X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/684fbbb940adb6ea4043bc437e527888687a53da..d037080638e8dbb0ebb2ac9cf23b9671518340f9:/youtube_dl/extractor/youtube.py?ds=sidebyside diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 963c73a..25d056b 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -27,9 +27,11 @@ from ..compat import ( compat_str, ) from ..utils import ( + bool_or_none, clean_html, dict_get, error_to_compat_str, + extract_attributes, ExtractorError, float_or_none, get_element_by_attribute, @@ -116,6 +118,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor): 'f.req': json.dumps(f_req), 'flowName': 'GlifWebSignIn', 'flowEntry': 'ServiceLogin', + # TODO: reverse actual botguard identifier generation algo + 'bgRequest': '["identifier",""]', }) return self._download_json( url, None, note=note, errnote=errnote, @@ -321,17 +325,18 @@ class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): for video_id, video_title in self.extract_videos_from_page(content): yield self.url_result(video_id, 'Youtube', video_id, video_title) - def extract_videos_from_page(self, page): - ids_in_page = [] - titles_in_page = [] - for mobj in re.finditer(self._VIDEO_RE, page): + def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page): + for mobj in re.finditer(video_re, page): # The link with index 0 is not the first video of the playlist (not sure if still actual) if 'index' in mobj.groupdict() and mobj.group('id') == '0': continue video_id = mobj.group('id') - video_title = unescapeHTML(mobj.group('title')) + video_title = unescapeHTML( + mobj.group('title')) if 'title' in mobj.groupdict() else None if video_title: video_title = video_title.strip() + if video_title == '► Play all': + video_title = None try: idx = ids_in_page.index(video_id) if video_title and not titles_in_page[idx]: @@ -339,6 +344,12 @@ class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): except ValueError: ids_in_page.append(video_id) titles_in_page.append(video_title) + + def extract_videos_from_page(self, page): + ids_in_page = [] + titles_in_page = [] + self.extract_videos_from_page_impl( + self._VIDEO_RE, page, ids_in_page, titles_in_page) return zip(ids_in_page, titles_in_page) @@ -368,11 +379,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?hooktube\.com/| (?:www\.)?yourepeat\.com/| tube\.majestyc\.net/| + # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances (?:(?:www|dev)\.)?invidio\.us/| - (?:www\.)?invidiou\.sh/| - (?:www\.)?invidious\.snopyta\.org/| + (?:(?:www|no)\.)?invidiou\.sh/| + (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/| (?:www\.)?invidious\.kabi\.tk/| + (?:www\.)?invidious\.enkirton\.net/| + (?:www\.)?invidious\.13ad\.de/| + (?:www\.)?invidious\.mastodon\.host/| + (?:www\.)?invidious\.nixnet\.xyz/| + (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| + (?:www\.)?yt\.elukerio\.org/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: @@ -500,6 +518,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # RTMP (unnamed) '_rtmp': {'protocol': 'rtmp'}, + + # av01 video only formats sometimes served with "unknown" codecs + '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, + '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, + '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, + '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, } _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt') @@ -1306,11 +1330,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _parse_sig_js(self, jscode): funcname = self._search_regex( - (r'(["\'])signature\1\s*,\s*(?P[a-zA-Z0-9$]+)\(', + (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P[a-zA-Z0-9$]+)\(', + r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P[a-zA-Z0-9$]+)\(', + 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'\.sig\|\|(?P[a-zA-Z0-9$]+)\(', - r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?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') jsi = JSInterpreter(jscode) @@ -1574,10 +1605,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_id = mobj.group(2) return video_id - def _extract_annotations(self, video_id): - url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id - return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') - @staticmethod def _extract_chapters(description, duration): if not description: @@ -1672,6 +1699,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def extract_token(v_info): return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token')) + def extract_player_response(player_response, video_id): + pl_response = str_or_none(player_response) + if not pl_response: + return + pl_response = self._parse_json(pl_response, video_id, fatal=False) + if isinstance(pl_response, dict): + add_dash_mpd_pr(pl_response) + return pl_response + player_response = {} # Get video info @@ -1694,7 +1730,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): note='Refetching age-gated info webpage', errnote='unable to download video info webpage') video_info = compat_parse_qs(video_info_webpage) + pl_response = video_info.get('player_response', [None])[0] + player_response = extract_player_response(pl_response, video_id) add_dash_mpd(video_info) + view_count = extract_view_count(video_info) else: age_gate = False video_info = None @@ -1717,11 +1756,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): is_live = True sts = ytplayer_config.get('sts') if not player_response: - pl_response = str_or_none(args.get('player_response')) - if pl_response: - pl_response = self._parse_json(pl_response, video_id, fatal=False) - if isinstance(pl_response, dict): - player_response = pl_response + player_response = extract_player_response(args.get('player_response'), video_id) if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): add_dash_mpd_pr(player_response) # We also try looking in get_video_info since it may contain different dashmpd @@ -1753,9 +1788,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): get_video_info = compat_parse_qs(video_info_webpage) if not player_response: pl_response = get_video_info.get('player_response', [None])[0] - if isinstance(pl_response, dict): - player_response = pl_response - add_dash_mpd_pr(player_response) + player_response = extract_player_response(pl_response, video_id) add_dash_mpd(get_video_info) if view_count is None: view_count = extract_view_count(get_video_info) @@ -1778,9 +1811,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): break def extract_unavailable_message(): - return self._html_search_regex( - r'(?s)]+id="unavailable-message"[^>]*>(.+?)', - video_webpage, 'unavailable message', default=None) + messages = [] + for tag, kind in (('h1', 'message'), ('div', 'submessage')): + msg = self._html_search_regex( + r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)'.format(tag=tag, kind=kind), + video_webpage, 'unavailable %s' % kind, default=None) + if msg: + messages.append(msg) + if messages: + return '\n'.join(messages) if not video_info: unavailable_message = extract_unavailable_message() @@ -1792,16 +1831,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} - # title - if 'title' in video_info: - video_title = video_info['title'][0] - elif 'title' in player_response: - video_title = video_details['title'] - else: + video_title = video_info.get('title', [None])[0] or video_details.get('title') + if not video_title: self._downloader.report_warning('Unable to extract video title') video_title = '_' - # description description_original = video_description = get_element_by_id("eow-description", video_webpage) if video_description: @@ -1826,11 +1860,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): ''', replace_url, video_description) video_description = clean_html(video_description) else: - fd_mobj = re.search(r'[A-Za-z0-9+/=]+)\2', + video_webpage, 'xsrf token', group='xsrf_token', fatal=False) + invideo_url = try_get( + player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) + if xsrf_token and invideo_url: + xsrf_field_name = self._search_regex( + r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P\w+)\2', + video_webpage, 'xsrf field name', + group='xsrf_field_name', default='session_token') + video_annotations = self._download_webpage( + self._proto_relative_url(invideo_url), + video_id, note='Downloading annotations', + errnote='Unable to download video annotations', fatal=False, + data=urlencode_postdata({xsrf_field_name: xsrf_token})) chapters = self._extract_chapters(description_original, video_duration) @@ -2401,7 +2453,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): (%(playlist_id)s) )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' - _VIDEO_RE = r'href="\s*/watch\?v=(?P[0-9A-Za-z_-]{11})&[^"]*?index=(?P\d+)(?:[^>]+>(?P[^<]+))?' + _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?' + _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' IE_NAME = 'youtube:playlist' _TESTS = [{ 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', @@ -2424,6 +2477,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': '29C3: Not my department', 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'uploader': 'Christiaan008', + 'uploader_id': 'ChRiStIaAn008', }, 'playlist_count': 95, }, { @@ -2432,6 +2487,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': '[OLD]Team Fortress 2 (Class-based LP)', 'id': 'PLBB231211A4F62143', + 'uploader': 'Wickydoo', + 'uploader_id': 'Wickydoo', }, 'playlist_mincount': 26, }, { @@ -2440,6 +2497,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': 'Uploads from Cauchemar', 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', + 'uploader': 'Cauchemar', + 'uploader_id': 'Cauchemar89', }, 'playlist_mincount': 799, }, { @@ -2457,13 +2516,17 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': 'JODA15', 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'uploader': 'milan', + 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', } }, { 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', 'playlist_mincount': 485, 'info_dict': { - 'title': '2017 華語最新單曲 (2/24更新)', + 'title': '2018 Chinese New Singles (11/6 updated)', 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', + 'uploader': 'LBK', + 'uploader_id': 'sdragonfang', } }, { 'note': 'Embedded SWF player', @@ -2472,13 +2535,16 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': 'JODA7', 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', - } + }, + 'skip': 'This playlist does not exist', }, { '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': 'InterstellarMovie1', }, 'playlist_mincount': 21, }, { @@ -2503,6 +2569,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'This video is not available.', 'add_ie': [YoutubeIE.ie_key()], }, { 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', @@ -2514,7 +2581,6 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'uploader_id': 'backuspagemuseum', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', 'upload_date': '20161008', - 'license': 'Standard YouTube License', 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', 'categories': ['Nonprofits & Activism'], 'tags': list, @@ -2525,6 +2591,16 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'noplaylist': True, 'skip_download': True, }, + }, { + # 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': 'Computerphile', + 'uploader': 'Computerphile', + }, + 'playlist_mincount': 11, }, { 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', 'only_matching': True, @@ -2543,6 +2619,34 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): def _real_initialize(self): self._login() + def extract_videos_from_page(self, page): + ids_in_page = [] + titles_in_page = [] + + for item in re.findall( + r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page): + attrs = extract_attributes(item) + video_id = attrs['data-video-id'] + video_title = unescapeHTML(attrs.get('data-title')) + if video_title: + video_title = video_title.strip() + ids_in_page.append(video_id) + titles_in_page.append(video_title) + + # Fallback with old _VIDEO_RE + self.extract_videos_from_page_impl( + self._VIDEO_RE, page, ids_in_page, titles_in_page) + + # Relaxed fallbacks + self.extract_videos_from_page_impl( + r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page, + ids_in_page, titles_in_page) + self.extract_videos_from_page_impl( + r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page, + ids_in_page, titles_in_page) + + return zip(ids_in_page, titles_in_page) + def _extract_mix(self, playlist_id): # The mixes are generated from a single video # the id of the playlist is just 'RD' + video_id @@ -2691,6 +2795,8 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', 'title': 'Uploads from lex will', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', } }, { 'note': 'Age restricted channel', @@ -2700,6 +2806,8 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'id': 'UUs0ifCMCm1icqRbqhUINa0w', 'title': 'Uploads from Deus Ex', + 'uploader': 'Deus Ex', + 'uploader_id': 'DeusExOfficial', }, }, { 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', @@ -2784,6 +2892,8 @@ class YoutubeUserIE(YoutubeChannelIE): 'info_dict': { 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', 'title': 'Uploads from The Linux Foundation', + 'uploader': 'The Linux Foundation', + 'uploader_id': 'TheLinuxFoundation', } }, { # Only available via https://www.youtube.com/c/12minuteathlete/videos @@ -2793,6 +2903,8 @@ class YoutubeUserIE(YoutubeChannelIE): 'info_dict': { 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', 'title': 'Uploads from 12 Minute Athlete', + 'uploader': '12 Minute Athlete', + 'uploader_id': 'the12minuteathlete', } }, { 'url': 'ytuser:phihag', @@ -2886,7 +2998,7 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): 'playlist_mincount': 4, 'info_dict': { 'id': 'ThirstForScience', - 'title': 'Thirst for Science', + 'title': 'ThirstForScience', }, }, { # with "Load more" button @@ -2903,6 +3015,7 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', 'title': 'Chem Player', }, + 'skip': 'Blocked', }]