'CYBERWAR (Trailer)', - 'description': 'Tapping into the geopolitics of hacking and surveillance, Ben Makuch travels the world to meet with hackers, government officials, and dissidents to investigate the ecosystem of cyberwarfare.', + 'title': 'TRAPPED (Series Trailer)', + 'description': 'md5:7a8e95c2b6cd86461502a2845e581ccf', 'age_limit': 14, - 'timestamp': 1466008539, - 'upload_date': '20160615', - 'uploader_id': '11', + 'timestamp': 1485474122, + 'upload_date': '20170126', + 'uploader_id': '57a204098cb727dec794c6a3', 'uploader': 'Viceland', }, 'params': { diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index 9950c62..d055629 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re -from .jwplatform import JWPlatformBaseIE +from .common import InfoExtractor from ..utils import ( decode_packed_codes, js_to_json, @@ -12,8 +12,8 @@ from ..utils import ( ) -class VidziIE(JWPlatformBaseIE): - _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' +class VidziIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://vidzi.tv/cghql9yq6emu.html', 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', @@ -29,6 +29,9 @@ class VidziIE(JWPlatformBaseIE): }, { 'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html', 'skip_download': True, + }, { + 'url': 'http://vidzi.cc/cghql9yq6emu.html', + 'skip_download': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py index 52dd95e..fcf0cb1 100644 --- a/youtube_dl/extractor/viewster.py +++ b/youtube_dl/extractor/viewster.py @@ -86,7 +86,9 @@ class ViewsterIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) # Get 'api_token' cookie - self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id) + self._request_webpage( + HEADRequest('http://www.viewster.com/'), + video_id, headers=self.geo_verification_headers()) cookies = self._get_cookies('http://www.viewster.com/') self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 9c48701..e9c8bf8 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -27,6 +27,7 @@ class VikiBaseIE(InfoExtractor): _APP_VERSION = '2.2.5.1428709186' _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)' + _GEO_BYPASS = False _NETRC_MACHINE = 'viki' _token = None @@ -77,8 +78,11 @@ class VikiBaseIE(InfoExtractor): def _check_errors(self, data): for reason, status in data.get('blocking', {}).items(): if status and reason in self._ERRORS: + message = self._ERRORS[reason] + if reason == 'geo': + self.raise_geo_restricted(msg=message) raise ExtractorError('%s said: %s' % ( - self.IE_NAME, self._ERRORS[reason]), expected=True) + self.IE_NAME, message), expected=True) def _real_initialize(self): self._login() diff --git a/youtube_dl/extractor/vodpl.py b/youtube_dl/extractor/vodpl.py new file mode 100644 index 0000000..9e91970 --- /dev/null +++ b/youtube_dl/extractor/vodpl.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .onet import OnetBaseIE + + +class VODPlIE(OnetBaseIE): + _VALID_URL = r'https?://vod\.pl/(?:[^/]+/)+(?P<id>[0-9a-zA-Z]+)' + + _TESTS = [{ + 'url': 'https://vod.pl/filmy/chlopaki-nie-placza/3ep3jns', + 'md5': 'a7dc3b2f7faa2421aefb0ecaabf7ec74', + 'info_dict': { + 'id': '3ep3jns', + 'ext': 'mp4', + 'title': 'Chłopaki nie płaczą', + 'description': 'md5:f5f03b84712e55f5ac9f0a3f94445224', + 'timestamp': 1463415154, + 'duration': 5765, + 'upload_date': '20160516', + }, + }, { + 'url': 'https://vod.pl/seriale/belfer-na-planie-praca-kamery-online/2c10heh', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + info_dict = self._extract_from_id(self._search_mvp_id(webpage), webpage) + info_dict['id'] = video_id + return info_dict diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 54eb514..c022fb3 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -1,10 +1,10 @@ from __future__ import unicode_literals +from .common import InfoExtractor from .youtube import YoutubeIE -from .jwplatform import JWPlatformBaseIE -class WimpIE(JWPlatformBaseIE): +class WimpIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://www.wimp.com/maru-is-exhausted/', diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 83bc1fe..5584674 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -44,6 +44,9 @@ class XTubeIE(InfoExtractor): }, { 'url': 'xtube:625837', 'only_matching': True, + }, { + 'url': 'xtube:kVTUy_G222_', + 'only_matching': True, }] def _real_extract(self, url): @@ -53,14 +56,20 @@ class XTubeIE(InfoExtractor): if not display_id: display_id = video_id - url = 'http://www.xtube.com/watch.php?v=%s' % video_id - req = sanitized_Request(url) - req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1') - webpage = self._download_webpage(req, display_id) + if video_id.isdigit() and len(video_id) < 11: + url_pattern = 'http://www.xtube.com/video-watch/-%s' + else: + url_pattern = 'http://www.xtube.com/watch.php?v=%s' + + webpage = self._download_webpage( + url_pattern % video_id, display_id, headers={ + 'Cookie': 'age_verified=1; cookiesAccepted=1', + }) sources = self._parse_json(self._search_regex( - r'sources\s*:\s*({.+?}),', webpage, 'sources'), video_id) + r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),', + webpage, 'sources', group='sources'), video_id) formats = [] for format_id, format_url in sources.items(): @@ -72,7 +81,7 @@ class XTubeIE(InfoExtractor): self._sort_formats(formats) title = self._search_regex( - (r'<h1>(?P<title>[^<]+)</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), webpage, 'title', group='title') description = self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) @@ -81,10 +90,10 @@ class XTubeIE(InfoExtractor): r'<span[^>]+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) duration = parse_duration(self._search_regex( - r'<dt>Runtime:</dt>\s*<dd>([^<]+)</dd>', + r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( - r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>', + r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>', webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( r'>Comments? \(([\d,\.]+)\)<', diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 7671093..dec0280 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -34,6 +34,7 @@ from ..utils import ( int_or_none, mimetype2ext, orderedSet, + parse_codecs, parse_duration, remove_quotes, remove_start, @@ -1696,15 +1697,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): codecs = mobj.group('val') break if codecs: - codecs = codecs.split(',') - if len(codecs) == 2: - acodec, vcodec = codecs[1], codecs[0] - else: - acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0]) - dct.update({ - 'acodec': acodec, - 'vcodec': vcodec, - }) + dct.update(parse_codecs(codecs)) formats.append(dct) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index a365923..523bb5c 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -20,9 +20,9 @@ from ..utils import ( class ZDFBaseIE(InfoExtractor): - def _call_api(self, url, player, referrer, video_id): + def _call_api(self, url, player, referrer, video_id, item): return self._download_json( - url, video_id, 'Downloading JSON content', + url, video_id, 'Downloading JSON %s' % item, headers={ 'Referer': referrer, 'Api-Auth': 'Bearer %s' % player['apiToken'], @@ -104,7 +104,7 @@ class ZDFIE(ZDFBaseIE): }) formats.append(f) - def _extract_entry(self, url, content, video_id): + def _extract_entry(self, url, player, content, video_id): title = content.get('title') or content['teaserHeadline'] t = content['mainVideoContent']['http://zdf.de/rels/target'] @@ -116,7 +116,8 @@ class ZDFIE(ZDFBaseIE): 'http://zdf.de/rels/streams/ptmd-template'].replace( '{playerId}', 'portal') - ptmd = self._download_json(urljoin(url, ptmd_path), video_id) + ptmd = self._call_api( + urljoin(url, ptmd_path), player, url, video_id, 'metadata') formats = [] track_uris = set() @@ -174,8 +175,9 @@ class ZDFIE(ZDFBaseIE): } def _extract_regular(self, url, player, video_id): - content = self._call_api(player['content'], player, url, video_id) - return self._extract_entry(player['content'], content, video_id) + content = self._call_api( + player['content'], player, url, video_id, 'content') + return self._extract_entry(player['content'], player, content, video_id) def _extract_mobile(self, video_id): document = self._download_json( |