logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

youtube.py (162702B)

    

  1. # coding: utf-8
  3. from __future__ import unicode_literals
  5. import itertools
  6. import json
  7. import os.path
  8. import random
  9. import re
  10. import traceback
  12. from .common import InfoExtractor, SearchInfoExtractor
  13. from ..compat import (
  14.     compat_chr,
  15.     compat_HTTPError,
  16.     compat_map as map,
  17.     compat_str,
  18.     compat_urllib_parse,
  19.     compat_urllib_parse_parse_qs as compat_parse_qs,
  20.     compat_urllib_parse_unquote_plus,
  21.     compat_urllib_parse_urlparse,
  22. )
  23. from ..jsinterp import JSInterpreter
  24. from ..utils import (
  25.     ExtractorError,
  26.     clean_html,
  27.     dict_get,
  28.     error_to_compat_str,
  29.     float_or_none,
  30.     extract_attributes,
  31.     get_element_by_attribute,
  32.     int_or_none,
  33.     js_to_json,
  34.     merge_dicts,
  35.     mimetype2ext,
  36.     parse_codecs,
  37.     parse_duration,
  38.     parse_qs,
  39.     qualities,
  40.     remove_start,
  41.     smuggle_url,
  42.     str_or_none,
  43.     str_to_int,
  44.     traverse_obj,
  45.     try_get,
  46.     unescapeHTML,
  47.     unified_strdate,
  48.     unsmuggle_url,
  49.     update_url,
  50.     update_url_query,
  51.     url_or_none,
  52.     urlencode_postdata,
  53.     urljoin,
  54. )
  57. class YoutubeBaseInfoExtractor(InfoExtractor):
  58.     """Provide base functions for Youtube extractors"""
  59.     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
  60.     _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
  62.     _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
  63.     _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
  64.     _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
  66.     _NETRC_MACHINE = 'youtube'
  67.     # If True it will raise an error if no login info is provided
  68.     _LOGIN_REQUIRED = False
  70.     _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
  72.     def _login(self):
  73.         """
  74.         Attempt to log in to YouTube.
  75.         True is returned if successful or skipped.
  76.         False is returned if login failed.
  78.         If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
  79.         """
  80.         username, password = self._get_login_info()
  81.         # No authentication to be performed
  82.         if username is None:
  83.             if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
  84.                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  85.             return True
  87.         login_page = self._download_webpage(
  88.             self._LOGIN_URL, None,
  89.             note='Downloading login page',
  90.             errnote='unable to fetch login page', fatal=False)
  91.         if login_page is False:
  92.             return
  94.         login_form = self._hidden_inputs(login_page)
  96.         def req(url, f_req, note, errnote):
  97.             data = login_form.copy()
  98.             data.update({
  99.                 'pstMsg': 1,
  100.                 'checkConnection': 'youtube',
  101.                 'checkedDomains': 'youtube',
  102.                 'hl': 'en',
  103.                 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
  104.                 'f.req': json.dumps(f_req),
  105.                 'flowName': 'GlifWebSignIn',
  106.                 'flowEntry': 'ServiceLogin',
  107.                 # TODO: reverse actual botguard identifier generation algo
  108.                 'bgRequest': '["identifier",""]',
  109.             })
  110.             return self._download_json(
  111.                 url, None, note=note, errnote=errnote,
  112.                 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
  113.                 fatal=False,
  114.                 data=urlencode_postdata(data), headers={
  115.                     'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
  116.                     'Google-Accounts-XSRF': 1,
  117.                 })
  119.         def warn(message):
  120.             self._downloader.report_warning(message)
  122.         lookup_req = [
  123.             username,
  124.             None, [], None, 'US', None, None, 2, False, True,
  125.             [
  126.                 None, None,
  127.                 [2, 1, None, 1,
  128.                  'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
  129.                  None, [], 4],
  130.                 1, [None, None, []], None, None, None, True
  131.             ],
  132.             username,
  133.         ]
  135.         lookup_results = req(
  136.             self._LOOKUP_URL, lookup_req,
  137.             'Looking up account info', 'Unable to look up account info')
  139.         if lookup_results is False:
  140.             return False
  142.         user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
  143.         if not user_hash:
  144.             warn('Unable to extract user hash')
  145.             return False
  147.         challenge_req = [
  148.             user_hash,
  149.             None, 1, None, [1, None, None, None, [password, None, True]],
  150.             [
  151.                 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
  152.                 1, [None, None, []], None, None, None, True
  153.             ]]
  155.         challenge_results = req(
  156.             self._CHALLENGE_URL, challenge_req,
  157.             'Logging in', 'Unable to log in')
  159.         if challenge_results is False:
  160.             return
  162.         login_res = try_get(challenge_results, lambda x: x[0][5], list)
  163.         if login_res:
  164.             login_msg = try_get(login_res, lambda x: x[5], compat_str)
  165.             warn(
  166.                 'Unable to login: %s' % 'Invalid password'
  167.                 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
  168.             return False
  170.         res = try_get(challenge_results, lambda x: x[0][-1], list)
  171.         if not res:
  172.             warn('Unable to extract result entry')
  173.             return False
  175.         login_challenge = try_get(res, lambda x: x[0][0], list)
  176.         if login_challenge:
  177.             challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
  178.             if challenge_str == 'TWO_STEP_VERIFICATION':
  179.                 # SEND_SUCCESS - TFA code has been successfully sent to phone
  180.                 # QUOTA_EXCEEDED - reached the limit of TFA codes
  181.                 status = try_get(login_challenge, lambda x: x[5], compat_str)
  182.                 if status == 'QUOTA_EXCEEDED':
  183.                     warn('Exceeded the limit of TFA codes, try later')
  184.                     return False
  186.                 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
  187.                 if not tl:
  188.                     warn('Unable to extract TL')
  189.                     return False
  191.                 tfa_code = self._get_tfa_info('2-step verification code')
  193.                 if not tfa_code:
  194.                     warn(
  195.                         'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
  196.                         '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
  197.                     return False
  199.                 tfa_code = remove_start(tfa_code, 'G-')
  201.                 tfa_req = [
  202.                     user_hash, None, 2, None,
  203.                     [
  204.                         9, None, None, None, None, None, None, None,
  205.                         [None, tfa_code, True, 2]
  206.                     ]]
  208.                 tfa_results = req(
  209.                     self._TFA_URL.format(tl), tfa_req,
  210.                     'Submitting TFA code', 'Unable to submit TFA code')
  212.                 if tfa_results is False:
  213.                     return False
  215.                 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
  216.                 if tfa_res:
  217.                     tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
  218.                     warn(
  219.                         'Unable to finish TFA: %s' % 'Invalid TFA code'
  220.                         if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
  221.                     return False
  223.                 check_cookie_url = try_get(
  224.                     tfa_results, lambda x: x[0][-1][2], compat_str)
  225.             else:
  226.                 CHALLENGES = {
  227.                     'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
  228.                     'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
  229.                     'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
  230.                 }
  231.                 challenge = CHALLENGES.get(
  232.                     challenge_str,
  233.                     '%s returned error %s.' % (self.IE_NAME, challenge_str))
  234.                 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
  235.                 return False
  236.         else:
  237.             check_cookie_url = try_get(res, lambda x: x[2], compat_str)
  239.         if not check_cookie_url:
  240.             warn('Unable to extract CheckCookie URL')
  241.             return False
  243.         check_cookie_results = self._download_webpage(
  244.             check_cookie_url, None, 'Checking cookie', fatal=False)
  246.         if check_cookie_results is False:
  247.             return False
  249.         if 'https://myaccount.google.com/' not in check_cookie_results:
  250.             warn('Unable to log in')
  251.             return False
  253.         return True
  255.     def _initialize_consent(self):
  256.         cookies = self._get_cookies('https://www.youtube.com/')
  257.         if cookies.get('__Secure-3PSID'):
  258.             return
  259.         consent_id = None
  260.         consent = cookies.get('CONSENT')
  261.         if consent:
  262.             if 'YES' in consent.value:
  263.                 return
  264.             consent_id = self._search_regex(
  265.                 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
  266.         if not consent_id:
  267.             consent_id = random.randint(100, 999)
  268.         self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
  270.     def _real_initialize(self):
  271.         self._initialize_consent()
  272.         if self._downloader is None:
  273.             return
  274.         if not self._login():
  275.             return
  277.     _DEFAULT_API_DATA = {
  278.         'context': {
  279.             'client': {
  280.                 'clientName': 'WEB',
  281.                 'clientVersion': '2.20201021.03.00',
  282.             }
  283.         },
  284.     }
  286.     _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
  287.     _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
  288.     _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
  290.     def _call_api(self, ep, query, video_id, fatal=True, headers=None):
  291.         data = self._DEFAULT_API_DATA.copy()
  292.         data.update(query)
  293.         real_headers = {'content-type': 'application/json'}
  294.         if headers:
  295.             real_headers.update(headers)
  297.         return self._download_json(
  298.             'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id,
  299.             note='Downloading API JSON', errnote='Unable to download API page',
  300.             data=json.dumps(data).encode('utf8'), fatal=fatal,
  301.             headers=real_headers,
  302.             query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'})
  304.     def _extract_yt_initial_data(self, video_id, webpage):
  305.         return self._parse_json(
  306.             self._search_regex(
  307.                 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
  308.                  self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
  309.             video_id)
  311.     def _extract_ytcfg(self, video_id, webpage):
  312.         return self._parse_json(
  313.             self._search_regex(
  314.                 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
  315.                 default='{}'), video_id, fatal=False) or {}
  317.     def _extract_video(self, renderer):
  318.         video_id = renderer['videoId']
  319.         title = try_get(
  320.             renderer,
  321.             (lambda x: x['title']['runs'][0]['text'],
  322.              lambda x: x['title']['simpleText'],
  323.              lambda x: x['headline']['simpleText']), compat_str)
  324.         description = try_get(
  325.             renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
  326.             compat_str)
  327.         duration = parse_duration(try_get(
  328.             renderer, lambda x: x['lengthText']['simpleText'], compat_str))
  329.         view_count_text = try_get(
  330.             renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
  331.         view_count = str_to_int(self._search_regex(
  332.             r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
  333.             'view count', default=None))
  334.         uploader = try_get(
  335.             renderer,
  336.             (lambda x: x['ownerText']['runs'][0]['text'],
  337.              lambda x: x['shortBylineText']['runs'][0]['text']), compat_str)
  338.         return {
  339.             '_type': 'url',
  340.             'ie_key': YoutubeIE.ie_key(),
  341.             'id': video_id,
  342.             'url': video_id,
  343.             'title': title,
  344.             'description': description,
  345.             'duration': duration,
  346.             'view_count': view_count,
  347.             'uploader': uploader,
  348.         }
  350.     def _search_results(self, query, params):
  351.         data = {
  352.             'context': {
  353.                 'client': {
  354.                     'clientName': 'WEB',
  355.                     'clientVersion': '2.20201021.03.00',
  356.                 }
  357.             },
  358.             'query': query,
  359.         }
  360.         if params:
  361.             data['params'] = params
  362.         for page_num in itertools.count(1):
  363.             search = self._download_json(
  364.                 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
  365.                 video_id='query "%s"' % query,
  366.                 note='Downloading page %s' % page_num,
  367.                 errnote='Unable to download API page', fatal=False,
  368.                 data=json.dumps(data).encode('utf8'),
  369.                 headers={'content-type': 'application/json'})
  370.             if not search:
  371.                 break
  372.             slr_contents = try_get(
  373.                 search,
  374.                 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
  375.                  lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
  376.                 list)
  377.             if not slr_contents:
  378.                 break
  379.             for slr_content in slr_contents:
  380.                 isr_contents = try_get(
  381.                     slr_content,
  382.                     lambda x: x['itemSectionRenderer']['contents'],
  383.                     list)
  384.                 if not isr_contents:
  385.                     continue
  386.                 for content in isr_contents:
  387.                     if not isinstance(content, dict):
  388.                         continue
  389.                     video = content.get('videoRenderer')
  390.                     if not isinstance(video, dict):
  391.                         continue
  392.                     video_id = video.get('videoId')
  393.                     if not video_id:
  394.                         continue
  395.                     yield self._extract_video(video)
  396.             token = try_get(
  397.                 slr_contents,
  398.                 lambda x: x[-1]['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
  399.                 compat_str)
  400.             if not token:
  401.                 break
  402.             data['continuation'] = token
  404.     @staticmethod
  405.     def _owner_endpoints_path():
  406.         return [
  407.             Ellipsis,
  408.             lambda k, _: k.endswith('SecondaryInfoRenderer'),
  409.             ('owner', 'videoOwner'), 'videoOwnerRenderer', 'title',
  410.             'runs', Ellipsis]
  412.     def _extract_channel_id(self, webpage, videodetails={}, metadata={}, renderers=[]):
  413.         channel_id = None
  414.         if any((videodetails, metadata, renderers)):
  415.             channel_id = (
  416.                 traverse_obj(videodetails, 'channelId')
  417.                 or traverse_obj(metadata, 'externalChannelId', 'externalId')
  418.                 or traverse_obj(renderers,
  419.                                 self._owner_endpoints_path() + [
  420.                                     'navigationEndpoint', 'browseEndpoint', 'browseId'],
  421.                                 get_all=False)
  422.             )
  423.         return channel_id or self._html_search_meta(
  424.             'channelId', webpage, 'channel id', default=None)
  426.     def _extract_author_var(self, webpage, var_name,
  427.                             videodetails={}, metadata={}, renderers=[]):
  428.         result = None
  429.         paths = {
  430.             #       (HTML, videodetails, metadata, renderers)
  431.             'name': ('content', 'author', (('ownerChannelName', None), 'title'), ['text']),
  432.             'url': ('href', 'ownerProfileUrl', 'vanityChannelUrl',
  433.                     ['navigationEndpoint', 'browseEndpoint', 'canonicalBaseUrl'])
  434.         }
  435.         if any((videodetails, metadata, renderers)):
  436.             result = (
  437.                 traverse_obj(videodetails, paths[var_name][1], get_all=False)
  438.                 or traverse_obj(metadata, paths[var_name][2], get_all=False)
  439.                 or traverse_obj(renderers,
  440.                                 self._owner_endpoints_path() + paths[var_name][3],
  441.                                 get_all=False)
  442.             )
  443.         return result or traverse_obj(
  444.             extract_attributes(self._search_regex(
  445.                 r'''(?s)(<link\b[^>]+\bitemprop\s*=\s*("|')%s\2[^>]*>)'''
  446.                 % re.escape(var_name),
  447.                 get_element_by_attribute('itemprop', 'author', webpage) or '',
  448.                 'author link', default='')),
  449.             paths[var_name][0])
  451.     @staticmethod
  452.     def _yt_urljoin(url_or_path):
  453.         return urljoin('https://www.youtube.com', url_or_path)
  455.     def _extract_uploader_id(self, uploader_url):
  456.         return self._search_regex(
  457.             r'/(?:(?:channel|user)/|(?=@))([^/?&#]+)', uploader_url or '',
  458.             'uploader id', default=None)
  461. class YoutubeIE(YoutubeBaseInfoExtractor):
  462.     IE_DESC = 'YouTube.com'
  463.     _INVIDIOUS_SITES = (
  464.         # invidious-redirect websites
  465.         r'(?:www\.)?redirect\.invidious\.io',
  466.         r'(?:(?:www|dev)\.)?invidio\.us',
  467.         # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
  468.         r'(?:(?:www|no)\.)?invidiou\.sh',
  469.         r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
  470.         r'(?:www\.)?invidious\.kabi\.tk',
  471.         r'(?:www\.)?invidious\.13ad\.de',
  472.         r'(?:www\.)?invidious\.mastodon\.host',
  473.         r'(?:www\.)?invidious\.zapashcanon\.fr',
  474.         r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
  475.         r'(?:www\.)?invidious\.tinfoil-hat\.net',
  476.         r'(?:www\.)?invidious\.himiko\.cloud',
  477.         r'(?:www\.)?invidious\.reallyancient\.tech',
  478.         r'(?:www\.)?invidious\.tube',
  479.         r'(?:www\.)?invidiou\.site',
  480.         r'(?:www\.)?invidious\.site',
  481.         r'(?:www\.)?invidious\.xyz',
  482.         r'(?:www\.)?invidious\.nixnet\.xyz',
  483.         r'(?:www\.)?invidious\.048596\.xyz',
  484.         r'(?:www\.)?invidious\.drycat\.fr',
  485.         r'(?:www\.)?inv\.skyn3t\.in',
  486.         r'(?:www\.)?tube\.poal\.co',
  487.         r'(?:www\.)?tube\.connect\.cafe',
  488.         r'(?:www\.)?vid\.wxzm\.sx',
  489.         r'(?:www\.)?vid\.mint\.lgbt',
  490.         r'(?:www\.)?vid\.puffyan\.us',
  491.         r'(?:www\.)?yewtu\.be',
  492.         r'(?:www\.)?yt\.elukerio\.org',
  493.         r'(?:www\.)?yt\.lelux\.fi',
  494.         r'(?:www\.)?invidious\.ggc-project\.de',
  495.         r'(?:www\.)?yt\.maisputain\.ovh',
  496.         r'(?:www\.)?ytprivate\.com',
  497.         r'(?:www\.)?invidious\.13ad\.de',
  498.         r'(?:www\.)?invidious\.toot\.koeln',
  499.         r'(?:www\.)?invidious\.fdn\.fr',
  500.         r'(?:www\.)?watch\.nettohikari\.com',
  501.         r'(?:www\.)?invidious\.namazso\.eu',
  502.         r'(?:www\.)?invidious\.silkky\.cloud',
  503.         r'(?:www\.)?invidious\.exonip\.de',
  504.         r'(?:www\.)?invidious\.riverside\.rocks',
  505.         r'(?:www\.)?invidious\.blamefran\.net',
  506.         r'(?:www\.)?invidious\.moomoo\.de',
  507.         r'(?:www\.)?ytb\.trom\.tf',
  508.         r'(?:www\.)?yt\.cyberhost\.uk',
  509.         r'(?:www\.)?kgg2m7yk5aybusll\.onion',
  510.         r'(?:www\.)?qklhadlycap4cnod\.onion',
  511.         r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
  512.         r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
  513.         r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
  514.         r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
  515.         r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
  516.         r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
  517.         r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
  518.         r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
  519.         r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
  520.         r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
  521.     )
  522.     _VALID_URL = r"""(?x)^
  523.                      (
  524.                          (?:https?://|//)                                    # http(s):// or protocol-independent URL
  525.                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
  526.                             (?:www\.)?deturl\.com/www\.youtube\.com|
  527.                             (?:www\.)?pwnyoutube\.com|
  528.                             (?:www\.)?hooktube\.com|
  529.                             (?:www\.)?yourepeat\.com|
  530.                             tube\.majestyc\.net|
  531.                             %(invidious)s|
  532.                             youtube\.googleapis\.com)/                        # the various hostnames, with wildcard subdomains
  533.                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
  534.                          (?:                                                  # the various things that can precede the ID:
  535.                              (?:(?:v|embed|e)/(?!videoseries))                # v/ or embed/ or e/
  536.                              |shorts/
  537.                              |(?:                                             # or the v= param in all its forms
  538.                                  (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
  539.                                  (?:\?|\#!?)                                  # the params delimiter ? or # or #!
  540.                                  (?:.*?[&;])??                                # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
  541.                                  v=
  542.                              )
  543.                          ))
  544.                          |(?:
  545.                             youtu\.be|                                        # just youtu.be/xxxx
  546.                             vid\.plus|                                        # or vid.plus/xxxx
  547.                             zwearz\.com/watch|                                # or zwearz.com/watch/xxxx
  548.                             %(invidious)s
  549.                          )/
  550.                          |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
  551.                          )
  552.                      )?                                                       # all until now is optional -> you can pass the naked ID
  553.                      (?P<id>[0-9A-Za-z_-]{11})                                # here is it! the YouTube video ID
  554.                      (?(1).+)?                                                # if we found the ID, everything can follow
  555.                      $""" % {
  556.         'invidious': '|'.join(_INVIDIOUS_SITES),
  557.     }
  558.     _PLAYER_INFO_RE = (
  559.         r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
  560.         r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
  561.         r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
  562.     )
  563.     _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
  565.     _GEO_BYPASS = False
  567.     IE_NAME = 'youtube'
  568.     _TESTS = [
  569.         {
  570.             'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
  571.             'info_dict': {
  572.                 'id': 'BaW_jenozKc',
  573.                 'ext': 'mp4',
  574.                 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
  575.                 'uploader': 'Philipp Hagemeister',
  576.                 'uploader_id': '@PhilippHagemeister',
  577.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@PhilippHagemeister',
  578.                 'channel': 'Philipp Hagemeister',
  579.                 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
  580.                 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
  581.                 'upload_date': '20121002',
  582.                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
  583.                 'categories': ['Science & Technology'],
  584.                 'tags': ['youtube-dl'],
  585.                 'duration': 10,
  586.                 'view_count': int,
  587.                 'like_count': int,
  588.                 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
  589.                 'start_time': 1,
  590.                 'end_time': 9,
  591.             },
  592.         },
  593.         {
  594.             'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
  595.             'note': 'Embed-only video (#1746)',
  596.             'info_dict': {
  597.                 'id': 'yZIXLfi8CZQ',
  598.                 'ext': 'mp4',
  599.                 'upload_date': '20120608',
  600.                 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
  601.                 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
  602.                 'uploader': 'SET India',
  603.                 'uploader_id': 'setindia',
  604.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
  605.                 'age_limit': 18,
  606.             },
  607.             'skip': 'Private video',
  608.         },
  609.         {
  610.             'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
  611.             'note': 'Use the first video ID in the URL',
  612.             'info_dict': {
  613.                 'id': 'BaW_jenozKc',
  614.                 'ext': 'mp4',
  615.                 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
  616.                 'uploader': 'Philipp Hagemeister',
  617.                 'uploader_id': '@PhilippHagemeister',
  618.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@PhilippHagemeister',
  619.                 'upload_date': '20121002',
  620.                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
  621.                 'categories': ['Science & Technology'],
  622.                 'tags': ['youtube-dl'],
  623.                 'duration': 10,
  624.                 'view_count': int,
  625.                 'like_count': int,
  626.             },
  627.             'params': {
  628.                 'skip_download': True,
  629.             },
  630.         },
  631.         {
  632.             'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
  633.             'note': '256k DASH audio (format 141) via DASH manifest',
  634.             'info_dict': {
  635.                 'id': 'a9LDPn-MO4I',
  636.                 'ext': 'm4a',
  637.                 'upload_date': '20121002',
  638.                 'uploader_id': '8KVIDEO',
  639.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
  640.                 'description': '',
  641.                 'uploader': '8KVIDEO',
  642.                 'title': 'UHDTV TEST 8K VIDEO.mp4'
  643.             },
  644.             'params': {
  645.                 'youtube_include_dash_manifest': True,
  646.                 'format': '141',
  647.             },
  648.             'skip': 'format 141 not served any more',
  649.         },
  650.         # DASH manifest with encrypted signature
  651.         {
  652.             'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
  653.             'info_dict': {
  654.                 'id': 'IB3lcPjvWLA',
  655.                 'ext': 'm4a',
  656.                 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
  657.                 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
  658.                 'duration': 244,
  659.                 'uploader': 'AfrojackVEVO',
  660.                 'uploader_id': '@AfrojackVEVO',
  661.                 'upload_date': '20131011',
  662.                 'abr': 129.495,
  663.             },
  664.             'params': {
  665.                 'youtube_include_dash_manifest': True,
  666.                 'format': '141/bestaudio[ext=m4a]',
  667.             },
  668.         },
  669.         # Controversy video
  670.         {
  671.             'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
  672.             'info_dict': {
  673.                 'id': 'T4XJQO3qol8',
  674.                 'ext': 'mp4',
  675.                 'duration': 219,
  676.                 'upload_date': '20100909',
  677.                 'uploader': 'Amazing Atheist',
  678.                 'uploader_id': '@theamazingatheist',
  679.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@theamazingatheist',
  680.                 'title': 'Burning Everyone\'s Koran',
  681.                 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms \r\n\r\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
  682.             }
  683.         },
  684.         # Age-gated videos
  685.         {
  686.             'note': 'Age-gated video (No vevo, embed allowed)',
  687.             'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
  688.             'info_dict': {
  689.                 'id': 'HtVdAasjOgU',
  690.                 'ext': 'mp4',
  691.                 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
  692.                 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
  693.                 'duration': 142,
  694.                 'uploader': 'The Witcher',
  695.                 'uploader_id': '@thewitcher',
  696.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@thewitcher',
  697.                 'upload_date': '20140605',
  698.                 'thumbnail': 'https://i.ytimg.com/vi/HtVdAasjOgU/maxresdefault.jpg',
  699.                 'age_limit': 18,
  700.                 'categories': ['Gaming'],
  701.                 'tags': 'count:17',
  702.                 'channel': 'The Witcher',
  703.                 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
  704.                 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
  705.                 'view_count': int,
  706.                 'like_count': int,
  707.             },
  708.         },
  709.         {
  710.             'note': 'Age-gated video with embed allowed in public site',
  711.             'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
  712.             'info_dict': {
  713.                 'id': 'HsUATh_Nc2U',
  714.                 'ext': 'mp4',
  715.                 'title': 'Godzilla 2 (Official Video)',
  716.                 'description': 'md5:bf77e03fcae5529475e500129b05668a',
  717.                 'duration': 177,
  718.                 'uploader': 'FlyingKitty',
  719.                 'uploader_id': '@FlyingKitty900',
  720.                 'upload_date': '20200408',
  721.                 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
  722.                 'age_limit': 18,
  723.                 'categories': ['Entertainment'],
  724.                 'tags': ['Flyingkitty', 'godzilla 2'],
  725.                 'channel': 'FlyingKitty',
  726.                 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
  727.                 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
  728.                 'view_count': int,
  729.                 'like_count': int,
  730.             },
  731.         },
  732.         {
  733.             'note': 'Age-gated video embeddable only with clientScreen=EMBED',
  734.             'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
  735.             'info_dict': {
  736.                 'id': 'Tq92D6wQ1mg',
  737.                 'ext': 'mp4',
  738.                 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
  739.                 'description': 'md5:17eccca93a786d51bc67646756894066',
  740.                 'duration': 106,
  741.                 'uploader': 'Projekt Melody',
  742.                 'uploader_id': '@ProjektMelody',
  743.                 'upload_date': '20191227',
  744.                 'age_limit': 18,
  745.                 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
  746.                 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
  747.                 'categories': ['Entertainment'],
  748.                 'channel': 'Projekt Melody',
  749.                 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
  750.                 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
  751.                 'view_count': int,
  752.                 'like_count': int,
  753.             },
  754.         },
  755.         {
  756.             'note': 'Non-Age-gated non-embeddable video',
  757.             'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
  758.             'info_dict': {
  759.                 'id': 'MeJVWBSsPAY',
  760.                 'ext': 'mp4',
  761.                 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
  762.                 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
  763.                 'duration': 210,
  764.                 'upload_date': '20130730',
  765.                 'uploader': 'Herr Lurik',
  766.                 'uploader_id': '@HerrLurik',
  767.                 'uploader_url': 'http://www.youtube.com/@HerrLurik',
  768.                 'age_limit': 0,
  769.                 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/hqdefault.jpg',
  770.                 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
  771.                 'categories': ['Music'],
  772.                 'channel': 'Herr Lurik',
  773.                 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
  774.                 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
  775.                 'artist': 'OOMPH!',
  776.                 'view_count': int,
  777.                 'like_count': int,
  778.             },
  779.         },
  780.         {
  781.             'note': 'Non-bypassable age-gated video',
  782.             'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
  783.             'only_matching': True,
  784.         },
  785.         {
  786.             'note': 'Age-gated video only available with authentication (not via embed workaround)',
  787.             'url': 'XgnwCQzjau8',
  788.             'only_matching': True,
  789.             'skip': '''This video has been removed for violating YouTube's Community Guidelines''',
  790.         },
  791.         # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
  792.         # YouTube Red ad is not captured for creator
  793.         {
  794.             'url': '__2ABJjxzNo',
  795.             'info_dict': {
  796.                 'id': '__2ABJjxzNo',
  797.                 'ext': 'mp4',
  798.                 'duration': 266,
  799.                 'upload_date': '20100430',
  800.                 'uploader_id': '@deadmau5',
  801.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@deadmau5',
  802.                 'creator': 'deadmau5',
  803.                 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
  804.                 'uploader': 'deadmau5',
  805.                 'title': 'Deadmau5 - Some Chords (HD)',
  806.                 'alt_title': 'Some Chords',
  807.             },
  808.             'expected_warnings': [
  809.                 'DASH manifest missing',
  810.             ]
  811.         },
  812.         # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
  813.         {
  814.             'url': 'lqQg6PlCWgI',
  815.             'info_dict': {
  816.                 'id': 'lqQg6PlCWgI',
  817.                 'ext': 'mp4',
  818.                 'title': 'Hockey - Women -  GER-AUS - London 2012 Olympic Games',
  819.                 'description': r're:(?s)(?:.+\s)?HO09  - Women -  GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games\s*',
  820.                 'duration': 6085,
  821.                 'upload_date': '20150827',
  822.                 'uploader_id': '@Olympics',
  823.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@Olympics',
  824.                 'uploader': r're:Olympics?',
  825.                 'age_limit': 0,
  826.                 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
  827.                 'categories': ['Sports'],
  828.                 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
  829.                 'channel': 'Olympics',
  830.                 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
  831.                 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
  832.                 'view_count': int,
  833.                 'like_count': int,
  834.             },
  835.         },
  836.         # Non-square pixels
  837.         {
  838.             'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
  839.             'info_dict': {
  840.                 'id': '_b-2C3KPAM0',
  841.                 'ext': 'mp4',
  842.                 'stretched_ratio': 16 / 9.,
  843.                 'duration': 85,
  844.                 'upload_date': '20110310',
  845.                 'uploader_id': '@AllenMeow',
  846.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@AllenMeow',
  847.                 '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',
  848.                 'uploader': '孫ᄋᄅ',
  849.                 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
  850.             },
  851.         },
  852.         # url_encoded_fmt_stream_map is empty string
  853.         {
  854.             'url': 'qEJwOuvDf7I',
  855.             'info_dict': {
  856.                 'id': 'qEJwOuvDf7I',
  857.                 'ext': 'webm',
  858.                 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
  859.                 'description': '',
  860.                 'upload_date': '20150404',
  861.                 'uploader_id': 'spbelect',
  862.                 'uploader': 'Наблюдатели Петербурга',
  863.             },
  864.             'params': {
  865.                 'skip_download': 'requires avconv',
  866.             },
  867.             'skip': 'This live event has ended.',
  868.         },
  869.         # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
  870.         {
  871.             'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
  872.             'info_dict': {
  873.                 'id': 'FIl7x6_3R5Y',
  874.                 'ext': 'webm',
  875.                 'title': 'md5:7b81415841e02ecd4313668cde88737a',
  876.                 'description': 'md5:116377fd2963b81ec4ce64b542173306',
  877.                 'duration': 220,
  878.                 'upload_date': '20150625',
  879.                 'uploader_id': 'dorappi2000',
  880.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
  881.                 'uploader': 'dorappi2000',
  882.                 'formats': 'mincount:31',
  883.             },
  884.             'skip': 'not actual any more',
  885.         },
  886.         # DASH manifest with segment_list
  887.         {
  888.             'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
  889.             'md5': '8ce563a1d667b599d21064e982ab9e31',
  890.             'info_dict': {
  891.                 'id': 'CsmdDsKjzN8',
  892.                 'ext': 'mp4',
  893.                 'upload_date': '20150501',  # According to '<meta itemprop="datePublished"', but in other places it's 20150510
  894.                 'uploader': 'Airtek',
  895.                 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
  896.                 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
  897.                 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
  898.             },
  899.             'params': {
  900.                 'youtube_include_dash_manifest': True,
  901.                 'format': '135',  # bestvideo
  902.             },
  903.             'skip': 'This live event has ended.',
  904.         },
  905.         {
  906.             # Multifeed videos (multiple cameras), URL is for Main Camera
  907.             'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
  908.             'info_dict': {
  909.                 'id': 'jvGDaLqkpTg',
  910.                 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
  911.                 'description': 'md5:e03b909557865076822aa169218d6a5d',
  912.             },
  913.             'playlist': [{
  914.                 'info_dict': {
  915.                     'id': 'jvGDaLqkpTg',
  916.                     'ext': 'mp4',
  917.                     'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
  918.                     'description': 'md5:e03b909557865076822aa169218d6a5d',
  919.                     'duration': 10643,
  920.                     'upload_date': '20161111',
  921.                     'uploader': 'Team PGP',
  922.                     'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
  923.                     'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
  924.                 },
  925.             }, {
  926.                 'info_dict': {
  927.                     'id': '3AKt1R1aDnw',
  928.                     'ext': 'mp4',
  929.                     'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
  930.                     'description': 'md5:e03b909557865076822aa169218d6a5d',
  931.                     'duration': 10991,
  932.                     'upload_date': '20161111',
  933.                     'uploader': 'Team PGP',
  934.                     'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
  935.                     'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
  936.                 },
  937.             }, {
  938.                 'info_dict': {
  939.                     'id': 'RtAMM00gpVc',
  940.                     'ext': 'mp4',
  941.                     'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
  942.                     'description': 'md5:e03b909557865076822aa169218d6a5d',
  943.                     'duration': 10995,
  944.                     'upload_date': '20161111',
  945.                     'uploader': 'Team PGP',
  946.                     'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
  947.                     'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
  948.                 },
  949.             }, {
  950.                 'info_dict': {
  951.                     'id': '6N2fdlP3C5U',
  952.                     'ext': 'mp4',
  953.                     'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
  954.                     'description': 'md5:e03b909557865076822aa169218d6a5d',
  955.                     'duration': 10990,
  956.                     'upload_date': '20161111',
  957.                     'uploader': 'Team PGP',
  958.                     'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
  959.                     'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
  960.                 },
  961.             }],
  962.             'params': {
  963.                 'skip_download': True,
  964.             },
  965.             'skip': 'Not multifeed any more',
  966.         },
  967.         {
  968.             # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
  969.             'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
  970.             'info_dict': {
  971.                 'id': 'gVfLd0zydlo',
  972.                 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
  973.             },
  974.             'playlist_count': 2,
  975.             'skip': 'Not multifeed any more',
  976.         },
  977.         {
  978.             'url': 'https://vid.plus/FlRa-iH7PGw',
  979.             'only_matching': True,
  980.         },
  981.         {
  982.             'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
  983.             'only_matching': True,
  984.         },
  985.         {
  986.             # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
  987.             # Also tests cut-off URL expansion in video description (see
  988.             # https://github.com/ytdl-org/youtube-dl/issues/1892,
  989.             # https://github.com/ytdl-org/youtube-dl/issues/8164)
  990.             'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
  991.             'info_dict': {
  992.                 'id': 'lsguqyKfVQg',
  993.                 'ext': 'mp4',
  994.                 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
  995.                 'alt_title': 'Dark Walk',
  996.                 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
  997.                 'duration': 133,
  998.                 'upload_date': '20151119',
  999.                 'uploader_id': '@IronSoulElf',
  1000.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@IronSoulElf',
  1001.                 'uploader': 'IronSoulElf',
  1002.                 'creator': r're:Todd Haberman[;,]\s+Daniel Law Heath and Aaron Kaplan',
  1003.                 'track': 'Dark Walk',
  1004.                 'artist': r're:Todd Haberman[;,]\s+Daniel Law Heath and Aaron Kaplan',
  1005.                 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
  1006.             },
  1007.             'params': {
  1008.                 'skip_download': True,
  1009.             },
  1010.         },
  1011.         {
  1012.             # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
  1013.             'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
  1014.             'only_matching': True,
  1015.         },
  1016.         {
  1017.             # Video with yt:stretch=17:0
  1018.             'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
  1019.             'info_dict': {
  1020.                 'id': 'Q39EVAstoRM',
  1021.                 'ext': 'mp4',
  1022.                 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
  1023.                 'description': 'md5:ee18a25c350637c8faff806845bddee9',
  1024.                 'upload_date': '20151107',
  1025.                 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
  1026.                 'uploader': 'CH GAMER DROID',
  1027.             },
  1028.             'params': {
  1029.                 'skip_download': True,
  1030.             },
  1031.             'skip': 'This video does not exist.',
  1032.         },
  1033.         {
  1034.             # Video with incomplete 'yt:stretch=16:'
  1035.             'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
  1036.             'only_matching': True,
  1037.         },
  1038.         {
  1039.             # Video licensed under Creative Commons
  1040.             'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
  1041.             'info_dict': {
  1042.                 'id': 'M4gD1WSo5mA',
  1043.                 'ext': 'mp4',
  1044.                 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
  1045.                 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
  1046.                 'duration': 721,
  1047.                 'upload_date': '20150127',
  1048.                 'uploader_id': '@BKCHarvard',
  1049.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@BKCHarvard',
  1050.                 'uploader': 'The Berkman Klein Center for Internet & Society',
  1051.                 'license': 'Creative Commons Attribution license (reuse allowed)',
  1052.             },
  1053.             'params': {
  1054.                 'skip_download': True,
  1055.             },
  1056.         },
  1057.         {
  1058.             # Channel-like uploader_url
  1059.             'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
  1060.             'info_dict': {
  1061.                 'id': 'eQcmzGIKrzg',
  1062.                 'ext': 'mp4',
  1063.                 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
  1064.                 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
  1065.                 'duration': 4060,
  1066.                 'upload_date': '20151119',
  1067.                 'uploader': 'Bernie Sanders',
  1068.                 'uploader_id': '@BernieSanders',
  1069.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@BernieSanders',
  1070.                 'license': 'Creative Commons Attribution license (reuse allowed)',
  1071.             },
  1072.             'params': {
  1073.                 'skip_download': True,
  1074.             },
  1075.         },
  1076.         {
  1077.             'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
  1078.             'only_matching': True,
  1079.         },
  1080.         {
  1081.             # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
  1082.             'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
  1083.             'only_matching': True,
  1084.         },
  1085.         {
  1086.             # Rental video preview
  1087.             'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
  1088.             'info_dict': {
  1089.                 'id': 'uGpuVWrhIzE',
  1090.                 'ext': 'mp4',
  1091.                 'title': 'Piku - Trailer',
  1092.                 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
  1093.                 'upload_date': '20150811',
  1094.                 'uploader': 'FlixMatrix',
  1095.                 'uploader_id': 'FlixMatrixKaravan',
  1096.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
  1097.                 'license': 'Standard YouTube License',
  1098.             },
  1099.             'params': {
  1100.                 'skip_download': True,
  1101.             },
  1102.             'skip': 'This video is not available.',
  1103.         },
  1104.         {
  1105.             # YouTube Red video with episode data
  1106.             'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
  1107.             'info_dict': {
  1108.                 'id': 'iqKdEhx-dD4',
  1109.                 'ext': 'mp4',
  1110.                 'title': 'Isolation - Mind Field (Ep 1)',
  1111.                 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
  1112.                 'duration': 2085,
  1113.                 'upload_date': '20170118',
  1114.                 'uploader': 'Vsauce',
  1115.                 'uploader_id': '@Vsauce',
  1116.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@Vsauce',
  1117.                 'series': 'Mind Field',
  1118.                 'season_number': 1,
  1119.                 'episode_number': 1,
  1120.             },
  1121.             'params': {
  1122.                 'skip_download': True,
  1123.             },
  1124.             'expected_warnings': [
  1125.                 'Skipping DASH manifest',
  1126.             ],
  1127.         },
  1128.         {
  1129.             # The following content has been identified by the YouTube community
  1130.             # as inappropriate or offensive to some audiences.
  1131.             'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
  1132.             'info_dict': {
  1133.                 'id': '6SJNVb0GnPI',
  1134.                 'ext': 'mp4',
  1135.                 'title': 'Race Differences in Intelligence',
  1136.                 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
  1137.                 'duration': 965,
  1138.                 'upload_date': '20140124',
  1139.                 'uploader': 'New Century Foundation',
  1140.                 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
  1141.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
  1142.             },
  1143.             'params': {
  1144.                 'skip_download': True,
  1145.             },
  1146.             'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
  1147.         },
  1148.         {
  1149.             # itag 212
  1150.             'url': '1t24XAntNCY',
  1151.             'only_matching': True,
  1152.         },
  1153.         {
  1154.             # geo restricted to JP
  1155.             'url': 'sJL6WA-aGkQ',
  1156.             'only_matching': True,
  1157.         },
  1158.         {
  1159.             'url': 'https://invidio.us/watch?v=BaW_jenozKc',
  1160.             'only_matching': True,
  1161.         },
  1162.         {
  1163.             'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
  1164.             'only_matching': True,
  1165.         },
  1166.         {
  1167.             # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
  1168.             'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
  1169.             'only_matching': True,
  1170.         },
  1171.         {
  1172.             # DRM protected
  1173.             'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
  1174.             'only_matching': True,
  1175.         },
  1176.         {
  1177.             # Video with unsupported adaptive stream type formats
  1178.             'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
  1179.             'info_dict': {
  1180.                 'id': 'Z4Vy8R84T1U',
  1181.                 'ext': 'mp4',
  1182.                 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
  1183.                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  1184.                 'duration': 433,
  1185.                 'upload_date': '20130923',
  1186.                 'uploader': 'Amelia Putri Harwita',
  1187.                 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
  1188.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
  1189.                 'formats': 'maxcount:10',
  1190.             },
  1191.             'params': {
  1192.                 'skip_download': True,
  1193.                 'youtube_include_dash_manifest': False,
  1194.             },
  1195.             'skip': 'not actual any more',
  1196.         },
  1197.         {
  1198.             # Youtube Music Auto-generated description
  1199.             'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
  1200.             'info_dict': {
  1201.                 'id': 'MgNrAu2pzNs',
  1202.                 'ext': 'mp4',
  1203.                 'title': 'Voyeur Girl',
  1204.                 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
  1205.                 'upload_date': '20190312',
  1206.                 'uploader': 'Stephen - Topic',
  1207.                 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
  1208.                 'artist': 'Stephen',
  1209.                 'track': 'Voyeur Girl',
  1210.                 'album': 'it\'s too much love to know my dear',
  1211.                 'release_date': '20190313',
  1212.                 'release_year': 2019,
  1213.             },
  1214.             'params': {
  1215.                 'skip_download': True,
  1216.             },
  1217.         },
  1218.         {
  1219.             'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
  1220.             'only_matching': True,
  1221.         },
  1222.         {
  1223.             # invalid -> valid video id redirection
  1224.             'url': 'DJztXj2GPfl',
  1225.             'info_dict': {
  1226.                 'id': 'DJztXj2GPfk',
  1227.                 'ext': 'mp4',
  1228.                 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
  1229.                 'description': 'md5:bf577a41da97918e94fa9798d9228825',
  1230.                 'upload_date': '20090125',
  1231.                 'uploader': 'Prochorowka',
  1232.                 'uploader_id': 'Prochorowka',
  1233.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
  1234.                 'artist': 'Panjabi MC',
  1235.                 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
  1236.                 'album': 'Beware of the Boys (Mundian To Bach Ke)',
  1237.             },
  1238.             'params': {
  1239.                 'skip_download': True,
  1240.             },
  1241.             'skip': 'Video unavailable',
  1242.         },
  1243.         {
  1244.             # empty description results in an empty string
  1245.             'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
  1246.             'info_dict': {
  1247.                 'id': 'x41yOUIvK2k',
  1248.                 'ext': 'mp4',
  1249.                 'title': 'IMG 3456',
  1250.                 'description': '',
  1251.                 'upload_date': '20170613',
  1252.                 'uploader': 'ElevageOrVert',
  1253.                 'uploader_id': '@ElevageOrVert',
  1254.             },
  1255.             'params': {
  1256.                 'skip_download': True,
  1257.             },
  1258.         },
  1259.         {
  1260.             # with '};' inside yt initial data (see [1])
  1261.             # see [2] for an example with '};' inside ytInitialPlayerResponse
  1262.             # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
  1263.             # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
  1264.             'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
  1265.             'info_dict': {
  1266.                 'id': 'CHqg6qOn4no',
  1267.                 'ext': 'mp4',
  1268.                 'title': 'Part 77   Sort a list of simple types in c#',
  1269.                 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
  1270.                 'upload_date': '20130831',
  1271.                 'uploader': 'kudvenkat',
  1272.                 'uploader_id': '@Csharp-video-tutorialsBlogspot',
  1273.             },
  1274.             'params': {
  1275.                 'skip_download': True,
  1276.             },
  1277.         },
  1278.         {
  1279.             # another example of '};' in ytInitialData
  1280.             'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
  1281.             'only_matching': True,
  1282.         },
  1283.         {
  1284.             'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
  1285.             'only_matching': True,
  1286.         },
  1287.         {
  1288.             # https://github.com/ytdl-org/youtube-dl/pull/28094
  1289.             'url': 'OtqTfy26tG0',
  1290.             'info_dict': {
  1291.                 'id': 'OtqTfy26tG0',
  1292.                 'ext': 'mp4',
  1293.                 'title': 'Burn Out',
  1294.                 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
  1295.                 'upload_date': '20141120',
  1296.                 'uploader': 'The Cinematic Orchestra - Topic',
  1297.                 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
  1298.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
  1299.                 'artist': 'The Cinematic Orchestra',
  1300.                 'track': 'Burn Out',
  1301.                 'album': 'Every Day',
  1302.                 'release_data': None,
  1303.                 'release_year': None,
  1304.             },
  1305.             'params': {
  1306.                 'skip_download': True,
  1307.             },
  1308.         },
  1309.         {
  1310.             # controversial video, only works with bpctr when authenticated with cookies
  1311.             'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
  1312.             'only_matching': True,
  1313.         },
  1314.         {
  1315.             # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
  1316.             'url': 'cBvYw8_A0vQ',
  1317.             'info_dict': {
  1318.                 'id': 'cBvYw8_A0vQ',
  1319.                 'ext': 'mp4',
  1320.                 'title': '4K Ueno Okachimachi  Street  Scenes  上野御徒町歩き',
  1321.                 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
  1322.                 'upload_date': '20201120',
  1323.                 'uploader': 'Walk around Japan',
  1324.                 'uploader_id': '@walkaroundjapan7124',
  1325.                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@walkaroundjapan7124',
  1326.             },
  1327.             'params': {
  1328.                 'skip_download': True,
  1329.             },
  1330.         },
  1331.         {
  1332.             # YT 'Shorts'
  1333.             'url': 'https://youtube.com/shorts/4L2J27mJ3Dc',
  1334.             'info_dict': {
  1335.                 'id': '4L2J27mJ3Dc',
  1336.                 'ext': 'mp4',
  1337.                 'title': 'Midwest Squid Game #Shorts',
  1338.                 'description': 'md5:976512b8a29269b93bbd8a61edc45a6d',
  1339.                 'upload_date': '20211025',
  1340.                 'uploader': 'Charlie Berens',
  1341.                 'uploader_id': '@CharlieBerens',
  1342.             },
  1343.             'params': {
  1344.                 'skip_download': True,
  1345.             },
  1346.         },
  1347.     ]
  1348.     _formats = {
  1349.         '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
  1350.         '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
  1351.         '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
  1352.         '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
  1353.         '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
  1354.         '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
  1355.         '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
  1356.         '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
  1357.         # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
  1358.         '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
  1359.         '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
  1360.         '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
  1361.         '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
  1362.         '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
  1363.         '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
  1364.         '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
  1365.         '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
  1366.         '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
  1369.         # 3D videos
  1370.         '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
  1371.         '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
  1372.         '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
  1373.         '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
  1374.         '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
  1375.         '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
  1376.         '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
  1378.         # Apple HTTP Live Streaming
  1379.         '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
  1380.         '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
  1381.         '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
  1382.         '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
  1383.         '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
  1384.         '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
  1385.         '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
  1386.         '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
  1388.         # DASH mp4 video
  1389.         '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1390.         '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1391.         '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1392.         '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1393.         '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1394.         '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'},  # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
  1395.         '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1396.         '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1397.         '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1398.         '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
  1399.         '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
  1400.         '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
  1402.         # Dash mp4 audio
  1403.         '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
  1404.         '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
  1405.         '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
  1406.         '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
  1407.         '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
  1408.         '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
  1409.         '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
  1411.         # Dash webm
  1412.         '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
  1413.         '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
  1414.         '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
  1415.         '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
  1416.         '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
  1417.         '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
  1418.         '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
  1419.         '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1420.         '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1421.         '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1422.         '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1423.         '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1424.         '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1425.         '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1426.         '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1427.         # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
  1428.         '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1429.         '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
  1430.         '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
  1431.         '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
  1432.         '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
  1433.         '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
  1435.         # Dash webm audio
  1436.         '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
  1437.         '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
  1439.         # Dash webm audio with opus inside
  1440.         '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
  1441.         '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
  1442.         '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
  1444.         # RTMP (unnamed)
  1445.         '_rtmp': {'protocol': 'rtmp'},
  1447.         # av01 video only formats sometimes served with "unknown" codecs
  1448.         '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
  1449.         '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
  1450.         '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
  1451.         '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
  1452.     }
  1454.     @classmethod
  1455.     def suitable(cls, url):
  1456.         if parse_qs(url).get('list', [None])[0]:
  1457.             return False
  1458.         return super(YoutubeIE, cls).suitable(url)
  1460.     def __init__(self, *args, **kwargs):
  1461.         super(YoutubeIE, self).__init__(*args, **kwargs)
  1462.         self._code_cache = {}
  1463.         self._player_cache = {}
  1465.     def _signature_cache_id(self, example_sig):
  1466.         """ Return a string representation of a signature """
  1467.         return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
  1469.     @classmethod
  1470.     def _extract_player_info(cls, player_url):
  1471.         for player_re in cls._PLAYER_INFO_RE:
  1472.             id_m = re.search(player_re, player_url)
  1473.             if id_m:
  1474.                 break
  1475.         else:
  1476.             raise ExtractorError('Cannot identify player %r' % player_url)
  1477.         return id_m.group('id')
  1479.     def _get_player_code(self, video_id, player_url, player_id=None):
  1480.         if not player_id:
  1481.             player_id = self._extract_player_info(player_url)
  1483.         if player_id not in self._code_cache:
  1484.             self._code_cache[player_id] = self._download_webpage(
  1485.                 player_url, video_id,
  1486.                 note='Downloading player ' + player_id,
  1487.                 errnote='Download of %s failed' % player_url)
  1488.         return self._code_cache[player_id]
  1490.     def _extract_signature_function(self, video_id, player_url, example_sig):
  1491.         player_id = self._extract_player_info(player_url)
  1493.         # Read from filesystem cache
  1494.         func_id = 'js_%s_%s' % (
  1495.             player_id, self._signature_cache_id(example_sig))
  1496.         assert os.path.basename(func_id) == func_id
  1498.         cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
  1499.         if cache_spec is not None:
  1500.             return lambda s: ''.join(s[i] for i in cache_spec)
  1502.         code = self._get_player_code(video_id, player_url, player_id)
  1503.         res = self._parse_sig_js(code)
  1505.         test_string = ''.join(map(compat_chr, range(len(example_sig))))
  1506.         cache_res = res(test_string)
  1507.         cache_spec = [ord(c) for c in cache_res]
  1509.         self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
  1510.         return res
  1512.     def _print_sig_code(self, func, example_sig):
  1513.         def gen_sig_code(idxs):
  1514.             def _genslice(start, end, step):
  1515.                 starts = '' if start == 0 else str(start)
  1516.                 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
  1517.                 steps = '' if step == 1 else (':%d' % step)
  1518.                 return 's[%s%s%s]' % (starts, ends, steps)
  1520.             step = None
  1521.             # Quelch pyflakes warnings - start will be set when step is set
  1522.             start = '(Never used)'
  1523.             for i, prev in zip(idxs[1:], idxs[:-1]):
  1524.                 if step is not None:
  1525.                     if i - prev == step:
  1526.                         continue
  1527.                     yield _genslice(start, prev, step)
  1528.                     step = None
  1529.                     continue
  1530.                 if i - prev in [-1, 1]:
  1531.                     step = i - prev
  1532.                     start = prev
  1533.                     continue
  1534.                 else:
  1535.                     yield 's[%d]' % prev
  1536.             if step is None:
  1537.                 yield 's[%d]' % i
  1538.             else:
  1539.                 yield _genslice(start, i, step)
  1541.         test_string = ''.join(map(compat_chr, range(len(example_sig))))
  1542.         cache_res = func(test_string)
  1543.         cache_spec = [ord(c) for c in cache_res]
  1544.         expr_code = ' + '.join(gen_sig_code(cache_spec))
  1545.         signature_id_tuple = '(%s)' % (
  1546.             ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
  1547.         code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
  1548.                 '    return %s\n') % (signature_id_tuple, expr_code)
  1549.         self.to_screen('Extracted signature function:\n' + code)
  1551.     def _parse_sig_js(self, jscode):
  1552.         funcname = self._search_regex(
  1553.             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1554.              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1555.              r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
  1556.              r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
  1557.              r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{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}\(a,\d+\)',
  1558.              r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
  1559.              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
  1560.              # Obsolete patterns
  1561.              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1562.              r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
  1563.              r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1564.              r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1565.              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1566.              r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1567.              r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
  1568.              r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
  1569.             jscode, 'Initial JS player signature function name', group='sig')
  1571.         jsi = JSInterpreter(jscode)
  1572.         initial_function = jsi.extract_function(funcname)
  1573.         return lambda s: initial_function([s])
  1575.     def _decrypt_signature(self, s, video_id, player_url):
  1576.         """Turn the encrypted s field into a working signature"""
  1578.         if player_url is None:
  1579.             raise ExtractorError('Cannot decrypt signature without player_url')
  1581.         try:
  1582.             player_id = (player_url, self._signature_cache_id(s))
  1583.             if player_id not in self._player_cache:
  1584.                 func = self._extract_signature_function(
  1585.                     video_id, player_url, s
  1586.                 )
  1587.                 self._player_cache[player_id] = func
  1588.             func = self._player_cache[player_id]
  1589.             if self._downloader.params.get('youtube_print_sig_code'):
  1590.                 self._print_sig_code(func, s)
  1591.             return func(s)
  1592.         except Exception as e:
  1593.             tb = traceback.format_exc()
  1594.             raise ExtractorError(
  1595.                 'Signature extraction failed: ' + tb, cause=e)
  1597.     def _extract_player_url(self, webpage):
  1598.         player_url = self._search_regex(
  1599.             r'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
  1600.             webpage or '', 'player URL', fatal=False)
  1601.         if not player_url:
  1602.             return
  1603.         if player_url.startswith('//'):
  1604.             player_url = 'https:' + player_url
  1605.         elif not re.match(r'https?://', player_url):
  1606.             player_url = compat_urllib_parse.urljoin(
  1607.                 'https://www.youtube.com', player_url)
  1608.         return player_url
  1610.     # from yt-dlp
  1611.     # See also:
  1612.     # 1. https://github.com/ytdl-org/youtube-dl/issues/29326#issuecomment-894619419
  1613.     # 2. https://code.videolan.org/videolan/vlc/-/blob/4fb284e5af69aa9ac2100ccbdd3b88debec9987f/share/lua/playlist/youtube.lua#L116
  1614.     # 3. https://github.com/ytdl-org/youtube-dl/issues/30097#issuecomment-950157377
  1615.     def _extract_n_function_name(self, jscode):
  1616.         target = r'(?P<nfunc>[a-zA-Z_$][\w$]*)(?:\[(?P<idx>\d+)\])?'
  1617.         nfunc_and_idx = self._search_regex(
  1618.             r'\.get\("n"\)\)&&\(b=(%s)\([\w$]+\)' % (target, ),
  1619.             jscode, 'Initial JS player n function name')
  1620.         nfunc, idx = re.match(target, nfunc_and_idx).group('nfunc', 'idx')
  1621.         if not idx:
  1622.             return nfunc
  1623.         if int_or_none(idx) == 0:
  1624.             real_nfunc = self._search_regex(
  1625.                 r'var %s\s*=\s*\[([a-zA-Z_$][\w$]*)\];' % (re.escape(nfunc), ), jscode,
  1626.                 'Initial JS player n function alias ({nfunc}[{idx}])'.format(**locals()))
  1627.             if real_nfunc:
  1628.                 return real_nfunc
  1629.         return self._parse_json(self._search_regex(
  1630.             r'var %s\s*=\s*(\[.+?\]);' % (re.escape(nfunc), ), jscode,
  1631.             'Initial JS player n function name ({nfunc}[{idx}])'.format(**locals())), nfunc, transform_source=js_to_json)[int(idx)]
  1633.     def _extract_n_function(self, video_id, player_url):
  1634.         player_id = self._extract_player_info(player_url)
  1635.         func_code = self._downloader.cache.load('youtube-nsig', player_id)
  1637.         if func_code:
  1638.             jsi = JSInterpreter(func_code)
  1639.         else:
  1640.             jscode = self._get_player_code(video_id, player_url, player_id)
  1641.             funcname = self._extract_n_function_name(jscode)
  1642.             jsi = JSInterpreter(jscode)
  1643.             func_code = jsi.extract_function_code(funcname)
  1644.             self._downloader.cache.store('youtube-nsig', player_id, func_code)
  1646.         if self._downloader.params.get('youtube_print_sig_code'):
  1647.             self.to_screen('Extracted nsig function from {0}:\n{1}\n'.format(player_id, func_code[1]))
  1649.         return lambda s: jsi.extract_function_from_code(*func_code)([s])
  1651.     def _n_descramble(self, n_param, player_url, video_id):
  1652.         """Compute the response to YT's "n" parameter challenge,
  1653.            or None
  1655.         Args:
  1656.         n_param     -- challenge string that is the value of the
  1657.                        URL's "n" query parameter
  1658.         player_url  -- URL of YT player JS
  1659.         video_id
  1660.         """
  1662.         sig_id = ('nsig_value', n_param)
  1663.         if sig_id in self._player_cache:
  1664.             return self._player_cache[sig_id]
  1666.         try:
  1667.             player_id = ('nsig', player_url)
  1668.             if player_id not in self._player_cache:
  1669.                 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
  1670.             func = self._player_cache[player_id]
  1671.             ret = func(n_param)
  1672.             if ret.startswith('enhanced_except_'):
  1673.                 raise ExtractorError('Unhandled exception in decode')
  1674.             self._player_cache[sig_id] = ret
  1675.             if self._downloader.params.get('verbose', False):
  1676.                 self._downloader.to_screen('[debug] [%s] %s' % (self.IE_NAME, 'Decrypted nsig {0} => {1}'.format(n_param, self._player_cache[sig_id])))
  1677.             return self._player_cache[sig_id]
  1678.         except Exception as e:
  1679.             self._downloader.report_warning(
  1680.                 '[%s] %s (%s %s)' % (
  1681.                     self.IE_NAME,
  1682.                     'Unable to decode n-parameter: download likely to be throttled',
  1683.                     error_to_compat_str(e),
  1684.                     traceback.format_exc()))
  1686.     def _unthrottle_format_urls(self, video_id, player_url, formats):
  1687.         for fmt in formats:
  1688.             parsed_fmt_url = compat_urllib_parse.urlparse(fmt['url'])
  1689.             n_param = compat_parse_qs(parsed_fmt_url.query).get('n')
  1690.             if not n_param:
  1691.                 continue
  1692.             n_param = n_param[-1]
  1693.             n_response = self._n_descramble(n_param, player_url, video_id)
  1694.             if n_response is None:
  1695.                 # give up if descrambling failed
  1696.                 break
  1697.             for fmt_dct in traverse_obj(fmt, (None, (None, ('fragments', Ellipsis))), expected_type=dict):
  1698.                 fmt_dct['url'] = update_url(
  1699.                     fmt_dct['url'], query_update={'n': [n_response]})
  1701.     # from yt-dlp, with tweaks
  1702.     def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
  1703.         """
  1704.         Extract signatureTimestamp (sts)
  1705.         Required to tell API what sig/player version is in use.
  1706.         """
  1707.         sts = int_or_none(ytcfg.get('STS')) if isinstance(ytcfg, dict) else None
  1708.         if not sts:
  1709.             # Attempt to extract from player
  1710.             if player_url is None:
  1711.                 error_msg = 'Cannot extract signature timestamp without player_url.'
  1712.                 if fatal:
  1713.                     raise ExtractorError(error_msg)
  1714.                 self._downloader.report_warning(error_msg)
  1715.                 return
  1716.             code = self._get_player_code(video_id, player_url)
  1717.             sts = int_or_none(self._search_regex(
  1718.                 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code or '',
  1719.                 'JS player signature timestamp', group='sts', fatal=fatal))
  1720.         return sts
  1722.     def _mark_watched(self, video_id, player_response):
  1723.         playback_url = url_or_none(try_get(
  1724.             player_response,
  1725.             lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']))
  1726.         if not playback_url:
  1727.             return
  1729.         # cpn generation algorithm is reverse engineered from base.js.
  1730.         # In fact it works even with dummy cpn.
  1731.         CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
  1732.         cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
  1734.         playback_url = update_url(
  1735.             playback_url, query_update={
  1736.                 'ver': ['2'],
  1737.                 'cpn': [cpn],
  1738.             })
  1740.         self._download_webpage(
  1741.             playback_url, video_id, 'Marking watched',
  1742.             'Unable to mark watched', fatal=False)
  1744.     @staticmethod
  1745.     def _extract_urls(webpage):
  1746.         # Embedded YouTube player
  1747.         entries = [
  1748.             unescapeHTML(mobj.group('url'))
  1749.             for mobj in re.finditer(r'''(?x)
  1750.             (?:
  1751.                 <iframe[^>]+?src=|
  1752.                 data-video-url=|
  1753.                 <embed[^>]+?src=|
  1754.                 embedSWF\(?:\s*|
  1755.                 <object[^>]+data=|
  1756.                 new\s+SWFObject\(
  1757.             )
  1758.             (["\'])
  1759.                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1760.                 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
  1761.             \1''', webpage)]
  1763.         # lazyYT YouTube embed
  1764.         entries.extend(list(map(
  1765.             unescapeHTML,
  1766.             re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
  1768.         # Wordpress "YouTube Video Importer" plugin
  1769.         matches = re.findall(r'''(?x)<div[^>]+
  1770.             class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
  1771.             data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
  1772.         entries.extend(m[-1] for m in matches)
  1774.         return entries
  1776.     @staticmethod
  1777.     def _extract_url(webpage):
  1778.         urls = YoutubeIE._extract_urls(webpage)
  1779.         return urls[0] if urls else None
  1781.     @classmethod
  1782.     def extract_id(cls, url):
  1783.         mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
  1784.         if mobj is None:
  1785.             raise ExtractorError('Invalid URL: %s' % url)
  1786.         video_id = mobj.group(2)
  1787.         return video_id
  1789.     def _extract_chapters_from_json(self, data, video_id, duration):
  1790.         chapters_list = try_get(
  1791.             data,
  1792.             lambda x: x['playerOverlays']
  1793.                        ['playerOverlayRenderer']
  1794.                        ['decoratedPlayerBarRenderer']
  1795.                        ['decoratedPlayerBarRenderer']
  1796.                        ['playerBar']
  1797.                        ['chapteredPlayerBarRenderer']
  1798.                        ['chapters'],
  1799.             list)
  1800.         if not chapters_list:
  1801.             return
  1803.         def chapter_time(chapter):
  1804.             return float_or_none(
  1805.                 try_get(
  1806.                     chapter,
  1807.                     lambda x: x['chapterRenderer']['timeRangeStartMillis'],
  1808.                     int),
  1809.                 scale=1000)
  1810.         chapters = []
  1811.         for next_num, chapter in enumerate(chapters_list, start=1):
  1812.             start_time = chapter_time(chapter)
  1813.             if start_time is None:
  1814.                 continue
  1815.             end_time = (chapter_time(chapters_list[next_num])
  1816.                         if next_num < len(chapters_list) else duration)
  1817.             if end_time is None:
  1818.                 continue
  1819.             title = try_get(
  1820.                 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
  1821.                 compat_str)
  1822.             chapters.append({
  1823.                 'start_time': start_time,
  1824.                 'end_time': end_time,
  1825.                 'title': title,
  1826.             })
  1827.         return chapters
  1829.     def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
  1830.         return self._parse_json(self._search_regex(
  1831.             (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
  1832.              regex), webpage, name, default='{}'), video_id, fatal=False)
  1834.     def _real_extract(self, url):
  1835.         url, smuggled_data = unsmuggle_url(url, {})
  1836.         video_id = self._match_id(url)
  1837.         base_url = self.http_scheme() + '//www.youtube.com/'
  1838.         webpage_url = base_url + 'watch?v=' + video_id
  1839.         webpage = self._download_webpage(
  1840.             webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
  1842.         player_response = None
  1843.         player_url = None
  1844.         if webpage:
  1845.             player_response = self._extract_yt_initial_variable(
  1846.                 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
  1847.                 video_id, 'initial player response')
  1848.         if not player_response:
  1849.             player_response = self._call_api(
  1850.                 'player', {'videoId': video_id}, video_id)
  1852.         def is_agegated(playability):
  1853.             if not isinstance(playability, dict):
  1854.                 return
  1856.             if playability.get('desktopLegacyAgeGateReason'):
  1857.                 return True
  1859.             reasons = filter(None, (playability.get(r) for r in ('status', 'reason')))
  1860.             AGE_GATE_REASONS = (
  1861.                 'confirm your age', 'age-restricted', 'inappropriate',  # reason
  1862.                 'age_verification_required', 'age_check_required',  # status
  1863.             )
  1864.             return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
  1866.         def get_playability_status(response):
  1867.             return try_get(response, lambda x: x['playabilityStatus'], dict) or {}
  1869.         playability_status = get_playability_status(player_response)
  1870.         if (is_agegated(playability_status)
  1871.                 and int_or_none(self._downloader.params.get('age_limit'), default=18) >= 18):
  1873.             self.report_age_confirmation()
  1875.             # Thanks: https://github.com/yt-dlp/yt-dlp/pull/3233
  1876.             pb_context = {'html5Preference': 'HTML5_PREF_WANTS'}
  1878.             # Use signatureTimestamp if available
  1879.             # Thanks https://github.com/ytdl-org/youtube-dl/issues/31034#issuecomment-1160718026
  1880.             player_url = self._extract_player_url(webpage)
  1881.             ytcfg = self._extract_ytcfg(video_id, webpage)
  1882.             sts = self._extract_signature_timestamp(video_id, player_url, ytcfg)
  1883.             if sts:
  1884.                 pb_context['signatureTimestamp'] = sts
  1886.             query = {
  1887.                 'playbackContext': {'contentPlaybackContext': pb_context},
  1888.                 'contentCheckOk': True,
  1889.                 'racyCheckOk': True,
  1890.                 'context': {
  1891.                     'client': {'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'clientVersion': '2.0', 'hl': 'en', 'clientScreen': 'EMBED'},
  1892.                     'thirdParty': {'embedUrl': 'https://google.com'},
  1893.                 },
  1894.                 'videoId': video_id,
  1895.             }
  1896.             headers = {
  1897.                 'X-YouTube-Client-Name': '85',
  1898.                 'X-YouTube-Client-Version': '2.0',
  1899.                 'Origin': 'https://www.youtube.com'
  1900.             }
  1902.             video_info = self._call_api('player', query, video_id, fatal=False, headers=headers)
  1903.             age_gate_status = get_playability_status(video_info)
  1904.             if age_gate_status.get('status') == 'OK':
  1905.                 player_response = video_info
  1906.                 playability_status = age_gate_status
  1908.         trailer_video_id = try_get(
  1909.             playability_status,
  1910.             lambda x: x['errorScreen']['playerLegacyDesktopYpcTrailerRenderer']['trailerVideoId'],
  1911.             compat_str)
  1912.         if trailer_video_id:
  1913.             return self.url_result(
  1914.                 trailer_video_id, self.ie_key(), trailer_video_id)
  1916.         def get_text(x):
  1917.             if not x:
  1918.                 return
  1919.             text = x.get('simpleText')
  1920.             if text and isinstance(text, compat_str):
  1921.                 return text
  1922.             runs = x.get('runs')
  1923.             if not isinstance(runs, list):
  1924.                 return
  1925.             return ''.join([r['text'] for r in runs if isinstance(r.get('text'), compat_str)])
  1927.         search_meta = (
  1928.             lambda x: self._html_search_meta(x, webpage, default=None)) \
  1929.             if webpage else lambda x: None
  1931.         video_details = player_response.get('videoDetails') or {}
  1932.         microformat = try_get(
  1933.             player_response,
  1934.             lambda x: x['microformat']['playerMicroformatRenderer'],
  1935.             dict) or {}
  1936.         video_title = video_details.get('title') \
  1937.             or get_text(microformat.get('title')) \
  1938.             or search_meta(['og:title', 'twitter:title', 'title'])
  1939.         video_description = video_details.get('shortDescription')
  1941.         if not smuggled_data.get('force_singlefeed', False):
  1942.             if not self._downloader.params.get('noplaylist'):
  1943.                 multifeed_metadata_list = try_get(
  1944.                     player_response,
  1945.                     lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
  1946.                     compat_str)
  1947.                 if multifeed_metadata_list:
  1948.                     entries = []
  1949.                     feed_ids = []
  1950.                     for feed in multifeed_metadata_list.split(','):
  1951.                         # Unquote should take place before split on comma (,) since textual
  1952.                         # fields may contain comma as well (see
  1953.                         # https://github.com/ytdl-org/youtube-dl/issues/8536)
  1954.                         feed_data = compat_parse_qs(
  1955.                             compat_urllib_parse_unquote_plus(feed))
  1957.                         def feed_entry(name):
  1958.                             return try_get(
  1959.                                 feed_data, lambda x: x[name][0], compat_str)
  1961.                         feed_id = feed_entry('id')
  1962.                         if not feed_id:
  1963.                             continue
  1964.                         feed_title = feed_entry('title')
  1965.                         title = video_title
  1966.                         if feed_title:
  1967.                             title += ' (%s)' % feed_title
  1968.                         entries.append({
  1969.                             '_type': 'url_transparent',
  1970.                             'ie_key': 'Youtube',
  1971.                             'url': smuggle_url(
  1972.                                 base_url + 'watch?v=' + feed_data['id'][0],
  1973.                                 {'force_singlefeed': True}),
  1974.                             'title': title,
  1975.                         })
  1976.                         feed_ids.append(feed_id)
  1977.                     self.to_screen(
  1978.                         'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
  1979.                         % (', '.join(feed_ids), video_id))
  1980.                     return self.playlist_result(
  1981.                         entries, video_id, video_title, video_description)
  1982.             else:
  1983.                 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
  1985.         formats = []
  1986.         itags = []
  1987.         itag_qualities = {}
  1988.         q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'])
  1989.         streaming_data = player_response.get('streamingData') or {}
  1990.         streaming_formats = streaming_data.get('formats') or []
  1991.         streaming_formats.extend(streaming_data.get('adaptiveFormats') or [])
  1992.         for fmt in streaming_formats:
  1993.             if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
  1994.                 continue
  1996.             itag = str_or_none(fmt.get('itag'))
  1997.             quality = fmt.get('quality')
  1998.             if itag and quality:
  1999.                 itag_qualities[itag] = quality
  2000.             # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
  2001.             # (adding `&sq=0` to the URL) and parsing emsg box to determine the
  2002.             # number of fragment that would subsequently requested with (`&sq=N`)
  2003.             if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
  2004.                 continue
  2006.             fmt_url = fmt.get('url')
  2007.             if not fmt_url:
  2008.                 sc = compat_parse_qs(fmt.get('signatureCipher'))
  2009.                 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
  2010.                 encrypted_sig = try_get(sc, lambda x: x['s'][0])
  2011.                 if not (sc and fmt_url and encrypted_sig):
  2012.                     continue
  2013.                 if not player_url:
  2014.                     player_url = self._extract_player_url(webpage)
  2015.                 if not player_url:
  2016.                     continue
  2017.                 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
  2018.                 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
  2019.                 fmt_url += '&' + sp + '=' + signature
  2021.             if itag:
  2022.                 itags.append(itag)
  2023.             tbr = float_or_none(
  2024.                 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
  2025.             dct = {
  2026.                 'asr': int_or_none(fmt.get('audioSampleRate')),
  2027.                 'filesize': int_or_none(fmt.get('contentLength')),
  2028.                 'format_id': itag,
  2029.                 'format_note': fmt.get('qualityLabel') or quality,
  2030.                 'fps': int_or_none(fmt.get('fps')),
  2031.                 'height': int_or_none(fmt.get('height')),
  2032.                 'quality': q(quality),
  2033.                 'tbr': tbr,
  2034.                 'url': fmt_url,
  2035.                 'width': fmt.get('width'),
  2036.             }
  2037.             mimetype = fmt.get('mimeType')
  2038.             if mimetype:
  2039.                 mobj = re.match(
  2040.                     r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', mimetype)
  2041.                 if mobj:
  2042.                     dct['ext'] = mimetype2ext(mobj.group(1))
  2043.                     dct.update(parse_codecs(mobj.group(2)))
  2044.             no_audio = dct.get('acodec') == 'none'
  2045.             no_video = dct.get('vcodec') == 'none'
  2046.             if no_audio:
  2047.                 dct['vbr'] = tbr
  2048.             if no_video:
  2049.                 dct['abr'] = tbr
  2050.             if no_audio or no_video:
  2051.                 CHUNK_SIZE = 10 << 20
  2052.                 # avoid Youtube throttling
  2053.                 dct.update({
  2054.                     'protocol': 'http_dash_segments',
  2055.                     'fragments': [{
  2056.                         'url': update_url_query(dct['url'], {
  2057.                             'range': '{0}-{1}'.format(range_start, min(range_start + CHUNK_SIZE - 1, dct['filesize']))
  2058.                         })
  2059.                     } for range_start in range(0, dct['filesize'], CHUNK_SIZE)]
  2060.                 } if dct['filesize'] else {
  2061.                     'downloader_options': {'http_chunk_size': CHUNK_SIZE}  # No longer useful?
  2062.                 })
  2064.                 if dct.get('ext'):
  2065.                     dct['container'] = dct['ext'] + '_dash'
  2066.             formats.append(dct)
  2068.         hls_manifest_url = streaming_data.get('hlsManifestUrl')
  2069.         if hls_manifest_url:
  2070.             for f in self._extract_m3u8_formats(
  2071.                     hls_manifest_url, video_id, 'mp4', fatal=False):
  2072.                 itag = self._search_regex(
  2073.                     r'/itag/(\d+)', f['url'], 'itag', default=None)
  2074.                 if itag:
  2075.                     f['format_id'] = itag
  2076.                 formats.append(f)
  2078.         if self._downloader.params.get('youtube_include_dash_manifest', True):
  2079.             dash_manifest_url = streaming_data.get('dashManifestUrl')
  2080.             if dash_manifest_url:
  2081.                 for f in self._extract_mpd_formats(
  2082.                         dash_manifest_url, video_id, fatal=False):
  2083.                     itag = f['format_id']
  2084.                     if itag in itags:
  2085.                         continue
  2086.                     if itag in itag_qualities:
  2087.                         f['quality'] = q(itag_qualities[itag])
  2088.                     filesize = int_or_none(self._search_regex(
  2089.                         r'/clen/(\d+)', f.get('fragment_base_url')
  2090.                         or f['url'], 'file size', default=None))
  2091.                     if filesize:
  2092.                         f['filesize'] = filesize
  2093.                     formats.append(f)
  2095.         if not formats:
  2096.             if streaming_data.get('licenseInfos'):
  2097.                 raise ExtractorError(
  2098.                     'This video is DRM protected.', expected=True)
  2099.             pemr = try_get(
  2100.                 playability_status,
  2101.                 lambda x: x['errorScreen']['playerErrorMessageRenderer'],
  2102.                 dict) or {}
  2103.             reason = get_text(pemr.get('reason')) or playability_status.get('reason')
  2104.             subreason = pemr.get('subreason')
  2105.             if subreason:
  2106.                 subreason = clean_html(get_text(subreason))
  2107.                 if subreason == 'The uploader has not made this video available in your country.':
  2108.                     countries = microformat.get('availableCountries')
  2109.                     if not countries:
  2110.                         regions_allowed = search_meta('regionsAllowed')
  2111.                         countries = regions_allowed.split(',') if regions_allowed else None
  2112.                     self.raise_geo_restricted(
  2113.                         subreason, countries)
  2114.                 reason += '\n' + subreason
  2115.             if reason:
  2116.                 raise ExtractorError(reason, expected=True)
  2118.         self._sort_formats(formats)
  2120.         keywords = video_details.get('keywords') or []
  2121.         if not keywords and webpage:
  2122.             keywords = [
  2123.                 unescapeHTML(m.group('content'))
  2124.                 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
  2125.         for keyword in keywords:
  2126.             if keyword.startswith('yt:stretch='):
  2127.                 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
  2128.                 if mobj:
  2129.                     # NB: float is intentional for forcing float division
  2130.                     w, h = (float(v) for v in mobj.groups())
  2131.                     if w > 0 and h > 0:
  2132.                         ratio = w / h
  2133.                         for f in formats:
  2134.                             if f.get('vcodec') != 'none':
  2135.                                 f['stretched_ratio'] = ratio
  2136.                         break
  2138.         thumbnails = []
  2139.         for container in (video_details, microformat):
  2140.             for thumbnail in try_get(
  2141.                     container,
  2142.                     lambda x: x['thumbnail']['thumbnails'], list) or []:
  2143.                 thumbnail_url = url_or_none(thumbnail.get('url'))
  2144.                 if not thumbnail_url:
  2145.                     continue
  2146.                 thumbnails.append({
  2147.                     'height': int_or_none(thumbnail.get('height')),
  2148.                     'url': update_url(thumbnail_url, query=None, fragment=None),
  2149.                     'width': int_or_none(thumbnail.get('width')),
  2150.                 })
  2151.             if thumbnails:
  2152.                 break
  2153.         else:
  2154.             thumbnail = search_meta(['og:image', 'twitter:image'])
  2155.             if thumbnail:
  2156.                 thumbnails = [{'url': thumbnail}]
  2158.         category = microformat.get('category') or search_meta('genre')
  2159.         channel_id = self._extract_channel_id(
  2160.             webpage, videodetails=video_details, metadata=microformat)
  2161.         duration = int_or_none(
  2162.             video_details.get('lengthSeconds')
  2163.             or microformat.get('lengthSeconds')) \
  2164.             or parse_duration(search_meta('duration'))
  2165.         is_live = video_details.get('isLive')
  2167.         owner_profile_url = self._yt_urljoin(self._extract_author_var(
  2168.             webpage, 'url', videodetails=video_details, metadata=microformat))
  2170.         uploader = self._extract_author_var(
  2171.             webpage, 'name', videodetails=video_details, metadata=microformat)
  2173.         if not player_url:
  2174.             player_url = self._extract_player_url(webpage)
  2175.         self._unthrottle_format_urls(video_id, player_url, formats)
  2177.         info = {
  2178.             'id': video_id,
  2179.             'title': self._live_title(video_title) if is_live else video_title,
  2180.             'formats': formats,
  2181.             'thumbnails': thumbnails,
  2182.             'description': video_description,
  2183.             'upload_date': unified_strdate(
  2184.                 microformat.get('uploadDate')
  2185.                 or search_meta('uploadDate')),
  2186.             'uploader': uploader,
  2187.             'channel_id': channel_id,
  2188.             'duration': duration,
  2189.             'view_count': int_or_none(
  2190.                 video_details.get('viewCount')
  2191.                 or microformat.get('viewCount')
  2192.                 or search_meta('interactionCount')),
  2193.             'average_rating': float_or_none(video_details.get('averageRating')),
  2194.             'age_limit': 18 if (
  2195.                 microformat.get('isFamilySafe') is False
  2196.                 or search_meta('isFamilyFriendly') == 'false'
  2197.                 or search_meta('og:restrictions:age') == '18+') else 0,
  2198.             'webpage_url': webpage_url,
  2199.             'categories': [category] if category else None,
  2200.             'tags': keywords,
  2201.             'is_live': is_live,
  2202.         }
  2204.         pctr = try_get(
  2205.             player_response,
  2206.             lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict)
  2207.         if pctr:
  2208.             def process_language(container, base_url, lang_code, query):
  2209.                 lang_subs = []
  2210.                 for fmt in self._SUBTITLE_FORMATS:
  2211.                     query.update({
  2212.                         'fmt': fmt,
  2213.                     })
  2214.                     lang_subs.append({
  2215.                         'ext': fmt,
  2216.                         'url': update_url_query(base_url, query),
  2217.                     })
  2218.                 container[lang_code] = lang_subs
  2220.             subtitles = {}
  2221.             for caption_track in (pctr.get('captionTracks') or []):
  2222.                 base_url = caption_track.get('baseUrl')
  2223.                 if not base_url:
  2224.                     continue
  2225.                 if caption_track.get('kind') != 'asr':
  2226.                     lang_code = caption_track.get('languageCode')
  2227.                     if not lang_code:
  2228.                         continue
  2229.                     process_language(
  2230.                         subtitles, base_url, lang_code, {})
  2231.                     continue
  2232.                 automatic_captions = {}
  2233.                 for translation_language in (pctr.get('translationLanguages') or []):
  2234.                     translation_language_code = translation_language.get('languageCode')
  2235.                     if not translation_language_code:
  2236.                         continue
  2237.                     process_language(
  2238.                         automatic_captions, base_url, translation_language_code,
  2239.                         {'tlang': translation_language_code})
  2240.                 info['automatic_captions'] = automatic_captions
  2241.             info['subtitles'] = subtitles
  2243.         parsed_url = compat_urllib_parse_urlparse(url)
  2244.         for component in [parsed_url.fragment, parsed_url.query]:
  2245.             query = compat_parse_qs(component)
  2246.             for k, v in query.items():
  2247.                 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
  2248.                     d_k += '_time'
  2249.                     if d_k not in info and k in s_ks:
  2250.                         info[d_k] = parse_duration(query[k][0])
  2252.         if video_description:
  2253.             # Youtube Music Auto-generated description
  2254.             mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
  2255.             if mobj:
  2256.                 release_year = mobj.group('release_year')
  2257.                 release_date = mobj.group('release_date')
  2258.                 if release_date:
  2259.                     release_date = release_date.replace('-', '')
  2260.                     if not release_year:
  2261.                         release_year = release_date[:4]
  2262.                 info.update({
  2263.                     'album': mobj.group('album'.strip()),
  2264.                     'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
  2265.                     'track': mobj.group('track').strip(),
  2266.                     'release_date': release_date,
  2267.                     'release_year': int_or_none(release_year),
  2268.                 })
  2270.         initial_data = None
  2271.         if webpage:
  2272.             initial_data = self._extract_yt_initial_variable(
  2273.                 webpage, self._YT_INITIAL_DATA_RE, video_id,
  2274.                 'yt initial data')
  2275.         if not initial_data:
  2276.             initial_data = self._call_api(
  2277.                 'next', {'videoId': video_id}, video_id, fatal=False)
  2279.         if initial_data:
  2280.             chapters = self._extract_chapters_from_json(
  2281.                 initial_data, video_id, duration)
  2282.             if not chapters:
  2283.                 for engagment_pannel in (initial_data.get('engagementPanels') or []):
  2284.                     contents = try_get(
  2285.                         engagment_pannel, lambda x: x['engagementPanelSectionListRenderer']['content']['macroMarkersListRenderer']['contents'],
  2286.                         list)
  2287.                     if not contents:
  2288.                         continue
  2290.                     def chapter_time(mmlir):
  2291.                         return parse_duration(
  2292.                             get_text(mmlir.get('timeDescription')))
  2294.                     chapters = []
  2295.                     for next_num, content in enumerate(contents, start=1):
  2296.                         mmlir = content.get('macroMarkersListItemRenderer') or {}
  2297.                         start_time = chapter_time(mmlir)
  2298.                         end_time = chapter_time(try_get(
  2299.                             contents, lambda x: x[next_num]['macroMarkersListItemRenderer'])) \
  2300.                             if next_num < len(contents) else duration
  2301.                         if start_time is None or end_time is None:
  2302.                             continue
  2303.                         chapters.append({
  2304.                             'start_time': start_time,
  2305.                             'end_time': end_time,
  2306.                             'title': get_text(mmlir.get('title')),
  2307.                         })
  2308.                     if chapters:
  2309.                         break
  2310.             if chapters:
  2311.                 info['chapters'] = chapters
  2313.             contents = try_get(
  2314.                 initial_data,
  2315.                 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
  2316.                 list) or []
  2317.             if not info['channel_id']:
  2318.                 channel_id = self._extract_channel_id('', renderers=contents)
  2319.             if not info['uploader']:
  2320.                 info['uploader'] = self._extract_author_var('', 'name', renderers=contents)
  2321.             if not owner_profile_url:
  2322.                 owner_profile_url = self._yt_urljoin(self._extract_author_var('', 'url', renderers=contents))
  2324.             for content in contents:
  2325.                 vpir = content.get('videoPrimaryInfoRenderer')
  2326.                 if vpir:
  2327.                     stl = vpir.get('superTitleLink')
  2328.                     if stl:
  2329.                         stl = get_text(stl)
  2330.                         if try_get(
  2331.                                 vpir,
  2332.                                 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
  2333.                             info['location'] = stl
  2334.                         else:
  2335.                             # •? doesn't match, but [•]? does; \xa0 = non-breaking space
  2336.                             mobj = re.search(r'([^\xa0\s].*?)[\xa0\s]*S(\d+)[\xa0\s]*[•]?[\xa0\s]*E(\d+)', stl)
  2337.                             if mobj:
  2338.                                 info.update({
  2339.                                     'series': mobj.group(1),
  2340.                                     'season_number': int(mobj.group(2)),
  2341.                                     'episode_number': int(mobj.group(3)),
  2342.                                 })
  2343.                     for tlb in (try_get(
  2344.                             vpir,
  2345.                             lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
  2346.                             list) or []):
  2347.                         tbr = traverse_obj(tlb, ('segmentedLikeDislikeButtonRenderer', 'likeButton', 'toggleButtonRenderer'), 'toggleButtonRenderer') or {}
  2348.                         for getter, regex in [(
  2349.                                 lambda x: x['defaultText']['accessibility']['accessibilityData'],
  2350.                                 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
  2351.                                     lambda x: x['accessibility'],
  2352.                                     lambda x: x['accessibilityData']['accessibilityData'],
  2353.                                 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
  2354.                             label = (try_get(tbr, getter, dict) or {}).get('label')
  2355.                             if label:
  2356.                                 mobj = re.match(regex, label)
  2357.                                 if mobj:
  2358.                                     info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
  2359.                                     break
  2360.                     sbr_tooltip = try_get(
  2361.                         vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
  2362.                     if sbr_tooltip:
  2363.                         # however dislike_count was hidden by YT, as if there could ever be dislikable content on YT
  2364.                         like_count, dislike_count = sbr_tooltip.split(' / ')
  2365.                         info.update({
  2366.                             'like_count': str_to_int(like_count),
  2367.                             'dislike_count': str_to_int(dislike_count),
  2368.                         })
  2369.                 vsir = content.get('videoSecondaryInfoRenderer')
  2370.                 if vsir:
  2371.                     rows = try_get(
  2372.                         vsir,
  2373.                         lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
  2374.                         list) or []
  2375.                     multiple_songs = False
  2376.                     for row in rows:
  2377.                         if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
  2378.                             multiple_songs = True
  2379.                             break
  2380.                     for row in rows:
  2381.                         mrr = row.get('metadataRowRenderer') or {}
  2382.                         mrr_title = mrr.get('title')
  2383.                         if not mrr_title:
  2384.                             continue
  2385.                         mrr_title = get_text(mrr['title'])
  2386.                         mrr_contents_text = get_text(mrr['contents'][0])
  2387.                         if mrr_title == 'License':
  2388.                             info['license'] = mrr_contents_text
  2389.                         elif not multiple_songs:
  2390.                             if mrr_title == 'Album':
  2391.                                 info['album'] = mrr_contents_text
  2392.                             elif mrr_title == 'Artist':
  2393.                                 info['artist'] = mrr_contents_text
  2394.                             elif mrr_title == 'Song':
  2395.                                 info['track'] = mrr_contents_text
  2397.             # this is not extraction but spelunking!
  2398.             carousel_lockups = traverse_obj(
  2399.                 initial_data,
  2400.                 ('engagementPanels', Ellipsis, 'engagementPanelSectionListRenderer',
  2401.                  'content', 'structuredDescriptionContentRenderer', 'items', Ellipsis,
  2402.                  'videoDescriptionMusicSectionRenderer', 'carouselLockups', Ellipsis),
  2403.                 expected_type=dict) or []
  2404.             # try to reproduce logic from metadataRowContainerRenderer above (if it still is)
  2405.             fields = (('ALBUM', 'album'), ('ARTIST', 'artist'), ('SONG', 'track'), ('LICENSES', 'license'))
  2406.             # multiple_songs ?
  2407.             if len(carousel_lockups) > 1:
  2408.                 fields = fields[-1:]
  2409.             for info_row in traverse_obj(
  2410.                     carousel_lockups,
  2411.                     (0, 'carouselLockupRenderer', 'infoRows', Ellipsis, 'infoRowRenderer'),
  2412.                     expected_type=dict):
  2413.                 row_title = traverse_obj(info_row, ('title', 'simpleText'))
  2414.                 row_text = traverse_obj(info_row, 'defaultMetadata', 'expandedMetadata', expected_type=get_text)
  2415.                 if not row_text:
  2416.                     continue
  2417.                 for name, field in fields:
  2418.                     if name == row_title and not info.get(field):
  2419.                         info[field] = row_text
  2421.         for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
  2422.             v = info.get(s_k)
  2423.             if v:
  2424.                 info[d_k] = v
  2426.         self.mark_watched(video_id, player_response)
  2428.         return merge_dicts(
  2429.             info, {
  2430.                 'uploader_id': self._extract_uploader_id(owner_profile_url),
  2431.                 'uploader_url': owner_profile_url,
  2432.                 'channel_id': channel_id,
  2433.                 'channel_url': channel_id and self._yt_urljoin('/channel/' + channel_id),
  2434.                 'channel': info['uploader'],
  2435.             })
  2438. class YoutubeTabIE(YoutubeBaseInfoExtractor):
  2439.     IE_DESC = 'YouTube.com tab'
  2440.     _VALID_URL = r'''(?x)
  2441.                     https?://
  2442.                         (?:\w+\.)?
  2443.                         (?:
  2444.                             youtube(?:kids)?\.com|
  2445.                             invidio\.us
  2446.                         )/
  2447.                         (?:
  2448.                             (?:channel|c|user|feed|hashtag)/|
  2449.                             (?:playlist|watch)\?.*?\blist=|
  2450.                             (?!(?:watch|embed|v|e|results)\b)
  2451.                         )
  2452.                         (?P<id>[^/?\#&]+)
  2453.                     '''
  2454.     IE_NAME = 'youtube:tab'
  2456.     _TESTS = [{
  2457.         # Shorts
  2458.         'url': 'https://www.youtube.com/@SuperCooperShorts/shorts',
  2459.         'playlist_mincount': 5,
  2460.         'info_dict': {
  2461.             'description': 'Short clips from Super Cooper Sundays!',
  2462.             'id': 'UCKMA8kHZ8bPYpnMNaUSxfEQ',
  2463.             'title': 'Super Cooper Shorts - Shorts',
  2464.             'uploader': 'Super Cooper Shorts',
  2465.             'uploader_id': '@SuperCooperShorts',
  2466.         }
  2467.     }, {
  2468.         # Channel that does not have a Shorts tab. Test should just download videos on Home tab instead
  2469.         'url': 'https://www.youtube.com/@emergencyawesome/shorts',
  2470.         'info_dict': {
  2471.             'description': 'md5:592c080c06fef4de3c902c4a8eecd850',
  2472.             'id': 'UCDiFRMQWpcp8_KD4vwIVicw',
  2473.             'title': 'Emergency Awesome - Home',
  2474.         },
  2475.         'playlist_mincount': 5,
  2476.         'skip': 'new test page needed to replace `Emergency Awesome - Shorts`',
  2477.     }, {
  2478.         # playlists, multipage
  2479.         'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
  2480.         'playlist_mincount': 94,
  2481.         'info_dict': {
  2482.             'id': 'UCqj7Cz7revf5maW9g5pgNcg',
  2483.             'title': 'Igor Kleiner - Playlists',
  2484.             'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
  2485.             'uploader': 'Igor Kleiner',
  2486.             'uploader_id': '@IgorDataScience',
  2487.         },
  2488.     }, {
  2489.         # playlists, multipage, different order
  2490.         'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
  2491.         'playlist_mincount': 94,
  2492.         'info_dict': {
  2493.             'id': 'UCqj7Cz7revf5maW9g5pgNcg',
  2494.             'title': 'Igor Kleiner - Playlists',
  2495.             'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
  2496.             'uploader': 'Igor Kleiner',
  2497.             'uploader_id': '@IgorDataScience',
  2498.         },
  2499.     }, {
  2500.         # playlists, series
  2501.         'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
  2502.         'playlist_mincount': 5,
  2503.         'info_dict': {
  2504.             'id': 'UCYO_jab_esuFRV4b17AJtAw',
  2505.             'title': '3Blue1Brown - Playlists',
  2506.             'description': 'md5:e1384e8a133307dd10edee76e875d62f',
  2507.             'uploader': '3Blue1Brown',
  2508.             'uploader_id': '@3blue1brown',
  2509.         },
  2510.     }, {
  2511.         # playlists, singlepage
  2512.         'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
  2513.         'playlist_mincount': 4,
  2514.         'info_dict': {
  2515.             'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
  2516.             'title': 'ThirstForScience - Playlists',
  2517.             'description': 'md5:609399d937ea957b0f53cbffb747a14c',
  2518.             'uploader': 'ThirstForScience',
  2519.             'uploader_id': '@ThirstForScience',
  2520.         }
  2521.     }, {
  2522.         'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
  2523.         'only_matching': True,
  2524.     }, {
  2525.         # basic, single video playlist
  2526.         'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
  2527.         'info_dict': {
  2528.             'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
  2529.             'title': 'youtube-dl public playlist',
  2530.             'uploader': 'Sergey M.',
  2531.             'uploader_id': '@sergeym.6173',
  2532.             'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
  2533.         },
  2534.         'playlist_count': 1,
  2535.     }, {
  2536.         # empty playlist
  2537.         'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
  2538.         'info_dict': {
  2539.             'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
  2540.             'title': 'youtube-dl empty playlist',
  2541.             'uploader': 'Sergey M.',
  2542.             'uploader_id': '@sergeym.6173',
  2543.             'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
  2544.         },
  2545.         'playlist_count': 0,
  2546.     }, {
  2547.         # Home tab
  2548.         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
  2549.         'info_dict': {
  2550.             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
  2551.             'title': 'lex will - Home',
  2552.             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
  2553.             'uploader': 'lex will',
  2554.             'uploader_id': '@lexwill718',
  2555.         },
  2556.         'playlist_mincount': 2,
  2557.     }, {
  2558.         # Videos tab
  2559.         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
  2560.         'info_dict': {
  2561.             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
  2562.             'title': 'lex will - Videos',
  2563.             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
  2564.             'uploader': 'lex will',
  2565.             'uploader_id': '@lexwill718',
  2566.         },
  2567.         'playlist_mincount': 975,
  2568.     }, {
  2569.         # Videos tab, sorted by popular
  2570.         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
  2571.         'info_dict': {
  2572.             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
  2573.             'title': 'lex will - Videos',
  2574.             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
  2575.             'uploader': 'lex will',
  2576.             'uploader_id': '@lexwill718',
  2577.         },
  2578.         'playlist_mincount': 199,
  2579.     }, {
  2580.         # Playlists tab
  2581.         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
  2582.         'info_dict': {
  2583.             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
  2584.             'title': 'lex will - Playlists',
  2585.             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
  2586.             'uploader': 'lex will',
  2587.             'uploader_id': '@lexwill718',
  2588.         },
  2589.         'playlist_mincount': 17,
  2590.     }, {
  2591.         # Community tab
  2592.         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
  2593.         'info_dict': {
  2594.             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
  2595.             'title': 'lex will - Community',
  2596.             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
  2597.             'uploader': 'lex will',
  2598.             'uploader_id': '@lexwill718',
  2599.         },
  2600.         'playlist_mincount': 18,
  2601.     }, {
  2602.         # Channels tab
  2603.         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
  2604.         'info_dict': {
  2605.             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
  2606.             'title': 'lex will - Channels',
  2607.             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
  2608.             'uploader': 'lex will',
  2609.             'uploader_id': '@lexwill718',
  2610.         },
  2611.         'playlist_mincount': 75,
  2612.     }, {
  2613.         'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
  2614.         'only_matching': True,
  2615.     }, {
  2616.         'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
  2617.         'only_matching': True,
  2618.     }, {
  2619.         'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
  2620.         'only_matching': True,
  2621.     }, {
  2622.         'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
  2623.         'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
  2624.         'info_dict': {
  2625.             'title': '29C3: Not my department',
  2626.             'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
  2627.             'uploader': 'Christiaan008',
  2628.             'uploader_id': '@ChRiStIaAn008',
  2629.             'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
  2630.         },
  2631.         'playlist_count': 96,
  2632.     }, {
  2633.         'note': 'Large playlist',
  2634.         'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
  2635.         'info_dict': {
  2636.             'title': 'Uploads from Cauchemar',
  2637.             'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
  2638.             'uploader': 'Cauchemar',
  2639.             'uploader_id': '@Cauchemar89',
  2640.             'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
  2641.         },
  2642.         'playlist_mincount': 1123,
  2643.     }, {
  2644.         # even larger playlist, 8832 videos
  2645.         'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
  2646.         'only_matching': True,
  2647.     }, {
  2648.         'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
  2649.         'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
  2650.         'info_dict': {
  2651.             'title': 'Uploads from Interstellar Movie',
  2652.             'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
  2653.             'uploader': 'Interstellar Movie',
  2654.             'uploader_id': '@InterstellarMovie',
  2655.             'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
  2656.         },
  2657.         'playlist_mincount': 21,
  2658.     }, {
  2659.         # https://github.com/ytdl-org/youtube-dl/issues/21844
  2660.         'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
  2661.         'info_dict': {
  2662.             'title': 'Data Analysis with Dr Mike Pound',
  2663.             'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
  2664.             'uploader': 'Computerphile',
  2665.             'uploader_id': '@Computerphile',
  2666.             'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
  2667.         },
  2668.         'playlist_mincount': 11,
  2669.     }, {
  2670.         'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
  2671.         'only_matching': True,
  2672.     }, {
  2673.         # Playlist URL that does not actually serve a playlist
  2674.         'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
  2675.         'info_dict': {
  2676.             'id': 'FqZTN594JQw',
  2677.             'ext': 'webm',
  2678.             'title': "Smiley's People 01 detective, Adventure Series, Action",
  2679.             'uploader': 'STREEM',
  2680.             'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
  2681.             'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
  2682.             'upload_date': '20150526',
  2683.             'license': 'Standard YouTube License',
  2684.             'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
  2685.             'categories': ['People & Blogs'],
  2686.             'tags': list,
  2687.             'view_count': int,
  2688.             'like_count': int,
  2689.         },
  2690.         'params': {
  2691.             'skip_download': True,
  2692.         },
  2693.         'skip': 'This video is not available.',
  2694.         'add_ie': [YoutubeIE.ie_key()],
  2695.     }, {
  2696.         'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
  2697.         'only_matching': True,
  2698.     }, {
  2699.         'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
  2700.         'only_matching': True,
  2701.     }, {
  2702.         'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
  2703.         'info_dict': {
  2704.             'id': r're:[\da-zA-Z_-]{8,}',
  2705.             'ext': 'mp4',
  2706.             'title': r're:(?s)[A-Z].{20,}',
  2707.             'uploader': 'Sky News',
  2708.             'uploader_id': '@SkyNews',
  2709.             'uploader_url': r're:https?://(?:www\.)?youtube\.com/@SkyNews',
  2710.             'upload_date': r're:\d{8}',
  2711.             'description': r're:(?s)(?:.*\n)+SUBSCRIBE to our YouTube channel for more videos: http://www\.youtube\.com/skynews *\n.*',
  2712.             'categories': ['News & Politics'],
  2713.             'tags': list,
  2714.             'like_count': int,
  2715.         },
  2716.         'params': {
  2717.             'skip_download': True,
  2718.         },
  2719.     }, {
  2720.         'url': 'https://www.youtube.com/user/TheYoungTurks/live',
  2721.         'info_dict': {
  2722.             'id': 'a48o2S1cPoo',
  2723.             'ext': 'mp4',
  2724.             'title': 'The Young Turks - Live Main Show',
  2725.             'uploader': 'The Young Turks',
  2726.             'uploader_id': 'TheYoungTurks',
  2727.             'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
  2728.             'upload_date': '20150715',
  2729.             'license': 'Standard YouTube License',
  2730.             'description': 'md5:438179573adcdff3c97ebb1ee632b891',
  2731.             'categories': ['News & Politics'],
  2732.             'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
  2733.             'like_count': int,
  2734.         },
  2735.         'params': {
  2736.             'skip_download': True,
  2737.         },
  2738.         'only_matching': True,
  2739.     }, {
  2740.         'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
  2741.         'only_matching': True,
  2742.     }, {
  2743.         'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
  2744.         'only_matching': True,
  2745.     }, {
  2746.         'url': 'https://www.youtube.com/feed/trending',
  2747.         'only_matching': True,
  2748.     }, {
  2749.         # needs auth
  2750.         'url': 'https://www.youtube.com/feed/library',
  2751.         'only_matching': True,
  2752.     }, {
  2753.         # needs auth
  2754.         'url': 'https://www.youtube.com/feed/history',
  2755.         'only_matching': True,
  2756.     }, {
  2757.         # needs auth
  2758.         'url': 'https://www.youtube.com/feed/subscriptions',
  2759.         'only_matching': True,
  2760.     }, {
  2761.         # needs auth
  2762.         'url': 'https://www.youtube.com/feed/watch_later',
  2763.         'only_matching': True,
  2764.     }, {
  2765.         # no longer available?
  2766.         'url': 'https://www.youtube.com/feed/recommended',
  2767.         'only_matching': True,
  2768.     }, {
  2769.         # inline playlist with not always working continuations
  2770.         'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
  2771.         'only_matching': True,
  2772.     }, {
  2773.         'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
  2774.         'only_matching': True,
  2775.     }, {
  2776.         'url': 'https://www.youtube.com/course',
  2777.         'only_matching': True,
  2778.     }, {
  2779.         'url': 'https://www.youtube.com/zsecurity',
  2780.         'only_matching': True,
  2781.     }, {
  2782.         'url': 'http://www.youtube.com/NASAgovVideo/videos',
  2783.         'only_matching': True,
  2784.     }, {
  2785.         'url': 'https://www.youtube.com/TheYoungTurks/live',
  2786.         'only_matching': True,
  2787.     }, {
  2788.         'url': 'https://www.youtube.com/hashtag/cctv9',
  2789.         'info_dict': {
  2790.             'id': 'cctv9',
  2791.             'title': '#cctv9',
  2792.         },
  2793.         'playlist_mincount': 350,
  2794.     }, {
  2795.         'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
  2796.         'only_matching': True,
  2797.     }, {
  2798.         'note': 'Search tab',
  2799.         'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
  2800.         'playlist_mincount': 20,
  2801.         'info_dict': {
  2802.             'id': 'UCYO_jab_esuFRV4b17AJtAw',
  2803.             'title': '3Blue1Brown - Search - linear algebra',
  2804.             'description': 'md5:e1384e8a133307dd10edee76e875d62f',
  2805.             'uploader': '3Blue1Brown',
  2806.             'uploader_id': '@3blue1brown',
  2807.             'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
  2808.         }
  2809.     }]
  2811.     @classmethod
  2812.     def suitable(cls, url):
  2813.         return not YoutubeIE.suitable(url) and super(
  2814.             YoutubeTabIE, cls).suitable(url)
  2816.     @staticmethod
  2817.     def _extract_grid_item_renderer(item):
  2818.         assert isinstance(item, dict)
  2819.         for key, renderer in item.items():
  2820.             if not key.startswith('grid') or not key.endswith('Renderer'):
  2821.                 continue
  2822.             if not isinstance(renderer, dict):
  2823.                 continue
  2824.             return renderer
  2826.     def _grid_entries(self, grid_renderer):
  2827.         for item in grid_renderer['items']:
  2828.             if not isinstance(item, dict):
  2829.                 continue
  2830.             renderer = self._extract_grid_item_renderer(item)
  2831.             if not isinstance(renderer, dict):
  2832.                 continue
  2833.             title = try_get(
  2834.                 renderer, (lambda x: x['title']['runs'][0]['text'],
  2835.                            lambda x: x['title']['simpleText']), compat_str)
  2836.             # playlist
  2837.             playlist_id = renderer.get('playlistId')
  2838.             if playlist_id:
  2839.                 yield self.url_result(
  2840.                     'https://www.youtube.com/playlist?list=%s' % playlist_id,
  2841.                     ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
  2842.                     video_title=title)
  2843.                 continue
  2844.             # video
  2845.             video_id = renderer.get('videoId')
  2846.             if video_id:
  2847.                 yield self._extract_video(renderer)
  2848.                 continue
  2849.             # channel
  2850.             channel_id = renderer.get('channelId')
  2851.             if channel_id:
  2852.                 title = try_get(
  2853.                     renderer, lambda x: x['title']['simpleText'], compat_str)
  2854.                 yield self.url_result(
  2855.                     'https://www.youtube.com/channel/%s' % channel_id,
  2856.                     ie=YoutubeTabIE.ie_key(), video_title=title)
  2857.                 continue
  2858.             # generic endpoint URL support
  2859.             ep_url = urljoin('https://www.youtube.com/', try_get(
  2860.                 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
  2861.                 compat_str))
  2862.             if ep_url:
  2863.                 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
  2864.                     if ie.suitable(ep_url):
  2865.                         yield self.url_result(
  2866.                             ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
  2867.                         break
  2869.     def _shelf_entries_from_content(self, shelf_renderer):
  2870.         content = shelf_renderer.get('content')
  2871.         if not isinstance(content, dict):
  2872.             return
  2873.         renderer = content.get('gridRenderer')
  2874.         if renderer:
  2875.             # TODO: add support for nested playlists so each shelf is processed
  2876.             # as separate playlist
  2877.             # TODO: this includes only first N items
  2878.             for entry in self._grid_entries(renderer):
  2879.                 yield entry
  2880.         renderer = content.get('horizontalListRenderer')
  2881.         if renderer:
  2882.             # TODO
  2883.             pass
  2885.     def _shelf_entries(self, shelf_renderer, skip_channels=False):
  2886.         ep = try_get(
  2887.             shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
  2888.             compat_str)
  2889.         shelf_url = urljoin('https://www.youtube.com', ep)
  2890.         if shelf_url:
  2891.             # Skipping links to another channels, note that checking for
  2892.             # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
  2893.             # will not work
  2894.             if skip_channels and '/channels?' in shelf_url:
  2895.                 return
  2896.             title = try_get(
  2897.                 shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
  2898.             yield self.url_result(shelf_url, video_title=title)
  2899.         # Shelf may not contain shelf URL, fallback to extraction from content
  2900.         for entry in self._shelf_entries_from_content(shelf_renderer):
  2901.             yield entry
  2903.     def _playlist_entries(self, video_list_renderer):
  2904.         for content in video_list_renderer['contents']:
  2905.             if not isinstance(content, dict):
  2906.                 continue
  2907.             renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
  2908.             if not isinstance(renderer, dict):
  2909.                 continue
  2910.             video_id = renderer.get('videoId')
  2911.             if not video_id:
  2912.                 continue
  2913.             yield self._extract_video(renderer)
  2915.     def _video_entry(self, video_renderer):
  2916.         video_id = video_renderer.get('videoId')
  2917.         if video_id:
  2918.             return self._extract_video(video_renderer)
  2920.     def _post_thread_entries(self, post_thread_renderer):
  2921.         post_renderer = try_get(
  2922.             post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
  2923.         if not post_renderer:
  2924.             return
  2925.         # video attachment
  2926.         video_renderer = try_get(
  2927.             post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict)
  2928.         video_id = None
  2929.         if video_renderer:
  2930.             entry = self._video_entry(video_renderer)
  2931.             if entry:
  2932.                 yield entry
  2933.         # inline video links
  2934.         runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
  2935.         for run in runs:
  2936.             if not isinstance(run, dict):
  2937.                 continue
  2938.             ep_url = try_get(
  2939.                 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
  2940.             if not ep_url:
  2941.                 continue
  2942.             if not YoutubeIE.suitable(ep_url):
  2943.                 continue
  2944.             ep_video_id = YoutubeIE._match_id(ep_url)
  2945.             if video_id == ep_video_id:
  2946.                 continue
  2947.             yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=video_id)
  2949.     def _post_thread_continuation_entries(self, post_thread_continuation):
  2950.         contents = post_thread_continuation.get('contents')
  2951.         if not isinstance(contents, list):
  2952.             return
  2953.         for content in contents:
  2954.             renderer = content.get('backstagePostThreadRenderer')
  2955.             if not isinstance(renderer, dict):
  2956.                 continue
  2957.             for entry in self._post_thread_entries(renderer):
  2958.                 yield entry
  2960.     def _rich_grid_entries(self, contents):
  2961.         for content in contents:
  2962.             video_renderer = try_get(
  2963.                 content,
  2964.                 (lambda x: x['richItemRenderer']['content']['videoRenderer'],
  2965.                  lambda x: x['richItemRenderer']['content']['reelItemRenderer']),
  2966.                 dict)
  2967.             if video_renderer:
  2968.                 entry = self._video_entry(video_renderer)
  2969.                 if entry:
  2970.                     yield entry
  2972.     @staticmethod
  2973.     def _build_continuation_query(continuation, ctp=None):
  2974.         query = {
  2975.             'ctoken': continuation,
  2976.             'continuation': continuation,
  2977.         }
  2978.         if ctp:
  2979.             query['itct'] = ctp
  2980.         return query
  2982.     @staticmethod
  2983.     def _extract_next_continuation_data(renderer):
  2984.         next_continuation = try_get(
  2985.             renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict)
  2986.         if not next_continuation:
  2987.             return
  2988.         continuation = next_continuation.get('continuation')
  2989.         if not continuation:
  2990.             return
  2991.         ctp = next_continuation.get('clickTrackingParams')
  2992.         return YoutubeTabIE._build_continuation_query(continuation, ctp)
  2994.     @classmethod
  2995.     def _extract_continuation(cls, renderer):
  2996.         next_continuation = cls._extract_next_continuation_data(renderer)
  2997.         if next_continuation:
  2998.             return next_continuation
  2999.         contents = []
  3000.         for key in ('contents', 'items'):
  3001.             contents.extend(try_get(renderer, lambda x: x[key], list) or [])
  3002.         for content in contents:
  3003.             if not isinstance(content, dict):
  3004.                 continue
  3005.             continuation_ep = try_get(
  3006.                 content, lambda x: x['continuationItemRenderer']['continuationEndpoint'],
  3007.                 dict)
  3008.             if not continuation_ep:
  3009.                 continue
  3010.             continuation = try_get(
  3011.                 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
  3012.             if not continuation:
  3013.                 continue
  3014.             ctp = continuation_ep.get('clickTrackingParams')
  3015.             return YoutubeTabIE._build_continuation_query(continuation, ctp)
  3017.     def _entries(self, tab, item_id, webpage):
  3018.         tab_content = try_get(tab, lambda x: x['content'], dict)
  3019.         if not tab_content:
  3020.             return
  3021.         slr_renderer = try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
  3022.         if slr_renderer:
  3023.             is_channels_tab = tab.get('title') == 'Channels'
  3024.             continuation = None
  3025.             slr_contents = try_get(slr_renderer, lambda x: x['contents'], list) or []
  3026.             for slr_content in slr_contents:
  3027.                 if not isinstance(slr_content, dict):
  3028.                     continue
  3029.                 is_renderer = try_get(slr_content, lambda x: x['itemSectionRenderer'], dict)
  3030.                 if not is_renderer:
  3031.                     continue
  3032.                 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
  3033.                 for isr_content in isr_contents:
  3034.                     if not isinstance(isr_content, dict):
  3035.                         continue
  3036.                     renderer = isr_content.get('playlistVideoListRenderer')
  3037.                     if renderer:
  3038.                         for entry in self._playlist_entries(renderer):
  3039.                             yield entry
  3040.                         continuation = self._extract_continuation(renderer)
  3041.                         continue
  3042.                     renderer = isr_content.get('gridRenderer')
  3043.                     if renderer:
  3044.                         for entry in self._grid_entries(renderer):
  3045.                             yield entry
  3046.                         continuation = self._extract_continuation(renderer)
  3047.                         continue
  3048.                     renderer = isr_content.get('shelfRenderer')
  3049.                     if renderer:
  3050.                         for entry in self._shelf_entries(renderer, not is_channels_tab):
  3051.                             yield entry
  3052.                         continue
  3053.                     renderer = isr_content.get('backstagePostThreadRenderer')
  3054.                     if renderer:
  3055.                         for entry in self._post_thread_entries(renderer):
  3056.                             yield entry
  3057.                         continuation = self._extract_continuation(renderer)
  3058.                         continue
  3059.                     renderer = isr_content.get('videoRenderer')
  3060.                     if renderer:
  3061.                         entry = self._video_entry(renderer)
  3062.                         if entry:
  3063.                             yield entry
  3065.                 if not continuation:
  3066.                     continuation = self._extract_continuation(is_renderer)
  3067.             if not continuation:
  3068.                 continuation = self._extract_continuation(slr_renderer)
  3069.         else:
  3070.             rich_grid_renderer = tab_content.get('richGridRenderer')
  3071.             if not rich_grid_renderer:
  3072.                 return
  3073.             for entry in self._rich_grid_entries(rich_grid_renderer.get('contents') or []):
  3074.                 yield entry
  3075.             continuation = self._extract_continuation(rich_grid_renderer)
  3077.         ytcfg = self._extract_ytcfg(item_id, webpage)
  3078.         client_version = try_get(
  3079.             ytcfg, lambda x: x['INNERTUBE_CLIENT_VERSION'], compat_str) or '2.20210407.08.00'
  3081.         headers = {
  3082.             'x-youtube-client-name': '1',
  3083.             'x-youtube-client-version': client_version,
  3084.             'content-type': 'application/json',
  3085.         }
  3087.         context = try_get(ytcfg, lambda x: x['INNERTUBE_CONTEXT'], dict) or {
  3088.             'client': {
  3089.                 'clientName': 'WEB',
  3090.                 'clientVersion': client_version,
  3091.             }
  3092.         }
  3093.         visitor_data = try_get(context, lambda x: x['client']['visitorData'], compat_str)
  3095.         identity_token = self._extract_identity_token(ytcfg, webpage)
  3096.         if identity_token:
  3097.             headers['x-youtube-identity-token'] = identity_token
  3099.         data = {
  3100.             'context': context,
  3101.         }
  3103.         for page_num in itertools.count(1):
  3104.             if not continuation:
  3105.                 break
  3106.             if visitor_data:
  3107.                 headers['x-goog-visitor-id'] = visitor_data
  3108.             data['continuation'] = continuation['continuation']
  3109.             data['clickTracking'] = {
  3110.                 'clickTrackingParams': continuation['itct']
  3111.             }
  3112.             count = 0
  3113.             retries = 3
  3114.             while count <= retries:
  3115.                 try:
  3116.                     # Downloading page may result in intermittent 5xx HTTP error
  3117.                     # that is usually worked around with a retry
  3118.                     response = self._download_json(
  3119.                         'https://www.youtube.com/youtubei/v1/browse?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
  3120.                         None, 'Downloading page %d%s' % (page_num, ' (retry #%d)' % count if count else ''),
  3121.                         headers=headers, data=json.dumps(data).encode('utf8'))
  3122.                     break
  3123.                 except ExtractorError as e:
  3124.                     if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
  3125.                         count += 1
  3126.                         if count <= retries:
  3127.                             continue
  3128.                     raise
  3129.             if not response:
  3130.                 break
  3132.             visitor_data = try_get(
  3133.                 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
  3135.             continuation_contents = try_get(
  3136.                 response, lambda x: x['continuationContents'], dict)
  3137.             if continuation_contents:
  3138.                 continuation_renderer = continuation_contents.get('playlistVideoListContinuation')
  3139.                 if continuation_renderer:
  3140.                     for entry in self._playlist_entries(continuation_renderer):
  3141.                         yield entry
  3142.                     continuation = self._extract_continuation(continuation_renderer)
  3143.                     continue
  3144.                 continuation_renderer = continuation_contents.get('gridContinuation')
  3145.                 if continuation_renderer:
  3146.                     for entry in self._grid_entries(continuation_renderer):
  3147.                         yield entry
  3148.                     continuation = self._extract_continuation(continuation_renderer)
  3149.                     continue
  3150.                 continuation_renderer = continuation_contents.get('itemSectionContinuation')
  3151.                 if continuation_renderer:
  3152.                     for entry in self._post_thread_continuation_entries(continuation_renderer):
  3153.                         yield entry
  3154.                     continuation = self._extract_continuation(continuation_renderer)
  3155.                     continue
  3157.             on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
  3158.             continuation_items = try_get(
  3159.                 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
  3160.             if continuation_items:
  3161.                 continuation_item = continuation_items[0]
  3162.                 if not isinstance(continuation_item, dict):
  3163.                     continue
  3164.                 renderer = self._extract_grid_item_renderer(continuation_item)
  3165.                 if renderer:
  3166.                     grid_renderer = {'items': continuation_items}
  3167.                     for entry in self._grid_entries(grid_renderer):
  3168.                         yield entry
  3169.                     continuation = self._extract_continuation(grid_renderer)
  3170.                     continue
  3171.                 renderer = continuation_item.get('playlistVideoRenderer') or continuation_item.get('itemSectionRenderer')
  3172.                 if renderer:
  3173.                     video_list_renderer = {'contents': continuation_items}
  3174.                     for entry in self._playlist_entries(video_list_renderer):
  3175.                         yield entry
  3176.                     continuation = self._extract_continuation(video_list_renderer)
  3177.                     continue
  3178.                 renderer = continuation_item.get('backstagePostThreadRenderer')
  3179.                 if renderer:
  3180.                     continuation_renderer = {'contents': continuation_items}
  3181.                     for entry in self._post_thread_continuation_entries(continuation_renderer):
  3182.                         yield entry
  3183.                     continuation = self._extract_continuation(continuation_renderer)
  3184.                     continue
  3185.                 renderer = continuation_item.get('richItemRenderer')
  3186.                 if renderer:
  3187.                     for entry in self._rich_grid_entries(continuation_items):
  3188.                         yield entry
  3189.                     continuation = self._extract_continuation({'contents': continuation_items})
  3190.                     continue
  3192.             break
  3194.     @staticmethod
  3195.     def _extract_selected_tab(tabs):
  3196.         for tab in tabs:
  3197.             renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
  3198.             if renderer.get('selected') is True:
  3199.                 return renderer
  3200.         else:
  3201.             raise ExtractorError('Unable to find selected tab')
  3203.     def _extract_uploader(self, metadata, data):
  3204.         uploader = {}
  3205.         renderers = traverse_obj(data,
  3206.                                  ('sidebar', 'playlistSidebarRenderer', 'items'))
  3207.         uploader['channel_id'] = self._extract_channel_id('', metadata=metadata, renderers=renderers)
  3208.         uploader['uploader'] = (
  3209.             self._extract_author_var('', 'name', renderers=renderers)
  3210.             or self._extract_author_var('', 'name', metadata=metadata))
  3211.         uploader['uploader_url'] = self._yt_urljoin(
  3212.             self._extract_author_var('', 'url', metadata=metadata, renderers=renderers))
  3213.         uploader['uploader_id'] = self._extract_uploader_id(uploader['uploader_url'])
  3214.         uploader['channel'] = uploader['uploader']
  3215.         return uploader
  3217.     @staticmethod
  3218.     def _extract_alert(data):
  3219.         alerts = []
  3220.         for alert in try_get(data, lambda x: x['alerts'], list) or []:
  3221.             if not isinstance(alert, dict):
  3222.                 continue
  3223.             alert_text = try_get(
  3224.                 alert, lambda x: x['alertRenderer']['text'], dict)
  3225.             if not alert_text:
  3226.                 continue
  3227.             text = try_get(
  3228.                 alert_text,
  3229.                 (lambda x: x['simpleText'], lambda x: x['runs'][0]['text']),
  3230.                 compat_str)
  3231.             if text:
  3232.                 alerts.append(text)
  3233.         return '\n'.join(alerts)
  3235.     def _extract_from_tabs(self, item_id, webpage, data, tabs):
  3236.         selected_tab = self._extract_selected_tab(tabs)
  3237.         renderer = try_get(
  3238.             data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
  3239.         playlist_id = item_id
  3240.         title = description = None
  3241.         if renderer:
  3242.             channel_title = renderer.get('title') or item_id
  3243.             tab_title = selected_tab.get('title')
  3244.             title = channel_title or item_id
  3245.             if tab_title:
  3246.                 title += ' - %s' % tab_title
  3247.             if selected_tab.get('expandedText'):
  3248.                 title += ' - %s' % selected_tab['expandedText']
  3249.             description = renderer.get('description')
  3250.             playlist_id = renderer.get('externalId')
  3251.         else:
  3252.             renderer = try_get(
  3253.                 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
  3254.             if renderer:
  3255.                 title = renderer.get('title')
  3256.             else:
  3257.                 renderer = try_get(
  3258.                     data, lambda x: x['header']['hashtagHeaderRenderer'], dict)
  3259.                 if renderer:
  3260.                     title = try_get(renderer, lambda x: x['hashtag']['simpleText'])
  3261.         playlist = self.playlist_result(
  3262.             self._entries(selected_tab, item_id, webpage),
  3263.             playlist_id=playlist_id, playlist_title=title,
  3264.             playlist_description=description)
  3265.         return merge_dicts(playlist, self._extract_uploader(renderer, data))
  3267.     def _extract_from_playlist(self, item_id, url, data, playlist):
  3268.         title = playlist.get('title') or try_get(
  3269.             data, lambda x: x['titleText']['simpleText'], compat_str)
  3270.         playlist_id = playlist.get('playlistId') or item_id
  3271.         # Inline playlist rendition continuation does not always work
  3272.         # at Youtube side, so delegating regular tab-based playlist URL
  3273.         # processing whenever possible.
  3274.         playlist_url = urljoin(url, try_get(
  3275.             playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
  3276.             compat_str))
  3277.         if playlist_url and playlist_url != url:
  3278.             return self.url_result(
  3279.                 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
  3280.                 video_title=title)
  3281.         return self.playlist_result(
  3282.             self._playlist_entries(playlist), playlist_id=playlist_id,
  3283.             playlist_title=title)
  3285.     def _extract_identity_token(self, ytcfg, webpage):
  3286.         if ytcfg:
  3287.             token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
  3288.             if token:
  3289.                 return token
  3290.         return self._search_regex(
  3291.             r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
  3292.             'identity token', default=None)
  3294.     def _real_extract(self, url):
  3295.         item_id = self._match_id(url)
  3296.         url = update_url(url, netloc='www.youtube.com')
  3297.         # Handle both video/playlist URLs
  3298.         qs = parse_qs(url)
  3299.         video_id = qs.get('v', [None])[0]
  3300.         playlist_id = qs.get('list', [None])[0]
  3301.         if video_id and playlist_id:
  3302.             if self._downloader.params.get('noplaylist'):
  3303.                 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
  3304.                 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
  3305.             self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
  3306.         webpage = self._download_webpage(url, item_id)
  3307.         data = self._extract_yt_initial_data(item_id, webpage)
  3308.         tabs = try_get(
  3309.             data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
  3310.         if tabs:
  3311.             return self._extract_from_tabs(item_id, webpage, data, tabs)
  3312.         playlist = try_get(
  3313.             data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
  3314.         if playlist:
  3315.             return self._extract_from_playlist(item_id, url, data, playlist)
  3316.         # Fallback to video extraction if no playlist alike page is recognized.
  3317.         # First check for the current video then try the v attribute of URL query.
  3318.         video_id = try_get(
  3319.             data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
  3320.             compat_str) or video_id
  3321.         if video_id:
  3322.             return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
  3323.         # Capture and output alerts
  3324.         alert = self._extract_alert(data)
  3325.         if alert:
  3326.             raise ExtractorError(alert, expected=True)
  3327.         # Failed to recognize
  3328.         raise ExtractorError('Unable to recognize tab page')
  3331. class YoutubePlaylistIE(InfoExtractor):
  3332.     IE_DESC = 'YouTube.com playlists'
  3333.     _VALID_URL = r'''(?x)(?:
  3334.                         (?:https?://)?
  3335.                         (?:\w+\.)?
  3336.                         (?:
  3337.                             (?:
  3338.                                 youtube(?:kids)?\.com|
  3339.                                 invidio\.us
  3340.                             )
  3341.                             /.*?\?.*?\blist=
  3342.                         )?
  3343.                         (?P<id>%(playlist_id)s)
  3344.                      )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
  3345.     IE_NAME = 'youtube:playlist'
  3346.     _TESTS = [{
  3347.         'note': 'issue #673',
  3348.         'url': 'PLBB231211A4F62143',
  3349.         'info_dict': {
  3350.             'title': '[OLD]Team Fortress 2 (Class-based LP)',
  3351.             'id': 'PLBB231211A4F62143',
  3352.             'uploader': 'Wickman',
  3353.             'uploader_id': '@WickmanVT',
  3354.             'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
  3355.         },
  3356.         'playlist_mincount': 29,
  3357.     }, {
  3358.         'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
  3359.         'info_dict': {
  3360.             'title': 'YDL_safe_search',
  3361.             'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
  3362.         },
  3363.         'playlist_count': 2,
  3364.         'skip': 'This playlist is private',
  3365.     }, {
  3366.         'note': 'embedded',
  3367.         'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
  3368.         # TODO: full playlist requires _reload_with_unavailable_videos()
  3369.         # 'playlist_count': 4,
  3370.         'playlist_mincount': 1,
  3371.         'info_dict': {
  3372.             'title': 'JODA15',
  3373.             'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
  3374.             'uploader': 'milan',
  3375.             'uploader_id': '@milan5503',
  3376.             'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
  3377.         }
  3378.     }, {
  3379.         'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
  3380.         'playlist_mincount': 455,
  3381.         'info_dict': {
  3382.             'title': '2018 Chinese New Singles (11/6 updated)',
  3383.             'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
  3384.             'uploader': 'LBK',
  3385.             'uploader_id': '@music_king',
  3386.             'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
  3387.         }
  3388.     }, {
  3389.         'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
  3390.         'only_matching': True,
  3391.     }, {
  3392.         # music album playlist
  3393.         'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
  3394.         'only_matching': True,
  3395.     }]
  3397.     @classmethod
  3398.     def suitable(cls, url):
  3399.         if YoutubeTabIE.suitable(url):
  3400.             return False
  3401.         if parse_qs(url).get('v', [None])[0]:
  3402.             return False
  3403.         return super(YoutubePlaylistIE, cls).suitable(url)
  3405.     def _real_extract(self, url):
  3406.         playlist_id = self._match_id(url)
  3407.         qs = parse_qs(url)
  3408.         if not qs:
  3409.             qs = {'list': playlist_id}
  3410.         return self.url_result(
  3411.             update_url_query('https://www.youtube.com/playlist', qs),
  3412.             ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
  3415. class YoutubeYtBeIE(InfoExtractor):
  3416.     _VALID_URL = r'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
  3417.     _TESTS = [{
  3418.         'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
  3419.         'info_dict': {
  3420.             'id': 'yeWKywCrFtk',
  3421.             'ext': 'mp4',
  3422.             'title': 'Small Scale Baler and Braiding Rugs',
  3423.             'uploader': 'Backus-Page House Museum',
  3424.             'uploader_id': '@backuspagemuseum',
  3425.             'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
  3426.             'upload_date': '20161008',
  3427.             'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
  3428.             'categories': ['Nonprofits & Activism'],
  3429.             'tags': list,
  3430.             'like_count': int,
  3431.         },
  3432.         'params': {
  3433.             'noplaylist': True,
  3434.             'skip_download': True,
  3435.         },
  3436.     }, {
  3437.         'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
  3438.         'only_matching': True,
  3439.     }]
  3441.     def _real_extract(self, url):
  3442.         mobj = re.match(self._VALID_URL, url)
  3443.         video_id = mobj.group('id')
  3444.         playlist_id = mobj.group('playlist_id')
  3445.         return self.url_result(
  3446.             update_url_query('https://www.youtube.com/watch', {
  3447.                 'v': video_id,
  3448.                 'list': playlist_id,
  3449.                 'feature': 'youtu.be',
  3450.             }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
  3453. class YoutubeYtUserIE(InfoExtractor):
  3454.     _VALID_URL = r'ytuser:(?P<id>.+)'
  3455.     _TESTS = [{
  3456.         'url': 'ytuser:phihag',
  3457.         'only_matching': True,
  3458.     }]
  3460.     def _real_extract(self, url):
  3461.         user_id = self._match_id(url)
  3462.         return self.url_result(
  3463.             'https://www.youtube.com/user/%s' % user_id,
  3464.             ie=YoutubeTabIE.ie_key(), video_id=user_id)
  3467. class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
  3468.     IE_NAME = 'youtube:favorites'
  3469.     IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
  3470.     _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
  3471.     _LOGIN_REQUIRED = True
  3472.     _TESTS = [{
  3473.         'url': ':ytfav',
  3474.         'only_matching': True,
  3475.     }, {
  3476.         'url': ':ytfavorites',
  3477.         'only_matching': True,
  3478.     }]
  3480.     def _real_extract(self, url):
  3481.         return self.url_result(
  3482.             'https://www.youtube.com/playlist?list=LL',
  3483.             ie=YoutubeTabIE.ie_key())
  3486. class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
  3487.     IE_DESC = 'YouTube.com searches'
  3488.     IE_NAME = 'youtube:search'
  3489.     _SEARCH_KEY = 'ytsearch'
  3490.     _SEARCH_PARAMS = 'EgIQAQ%3D%3D'  # Videos only
  3491.     _MAX_RESULTS = float('inf')
  3492.     _TESTS = [{
  3493.         'url': 'ytsearch10:youtube-dl test video',
  3494.         'playlist_count': 10,
  3495.         'info_dict': {
  3496.             'id': 'youtube-dl test video',
  3497.             'title': 'youtube-dl test video',
  3498.         }
  3499.     }]
  3501.     def _get_n_results(self, query, n):
  3502.         """Get a specified number of results for a query"""
  3503.         entries = itertools.islice(self._search_results(query, self._SEARCH_PARAMS), 0, None if n == float('inf') else n)
  3504.         return self.playlist_result(entries, query, query)
  3507. class YoutubeSearchDateIE(YoutubeSearchIE):
  3508.     IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
  3509.     _SEARCH_KEY = 'ytsearchdate'
  3510.     IE_DESC = 'YouTube.com searches, newest videos first'
  3511.     _SEARCH_PARAMS = 'CAISAhAB'  # Videos only, sorted by date
  3512.     _TESTS = [{
  3513.         'url': 'ytsearchdate10:youtube-dl test video',
  3514.         'playlist_count': 10,
  3515.         'info_dict': {
  3516.             'id': 'youtube-dl test video',
  3517.             'title': 'youtube-dl test video',
  3518.         }
  3519.     }]
  3522. class YoutubeSearchURLIE(YoutubeBaseInfoExtractor):
  3523.     IE_DESC = 'YouTube search URLs with sorting and filter support'
  3524.     IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
  3525.     _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
  3526.     _TESTS = [{
  3527.         'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
  3528.         'playlist_mincount': 5,
  3529.         'info_dict': {
  3530.             'id': 'youtube-dl test video',
  3531.             'title': 'youtube-dl test video',
  3532.         },
  3533.         'params': {'playlistend': 5}
  3534.     }, {
  3535.         'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
  3536.         'only_matching': True,
  3537.     }]
  3539.     def _real_extract(self, url):
  3540.         qs = parse_qs(url)
  3541.         query = (qs.get('search_query') or qs.get('q'))[-1]
  3542.         params = qs.get('sp', ('',))[-1]
  3543.         return self.playlist_result(self._search_results(query, params), query, query)
  3546. class YoutubeFeedsInfoExtractor(YoutubeTabIE):
  3547.     """
  3548.     Base class for feed extractors
  3549.     Subclasses must define the _FEED_NAME property.
  3550.     """
  3551.     _LOGIN_REQUIRED = True
  3553.     @property
  3554.     def IE_NAME(self):
  3555.         return 'youtube:%s' % self._FEED_NAME
  3557.     def _real_initialize(self):
  3558.         self._login()
  3560.     def _real_extract(self, url):
  3561.         return self.url_result(
  3562.             'https://www.youtube.com/feed/%s' % self._FEED_NAME,
  3563.             ie=YoutubeTabIE.ie_key())
  3566. class YoutubeWatchLaterIE(InfoExtractor):
  3567.     IE_NAME = 'youtube:watchlater'
  3568.     IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
  3569.     _VALID_URL = r':ytwatchlater'
  3570.     _TESTS = [{
  3571.         'url': ':ytwatchlater',
  3572.         'only_matching': True,
  3573.     }]
  3575.     def _real_extract(self, url):
  3576.         return self.url_result(
  3577.             'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
  3580. class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
  3581.     IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
  3582.     _VALID_URL = r':ytrec(?:ommended)?'
  3583.     _FEED_NAME = 'recommended'
  3584.     _TESTS = [{
  3585.         'url': ':ytrec',
  3586.         'only_matching': True,
  3587.     }, {
  3588.         'url': ':ytrecommended',
  3589.         'only_matching': True,
  3590.     }]
  3593. class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
  3594.     IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
  3595.     _VALID_URL = r':ytsubs(?:criptions)?'
  3596.     _FEED_NAME = 'subscriptions'
  3597.     _TESTS = [{
  3598.         'url': ':ytsubs',
  3599.         'only_matching': True,
  3600.     }, {
  3601.         'url': ':ytsubscriptions',
  3602.         'only_matching': True,
  3603.     }]
  3606. class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
  3607.     IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
  3608.     _VALID_URL = r':ythistory'
  3609.     _FEED_NAME = 'history'
  3610.     _TESTS = [{
  3611.         'url': ':ythistory',
  3612.         'only_matching': True,
  3613.     }]
  3616. class YoutubeTruncatedURLIE(InfoExtractor):
  3617.     IE_NAME = 'youtube:truncated_url'
  3618.     IE_DESC = False  # Do not list
  3619.     _VALID_URL = r'''(?x)
  3620.         (?:https?://)?
  3621.         (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
  3622.         (?:watch\?(?:
  3623.             feature=[a-z_]+|
  3624.             annotation_id=annotation_[^&]+|
  3625.             x-yt-cl=[0-9]+|
  3626.             hl=[^&]*|
  3627.             t=[0-9]+
  3628.         )?
  3629.         |
  3630.             attribution_link\?a=[^&]+
  3631.         )
  3632.         $
  3633.     '''
  3635.     _TESTS = [{
  3636.         'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
  3637.         'only_matching': True,
  3638.     }, {
  3639.         'url': 'https://www.youtube.com/watch?',
  3640.         'only_matching': True,
  3641.     }, {
  3642.         'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
  3643.         'only_matching': True,
  3644.     }, {
  3645.         'url': 'https://www.youtube.com/watch?feature=foo',
  3646.         'only_matching': True,
  3647.     }, {
  3648.         'url': 'https://www.youtube.com/watch?hl=en-GB',
  3649.         'only_matching': True,
  3650.     }, {
  3651.         'url': 'https://www.youtube.com/watch?t=2372',
  3652.         'only_matching': True,
  3653.     }]
  3655.     def _real_extract(self, url):
  3656.         raise ExtractorError(
  3657.             'Did you forget to quote the URL? Remember that & is a meta '
  3658.             'character in most shells, so you want to put the URL in quotes, '
  3659.             'like  youtube-dl '
  3660.             '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
  3661.             ' or simply  youtube-dl BaW_jenozKc  .',
  3662.             expected=True)
  3665. class YoutubeTruncatedIDIE(InfoExtractor):
  3666.     IE_NAME = 'youtube:truncated_id'
  3667.     IE_DESC = False  # Do not list
  3668.     _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
  3670.     _TESTS = [{
  3671.         'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
  3672.         'only_matching': True,
  3673.     }]
  3675.     def _real_extract(self, url):
  3676.         video_id = self._match_id(url)
  3677.         raise ExtractorError(
  3678.             'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
  3679.             expected=True)