youtube.py

# coding: utf-8
from __future__ import unicode_literals

from datetime import datetime
import json
import hashlib
import random
import re
import time

from .common import InfoExtractor, SearchInfoExtractor
from ..compat import (
    compat_chr,
    compat_kwargs,
    compat_parse_qs,
    compat_urllib_parse_unquote,
    compat_urllib_parse_unquote_plus,
    compat_urllib_parse_urlencode,
    compat_urllib_parse_urlparse,
    compat_urlparse,
    compat_str,
)
from ..utils import (
    bool_or_none,
    clean_html,
    error_to_compat_str,
    ExtractorError,
    float_or_none,
    get_element_by_id,
    int_or_none,
    mimetype2ext,
    parse_codecs,
    parse_duration,
    remove_quotes,
    remove_start,
    smuggle_url,
    str_or_none,
    str_to_int,
    try_get,
    unescapeHTML,
    unified_strdate,
    unsmuggle_url,
    uppercase_escape,
    url_or_none,
    urlencode_postdata,
    GeoRestrictedError,
)


class YoutubeBaseInfoExtractor(InfoExtractor):
    """Provide base functions for Youtube extractors"""
    _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
    _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'

    _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
    _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
    _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'

    _NETRC_MACHINE = 'youtube'
    # If True it will raise an error if no login info is provided
    _LOGIN_REQUIRED = False

    _PLAYLIST_ID_RE = r'(?:LL|WL|(?:PL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,})'

    _YOUTUBE_CLIENT_HEADERS = {
        'x-youtube-client-name': '1',
        'x-youtube-client-version': '2.20201112.04.01',
    }

    _YOUTUBE_API_KEY = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'

    def _set_consent(self):
        self._set_cookie(
            '.youtube.com', 'CONSENT', 'YES+0x557755',
            expire_time=time.time() + 2 * 30 * 24 * 3600)

    def _ids_to_results(self, ids):
        return [
            self.url_result(vid_id, 'Youtube', video_id=vid_id)
            for vid_id in ids]

    def _login(self):
        """
        Attempt to log in to YouTube.
        True is returned if successful or skipped.
        False is returned if login failed.

        If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
        """
        username, password = self._get_login_info()
        # No authentication to be performed
        if username is None:
            if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
                raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
            return True

        login_page = self._download_webpage(
            self._LOGIN_URL, None,
            note='Downloading login page',
            errnote='unable to fetch login page', fatal=False)
        if login_page is False:
            return

        login_form = self._hidden_inputs(login_page)

        def req(url, f_req, note, errnote):
            data = login_form.copy()
            data.update({
                'pstMsg': 1,
                'checkConnection': 'youtube',
                'checkedDomains': 'youtube',
                'hl': 'en',
                'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
                'f.req': json.dumps(f_req),
                'flowName': 'GlifWebSignIn',
                'flowEntry': 'ServiceLogin',
                # TODO: reverse actual botguard identifier generation algo
                'bgRequest': '["identifier",""]',
            })
            return self._download_json(
                url, None, note=note, errnote=errnote,
                transform_source=lambda s: re.sub(r'^[^[]*', '', s),
                fatal=False,
                data=urlencode_postdata(data), headers={
                    'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
                    'Google-Accounts-XSRF': 1,
                })

        def warn(message):
            self._downloader.report_warning(message)

        lookup_req = [
            username,
            None, [], None, 'US', None, None, 2, False, True,
            [
                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],
                1, [None, None, []], None, None, None, True
            ],
            username,
        ]

        lookup_results = req(
            self._LOOKUP_URL, lookup_req,
            'Looking up account info', 'Unable to look up account info')

        if lookup_results is False:
            return False

        user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
        if not user_hash:
            warn('Unable to extract user hash')
            return False

        challenge_req = [
            user_hash,
            None, 1, None, [1, None, None, None, [password, None, True]],
            [
                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],
                1, [None, None, []], None, None, None, True
            ]]

        challenge_results = req(
            self._CHALLENGE_URL, challenge_req,
            'Logging in', 'Unable to log in')

        if challenge_results is False:
            return

        login_res = try_get(challenge_results, lambda x: x[0][5], list)
        if login_res:
            login_msg = try_get(login_res, lambda x: x[5], compat_str)
            warn(
                'Unable to login: %s' % 'Invalid password'
                if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
            return False

        res = try_get(challenge_results, lambda x: x[0][-1], list)
        if not res:
            warn('Unable to extract result entry')
            return False

        login_challenge = try_get(res, lambda x: x[0][0], list)
        if login_challenge:
            challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
            if challenge_str == 'TWO_STEP_VERIFICATION':
                # SEND_SUCCESS - TFA code has been successfully sent to phone
                # QUOTA_EXCEEDED - reached the limit of TFA codes
                status = try_get(login_challenge, lambda x: x[5], compat_str)
                if status == 'QUOTA_EXCEEDED':
                    warn('Exceeded the limit of TFA codes, try later')
                    return False

                tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
                if not tl:
                    warn('Unable to extract TL')
                    return False

                tfa_code = self._get_tfa_info('2-step verification code')

                if not tfa_code:
                    warn(
                        'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
                        '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
                    return False

                tfa_code = remove_start(tfa_code, 'G-')

                tfa_req = [
                    user_hash, None, 2, None,
                    [
                        9, None, None, None, None, None, None, None,
                        [None, tfa_code, True, 2]
                    ]]

                tfa_results = req(
                    self._TFA_URL.format(tl), tfa_req,
                    'Submitting TFA code', 'Unable to submit TFA code')

                if tfa_results is False:
                    return False

                tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
                if tfa_res:
                    tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
                    warn(
                        'Unable to finish TFA: %s' % 'Invalid TFA code'
                        if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
                    return False

                check_cookie_url = try_get(
                    tfa_results, lambda x: x[0][-1][2], compat_str)
            else:
                CHALLENGES = {
                    'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
                    'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
                    'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
                }
                challenge = CHALLENGES.get(
                    challenge_str,
                    '%s returned error %s.' % (self.IE_NAME, challenge_str))
                warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
                return False
        else:
            check_cookie_url = try_get(res, lambda x: x[2], compat_str)

        if not check_cookie_url:
            warn('Unable to extract CheckCookie URL')
            return False

        check_cookie_results = self._download_webpage(
            check_cookie_url, None, 'Checking cookie', fatal=False)

        if check_cookie_results is False:
            return False

        if 'https://myaccount.google.com/' not in check_cookie_results:
            warn('Unable to log in')
            return False

        return True

    def _download_webpage_handle(self, *args, **kwargs):
        return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
            *args, **compat_kwargs(kwargs))

    def _real_initialize(self):
        if self._downloader is None:
            return
        self._set_consent()
        if not self._login():
            return


class YoutubeIE(YoutubeBaseInfoExtractor):
    IE_DESC = 'YouTube.com'
    _VALID_URL = r"""(?x)^
                     (
                         (?:https?://|//)                                    # http(s):// or protocol-independent URL
                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
                            (?:www\.)?deturl\.com/www\.youtube\.com/|
                            (?:www\.)?pwnyoutube\.com/|
                            (?:www\.)?hooktube\.com/|
                            (?:www\.)?yourepeat\.com/|
                            tube\.majestyc\.net/|
                            # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
                            (?:(?:www|dev)\.)?invidio\.us/|
                            (?:(?:www|no)\.)?invidiou\.sh/|
                            (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
                            (?:www\.)?invidious\.kabi\.tk/|
                            (?:www\.)?invidious\.13ad\.de/|
                            (?:www\.)?invidious\.mastodon\.host/|
                            (?:www\.)?invidious\.zapashcanon\.fr/|
                            (?:www\.)?invidious\.kavin\.rocks/|
                            (?:www\.)?invidious\.tube/|
                            (?:www\.)?invidiou\.site/|
                            (?:www\.)?invidious\.site/|
                            (?:www\.)?invidious\.xyz/|
                            (?:www\.)?invidious\.nixnet\.xyz/|
                            (?:www\.)?invidious\.drycat\.fr/|
                            (?:www\.)?tube\.poal\.co/|
                            (?:www\.)?tube\.connect\.cafe/|
                            (?:www\.)?vid\.wxzm\.sx/|
                            (?:www\.)?vid\.mint\.lgbt/|
                            (?:www\.)?yewtu\.be/|
                            (?:www\.)?yt\.elukerio\.org/|
                            (?:www\.)?yt\.lelux\.fi/|
                            (?:www\.)?invidious\.ggc-project\.de/|
                            (?:www\.)?yt\.maisputain\.ovh/|
                            (?:www\.)?invidious\.13ad\.de/|
                            (?:www\.)?invidious\.toot\.koeln/|
                            (?:www\.)?invidious\.fdn\.fr/|
                            (?:www\.)?watch\.nettohikari\.com/|
                            (?:www\.)?kgg2m7yk5aybusll\.onion/|
                            (?:www\.)?qklhadlycap4cnod\.onion/|
                            (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
                            (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
                            (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
                            (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
                            (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
                            (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
                            youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                         (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                         (?:                                                  # the various things that can precede the ID:
                             (?:(?:v|embed|e)/(?!videoseries))                # v/ or embed/ or e/
                             |(?:                                             # or the v= param in all its forms
                                 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
                                 (?:\?|\#!?)                                  # the params delimiter ? or # or #!
                                 (?:.*?[&;])??                                # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
                                 v=
                             )
                         ))
                         |(?:
                            youtu\.be|                                        # just youtu.be/xxxx
                            (?:www\.)?youtube\.com/(?:
                                shorts|                                       # or youtube.com/shorts/xxx
                                video                                         # or youtube.com/video/xxx
                            )|
                            vid\.plus|                                        # or vid.plus/xxxx
                            zwearz\.com/watch|                                # or zwearz.com/watch/xxxx
                         )/
                         |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                         )
                     )?                                                       # all until now is optional -> you can pass the naked ID
                     ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
                     (?!.*?\blist=
                        (?:
                            %(playlist_id)s|                                  # combined list/video URLs are handled by the playlist IE
                            WL                                                # WL are handled by the watch later IE
                        )
                     )
                     (?(1).+)?                                                # if we found the ID, everything can follow
                     $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
    _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
    _PLAYER_INFO_RE = (
        r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$',
        r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$',
    )
    _formats = {
        # '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
        # '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
        # '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
        # '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
        '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
        # '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
        # '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
        # '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
        # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
        # '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
        # '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
        # '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
        # '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
        # '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
        # '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
        # '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
        # '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
        # '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},


        # 3D videos
        '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
        '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
        '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
        '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
        '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
        '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
        '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},

        # Apple HTTP Live Streaming
        '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
        '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
        '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
        '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
        '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
        '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
        '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
        '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},

        # DASH mp4 video
        '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'},  # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
        '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
        '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
        '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
        '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},

        # Dash mp4 audio
        '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
        '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
        '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
        '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
        '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
        '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
        '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},

        # Dash webm
        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
        '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
        '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
        '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
        '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
        '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
        '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
        '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},

        # Dash webm audio
        '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
        '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},

        # Dash webm audio with opus inside
        '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
        '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
        '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},

        # RTMP (unnamed)
        # '_rtmp': {'protocol': 'rtmp'},

        # av01 video only formats sometimes served with "unknown" codecs
        '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
        '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
        '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
        '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
    }
    _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')

    _GEO_BYPASS = False

    IE_NAME = 'youtube'
    _TESTS = [
        {
            'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
            'info_dict': {
                'id': 'BaW_jenozKc',
                'ext': 'mp4',
                'title': 'youtube-dl test video "\'/\\ä↭𝕐',
                'uploader': 'Philipp Hagemeister',
                'uploader_id': 'phihag',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
                'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
                'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
                'upload_date': '20121002',
                '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 .',
                'categories': ['Science & Technology'],
                'tags': ['youtube-dl'],
                'duration': 10,
                'view_count': int,
                'like_count': int,
                'dislike_count': int,
                'start_time': 1,
                'end_time': 9,
            }
        },
        {
            'url': 'https://www.youtube.com/watch?v=MURua52_YPg',
            'note': 'cipher "encrypted" signature',
            'info_dict': {
                'id': 'MURua52_YPg',
                'ext': 'mp4',
                'upload_date': '20200418',
                'title': 'My Ordinary Life',
                'description': 'Provided to YouTube by Fandalism\n\nMy Ordinary Life · The Living Tombstone\n\nMy Ordinary Life\n\n℗ The Living Tombstone\n\nReleased on: 2017-11-23\n\nAuto-generated by YouTube.',
                'duration': 231,
                'uploader': 'The Living Tombstone - Topic',
                'uploader_id': 'UC5EH9egdct4dmAo3AHwzPBA',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC5EH9egdct4dmAo3AHwzPBA',
                'creator': 'The Living Tombstone',
                'track': 'My Ordinary Life',
                'artist': 'The Living Tombstone',
            }
        },
        {
            'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
            'note': 'Test VEVO video with age protection (#956)',
            'info_dict': {
                'id': '07FYdnEawAQ',
                'ext': 'mp4',
                'upload_date': '20130703',
                'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
                'description': 'md5:fc2016d319b50b68c5541c3fd66ffd16',
                'duration': 419,
                'uploader': 'justintimberlakeVEVO',
                'uploader_id': 'justintimberlakeVEVO',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
                'age_limit': 18,
            }
        },
        {
            'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
            'note': 'Use the first video ID in the URL',
            'info_dict': {
                'id': 'BaW_jenozKc',
                'ext': 'mp4',
                'title': 'youtube-dl test video "\'/\\ä↭𝕐',
                'uploader': 'Philipp Hagemeister',
                'uploader_id': 'phihag',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
                'upload_date': '20121002',
                '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 .',
                'categories': ['Science & Technology'],
                'tags': ['youtube-dl'],
                'duration': 10,
                'view_count': int,
                'like_count': int,
                'dislike_count': int,
            },
            'params': {
                'skip_download': True,
            },
        },
        # DASH manifest with encrypted signature
        {
            'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
            'info_dict': {
                'id': 'IB3lcPjvWLA',
                'ext': 'm4a',
                'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
                'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
                'duration': 244,
                'uploader': 'AfrojackVEVO',
                'uploader_id': 'AfrojackVEVO',
                'upload_date': '20131011',
            },
            'params': {
                'youtube_include_dash_manifest': True,
                'format': '141/bestaudio[ext=m4a]',
            },
        },
        # Normal age-gate video (No vevo, embed allowed)
        {
            'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
            'info_dict': {
                'id': 'HtVdAasjOgU',
                'ext': 'mp4',
                'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
                'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
                'duration': 142,
                'uploader': 'The Witcher',
                'uploader_id': 'WitcherGame',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
                'upload_date': '20140605',
                'age_limit': 18,
            },
        },
        # Age-gate video with encrypted signature
        {
            'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
            'info_dict': {
                'id': '6kLq3WMV1nU',
                'ext': 'mp4',
                'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
                'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
                'duration': 246,
                'uploader': 'LloydVEVO',
                'uploader_id': 'LloydVEVO',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
                'upload_date': '20110629',
                'age_limit': 18,
            },
        },
        # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
        # YouTube Red ad is not captured for creator
        {
            'url': '__2ABJjxzNo',
            'info_dict': {
                'id': '__2ABJjxzNo',
                'ext': 'mp4',
                'duration': 266,
                'upload_date': '20100430',
                'uploader_id': 'deadmau5',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
                'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
                'uploader': 'deadmau5',
                'title': 'Deadmau5 - Some Chords (HD)',
            },
            'expected_warnings': [
                'DASH manifest missing',
            ]
        },
        # Non-square pixels
        {
            'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
            'info_dict': {
                'id': '_b-2C3KPAM0',
                'ext': 'mp4',
                'stretched_ratio': 16 / 9.,
                'duration': 85,
                'upload_date': '20110310',
                'uploader_id': 'AllenMeow',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
                'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
                'uploader': '孫ᄋᄅ',
                'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
            },
        },
        {
            'url': 'https://vid.plus/FlRa-iH7PGw',
            'only_matching': True,
        },
        {
            'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
            'only_matching': True,
        },
        {
            # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
            # Also tests cut-off URL expansion in video description (see
            # https://github.com/ytdl-org/youtube-dl/issues/1892,
            # https://github.com/ytdl-org/youtube-dl/issues/8164)
            'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
            'info_dict': {
                'id': 'lsguqyKfVQg',
                'ext': 'mp4',
                'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
                'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
                'duration': 133,
                'upload_date': '20151119',
                'uploader_id': 'IronSoulElf',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
                'uploader': 'IronSoulElf',
                'creator': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
                'track': 'Dark Walk - Position Music',
                'artist': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
                'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
            'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
            'only_matching': True,
        },
        {
            # Video licensed under Creative Commons
            'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
            'info_dict': {
                'id': 'M4gD1WSo5mA',
                'ext': 'mp4',
                'title': 'md5:e41008789470fc2533a3252216f1c1d1',
                'description': 'md5:a677553cf0840649b731a3024aeff4cc',
                'duration': 721,
                'upload_date': '20150127',
                'uploader_id': 'BerkmanCenter',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
                'uploader': 'The Berkman Klein Center for Internet & Society',
                'license': 'Creative Commons Attribution license (reuse allowed)',
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            # Channel-like uploader_url
            'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
            'info_dict': {
                'id': 'eQcmzGIKrzg',
                'ext': 'mp4',
                'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
                'description': 'md5:dda0d780d5a6e120758d1711d062a867',
                'duration': 4060,
                'upload_date': '20151119',
                'uploader': 'Bernie Sanders',
                'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
                'license': 'Creative Commons Attribution license (reuse allowed)',
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
            'only_matching': True,
        },
        {
            # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
            'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
            'only_matching': True,
        },
        {
            # YouTube Red video with episode data
            'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
            'info_dict': {
                'id': 'iqKdEhx-dD4',
                'ext': 'mp4',
                'title': 'Isolation - Mind Field (Ep 1)',
                'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
                'duration': 2085,
                'upload_date': '20170118',
                'uploader': 'Vsauce',
                'uploader_id': 'Vsauce',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
                'series': 'Mind Field',
                'season_number': 1,
                'episode_number': 1,
            },
            'params': {
                'skip_download': True,
            },
            'expected_warnings': [
                'Skipping DASH manifest',
            ],
        },
        {
            'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
            'only_matching': True,
        },
        {
            'url': 'https://invidio.us/watch?v=BaW_jenozKc',
            'only_matching': True,
        },
        {
            # Youtube Music Auto-generated description
            'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
            'info_dict': {
                'id': 'MgNrAu2pzNs',
                'ext': 'mp4',
                'title': 'Voyeur Girl',
                'description': 'md5:7ae382a65843d6df2685993e90a8628f',
                'upload_date': '20190312',
                'uploader': 'Stephen - Topic',
                'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
                'artist': 'Stephen',
                'track': 'Voyeur Girl',
                'album': 'it\'s too much love to know my dear',
                'release_date': '20190313',
                'release_year': 2019,
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            # Youtube Music Auto-generated description
            # Retrieve 'artist' field from 'Artist:' in video description
            # when it is present on youtube music video
            'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
            'info_dict': {
                'id': 'k0jLE7tTwjY',
                'ext': 'mp4',
                'title': 'Latch Feat. Sam Smith',
                'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
                'upload_date': '20150110',
                'uploader': 'Various Artists - Topic',
                'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
                'artist': 'Disclosure',
                'track': 'Latch Feat. Sam Smith',
                'album': 'Latch Featuring Sam Smith',
                'release_date': '20121008',
                'release_year': 2012,
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            # Youtube Music Auto-generated description
            # handle multiple artists on youtube music video
            'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
            'info_dict': {
                'id': '74qn0eJSjpA',
                'ext': 'mp4',
                'title': 'Eastside',
                'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
                'upload_date': '20180710',
                'uploader': 'Benny Blanco - Topic',
                'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
                'artist': 'benny blanco, Halsey, Khalid',
                'track': 'Eastside',
                'album': 'Eastside',
                'release_date': '20180713',
                'release_year': 2018,
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            # Youtube Music Auto-generated description
            # handle youtube music video with release_year and no release_date
            'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
            'info_dict': {
                'id': '-hcAI0g-f5M',
                'ext': 'mp4',
                'title': 'Put It On Me',
                'description': 'md5:f6422397c07c4c907c6638e1fee380a5',
                'upload_date': '20180426',
                'uploader': 'Matt Maeson - Topic',
                'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
                'artist': 'Matt Maeson',
                'track': 'Put It On Me',
                'album': 'The Hearse',
                'release_date': None,
                'release_year': 2018,
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            'url': 'https://www.youtubekids.com/watch?v=BnC-cpUCdns',
            'only_matching': True,
        },
        {
            # empty description results in an empty string
            'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
            'info_dict': {
                'id': 'x41yOUIvK2k',
                'ext': 'mp4',
                'title': 'IMG 3456',
                'description': '',
                'upload_date': '20170613',
                'uploader_id': 'ElevageOrVert',
                'uploader': 'ElevageOrVert',
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            'url': 'https://youtube.com/shorts/7awd-y_DTQY',
            'only_matching': True,
        },
        {
            'url': 'https://www.youtube.com/video/2NDLF-k2PwA',
            'only_matching': True,
        }
    ]

    _VALID_SIG_VALUE_RE = r'^AO[a-zA-Z0-9_-]+=*$'

    def __init__(self, *args, **kwargs):
        super(YoutubeIE, self).__init__(*args, **kwargs)
        self._player_cache = {}

    def report_video_info_webpage_download(self, video_id):
        """Report attempt to download video info webpage."""
        self.to_screen('%s: Downloading video info webpage' % video_id)

    def report_information_extraction(self, video_id):
        """Report attempt to extract video information."""
        self.to_screen('%s: Extracting video information' % video_id)

    def report_unavailable_format(self, video_id, format):
        """Report extracted video URL."""
        self.to_screen('%s: Format %s not available' % (video_id, format))

    def _signature_cache_id(self, example_sig):
        """ Return a string representation of a signature """
        return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))

    @classmethod
    def _extract_player_info(cls, player_url):
        for player_re in cls._PLAYER_INFO_RE:
            id_m = re.search(player_re, player_url)
            if id_m:
                break
        else:
            raise ExtractorError('Cannot identify player %r' % player_url)
        return id_m.group('id')

    def _extract_signature_function(self, video_id, player_url, example_sig):
        player_id = self._extract_player_info(player_url)

        # Read from filesystem cache
        cache_spec = self._downloader.cache.load('youtube-sigfuncs', player_id)
        if cache_spec is not None:
            return cache_spec

        if not player_url.startswith('http'):
            player_url = 'https://www.youtube.com' + player_url
        download_note = (
            'Downloading player %s' % player_url
            if self._downloader.params.get('verbose') else
            'Downloading js player %s' % player_id
        )
        code = self._download_webpage(
            player_url, video_id,
            note=download_note,
            errnote='Download of js player %s failed' % player_url)
        res = self._parse_sig_js(code)

        self._downloader.cache.store('youtube-sigfuncs', player_id, res)
        return res

    def _parse_sig_js(self, js_player):
        shit_parser = re.search(r'[a-z]\=a\.split\((?:""|\'\')\);(([a-zA-Z_][a-zA-Z\d_]+).*);return a\.join', js_player)
        if not shit_parser:
            raise ExtractorError('Signature decryption code not found')
        func, obfuscated_name = shit_parser.group(1, 2)
        obfuscated_func = re.search(r'%s\s*=\s*{([\s\w(){}[\].,:;=%s"\']*?})};' % (re.escape(obfuscated_name), '%'),
                                    js_player)
        if not obfuscated_func:
            raise ExtractorError('Signature decrypting deobfuscated functions not found')
        obfuscated_stack = obfuscated_func.group(1)
        obf_map = {}
        for obffun in re.finditer(r'(?P<kp>["\'`]?)([a-zA-Z_][a-zA-Z\d_]+)(?P=kp):function\(a(?:,b)?\){(.*?)}', obfuscated_stack):
            obfname, obfval = obffun.group(2, 3)
            if 'splice' in obfval:
                obf_map[obfname] = 'splice'
            elif 'reverse' in obfval:
                obf_map[obfname] = 'reverse'
            elif 'var' in obfval and 'length' in obfval:
                obf_map[obfname] = 'mess'