X-Git-Url: https://jfr.im/git/yt-dlp.git/blobdiff_plain/9bb856998b0d5a0ad58268f0ba8d784fb9d934e3..1c16d9df5330819cc79ad588b24aa5b72765c168:/yt_dlp/extractor/youtube.py diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 506bd1e19..ae4b58205 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -66,6 +66,7 @@ variadic, ) +STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client' # any clients starting with _ cannot be explicitly requested by the user INNERTUBE_CLIENTS = { 'web': { @@ -248,6 +249,11 @@ def _split_innertube_client(client_name): return client_name, base, variant[0] if variant else None +def short_client_name(client_name): + main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_') + return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper() + + def build_innertube_clients(): THIRD_PARTY = { 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL @@ -292,7 +298,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): """Provide base functions for Youtube extractors""" _RESERVED_NAMES = ( - r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|' + r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|' r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' r'browse|oembed|get_video_info|iframe_api|s/player|source|' r'storefront|oops|index|account|t/terms|about|upload|signin|logout') @@ -312,6 +318,40 @@ class YoutubeBaseInfoExtractor(InfoExtractor): r'(?:www\.)?invidious\.pussthecat\.org', r'(?:www\.)?invidious\.zee\.li', r'(?:www\.)?invidious\.ethibox\.fr', + r'(?:www\.)?iv\.ggtyler\.dev', + r'(?:www\.)?inv\.vern\.i2p', + r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion', + r'(?:www\.)?inv\.riverside\.rocks', + r'(?:www\.)?invidious\.silur\.me', + r'(?:www\.)?inv\.bp\.projectsegfau\.lt', + r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion', + r'(?:www\.)?invidious\.slipfox\.xyz', + r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion', + r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion', + r'(?:www\.)?invidious\.tiekoetter\.com', + r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion', + r'(?:www\.)?invidious\.nerdvpn\.de', + r'(?:www\.)?invidious\.weblibre\.org', + r'(?:www\.)?inv\.odyssey346\.dev', + r'(?:www\.)?invidious\.dhusch\.de', + r'(?:www\.)?iv\.melmac\.space', + r'(?:www\.)?watch\.thekitty\.zone', + r'(?:www\.)?invidious\.privacydev\.net', + r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion', + r'(?:www\.)?invidious\.drivet\.xyz', + r'(?:www\.)?vid\.priv\.au', + r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion', + r'(?:www\.)?inv\.vern\.cc', + r'(?:www\.)?invidious\.esmailelbob\.xyz', + r'(?:www\.)?invidious\.sethforprivacy\.com', + r'(?:www\.)?yt\.oelrichsgarcia\.de', + r'(?:www\.)?yt\.artemislena\.eu', + r'(?:www\.)?invidious\.flokinet\.to', + r'(?:www\.)?invidious\.baczek\.me', + r'(?:www\.)?y\.com\.sb', + r'(?:www\.)?invidious\.epicsite\.xyz', + r'(?:www\.)?invidious\.lidarshield\.cloud', + r'(?:www\.)?yt\.funami\.tech', r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', @@ -390,6 +430,17 @@ class YoutubeBaseInfoExtractor(InfoExtractor): r'(?:www\.)?piped\.qdi\.fi', r'(?:www\.)?piped\.video', r'(?:www\.)?piped\.aeong\.one', + r'(?:www\.)?piped\.moomoo\.me', + r'(?:www\.)?piped\.chauvet\.pro', + r'(?:www\.)?watch\.leptons\.xyz', + r'(?:www\.)?pd\.vern\.cc', + r'(?:www\.)?piped\.hostux\.net', + r'(?:www\.)?piped\.lunar\.icu', + # Hyperpipe instances from https://hyperpipe.codeberg.page/ + r'(?:www\.)?hyperpipe\.surge\.sh', + r'(?:www\.)?hyperpipe\.esmailelbob\.xyz', + r'(?:www\.)?listen\.whatever\.social', + r'(?:www\.)?music\.adminforge\.de', ) # extracted from account/account_menu ep @@ -406,6 +457,23 @@ class YoutubeBaseInfoExtractor(InfoExtractor): _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'} + _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en + _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}' + + def ucid_or_none(self, ucid): + return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None) + + def handle_or_none(self, handle): + return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None) + + def handle_from_url(self, url): + return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})', + url, 'channel handle', default=None) + + def ucid_from_url(self, url): + return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})', + url, 'channel id', default=None) + @functools.cached_property def _preferred_lang(self): """ @@ -745,7 +813,7 @@ def _extract_badges(self, renderer: dict): } badges = [] - for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer'), default=[]): + for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')): badge_type = ( privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str)) or badge_style_map.get(traverse_obj(badge, 'style')) @@ -785,7 +853,7 @@ def _get_text(data, *path_list, max_runs=None): runs = item runs = runs[:min(len(runs), max_runs or len(runs))] - text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[])) + text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str)) if text: return text @@ -805,7 +873,7 @@ def _extract_thumbnails(data, *path_list): """ thumbnails = [] for path in path_list or [()]: - for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]): + for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)): thumbnail_url = url_or_none(thumbnail.get('url')) if not thumbnail_url: continue @@ -911,7 +979,7 @@ def _extract_response(self, item_id, query, note='Downloading API JSON', headers @staticmethod def is_music_url(url): - return re.match(r'https?://music\.youtube\.com/', url) is not None + return re.match(r'(https?://)?music\.youtube\.com/', url) is not None def _extract_video(self, renderer): video_id = renderer.get('videoId') @@ -940,6 +1008,8 @@ def _extract_video(self, renderer): if not channel_id: channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId')) + channel_id = self.ucid_or_none(channel_id) + overlay_style = traverse_obj( renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str) @@ -968,6 +1038,13 @@ def _extract_video(self, renderer): else self._get_count({'simpleText': view_count_text})) view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count' + channel = (self._get_text(renderer, 'ownerText', 'shortBylineText') + or self._get_text(reel_header_renderer, 'channelTitleText')) + + channel_handle = traverse_obj(renderer, ( + 'shortBylineText', 'runs', ..., 'navigationEndpoint', + (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))), + expected_type=self.handle_from_url, get_all=False) return { '_type': 'url', 'ie_key': YoutubeIE.ie_key(), @@ -977,9 +1054,11 @@ def _extract_video(self, renderer): 'description': description, 'duration': duration, 'channel_id': channel_id, - 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText') - or self._get_text(reel_header_renderer, 'channelTitleText')), + 'channel': channel, 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None, + 'uploader': channel, + 'uploader_id': channel_handle, + 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'), 'timestamp': (self._parse_time_text(time_text) if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE) @@ -1012,7 +1091,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: - (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/ + (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/ |(?: # or the v= param in all its forms (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! @@ -1181,9 +1260,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'BaW_jenozKc', 'ext': 'mp4', 'title': 'youtube-dl test video "\'/\\ä↭𝕐', - 'uploader': 'Philipp Hagemeister', - 'uploader_id': 'phihag', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', 'channel': 'Philipp Hagemeister', 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', @@ -1202,7 +1278,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'start_time': 1, 'end_time': 9, 'comment_count': int, - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'Philipp Hagemeister', + 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister', + 'uploader_id': '@PhilippHagemeister', + 'heatmap': 'count:100', } }, { @@ -1214,9 +1294,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20120608', 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', - 'uploader': 'SET India', - 'uploader_id': 'setindia', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', 'age_limit': 18, }, 'skip': 'Private video', @@ -1228,9 +1305,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'BaW_jenozKc', 'ext': 'mp4', 'title': 'youtube-dl test video "\'/\\ä↭𝕐', - 'uploader': 'Philipp Hagemeister', - 'uploader_id': 'phihag', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', 'channel': 'Philipp Hagemeister', 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', @@ -1247,7 +1321,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'live_status': 'not_live', 'age_limit': 0, 'comment_count': int, - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'Philipp Hagemeister', + 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister', + 'uploader_id': '@PhilippHagemeister', }, 'params': { 'skip_download': True, @@ -1260,10 +1337,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'a9LDPn-MO4I', 'ext': 'm4a', 'upload_date': '20121002', - 'uploader_id': '8KVIDEO', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', 'description': '', - 'uploader': '8KVIDEO', 'title': 'UHDTV TEST 8K VIDEO.mp4' }, 'params': { @@ -1281,8 +1355,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', 'duration': 244, - 'uploader': 'AfrojackVEVO', - 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', 'abr': 129.495, 'like_count': int, @@ -1294,13 +1366,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'live_status': 'not_live', 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp', 'channel': 'Afrojack', - 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO', 'tags': 'count:19', 'availability': 'public', 'categories': ['Music'], 'age_limit': 0, 'alt_title': 'The Spark', - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'Afrojack', + 'uploader_url': 'https://www.youtube.com/@Afrojack', + 'uploader_id': '@Afrojack', }, 'params': { 'youtube_include_dash_manifest': True, @@ -1317,9 +1391,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', 'duration': 142, - 'uploader': 'The Witcher', - 'uploader_id': 'WitcherGame', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', 'upload_date': '20140605', 'age_limit': 18, 'categories': ['Gaming'], @@ -1333,7 +1404,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg', 'playable_in_embed': True, 'view_count': int, - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'The Witcher', + 'uploader_url': 'https://www.youtube.com/@thewitcher', + 'uploader_id': '@thewitcher', }, }, { @@ -1345,12 +1419,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Godzilla 2 (Official Video)', 'description': 'md5:bf77e03fcae5529475e500129b05668a', 'upload_date': '20200408', - 'uploader_id': 'FlyingKitty900', - 'uploader': 'FlyingKitty', 'age_limit': 18, 'availability': 'needs_auth', 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg', - 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900', 'channel': 'FlyingKitty', 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg', 'view_count': int, @@ -1361,7 +1432,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'like_count': int, 'duration': 177, 'playable_in_embed': True, - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'FlyingKitty', + 'uploader_url': 'https://www.youtube.com/@FlyingKitty900', + 'uploader_id': '@FlyingKitty900', + 'comment_count': int, }, }, { @@ -1372,13 +1447,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', 'ext': 'mp4', 'upload_date': '20191228', - 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', - 'uploader': 'Projekt Melody', 'description': 'md5:17eccca93a786d51bc67646756894066', 'age_limit': 18, 'like_count': int, 'availability': 'needs_auth', - 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', 'view_count': int, 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp', @@ -1390,7 +1462,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'duration': 106, 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', 'comment_count': int, - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'Projekt Melody', + 'uploader_url': 'https://www.youtube.com/@ProjektMelody', + 'uploader_id': '@ProjektMelody', }, }, { @@ -1400,8 +1475,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'MeJVWBSsPAY', 'ext': 'mp4', 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)', - 'uploader': 'Herr Lurik', - 'uploader_id': 'st3in234', 'description': 'Fan Video. Music & Lyrics by OOMPH!.', 'upload_date': '20130730', 'track': 'Such mich find mich', @@ -1418,11 +1491,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA', 'categories': ['Music'], 'availability': 'public', - 'uploader_url': 'http://www.youtube.com/user/st3in234', 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA', 'live_status': 'not_live', 'artist': 'OOMPH!', - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'Herr Lurik', + 'uploader_url': 'https://www.youtube.com/@HerrLurik', + 'uploader_id': '@HerrLurik', }, }, { @@ -1439,11 +1514,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'duration': 266, 'upload_date': '20100430', - 'uploader_id': 'deadmau5', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', 'creator': 'deadmau5', 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', - 'uploader': 'deadmau5', 'title': 'Deadmau5 - Some Chords (HD)', 'alt_title': 'Some Chords', 'availability': 'public', @@ -1461,7 +1533,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ', 'categories': ['Music'], 'album': 'Some Chords', - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'deadmau5', + 'uploader_url': 'https://www.youtube.com/@deadmau5', + 'uploader_id': '@deadmau5', }, 'expected_warnings': [ 'DASH manifest missing', @@ -1475,10 +1550,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'duration': 6085, 'upload_date': '20150827', - 'uploader_id': 'olympic', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', 'description': 'md5:04bbbf3ccceb6795947572ca36f45904', - 'uploader': 'Olympics', 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', 'like_count': int, 'release_timestamp': 1343767800, @@ -1494,7 +1566,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'live_status': 'was_live', 'view_count': int, 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q', - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': 'Olympics', + 'uploader_url': 'https://www.youtube.com/@Olympics', + 'uploader_id': '@Olympics', }, 'params': { 'skip_download': 'requires avconv', @@ -1509,10 +1584,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'stretched_ratio': 16 / 9., 'duration': 85, 'upload_date': '20110310', - 'uploader_id': 'AllenMeow', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', - 'uploader': '孫ᄋᄅ', 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', 'playable_in_embed': True, 'channel': '孫ᄋᄅ', @@ -1527,7 +1599,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'live_status': 'not_live', 'availability': 'unlisted', 'comment_count': int, - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader': '孫ᄋᄅ', + 'uploader_url': 'https://www.youtube.com/@AllenMeow', + 'uploader_id': '@AllenMeow', }, }, # url_encoded_fmt_stream_map is empty string @@ -1539,8 +1614,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', 'description': '', 'upload_date': '20150404', - 'uploader_id': 'spbelect', - 'uploader': 'Наблюдатели Петербурга', }, 'params': { 'skip_download': 'requires avconv', @@ -1557,9 +1630,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 'md5:116377fd2963b81ec4ce64b542173306', 'duration': 220, 'upload_date': '20150625', - 'uploader_id': 'dorappi2000', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', - 'uploader': 'dorappi2000', 'formats': 'mincount:31', }, 'skip': 'not actual anymore', @@ -1572,9 +1642,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'CsmdDsKjzN8', 'ext': 'mp4', 'upload_date': '20150501', # According to '[a-zA-Z0-9$]+)\(', r'\bm=(?P[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', r'\bc&&\(c=(?P[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', - r'(?:\b|[^a-zA-Z0-9$])(?P[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)', - r'(?:\b|[^a-zA-Z0-9$])(?P[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', + r'(?:\b|[^a-zA-Z0-9$])(?P[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?', r'(?P[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', # Obsolete patterns - r'(["\'])signature\1\s*,\s*(?P[a-zA-Z0-9$]+)\(', + r'("|\')signature\1\s*,\s*(?P[a-zA-Z0-9$]+)\(', r'\.sig\|\|(?P[a-zA-Z0-9$]+)\(', r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P[a-zA-Z0-9$]+)\(', r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P[a-zA-Z0-9$]+)\(', r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P[a-zA-Z0-9$]+)\(', r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') @@ -3129,11 +3234,11 @@ def _extract_chapters_from_json(self, data, duration): 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters' ), expected_type=list) - return self._extract_chapters( + return self._extract_chapters_helper( chapter_list, - chapter_time=lambda chapter: float_or_none( + start_function=lambda chapter: float_or_none( traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000), - chapter_title=lambda chapter: traverse_obj( + title_function=lambda chapter: traverse_obj( chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str), duration=duration) @@ -3141,46 +3246,25 @@ def _extract_chapters_from_engagement_panel(self, data, duration): content_list = traverse_obj( data, ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'), - expected_type=list, default=[]) + expected_type=list) chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription')) chapter_title = lambda chapter: self._get_text(chapter, 'title') return next(filter(None, ( - self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), - chapter_time, chapter_title, duration) + self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), + chapter_time, chapter_title, duration) for contents in content_list)), []) - def _extract_chapters_from_description(self, description, duration): - duration_re = r'(?:\d+:)?\d{1,2}:\d{2}' - sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$' - return self._extract_chapters( - re.findall(sep_re % (duration_re, r'.+?'), description or ''), - chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1], - duration=duration, strict=False) or self._extract_chapters( - re.findall(sep_re % (r'.+?', duration_re), description or ''), - chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0], - duration=duration, strict=False) - - def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True): - if not duration: - return - chapter_list = [{ - 'start_time': chapter_time(chapter), - 'title': chapter_title(chapter), - } for chapter in chapter_list or []] - if not strict: - chapter_list.sort(key=lambda c: c['start_time'] or 0) - - chapters = [{'start_time': 0}] - for idx, chapter in enumerate(chapter_list): - if chapter['start_time'] is None: - self.report_warning(f'Incomplete chapter {idx}') - elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration: - chapters.append(chapter) - elif chapter not in chapters: - self.report_warning( - f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"') - return chapters[1:] + def _extract_heatmap_from_player_overlay(self, data): + content_list = traverse_obj(data, ( + 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', 'decoratedPlayerBarRenderer', 'playerBar', + 'multiMarkersPlayerBarRenderer', 'markersMap', ..., 'value', 'heatmap', 'heatmapRenderer', 'heatMarkers', {list})) + return next(filter(None, ( + traverse_obj(contents, (..., 'heatMarkerRenderer', { + 'start_time': ('timeRangeStartMillis', {functools.partial(float_or_none, scale=1000)}), + 'end_time': {lambda x: (x['timeRangeStartMillis'] + x['markerDurationMillis']) / 1000}, + 'value': ('heatMarkerIntensityScoreNormalized', {float_or_none}), + })) for contents in content_list)), None) def _extract_comment(self, comment_renderer, parent=None): comment_id = comment_renderer.get('commentId') @@ -3230,7 +3314,7 @@ def extract_header(contents): expected_comment_count = self._get_count( comments_header_renderer, 'countText', 'commentsCount') - if expected_comment_count: + if expected_comment_count is not None: tracker['est_total'] = expected_comment_count self.to_screen(f'Downloading ~{expected_comment_count} comments') comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top @@ -3265,6 +3349,21 @@ def extract_thread(contents): comment = self._extract_comment(comment_renderer, parent) if not comment: continue + is_pinned = bool(traverse_obj(comment_renderer, 'pinnedCommentBadge')) + comment_id = comment['id'] + if is_pinned: + tracker['pinned_comment_ids'].add(comment_id) + # Sometimes YouTube may break and give us infinite looping comments. + # See: https://github.com/yt-dlp/yt-dlp/issues/6290 + if comment_id in tracker['seen_comment_ids']: + if comment_id in tracker['pinned_comment_ids'] and not is_pinned: + # Pinned comments may appear a second time in newest first sort + # See: https://github.com/yt-dlp/yt-dlp/issues/6712 + continue + self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.') + yield + else: + tracker['seen_comment_ids'].add(comment['id']) tracker['running_total'] += 1 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1 @@ -3286,10 +3385,13 @@ def extract_thread(contents): if not tracker: tracker = dict( running_total=0, - est_total=0, + est_total=None, current_page_thread=0, total_parent_comments=0, - total_reply_comments=0) + total_reply_comments=0, + seen_comment_ids=set(), + pinned_comment_ids=set() + ) # TODO: Deprecated # YouTube comments have a max depth of 2 @@ -3316,11 +3418,13 @@ def extract_thread(contents): continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id)) is_forced_continuation = True + continuation_items_path = ( + 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems') for page_num in itertools.count(0): if not continuation: break headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)) - comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})" + comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})" if page_num == 0: if is_first_continuation: note_prefix = 'Downloading comment section API JSON' @@ -3331,11 +3435,18 @@ def extract_thread(contents): note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( ' ' if parent else '', ' replies' if parent else '', page_num, comment_prog_str) + + # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation + # Ignore check if YouTube says the comment count is 0. + check_get_keys = None + if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0): + check_get_keys = [[*continuation_items_path, ..., ( + 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]] try: response = self._extract_response( item_id=None, query=continuation, ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, - check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None) + check_get_keys=check_get_keys) except ExtractorError as e: # Ignore incomplete data error for replies if retries didn't work. # This is to allow any other parent comments and comment threads to be downloaded. @@ -3347,15 +3458,8 @@ def extract_thread(contents): else: raise is_forced_continuation = False - continuation_contents = traverse_obj( - response, 'onResponseReceivedEndpoints', expected_type=list, default=[]) - continuation = None - for continuation_section in continuation_contents: - continuation_items = traverse_obj( - continuation_section, - (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'), - get_all=False, expected_type=list) or [] + for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]): if is_first_continuation: continuation = extract_header(continuation_items) is_first_continuation = False @@ -3418,7 +3522,7 @@ def _is_agegated(player_response): if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): return True - reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[]) + reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason'))) AGE_GATE_REASONS = ( 'confirm your age', 'age-restricted', 'inappropriate', # reason 'age_verification_required', 'age_check_required', # status @@ -3542,6 +3646,12 @@ def append_client(*client_names): self.report_warning( f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message()) else: + # Save client name for introspection later + name = short_client_name(client) + sd = traverse_obj(pr, ('streamingData', {dict})) or {} + sd[STREAMING_DATA_CLIENT_NAME] = name + for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})): + f[STREAMING_DATA_CLIENT_NAME] = name prs.append(pr) # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in @@ -3565,6 +3675,7 @@ def _needs_live_processing(self, live_status, duration): return live_status def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration): + CHUNK_SIZE = 10 << 20 itags, stream_ids = collections.defaultdict(set), [] itag_qualities, res_qualities = {}, {0: None} q = qualities([ @@ -3574,7 +3685,15 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres' ]) - streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[]) + streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...)) + all_formats = self._configuration_arg('include_duplicate_formats') + + def build_fragments(f): + return LazyList({ + 'url': update_url_query(f['url'], { + 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}' + }) + } for range_start in range(0, f['filesize'], CHUNK_SIZE)) for fmt in streaming_formats: if fmt.get('targetDurationSec'): @@ -3583,8 +3702,9 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l itag = str_or_none(fmt.get('itag')) audio_track = fmt.get('audioTrack') or {} stream_id = (itag, audio_track.get('id'), fmt.get('isDrc')) - if stream_id in stream_ids: - continue + if not all_formats: + if stream_id in stream_ids: + continue quality = fmt.get('quality') height = int_or_none(fmt.get('height')) @@ -3660,18 +3780,22 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l if is_damaged: self.report_warning( f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) + + client_name = fmt.get(STREAMING_DATA_CLIENT_NAME) dct = { 'asr': int_or_none(fmt.get('audioSampleRate')), 'filesize': int_or_none(fmt.get('contentLength')), 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}', 'format_note': join_nonempty( - '%s%s' % (audio_track.get('displayName') or '', - ' (default)' if language_preference > 0 else ''), + join_nonempty(audio_track.get('displayName'), + language_preference > 0 and ' (default)', delim=''), fmt.get('qualityLabel') or quality.replace('audio_quality_', ''), - 'DRC' if fmt.get('isDrc') else None, + fmt.get('isDrc') and 'DRC', try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()), try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()), - throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '), + throttled and 'THROTTLED', is_damaged and 'DAMAGED', + (self.get_param('verbose') or all_formats) and client_name, + delim=', '), # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372 'source_preference': -10 if throttled else -5 if itag == '22' else -1, 'fps': int_or_none(fmt.get('fps')) or None, @@ -3683,7 +3807,7 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l 'url': fmt_url, 'width': int_or_none(fmt.get('width')), 'language': join_nonempty(audio_track.get('id', '').split('.')[0], - 'desc' if language_preference < -1 else ''), + 'desc' if language_preference < -1 else '') or None, 'language_preference': language_preference, # Strictly de-prioritize damaged and 3gp formats 'preference': -10 if is_damaged else -2 if itag == '17' else None, @@ -3693,23 +3817,21 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l if mime_mobj: dct['ext'] = mimetype2ext(mime_mobj.group(1)) dct.update(parse_codecs(mime_mobj.group(2))) - no_audio = dct.get('acodec') == 'none' - no_video = dct.get('vcodec') == 'none' - if no_audio: - dct['vbr'] = tbr - if no_video: - dct['abr'] = tbr - if no_audio or no_video: - dct['downloader_options'] = { - # Youtube throttles chunks >~10M - 'http_chunk_size': 10485760, - } - if dct.get('ext'): - dct['container'] = dct['ext'] + '_dash' - if itag: itags[itag].add(('https', dct.get('language'))) stream_ids.append(stream_id) + single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec')) + if single_stream and dct.get('ext'): + dct['container'] = dct['ext'] + '_dash' + + if all_formats and dct['filesize']: + yield { + **dct, + 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'], + 'protocol': 'http_dash_segments', + 'fragments': build_fragments(dct), + } + dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE} yield dct needs_live_processing = self._needs_live_processing(live_status, duration) @@ -3729,13 +3851,15 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live': skip_manifests.add('dash') - def process_manifest_format(f, proto, itag): + def process_manifest_format(f, proto, client_name, itag): key = (proto, f.get('language')) - if key in itags[itag]: + if not all_formats and key in itags[itag]: return False itags[itag].add(key) - if any(p != proto for p, _ in itags[itag]): + if itag and all_formats: + f['format_id'] = f'{itag}-{proto}' + elif any(p != proto for p, _ in itags[itag]): f['format_id'] = f'{itag}-{proto}' elif itag: f['format_id'] = itag @@ -3743,17 +3867,21 @@ def process_manifest_format(f, proto, itag): f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)) if f['quality'] == -1 and f.get('height'): f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))]) + if self.get_param('verbose'): + f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ') return True subtitles = {} for sd in streaming_data: + client_name = sd.get(STREAMING_DATA_CLIENT_NAME) + hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl') if hls_manifest_url: fmts, subs = self._extract_m3u8_formats_and_subtitles( hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live') subtitles = self._merge_subtitles(subs, subtitles) for f in fmts: - if process_manifest_format(f, 'hls', self._search_regex( + if process_manifest_format(f, 'hls', client_name, self._search_regex( r'/itag/(\d+)', f['url'], 'itag', default=None)): yield f @@ -3762,7 +3890,7 @@ def process_manifest_format(f, proto, itag): formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False) subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH for f in formats: - if process_manifest_format(f, 'dash', f['format_id']): + if process_manifest_format(f, 'dash', client_name, f['format_id']): f['filesize'] = int_or_none(self._search_regex( r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None)) if needs_live_processing: @@ -3840,7 +3968,7 @@ def _list_formats(self, video_id, microformats, video_details, player_responses, else 'was_live' if live_content else 'not_live' if False in (is_live, live_content) else None) - streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[]) + streaming_data = traverse_obj(player_responses, (..., 'streamingData')) *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration) return live_broadcast_details, live_status, streaming_data, formats, subtitles @@ -3855,7 +3983,7 @@ def _real_extract(self, url): webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) playability_statuses = traverse_obj( - player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[]) + player_responses, (..., 'playabilityStatus'), expected_type=dict) trailer_video_id = get_first( playability_statuses, @@ -3868,11 +3996,10 @@ def _real_extract(self, url): search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) if webpage else (lambda x: None)) - video_details = traverse_obj( - player_responses, (..., 'videoDetails'), expected_type=dict, default=[]) + video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict) microformats = traverse_obj( player_responses, (..., 'microformat', 'playerMicroformatRenderer'), - expected_type=dict, default=[]) + expected_type=dict) translated_title = self._get_text(microformats, (..., 'title')) video_title = (self._preferred_lang and translated_title @@ -4005,10 +4132,10 @@ def feed_entry(name): self._downloader._sort_thumbnails(original_thumbnails) category = get_first(microformats, 'category') or search_meta('genre') - channel_id = str_or_none( + channel_id = self.ucid_or_none(str_or_none( get_first(video_details, 'channelId') or get_first(microformats, 'externalChannelId') - or search_meta('channelId')) + or search_meta('channelId'))) owner_profile_url = get_first(microformats, 'ownerProfileUrl') live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp')) @@ -4035,6 +4162,8 @@ def is_bad_format(fmt): formats.extend(self._extract_storyboard(player_responses, duration)) + channel_handle = self.handle_from_url(owner_profile_url) + info = { 'id': video_id, 'title': video_title, @@ -4044,11 +4173,8 @@ def is_bad_format(fmt): # URL checking if user don't care about getting the best possible thumbnail 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')), 'description': video_description, - 'uploader': get_first(video_details, 'author'), - 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None, - 'uploader_url': owner_profile_url, 'channel_id': channel_id, - 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'), + 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None), 'duration': duration, 'view_count': int_or_none( get_first((video_details, microformats), (..., 'viewCount')) @@ -4078,10 +4204,10 @@ def get_lang_code(track): # Converted into dicts to remove duplicates captions = { get_lang_code(sub): sub - for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])} + for sub in traverse_obj(pctr, (..., 'captionTracks', ...))} translation_languages = { lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1) - for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])} + for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))} def process_language(container, base_url, lang_code, sub_name, query): lang_subs = container.setdefault(lang_code, []) @@ -4170,22 +4296,25 @@ def process_language(container, base_url, lang_code, sub_name, query): initial_data = None if webpage: initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False) + if not traverse_obj(initial_data, 'contents'): + self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.') + initial_data = None if not initial_data: query = {'videoId': video_id} query.update(self._get_checkok_params()) initial_data = self._extract_response( item_id=video_id, ep='next', fatal=False, - ytcfg=master_ytcfg, query=query, + ytcfg=master_ytcfg, query=query, check_get_keys='contents', headers=self.generate_api_headers(ytcfg=master_ytcfg), note='Downloading initial data API JSON') info['comment_count'] = traverse_obj(initial_data, ( 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer', - 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText' + 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount' ), ( 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section', - 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text' - ), expected_type=int_or_none, get_all=False) + 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo' + ), expected_type=self._get_count, get_all=False) try: # This will error if there is no livechat initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] @@ -4208,6 +4337,8 @@ def process_language(container, base_url, lang_code, sub_name, query): or self._extract_chapters_from_description(video_description, duration) or None) + info['heatmap'] = self._extract_heatmap_from_player_overlay(initial_data) + contents = traverse_obj( initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'), expected_type=list, default=[]) @@ -4235,9 +4366,8 @@ def process_language(container, base_url, lang_code, sub_name, query): list) or []): tbrs = variadic( traverse_obj( - tlb, 'toggleButtonRenderer', - ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'), - default=[])) + tlb, ('toggleButtonRenderer', ...), + ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'))) for tbr in tbrs: for getter, regex in [( lambda x: x['defaultText']['accessibility']['accessibilityData'], @@ -4275,6 +4405,13 @@ def process_language(container, base_url, lang_code, sub_name, query): 'channel': self._get_text(vor, 'title'), 'channel_follower_count': self._get_count(vor, 'subscriberCountText')}) + if not channel_handle: + channel_handle = self.handle_from_url( + traverse_obj(vor, ( + ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')), + (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')), + {str}), get_all=False)) + rows = try_get( vsir, lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], @@ -4301,12 +4438,11 @@ def process_language(container, base_url, lang_code, sub_name, query): elif mrr_title == 'Song': info['track'] = mrr_contents_text - fallbacks = { - 'channel': 'uploader', - 'channel_id': 'uploader_id', - 'channel_url': 'uploader_url', - } - + info.update({ + 'uploader': info.get('channel'), + 'uploader_id': channel_handle, + 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), + }) # The upload date for scheduled, live and past live streams / premieres in microformats # may be different from the stream date. Although not in UTC, we will prefer it in this case. # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139 @@ -4321,10 +4457,6 @@ def process_language(container, base_url, lang_code, sub_name, query): self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date info['upload_date'] = upload_date - for to, frm in fallbacks.items(): - if not info.get(to): - info[to] = info.get(frm) - for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]: v = info.get(s_k) if v: @@ -4385,19 +4517,6 @@ def wrapper(self, url): return info_dict return wrapper - 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): # Modified from _extract_grid_item_renderer @@ -4413,18 +4532,28 @@ def _extract_basic_item_renderer(item): return renderer def _extract_channel_renderer(self, renderer): - channel_id = renderer['channelId'] + channel_id = self.ucid_or_none(renderer['channelId']) title = self._get_text(renderer, 'title') - channel_url = f'https://www.youtube.com/channel/{channel_id}' + channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None) + # As of 2023-03-01 YouTube doesn't use the channel handles on these renderers yet. + # However we can expect them to change that in the future. + channel_handle = self.handle_from_url( + traverse_obj(renderer, ( + 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'), + ('browseEndpoint', 'canonicalBaseUrl')), + {str}), get_all=False)) return { '_type': 'url', 'url': channel_url, 'id': channel_id, 'ie_key': YoutubeTabIE.ie_key(), 'channel': title, + 'uploader': title, 'channel_id': channel_id, 'channel_url': channel_url, 'title': title, + 'uploader_id': channel_handle, + 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'), 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'), 'playlist_count': self._get_count(renderer, 'videoCountText'), @@ -4472,8 +4601,11 @@ def _grid_entries(self, grid_renderer): def _music_reponsive_list_entry(self, renderer): video_id = traverse_obj(renderer, ('playlistItemData', 'videoId')) if video_id: + title = traverse_obj(renderer, ( + 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer', + 'text', 'runs', 0, 'text')) return self.url_result(f'https://music.youtube.com/watch?v={video_id}', - ie=YoutubeIE.ie_key(), video_id=video_id) + ie=YoutubeIE.ie_key(), video_id=video_id, title=title) playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) if playlist_id: video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) @@ -4532,11 +4664,19 @@ def _playlist_entries(self, video_list_renderer): def _rich_entries(self, rich_grid_renderer): renderer = traverse_obj( - rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {} + rich_grid_renderer, + ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {} video_id = renderer.get('videoId') - if not video_id: + if video_id: + yield self._extract_video(renderer) + return + playlist_id = renderer.get('playlistId') + if playlist_id: + yield self.url_result( + f'https://www.youtube.com/playlist?list={playlist_id}', + ie=YoutubeTabIE.ie_key(), video_id=playlist_id, + video_title=self._get_text(renderer, 'title')) return - yield self._extract_video(renderer) def _video_entry(self, video_renderer): video_id = video_renderer.get('videoId') @@ -4764,13 +4904,14 @@ def _extract_metadata_from_tabs(self, item_id, data): metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict) if metadata_renderer: + channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}), + ('channelUrl', {self.ucid_from_url})) info.update({ - 'uploader': metadata_renderer.get('title'), - 'uploader_id': metadata_renderer.get('externalId'), - 'uploader_url': metadata_renderer.get('channelUrl'), + 'channel': metadata_renderer.get('title'), + 'channel_id': channel_id, }) - if info['uploader_id']: - info['id'] = info['uploader_id'] + if info['channel_id']: + info['id'] = info['channel_id'] else: metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict) @@ -4823,6 +4964,15 @@ def _get_uncropped(url): 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners, }) + channel_handle = ( + traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False) + or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False)) + + if channel_handle: + info.update({ + 'uploader_id': channel_handle, + 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), + }) # Playlist stats is a text runs array containing [video count, view count, last updated]. # last updated or (view count and last updated) may be missing. playlist_stats = get_first( @@ -4836,12 +4986,16 @@ def _get_uncropped(url): info['view_count'] = self._get_count(playlist_stats, 1) if info['view_count'] is None: # 0 is allowed info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText') + if info['view_count'] is None: + info['view_count'] = self._get_count(data, ( + 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer', + 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText')) info['playlist_count'] = self._get_count(playlist_stats, 0) if info['playlist_count'] is None: # 0 is allowed info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text')) - if not info.get('uploader_id'): + if not info.get('channel_id'): owner = traverse_obj(playlist_header_renderer, 'ownerText') if not owner: # Deprecated owner = traverse_obj( @@ -4850,16 +5004,17 @@ def _get_uncropped(url): owner_text = self._get_text(owner) browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {} info.update({ - 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text), - 'uploader_id': browse_ep.get('browseId'), - 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')) + 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text), + 'channel_id': self.ucid_or_none(browse_ep.get('browseId')), + 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))) }) info.update({ - 'channel': info['uploader'], - 'channel_id': info['uploader_id'], - 'channel_url': info['uploader_url'] + 'uploader': info['channel'], + 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None), + 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None), }) + return info def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg): @@ -5107,7 +5262,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): IE_DESC = 'YouTube Tabs' _VALID_URL = r'''(?x: https?:// - (?:\w+\.)? + (?!consent\.)(?:\w+\.)? (?: youtube(?:kids)?\.com| %(invidious)s @@ -5136,12 +5291,12 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'title': 'Igor Kleiner - Playlists', 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', 'uploader': 'Igor Kleiner', - 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'uploader_id': '@IgorDataScience', + 'uploader_url': 'https://www.youtube.com/@IgorDataScience', 'channel': 'Igor Kleiner', 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', - 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', 'channel_follower_count': int }, }, { @@ -5152,9 +5307,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'id': 'UCqj7Cz7revf5maW9g5pgNcg', 'title': 'Igor Kleiner - Playlists', 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', - 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', 'uploader': 'Igor Kleiner', - 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', + 'uploader_id': '@IgorDataScience', + 'uploader_url': 'https://www.youtube.com/@IgorDataScience', 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', 'channel': 'Igor Kleiner', @@ -5169,12 +5324,12 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'id': 'UCYO_jab_esuFRV4b17AJtAw', 'title': '3Blue1Brown - Playlists', 'description': 'md5:e1384e8a133307dd10edee76e875d62f', - 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', - 'uploader': '3Blue1Brown', 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', - 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', 'channel': '3Blue1Brown', 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', + 'uploader_id': '@3blue1brown', + 'uploader_url': 'https://www.youtube.com/@3blue1brown', + 'uploader': '3Blue1Brown', 'tags': ['Mathematics'], 'channel_follower_count': int }, @@ -5187,10 +5342,10 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'title': 'ThirstForScience - Playlists', 'description': 'md5:609399d937ea957b0f53cbffb747a14c', 'uploader': 'ThirstForScience', - 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', - 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', - 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', + 'uploader_url': 'https://www.youtube.com/@ThirstForScience', + 'uploader_id': '@ThirstForScience', 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', + 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', 'tags': 'count:13', 'channel': 'ThirstForScience', 'channel_follower_count': int @@ -5202,8 +5357,6 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): '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', 'description': '', @@ -5212,17 +5365,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'modified_date': '20201130', 'channel': 'Sergey M.', 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', - 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', 'availability': 'public', + 'uploader': 'Sergey M.', + 'uploader_url': 'https://www.youtube.com/@sergeym.6173', + 'uploader_id': '@sergeym.6173', }, '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', 'tags': [], @@ -5231,8 +5384,10 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'modified_date': '20160902', 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', 'availability': 'public', + 'uploader_url': 'https://www.youtube.com/@sergeym.6173', + 'uploader_id': '@sergeym.6173', + 'uploader': 'Sergey M.', }, 'playlist_count': 0, }, { @@ -5243,10 +5398,10 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'title': 'lex will - Home', 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_id': '@lexwill718', 'channel': 'lex will', 'tags': ['bible', 'history', 'prophesy'], - 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_url': 'https://www.youtube.com/@lexwill718', 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'channel_follower_count': int @@ -5260,11 +5415,11 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'title': 'lex will - Videos', 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_id': '@lexwill718', 'tags': ['bible', 'history', 'prophesy'], 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_url': 'https://www.youtube.com/@lexwill718', 'channel': 'lex will', 'channel_follower_count': int }, @@ -5277,9 +5432,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'title': 'lex will - Videos', 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_id': '@lexwill718', 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_url': 'https://www.youtube.com/@lexwill718', 'channel': 'lex will', 'tags': ['bible', 'history', 'prophesy'], 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', @@ -5294,8 +5449,8 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'title': 'lex will - Playlists', 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_id': '@lexwill718', + 'uploader_url': 'https://www.youtube.com/@lexwill718', 'channel': 'lex will', 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', @@ -5310,14 +5465,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'title': 'lex will - Community', 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel': 'lex will', 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'tags': ['bible', 'history', 'prophesy'], - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'uploader_id': '@lexwill718', + 'uploader': 'lex will', }, 'playlist_mincount': 18, }, { @@ -5327,14 +5482,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'title': 'lex will - Channels', 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel': 'lex will', 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'tags': ['bible', 'history', 'prophesy'], - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'uploader_id': '@lexwill718', + 'uploader': 'lex will', }, 'playlist_mincount': 12, }, { @@ -5345,14 +5500,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'id': 'UCYO_jab_esuFRV4b17AJtAw', 'title': '3Blue1Brown - Search - linear algebra', 'description': 'md5:e1384e8a133307dd10edee76e875d62f', - 'uploader': '3Blue1Brown', - 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', - 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', 'tags': ['Mathematics'], 'channel': '3Blue1Brown', 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', - 'channel_follower_count': int + 'channel_follower_count': int, + 'uploader_url': 'https://www.youtube.com/@3blue1brown', + 'uploader_id': '@3blue1brown', + 'uploader': '3Blue1Brown', }, }, { 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', @@ -5369,17 +5524,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'title': '29C3: Not my department', 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', - 'uploader': 'Christiaan008', - 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', 'tags': [], - 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008', 'view_count': int, 'modified_date': '20150605', 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', - 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008', + 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg', 'channel': 'Christiaan008', 'availability': 'public', + 'uploader_id': '@ChRiStIaAn008', + 'uploader': 'Christiaan008', + 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008', }, 'playlist_count': 96, }, { @@ -5388,17 +5543,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'title': 'Uploads from Cauchemar', 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', - 'uploader': 'Cauchemar', - 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', - 'channel_url': 'https://www.youtube.com/c/Cauchemar89', + 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q', 'tags': [], 'modified_date': r're:\d{8}', 'channel': 'Cauchemar', - 'uploader_url': 'https://www.youtube.com/c/Cauchemar89', 'view_count': int, 'description': '', 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', 'availability': 'public', + 'uploader_id': '@Cauchemar89', + 'uploader': 'Cauchemar', + 'uploader_url': 'https://www.youtube.com/@Cauchemar89', }, 'playlist_mincount': 1123, 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], @@ -5412,17 +5567,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'title': 'Uploads from Interstellar Movie', 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', - 'uploader': 'Interstellar Movie', - 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', - 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie', 'tags': [], 'view_count': int, 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', - 'channel_url': 'https://www.youtube.com/c/InterstellarMovie', + 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA', 'channel': 'Interstellar Movie', 'description': '', 'modified_date': r're:\d{8}', 'availability': 'public', + 'uploader_id': '@InterstellarMovie', + 'uploader': 'Interstellar Movie', + 'uploader_url': 'https://www.youtube.com/@InterstellarMovie', }, 'playlist_mincount': 21, }, { @@ -5431,17 +5586,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', - 'uploader': 'Phim Siêu Nhân Nhật Bản', - 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', 'view_count': int, 'channel': 'Phim Siêu Nhân Nhật Bản', 'tags': [], - 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', 'description': '', 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', 'modified_date': r're:\d{8}', 'availability': 'public', + 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban', + 'uploader_id': '@phimsieunhannhatban', + 'uploader': 'Phim Siêu Nhân Nhật Bản', }, 'playlist_mincount': 200, 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], @@ -5451,17 +5606,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'title': 'Uploads from BlankTV', 'id': 'UU8l9frL61Yl5KFOl87nIm2w', - 'uploader': 'BlankTV', - 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', 'channel': 'BlankTV', - 'channel_url': 'https://www.youtube.com/c/blanktv', + 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w', 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', 'view_count': int, 'tags': [], - 'uploader_url': 'https://www.youtube.com/c/blanktv', 'modified_date': r're:\d{8}', 'description': '', 'availability': 'public', + 'uploader_id': '@blanktv', + 'uploader': 'BlankTV', + 'uploader_url': 'https://www.youtube.com/@blanktv', }, 'playlist_mincount': 1000, 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], @@ -5471,17 +5626,17 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'title': 'Data Analysis with Dr Mike Pound', 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', - 'uploader': 'Computerphile', 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', - 'uploader_url': 'https://www.youtube.com/user/Computerphile', 'tags': [], 'view_count': int, 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', - 'channel_url': 'https://www.youtube.com/user/Computerphile', + 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA', 'channel': 'Computerphile', 'availability': 'public', 'modified_date': '20190712', + 'uploader_id': '@Computerphile', + 'uploader': 'Computerphile', + 'uploader_url': 'https://www.youtube.com/@Computerphile', }, 'playlist_mincount': 11, }, { @@ -5494,9 +5649,6 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): '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', @@ -5519,12 +5671,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): }, { 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', 'info_dict': { - 'id': 'Wq15eF5vCbI', # This will keep changing + 'id': 'AlTsmyW4auo', # This will keep changing 'ext': 'mp4', 'title': str, - 'uploader': 'Sky News', - 'uploader_id': 'skynews', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', 'upload_date': r're:\d{8}', 'description': str, 'categories': ['News & Politics'], @@ -5543,6 +5692,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ', 'channel_follower_count': int, 'concurrent_view_count': int, + 'uploader_url': 'https://www.youtube.com/@SkyNews', + 'uploader_id': '@SkyNews', + 'uploader': 'Sky News', }, 'params': { 'skip_download': True, @@ -5554,9 +5706,6 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): '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', @@ -5637,41 +5786,40 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): '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 : All Releases 💿', - 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds', - 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds', + 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg', 'modified_date': r're:\d{8}', 'view_count': int, 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', 'tags': [], 'channel': 'NoCopyrightSounds', 'availability': 'public', + 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds', + 'uploader': 'NoCopyrightSounds', + 'uploader_id': '@NoCopyrightSounds', }, 'playlist_mincount': 166, - 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], + 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'], }, { + # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos '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', 'tags': [], 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', 'channel': 'Royalty Free Music - Topic', 'view_count': int, 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', - 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', 'modified_date': r're:\d{8}', - 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', 'description': '', 'availability': 'public', + 'uploader': 'Royalty Free Music - Topic', }, 'playlist_mincount': 101, + 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'], }, { # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg) # Treat as a general feed @@ -5695,12 +5843,11 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'modified_date': r're:\d{8}', }, 'playlist_count': 50, + 'expected_warnings': ['YouTube Music is not directly supported'], }, { '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', @@ -5709,11 +5856,31 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'channel': 'colethedj', 'view_count': int, 'description': '', - 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', + 'uploader_url': 'https://www.youtube.com/@colethedj1894', + 'uploader_id': '@colethedj1894', + 'uploader': 'colethedj', }, + 'playlist': [{ + 'info_dict': { + 'title': 'youtube-dl test video "\'/\\ä↭𝕐', + 'id': 'BaW_jenozKc', + '_type': 'url', + 'ie_key': 'Youtube', + 'duration': 10, + 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', + 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', + 'view_count': int, + 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc', + 'channel': 'Philipp Hagemeister', + 'uploader_id': '@PhilippHagemeister', + 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister', + 'uploader': 'Philipp Hagemeister', + } + }], 'playlist_count': 1, + 'params': {'extract_flat': True}, }, { 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', 'url': 'https://www.youtube.com/feed/recommended', @@ -5734,13 +5901,10 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', 'title': 'Cody\'sLab - Videos', 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', - 'uploader': 'Cody\'sLab', - 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', 'channel': 'Cody\'sLab', 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', 'tags': [], 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', - 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', 'channel_follower_count': int }, 'playlist_mincount': 650, @@ -5754,9 +5918,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): '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', 'modified_date': r're:\d{8}', 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', 'description': '', @@ -5764,14 +5926,15 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'tags': [], 'channel': 'Royalty Free Music - Topic', 'view_count': int, - 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', 'availability': 'public', + 'uploader': 'Royalty Free Music - Topic', }, 'playlist_mincount': 101, 'params': { 'skip_download': True, 'extractor_args': {'youtubetab': {'skip': ['webpage']}} }, + 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'], }, { 'note': 'non-standard redirect to regional channel', 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ', @@ -5784,15 +5947,15 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'modified_date': '20220407', 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', 'tags': [], - 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', - 'uploader': 'pukkandan', 'availability': 'unlisted', 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', 'channel': 'pukkandan', 'description': 'Test for collaborative playlist', 'title': 'yt-dlp test - collaborative playlist', 'view_count': int, - 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', + 'uploader_url': 'https://www.youtube.com/@pukkandan', + 'uploader_id': '@pukkandan', + 'uploader': 'pukkandan', }, 'playlist_mincount': 2 }, { @@ -5801,14 +5964,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'id': 'UCiu-3thuViMebBjw_5nWYrA', 'tags': [], - 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', 'description': 'test description', 'title': 'cole-dlp-test-acc - 再生リスト', - 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', - 'uploader': 'cole-dlp-test-acc', 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel': 'cole-dlp-test-acc', + 'uploader_url': 'https://www.youtube.com/@coletdjnz', + 'uploader_id': '@coletdjnz', + 'uploader': 'cole-dlp-test-acc', }, 'playlist_mincount': 1, 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}}, @@ -5822,14 +5985,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'tags': [], 'view_count': int, 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', - 'uploader': 'cole-dlp-test-acc', - 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel': 'cole-dlp-test-acc', 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', 'description': 'test', - 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', 'title': 'dlp test playlist', 'availability': 'public', + 'uploader_url': 'https://www.youtube.com/@coletdjnz', + 'uploader_id': '@coletdjnz', + 'uploader': 'cole-dlp-test-acc', }, 'playlist_mincount': 1, 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}}, @@ -5881,29 +6044,30 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'channel_follower_count': int, 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA', 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', - 'uploader': 'Polka Ch. 尾丸ポルカ', - 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9', + 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822', 'channel': 'Polka Ch. 尾丸ポルカ', 'tags': 'count:35', - 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', - 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA', + 'uploader_url': 'https://www.youtube.com/@OmaruPolka', + 'uploader': 'Polka Ch. 尾丸ポルカ', + 'uploader_id': '@OmaruPolka', }, 'playlist_count': 3, }, { # Shorts tab with channel with handle + # TODO: fix channel description 'url': 'https://www.youtube.com/@NotJustBikes/shorts', 'info_dict': { 'id': 'UC0intLFzLaudFG-xAvUEO-A', 'title': 'Not Just Bikes - Shorts', 'tags': 'count:12', - 'uploader': 'Not Just Bikes', 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A', - 'description': 'md5:7513148b1f02b924783157d84c4ea555', + 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d', 'channel_follower_count': int, - 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A', 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A', - 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A', 'channel': 'Not Just Bikes', + 'uploader_url': 'https://www.youtube.com/@NotJustBikes', + 'uploader': 'Not Just Bikes', + 'uploader_id': '@NotJustBikes', }, 'playlist_mincount': 10, }, { @@ -5915,12 +6079,12 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'tags': 'count:7', 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig', 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig', - 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig', 'channel': '中村悠一', - 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig', 'channel_follower_count': int, - 'uploader': '中村悠一', 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300', + 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura', + 'uploader_id': '@Yuichi-Nakamura', + 'uploader': '中村悠一', }, 'playlist_mincount': 60, }, { @@ -5939,15 +6103,15 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg', 'title': 'Shorts Break - Shorts', - 'tags': 'count:32', + 'tags': 'count:48', 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg', 'channel': 'Shorts Break', - 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11', - 'uploader': 'Shorts Break', + 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499', 'channel_follower_count': int, - 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg', - 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg', 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg', + 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official', + 'uploader': 'Shorts Break', + 'uploader_id': '@ShortsBreak_Official', }, 'playlist_mincount': 30, }, { @@ -5970,30 +6134,28 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'playlist_mincount': 30, }, { # Shorts url result in shorts tab + # TODO: Fix channel id extraction 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts', 'info_dict': { 'id': 'UCiu-3thuViMebBjw_5nWYrA', 'title': 'cole-dlp-test-acc - Shorts', - 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel': 'cole-dlp-test-acc', 'description': 'test description', 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', 'tags': [], + 'uploader_url': 'https://www.youtube.com/@coletdjnz', + 'uploader_id': '@coletdjnz', 'uploader': 'cole-dlp-test-acc', - 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', - }, 'playlist': [{ 'info_dict': { + # Channel data is not currently available for short renderers (as of 2023-03-01) '_type': 'url', 'ie_key': 'Youtube', 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60', 'id': 'sSM9J5YH_60', - 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', 'title': 'SHORT short', - 'channel': 'cole-dlp-test-acc', - 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', 'view_count': int, 'thumbnails': list, } @@ -6019,6 +6181,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'channel_url': str, 'concurrent_view_count': int, 'channel': str, + 'uploader': str, + 'uploader_url': str, + 'uploader_id': str } }], 'params': {'extract_flat': True, 'playlist_items': '1'}, @@ -6029,15 +6194,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'info_dict': { 'id': 'UCiu-3thuViMebBjw_5nWYrA', 'title': 'cole-dlp-test-acc - Channels', - 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel': 'cole-dlp-test-acc', 'description': 'test description', 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', 'tags': [], + 'uploader_url': 'https://www.youtube.com/@coletdjnz', + 'uploader_id': '@coletdjnz', 'uploader': 'cole-dlp-test-acc', - 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', - }, 'playlist': [{ 'info_dict': { @@ -6051,10 +6215,64 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', 'thumbnails': list, 'channel_follower_count': int, - 'playlist_count': int + 'playlist_count': int, + 'uploader': 'PewDiePie', + 'uploader_url': 'https://www.youtube.com/@PewDiePie', + 'uploader_id': '@PewDiePie', } }], 'params': {'extract_flat': True}, + }, { + 'url': 'https://www.youtube.com/@3blue1brown/about', + 'info_dict': { + 'id': 'UCYO_jab_esuFRV4b17AJtAw', + 'tags': ['Mathematics'], + 'title': '3Blue1Brown - About', + 'channel_follower_count': int, + 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', + 'channel': '3Blue1Brown', + 'view_count': int, + 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', + 'description': 'md5:e1384e8a133307dd10edee76e875d62f', + 'uploader_url': 'https://www.youtube.com/@3blue1brown', + 'uploader_id': '@3blue1brown', + 'uploader': '3Blue1Brown', + }, + 'playlist_count': 0, + }, { + # Podcasts tab, with rich entry playlistRenderers + 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts', + 'info_dict': { + 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw', + 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw', + 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast', + 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c', + 'title': '99 Percent Invisible - Podcasts', + 'uploader': '99 Percent Invisible', + 'channel_follower_count': int, + 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw', + 'tags': [], + 'channel': '99 Percent Invisible', + 'uploader_id': '@99percentinvisiblepodcast', + }, + 'playlist_count': 1, + }, { + # Releases tab, with rich entry playlistRenderers (same as Podcasts tab) + 'url': 'https://www.youtube.com/@AHimitsu/releases', + 'info_dict': { + 'id': 'UCgFwu-j5-xNJml2FtTrrB3A', + 'channel': 'A Himitsu', + 'uploader_url': 'https://www.youtube.com/@AHimitsu', + 'title': 'A Himitsu - Releases', + 'uploader_id': '@AHimitsu', + 'uploader': 'A Himitsu', + 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A', + 'tags': 'count:16', + 'description': 'I make music', + 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A', + 'channel_follower_count': int, + }, + 'playlist_mincount': 10, }] @classmethod @@ -6121,6 +6339,8 @@ def _real_extract(self, url, smuggled_data): original_tab_id, display_id = tab[1:], f'{item_id}{tab}' if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: url = f'{pre}/videos{post}' + if smuggled_data.get('is_music_url'): + self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}') # Handle both video/playlist URLs qs = parse_qs(url) @@ -6269,15 +6489,15 @@ class YoutubePlaylistIE(InfoExtractor): 'title': '[OLD]Team Fortress 2 (Class-based LP)', 'id': 'PLBB231211A4F62143', 'uploader': 'Wickman', - 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', + 'uploader_id': '@WickmanVT', 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', 'view_count': int, - 'uploader_url': 'https://www.youtube.com/c/WickmanVT', + 'uploader_url': 'https://www.youtube.com/@WickmanVT', 'modified_date': r're:\d{8}', 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', 'channel': 'Wickman', 'tags': [], - 'channel_url': 'https://www.youtube.com/c/WickmanVT', + 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q', 'availability': 'public', }, 'playlist_mincount': 29, @@ -6297,7 +6517,7 @@ class YoutubePlaylistIE(InfoExtractor): 'title': 'JODA15', 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', 'uploader': 'milan', - 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', + 'uploader_id': '@milan5503', 'description': '', 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', 'tags': [], @@ -6305,7 +6525,7 @@ class YoutubePlaylistIE(InfoExtractor): 'view_count': int, 'channel': 'milan', 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', - 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', + 'uploader_url': 'https://www.youtube.com/@milan5503', 'availability': 'public', }, 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'], @@ -6316,13 +6536,13 @@ class YoutubePlaylistIE(InfoExtractor): 'title': '2018 Chinese New Singles (11/6 updated)', 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', 'uploader': 'LBK', - 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', + 'uploader_id': '@music_king', 'description': 'md5:da521864744d60a198e3a88af4db0d9d', 'channel': 'LBK', 'view_count': int, - 'channel_url': 'https://www.youtube.com/c/愛低音的國王', + 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA', 'tags': [], - 'uploader_url': 'https://www.youtube.com/c/愛低音的國王', + 'uploader_url': 'https://www.youtube.com/@music_king', 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', 'modified_date': r're:\d{8}', 'availability': 'public', @@ -6368,8 +6588,8 @@ class YoutubeYtBeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Small Scale Baler and Braiding Rugs', 'uploader': 'Backus-Page House Museum', - 'uploader_id': 'backuspagemuseum', - 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', + 'uploader_id': '@backuspagemuseum', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum', 'upload_date': '20161008', 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', 'categories': ['Nonprofits & Activism'], @@ -6377,7 +6597,7 @@ class YoutubeYtBeIE(InfoExtractor): 'like_count': int, 'age_limit': 0, 'playable_in_embed': True, - 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp', + 'thumbnail': r're:^https?://.*\.webp', 'channel': 'Backus-Page House Museum', 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', 'live_status': 'not_live', @@ -6493,7 +6713,7 @@ def _extract_notification_renderer(self, notification): if not video_id: browse_ep = traverse_obj( notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict) - channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str) + channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str)) post_id = self._search_regex( r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str), 'post id', default=None) @@ -6523,6 +6743,7 @@ def _extract_notification_renderer(self, notification): 'title': title, 'channel_id': channel_id, 'channel': channel, + 'uploader': channel, 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'), 'timestamp': timestamp, } @@ -6627,7 +6848,10 @@ class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q', 'playlist_count': int, # XXX: should have a way of saying > 1 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q', - 'thumbnails': list + 'thumbnails': list, + 'uploader_id': '@kurzgesagt', + 'uploader_url': 'https://www.youtube.com/@kurzgesagt', + 'uploader': 'Kurzgesagt – In a Nutshell', } }], 'params': {'extract_flat': True, 'playlist_items': '1'}, @@ -6885,11 +7109,12 @@ class YoutubeClipIE(YoutubeTabBaseInfoExtractor): 'title': 'Mobile Games on Console - Scott The Woz', 'upload_date': '20210920', 'uploader': 'Scott The Woz', - 'uploader_id': 'scottthewoz', - 'uploader_url': 'http://www.youtube.com/user/scottthewoz', + 'uploader_id': '@ScottTheWoz', + 'uploader_url': 'https://www.youtube.com/@ScottTheWoz', 'view_count': int, 'live_status': 'not_live', - 'channel_follower_count': int + 'channel_follower_count': int, + 'chapters': 'count:20', } }] @@ -6917,6 +7142,51 @@ def _real_extract(self, url): } +class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor): + IE_NAME = 'youtube:consent' + IE_DESC = False # Do not list + _VALID_URL = r'https?://consent\.youtube\.com/m\?' + _TESTS = [{ + 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1', + 'info_dict': { + 'id': 'qVv6vCqciTM', + 'ext': 'mp4', + 'age_limit': 0, + 'uploader_id': '@sana_natori', + 'comment_count': int, + 'chapters': 'count:13', + 'upload_date': '20221223', + 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg', + 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA', + 'uploader_url': 'https://www.youtube.com/@sana_natori', + 'like_count': int, + 'release_date': '20221223', + 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'], + 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】', + 'view_count': int, + 'playable_in_embed': True, + 'duration': 4438, + 'availability': 'public', + 'channel_follower_count': int, + 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA', + 'categories': ['Entertainment'], + 'live_status': 'was_live', + 'release_timestamp': 1671793345, + 'channel': 'さなちゃんねる', + 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d', + 'uploader': 'さなちゃんねる', + }, + 'add_ie': ['Youtube'], + 'params': {'skip_download': 'Youtube'}, + }] + + def _real_extract(self, url): + redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1]) + if not redirect_url: + raise ExtractorError('Invalid cookie consent redirect URL', expected=True) + return self.url_result(redirect_url) + + class YoutubeTruncatedIDIE(InfoExtractor): IE_NAME = 'youtube:truncated_id' IE_DESC = False # Do not list