diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 632129bc6..a8d515f5c 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -44,6 +44,7 @@ from ..utils import ( join_nonempty, mimetype2ext, network_exceptions, + NO_DEFAULT, orderedSet, parse_codecs, parse_count, @@ -3116,508 +3117,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return info +class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): -class YoutubeTabIE(YoutubeBaseInfoExtractor): - IE_DESC = 'YouTube Tabs' - _VALID_URL = r'''(?x) - https?:// - (?:\w+\.)? - (?: - youtube(?:kids)?\.com| - %(invidious)s - )/ - (?: - (?Pchannel|c|user|browse)/| - (?P - feed/|hashtag/| - (?:playlist|watch)\?.*?\blist= - )| - (?!(?:%(reserved_names)s)\b) # Direct URLs - ) - (?P[^/?\#&]+) - ''' % { - 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES, - 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), - } - IE_NAME = 'youtube:tab' - - _TESTS = [{ - 'note': 'playlists, multipage', - 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', - 'playlist_mincount': 94, - 'info_dict': { - 'id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'title': 'Игорь Клейнер - Playlists', - 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', - 'uploader': 'Игорь Клейнер', - 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', - }, - }, { - 'note': 'playlists, multipage, different order', - 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', - 'playlist_mincount': 94, - 'info_dict': { - 'id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'title': 'Игорь Клейнер - Playlists', - 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', - 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'uploader': 'Игорь Клейнер', - }, - }, { - 'note': 'playlists, series', - 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', - 'playlist_mincount': 5, - 'info_dict': { - 'id': 'UCYO_jab_esuFRV4b17AJtAw', - 'title': '3Blue1Brown - Playlists', - 'description': 'md5:e1384e8a133307dd10edee76e875d62f', - 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', - 'uploader': '3Blue1Brown', - }, - }, { - 'note': 'playlists, singlepage', - 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', - 'playlist_mincount': 4, - 'info_dict': { - 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', - 'title': 'ThirstForScience - Playlists', - 'description': 'md5:609399d937ea957b0f53cbffb747a14c', - 'uploader': 'ThirstForScience', - 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', - } - }, { - 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', - 'only_matching': True, - }, { - 'note': 'basic, single video playlist', - 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', - 'info_dict': { - 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', - 'uploader': 'Sergey M.', - 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', - 'title': 'youtube-dl public playlist', - }, - 'playlist_count': 1, - }, { - 'note': 'empty playlist', - 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', - 'info_dict': { - 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', - 'uploader': 'Sergey M.', - 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', - 'title': 'youtube-dl empty playlist', - }, - 'playlist_count': 0, - }, { - 'note': 'Home tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Home', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - }, - 'playlist_mincount': 2, - }, { - 'note': 'Videos tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Videos', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - }, - 'playlist_mincount': 975, - }, { - 'note': 'Videos tab, sorted by popular', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Videos', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - }, - 'playlist_mincount': 199, - }, { - 'note': 'Playlists tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Playlists', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - }, - 'playlist_mincount': 17, - }, { - 'note': 'Community tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Community', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - }, - 'playlist_mincount': 18, - }, { - 'note': 'Channels tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Channels', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - }, - 'playlist_mincount': 12, - }, { - 'note': 'Search tab', - 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', - 'playlist_mincount': 40, - 'info_dict': { - 'id': 'UCYO_jab_esuFRV4b17AJtAw', - 'title': '3Blue1Brown - Search - linear algebra', - 'description': 'md5:e1384e8a133307dd10edee76e875d62f', - 'uploader': '3Blue1Brown', - 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', - }, - }, { - 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'only_matching': True, - }, { - 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'only_matching': True, - }, { - 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'only_matching': True, - }, { - 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', - 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', - 'info_dict': { - 'title': '29C3: Not my department', - 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', - 'uploader': 'Christiaan008', - 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', - 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', - }, - 'playlist_count': 96, - }, { - 'note': 'Large playlist', - 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', - 'info_dict': { - 'title': 'Uploads from Cauchemar', - 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', - 'uploader': 'Cauchemar', - 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', - }, - 'playlist_mincount': 1123, - }, { - 'note': 'even larger playlist, 8832 videos', - 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', - 'only_matching': True, - }, { - 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', - 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', - 'info_dict': { - 'title': 'Uploads from Interstellar Movie', - 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', - 'uploader': 'Interstellar Movie', - 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', - }, - 'playlist_mincount': 21, - }, { - 'note': 'Playlist with "show unavailable videos" button', - 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', - 'info_dict': { - 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', - 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', - 'uploader': 'Phim Siêu Nhân Nhật Bản', - 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', - }, - 'playlist_mincount': 200, - }, { - 'note': 'Playlist with unavailable videos in page 7', - 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', - 'info_dict': { - 'title': 'Uploads from BlankTV', - 'id': 'UU8l9frL61Yl5KFOl87nIm2w', - 'uploader': 'BlankTV', - 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', - }, - 'playlist_mincount': 1000, - }, { - 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', - 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'info_dict': { - 'title': 'Data Analysis with Dr Mike Pound', - 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', - 'uploader': 'Computerphile', - 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', - }, - 'playlist_mincount': 11, - }, { - 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', - 'only_matching': True, - }, { - 'note': 'Playlist URL that does not actually serve a playlist', - 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', - 'info_dict': { - 'id': 'FqZTN594JQw', - 'ext': 'webm', - 'title': "Smiley's People 01 detective, Adventure Series, Action", - 'uploader': 'STREEM', - 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', - 'upload_date': '20150526', - 'license': 'Standard YouTube License', - 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', - 'categories': ['People & Blogs'], - 'tags': list, - 'view_count': int, - 'like_count': int, - 'dislike_count': int, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'This video is not available.', - 'add_ie': [YoutubeIE.ie_key()], - }, { - 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', - 'info_dict': { - 'id': '3yImotZU3tw', # This will keep changing - 'ext': 'mp4', - 'title': compat_str, - 'uploader': 'Sky News', - 'uploader_id': 'skynews', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', - 'upload_date': r're:\d{8}', - 'description': compat_str, - 'categories': ['News & Politics'], - 'tags': list, - 'like_count': int, - 'dislike_count': int, - }, - 'params': { - 'skip_download': True, - }, - 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '], - }, { - 'url': 'https://www.youtube.com/user/TheYoungTurks/live', - 'info_dict': { - 'id': 'a48o2S1cPoo', - 'ext': 'mp4', - 'title': 'The Young Turks - Live Main Show', - 'uploader': 'The Young Turks', - 'uploader_id': 'TheYoungTurks', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', - 'upload_date': '20150715', - 'license': 'Standard YouTube License', - 'description': 'md5:438179573adcdff3c97ebb1ee632b891', - 'categories': ['News & Politics'], - 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], - 'like_count': int, - 'dislike_count': int, - }, - 'params': { - 'skip_download': True, - }, - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', - 'only_matching': True, - }, { - 'note': 'A channel that is not live. Should raise error', - 'url': 'https://www.youtube.com/user/numberphile/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/trending', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/library', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/history', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/subscriptions', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/watch_later', - 'only_matching': True, - }, { - 'note': 'Recommended - redirects to home page.', - 'url': 'https://www.youtube.com/feed/recommended', - 'only_matching': True, - }, { - 'note': 'inline playlist with not always working continuations', - 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/course', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/zsecurity', - 'only_matching': True, - }, { - 'url': 'http://www.youtube.com/NASAgovVideo/videos', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/TheYoungTurks/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/hashtag/cctv9', - 'info_dict': { - 'id': 'cctv9', - 'title': '#cctv9', - }, - 'playlist_mincount': 350, - }, { - 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', - 'only_matching': True, - }, { - 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', - 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', - 'only_matching': True - }, { - 'note': '/browse/ should redirect to /channel/', - 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', - 'only_matching': True - }, { - 'note': 'VLPL, should redirect to playlist?list=PL...', - 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', - 'info_dict': { - 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', - 'uploader': 'NoCopyrightSounds', - 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', - 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', - 'title': 'NCS Releases', - }, - 'playlist_mincount': 166, - }, { - 'note': 'Topic, should redirect to playlist?list=UU...', - 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', - 'info_dict': { - 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', - 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', - 'title': 'Uploads from Royalty Free Music - Topic', - 'uploader': 'Royalty Free Music - Topic', - }, - 'expected_warnings': [ - 'A channel/user page was given', - 'The URL does not have a videos tab', - ], - 'playlist_mincount': 101, - }, { - 'note': 'Topic without a UU playlist', - 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', - 'info_dict': { - 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', - 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', - }, - 'expected_warnings': [ - 'A channel/user page was given', - 'The URL does not have a videos tab', - 'Falling back to channel URL', - ], - 'playlist_mincount': 9, - }, { - 'note': 'Youtube music Album', - 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', - 'info_dict': { - 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', - 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', - }, - 'playlist_count': 50, - }, { - 'note': 'unlisted single video playlist', - 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', - 'info_dict': { - 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', - 'uploader': 'colethedj', - 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', - 'title': 'yt-dlp unlisted playlist test', - 'availability': 'unlisted' - }, - 'playlist_count': 1, - }, { - 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', - 'url': 'https://www.youtube.com/feed/recommended', - 'info_dict': { - 'id': 'recommended', - 'title': 'recommended', - }, - 'playlist_mincount': 50, - 'params': { - 'skip_download': True, - 'extractor_args': {'youtubetab': {'skip': ['webpage']}} - }, - }, { - 'note': 'API Fallback: /videos tab, sorted by oldest first', - 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', - 'info_dict': { - 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', - 'title': 'Cody\'sLab - Videos', - 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', - 'uploader': 'Cody\'sLab', - 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', - }, - 'playlist_mincount': 650, - 'params': { - 'skip_download': True, - 'extractor_args': {'youtubetab': {'skip': ['webpage']}} - }, - }, { - 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', - 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', - 'info_dict': { - 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', - 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', - 'title': 'Uploads from Royalty Free Music - Topic', - 'uploader': 'Royalty Free Music - Topic', - }, - 'expected_warnings': [ - 'A channel/user page was given', - 'The URL does not have a videos tab', - ], - 'playlist_mincount': 101, - 'params': { - 'skip_download': True, - 'extractor_args': {'youtubetab': {'skip': ['webpage']}} - }, - }] - - @classmethod - def suitable(cls, url): - return False if YoutubeIE.suitable(url) else super( - YoutubeTabIE, cls).suitable(url) - - def _extract_channel_id(self, webpage): - channel_id = self._html_search_meta( - 'channelId', webpage, 'channel id', default=None) - if channel_id: - return channel_id - channel_url = self._html_search_meta( - ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', - 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', - 'twitter:app:url:googleplay'), webpage, 'channel url') - return self._search_regex( - r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', - channel_url, 'channel id') + def _extract_channel_id(self, webpage): + channel_id = self._html_search_meta( + 'channelId', webpage, 'channel id', default=None) + if channel_id: + return channel_id + channel_url = self._html_search_meta( + ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', + 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', + 'twitter:app:url:googleplay'), webpage, 'channel url') + return self._search_regex( + r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', + channel_url, 'channel id') @staticmethod def _extract_basic_item_renderer(item): @@ -3787,49 +3300,51 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor): if entry: yield entry ''' - def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): - - def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds - contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] - for content in contents: - if not isinstance(content, dict): - continue - is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict) - if not is_renderer: - renderer = content.get('richItemRenderer') - if renderer: - for entry in self._rich_entries(renderer): - yield entry - continuation_list[0] = self._extract_continuation(parent_renderer) + def _extract_entries(self, parent_renderer, continuation_list): + # continuation_list is modified in-place with continuation_list = [continuation_token] + continuation_list[:] = [None] + contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] + for content in contents: + if not isinstance(content, dict): + continue + is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict) + if not is_renderer: + renderer = content.get('richItemRenderer') + if renderer: + for entry in self._rich_entries(renderer): + yield entry + continuation_list[0] = self._extract_continuation(parent_renderer) + continue + isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] + for isr_content in isr_contents: + if not isinstance(isr_content, dict): continue - isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] - for isr_content in isr_contents: - if not isinstance(isr_content, dict): - continue - known_renderers = { - 'playlistVideoListRenderer': self._playlist_entries, - 'gridRenderer': self._grid_entries, - 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'), - 'backstagePostThreadRenderer': self._post_thread_entries, - 'videoRenderer': lambda x: [self._video_entry(x)], - } - for key, renderer in isr_content.items(): - if key not in known_renderers: - continue - for entry in known_renderers[key](renderer): - if entry: - yield entry - continuation_list[0] = self._extract_continuation(renderer) - break - - if not continuation_list[0]: - continuation_list[0] = self._extract_continuation(is_renderer) + known_renderers = { + 'playlistVideoListRenderer': self._playlist_entries, + 'gridRenderer': self._grid_entries, + 'shelfRenderer': lambda x: self._shelf_entries(x), + 'backstagePostThreadRenderer': self._post_thread_entries, + 'videoRenderer': lambda x: [self._video_entry(x)], + } + for key, renderer in isr_content.items(): + if key not in known_renderers: + continue + for entry in known_renderers[key](renderer): + if entry: + yield entry + continuation_list[0] = self._extract_continuation(renderer) + break if not continuation_list[0]: - continuation_list[0] = self._extract_continuation(parent_renderer) + continuation_list[0] = self._extract_continuation(is_renderer) + + if not continuation_list[0]: + continuation_list[0] = self._extract_continuation(parent_renderer) - continuation_list = [None] # Python 2 does not support nonlocal + def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): + continuation_list = [None] + extract_entries = lambda x: self._extract_entries(x, continuation_list) tab_content = try_get(tab, lambda x: x['content'], dict) if not tab_content: return @@ -4214,12 +3729,556 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor): raise ExtractorError(err_note, expected=True) self.report_warning(err_note, item_id) - @staticmethod - def _smuggle_data(entries, data): - for entry in entries: - if data: - entry['url'] = smuggle_url(entry['url'], data) - yield entry + @staticmethod + def _smuggle_data(entries, data): + for entry in entries: + if data: + entry['url'] = smuggle_url(entry['url'], data) + yield entry + + _SEARCH_PARAMS = None + + def _search_results(self, query, params=NO_DEFAULT): + data = {'query': query} + if params is NO_DEFAULT: + params = self._SEARCH_PARAMS + if params: + data['params'] = params + continuation = {} + for page_num in itertools.count(1): + data.update(continuation) + search = self._extract_response( + item_id='query "%s" page %s' % (query, page_num), ep='search', query=data, + check_get_keys=('contents', 'onResponseReceivedCommands') + ) + if not search: + break + slr_contents = try_get( + search, + (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'], + lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']), + list) + if not slr_contents: + break + + # Youtube sometimes adds promoted content to searches, + # changing the index location of videos and token. + # So we search through all entries till we find them. + continuation = None + for slr_content in slr_contents: + if not continuation: + continuation = self._extract_continuation({'contents': [slr_content]}) + + isr_contents = try_get( + slr_content, + lambda x: x['itemSectionRenderer']['contents'], + list) + if not isr_contents: + continue + for content in isr_contents: + if not isinstance(content, dict): + continue + video = content.get('videoRenderer') + if not isinstance(video, dict): + continue + video_id = video.get('videoId') + if not video_id: + continue + + yield self._extract_video(video) + + if not continuation: + break + + +class YoutubeTabIE(YoutubeTabBaseInfoExtractor): + IE_DESC = 'YouTube Tabs' + _VALID_URL = r'''(?x: + https?:// + (?:\w+\.)? + (?: + youtube(?:kids)?\.com| + %(invidious)s + )/ + (?: + (?Pchannel|c|user|browse)/| + (?P + feed/|hashtag/| + (?:playlist|watch)\?.*?\blist= + )| + (?!(?:%(reserved_names)s)\b) # Direct URLs + ) + (?P[^/?\#&]+) + )''' % { + 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES, + 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), + } + IE_NAME = 'youtube:tab' + + _TESTS = [{ + 'note': 'playlists, multipage', + 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', + 'playlist_mincount': 94, + 'info_dict': { + 'id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'title': 'Игорь Клейнер - Playlists', + 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', + 'uploader': 'Игорь Клейнер', + 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', + }, + }, { + 'note': 'playlists, multipage, different order', + 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', + 'playlist_mincount': 94, + 'info_dict': { + 'id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'title': 'Игорь Клейнер - Playlists', + 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', + 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'uploader': 'Игорь Клейнер', + }, + }, { + 'note': 'playlists, series', + 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', + 'playlist_mincount': 5, + 'info_dict': { + 'id': 'UCYO_jab_esuFRV4b17AJtAw', + 'title': '3Blue1Brown - Playlists', + 'description': 'md5:e1384e8a133307dd10edee76e875d62f', + 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', + 'uploader': '3Blue1Brown', + }, + }, { + 'note': 'playlists, singlepage', + 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', + 'playlist_mincount': 4, + 'info_dict': { + 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', + 'title': 'ThirstForScience - Playlists', + 'description': 'md5:609399d937ea957b0f53cbffb747a14c', + 'uploader': 'ThirstForScience', + 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', + } + }, { + 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', + 'only_matching': True, + }, { + 'note': 'basic, single video playlist', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'info_dict': { + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'title': 'youtube-dl public playlist', + }, + 'playlist_count': 1, + }, { + 'note': 'empty playlist', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', + 'info_dict': { + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', + 'title': 'youtube-dl empty playlist', + }, + 'playlist_count': 0, + }, { + 'note': 'Home tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Home', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + }, + 'playlist_mincount': 2, + }, { + 'note': 'Videos tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Videos', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + }, + 'playlist_mincount': 975, + }, { + 'note': 'Videos tab, sorted by popular', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Videos', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + }, + 'playlist_mincount': 199, + }, { + 'note': 'Playlists tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Playlists', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + }, + 'playlist_mincount': 17, + }, { + 'note': 'Community tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Community', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + }, + 'playlist_mincount': 18, + }, { + 'note': 'Channels tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Channels', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + }, + 'playlist_mincount': 12, + }, { + 'note': 'Search tab', + 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', + 'playlist_mincount': 40, + 'info_dict': { + 'id': 'UCYO_jab_esuFRV4b17AJtAw', + 'title': '3Blue1Brown - Search - linear algebra', + 'description': 'md5:e1384e8a133307dd10edee76e875d62f', + 'uploader': '3Blue1Brown', + 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', + }, + }, { + 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', + 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'info_dict': { + 'title': '29C3: Not my department', + 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'uploader': 'Christiaan008', + 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', + 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', + }, + 'playlist_count': 96, + }, { + 'note': 'Large playlist', + 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', + 'info_dict': { + 'title': 'Uploads from Cauchemar', + 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', + 'uploader': 'Cauchemar', + 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', + }, + 'playlist_mincount': 1123, + }, { + 'note': 'even larger playlist, 8832 videos', + 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', + 'only_matching': True, + }, { + 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', + 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', + 'info_dict': { + 'title': 'Uploads from Interstellar Movie', + 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', + 'uploader': 'Interstellar Movie', + 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', + }, + 'playlist_mincount': 21, + }, { + 'note': 'Playlist with "show unavailable videos" button', + 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', + 'info_dict': { + 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', + 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', + 'uploader': 'Phim Siêu Nhân Nhật Bản', + 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', + }, + 'playlist_mincount': 200, + }, { + 'note': 'Playlist with unavailable videos in page 7', + 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', + 'info_dict': { + 'title': 'Uploads from BlankTV', + 'id': 'UU8l9frL61Yl5KFOl87nIm2w', + 'uploader': 'BlankTV', + 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', + }, + 'playlist_mincount': 1000, + }, { + 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', + 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'info_dict': { + 'title': 'Data Analysis with Dr Mike Pound', + 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', + 'uploader': 'Computerphile', + 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', + }, + 'playlist_mincount': 11, + }, { + 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'only_matching': True, + }, { + 'note': 'Playlist URL that does not actually serve a playlist', + 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', + 'info_dict': { + 'id': 'FqZTN594JQw', + 'ext': 'webm', + 'title': "Smiley's People 01 detective, Adventure Series, Action", + 'uploader': 'STREEM', + 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', + 'upload_date': '20150526', + 'license': 'Standard YouTube License', + 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', + 'categories': ['People & Blogs'], + 'tags': list, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'This video is not available.', + 'add_ie': [YoutubeIE.ie_key()], + }, { + 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', + 'info_dict': { + 'id': '3yImotZU3tw', # This will keep changing + 'ext': 'mp4', + 'title': compat_str, + 'uploader': 'Sky News', + 'uploader_id': 'skynews', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', + 'upload_date': r're:\d{8}', + 'description': compat_str, + 'categories': ['News & Politics'], + 'tags': list, + 'like_count': int, + 'dislike_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '], + }, { + 'url': 'https://www.youtube.com/user/TheYoungTurks/live', + 'info_dict': { + 'id': 'a48o2S1cPoo', + 'ext': 'mp4', + 'title': 'The Young Turks - Live Main Show', + 'uploader': 'The Young Turks', + 'uploader_id': 'TheYoungTurks', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', + 'upload_date': '20150715', + 'license': 'Standard YouTube License', + 'description': 'md5:438179573adcdff3c97ebb1ee632b891', + 'categories': ['News & Politics'], + 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], + 'like_count': int, + 'dislike_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', + 'only_matching': True, + }, { + 'note': 'A channel that is not live. Should raise error', + 'url': 'https://www.youtube.com/user/numberphile/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/trending', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/library', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/history', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/subscriptions', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/watch_later', + 'only_matching': True, + }, { + 'note': 'Recommended - redirects to home page.', + 'url': 'https://www.youtube.com/feed/recommended', + 'only_matching': True, + }, { + 'note': 'inline playlist with not always working continuations', + 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/course', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/zsecurity', + 'only_matching': True, + }, { + 'url': 'http://www.youtube.com/NASAgovVideo/videos', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/TheYoungTurks/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/hashtag/cctv9', + 'info_dict': { + 'id': 'cctv9', + 'title': '#cctv9', + }, + 'playlist_mincount': 350, + }, { + 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', + 'only_matching': True, + }, { + 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', + 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', + 'only_matching': True + }, { + 'note': '/browse/ should redirect to /channel/', + 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', + 'only_matching': True + }, { + 'note': 'VLPL, should redirect to playlist?list=PL...', + 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', + 'info_dict': { + 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', + 'uploader': 'NoCopyrightSounds', + 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', + 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', + 'title': 'NCS Releases', + }, + 'playlist_mincount': 166, + }, { + 'note': 'Topic, should redirect to playlist?list=UU...', + 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', + 'info_dict': { + 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', + 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', + 'title': 'Uploads from Royalty Free Music - Topic', + 'uploader': 'Royalty Free Music - Topic', + }, + 'expected_warnings': [ + 'A channel/user page was given', + 'The URL does not have a videos tab', + ], + 'playlist_mincount': 101, + }, { + 'note': 'Topic without a UU playlist', + 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', + 'info_dict': { + 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', + 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', + }, + 'expected_warnings': [ + 'A channel/user page was given', + 'The URL does not have a videos tab', + 'Falling back to channel URL', + ], + 'playlist_mincount': 9, + }, { + 'note': 'Youtube music Album', + 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', + 'info_dict': { + 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', + 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', + }, + 'playlist_count': 50, + }, { + 'note': 'unlisted single video playlist', + 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', + 'info_dict': { + 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', + 'uploader': 'colethedj', + 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', + 'title': 'yt-dlp unlisted playlist test', + 'availability': 'unlisted' + }, + 'playlist_count': 1, + }, { + 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', + 'url': 'https://www.youtube.com/feed/recommended', + 'info_dict': { + 'id': 'recommended', + 'title': 'recommended', + }, + 'playlist_mincount': 50, + 'params': { + 'skip_download': True, + 'extractor_args': {'youtubetab': {'skip': ['webpage']}} + }, + }, { + 'note': 'API Fallback: /videos tab, sorted by oldest first', + 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', + 'info_dict': { + 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', + 'title': 'Cody\'sLab - Videos', + 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', + 'uploader': 'Cody\'sLab', + 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', + }, + 'playlist_mincount': 650, + 'params': { + 'skip_download': True, + 'extractor_args': {'youtubetab': {'skip': ['webpage']}} + }, + }, { + 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', + 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', + 'info_dict': { + 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', + 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', + 'title': 'Uploads from Royalty Free Music - Topic', + 'uploader': 'Royalty Free Music - Topic', + }, + 'expected_warnings': [ + 'A channel/user page was given', + 'The URL does not have a videos tab', + ], + 'playlist_mincount': 101, + 'params': { + 'skip_download': True, + 'extractor_args': {'youtubetab': {'skip': ['webpage']}} + }, + }] + + @classmethod + def suitable(cls, url): + return False if YoutubeIE.suitable(url) else super( + YoutubeTabIE, cls).suitable(url) def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) @@ -4506,77 +4565,24 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): ie=YoutubeTabIE.ie_key()) -class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE): - IE_DESC = 'YouTube searches' +class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): + IE_DESC = 'YouTube search' IE_NAME = 'youtube:search' _SEARCH_KEY = 'ytsearch' _SEARCH_PARAMS = None _TESTS = [] - def _search_results(self, query): - data = {'query': query} - if self._SEARCH_PARAMS: - data['params'] = self._SEARCH_PARAMS - continuation = {} - for page_num in itertools.count(1): - data.update(continuation) - search = self._extract_response( - item_id='query "%s" page %s' % (query, page_num), ep='search', query=data, - check_get_keys=('contents', 'onResponseReceivedCommands') - ) - if not search: - break - slr_contents = try_get( - search, - (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'], - lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']), - list) - if not slr_contents: - break - - # Youtube sometimes adds promoted content to searches, - # changing the index location of videos and token. - # So we search through all entries till we find them. - continuation = None - for slr_content in slr_contents: - if not continuation: - continuation = self._extract_continuation({'contents': [slr_content]}) - - isr_contents = try_get( - slr_content, - lambda x: x['itemSectionRenderer']['contents'], - list) - if not isr_contents: - continue - for content in isr_contents: - if not isinstance(content, dict): - continue - video = content.get('videoRenderer') - if not isinstance(video, dict): - continue - video_id = video.get('videoId') - if not video_id: - continue - - yield self._extract_video(video) - - if not continuation: - break - - -class YoutubeSearchDateIE(YoutubeSearchIE): +class YoutubeSearchDateIE(SearchInfoExtractor, YoutubeTabBaseInfoExtractor): IE_NAME = YoutubeSearchIE.IE_NAME + ':date' _SEARCH_KEY = 'ytsearchdate' - IE_DESC = 'YouTube searches, newest videos first' + IE_DESC = 'YouTube search, newest videos first' _SEARCH_PARAMS = 'CAI%3D' -class YoutubeSearchURLIE(YoutubeSearchIE): +class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): IE_DESC = 'YouTube search URLs with sorting and filter support' IE_NAME = YoutubeSearchIE.IE_NAME + '_url' - _SEARCH_KEY = None _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)' - # _MAX_RESULTS = 100 _TESTS = [{ 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', 'playlist_mincount': 5, @@ -4589,15 +4595,10 @@ class YoutubeSearchURLIE(YoutubeSearchIE): 'only_matching': True, }] - @classmethod - def _make_valid_url(cls): - return cls._VALID_URL - def _real_extract(self, url): qs = parse_qs(url) query = (qs.get('search_query') or qs.get('q'))[0] - self._SEARCH_PARAMS = qs.get('sp', ('',))[0] - return self._get_n_results(query, self._MAX_RESULTS) + return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) class YoutubeFeedsInfoExtractor(YoutubeTabIE):