import threading
import time
import traceback
-import urllib.error
import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from .openload import PhantomJSwrapper
from ..compat import functools
from ..jsinterp import JSInterpreter
+from ..networking.exceptions import HTTPError, network_exceptions
from ..utils import (
NO_DEFAULT,
ExtractorError,
join_nonempty,
js_to_json,
mimetype2ext,
- network_exceptions,
orderedSet,
parse_codecs,
parse_count,
variadic,
)
-
STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
# any clients starting with _ cannot be explicitly requested by the user
INNERTUBE_CLIENTS = {
THIRD_PARTY = {
'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
}
- BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
+ BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
priority = qualities(BASE_CLIENTS[::-1])
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
AVAILABILITY_PREMIUM = enum.auto()
AVAILABILITY_SUBSCRIPTION = enum.auto()
LIVE_NOW = enum.auto()
+ VERIFIED = enum.auto()
class YoutubeBaseInfoExtractor(InfoExtractor):
_IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
+ _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
+ _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
+
+ def ucid_or_none(self, ucid):
+ return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
+
+ def handle_or_none(self, handle):
+ return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
+
+ def handle_from_url(self, url):
+ return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
+ url, 'channel handle', default=None)
+
+ def ucid_from_url(self, url):
+ return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
+ url, 'channel id', default=None)
+
@functools.cached_property
def _preferred_lang(self):
"""
cookies = self._get_cookies('https://www.youtube.com/')
if cookies.get('__Secure-3PSID'):
return
- consent_id = None
- consent = cookies.get('CONSENT')
- if consent:
- if 'YES' in consent.value:
- return
- consent_id = self._search_regex(
- r'PENDING\+(\d+)', consent.value, 'consent', default=None)
- if not consent_id:
- consent_id = random.randint(100, 999)
- self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
+ socs = cookies.get('SOCS')
+ if socs and not socs.value.startswith('CAA'): # not consented
+ return
+ self._set_cookie('.youtube.com', 'SOCS', 'CAI', secure=True) # accept all (required for mixes)
def _initialize_pref(self):
cookies = self._get_cookies('https://www.youtube.com/')
def _extract_and_report_alerts(self, data, *args, **kwargs):
return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
- def _extract_badges(self, renderer: dict):
- privacy_icon_map = {
+ def _extract_badges(self, badge_list: list):
+ """
+ Extract known BadgeType's from a list of badge renderers.
+ @returns [{'type': BadgeType}]
+ """
+ icon_type_map = {
'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
- 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
+ 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC,
+ 'CHECK_CIRCLE_THICK': BadgeType.VERIFIED,
+ 'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED,
+ 'CHECK': BadgeType.VERIFIED,
}
badge_style_map = {
'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
- 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
+ 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW,
+ 'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED,
+ 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED,
}
label_map = {
'private': BadgeType.AVAILABILITY_PRIVATE,
'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
'live': BadgeType.LIVE_NOW,
- 'premium': BadgeType.AVAILABILITY_PREMIUM
+ 'premium': BadgeType.AVAILABILITY_PREMIUM,
+ 'verified': BadgeType.VERIFIED,
+ 'official artist channel': BadgeType.VERIFIED,
}
badges = []
- for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')):
+ for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))):
badge_type = (
- privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
+ icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
or badge_style_map.get(traverse_obj(badge, 'style'))
)
if badge_type:
continue
# fallback, won't work in some languages
- label = traverse_obj(badge, 'label', expected_type=str, default='')
+ label = traverse_obj(
+ badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='')
for match, label_badge_type in label_map.items():
if match in label.lower():
- badges.append({'type': badge_type})
- continue
+ badges.append({'type': label_badge_type})
+ break
return badges
def extract_relative_time(relative_time_text):
"""
Extracts a relative time from string and converts to dt object
- e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
+ e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago'
"""
- mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
+
+ # XXX: this could be moved to a general function in utils/_utils.py
+ # The relative time text strings are roughly the same as what
+ # Javascript's Intl.RelativeTimeFormat function generates.
+ # See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat
+ mobj = re.search(
+ r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>sec(?:ond)?|s|min(?:ute)?|h(?:our|r)?|d(?:ay)?|w(?:eek|k)?|mo(?:nth)?|y(?:ear|r)?)s?\s*ago',
+ relative_time_text)
if mobj:
start = mobj.group('start')
if start:
def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
default_client='web'):
- for retry in self.RetryManager():
+ raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE))
+ # Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal.
+ icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete))
+ icd_rm = next(icd_retries)
+ main_retries = iter(self.RetryManager())
+ main_rm = next(main_retries)
+ # Manual retry loop for multiple RetryManagers
+ # The proper RetryManager MUST be advanced after an error
+ # and it's result MUST be checked if the manager is non fatal
+ while True:
try:
response = self._call_api(
ep=ep, fatal=True, headers=headers,
except ExtractorError as e:
if not isinstance(e.cause, network_exceptions):
return self._error_or_warning(e, fatal=fatal)
- elif not isinstance(e.cause, urllib.error.HTTPError):
- retry.error = e
+ elif not isinstance(e.cause, HTTPError):
+ main_rm.error = e
+ next(main_retries)
continue
- first_bytes = e.cause.read(512)
+ first_bytes = e.cause.response.read(512)
if not is_html(first_bytes):
yt_error = try_get(
self._parse_json(
- self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
+ self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
lambda x: x['error']['message'], str)
if yt_error:
self._report_alerts([('ERROR', yt_error)], fatal=False)
# Downloading page may result in intermittent 5xx HTTP error
- # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
+ # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
# We also want to catch all other network exceptions since errors in later pages can be troublesome
# See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
- if e.cause.code not in (403, 429):
- retry.error = e
+ if e.cause.status not in (403, 429):
+ main_rm.error = e
+ next(main_retries)
continue
return self._error_or_warning(e, fatal=fatal)
try:
self._extract_and_report_alerts(response, only_once=True)
except ExtractorError as e:
- # YouTube servers may return errors we want to retry on in a 200 OK response
+ # YouTube's servers may return errors we want to retry on in a 200 OK response
# See: https://github.com/yt-dlp/yt-dlp/issues/839
if 'unknown error' in e.msg.lower():
- retry.error = e
+ main_rm.error = e
+ next(main_retries)
continue
return self._error_or_warning(e, fatal=fatal)
# Youtube sometimes sends incomplete data
# See: https://github.com/ytdl-org/youtube-dl/issues/28194
if not traverse_obj(response, *variadic(check_get_keys)):
- retry.error = ExtractorError('Incomplete data received', expected=True)
+ icd_rm.error = ExtractorError('Incomplete data received', expected=True)
+ should_retry = next(icd_retries, None)
+ if not should_retry:
+ return None
continue
return response
if not channel_id:
channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
+ channel_id = self.ucid_or_none(channel_id)
+
overlay_style = traverse_obj(
renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
get_all=False, expected_type=str)
- badges = self._extract_badges(renderer)
-
+ badges = self._extract_badges(traverse_obj(renderer, 'badges'))
+ owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
expected_type=str)) or ''
else self._get_count({'simpleText': view_count_text}))
view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
+ channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
+ or self._get_text(reel_header_renderer, 'channelTitleText'))
+
+ channel_handle = traverse_obj(renderer, (
+ 'shortBylineText', 'runs', ..., 'navigationEndpoint',
+ (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
+ expected_type=self.handle_from_url, get_all=False)
return {
'_type': 'url',
'ie_key': YoutubeIE.ie_key(),
'description': description,
'duration': duration,
'channel_id': channel_id,
- 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
- or self._get_text(reel_header_renderer, 'channelTitleText')),
+ 'channel': channel,
'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
+ 'uploader': channel,
+ 'uploader_id': channel_handle,
+ 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
'timestamp': (self._parse_time_text(time_text)
if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
view_count_field: view_count,
- 'live_status': live_status
+ 'live_status': live_status,
+ 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
}
'id': 'BaW_jenozKc',
'ext': 'mp4',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
- 'uploader': 'Philipp Hagemeister',
- 'uploader_id': 'phihag',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
'channel': 'Philipp Hagemeister',
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
'start_time': 1,
'end_time': 9,
'comment_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Philipp Hagemeister',
+ 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
+ 'uploader_id': '@PhilippHagemeister',
+ 'heatmap': 'count:100',
}
},
{
'upload_date': '20120608',
'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
- 'uploader': 'SET India',
- 'uploader_id': 'setindia',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
'age_limit': 18,
},
'skip': 'Private video',
'id': 'BaW_jenozKc',
'ext': 'mp4',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
- 'uploader': 'Philipp Hagemeister',
- 'uploader_id': 'phihag',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
'channel': 'Philipp Hagemeister',
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
'live_status': 'not_live',
'age_limit': 0,
'comment_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Philipp Hagemeister',
+ 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
+ 'uploader_id': '@PhilippHagemeister',
+ 'heatmap': 'count:100',
},
'params': {
'skip_download': True,
'id': 'a9LDPn-MO4I',
'ext': 'm4a',
'upload_date': '20121002',
- 'uploader_id': '8KVIDEO',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
'description': '',
- 'uploader': '8KVIDEO',
'title': 'UHDTV TEST 8K VIDEO.mp4'
},
'params': {
'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
'duration': 244,
- 'uploader': 'AfrojackVEVO',
- 'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
'abr': 129.495,
'like_count': int,
'live_status': 'not_live',
'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
'channel': 'Afrojack',
- 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
'tags': 'count:19',
'availability': 'public',
'categories': ['Music'],
'age_limit': 0,
'alt_title': 'The Spark',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Afrojack',
+ 'uploader_url': 'https://www.youtube.com/@Afrojack',
+ 'uploader_id': '@Afrojack',
},
'params': {
'youtube_include_dash_manifest': True,
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
'duration': 142,
- 'uploader': 'The Witcher',
- 'uploader_id': 'WitcherGame',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
'upload_date': '20140605',
'age_limit': 18,
'categories': ['Gaming'],
'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
'playable_in_embed': True,
'view_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'The Witcher',
+ 'uploader_url': 'https://www.youtube.com/@thewitcher',
+ 'uploader_id': '@thewitcher',
+ 'comment_count': int,
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
},
},
{
'title': 'Godzilla 2 (Official Video)',
'description': 'md5:bf77e03fcae5529475e500129b05668a',
'upload_date': '20200408',
- 'uploader_id': 'FlyingKitty900',
- 'uploader': 'FlyingKitty',
'age_limit': 18,
'availability': 'needs_auth',
'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
- 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
'channel': 'FlyingKitty',
'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
'view_count': int,
'like_count': int,
'duration': 177,
'playable_in_embed': True,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'FlyingKitty',
+ 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
+ 'uploader_id': '@FlyingKitty900',
+ 'comment_count': int,
+ 'channel_is_verified': True,
},
},
{
'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
'ext': 'mp4',
'upload_date': '20191228',
- 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
- 'uploader': 'Projekt Melody',
'description': 'md5:17eccca93a786d51bc67646756894066',
'age_limit': 18,
'like_count': int,
'availability': 'needs_auth',
- 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
'view_count': int,
'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
'duration': 106,
'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
'comment_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Projekt Melody',
+ 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
+ 'uploader_id': '@ProjektMelody',
},
},
{
'id': 'MeJVWBSsPAY',
'ext': 'mp4',
'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
- 'uploader': 'Herr Lurik',
- 'uploader_id': 'st3in234',
'description': 'Fan Video. Music & Lyrics by OOMPH!.',
'upload_date': '20130730',
'track': 'Such mich find mich',
'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
'categories': ['Music'],
'availability': 'public',
- 'uploader_url': 'http://www.youtube.com/user/st3in234',
'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
'live_status': 'not_live',
'artist': 'OOMPH!',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Herr Lurik',
+ 'uploader_url': 'https://www.youtube.com/@HerrLurik',
+ 'uploader_id': '@HerrLurik',
},
},
{
'ext': 'mp4',
'duration': 266,
'upload_date': '20100430',
- 'uploader_id': 'deadmau5',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
'creator': 'deadmau5',
'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
- 'uploader': 'deadmau5',
'title': 'Deadmau5 - Some Chords (HD)',
'alt_title': 'Some Chords',
'availability': 'public',
'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
'categories': ['Music'],
'album': 'Some Chords',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'deadmau5',
+ 'uploader_url': 'https://www.youtube.com/@deadmau5',
+ 'uploader_id': '@deadmau5',
},
'expected_warnings': [
'DASH manifest missing',
'ext': 'mp4',
'duration': 6085,
'upload_date': '20150827',
- 'uploader_id': 'olympic',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
- 'uploader': 'Olympics',
'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
'like_count': int,
'release_timestamp': 1343767800,
'live_status': 'was_live',
'view_count': int,
'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Olympics',
+ 'uploader_url': 'https://www.youtube.com/@Olympics',
+ 'uploader_id': '@Olympics',
+ 'channel_is_verified': True,
},
'params': {
'skip_download': 'requires avconv',
'stretched_ratio': 16 / 9.,
'duration': 85,
'upload_date': '20110310',
- 'uploader_id': 'AllenMeow',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
- 'uploader': '孫ᄋᄅ',
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
'playable_in_embed': True,
'channel': '孫ᄋᄅ',
'live_status': 'not_live',
'availability': 'unlisted',
'comment_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': '孫ᄋᄅ',
+ 'uploader_url': 'https://www.youtube.com/@AllenMeow',
+ 'uploader_id': '@AllenMeow',
},
},
# url_encoded_fmt_stream_map is empty string
'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
'description': '',
'upload_date': '20150404',
- 'uploader_id': 'spbelect',
- 'uploader': 'Наблюдатели Петербурга',
},
'params': {
'skip_download': 'requires avconv',
'description': 'md5:116377fd2963b81ec4ce64b542173306',
'duration': 220,
'upload_date': '20150625',
- 'uploader_id': 'dorappi2000',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
- 'uploader': 'dorappi2000',
'formats': 'mincount:31',
},
'skip': 'not actual anymore',
'id': 'CsmdDsKjzN8',
'ext': 'mp4',
'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
- 'uploader': 'Airtek',
'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
- 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
},
'params': {
},
{
# Multifeed videos (multiple cameras), URL can be of any Camera
+ # TODO: fix multifeed titles
'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
'info_dict': {
'id': 'zaPI8MvL8pg',
'id': 'j5yGuxZ8lLU',
'ext': 'mp4',
'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
- 'uploader': 'WiiLikeToPlay',
'description': 'md5:563ccbc698b39298481ca3c571169519',
- 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
'duration': 10120,
'channel_follower_count': int,
'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
'availability': 'public',
'playable_in_embed': True,
'upload_date': '20131105',
- 'uploader_id': 'WiiRikeToPray',
'categories': ['Gaming'],
'live_status': 'was_live',
'tags': 'count:24',
'channel': 'WiiLikeToPlay',
'view_count': int,
'release_date': '20131106',
+ 'uploader': 'WiiLikeToPlay',
+ 'uploader_id': '@WLTP',
+ 'uploader_url': 'https://www.youtube.com/@WLTP',
},
}, {
'info_dict': {
'id': 'zaPI8MvL8pg',
'ext': 'mp4',
'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
- 'uploader_id': 'WiiRikeToPray',
'availability': 'public',
'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
'channel': 'WiiLikeToPlay',
- 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
'channel_follower_count': int,
'description': 'md5:563ccbc698b39298481ca3c571169519',
'duration': 10108,
'like_count': int,
'tags': 'count:24',
'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
- 'uploader': 'WiiLikeToPlay',
'release_timestamp': 1383701915,
'comment_count': int,
'upload_date': '20131105',
'live_status': 'was_live',
'categories': ['Gaming'],
'view_count': int,
+ 'uploader': 'WiiLikeToPlay',
+ 'uploader_id': '@WLTP',
+ 'uploader_url': 'https://www.youtube.com/@WLTP',
},
}, {
'info_dict': {
'playable_in_embed': True,
'upload_date': '20131105',
'description': 'md5:563ccbc698b39298481ca3c571169519',
- 'uploader_id': 'WiiRikeToPray',
- 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
'channel_follower_count': int,
'tags': 'count:24',
'release_date': '20131106',
- 'uploader': 'WiiLikeToPlay',
'comment_count': int,
'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
'channel': 'WiiLikeToPlay',
'age_limit': 0,
'duration': 10128,
'view_count': int,
+ 'uploader': 'WiiLikeToPlay',
+ 'uploader_id': '@WLTP',
+ 'uploader_url': 'https://www.youtube.com/@WLTP',
},
}],
'params': {'skip_download': True},
'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;\nDaniel Law Heath and Aaron Kaplan',
'track': 'Dark Walk',
'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
'description': 'md5:ee18a25c350637c8faff806845bddee9',
'upload_date': '20151107',
- 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
- 'uploader': 'CH GAMER DROID',
},
'params': {
'skip_download': True,
'description': 'md5:a677553cf0840649b731a3024aeff4cc',
'duration': 721,
'upload_date': '20150128',
- '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)',
'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
'live_status': 'not_live',
'playable_in_embed': True,
- 'comment_count': int,
'channel_follower_count': int,
'chapters': list,
+ 'uploader': 'The Berkman Klein Center for Internet & Society',
+ 'uploader_id': '@BKCHarvard',
+ 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
},
'params': {
'skip_download': True,
},
},
{
- # Channel-like uploader_url
'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
'info_dict': {
'id': 'eQcmzGIKrzg',
'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
'duration': 4060,
'upload_date': '20151120',
- 'uploader': 'Bernie Sanders',
- 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
'license': 'Creative Commons Attribution license (reuse allowed)',
'playable_in_embed': True,
'tags': 'count:12',
'comment_count': int,
'channel_follower_count': int,
'chapters': list,
+ 'uploader': 'Bernie Sanders',
+ 'uploader_url': 'https://www.youtube.com/@BernieSanders',
+ 'uploader_id': '@BernieSanders',
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
},
'params': {
'skip_download': True,
'title': 'Piku - Trailer',
'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
'upload_date': '20150811',
- 'uploader': 'FlixMatrix',
- 'uploader_id': 'FlixMatrixKaravan',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
'license': 'Standard YouTube License',
},
'params': {
'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
'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,
'like_count': int,
'playable_in_embed': True,
'live_status': 'not_live',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Vsauce',
+ 'uploader_url': 'https://www.youtube.com/@Vsauce',
+ 'uploader_id': '@Vsauce',
+ 'comment_count': int,
+ 'channel_is_verified': True,
},
'params': {
'skip_download': True,
'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
'duration': 965,
'upload_date': '20140124',
- 'uploader': 'New Century Foundation',
- 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
},
'params': {
'skip_download': True,
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'duration': 433,
'upload_date': '20130923',
- 'uploader': 'Amelia Putri Harwita',
- 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
'formats': 'maxcount:10',
},
'params': {
},
{
# Youtube Music Auto-generated description
+ # TODO: fix metadata extraction
'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
'info_dict': {
'id': 'MgNrAu2pzNs',
'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_year': 2019,
'alt_title': 'Voyeur Girl',
'view_count': int,
- 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
'playable_in_embed': True,
'like_count': int,
'categories': ['Music'],
'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
- 'channel': 'Stephen',
+ 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
+ 'uploader': 'Stephen',
'availability': 'public',
'creator': 'Stephen',
'duration': 169,
'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
'description': 'md5:bf577a41da97918e94fa9798d9228825',
'upload_date': '20090125',
- 'uploader': 'Prochorowka',
- 'uploader_id': 'Prochorowka',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
'artist': 'Panjabi MC',
'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
'album': 'Beware of the Boys (Mundian To Bach Ke)',
'title': 'IMG 3456',
'description': '',
'upload_date': '20170613',
- 'uploader_id': 'ElevageOrVert',
- 'uploader': 'ElevageOrVert',
'view_count': int,
'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
- 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
'like_count': int,
'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
'tags': [],
'duration': 7,
'playable_in_embed': True,
'live_status': 'not_live',
- 'channel': 'ElevageOrVert',
- 'channel_follower_count': int
+ 'channel': 'l\'Or Vert asbl',
+ 'channel_follower_count': int,
+ 'uploader': 'l\'Or Vert asbl',
+ 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
+ 'uploader_id': '@ElevageOrVert',
},
'params': {
'skip_download': True,
'title': 'Part 77 Sort a list of simple types in c#',
'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
'upload_date': '20130831',
- 'uploader_id': 'kudvenkat',
- 'uploader': 'kudvenkat',
'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
'like_count': int,
- 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
'live_status': 'not_live',
'categories': ['Education'],
'comment_count': int,
'channel_follower_count': int,
'chapters': list,
+ 'uploader': 'kudvenkat',
+ 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
+ 'uploader_id': '@Csharp-video-tutorialsBlogspot',
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
},
'params': {
'skip_download': True,
'title': 'Burn Out',
'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
'upload_date': '20141120',
- 'uploader': 'The Cinematic Orchestra - Topic',
- 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
'artist': 'The Cinematic Orchestra',
'track': 'Burn Out',
'album': 'Every Day',
'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
'categories': ['Music'],
'playable_in_embed': True,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'The Cinematic Orchestra',
+ 'comment_count': int,
},
'params': {
'skip_download': True,
'ext': 'mp4',
'title': 'San Diego teen commits suicide after bullying over embarrassing video',
'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
- 'uploader': 'CBS Mornings',
- 'uploader_id': 'CBSThisMorning',
'upload_date': '20140716',
'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
'duration': 170,
'categories': ['News & Politics'],
- 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
'view_count': int,
'channel': 'CBS Mornings',
'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
'like_count': int,
'live_status': 'not_live',
'playable_in_embed': True,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'CBS Mornings',
+ 'uploader_url': 'https://www.youtube.com/@CBSMornings',
+ 'uploader_id': '@CBSMornings',
+ 'comment_count': int,
+ 'channel_is_verified': True,
}
},
{
'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
'upload_date': '20201120',
- 'uploader': 'Walk around Japan',
- 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
'duration': 1456,
'categories': ['Travel & Events'],
'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
'live_status': 'not_live',
'playable_in_embed': True,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Walk around Japan',
+ 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
+ 'uploader_id': '@walkaroundjapan7124',
},
'params': {
'skip_download': True,
'ext': '3gp',
'upload_date': '20210624',
'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
- 'uploader': 'colinfurze',
- 'uploader_id': 'colinfurze',
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
'description': 'md5:5d5991195d599b56cd0c4148907eec50',
'duration': 596,
'categories': ['Entertainment'],
- 'uploader_url': 'http://www.youtube.com/user/colinfurze',
'view_count': int,
'channel': 'colinfurze',
'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
'playable_in_embed': True,
'channel_follower_count': int,
'chapters': list,
+ 'uploader': 'colinfurze',
+ 'uploader_url': 'https://www.youtube.com/@colinfurze',
+ 'uploader_id': '@colinfurze',
+ 'comment_count': int,
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
},
'params': {
'format': '17', # 3gp format available on android
'ext': 'mhtml',
'format_id': 'sb0',
'title': 'Your Brain is Plastic',
- 'uploader_id': 'scishow',
'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
'upload_date': '20140324',
- 'uploader': 'SciShow',
'like_count': int,
'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
'playable_in_embed': True,
'tags': 'count:12',
- 'uploader_url': 'http://www.youtube.com/user/scishow',
'availability': 'public',
'channel': 'SciShow',
'live_status': 'not_live',
'age_limit': 0,
'channel_follower_count': int,
'chapters': list,
+ 'uploader': 'SciShow',
+ 'uploader_url': 'https://www.youtube.com/@SciShow',
+ 'uploader_id': '@SciShow',
+ 'comment_count': int,
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
}, 'params': {'format': 'mhtml', 'skip_download': True}
}, {
# Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
'ext': 'mp4',
'title': 'The NP that test your phone performance 🙂',
'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
- 'uploader': 'Leon Nguyen',
- 'uploader_id': 'VNSXIII',
- 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
'duration': 21,
'channel': 'Leon Nguyen',
'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
'comment_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Leon Nguyen',
+ 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
+ 'uploader_id': '@LeonNguyen',
+ 'heatmap': 'count:100',
}
}, {
# Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
'ext': 'mp4',
'title': 'The NP that test your phone performance 🙂',
'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
- 'uploader': 'Leon Nguyen',
- 'uploader_id': 'VNSXIII',
- 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
'duration': 21,
'channel': 'Leon Nguyen',
'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
'comment_count': int,
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Leon Nguyen',
+ 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
+ 'uploader_id': '@LeonNguyen',
+ 'heatmap': 'count:100',
},
'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
}, {
'id': 'mzZzzBU6lrM',
'ext': 'mp4',
'title': 'I Met GeorgeNotFound In Real Life...',
- 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
- 'uploader': 'Quackity',
- 'uploader_id': 'QuackityHQ',
- 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
+ 'description': 'md5:978296ec9783a031738b684d4ebf302d',
'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
'duration': 955,
'availability': 'public',
'channel': 'Quackity',
'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader': 'Quackity',
+ 'uploader_id': '@Quackity',
+ 'uploader_url': 'https://www.youtube.com/@Quackity',
+ 'comment_count': int,
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
}
},
{ # continuous livestream. Microformat upload date should be preferred.
'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
'live_status': 'is_live',
'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
- 'uploader': '阿鲍Abao',
- 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
'channel': 'Abao in Tokyo',
'channel_follower_count': int,
'release_date': '20211127',
'tags': 'count:39',
'categories': ['People & Blogs'],
'like_count': int,
- 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
'view_count': int,
'playable_in_embed': True,
'description': 'md5:2ef1d002cad520f65825346e2084e49d',
'concurrent_view_count': int,
+ 'uploader': 'Abao in Tokyo',
+ 'uploader_url': 'https://www.youtube.com/@abaointokyo',
+ 'uploader_id': '@abaointokyo',
},
'params': {'skip_download': True}
- }, {
- # Story. Requires specific player params to work.
- 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
- 'info_dict': {
- 'id': 'vv8qTUWmulI',
- 'ext': 'mp4',
- 'availability': 'unlisted',
- 'view_count': int,
- 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
- 'upload_date': '20220526',
- 'categories': ['Education'],
- 'title': 'Story',
- 'channel': 'IT\'S HISTORY',
- 'description': '',
- 'uploader_id': 'BlastfromthePast',
- 'duration': 12,
- 'uploader': 'IT\'S HISTORY',
- 'playable_in_embed': True,
- 'age_limit': 0,
- 'live_status': 'not_live',
- 'tags': [],
- 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
- 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
- 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
- },
- 'skip': 'stories get removed after some period of time',
}, {
'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
'info_dict': {
'upload_date': '20220323',
'like_count': int,
'availability': 'unlisted',
- 'channel': 'nao20010128nao',
- 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
+ 'channel': 'Lesmiscore',
+ 'thumbnail': r're:^https?://.*\.jpg',
'age_limit': 0,
- 'uploader': 'nao20010128nao',
- 'uploader_id': 'nao20010128nao',
'categories': ['Music'],
'view_count': int,
'description': '',
'channel_follower_count': int,
'duration': 6,
'tags': [],
- 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
+ 'uploader_id': '@lesmiscore',
+ 'uploader': 'Lesmiscore',
+ 'uploader_url': 'https://www.youtube.com/@lesmiscore',
}
}, {
# Prefer primary title+description language metadata by default
'like_count': int,
'playable_in_embed': True,
'availability': 'unlisted',
- 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
+ 'thumbnail': r're:^https?://.*\.jpg',
'age_limit': 0,
'duration': 5,
- 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
- 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'live_status': 'not_live',
'upload_date': '20220908',
'categories': ['People & Blogs'],
- 'uploader': 'cole-dlp-test-acc',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
+ 'uploader_url': 'https://www.youtube.com/@coletdjnz',
+ 'uploader_id': '@coletdjnz',
+ 'uploader': 'cole-dlp-test-acc',
},
'params': {'skip_download': True}
}, {
'live_status': 'not_live',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'upload_date': '20220728',
- 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
'view_count': int,
'categories': ['People & Blogs'],
- 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
+ 'thumbnail': r're:^https?://.*\.jpg',
'title': 'dlp test video title translated (fr)',
'availability': 'public',
- 'uploader': 'cole-dlp-test-acc',
'age_limit': 0,
'description': 'dlp test video description translated (fr)',
'playable_in_embed': True,
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
- 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
+ 'uploader_url': 'https://www.youtube.com/@coletdjnz',
+ 'uploader_id': '@coletdjnz',
+ 'uploader': 'cole-dlp-test-acc',
},
'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
'expected_warnings': [r'Preferring "fr" translated fields'],
'ext': 'mp4',
'categories': ['Entertainment'],
'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
- 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
'live_status': 'not_live',
'duration': 937,
'channel_follower_count': int,
'playable_in_embed': True,
'view_count': int,
'upload_date': '20221112',
- 'uploader': 'MrBeast',
- 'uploader_id': 'MrBeast6000',
'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
'age_limit': 0,
'availability': 'public',
'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
'like_count': int,
'tags': [],
+ 'uploader': 'MrBeast',
+ 'uploader_url': 'https://www.youtube.com/@MrBeast',
+ 'uploader_id': '@MrBeast',
+ 'comment_count': int,
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
},
'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
}, {
'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
'info_dict': {
'id': 'Tq92D6wQ1mg',
- 'ext': 'weba',
+ 'ext': 'webm',
'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
'channel_follower_count': int,
'description': 'md5:17eccca93a786d51bc67646756894066',
'upload_date': '20191228',
- 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
'playable_in_embed': True,
'like_count': int,
'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
'age_limit': 18,
'channel': 'Projekt Melody',
- 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
'view_count': int,
'availability': 'needs_auth',
'comment_count': int,
'live_status': 'not_live',
- 'uploader': 'Projekt Melody',
'duration': 106,
+ 'uploader': 'Projekt Melody',
+ 'uploader_id': '@ProjektMelody',
+ 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
},
'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
},
'id': 'qVv6vCqciTM',
'ext': 'mp4',
'age_limit': 0,
- 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
'comment_count': int,
'chapters': 'count:13',
'upload_date': '20221223',
'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
- 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
'like_count': int,
'release_date': '20221223',
'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
'channel': 'さなちゃんねる',
'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
'uploader': 'さなちゃんねる',
+ 'uploader_url': 'https://www.youtube.com/@sana_natori',
+ 'uploader_id': '@sana_natori',
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
+ },
+ },
+ {
+ # Fallbacks when webpage and web client is unavailable
+ 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
+ 'info_dict': {
+ 'id': 'wSSmNUl9Snw',
+ 'ext': 'mp4',
+ # 'categories': ['Science & Technology'],
+ 'view_count': int,
+ 'chapters': 'count:2',
+ 'channel': 'Scott Manley',
+ 'like_count': int,
+ 'age_limit': 0,
+ # 'availability': 'public',
+ 'channel_follower_count': int,
+ 'live_status': 'not_live',
+ 'upload_date': '20170831',
+ 'duration': 682,
+ 'tags': 'count:8',
+ 'uploader_url': 'https://www.youtube.com/@scottmanley',
+ 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
+ 'uploader': 'Scott Manley',
+ 'uploader_id': '@scottmanley',
+ 'title': 'The Computer Hack That Saved Apollo 14',
+ 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
+ 'thumbnail': r're:^https?://.*\.webp',
+ 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
+ 'playable_in_embed': True,
+ 'comment_count': int,
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
+ },
+ 'params': {
+ 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
},
},
]
'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
'upload_date': '20080526',
'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
- 'uploader': 'Christopher Sykes',
- 'uploader_id': 'ChristopherJSykes',
'age_limit': 0,
'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
'view_count': int,
'categories': ['Science & Technology'],
'channel_follower_count': int,
- 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
+ 'uploader': 'Christopher Sykes',
+ 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
+ 'uploader_id': '@ChristopherSykesDocumentaries',
+ 'heatmap': 'count:100',
},
'params': {
'skip_download': True,
# Obtain from MPD's maximum seq value
old_mpd_url = mpd_url
last_error = ctx.pop('last_error', None)
- expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
+ expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
or (mpd_url, stream_number, False))
if not refresh_sequence:
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
- 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}\(a,\d+\)',
- 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\(\s*""\s*\)',
+ 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}\(a,\d+\))?',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
# Obsolete patterns
- r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
- r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
- r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
jscode, 'Initial JS player signature function name', group='sig')
return funcname
return json.loads(js_to_json(self._search_regex(
- rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
+ rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
def _extract_n_function_code(self, video_id, player_url):
chapter_time, chapter_title, duration)
for contents in content_list)), [])
+ def _extract_heatmap(self, data):
+ return traverse_obj(data, (
+ 'frameworkUpdates', 'entityBatchUpdate', 'mutations',
+ lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
+ 'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
+ 'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
+ 'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
+ 'value': ('intensityScoreNormalized', {float_or_none}),
+ })) or None
+
def _extract_comment(self, comment_renderer, parent=None):
comment_id = comment_renderer.get('commentId')
if not comment_id:
return
- text = self._get_text(comment_renderer, 'contentText')
+ info = {
+ 'id': comment_id,
+ 'text': self._get_text(comment_renderer, 'contentText'),
+ 'like_count': self._get_count(comment_renderer, 'voteCount'),
+ 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
+ 'author': self._get_text(comment_renderer, 'authorText'),
+ 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
+ 'parent': parent or 'root',
+ }
# Timestamp is an estimate calculated from the current time and time_text
time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
timestamp = self._parse_time_text(time_text)
- author = self._get_text(comment_renderer, 'authorText')
- author_id = try_get(comment_renderer,
- lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
+ info.update({
+ # FIXME: non-standard, but we need a way of showing that it is an estimate.
+ '_time_text': time_text,
+ 'timestamp': timestamp,
+ })
- votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
- lambda x: x['likeCount']), str)) or 0
- author_thumbnail = try_get(comment_renderer,
- lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
+ info['author_url'] = urljoin(
+ 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
+ ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
+ expected_type=str, get_all=False))
- author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
- is_favorited = 'creatorHeart' in (try_get(
- comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
- return {
- 'id': comment_id,
- 'text': text,
- 'timestamp': timestamp,
- 'time_text': time_text,
- 'like_count': votes,
- 'is_favorited': is_favorited,
- 'author': author,
- 'author_id': author_id,
- 'author_thumbnail': author_thumbnail,
- 'author_is_uploader': author_is_uploader,
- 'parent': parent or 'root'
- }
+ author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
+ if author_is_uploader is not None:
+ info['author_is_uploader'] = author_is_uploader
+
+ comment_abr = traverse_obj(
+ comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
+ if comment_abr is not None:
+ info['is_favorited'] = 'creatorHeart' in comment_abr
+
+ badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
+ if self._has_badge(badges, BadgeType.VERIFIED):
+ info['author_is_verified'] = True
+
+ is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
+ if is_pinned:
+ info['is_pinned'] = True
+
+ return info
def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
expected_comment_count = self._get_count(
comments_header_renderer, 'countText', 'commentsCount')
- if expected_comment_count:
+ if expected_comment_count is not None:
tracker['est_total'] = expected_comment_count
self.to_screen(f'Downloading ~{expected_comment_count} comments')
comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
comment = self._extract_comment(comment_renderer, parent)
if not comment:
continue
+ comment_id = comment['id']
+ if comment.get('is_pinned'):
+ tracker['pinned_comment_ids'].add(comment_id)
# Sometimes YouTube may break and give us infinite looping comments.
# See: https://github.com/yt-dlp/yt-dlp/issues/6290
- if comment['id'] in tracker['seen_comment_ids']:
- self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
+ if comment_id in tracker['seen_comment_ids']:
+ if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
+ # Pinned comments may appear a second time in newest first sort
+ # See: https://github.com/yt-dlp/yt-dlp/issues/6712
+ continue
+ self.report_warning(
+ 'Detected YouTube comments looping. Stopping comment extraction '
+ f'{"for this thread" if parent else ""} as we probably cannot get any more.')
yield
else:
tracker['seen_comment_ids'].add(comment['id'])
if not tracker:
tracker = dict(
running_total=0,
- est_total=0,
+ est_total=None,
current_page_thread=0,
total_parent_comments=0,
total_reply_comments=0,
- seen_comment_ids=set())
+ seen_comment_ids=set(),
+ pinned_comment_ids=set()
+ )
# TODO: Deprecated
# YouTube comments have a max depth of 2
continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
is_forced_continuation = True
+ continuation_items_path = (
+ 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
for page_num in itertools.count(0):
if not continuation:
break
headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
- comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
+ comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
if page_num == 0:
if is_first_continuation:
note_prefix = 'Downloading comment section API JSON'
note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
' ' if parent else '', ' replies' if parent else '',
page_num, comment_prog_str)
+
+ # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
+ # Ignore check if YouTube says the comment count is 0.
+ check_get_keys = None
+ if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
+ check_get_keys = [[*continuation_items_path, ..., (
+ 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
try:
response = self._extract_response(
item_id=None, query=continuation,
ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
- check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
+ check_get_keys=check_get_keys)
except ExtractorError as e:
# Ignore incomplete data error for replies if retries didn't work.
# This is to allow any other parent comments and comment threads to be downloaded.
# See: https://github.com/yt-dlp/yt-dlp/issues/4669
- if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
- self.report_warning(
- 'Received incomplete data for a comment reply thread and retrying did not help. '
- 'Ignoring to let other comments be downloaded.')
- else:
- raise
+ if 'incomplete data' in str(e).lower() and parent:
+ if self.get_param('ignoreerrors') in (True, 'only_download'):
+ self.report_warning(
+ 'Received incomplete data for a comment reply thread and retrying did not help. '
+ 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
+ return
+ else:
+ raise ExtractorError(
+ 'Incomplete data received for comment reply thread. '
+ 'Pass --ignore-errors to ignore and allow rest of comments to download.',
+ expected=True)
+ raise
is_forced_continuation = False
- continuation_contents = traverse_obj(
- response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
-
continuation = None
- for continuation_section in continuation_contents:
- continuation_items = traverse_obj(
- continuation_section,
- (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
- get_all=False, expected_type=list) or []
+ for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
if is_first_continuation:
continuation = extract_header(continuation_items)
is_first_continuation = False
def _is_unplayable(player_response):
return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
- _STORY_PLAYER_PARAMS = '8AEB'
-
def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
yt_query = {
'videoId': video_id,
}
- if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
- yt_query['params'] = self._STORY_PLAYER_PARAMS
+ if _split_innertube_client(client)[0] == 'android':
+ yt_query['params'] = 'CgIQBg=='
+
+ pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
+ if pp_arg:
+ yt_query['params'] = pp_arg
yt_query.update(self._generate_player_context(sts))
return self._extract_response(
def _get_requested_clients(self, url, smuggled_data):
requested_clients = []
- default = ['android', 'web']
+ default = ['ios', 'android', 'web']
allowed_clients = sorted(
(client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
def _needs_live_processing(self, live_status, duration):
if (live_status == 'is_live' and self.get_param('live_from_start')
- or live_status == 'post_live' and (duration or 0) > 4 * 3600):
+ or live_status == 'post_live' and (duration or 0) > 2 * 3600):
return live_status
def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
])
streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
- all_formats = self._configuration_arg('include_duplicate_formats')
+ format_types = self._configuration_arg('formats')
+ all_formats = 'duplicate' in format_types
+ if self._configuration_arg('include_duplicate_formats'):
+ all_formats = True
+ self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
+ 'Use formats=duplicate extractor argument instead')
def build_fragments(f):
return LazyList({
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
+ name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
+ fps = int_or_none(fmt.get('fps')) or 0
dct = {
'asr': int_or_none(fmt.get('audioSampleRate')),
'filesize': int_or_none(fmt.get('contentLength')),
'format_note': join_nonempty(
join_nonempty(audio_track.get('displayName'),
language_preference > 0 and ' (default)', delim=''),
- fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
- fmt.get('isDrc') and 'DRC',
+ name, fmt.get('isDrc') and 'DRC',
try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
throttled and 'THROTTLED', is_damaged and 'DAMAGED',
(self.get_param('verbose') or all_formats) and client_name,
delim=', '),
# Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
- 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
- 'fps': int_or_none(fmt.get('fps')) or None,
+ 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
+ + (100 if 'Premium' in name else 0)),
+ 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
'audio_channels': fmt.get('audioChannels'),
'height': height,
'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
if single_stream and dct.get('ext'):
dct['container'] = dct['ext'] + '_dash'
- if dct['filesize']:
+ if (all_formats or 'dashy' in format_types) and dct['filesize']:
yield {
**dct,
'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
'protocol': 'http_dash_segments',
'fragments': build_fragments(dct),
}
- if not all_formats:
- continue
- dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
- yield dct
+ if all_formats or 'dashy' not in format_types:
+ dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
+ yield dct
needs_live_processing = self._needs_live_processing(live_status, duration)
- skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
+ skip_bad_formats = 'incomplete' not in format_types
+ if self._configuration_arg('include_incomplete_formats'):
+ skip_bad_formats = False
+ self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
+ 'Use formats=incomplete extractor argument instead')
skip_manifests = set(self._configuration_arg('skip'))
if (not self.get_param('youtube_include_hls_manifest', True)
skip_manifests.add('dash')
if self._configuration_arg('include_live_dash'):
self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
- 'Use include_incomplete_formats extractor argument instead')
+ 'Use formats=incomplete extractor argument instead')
elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
skip_manifests.add('dash')
elif itag:
f['format_id'] = itag
+ if f.get('source_preference') is None:
+ f['source_preference'] = -1
+
+ if itag in ('616', '235'):
+ f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
+ f['source_preference'] += 100
+
f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
if f['quality'] == -1 and f.get('height'):
f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
- if self.get_param('verbose'):
+ if self.get_param('verbose') or all_formats:
f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
+ if f.get('fps') and f['fps'] <= 1:
+ del f['fps']
+
+ if proto == 'hls' and f.get('has_drm'):
+ f['has_drm'] = 'maybe'
+ f['source_preference'] -= 5
return True
subtitles = {}
webpage = None
if 'webpage' not in self._configuration_arg('player_skip'):
query = {'bpctr': '9999999999', 'has_verified': '1'}
- if smuggled_data.get('is_story'):
- query['pp'] = self._STORY_PLAYER_PARAMS
+ pp = self._configuration_arg('player_params', [None], casesense=True)[0]
+ if pp:
+ query['pp'] = pp
webpage = self._download_webpage(
webpage_url, video_id, fatal=False, query=query)
else None)
streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
*formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
+ if all(f.get('has_drm') for f in formats):
+ # If there are no formats that definitely don't have DRM, all have DRM
+ for f in formats:
+ f['has_drm'] = True
return live_broadcast_details, live_status, streaming_data, formats, subtitles
self._downloader._sort_thumbnails(original_thumbnails)
category = get_first(microformats, 'category') or search_meta('genre')
- channel_id = str_or_none(
+ channel_id = self.ucid_or_none(str_or_none(
get_first(video_details, 'channelId')
or get_first(microformats, 'externalChannelId')
- or search_meta('channelId'))
+ or search_meta('channelId')))
owner_profile_url = get_first(microformats, 'ownerProfileUrl')
live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
for fmt in filter(is_bad_format, formats):
fmt['preference'] = (fmt.get('preference') or -1) - 10
- fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
+ fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
if needs_live_processing:
self._prepare_live_from_start_formats(
formats.extend(self._extract_storyboard(player_responses, duration))
+ channel_handle = self.handle_from_url(owner_profile_url)
+
info = {
'id': video_id,
'title': video_title,
# URL checking if user don't care about getting the best possible thumbnail
'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
'description': video_description,
- 'uploader': get_first(video_details, 'author'),
- 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
- 'uploader_url': owner_profile_url,
'channel_id': channel_id,
- 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
+ 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
'duration': duration,
'view_count': int_or_none(
get_first((video_details, microformats), (..., 'viewCount'))
continue
trans_code += f'-{lang_code}'
trans_name += format_field(lang_name, None, ' from %s')
- # Add an "-orig" label to the original language so that it can be distinguished.
- # The subs are returned without "-orig" as well for compatibility
if lang_code == f'a-{orig_trans_code}':
+ # Set audio language based on original subtitles
+ for f in formats:
+ if f.get('acodec') != 'none' and not f.get('language'):
+ f['language'] = orig_trans_code
+ # Add an "-orig" label to the original language so that it can be distinguished.
+ # The subs are returned without "-orig" as well for compatibility
process_language(
automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
# Setting tlang=lang returns damaged subtitles.
info[d_k] = parse_duration(query[k][0])
# Youtube Music Auto-generated description
- if video_description:
+ if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
+ # XXX: Causes catastrophic backtracking if description has "·"
+ # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
+ # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
+ # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
mobj = re.search(
r'''(?xs)
- (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
- (?P<album>[^\n]+)
+ (?=(?P<track>[^\n·]+))(?P=track)·
+ (?=(?P<artist>[^\n]+))(?P=artist)\n+
+ (?=(?P<album>[^\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*$
+ (.+?\nArtist\s*:\s*
+ (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
+ )?.+\nAuto-generated\ by\ YouTube\.\s*$
''', video_description)
if mobj:
release_year = mobj.group('release_year')
info['comment_count'] = traverse_obj(initial_data, (
'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
- 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
+ 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
), (
'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
- 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
- ), expected_type=int_or_none, get_all=False)
+ 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
+ ), expected_type=self._get_count, get_all=False)
try: # This will error if there is no livechat
initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
or self._extract_chapters_from_description(video_description, duration)
or None)
+ info['heatmap'] = self._extract_heatmap(initial_data)
+
contents = traverse_obj(
initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
expected_type=list, default=[])
'channel': self._get_text(vor, 'title'),
'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
+ if not channel_handle:
+ channel_handle = self.handle_from_url(
+ traverse_obj(vor, (
+ ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
+ (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
+ {str}), get_all=False))
+
rows = try_get(
vsir,
lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
info['artist'] = mrr_contents_text
elif mrr_title == 'Song':
info['track'] = mrr_contents_text
+ owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
+ if self._has_badge(owner_badges, BadgeType.VERIFIED):
+ info['channel_is_verified'] = True
- fallbacks = {
- 'channel': 'uploader',
- 'channel_id': 'uploader_id',
- 'channel_url': 'uploader_url',
- }
-
+ info.update({
+ 'uploader': info.get('channel'),
+ 'uploader_id': channel_handle,
+ 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
+ })
# The upload date for scheduled, live and past live streams / premieres in microformats
# may be different from the stream date. Although not in UTC, we will prefer it in this case.
# See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
):
upload_date = strftime_or_none(
- self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
+ self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
info['upload_date'] = upload_date
- for to, frm in fallbacks.items():
- if not info.get(to):
- info[to] = info.get(frm)
-
for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
v = info.get(s_k)
if v:
info[d_k] = v
- badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
+ badges = self._extract_badges(traverse_obj(vpir, 'badges'))
is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
or get_first(video_details, 'isPrivate', expected_type=bool))
return renderer
def _extract_channel_renderer(self, renderer):
- channel_id = renderer['channelId']
+ channel_id = self.ucid_or_none(renderer['channelId'])
title = self._get_text(renderer, 'title')
- channel_url = f'https://www.youtube.com/channel/{channel_id}'
+ channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
+ channel_handle = self.handle_from_url(
+ traverse_obj(renderer, (
+ 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
+ ('browseEndpoint', 'canonicalBaseUrl')),
+ {str}), get_all=False))
+ if not channel_handle:
+ # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
+ channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
return {
'_type': 'url',
'url': channel_url,
'id': channel_id,
'ie_key': YoutubeTabIE.ie_key(),
'channel': title,
+ 'uploader': title,
'channel_id': channel_id,
'channel_url': channel_url,
'title': title,
- 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
+ 'uploader_id': channel_handle,
+ 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
+ # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
+ # However, in feed/channels this is set correctly to the subscriber count
+ 'channel_follower_count': traverse_obj(
+ renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
- 'playlist_count': self._get_count(renderer, 'videoCountText'),
+ 'playlist_count': (
+ # videoCountText may be the subscriber count
+ self._get_count(renderer, 'videoCountText')
+ if self._get_count(renderer, 'subscriberCountText') is not None else None),
'description': self._get_text(renderer, 'descriptionSnippet'),
+ 'channel_is_verified': True if self._has_badge(
+ self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
}
def _grid_entries(self, grid_renderer):
def _music_reponsive_list_entry(self, renderer):
video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
if video_id:
+ title = traverse_obj(renderer, (
+ 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
+ 'text', 'runs', 0, 'text'))
return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
- ie=YoutubeIE.ie_key(), video_id=video_id)
+ ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
if playlist_id:
video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
def _rich_entries(self, rich_grid_renderer):
renderer = traverse_obj(
- rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
+ rich_grid_renderer,
+ ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
video_id = renderer.get('videoId')
- if not video_id:
+ if video_id:
+ yield self._extract_video(renderer)
+ return
+ playlist_id = renderer.get('playlistId')
+ if playlist_id:
+ yield self.url_result(
+ f'https://www.youtube.com/playlist?list={playlist_id}',
+ ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
+ video_title=self._get_text(renderer, 'title'))
return
- yield self._extract_video(renderer)
def _video_entry(self, video_renderer):
video_id = video_renderer.get('videoId')
'videoRenderer': lambda x: [self._video_entry(x)],
'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
- 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
+ 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
+ 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
}
for key, renderer in isr_content.items():
if key not in known_renderers:
or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
yield from extract_entries(parent_renderer)
continuation = continuation_list[0]
-
+ seen_continuations = set()
for page_num in itertools.count(1):
if not continuation:
break
+ continuation_token = continuation.get('continuation')
+ if continuation_token is not None and continuation_token in seen_continuations:
+ self.write_debug('Detected YouTube feed looping - assuming end of feed.')
+ break
+ seen_continuations.add(continuation_token)
headers = self.generate_api_headers(
ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
response = self._extract_response(
metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
if metadata_renderer:
+ channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
+ ('channelUrl', {self.ucid_from_url}))
info.update({
- 'uploader': metadata_renderer.get('title'),
- 'uploader_id': metadata_renderer.get('externalId'),
- 'uploader_url': metadata_renderer.get('channelUrl'),
+ 'channel': metadata_renderer.get('title'),
+ 'channel_id': channel_id,
})
- if info['uploader_id']:
- info['id'] = info['uploader_id']
+ if info['channel_id']:
+ info['id'] = info['channel_id']
else:
metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
})
+ channel_handle = (
+ traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
+ or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
+
+ if channel_handle:
+ info.update({
+ 'uploader_id': channel_handle,
+ 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
+ })
+
+ channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
+ if self._has_badge(channel_badges, BadgeType.VERIFIED):
+ info['channel_is_verified'] = True
# Playlist stats is a text runs array containing [video count, view count, last updated].
# last updated or (view count and last updated) may be missing.
playlist_stats = get_first(
last_updated_unix = self._parse_time_text(
self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
- info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
+ info['modified_date'] = strftime_or_none(last_updated_unix)
info['view_count'] = self._get_count(playlist_stats, 1)
if info['view_count'] is None: # 0 is allowed
if info['playlist_count'] is None: # 0 is allowed
info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
- if not info.get('uploader_id'):
+ if not info.get('channel_id'):
owner = traverse_obj(playlist_header_renderer, 'ownerText')
if not owner: # Deprecated
owner = traverse_obj(
owner_text = self._get_text(owner)
browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
info.update({
- 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
- 'uploader_id': browse_ep.get('browseId'),
- 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
+ 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
+ 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
+ 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
})
info.update({
- 'channel': info['uploader'],
- 'channel_id': info['uploader_id'],
- 'channel_url': info['uploader_url']
+ 'uploader': info['channel'],
+ 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
+ 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
})
+
return info
def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
player_header_privacy = playlist_header_renderer.get('privacy')
- badges = self._extract_badges(sidebar_renderer)
+ badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
# Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
privacy_setting_icon = get_first(
data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
except ExtractorError as e:
if isinstance(e.cause, network_exceptions):
- if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
+ if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
retry.error = e
continue
self._error_or_warning(e, fatal=fatal)
'title': 'Igor Kleiner - Playlists',
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
'uploader': 'Igor Kleiner',
- 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
+ 'uploader_id': '@IgorDataScience',
+ 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
'channel': 'Igor Kleiner',
'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
- 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
'channel_follower_count': int
},
}, {
'id': 'UCqj7Cz7revf5maW9g5pgNcg',
'title': 'Igor Kleiner - Playlists',
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
- 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
'uploader': 'Igor Kleiner',
- 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
+ 'uploader_id': '@IgorDataScience',
+ 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
'channel': 'Igor Kleiner',
'id': 'UCYO_jab_esuFRV4b17AJtAw',
'title': '3Blue1Brown - Playlists',
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
- 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
- 'uploader': '3Blue1Brown',
'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
- 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
'channel': '3Blue1Brown',
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
+ 'uploader_id': '@3blue1brown',
+ 'uploader_url': 'https://www.youtube.com/@3blue1brown',
+ 'uploader': '3Blue1Brown',
'tags': ['Mathematics'],
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'channel_is_verified': True,
},
}, {
'note': 'playlists, singlepage',
'title': 'ThirstForScience - Playlists',
'description': 'md5:609399d937ea957b0f53cbffb747a14c',
'uploader': 'ThirstForScience',
- 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
- 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
- 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
+ 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
+ 'uploader_id': '@ThirstForScience',
'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
+ 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
'tags': 'count:13',
'channel': 'ThirstForScience',
'channel_follower_count': int
'note': 'basic, single video playlist',
'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
'info_dict': {
- 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
- 'uploader': 'Sergey M.',
'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
'title': 'youtube-dl public playlist',
'description': '',
'modified_date': '20201130',
'channel': 'Sergey M.',
'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
- 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
'availability': 'public',
+ 'uploader': 'Sergey M.',
+ 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
+ 'uploader_id': '@sergeym.6173',
},
'playlist_count': 1,
}, {
'note': 'empty playlist',
'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
'info_dict': {
- 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
- 'uploader': 'Sergey M.',
'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
'title': 'youtube-dl empty playlist',
'tags': [],
'modified_date': '20160902',
'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
- 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
'availability': 'public',
+ 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
+ 'uploader_id': '@sergeym.6173',
+ 'uploader': 'Sergey M.',
},
'playlist_count': 0,
}, {
'title': 'lex will - Home',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
- 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_id': '@lexwill718',
'channel': 'lex will',
'tags': ['bible', 'history', 'prophesy'],
- 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/@lexwill718',
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_follower_count': int
'title': 'lex will - Videos',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
- 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_id': '@lexwill718',
'tags': ['bible', 'history', 'prophesy'],
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
- 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/@lexwill718',
'channel': 'lex will',
'channel_follower_count': int
},
'title': 'lex will - Videos',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
- 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_id': '@lexwill718',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
- 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/@lexwill718',
'channel': 'lex will',
'tags': ['bible', 'history', 'prophesy'],
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Playlists',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
- 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
- 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_id': '@lexwill718',
+ 'uploader_url': 'https://www.youtube.com/@lexwill718',
'channel': 'lex will',
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Community',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
- 'uploader': 'lex will',
- 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
- 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel': 'lex will',
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'tags': ['bible', 'history', 'prophesy'],
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader_url': 'https://www.youtube.com/@lexwill718',
+ 'uploader_id': '@lexwill718',
+ 'uploader': 'lex will',
},
'playlist_mincount': 18,
}, {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Channels',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
- 'uploader': 'lex will',
- 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
- 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel': 'lex will',
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'tags': ['bible', 'history', 'prophesy'],
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader_url': 'https://www.youtube.com/@lexwill718',
+ 'uploader_id': '@lexwill718',
+ 'uploader': 'lex will',
},
'playlist_mincount': 12,
}, {
'id': 'UCYO_jab_esuFRV4b17AJtAw',
'title': '3Blue1Brown - Search - linear algebra',
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
- 'uploader': '3Blue1Brown',
- 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
- 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
'tags': ['Mathematics'],
'channel': '3Blue1Brown',
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'uploader_url': 'https://www.youtube.com/@3blue1brown',
+ 'uploader_id': '@3blue1brown',
+ 'uploader': '3Blue1Brown',
+ 'channel_is_verified': True,
},
}, {
'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
'info_dict': {
'title': '29C3: Not my department',
'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
- 'uploader': 'Christiaan008',
- 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
'tags': [],
- 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
'view_count': int,
'modified_date': '20150605',
'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
- 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
+ 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
'channel': 'Christiaan008',
'availability': 'public',
+ 'uploader_id': '@ChRiStIaAn008',
+ 'uploader': 'Christiaan008',
+ 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
},
'playlist_count': 96,
}, {
'info_dict': {
'title': 'Uploads from Cauchemar',
'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
- 'uploader': 'Cauchemar',
- 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
- 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
+ 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
'tags': [],
'modified_date': r're:\d{8}',
'channel': 'Cauchemar',
- 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
'view_count': int,
'description': '',
'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
'availability': 'public',
+ 'uploader_id': '@Cauchemar89',
+ 'uploader': 'Cauchemar',
+ 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
},
'playlist_mincount': 1123,
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
'info_dict': {
'title': 'Uploads from Interstellar Movie',
'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
- 'uploader': 'Interstellar Movie',
- 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
- 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
'tags': [],
'view_count': int,
'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
- 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
+ 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
'channel': 'Interstellar Movie',
'description': '',
'modified_date': r're:\d{8}',
'availability': 'public',
+ 'uploader_id': '@InterstellarMovie',
+ 'uploader': 'Interstellar Movie',
+ 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
},
'playlist_mincount': 21,
}, {
'info_dict': {
'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
- 'uploader': 'Phim Siêu Nhân Nhật Bản',
- 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
'view_count': int,
'channel': 'Phim Siêu Nhân Nhật Bản',
'tags': [],
- 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
'description': '',
'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
'modified_date': r're:\d{8}',
'availability': 'public',
+ 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
+ 'uploader_id': '@phimsieunhannhatban',
+ 'uploader': 'Phim Siêu Nhân Nhật Bản',
},
'playlist_mincount': 200,
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
'info_dict': {
'title': 'Uploads from BlankTV',
'id': 'UU8l9frL61Yl5KFOl87nIm2w',
- 'uploader': 'BlankTV',
- 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
'channel': 'BlankTV',
- 'channel_url': 'https://www.youtube.com/c/blanktv',
+ 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
'view_count': int,
'tags': [],
- 'uploader_url': 'https://www.youtube.com/c/blanktv',
'modified_date': r're:\d{8}',
'description': '',
'availability': 'public',
+ 'uploader_id': '@blanktv',
+ 'uploader': 'BlankTV',
+ 'uploader_url': 'https://www.youtube.com/@blanktv',
},
'playlist_mincount': 1000,
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
'info_dict': {
'title': 'Data Analysis with Dr Mike Pound',
'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
- 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
- 'uploader': 'Computerphile',
'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
- 'uploader_url': 'https://www.youtube.com/user/Computerphile',
'tags': [],
'view_count': int,
'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
- 'channel_url': 'https://www.youtube.com/user/Computerphile',
+ 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
'channel': 'Computerphile',
'availability': 'public',
'modified_date': '20190712',
+ 'uploader_id': '@Computerphile',
+ 'uploader': 'Computerphile',
+ 'uploader_url': 'https://www.youtube.com/@Computerphile',
},
'playlist_mincount': 11,
}, {
'id': 'FqZTN594JQw',
'ext': 'webm',
'title': "Smiley's People 01 detective, Adventure Series, Action",
- 'uploader': 'STREEM',
- 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
'upload_date': '20150526',
'license': 'Standard YouTube License',
'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
}, {
'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
'info_dict': {
- 'id': 'Wq15eF5vCbI', # This will keep changing
+ 'id': 'hGkQjiJLjWQ', # This will keep changing
'ext': 'mp4',
'title': str,
- 'uploader': 'Sky News',
- 'uploader_id': 'skynews',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
'upload_date': r're:\d{8}',
'description': str,
'categories': ['News & Politics'],
'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
'channel_follower_count': int,
'concurrent_view_count': int,
+ 'uploader_url': 'https://www.youtube.com/@SkyNews',
+ 'uploader_id': '@SkyNews',
+ 'uploader': 'Sky News',
+ 'channel_is_verified': True,
},
'params': {
'skip_download': True,
'id': 'a48o2S1cPoo',
'ext': 'mp4',
'title': 'The Young Turks - Live Main Show',
- 'uploader': 'The Young Turks',
- 'uploader_id': 'TheYoungTurks',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
'upload_date': '20150715',
'license': 'Standard YouTube License',
'description': 'md5:438179573adcdff3c97ebb1ee632b891',
'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
'info_dict': {
'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
- 'uploader': 'NoCopyrightSounds',
'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
- 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'title': 'NCS : All Releases 💿',
- 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
- 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
+ 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
'modified_date': r're:\d{8}',
'view_count': int,
'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'tags': [],
'channel': 'NoCopyrightSounds',
'availability': 'public',
+ 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
+ 'uploader': 'NoCopyrightSounds',
+ 'uploader_id': '@NoCopyrightSounds',
},
'playlist_mincount': 166,
- 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
}, {
+ # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
'note': 'Topic, should redirect to playlist?list=UU...',
'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
'info_dict': {
'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
- 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
'title': 'Uploads from Royalty Free Music - Topic',
- 'uploader': 'Royalty Free Music - Topic',
'tags': [],
'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
'channel': 'Royalty Free Music - Topic',
'view_count': int,
'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
- 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
'modified_date': r're:\d{8}',
- 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
'description': '',
'availability': 'public',
+ 'uploader': 'Royalty Free Music - Topic',
},
'playlist_mincount': 101,
+ 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
}, {
# Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
# Treat as a general feed
'modified_date': r're:\d{8}',
},
'playlist_count': 50,
+ 'expected_warnings': ['YouTube Music is not directly supported'],
}, {
'note': 'unlisted single video playlist',
'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
'info_dict': {
- 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
- 'uploader': 'colethedj',
'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
'title': 'yt-dlp unlisted playlist test',
'availability': 'unlisted',
'channel': 'colethedj',
'view_count': int,
'description': '',
- 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
+ 'uploader_url': 'https://www.youtube.com/@colethedj1894',
+ 'uploader_id': '@colethedj1894',
+ 'uploader': 'colethedj',
},
+ 'playlist': [{
+ 'info_dict': {
+ 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
+ 'id': 'BaW_jenozKc',
+ '_type': 'url',
+ 'ie_key': 'Youtube',
+ 'duration': 10,
+ 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
+ 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
+ 'view_count': int,
+ 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
+ 'channel': 'Philipp Hagemeister',
+ 'uploader_id': '@PhilippHagemeister',
+ 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
+ 'uploader': 'Philipp Hagemeister',
+ }
+ }],
'playlist_count': 1,
+ 'params': {'extract_flat': True},
}, {
'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
'url': 'https://www.youtube.com/feed/recommended',
'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
'title': 'Cody\'sLab - Videos',
'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
- 'uploader': 'Cody\'sLab',
- 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
'channel': 'Cody\'sLab',
'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
'tags': [],
'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
- 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
'channel_follower_count': int
},
'playlist_mincount': 650,
'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
'info_dict': {
'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
- 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
'title': 'Uploads from Royalty Free Music - Topic',
- 'uploader': 'Royalty Free Music - Topic',
'modified_date': r're:\d{8}',
'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
'description': '',
'tags': [],
'channel': 'Royalty Free Music - Topic',
'view_count': int,
- 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
'availability': 'public',
+ 'uploader': 'Royalty Free Music - Topic',
},
'playlist_mincount': 101,
'params': {
'skip_download': True,
'extractor_args': {'youtubetab': {'skip': ['webpage']}}
},
+ 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
}, {
'note': 'non-standard redirect to regional channel',
'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
'modified_date': '20220407',
'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
'tags': [],
- 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
- 'uploader': 'pukkandan',
'availability': 'unlisted',
'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
'channel': 'pukkandan',
'description': 'Test for collaborative playlist',
'title': 'yt-dlp test - collaborative playlist',
'view_count': int,
- 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
+ 'uploader_url': 'https://www.youtube.com/@pukkandan',
+ 'uploader_id': '@pukkandan',
+ 'uploader': 'pukkandan',
},
'playlist_mincount': 2
}, {
'info_dict': {
'id': 'UCiu-3thuViMebBjw_5nWYrA',
'tags': [],
- 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'description': 'test description',
'title': 'cole-dlp-test-acc - 再生リスト',
- 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
- 'uploader': 'cole-dlp-test-acc',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel': 'cole-dlp-test-acc',
+ 'uploader_url': 'https://www.youtube.com/@coletdjnz',
+ 'uploader_id': '@coletdjnz',
+ 'uploader': 'cole-dlp-test-acc',
},
'playlist_mincount': 1,
'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
'tags': [],
'view_count': int,
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
- 'uploader': 'cole-dlp-test-acc',
- 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel': 'cole-dlp-test-acc',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'description': 'test',
- 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'title': 'dlp test playlist',
'availability': 'public',
+ 'uploader_url': 'https://www.youtube.com/@coletdjnz',
+ 'uploader_id': '@coletdjnz',
+ 'uploader': 'cole-dlp-test-acc',
},
'playlist_mincount': 1,
'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
'channel_follower_count': int,
'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
- 'uploader': 'Polka Ch. 尾丸ポルカ',
- 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
+ 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
'channel': 'Polka Ch. 尾丸ポルカ',
'tags': 'count:35',
- 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
- 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
+ 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
+ 'uploader': 'Polka Ch. 尾丸ポルカ',
+ 'uploader_id': '@OmaruPolka',
},
'playlist_count': 3,
}, {
# Shorts tab with channel with handle
+ # TODO: fix channel description
'url': 'https://www.youtube.com/@NotJustBikes/shorts',
'info_dict': {
'id': 'UC0intLFzLaudFG-xAvUEO-A',
'title': 'Not Just Bikes - Shorts',
'tags': 'count:12',
- 'uploader': 'Not Just Bikes',
'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
- 'description': 'md5:7513148b1f02b924783157d84c4ea555',
+ 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
'channel_follower_count': int,
- 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
- 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
'channel': 'Not Just Bikes',
+ 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
+ 'uploader': 'Not Just Bikes',
+ 'uploader_id': '@NotJustBikes',
},
'playlist_mincount': 10,
}, {
'tags': 'count:7',
'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
- 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
'channel': '中村悠一',
- 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
'channel_follower_count': int,
- 'uploader': '中村悠一',
'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
+ 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
+ 'uploader_id': '@Yuichi-Nakamura',
+ 'uploader': '中村悠一',
},
'playlist_mincount': 60,
}, {
'info_dict': {
'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
'title': 'Shorts Break - Shorts',
- 'tags': 'count:32',
+ 'tags': 'count:48',
'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
'channel': 'Shorts Break',
- 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
- 'uploader': 'Shorts Break',
+ 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
'channel_follower_count': int,
- 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
- 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
+ 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
+ 'uploader': 'Shorts Break',
+ 'uploader_id': '@ShortsBreak_Official',
},
'playlist_mincount': 30,
}, {
'playlist_mincount': 30,
}, {
# Shorts url result in shorts tab
+ # TODO: Fix channel id extraction
'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
'info_dict': {
'id': 'UCiu-3thuViMebBjw_5nWYrA',
'title': 'cole-dlp-test-acc - Shorts',
- 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel': 'cole-dlp-test-acc',
'description': 'test description',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'tags': [],
+ 'uploader_url': 'https://www.youtube.com/@coletdjnz',
+ 'uploader_id': '@coletdjnz',
'uploader': 'cole-dlp-test-acc',
- 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
-
},
'playlist': [{
'info_dict': {
+ # Channel data is not currently available for short renderers (as of 2023-03-01)
'_type': 'url',
'ie_key': 'Youtube',
'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
'id': 'sSM9J5YH_60',
- 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'title': 'SHORT short',
- 'channel': 'cole-dlp-test-acc',
- 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'view_count': int,
'thumbnails': list,
}
'channel_url': str,
'concurrent_view_count': int,
'channel': str,
+ 'uploader': str,
+ 'uploader_url': str,
+ 'uploader_id': str,
+ 'channel_is_verified': bool, # this will keep changing
}
}],
'params': {'extract_flat': True, 'playlist_items': '1'},
'info_dict': {
'id': 'UCiu-3thuViMebBjw_5nWYrA',
'title': 'cole-dlp-test-acc - Channels',
- 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel': 'cole-dlp-test-acc',
'description': 'test description',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'tags': [],
+ 'uploader_url': 'https://www.youtube.com/@coletdjnz',
+ 'uploader_id': '@coletdjnz',
'uploader': 'cole-dlp-test-acc',
- 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
-
},
'playlist': [{
'info_dict': {
'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
'thumbnails': list,
'channel_follower_count': int,
- 'playlist_count': int
+ 'playlist_count': int,
+ 'uploader': 'PewDiePie',
+ 'uploader_url': 'https://www.youtube.com/@PewDiePie',
+ 'uploader_id': '@PewDiePie',
+ 'channel_is_verified': True,
}
}],
'params': {'extract_flat': True},
'id': 'UCYO_jab_esuFRV4b17AJtAw',
'tags': ['Mathematics'],
'title': '3Blue1Brown - About',
- 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
'channel_follower_count': int,
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
- 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
'channel': '3Blue1Brown',
- 'uploader': '3Blue1Brown',
'view_count': int,
'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
+ 'uploader_url': 'https://www.youtube.com/@3blue1brown',
+ 'uploader_id': '@3blue1brown',
+ 'uploader': '3Blue1Brown',
+ 'channel_is_verified': True,
},
'playlist_count': 0,
+ }, {
+ # Podcasts tab, with rich entry playlistRenderers
+ 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
+ 'info_dict': {
+ 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
+ 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
+ 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
+ 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
+ 'title': '99 Percent Invisible - Podcasts',
+ 'uploader': '99 Percent Invisible',
+ 'channel_follower_count': int,
+ 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
+ 'tags': [],
+ 'channel': '99 Percent Invisible',
+ 'uploader_id': '@99percentinvisiblepodcast',
+ },
+ 'playlist_count': 1,
+ }, {
+ # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
+ 'url': 'https://www.youtube.com/@AHimitsu/releases',
+ 'info_dict': {
+ 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
+ 'channel': 'A Himitsu',
+ 'uploader_url': 'https://www.youtube.com/@AHimitsu',
+ 'title': 'A Himitsu - Releases',
+ 'uploader_id': '@AHimitsu',
+ 'uploader': 'A Himitsu',
+ 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
+ 'tags': 'count:16',
+ 'description': 'I make music',
+ 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
+ 'channel_follower_count': int,
+ 'channel_is_verified': True,
+ },
+ 'playlist_mincount': 10,
+ }, {
+ # Playlist with only shorts, shown as reel renderers
+ # FIXME: future: YouTube currently doesn't give continuation for this,
+ # may do in future.
+ 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
+ 'info_dict': {
+ 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
+ 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
+ 'view_count': int,
+ 'uploader_id': '@BangyShorts',
+ 'description': '',
+ 'uploader_url': 'https://www.youtube.com/@BangyShorts',
+ 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
+ 'channel': 'Bangy Shorts',
+ 'uploader': 'Bangy Shorts',
+ 'tags': [],
+ 'availability': 'public',
+ 'modified_date': '20230626',
+ 'title': 'Uploads from Bangy Shorts',
+ },
+ 'playlist_mincount': 100,
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}]
@classmethod
'title': '[OLD]Team Fortress 2 (Class-based LP)',
'id': 'PLBB231211A4F62143',
'uploader': 'Wickman',
- 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
+ 'uploader_id': '@WickmanVT',
'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
'view_count': int,
- 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
+ 'uploader_url': 'https://www.youtube.com/@WickmanVT',
'modified_date': r're:\d{8}',
'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
'channel': 'Wickman',
'tags': [],
- 'channel_url': 'https://www.youtube.com/c/WickmanVT',
+ 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
'availability': 'public',
},
'playlist_mincount': 29,
'title': 'JODA15',
'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
'uploader': 'milan',
- 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
+ 'uploader_id': '@milan5503',
'description': '',
'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
'tags': [],
'view_count': int,
'channel': 'milan',
'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
- 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
+ 'uploader_url': 'https://www.youtube.com/@milan5503',
'availability': 'public',
},
'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
'title': '2018 Chinese New Singles (11/6 updated)',
'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
'uploader': 'LBK',
- 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
+ 'uploader_id': '@music_king',
'description': 'md5:da521864744d60a198e3a88af4db0d9d',
'channel': 'LBK',
'view_count': int,
- 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
+ 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
'tags': [],
- 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
+ 'uploader_url': 'https://www.youtube.com/@music_king',
'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
'modified_date': r're:\d{8}',
'availability': 'public',
'ext': 'mp4',
'title': 'Small Scale Baler and Braiding Rugs',
'uploader': 'Backus-Page House Museum',
- 'uploader_id': 'backuspagemuseum',
- 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
+ 'uploader_id': '@backuspagemuseum',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
'upload_date': '20161008',
'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
'categories': ['Nonprofits & Activism'],
'like_count': int,
'age_limit': 0,
'playable_in_embed': True,
- 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
+ 'thumbnail': r're:^https?://.*\.webp',
'channel': 'Backus-Page House Museum',
'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
'live_status': 'not_live',
if not video_id:
browse_ep = traverse_obj(
notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
- channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
+ channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
post_id = self._search_regex(
r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
'post id', default=None)
'title': title,
'channel_id': channel_id,
'channel': channel,
+ 'uploader': channel,
'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
'timestamp': timestamp,
}
'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
'title': 'Kurzgesagt – In a Nutshell',
'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
- 'playlist_count': int, # XXX: should have a way of saying > 1
+ # No longer available for search as it is set to the handle.
+ # 'playlist_count': int,
'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
- 'thumbnails': list
+ 'thumbnails': list,
+ 'uploader_id': '@kurzgesagt',
+ 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
+ 'uploader': 'Kurzgesagt – In a Nutshell',
+ 'channel_is_verified': True,
+ 'channel_follower_count': int,
}
}],
'params': {'extract_flat': True, 'playlist_items': '1'},
}]
-class YoutubeStoriesIE(InfoExtractor):
- IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
- IE_NAME = 'youtube:stories'
- _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
- _TESTS = [{
- 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
- 'only_matching': True,
- }]
-
- def _real_extract(self, url):
- playlist_id = f'RLTD{self._match_id(url)}'
- return self.url_result(
- smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
- ie=YoutubeTabIE, video_id=playlist_id)
-
-
class YoutubeShortsAudioPivotIE(InfoExtractor):
IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
IE_NAME = 'youtube:shorts:pivot:audio'
'title': 'Mobile Games on Console - Scott The Woz',
'upload_date': '20210920',
'uploader': 'Scott The Woz',
- 'uploader_id': 'scottthewoz',
- 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
+ 'uploader_id': '@ScottTheWoz',
+ 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
'view_count': int,
'live_status': 'not_live',
- 'channel_follower_count': int
+ 'channel_follower_count': int,
+ 'chapters': 'count:20',
+ 'comment_count': int,
+ 'heatmap': 'count:100',
}
}]
'id': 'qVv6vCqciTM',
'ext': 'mp4',
'age_limit': 0,
- 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
+ 'uploader_id': '@sana_natori',
'comment_count': int,
'chapters': 'count:13',
'upload_date': '20221223',
'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
- 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
+ 'uploader_url': 'https://www.youtube.com/@sana_natori',
'like_count': int,
'release_date': '20221223',
'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
'channel': 'さなちゃんねる',
'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
'uploader': 'さなちゃんねる',
+ 'channel_is_verified': True,
+ 'heatmap': 'count:100',
},
'add_ie': ['Youtube'],
'params': {'skip_download': 'Youtube'},