diff options
author | coletdjnz <coletdjnz@protonmail.com> | 2025-03-13 17:37:33 +1300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-03-13 17:37:33 +1300 |
commit | 4432a9390c79253ac830702b226d2e558b636725 (patch) | |
tree | a410c277cad901bfd9545ab3797132204d4a3ed2 | |
parent | 05c8023a27dd37c49163c0498bf98e3e3c1cb4b9 (diff) |
[ie/youtube] Split into package (#12557)
Authored by: coletdjnz
-rw-r--r-- | yt_dlp/extractor/youtube/__init__.py | 50 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_base.py | 1145 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_clip.py | 66 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_mistakes.py | 69 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_notifications.py | 98 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_redirect.py | 247 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_search.py | 167 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_tab.py | 2348 | ||||
-rw-r--r-- | yt_dlp/extractor/youtube/_video.py (renamed from yt_dlp/extractor/youtube.py) | 4078 |
9 files changed, 4203 insertions, 4065 deletions
diff --git a/yt_dlp/extractor/youtube/__init__.py b/yt_dlp/extractor/youtube/__init__.py new file mode 100644 index 000000000..892d860b0 --- /dev/null +++ b/yt_dlp/extractor/youtube/__init__.py @@ -0,0 +1,50 @@ +# flake8: noqa: F401 +from ._base import YoutubeBaseInfoExtractor +from ._clip import YoutubeClipIE +from ._mistakes import YoutubeTruncatedIDIE, YoutubeTruncatedURLIE +from ._notifications import YoutubeNotificationsIE +from ._redirect import ( + YoutubeConsentRedirectIE, + YoutubeFavouritesIE, + YoutubeFeedsInfoExtractor, + YoutubeHistoryIE, + YoutubeLivestreamEmbedIE, + YoutubeRecommendedIE, + YoutubeShortsAudioPivotIE, + YoutubeSubscriptionsIE, + YoutubeWatchLaterIE, + YoutubeYtBeIE, + YoutubeYtUserIE, +) +from ._search import YoutubeMusicSearchURLIE, YoutubeSearchDateIE, YoutubeSearchIE, YoutubeSearchURLIE +from ._tab import YoutubePlaylistIE, YoutubeTabBaseInfoExtractor, YoutubeTabIE +from ._video import YoutubeIE + +# Hack to allow plugin overrides work +for _cls in [ + YoutubeBaseInfoExtractor, + YoutubeClipIE, + YoutubeTruncatedIDIE, + YoutubeTruncatedURLIE, + YoutubeNotificationsIE, + YoutubeConsentRedirectIE, + YoutubeFavouritesIE, + YoutubeFeedsInfoExtractor, + YoutubeHistoryIE, + YoutubeLivestreamEmbedIE, + YoutubeRecommendedIE, + YoutubeShortsAudioPivotIE, + YoutubeSubscriptionsIE, + YoutubeWatchLaterIE, + YoutubeYtBeIE, + YoutubeYtUserIE, + YoutubeMusicSearchURLIE, + YoutubeSearchDateIE, + YoutubeSearchIE, + YoutubeSearchURLIE, + YoutubePlaylistIE, + YoutubeTabBaseInfoExtractor, + YoutubeTabIE, + YoutubeIE, +]: + _cls.__module__ = 'yt_dlp.extractor.youtube' diff --git a/yt_dlp/extractor/youtube/_base.py b/yt_dlp/extractor/youtube/_base.py new file mode 100644 index 000000000..ba28189a6 --- /dev/null +++ b/yt_dlp/extractor/youtube/_base.py @@ -0,0 +1,1145 @@ +import calendar +import copy +import datetime as dt +import enum +import functools +import hashlib +import json +import re +import time +import urllib.parse + +from ..common import InfoExtractor +from ...networking.exceptions import HTTPError, network_exceptions +from ...utils import ( + ExtractorError, + bug_reports_message, + datetime_from_str, + filter_dict, + get_first, + int_or_none, + is_html, + join_nonempty, + parse_count, + qualities, + str_to_int, + traverse_obj, + try_call, + try_get, + unified_timestamp, + url_or_none, + variadic, +) + + +class _PoTokenContext(enum.Enum): + PLAYER = 'player' + GVS = 'gvs' + + +# any clients starting with _ cannot be explicitly requested by the user +INNERTUBE_CLIENTS = { + 'web': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'WEB', + 'clientVersion': '2.20241126.01.00', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'SUPPORTS_COOKIES': True, + }, + # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats + 'web_safari': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'WEB', + 'clientVersion': '2.20241126.01.00', + 'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'SUPPORTS_COOKIES': True, + }, + 'web_embedded': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'WEB_EMBEDDED_PLAYER', + 'clientVersion': '1.20241201.00.00', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 56, + 'SUPPORTS_COOKIES': True, + }, + 'web_music': { + 'INNERTUBE_HOST': 'music.youtube.com', + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'WEB_REMIX', + 'clientVersion': '1.20241127.01.00', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'SUPPORTS_COOKIES': True, + }, + # This client now requires sign-in for every video + 'web_creator': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'WEB_CREATOR', + 'clientVersion': '1.20241203.01.00', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'REQUIRE_AUTH': True, + 'SUPPORTS_COOKIES': True, + }, + 'android': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID', + 'clientVersion': '19.44.38', + 'androidSdkVersion': 30, + 'userAgent': 'com.google.android.youtube/19.44.38 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, + 'REQUIRE_JS_PLAYER': False, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + }, + # This client now requires sign-in for every video + 'android_music': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID_MUSIC', + 'clientVersion': '7.27.52', + 'androidSdkVersion': 30, + 'userAgent': 'com.google.android.apps.youtube.music/7.27.52 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, + 'REQUIRE_JS_PLAYER': False, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'REQUIRE_AUTH': True, + }, + # This client now requires sign-in for every video + 'android_creator': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID_CREATOR', + 'clientVersion': '24.45.100', + 'androidSdkVersion': 30, + 'userAgent': 'com.google.android.apps.youtube.creator/24.45.100 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, + 'REQUIRE_JS_PLAYER': False, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'REQUIRE_AUTH': True, + }, + # YouTube Kids videos aren't returned on this client for some reason + 'android_vr': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID_VR', + 'clientVersion': '1.60.19', + 'deviceMake': 'Oculus', + 'deviceModel': 'Quest 3', + 'androidSdkVersion': 32, + 'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.60.19 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip', + 'osName': 'Android', + 'osVersion': '12L', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 28, + 'REQUIRE_JS_PLAYER': False, + }, + # iOS clients have HLS live streams. Setting device model to get 60fps formats. + # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 + 'ios': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'IOS', + 'clientVersion': '20.03.02', + 'deviceMake': 'Apple', + 'deviceModel': 'iPhone16,2', + 'userAgent': 'com.google.ios.youtube/20.03.02 (iPhone16,2; U; CPU iOS 18_2_1 like Mac OS X;)', + 'osName': 'iPhone', + 'osVersion': '18.2.1.22C161', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'REQUIRE_JS_PLAYER': False, + }, + # This client now requires sign-in for every video + 'ios_music': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'IOS_MUSIC', + 'clientVersion': '7.27.0', + 'deviceMake': 'Apple', + 'deviceModel': 'iPhone16,2', + 'userAgent': 'com.google.ios.youtubemusic/7.27.0 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)', + 'osName': 'iPhone', + 'osVersion': '18.1.0.22B83', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, + 'REQUIRE_JS_PLAYER': False, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'REQUIRE_AUTH': True, + }, + # This client now requires sign-in for every video + 'ios_creator': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'IOS_CREATOR', + 'clientVersion': '24.45.100', + 'deviceMake': 'Apple', + 'deviceModel': 'iPhone16,2', + 'userAgent': 'com.google.ios.ytcreator/24.45.100 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)', + 'osName': 'iPhone', + 'osVersion': '18.1.0.22B83', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, + 'REQUIRE_JS_PLAYER': False, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'REQUIRE_AUTH': True, + }, + # mweb has 'ultralow' formats + # See: https://github.com/yt-dlp/yt-dlp/pull/557 + 'mweb': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'MWEB', + 'clientVersion': '2.20241202.07.00', + # mweb previously did not require PO Token with this UA + 'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 2, + 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], + 'SUPPORTS_COOKIES': True, + }, + 'tv': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'TVHTML5', + 'clientVersion': '7.20250120.19.00', + 'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 7, + 'SUPPORTS_COOKIES': True, + }, + # This client now requires sign-in for every video + # It was previously an age-gate workaround for videos that were `playable_in_embed` + # It may still be useful if signed into an EU account that is not age-verified + 'tv_embedded': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', + 'clientVersion': '2.0', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 85, + 'REQUIRE_AUTH': True, + 'SUPPORTS_COOKIES': True, + }, +} + + +def _split_innertube_client(client_name): + variant, *base = client_name.rsplit('.', 1) + if base: + return variant, base[0], variant + base, *variant = client_name.split('_', 1) + return client_name, base, variant[0] if variant else None + + +def short_client_name(client_name): + main, *parts = _split_innertube_client(client_name)[0].split('_') + return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper() + + +def build_innertube_clients(): + THIRD_PARTY = { + 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL + } + BASE_CLIENTS = ('ios', 'web', 'tv', 'mweb', 'android') + priority = qualities(BASE_CLIENTS[::-1]) + + for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): + ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') + ytcfg.setdefault('REQUIRE_JS_PLAYER', True) + ytcfg.setdefault('PO_TOKEN_REQUIRED_CONTEXTS', []) + ytcfg.setdefault('REQUIRE_AUTH', False) + ytcfg.setdefault('SUPPORTS_COOKIES', False) + ytcfg.setdefault('PLAYER_PARAMS', None) + ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') + + _, base_client, variant = _split_innertube_client(client) + ytcfg['priority'] = 10 * priority(base_client) + + if variant == 'embedded': + ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY + ytcfg['priority'] -= 2 + elif variant: + ytcfg['priority'] -= 3 + + +build_innertube_clients() + + +class BadgeType(enum.Enum): + AVAILABILITY_UNLISTED = enum.auto() + AVAILABILITY_PRIVATE = enum.auto() + AVAILABILITY_PUBLIC = enum.auto() + AVAILABILITY_PREMIUM = enum.auto() + AVAILABILITY_SUBSCRIPTION = enum.auto() + LIVE_NOW = enum.auto() + VERIFIED = enum.auto() + + +CONFIGURATION_ARG_KEY = 'youtube' + + +class YoutubeBaseInfoExtractor(InfoExtractor): + """Provide base functions for Youtube extractors""" + + _RESERVED_NAMES = ( + r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|' + r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' + r'browse|oembed|get_video_info|iframe_api|s/player|source|' + r'storefront|oops|index|account|t/terms|about|upload|signin|logout') + + _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' + + # _NETRC_MACHINE = 'youtube' + + # If True it will raise an error if no login info is provided + _LOGIN_REQUIRED = False + + _INVIDIOUS_SITES = ( + # invidious-redirect websites + r'(?:www\.)?redirect\.invidious\.io', + r'(?:(?:www|dev)\.)?invidio\.us', + # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md + r'(?:www\.)?invidious\.pussthecat\.org', + r'(?:www\.)?invidious\.zee\.li', + r'(?:www\.)?invidious\.ethibox\.fr', + r'(?:www\.)?iv\.ggtyler\.dev', + r'(?:www\.)?inv\.vern\.i2p', + r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion', + r'(?:www\.)?inv\.riverside\.rocks', + r'(?:www\.)?invidious\.silur\.me', + r'(?:www\.)?inv\.bp\.projectsegfau\.lt', + r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion', + r'(?:www\.)?invidious\.slipfox\.xyz', + r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion', + r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion', + r'(?:www\.)?invidious\.tiekoetter\.com', + r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion', + r'(?:www\.)?invidious\.nerdvpn\.de', + r'(?:www\.)?invidious\.weblibre\.org', + r'(?:www\.)?inv\.odyssey346\.dev', + r'(?:www\.)?invidious\.dhusch\.de', + r'(?:www\.)?iv\.melmac\.space', + r'(?:www\.)?watch\.thekitty\.zone', + r'(?:www\.)?invidious\.privacydev\.net', + r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion', + r'(?:www\.)?invidious\.drivet\.xyz', + r'(?:www\.)?vid\.priv\.au', + r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion', + r'(?:www\.)?inv\.vern\.cc', + r'(?:www\.)?invidious\.esmailelbob\.xyz', + r'(?:www\.)?invidious\.sethforprivacy\.com', + r'(?:www\.)?yt\.oelrichsgarcia\.de', + r'(?:www\.)?yt\.artemislena\.eu', + r'(?:www\.)?invidious\.flokinet\.to', + r'(?:www\.)?invidious\.baczek\.me', + r'(?:www\.)?y\.com\.sb', + r'(?:www\.)?invidious\.epicsite\.xyz', + r'(?:www\.)?invidious\.lidarshield\.cloud', + r'(?:www\.)?yt\.funami\.tech', + r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', + r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', + r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', + # youtube-dl invidious instances list + r'(?:(?:www|no)\.)?invidiou\.sh', + r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', + r'(?:www\.)?invidious\.kabi\.tk', + r'(?:www\.)?invidious\.mastodon\.host', + r'(?:www\.)?invidious\.zapashcanon\.fr', + r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', + r'(?:www\.)?invidious\.tinfoil-hat\.net', + r'(?:www\.)?invidious\.himiko\.cloud', + r'(?:www\.)?invidious\.reallyancient\.tech', + r'(?:www\.)?invidious\.tube', + r'(?:www\.)?invidiou\.site', + r'(?:www\.)?invidious\.site', + r'(?:www\.)?invidious\.xyz', + r'(?:www\.)?invidious\.nixnet\.xyz', + r'(?:www\.)?invidious\.048596\.xyz', + r'(?:www\.)?invidious\.drycat\.fr', + r'(?:www\.)?inv\.skyn3t\.in', + r'(?:www\.)?tube\.poal\.co', + r'(?:www\.)?tube\.connect\.cafe', + r'(?:www\.)?vid\.wxzm\.sx', + r'(?:www\.)?vid\.mint\.lgbt', + r'(?:www\.)?vid\.puffyan\.us', + r'(?:www\.)?yewtu\.be', + r'(?:www\.)?yt\.elukerio\.org', + r'(?:www\.)?yt\.lelux\.fi', + r'(?:www\.)?invidious\.ggc-project\.de', + r'(?:www\.)?yt\.maisputain\.ovh', + r'(?:www\.)?ytprivate\.com', + r'(?:www\.)?invidious\.13ad\.de', + r'(?:www\.)?invidious\.toot\.koeln', + r'(?:www\.)?invidious\.fdn\.fr', + r'(?:www\.)?watch\.nettohikari\.com', + r'(?:www\.)?invidious\.namazso\.eu', + r'(?:www\.)?invidious\.silkky\.cloud', + r'(?:www\.)?invidious\.exonip\.de', + r'(?:www\.)?invidious\.riverside\.rocks', + r'(?:www\.)?invidious\.blamefran\.net', + r'(?:www\.)?invidious\.moomoo\.de', + r'(?:www\.)?ytb\.trom\.tf', + r'(?:www\.)?yt\.cyberhost\.uk', + r'(?:www\.)?kgg2m7yk5aybusll\.onion', + r'(?:www\.)?qklhadlycap4cnod\.onion', + r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', + r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', + r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', + r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', + r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', + r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', + r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', + r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', + r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', + r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', + # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances + r'(?:www\.)?piped\.kavin\.rocks', + r'(?:www\.)?piped\.tokhmi\.xyz', + r'(?:www\.)?piped\.syncpundit\.io', + r'(?:www\.)?piped\.mha\.fi', + r'(?:www\.)?watch\.whatever\.social', + r'(?:www\.)?piped\.garudalinux\.org', + r'(?:www\.)?piped\.rivo\.lol', + r'(?:www\.)?piped-libre\.kavin\.rocks', + r'(?:www\.)?yt\.jae\.fi', + r'(?:www\.)?piped\.mint\.lgbt', + r'(?:www\.)?il\.ax', + r'(?:www\.)?piped\.esmailelbob\.xyz', + r'(?:www\.)?piped\.projectsegfau\.lt', + r'(?:www\.)?piped\.privacydev\.net', + r'(?:www\.)?piped\.palveluntarjoaja\.eu', + r'(?:www\.)?piped\.smnz\.de', + r'(?:www\.)?piped\.adminforge\.de', + r'(?:www\.)?watch\.whatevertinfoil\.de', + r'(?:www\.)?piped\.qdi\.fi', + r'(?:(?:www|cf)\.)?piped\.video', + r'(?:www\.)?piped\.aeong\.one', + r'(?:www\.)?piped\.moomoo\.me', + r'(?:www\.)?piped\.chauvet\.pro', + r'(?:www\.)?watch\.leptons\.xyz', + r'(?:www\.)?pd\.vern\.cc', + r'(?:www\.)?piped\.hostux\.net', + r'(?:www\.)?piped\.lunar\.icu', + # Hyperpipe instances from https://hyperpipe.codeberg.page/ + r'(?:www\.)?hyperpipe\.surge\.sh', + r'(?:www\.)?hyperpipe\.esmailelbob\.xyz', + r'(?:www\.)?listen\.whatever\.social', + r'(?:www\.)?music\.adminforge\.de', + ) + + # extracted from account/account_menu ep + # XXX: These are the supported YouTube UI and API languages, + # which is slightly different from languages supported for translation in YouTube studio + _SUPPORTED_LANG_CODES = [ + 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es', + 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv', + 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi', + 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw', + 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml', + 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko', + ] + + _IGNORED_WARNINGS = { + 'Unavailable videos will be hidden during playback', + 'Unavailable videos are hidden', + } + + _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en + _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}' + + _NETRC_MACHINE = 'youtube' + + def ucid_or_none(self, ucid): + return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None) + + def handle_or_none(self, handle): + return self._search_regex(rf'^({self._YT_HANDLE_RE})$', urllib.parse.unquote(handle or ''), + '@-handle', default=None) + + def handle_from_url(self, url): + return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})', + urllib.parse.unquote(url or ''), '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): + """ + Returns a language code supported by YouTube for the user preferred language. + Returns None if no preferred language set. + """ + preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0] + if not preferred_lang: + return + if preferred_lang not in self._SUPPORTED_LANG_CODES: + raise ExtractorError( + f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.', + expected=True) + elif preferred_lang != 'en': + self.report_warning( + f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.') + return preferred_lang + + def _initialize_consent(self): + cookies = self._get_cookies('https://www.youtube.com/') + if cookies.get('__Secure-3PSID'): + return + 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/') + pref_cookie = cookies.get('PREF') + pref = {} + if pref_cookie: + try: + pref = dict(urllib.parse.parse_qsl(pref_cookie.value)) + except ValueError: + self.report_warning('Failed to parse user PREF cookie' + bug_reports_message()) + pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'}) + self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref)) + + def _initialize_cookie_auth(self): + yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies() + if yt_sapisid or yt_1psapisid or yt_3psapisid: + self.write_debug('Found YouTube account cookies') + + def _real_initialize(self): + self._initialize_pref() + self._initialize_consent() + self._initialize_cookie_auth() + self._check_login_required() + + def _perform_login(self, username, password): + if username.startswith('oauth'): + raise ExtractorError( + f'Login with OAuth is no longer supported. {self._youtube_login_hint}', expected=True) + + self.report_warning( + f'Login with password is not supported for YouTube. {self._youtube_login_hint}') + + @property + def _youtube_login_hint(self): + return (f'{self._login_hint(method="cookies")}. Also see ' + 'https://github.com/yt-dlp/yt-dlp/wiki/Extractors#exporting-youtube-cookies ' + 'for tips on effectively exporting YouTube cookies') + + def _check_login_required(self): + if self._LOGIN_REQUIRED and not self.is_authenticated: + self.raise_login_required( + f'Login details are needed to download this content. {self._youtube_login_hint}', method=None) + + _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=' + _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=' + + def _get_default_ytcfg(self, client='web'): + return copy.deepcopy(INNERTUBE_CLIENTS[client]) + + def _get_innertube_host(self, client='web'): + return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] + + def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): + # try_get but with fallback to default ytcfg client values when present + _func = lambda y: try_get(y, getter, expected_type) + return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) + + def _extract_client_name(self, ytcfg, default_client='web'): + return self._ytcfg_get_safe( + ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], + lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client) + + def _extract_client_version(self, ytcfg, default_client='web'): + return self._ytcfg_get_safe( + ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], + lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client) + + def _select_api_hostname(self, req_api_hostname, default_client=None): + return (self._configuration_arg('innertube_host', [''], ie_key=CONFIGURATION_ARG_KEY)[0] + or req_api_hostname or self._get_innertube_host(default_client or 'web')) + + def _extract_context(self, ytcfg=None, default_client='web'): + context = get_first( + (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) + # Enforce language and tz for extraction + client_context = traverse_obj(context, 'client', expected_type=dict, default={}) + client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) + return context + + @staticmethod + def _make_sid_authorization(scheme, sid, origin, additional_parts): + timestamp = str(round(time.time())) + + hash_parts = [] + if additional_parts: + hash_parts.append(':'.join(additional_parts.values())) + hash_parts.extend([timestamp, sid, origin]) + sidhash = hashlib.sha1(' '.join(hash_parts).encode()).hexdigest() + + parts = [timestamp, sidhash] + if additional_parts: + parts.append(''.join(additional_parts)) + + return f'{scheme} {"_".join(parts)}' + + def _get_sid_cookies(self): + """ + Get SAPISID, 1PSAPISID, 3PSAPISID cookie values + @returns sapisid, 1psapisid, 3psapisid + """ + yt_cookies = self._get_cookies('https://www.youtube.com') + yt_sapisid = try_call(lambda: yt_cookies['SAPISID'].value) + yt_3papisid = try_call(lambda: yt_cookies['__Secure-3PAPISID'].value) + yt_1papisid = try_call(lambda: yt_cookies['__Secure-1PAPISID'].value) + + # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. + # YouTube also falls back to __Secure-3PAPISID if SAPISID is missing. + # See: https://github.com/yt-dlp/yt-dlp/issues/393 + + return yt_sapisid or yt_3papisid, yt_1papisid, yt_3papisid + + def _get_sid_authorization_header(self, origin='https://www.youtube.com', user_session_id=None): + """ + Generate API Session ID Authorization for Innertube requests. Assumes all requests are secure (https). + @param origin: Origin URL + @param user_session_id: Optional User Session ID + @return: Authorization header value + """ + + authorizations = [] + additional_parts = {} + if user_session_id: + additional_parts['u'] = user_session_id + + yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies() + + for scheme, sid in (('SAPISIDHASH', yt_sapisid), + ('SAPISID1PHASH', yt_1psapisid), + ('SAPISID3PHASH', yt_3psapisid)): + if sid: + authorizations.append(self._make_sid_authorization(scheme, sid, origin, additional_parts)) + + if not authorizations: + return None + + return ' '.join(authorizations) + + def _call_api(self, ep, query, video_id, fatal=True, headers=None, + note='Downloading API JSON', errnote='Unable to download API page', + context=None, api_key=None, api_hostname=None, default_client='web'): + + data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} + data.update(query) + real_headers = self.generate_api_headers(default_client=default_client) + real_headers.update({'content-type': 'application/json'}) + if headers: + real_headers.update(headers) + return self._download_json( + f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}', + video_id=video_id, fatal=fatal, note=note, errnote=errnote, + data=json.dumps(data).encode('utf8'), headers=real_headers, + query=filter_dict({ + 'key': self._configuration_arg( + 'innertube_key', [api_key], ie_key=CONFIGURATION_ARG_KEY, casesense=True)[0], + 'prettyPrint': 'false', + }, cndn=lambda _, v: v)) + + def extract_yt_initial_data(self, item_id, webpage, fatal=True): + return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal) + + @staticmethod + def _extract_session_index(*data): + """ + Index of current account in account list. + See: https://github.com/yt-dlp/yt-dlp/pull/519 + """ + for ytcfg in data: + session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) + if session_index is not None: + return session_index + + @staticmethod + def _parse_data_sync_id(data_sync_id): + """ + Parse data_sync_id into delegated_session_id and user_session_id. + + data_sync_id is of the form "delegated_session_id||user_session_id" for secondary channel + and just "user_session_id||" for primary channel. + + @param data_sync_id: data_sync_id string + @return: Tuple of (delegated_session_id, user_session_id) + """ + if not data_sync_id: + return None, None + first, _, second = data_sync_id.partition('||') + if second: + return first, second + return None, first + + def _extract_delegated_session_id(self, *args): + """ + Extract current delegated session ID required to download private playlists of secondary channels + @params response and/or ytcfg + @return: delegated session ID + """ + # ytcfg includes channel_syncid if on secondary channel + if delegated_sid := traverse_obj(args, (..., 'DELEGATED_SESSION_ID', {str}, any)): + return delegated_sid + + data_sync_id = self._extract_data_sync_id(*args) + return self._parse_data_sync_id(data_sync_id)[0] + + def _extract_user_session_id(self, *args): + """ + Extract current user session ID + @params response and/or ytcfg + @return: user session ID + """ + if user_sid := traverse_obj(args, (..., 'USER_SESSION_ID', {str}, any)): + return user_sid + + data_sync_id = self._extract_data_sync_id(*args) + return self._parse_data_sync_id(data_sync_id)[1] + + def _extract_data_sync_id(self, *args): + """ + Extract current account dataSyncId. + In the format DELEGATED_SESSION_ID||USER_SESSION_ID or USER_SESSION_ID|| + @params response and/or ytcfg + """ + if data_sync_id := self._configuration_arg('data_sync_id', [None], ie_key=CONFIGURATION_ARG_KEY, casesense=True)[0]: + return data_sync_id + + return traverse_obj( + args, (..., ('DATASYNC_ID', ('responseContext', 'mainAppWebResponseContext', 'datasyncId')), {str}, any)) + + def _extract_visitor_data(self, *args): + """ + Extracts visitorData from an API response or ytcfg + Appears to be used to track session state + """ + if visitor_data := self._configuration_arg('visitor_data', [None], ie_key=CONFIGURATION_ARG_KEY, casesense=True)[0]: + return visitor_data + return get_first( + args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], + expected_type=str) + + @functools.cached_property + def is_authenticated(self): + return bool(self._get_sid_authorization_header()) + + def extract_ytcfg(self, video_id, webpage): + if not webpage: + return {} + return self._parse_json( + self._search_regex( + r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', + default='{}'), video_id, fatal=False) or {} + + def _generate_cookie_auth_headers(self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, origin=None, **kwargs): + headers = {} + delegated_session_id = delegated_session_id or self._extract_delegated_session_id(ytcfg) + if delegated_session_id: + headers['X-Goog-PageId'] = delegated_session_id + if session_index is None: + session_index = self._extract_session_index(ytcfg) + if delegated_session_id or session_index is not None: + headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 + + auth = self._get_sid_authorization_header(origin, user_session_id=user_session_id or self._extract_user_session_id(ytcfg)) + if auth is not None: + headers['Authorization'] = auth + headers['X-Origin'] = origin + + if traverse_obj(ytcfg, 'LOGGED_IN', expected_type=bool): + headers['X-Youtube-Bootstrap-Logged-In'] = 'true' + + return headers + + def generate_api_headers( + self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, + visitor_data=None, api_hostname=None, default_client='web', **kwargs): + + origin = 'https://' + (self._select_api_hostname(api_hostname, default_client)) + headers = { + 'X-YouTube-Client-Name': str( + self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), + 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), + 'Origin': origin, + 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg), + 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client), + **self._generate_cookie_auth_headers( + ytcfg=ytcfg, + delegated_session_id=delegated_session_id, + user_session_id=user_session_id, + session_index=session_index, + origin=origin), + } + return filter_dict(headers) + + def _download_webpage_with_retries(self, *args, retry_fatal=False, retry_on_status=None, **kwargs): + for retry in self.RetryManager(fatal=retry_fatal): + try: + return self._download_webpage(*args, **kwargs) + except ExtractorError as e: + if isinstance(e.cause, network_exceptions): + if not isinstance(e.cause, HTTPError) or e.cause.status not in (retry_on_status or (403, 429)): + retry.error = e + continue + self._error_or_warning(e, fatal=retry_fatal) + break + + def _download_ytcfg(self, client, video_id): + url = { + 'web': 'https://www.youtube.com', + 'web_music': 'https://music.youtube.com', + 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1', + 'tv': 'https://www.youtube.com/tv', + }.get(client) + if not url: + return {} + webpage = self._download_webpage_with_retries( + url, video_id, note=f'Downloading {client.replace("_", " ").strip()} client config', + headers=traverse_obj(self._get_default_ytcfg(client), { + 'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}), + })) + return self.extract_ytcfg(video_id, webpage) or {} + + @staticmethod + def _build_api_continuation_query(continuation, ctp=None): + query = { + 'continuation': continuation, + } + # TODO: Inconsistency with clickTrackingParams. + # Currently we have a fixed ctp contained within context (from ytcfg) + # and a ctp in root query for continuation. + if ctp: + query['clickTracking'] = {'clickTrackingParams': ctp} + return query + + @classmethod + def _extract_next_continuation_data(cls, renderer): + next_continuation = try_get( + renderer, (lambda x: x['continuations'][0]['nextContinuationData'], + lambda x: x['continuation']['reloadContinuationData']), dict) + if not next_continuation: + return + continuation = next_continuation.get('continuation') + if not continuation: + return + ctp = next_continuation.get('clickTrackingParams') + return cls._build_api_continuation_query(continuation, ctp) + + @classmethod + def _extract_continuation_ep_data(cls, continuation_ep: dict): + if isinstance(continuation_ep, dict): + continuation = try_get( + continuation_ep, lambda x: x['continuationCommand']['token'], str) + if not continuation: + return + ctp = continuation_ep.get('clickTrackingParams') + return cls._build_api_continuation_query(continuation, ctp) + + @classmethod + def _extract_continuation(cls, renderer): + next_continuation = cls._extract_next_continuation_data(renderer) + if next_continuation: + return next_continuation + + return traverse_obj(renderer, ( + ('contents', 'items', 'rows'), ..., 'continuationItemRenderer', + ('continuationEndpoint', ('button', 'buttonRenderer', 'command')), + ), get_all=False, expected_type=cls._extract_continuation_ep_data) + + @classmethod + def _extract_alerts(cls, data): + for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: + if not isinstance(alert_dict, dict): + continue + for alert in alert_dict.values(): + alert_type = alert.get('type') + if not alert_type: + continue + message = cls._get_text(alert, 'text') + if message: + yield alert_type, message + + def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): + errors, warnings = [], [] + for alert_type, alert_message in alerts: + if alert_type.lower() == 'error' and fatal: + errors.append([alert_type, alert_message]) + elif alert_message not in self._IGNORED_WARNINGS: + warnings.append([alert_type, alert_message]) + + for alert_type, alert_message in (warnings + errors[:-1]): + self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once) + if errors: + raise ExtractorError(f'YouTube said: {errors[-1][1]}', expected=expected) + + def _extract_and_report_alerts(self, data, *args, **kwargs): + return self._report_alerts(self._extract_alerts(data), *args, **kwargs) + + 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, + '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_VERIFIED': BadgeType.VERIFIED, + 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED, + } + + label_map = { + 'unlisted': BadgeType.AVAILABILITY_UNLISTED, + 'private': BadgeType.AVAILABILITY_PRIVATE, + 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION, + 'live': BadgeType.LIVE_NOW, + 'premium': BadgeType.AVAILABILITY_PREMIUM, + 'verified': BadgeType.VERIFIED, + 'official artist channel': BadgeType.VERIFIED, + } + + badges = [] + for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))): + badge_type = ( + icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str)) + or badge_style_map.get(traverse_obj(badge, 'style')) + ) + if badge_type: + badges.append({'type': badge_type}) + continue + + # fallback, won't work in some languages + 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': label_badge_type}) + break + + return badges + + @staticmethod + def _has_badge(badges, badge_type): + return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type)) + + @staticmethod + def _get_text(data, *path_list, max_runs=None): + for path in path_list or [None]: + if path is None: + obj = [data] + else: + obj = traverse_obj(data, path, default=[]) + if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): + obj = [obj] + for item in obj: + text = try_get(item, lambda x: x['simpleText'], str) + if text: + return text + runs = try_get(item, lambda x: x['runs'], list) or [] + if not runs and isinstance(item, list): + runs = item + + runs = runs[:min(len(runs), max_runs or len(runs))] + text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str)) + if text: + return text + + def _get_count(self, data, *path_list): + count_text = self._get_text(data, *path_list) or '' + count = parse_count(count_text) + if count is None: + count = str_to_int( + self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None)) + return count + + @staticmethod + def _extract_thumbnails(data, *path_list, final_key='thumbnails'): + """ + Extract thumbnails from thumbnails dict + @param path_list: path list to level that contains 'thumbnails' key + """ + thumbnails = [] + for path in path_list or [()]: + for thumbnail in traverse_obj(data, (*variadic(path), final_key, ...)): + thumbnail_url = url_or_none(thumbnail.get('url')) + if not thumbnail_url: + continue + # Sometimes youtube gives a wrong thumbnail URL. See: + # https://github.com/yt-dlp/yt-dlp/issues/233 + # https://github.com/ytdl-org/youtube-dl/issues/28023 + if 'maxresdefault' in thumbnail_url: + thumbnail_url = thumbnail_url.split('?')[0] + thumbnails.append({ + 'url': thumbnail_url, + 'height': int_or_none(thumbnail.get('height')), + 'width': int_or_none(thumbnail.get('width')), + }) + return thumbnails + + @staticmethod + 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', '8 yr ago' + """ + + # 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: + return datetime_from_str(start) + try: + return datetime_from_str('now-{}{}'.format(mobj.group('time'), mobj.group('unit'))) + except ValueError: + return None + + def _parse_time_text(self, text): + if not text: + return + dt_ = self.extract_relative_time(text) + timestamp = None + if isinstance(dt_, dt.datetime): + timestamp = calendar.timegm(dt_.timetuple()) + + if timestamp is None: + timestamp = ( + unified_timestamp(text) or unified_timestamp( + self._search_regex( + (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'), + text.lower(), 'time text', default=None))) + + if text and timestamp is None and self._preferred_lang in (None, 'en'): + self.report_warning( + f'Cannot parse localized time text "{text}"', only_once=True) + return timestamp + + 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'): + raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=CONFIGURATION_ARG_KEY)) + # 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 its result MUST be checked if the manager is non fatal + while True: + try: + response = self._call_api( + ep=ep, fatal=True, headers=headers, + video_id=item_id, query=query, note=note, + context=self._extract_context(ytcfg, default_client), + api_hostname=api_hostname, default_client=default_client) + except ExtractorError as e: + if not isinstance(e.cause, network_exceptions): + return self._error_or_warning(e, fatal=fatal) + elif not isinstance(e.cause, HTTPError): + main_rm.error = e + next(main_retries) + continue + + 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.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 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.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'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(): + 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)): + icd_rm.error = ExtractorError('Incomplete data received', expected=True) + should_retry = next(icd_retries, None) + if not should_retry: + return None + continue + + return response + + @staticmethod + def is_music_url(url): + return re.match(r'(https?://)?music\.youtube\.com/', url) is not None diff --git a/yt_dlp/extractor/youtube/_clip.py b/yt_dlp/extractor/youtube/_clip.py new file mode 100644 index 000000000..7d063700e --- /dev/null +++ b/yt_dlp/extractor/youtube/_clip.py @@ -0,0 +1,66 @@ +from ._tab import YoutubeTabBaseInfoExtractor +from ._video import YoutubeIE +from ...utils import ExtractorError, traverse_obj + + +class YoutubeClipIE(YoutubeTabBaseInfoExtractor): + IE_NAME = 'youtube:clip' + _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)' + _TESTS = [{ + # FIXME: Other metadata should be extracted from the clip, not from the base video + 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ', + 'info_dict': { + 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ', + 'ext': 'mp4', + 'section_start': 29.0, + 'section_end': 39.7, + 'duration': 10.7, + 'age_limit': 0, + 'availability': 'public', + 'categories': ['Gaming'], + 'channel': 'Scott The Woz', + 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ', + 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ', + 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7', + 'like_count': int, + 'playable_in_embed': True, + 'tags': 'count:17', + 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp', + 'title': 'Mobile Games on Console - Scott The Woz', + 'upload_date': '20210920', + 'uploader': 'Scott The Woz', + 'uploader_id': '@ScottTheWoz', + 'uploader_url': 'https://www.youtube.com/@ScottTheWoz', + 'view_count': int, + 'live_status': 'not_live', + 'channel_follower_count': int, + 'chapters': 'count:20', + 'comment_count': int, + 'heatmap': 'count:100', + }, + }] + + def _real_extract(self, url): + clip_id = self._match_id(url) + _, data = self._extract_webpage(url, clip_id) + + video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId')) + if not video_id: + raise ExtractorError('Unable to find video ID') + + clip_data = traverse_obj(data, ( + 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer', + 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ..., + 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command', + 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False) + + return { + '_type': 'url_transparent', + 'url': f'https://www.youtube.com/watch?v={video_id}', + 'ie_key': YoutubeIE.ie_key(), + 'id': clip_id, + 'section_start': int(clip_data['startTimeMs']) / 1000, + 'section_end': int(clip_data['endTimeMs']) / 1000, + '_format_sort_fields': ( # https protocol is prioritized for ffmpeg compatibility + 'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang'), + } diff --git a/yt_dlp/extractor/youtube/_mistakes.py b/yt_dlp/extractor/youtube/_mistakes.py new file mode 100644 index 000000000..c5eb5161c --- /dev/null +++ b/yt_dlp/extractor/youtube/_mistakes.py @@ -0,0 +1,69 @@ + +from ._base import YoutubeBaseInfoExtractor +from ...utils import ExtractorError + + +class YoutubeTruncatedURLIE(YoutubeBaseInfoExtractor): + IE_NAME = 'youtube:truncated_url' + IE_DESC = False # Do not list + _VALID_URL = r'''(?x) + (?:https?://)? + (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ + (?:watch\?(?: + feature=[a-z_]+| + annotation_id=annotation_[^&]+| + x-yt-cl=[0-9]+| + hl=[^&]*| + t=[0-9]+ + )? + | + attribution_link\?a=[^&]+ + ) + $ + ''' + + _TESTS = [{ + 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?feature=foo', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?hl=en-GB', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?t=2372', + 'only_matching': True, + }] + + def _real_extract(self, url): + raise ExtractorError( + 'Did you forget to quote the URL? Remember that & is a meta ' + 'character in most shells, so you want to put the URL in quotes, ' + 'like yt-dlp ' + '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' + ' or simply yt-dlp BaW_jenozKc .', + expected=True) + + +class YoutubeTruncatedIDIE(YoutubeBaseInfoExtractor): + IE_NAME = 'youtube:truncated_id' + IE_DESC = False # Do not list + _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' + + _TESTS = [{ + 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + raise ExtractorError( + f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.', + expected=True) diff --git a/yt_dlp/extractor/youtube/_notifications.py b/yt_dlp/extractor/youtube/_notifications.py new file mode 100644 index 000000000..ae55528da --- /dev/null +++ b/yt_dlp/extractor/youtube/_notifications.py @@ -0,0 +1,98 @@ +import itertools +import re + +from ._tab import YoutubeTabBaseInfoExtractor, YoutubeTabIE +from ._video import YoutubeIE +from ...utils import traverse_obj + + +class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor): + IE_NAME = 'youtube:notif' + IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)' + _VALID_URL = r':ytnotif(?:ication)?s?' + _LOGIN_REQUIRED = True + _TESTS = [{ + 'url': ':ytnotif', + 'only_matching': True, + }, { + 'url': ':ytnotifications', + 'only_matching': True, + }] + + def _extract_notification_menu(self, response, continuation_list): + notification_list = traverse_obj( + response, + ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'), + ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'), + expected_type=list) or [] + continuation_list[0] = None + for item in notification_list: + entry = self._extract_notification_renderer(item.get('notificationRenderer')) + if entry: + yield entry + continuation = item.get('continuationItemRenderer') + if continuation: + continuation_list[0] = continuation + + def _extract_notification_renderer(self, notification): + video_id = traverse_obj( + notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) + url = f'https://www.youtube.com/watch?v={video_id}' + channel_id = None + if not video_id: + browse_ep = traverse_obj( + notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict) + 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) + if not channel_id or not post_id: + return + # The direct /post url redirects to this in the browser + url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}' + + channel = traverse_obj( + notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'), + expected_type=str) + notification_title = self._get_text(notification, 'shortMessage') + if notification_title: + notification_title = notification_title.replace('\xad', '') # remove soft hyphens + # TODO: handle recommended videos + title = self._search_regex( + rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title, + 'video title', default=None) + timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText')) + if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE) + else None) + return { + '_type': 'url', + 'url': url, + 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(), + 'video_id': video_id, + 'title': title, + 'channel_id': channel_id, + 'channel': channel, + 'uploader': channel, + 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'), + 'timestamp': timestamp, + } + + def _notification_menu_entries(self, ytcfg): + continuation_list = [None] + response = None + for page in itertools.count(1): + ctoken = traverse_obj( + continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str) + response = self._extract_response( + item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg, + ep='notification/get_notification_menu', check_get_keys='actions', + headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))) + yield from self._extract_notification_menu(response, continuation_list) + if not continuation_list[0]: + break + + def _real_extract(self, url): + display_id = 'notifications' + ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {} + self._report_playlist_authcheck(ytcfg) + return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id) diff --git a/yt_dlp/extractor/youtube/_redirect.py b/yt_dlp/extractor/youtube/_redirect.py new file mode 100644 index 000000000..1908df124 --- /dev/null +++ b/yt_dlp/extractor/youtube/_redirect.py @@ -0,0 +1,247 @@ +import base64 +import urllib.parse + +from ._base import YoutubeBaseInfoExtractor +from ._tab import YoutubeTabIE +from ...utils import ExtractorError, classproperty, parse_qs, update_url_query, url_or_none + + +class YoutubeYtBeIE(YoutubeBaseInfoExtractor): + IE_DESC = 'youtu.be' + _VALID_URL = rf'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{{11}})/*?.*?\blist=(?P<playlist_id>{YoutubeBaseInfoExtractor._PLAYLIST_ID_RE})' + _TESTS = [{ + 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', + 'info_dict': { + 'id': 'yeWKywCrFtk', + '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/@backuspagemuseum', + 'upload_date': '20161008', + 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', + 'categories': ['Nonprofits & Activism'], + 'tags': list, + 'like_count': int, + 'age_limit': 0, + 'playable_in_embed': True, + 'thumbnail': r're:^https?://.*\.webp', + 'channel': 'Backus-Page House Museum', + 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', + 'live_status': 'not_live', + 'view_count': int, + 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw', + 'availability': 'public', + 'duration': 59, + 'comment_count': int, + 'channel_follower_count': int, + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, + }, + }, { + 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = self._match_valid_url(url) + video_id = mobj.group('id') + playlist_id = mobj.group('playlist_id') + return self.url_result( + update_url_query('https://www.youtube.com/watch', { + 'v': video_id, + 'list': playlist_id, + 'feature': 'youtu.be', + }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) + + +class YoutubeLivestreamEmbedIE(YoutubeBaseInfoExtractor): + IE_DESC = 'YouTube livestream embeds' + _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)' + _TESTS = [{ + 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA', + 'only_matching': True, + }] + + def _real_extract(self, url): + channel_id = self._match_id(url) + return self.url_result( + f'https://www.youtube.com/channel/{channel_id}/live', + ie=YoutubeTabIE.ie_key(), video_id=channel_id) + + +class YoutubeYtUserIE(YoutubeBaseInfoExtractor): + IE_DESC = 'YouTube user videos; "ytuser:" prefix' + IE_NAME = 'youtube:user' + _VALID_URL = r'ytuser:(?P<id>.+)' + _TESTS = [{ + 'url': 'ytuser:phihag', + 'only_matching': True, + }] + + def _real_extract(self, url): + user_id = self._match_id(url) + return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id) + + +class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): + IE_NAME = 'youtube:favorites' + IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)' + _VALID_URL = r':ytfav(?:ou?rite)?s?' + _LOGIN_REQUIRED = True + _TESTS = [{ + 'url': ':ytfav', + 'only_matching': True, + }, { + 'url': ':ytfavorites', + 'only_matching': True, + }] + + def _real_extract(self, url): + return self.url_result( + 'https://www.youtube.com/playlist?list=LL', + ie=YoutubeTabIE.ie_key()) + + +class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): + """ + Base class for feed extractors + Subclasses must re-define the _FEED_NAME property. + """ + _LOGIN_REQUIRED = True + _FEED_NAME = 'feeds' + + @classproperty + def IE_NAME(cls): + return f'youtube:{cls._FEED_NAME}' + + def _real_extract(self, url): + return self.url_result( + f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key()) + + +class YoutubeWatchLaterIE(YoutubeBaseInfoExtractor): + IE_NAME = 'youtube:watchlater' + IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)' + _VALID_URL = r':ytwatchlater' + _TESTS = [{ + 'url': ':ytwatchlater', + 'only_matching': True, + }] + + def _real_extract(self, url): + return self.url_result( + 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) + + +class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): + IE_DESC = 'YouTube recommended videos; ":ytrec" keyword' + _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' + _FEED_NAME = 'recommended' + _LOGIN_REQUIRED = False + _TESTS = [{ + 'url': ':ytrec', + 'only_matching': True, + }, { + 'url': ':ytrecommended', + 'only_matching': True, + }, { + 'url': 'https://youtube.com', + 'only_matching': True, + }] + + +class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): + IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)' + _VALID_URL = r':ytsub(?:scription)?s?' + _FEED_NAME = 'subscriptions' + _TESTS = [{ + 'url': ':ytsubs', + 'only_matching': True, + }, { + 'url': ':ytsubscriptions', + 'only_matching': True, + }] + + +class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): + IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)' + _VALID_URL = r':ythis(?:tory)?' + _FEED_NAME = 'history' + _TESTS = [{ + 'url': ':ythistory', + 'only_matching': True, + }] + + +class YoutubeShortsAudioPivotIE(YoutubeBaseInfoExtractor): + IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)' + IE_NAME = 'youtube:shorts:pivot:audio' + _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts' + _TESTS = [{ + 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts', + 'only_matching': True, + }] + + @staticmethod + def _generate_audio_pivot_params(video_id): + """ + Generates sfv_audio_pivot browse params for this video id + """ + pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3) + return urllib.parse.quote(base64.b64encode(pb_params).decode()) + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}', + ie=YoutubeTabIE) + + +class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor): + IE_NAME = 'youtube:consent' + IE_DESC = False # Do not list + _VALID_URL = r'https?://consent\.youtube\.com/m\?' + _TESTS = [{ + 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1', + 'info_dict': { + 'id': 'qVv6vCqciTM', + 'ext': 'mp4', + 'age_limit': 0, + 'uploader_id': '@sana_natori', + 'comment_count': int, + 'chapters': 'count:13', + 'upload_date': '20221223', + 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg', + 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA', + 'uploader_url': 'https://www.youtube.com/@sana_natori', + 'like_count': int, + 'release_date': '20221223', + 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'], + 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】', + 'view_count': int, + 'playable_in_embed': True, + 'duration': 4438, + 'availability': 'public', + 'channel_follower_count': int, + 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA', + 'categories': ['Entertainment'], + 'live_status': 'was_live', + 'release_timestamp': 1671793345, + 'channel': 'さなちゃんねる', + 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d', + 'uploader': 'さなちゃんねる', + 'channel_is_verified': True, + 'heatmap': 'count:100', + }, + 'add_ie': ['Youtube'], + 'params': {'skip_download': 'Youtube'}, + }] + + def _real_extract(self, url): + redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1]) + if not redirect_url: + raise ExtractorError('Invalid cookie consent redirect URL', expected=True) + return self.url_result(redirect_url) diff --git a/yt_dlp/extractor/youtube/_search.py b/yt_dlp/extractor/youtube/_search.py new file mode 100644 index 000000000..be10a20da --- /dev/null +++ b/yt_dlp/extractor/youtube/_search.py @@ -0,0 +1,167 @@ +import urllib.parse + +from ._tab import YoutubeTabBaseInfoExtractor +from ..common import SearchInfoExtractor +from ...utils import join_nonempty, parse_qs + + +class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): + IE_DESC = 'YouTube search' + IE_NAME = 'youtube:search' + _SEARCH_KEY = 'ytsearch' + _SEARCH_PARAMS = 'EgIQAfABAQ==' # Videos only + _TESTS = [{ + 'url': 'ytsearch5:youtube-dl test video', + 'playlist_count': 5, + 'info_dict': { + 'id': 'youtube-dl test video', + 'title': 'youtube-dl test video', + }, + }, { + 'note': 'Suicide/self-harm search warning', + 'url': 'ytsearch1:i hate myself and i wanna die', + 'playlist_count': 1, + 'info_dict': { + 'id': 'i hate myself and i wanna die', + 'title': 'i hate myself and i wanna die', + }, + }] + + +class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): + IE_NAME = YoutubeSearchIE.IE_NAME + ':date' + _SEARCH_KEY = 'ytsearchdate' + IE_DESC = 'YouTube search, newest videos first' + _SEARCH_PARAMS = 'CAISAhAB8AEB' # Videos only, sorted by date + _TESTS = [{ + 'url': 'ytsearchdate5:youtube-dl test video', + 'playlist_count': 5, + 'info_dict': { + 'id': 'youtube-dl test video', + 'title': 'youtube-dl test video', + }, + }] + + +class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): + IE_DESC = 'YouTube search URLs with sorting and filter support' + IE_NAME = YoutubeSearchIE.IE_NAME + '_url' + _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' + _TESTS = [{ + 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', + 'playlist_mincount': 5, + 'info_dict': { + 'id': 'youtube-dl test video', + 'title': 'youtube-dl test video', + }, + }, { + 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D', + 'playlist_mincount': 5, + 'info_dict': { + 'id': 'python', + 'title': 'python', + }, + }, { + 'url': 'https://www.youtube.com/results?search_query=%23cats', + 'playlist_mincount': 1, + 'info_dict': { + 'id': '#cats', + 'title': '#cats', + # The test suite does not have support for nested playlists + # 'entries': [{ + # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats', + # 'title': '#cats', + # }], + }, + }, { + # Channel results + 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D', + 'info_dict': { + 'id': 'kurzgesagt', + 'title': 'kurzgesagt', + }, + 'playlist': [{ + 'info_dict': { + '_type': 'url', + 'id': 'UCsXVk37bltHxD1rDPwtNM8Q', + 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q', + 'ie_key': 'YoutubeTab', + 'channel': 'Kurzgesagt – In a Nutshell', + 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc', + 'title': 'Kurzgesagt – In a Nutshell', + 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q', + # 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, + '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'}, + 'playlist_mincount': 1, + }, { + 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', + 'only_matching': True, + }] + + def _real_extract(self, url): + qs = parse_qs(url) + query = (qs.get('search_query') or qs.get('q'))[0] + return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) + + +class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor): + IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs' + IE_NAME = 'youtube:music:search_url' + _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' + _TESTS = [{ + 'url': 'https://music.youtube.com/search?q=royalty+free+music', + 'playlist_count': 16, + 'info_dict': { + 'id': 'royalty free music', + 'title': 'royalty free music', + }, + }, { + 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D', + 'playlist_mincount': 30, + 'info_dict': { + 'id': 'royalty free music - songs', + 'title': 'royalty free music - songs', + }, + 'params': {'extract_flat': 'in_playlist'}, + }, { + 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists', + 'playlist_mincount': 30, + 'info_dict': { + 'id': 'royalty free music - community playlists', + 'title': 'royalty free music - community playlists', + }, + 'params': {'extract_flat': 'in_playlist'}, + }] + + _SECTIONS = { + 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==', + 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==', + 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF', + 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==', + 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==', + 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==', + } + + def _real_extract(self, url): + qs = parse_qs(url) + query = (qs.get('search_query') or qs.get('q'))[0] + params = qs.get('sp', (None,))[0] + if params: + section = next((k for k, v in self._SECTIONS.items() if v == params), params) + else: + section = urllib.parse.unquote_plus(([*url.split('#'), ''])[1]).lower() + params = self._SECTIONS.get(section) + if not params: + section = None + title = join_nonempty(query, section, delim=' - ') + return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title) diff --git a/yt_dlp/extractor/youtube/_tab.py b/yt_dlp/extractor/youtube/_tab.py new file mode 100644 index 000000000..122300e60 --- /dev/null +++ b/yt_dlp/extractor/youtube/_tab.py @@ -0,0 +1,2348 @@ +import functools +import itertools +import re +import shlex +import urllib.parse + +from ._base import BadgeType, YoutubeBaseInfoExtractor +from ._video import YoutubeIE +from ...networking.exceptions import HTTPError, network_exceptions +from ...utils import ( + NO_DEFAULT, + ExtractorError, + UserNotLive, + bug_reports_message, + format_field, + get_first, + int_or_none, + parse_count, + parse_duration, + parse_qs, + smuggle_url, + str_to_int, + strftime_or_none, + traverse_obj, + try_get, + unsmuggle_url, + update_url_query, + url_or_none, + urljoin, + variadic, +) + + +class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): + @staticmethod + def passthrough_smuggled_data(func): + def _smuggle(info, smuggled_data): + if info.get('_type') not in ('url', 'url_transparent'): + return info + if smuggled_data.get('is_music_url'): + parsed_url = urllib.parse.urlparse(info['url']) + if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'): + smuggled_data.pop('is_music_url') + info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com')) + if smuggled_data: + info['url'] = smuggle_url(info['url'], smuggled_data) + return info + + @functools.wraps(func) + def wrapper(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + if self.is_music_url(url): + smuggled_data['is_music_url'] = True + info_dict = func(self, url, smuggled_data) + if smuggled_data: + _smuggle(info_dict, smuggled_data) + if info_dict.get('entries'): + info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries']) + return info_dict + return wrapper + + @staticmethod + def _extract_basic_item_renderer(item): + # Modified from _extract_grid_item_renderer + known_basic_renderers = ( + 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer', + ) + for key, renderer in item.items(): + if not isinstance(renderer, dict): + continue + elif key in known_basic_renderers: + return renderer + elif key.startswith('grid') and key.endswith('Renderer'): + return renderer + + def _extract_video(self, renderer): + video_id = renderer.get('videoId') + + reel_header_renderer = traverse_obj(renderer, ( + 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer', + 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer')) + + title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText') + description = self._get_text(renderer, 'descriptionSnippet') + + duration = int_or_none(renderer.get('lengthSeconds')) + if duration is None: + duration = parse_duration(self._get_text( + renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) + if duration is None: + # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab) + duration = parse_duration(self._search_regex( + r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$', + traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str), + video_id, default=None, group='duration')) + + channel_id = traverse_obj( + renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), + expected_type=str, get_all=False) + 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(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 '' + url = f'https://www.youtube.com/watch?v={video_id}' + if overlay_style == 'SHORTS' or '/shorts/' in navigation_url: + url = f'https://www.youtube.com/shorts/{video_id}' + + time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo') + or self._get_text(reel_header_renderer, 'timestampText') or '') + scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False)) + + live_status = ( + 'is_upcoming' if scheduled_timestamp is not None + else 'was_live' if 'streamed' in time_text.lower() + else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW) + else None) + + # videoInfo is a string like '50K views • 10 years ago'. + view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or '' + view_count = (0 if 'no views' in view_count_text.lower() + 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(), + 'id': video_id, + 'url': url, + 'title': title, + 'description': description, + 'duration': duration, + 'channel_id': channel_id, + '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) + else None), + 'release_timestamp': scheduled_timestamp, + 'availability': + 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) + else self._availability( + is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None, + needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None, + 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, + 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None, + } + + def _extract_channel_renderer(self, renderer): + channel_id = self.ucid_or_none(renderer['channelId']) + title = self._get_text(renderer, 'title') + 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, + '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': ( + # 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): + for item in grid_renderer['items']: + if not isinstance(item, dict): + continue + if lockup_view_model := traverse_obj(item, ('lockupViewModel', {dict})): + if entry := self._extract_lockup_view_model(lockup_view_model): + yield entry + continue + renderer = self._extract_basic_item_renderer(item) + if not isinstance(renderer, dict): + continue + title = self._get_text(renderer, 'title') + + # playlist + 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=title) + continue + # video + video_id = renderer.get('videoId') + if video_id: + yield self._extract_video(renderer) + continue + # channel + channel_id = renderer.get('channelId') + if channel_id: + yield self._extract_channel_renderer(renderer) + continue + # generic endpoint URL support + ep_url = urljoin('https://www.youtube.com/', try_get( + renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], + str)) + if ep_url: + + for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): + if ie.suitable(ep_url): + yield self.url_result( + ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) + break + + 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, title=title) + playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) + if playlist_id: + video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) + if video_id: + return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}', + ie=YoutubeTabIE.ie_key(), video_id=playlist_id) + return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}', + ie=YoutubeTabIE.ie_key(), video_id=playlist_id) + browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId')) + if browse_id: + return self.url_result(f'https://music.youtube.com/browse/{browse_id}', + ie=YoutubeTabIE.ie_key(), video_id=browse_id) + + def _shelf_entries_from_content(self, shelf_renderer): + content = shelf_renderer.get('content') + if not isinstance(content, dict): + return + renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') + if renderer: + # TODO: add support for nested playlists so each shelf is processed + # as separate playlist + # TODO: this includes only first N items + yield from self._grid_entries(renderer) + renderer = content.get('horizontalListRenderer') + if renderer: + # TODO: handle case + pass + + def _shelf_entries(self, shelf_renderer, skip_channels=False): + ep = try_get( + shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], + str) + shelf_url = urljoin('https://www.youtube.com', ep) + if shelf_url: + # Skipping links to another channels, note that checking for + # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL + # will not work + if skip_channels and '/channels?' in shelf_url: + return + title = self._get_text(shelf_renderer, 'title') + yield self.url_result(shelf_url, video_title=title) + # Shelf may not contain shelf URL, fallback to extraction from content + yield from self._shelf_entries_from_content(shelf_renderer) + + def _playlist_entries(self, video_list_renderer): + for content in video_list_renderer['contents']: + if not isinstance(content, dict): + continue + renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') + if not isinstance(renderer, dict): + continue + video_id = renderer.get('videoId') + if not video_id: + continue + yield self._extract_video(renderer) + + def _extract_lockup_view_model(self, view_model): + content_id = view_model.get('contentId') + if not content_id: + return + content_type = view_model.get('contentType') + if content_type not in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'): + self.report_warning( + f'Unsupported lockup view model content type "{content_type}"{bug_reports_message()}', only_once=True) + return + return self.url_result( + f'https://www.youtube.com/playlist?list={content_id}', ie=YoutubeTabIE, video_id=content_id, + title=traverse_obj(view_model, ( + 'metadata', 'lockupMetadataViewModel', 'title', 'content', {str})), + thumbnails=self._extract_thumbnails(view_model, ( + 'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image'), final_key='sources')) + + def _rich_entries(self, rich_grid_renderer): + if lockup_view_model := traverse_obj(rich_grid_renderer, ('content', 'lockupViewModel', {dict})): + if entry := self._extract_lockup_view_model(lockup_view_model): + yield entry + return + renderer = traverse_obj( + rich_grid_renderer, + ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel'), any)) or {} + video_id = renderer.get('videoId') + 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 + # shortsLockupViewModel extraction + entity_id = renderer.get('entityId') + if entity_id: + video_id = traverse_obj(renderer, ('onTap', 'innertubeCommand', 'reelWatchEndpoint', 'videoId', {str})) + if not video_id: + return + yield self.url_result( + f'https://www.youtube.com/shorts/{video_id}', + ie=YoutubeIE, video_id=video_id, + **traverse_obj(renderer, { + 'title': (( + ('overlayMetadata', 'primaryText', 'content', {str}), + ('accessibilityText', {lambda x: re.fullmatch(r'(.+), (?:[\d,.]+(?:[KM]| million)?|No) views? - play Short', x)}, 1)), any), + 'view_count': ('overlayMetadata', 'secondaryText', 'content', {parse_count}), + }), + thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources')) + return + + def _video_entry(self, video_renderer): + video_id = video_renderer.get('videoId') + if video_id: + return self._extract_video(video_renderer) + + def _hashtag_tile_entry(self, hashtag_tile_renderer): + url = urljoin('https://youtube.com', traverse_obj( + hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url'))) + if url: + return self.url_result( + url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag')) + + def _post_thread_entries(self, post_thread_renderer): + post_renderer = try_get( + post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) + if not post_renderer: + return + # video attachment + video_renderer = try_get( + post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} + video_id = video_renderer.get('videoId') + if video_id: + entry = self._extract_video(video_renderer) + if entry: + yield entry + # playlist attachment + playlist_id = try_get( + post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str) + if playlist_id: + yield self.url_result( + f'https://www.youtube.com/playlist?list={playlist_id}', + ie=YoutubeTabIE.ie_key(), video_id=playlist_id) + # inline video links + runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] + for run in runs: + if not isinstance(run, dict): + continue + ep_url = try_get( + run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str) + if not ep_url: + continue + if not YoutubeIE.suitable(ep_url): + continue + ep_video_id = YoutubeIE._match_id(ep_url) + if video_id == ep_video_id: + continue + yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) + + def _post_thread_continuation_entries(self, post_thread_continuation): + contents = post_thread_continuation.get('contents') + if not isinstance(contents, list): + return + for content in contents: + renderer = content.get('backstagePostThreadRenderer') + if isinstance(renderer, dict): + yield from self._post_thread_entries(renderer) + continue + renderer = content.get('videoRenderer') + if isinstance(renderer, dict): + yield self._video_entry(renderer) + + r''' # unused + def _rich_grid_entries(self, contents): + for content in contents: + video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) + if video_renderer: + entry = self._video_entry(video_renderer) + if entry: + yield entry + ''' + + def _report_history_entries(self, renderer): + for url in traverse_obj(renderer, ( + 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ..., + 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ..., + 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')): + yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE) + + def _extract_entries(self, parent_renderer, continuation_list): + # continuation_list is modified in-place with continuation_list = [continuation_token] + continuation_list[:] = [None] + contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] + for content in contents: + if not isinstance(content, dict): + continue + is_renderer = traverse_obj( + content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation', + expected_type=dict) + if not is_renderer: + if content.get('richItemRenderer'): + for entry in self._rich_entries(content['richItemRenderer']): + yield entry + continuation_list[0] = self._extract_continuation(parent_renderer) + elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory + table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer')) + yield from self._report_history_entries(table) + continuation_list[0] = self._extract_continuation(table) + continue + + isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] + for isr_content in isr_contents: + if not isinstance(isr_content, dict): + continue + + known_renderers = { + 'playlistVideoListRenderer': self._playlist_entries, + 'gridRenderer': self._grid_entries, + 'reelShelfRenderer': self._grid_entries, + 'shelfRenderer': self._shelf_entries, + 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)], + 'backstagePostThreadRenderer': self._post_thread_entries, + '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)], + 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list), + 'lockupViewModel': lambda x: [self._extract_lockup_view_model(x)], + } + for key, renderer in isr_content.items(): + if key not in known_renderers: + continue + for entry in known_renderers[key](renderer): + if entry: + yield entry + continuation_list[0] = self._extract_continuation(renderer) + break + + if not continuation_list[0]: + continuation_list[0] = self._extract_continuation(is_renderer) + + if not continuation_list[0]: + continuation_list[0] = self._extract_continuation(parent_renderer) + + def _entries(self, tab, item_id, ytcfg, delegated_session_id, visitor_data): + continuation_list = [None] + extract_entries = lambda x: self._extract_entries(x, continuation_list) + tab_content = try_get(tab, lambda x: x['content'], dict) + if not tab_content: + return + parent_renderer = ( + try_get(tab_content, lambda x: x['sectionListRenderer'], dict) + 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, delegated_session_id=delegated_session_id, visitor_data=visitor_data) + response = self._extract_response( + item_id=f'{item_id} page {page_num}', + query=continuation, headers=headers, ytcfg=ytcfg, + check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) + + if not response: + break + # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases + # See: https://github.com/ytdl-org/youtube-dl/issues/28702 + visitor_data = self._extract_visitor_data(response) or visitor_data + + known_renderers = { + 'videoRenderer': (self._grid_entries, 'items'), # for membership tab + 'gridPlaylistRenderer': (self._grid_entries, 'items'), + 'gridVideoRenderer': (self._grid_entries, 'items'), + 'gridChannelRenderer': (self._grid_entries, 'items'), + 'playlistVideoRenderer': (self._playlist_entries, 'contents'), + 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds + 'richItemRenderer': (extract_entries, 'contents'), # for hashtag + 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'), + 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'), + 'playlistVideoListContinuation': (self._playlist_entries, None), + 'gridContinuation': (self._grid_entries, None), + 'itemSectionContinuation': (self._post_thread_continuation_entries, None), + 'sectionListContinuation': (extract_entries, None), # for feeds + } + + continuation_items = traverse_obj(response, ( + ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ..., + 'appendContinuationItemsAction', 'continuationItems', + ), 'continuationContents', get_all=False) + continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={}) + + video_items_renderer = None + for key in continuation_item: + if key not in known_renderers: + continue + func, parent_key = known_renderers[key] + video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items + continuation_list = [None] + yield from func(video_items_renderer) + continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) + + if not video_items_renderer: + break + + @staticmethod + def _extract_selected_tab(tabs, fatal=True): + for tab_renderer in tabs: + if tab_renderer.get('selected'): + return tab_renderer + if fatal: + raise ExtractorError('Unable to find selected tab') + + @staticmethod + def _extract_tab_renderers(response): + return traverse_obj( + response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict) + + def _extract_from_tabs(self, item_id, ytcfg, data, tabs): + metadata = self._extract_metadata_from_tabs(item_id, data) + + selected_tab = self._extract_selected_tab(tabs) + metadata['title'] += format_field(selected_tab, 'title', ' - %s') + metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s') + + return self.playlist_result( + self._entries( + selected_tab, metadata['id'], ytcfg, + self._extract_delegated_session_id(ytcfg, data), + self._extract_visitor_data(data, ytcfg)), + **metadata) + + def _extract_metadata_from_tabs(self, item_id, data): + info = {'id': item_id} + + 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({ + 'channel': metadata_renderer.get('title'), + 'channel_id': channel_id, + }) + if info['channel_id']: + info['id'] = info['channel_id'] + else: + metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict) + + # pageHeaderViewModel slow rollout began April 2024 + page_header_view_model = traverse_obj(data, ( + 'header', 'pageHeaderRenderer', 'content', 'pageHeaderViewModel', {dict})) + + # We can get the uncropped banner/avatar by replacing the crop params with '=s0' + # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714 + def _get_uncropped(url): + return url_or_none((url or '').split('=')[0] + '=s0') + + avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar') + if avatar_thumbnails: + uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url']) + if uncropped_avatar: + avatar_thumbnails.append({ + 'url': uncropped_avatar, + 'id': 'avatar_uncropped', + 'preference': 1, + }) + + channel_banners = ( + self._extract_thumbnails(data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner'))) + or self._extract_thumbnails( + page_header_view_model, ('banner', 'imageBannerViewModel', 'image'), final_key='sources')) + for banner in channel_banners: + banner['preference'] = -10 + + if channel_banners: + uncropped_banner = _get_uncropped(channel_banners[0]['url']) + if uncropped_banner: + channel_banners.append({ + 'url': uncropped_banner, + 'id': 'banner_uncropped', + 'preference': -5, + }) + + # Deprecated - remove primary_sidebar_renderer when layout discontinued + primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') + playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict) + + primary_thumbnails = self._extract_thumbnails( + primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail')) + playlist_thumbnails = self._extract_thumbnails( + playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail')) + + info.update({ + 'title': (traverse_obj(metadata_renderer, 'title') + or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) + or info['id']), + 'availability': self._extract_availability(data), + 'channel_follower_count': ( + self._get_count(data, ('header', ..., 'subscriberCountText')) + or traverse_obj(page_header_view_model, ( + 'metadata', 'contentMetadataViewModel', 'metadataRows', ..., 'metadataParts', + lambda _, v: 'subscribers' in v['text']['content'], 'text', 'content', {parse_count}, any))), + 'description': try_get(metadata_renderer, lambda x: x.get('description', '')), + 'tags': (traverse_obj(data, ('microformat', 'microformatDataRenderer', 'tags', ..., {str})) + or traverse_obj(metadata_renderer, ('keywords', {lambda x: x and shlex.split(x)}, ...))), + '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( + (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), )) + + 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) + + info['view_count'] = self._get_count(playlist_stats, 1) + if info['view_count'] is None: # 0 is allowed + info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText') + if info['view_count'] is None: + info['view_count'] = self._get_count(data, ( + 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer', + 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText')) + + info['playlist_count'] = self._get_count(playlist_stats, 0) + if info['playlist_count'] is None: # 0 is allowed + info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text')) + + if not info.get('channel_id'): + owner = traverse_obj(playlist_header_renderer, 'ownerText') + if not owner: # Deprecated + owner = traverse_obj( + self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'), + ('videoOwner', 'videoOwnerRenderer', 'title')) + owner_text = self._get_text(owner) + browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {} + info.update({ + '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({ + '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): + first_id = last_id = response = None + for page_num in itertools.count(1): + videos = list(self._playlist_entries(playlist)) + if not videos: + return + start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 + if start >= len(videos): + return + yield from videos[start:] + first_id = first_id or videos[0]['id'] + last_id = videos[-1]['id'] + watch_endpoint = try_get( + playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) + headers = self.generate_api_headers( + ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data), + visitor_data=self._extract_visitor_data(response, data, ytcfg)) + query = { + 'playlistId': playlist_id, + 'videoId': watch_endpoint.get('videoId') or last_id, + 'index': watch_endpoint.get('index') or len(videos), + 'params': watch_endpoint.get('params') or 'OAE%3D', + } + response = self._extract_response( + item_id=f'{playlist_id} page {page_num}', + query=query, ep='next', headers=headers, ytcfg=ytcfg, + check_get_keys='contents', + ) + playlist = try_get( + response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) + + def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg): + title = playlist.get('title') or try_get( + data, lambda x: x['titleText']['simpleText'], str) + playlist_id = playlist.get('playlistId') or item_id + + # Delegating everything except mix playlists to regular tab-based playlist URL + playlist_url = urljoin(url, try_get( + playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], + str)) + + # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1] + # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg + is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id) + + if playlist_url and playlist_url != url and not is_known_unviewable: + return self.url_result( + playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, + video_title=title) + + return self.playlist_result( + self._extract_inline_playlist(playlist, playlist_id, data, ytcfg), + playlist_id=playlist_id, playlist_title=title) + + def _extract_availability(self, data): + """ + Gets the availability of a given playlist/tab. + Note: Unless YouTube tells us explicitly, we do not assume it is public + @param data: response + """ + sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} + playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {} + player_header_privacy = playlist_header_renderer.get('privacy') + + 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( + (playlist_header_renderer, sidebar_renderer), + ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries', + lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'), + expected_type=str) + + microformats_is_unlisted = traverse_obj( + data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool) + + return ( + 'public' if ( + self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) + or player_header_privacy == 'PUBLIC' + or privacy_setting_icon == 'PRIVACY_PUBLIC') + else self._availability( + is_private=( + self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) + or player_header_privacy == 'PRIVATE' if player_header_privacy is not None + else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None), + is_unlisted=( + self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) + or player_header_privacy == 'UNLISTED' if player_header_privacy is not None + else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None + else microformats_is_unlisted if microformats_is_unlisted is not None else None), + needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None, + needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None, + needs_auth=False)) + + @staticmethod + def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): + sidebar_renderer = try_get( + data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] + for item in sidebar_renderer: + renderer = try_get(item, lambda x: x[info_renderer], expected_type) + if renderer: + return renderer + + def _reload_with_unavailable_videos(self, item_id, data, ytcfg): + """ + Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.) + """ + is_playlist = bool(traverse_obj( + data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer'))) + if not is_playlist: + return + headers = self.generate_api_headers( + ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data), + visitor_data=self._extract_visitor_data(data, ytcfg)) + query = { + 'params': 'wgYCCAA=', + 'browseId': f'VL{item_id}', + } + return self._extract_response( + item_id=item_id, headers=headers, query=query, + check_get_keys='contents', fatal=False, ytcfg=ytcfg, + note='Redownloading playlist API JSON with unavailable videos') + + @functools.cached_property + def skip_webpage(self): + return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) + + def _extract_webpage(self, url, item_id, fatal=True): + webpage, data = None, None + for retry in self.RetryManager(fatal=fatal): + try: + webpage = self._download_webpage(url, item_id, note='Downloading webpage') + 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, HTTPError) or e.cause.status not in (403, 429): + retry.error = e + continue + self._error_or_warning(e, fatal=fatal) + break + + try: + self._extract_and_report_alerts(data) + except ExtractorError as e: + self._error_or_warning(e, fatal=fatal) + break + + # Sometimes youtube returns a webpage with incomplete ytInitialData + # See: https://github.com/yt-dlp/yt-dlp/issues/116 + if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'): + retry.error = ExtractorError('Incomplete yt initial data received') + data = None + continue + + return webpage, data + + def _report_playlist_authcheck(self, ytcfg, fatal=True): + """Use if failed to extract ytcfg (and data) from initial webpage""" + if not ytcfg and self.is_authenticated: + msg = 'Playlists that require authentication may not extract correctly without a successful webpage download' + if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal: + raise ExtractorError( + f'{msg}. If you are not downloading private content, or ' + 'your cookies are only for the first account and channel,' + ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check', + expected=True) + self.report_warning(msg, only_once=True) + + def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'): + data = None + if not self.skip_webpage: + webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal) + ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage) + # Reject webpage data if redirected to home page without explicitly requesting + selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {} + if (url != 'https://www.youtube.com/feed/recommended' + and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page + and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])): + msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page' + if fatal: + raise ExtractorError(msg, expected=True) + self.report_warning(msg, only_once=True) + if not data: + self._report_playlist_authcheck(ytcfg, fatal=fatal) + data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client) + return data, ytcfg + + def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'): + headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client) + resolve_response = self._extract_response( + item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal, + ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client) + endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'} + for ep_key, ep in endpoints.items(): + params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict) + if params: + return self._extract_response( + item_id=item_id, query=params, ep=ep, headers=headers, + ytcfg=ytcfg, fatal=fatal, default_client=default_client, + check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')) + err_note = 'Failed to resolve url (does the playlist exist?)' + if fatal: + raise ExtractorError(err_note, expected=True) + self.report_warning(err_note, item_id) + + _SEARCH_PARAMS = None + + def _search_results(self, query, params=NO_DEFAULT, default_client='web'): + data = {'query': query} + if params is NO_DEFAULT: + params = self._SEARCH_PARAMS + if params: + data['params'] = params + + content_keys = ( + ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'), + ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'), + # ytmusic search + ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'), + ('continuationContents', ), + ) + display_id = f'query "{query}"' + check_get_keys = tuple({keys[0] for keys in content_keys}) + ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {} + self._report_playlist_authcheck(ytcfg, fatal=False) + + continuation_list = [None] + search = None + for page_num in itertools.count(1): + data.update(continuation_list[0] or {}) + headers = self.generate_api_headers( + ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client) + search = self._extract_response( + item_id=f'{display_id} page {page_num}', ep='search', query=data, + default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers) + slr_contents = traverse_obj(search, *content_keys) + yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list) + if not continuation_list[0]: + break + + +class YoutubeTabIE(YoutubeTabBaseInfoExtractor): + IE_DESC = 'YouTube Tabs' + _VALID_URL = r'''(?x: + https?:// + (?!consent\.)(?:\w+\.)? + (?: + youtube(?:kids)?\.com| + {invidious} + )/ + (?: + (?P<channel_type>channel|c|user|browse)/| + (?P<not_channel> + feed/|hashtag/| + (?:playlist|watch)\?.*?\blist= + )| + (?!(?:{reserved_names})\b) # Direct URLs + ) + (?P<id>[^/?\#&]+) + )'''.format( + reserved_names=YoutubeBaseInfoExtractor._RESERVED_NAMES, + invidious='|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), + ) + IE_NAME = 'youtube:tab' + + _TESTS = [{ + 'note': 'playlists, multipage', + 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', + 'playlist_mincount': 94, + 'info_dict': { + 'id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'title': 'Igor Kleiner Ph.D. - Playlists', + 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a', + 'uploader': 'Igor Kleiner Ph.D.', + 'uploader_id': '@IgorDataScience', + 'uploader_url': 'https://www.youtube.com/@IgorDataScience', + 'channel': 'Igor Kleiner Ph.D.', + 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'], + 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', + 'channel_follower_count': int, + }, + }, { + 'note': 'playlists, multipage, different order', + 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', + 'playlist_mincount': 94, + 'info_dict': { + 'id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'title': 'Igor Kleiner Ph.D. - Playlists', + 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a', + 'uploader': 'Igor Kleiner Ph.D.', + 'uploader_id': '@IgorDataScience', + 'uploader_url': 'https://www.youtube.com/@IgorDataScience', + 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'], + 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', + 'channel': 'Igor Kleiner Ph.D.', + 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', + 'channel_follower_count': int, + }, + }, { + 'note': 'playlists, series', + 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', + 'playlist_mincount': 5, + 'info_dict': { + 'id': 'UCYO_jab_esuFRV4b17AJtAw', + 'title': '3Blue1Brown - Playlists', + 'description': 'md5:602e3789e6a0cb7d9d352186b720e395', + 'channel_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_is_verified': True, + }, + }, { + 'note': 'playlists, singlepage', + 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', + 'playlist_mincount': 4, + 'info_dict': { + 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', + 'title': 'ThirstForScience - Playlists', + 'description': 'md5:609399d937ea957b0f53cbffb747a14c', + 'uploader': 'ThirstForScience', + 'uploader_url': 'https://www.youtube.com/@ThirstForScience', + 'uploader_id': '@ThirstForScience', + 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', + 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', + 'tags': 'count:12', + 'channel': 'ThirstForScience', + 'channel_follower_count': int, + }, + }, { + 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', + 'only_matching': True, + }, { + 'note': 'basic, single video playlist', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'info_dict': { + 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'title': 'youtube-dl public playlist', + 'description': '', + 'tags': [], + 'view_count': int, + 'modified_date': '20201130', + 'channel': 'Sergey M.', + 'channel_id': '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': { + 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', + 'title': 'youtube-dl empty playlist', + 'tags': [], + 'channel': 'Sergey M.', + 'description': '', + 'modified_date': '20230921', + 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'availability': 'unlisted', + 'uploader_url': 'https://www.youtube.com/@sergeym.6173', + 'uploader_id': '@sergeym.6173', + 'uploader': 'Sergey M.', + }, + 'playlist_count': 0, + }, { + 'note': 'Home tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Home', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': '@lexwill718', + 'channel': 'lex will', + 'tags': ['bible', 'history', 'prophesy'], + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_follower_count': int, + }, + 'playlist_mincount': 2, + }, { + 'note': 'Videos tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Videos', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': '@lexwill718', + 'tags': ['bible', 'history', 'prophesy'], + 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'channel': 'lex will', + 'channel_follower_count': int, + }, + 'playlist_mincount': 975, + }, { + 'note': 'Videos tab, sorted by popular', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Videos', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': '@lexwill718', + 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'channel': 'lex will', + 'tags': ['bible', 'history', 'prophesy'], + 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_follower_count': int, + }, + 'playlist_mincount': 199, + }, { + 'note': 'Playlists tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Playlists', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'uploader': 'lex will', + 'uploader_id': '@lexwill718', + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'channel': 'lex will', + 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'tags': ['bible', 'history', 'prophesy'], + 'channel_follower_count': int, + }, + 'playlist_mincount': 17, + }, { + 'note': 'Community tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Community', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'channel': 'lex will', + 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'tags': ['bible', 'history', 'prophesy'], + 'channel_follower_count': int, + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'uploader_id': '@lexwill718', + 'uploader': 'lex will', + }, + 'playlist_mincount': 18, + }, { + 'note': 'Channels tab', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', + 'info_dict': { + 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'lex will - Channels', + 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', + 'channel': 'lex will', + 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'tags': ['bible', 'history', 'prophesy'], + 'channel_follower_count': int, + 'uploader_url': 'https://www.youtube.com/@lexwill718', + 'uploader_id': '@lexwill718', + 'uploader': 'lex will', + }, + 'playlist_mincount': 12, + }, { + 'note': 'Search tab', + 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', + 'playlist_mincount': 40, + 'info_dict': { + 'id': 'UCYO_jab_esuFRV4b17AJtAw', + 'title': '3Blue1Brown - Search - linear algebra', + 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', + 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', + 'tags': ['Mathematics'], + 'channel': '3Blue1Brown', + 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', + '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', + 'only_matching': True, + }, { + 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', + 'only_matching': True, + }, { + 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', + 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'info_dict': { + 'title': '29C3: Not my department', + 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', + 'tags': [], + 'view_count': int, + 'modified_date': '20150605', + 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', + '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, + }, { + 'note': 'Large playlist', + 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', + 'info_dict': { + 'title': 'Uploads from Cauchemar', + 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', + 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q', + 'tags': [], + 'modified_date': r're:\d{8}', + 'channel': 'Cauchemar', + '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'], + }, { + 'note': 'even larger playlist, 8832 videos', + 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', + 'only_matching': True, + }, { + 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', + 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', + 'info_dict': { + 'title': 'Uploads from Interstellar Movie', + 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', + 'tags': [], + 'view_count': int, + 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', + '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, + }, { + 'note': 'Playlist with "show unavailable videos" button', + 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', + 'info_dict': { + 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', + 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', + 'view_count': int, + 'channel': 'Phim Siêu Nhân Nhật Bản', + 'tags': [], + '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'], + }, { + 'note': 'Playlist with unavailable videos in page 7', + 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', + 'info_dict': { + 'title': 'Uploads from BlankTV', + 'id': 'UU8l9frL61Yl5KFOl87nIm2w', + 'channel': 'BlankTV', + 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w', + 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', + 'view_count': int, + 'tags': [], + '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'], + }, { + 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', + 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'info_dict': { + 'title': 'Data Analysis with Dr Mike Pound', + 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', + 'tags': [], + 'view_count': int, + 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', + '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, + }, { + 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'only_matching': True, + }, { + 'note': 'Playlist URL that does not actually serve a playlist', + 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', + 'info_dict': { + 'id': 'FqZTN594JQw', + 'ext': 'webm', + 'title': "Smiley's People 01 detective, Adventure Series, Action", + 'upload_date': '20150526', + 'license': 'Standard YouTube License', + 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', + 'categories': ['People & Blogs'], + 'tags': list, + 'view_count': int, + 'like_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'This video is not available.', + 'add_ie': [YoutubeIE.ie_key()], + }, { + 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', + 'info_dict': { + 'id': 'hGkQjiJLjWQ', # This will keep changing + 'ext': 'mp4', + 'title': str, + 'upload_date': r're:\d{8}', + 'description': str, + 'categories': ['News & Politics'], + 'tags': list, + 'like_count': int, + 'release_timestamp': int, + 'channel': 'Sky News', + 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ', + 'age_limit': 0, + 'view_count': int, + 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg', + 'playable_in_embed': True, + 'release_date': r're:\d+', + 'availability': 'public', + 'live_status': 'is_live', + '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, + }, + 'expected_warnings': ['Ignoring subtitle tracks found in '], + }, { + 'url': 'https://www.youtube.com/user/TheYoungTurks/live', + 'info_dict': { + 'id': 'a48o2S1cPoo', + 'ext': 'mp4', + 'title': 'The Young Turks - Live Main Show', + 'upload_date': '20150715', + 'license': 'Standard YouTube License', + 'description': 'md5:438179573adcdff3c97ebb1ee632b891', + 'categories': ['News & Politics'], + 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], + 'like_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', + 'only_matching': True, + }, { + 'note': 'A channel that is not live. Should raise error', + 'url': 'https://www.youtube.com/user/numberphile/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/trending', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/library', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/history', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/subscriptions', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/feed/watch_later', + 'only_matching': True, + }, { + 'note': 'Recommended - redirects to home page.', + 'url': 'https://www.youtube.com/feed/recommended', + 'only_matching': True, + }, { + 'note': 'inline playlist with not always working continuations', + 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/course', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/zsecurity', + 'only_matching': True, + }, { + 'url': 'http://www.youtube.com/NASAgovVideo/videos', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/TheYoungTurks/live', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/hashtag/cctv9', + 'info_dict': { + 'id': 'cctv9', + 'title': 'cctv9 - All', + 'tags': [], + }, + 'playlist_mincount': 300, # not consistent but should be over 300 + }, { + 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', + 'only_matching': True, + }, { + 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', + 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', + 'only_matching': True, + }, { + 'note': '/browse/ should redirect to /channel/', + 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', + 'only_matching': True, + }, { + 'note': 'VLPL, should redirect to playlist?list=PL...', + 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', + 'info_dict': { + 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', + 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', + 'title': 'NCS : All Releases 💿', + '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', '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', + 'title': 'Uploads from Royalty Free Music - Topic', + 'tags': [], + 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', + 'channel': 'Royalty Free Music - Topic', + 'view_count': int, + 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', + 'modified_date': r're:\d{8}', + '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 + 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', + 'info_dict': { + 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', + 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', + 'tags': [], + }, + 'playlist_mincount': 9, + }, { + 'note': 'Youtube music Album', + 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', + 'info_dict': { + 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', + 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', + 'tags': [], + 'view_count': int, + 'description': '', + 'availability': 'unlisted', + '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': { + 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', + 'title': 'yt-dlp unlisted playlist test', + 'availability': 'unlisted', + 'tags': [], + 'modified_date': '20220418', + 'channel': 'colethedj', + 'view_count': int, + 'description': '', + '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', + 'info_dict': { + 'id': 'recommended', + 'title': 'recommended', + 'tags': [], + }, + 'playlist_mincount': 50, + 'params': { + 'skip_download': True, + 'extractor_args': {'youtubetab': {'skip': ['webpage']}}, + }, + }, { + 'note': 'API Fallback: /videos tab, sorted by oldest first', + 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', + 'info_dict': { + 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', + 'title': 'Cody\'sLab - Videos', + 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', + 'channel': 'Cody\'sLab', + 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', + 'tags': [], + 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', + 'channel_follower_count': int, + }, + 'playlist_mincount': 650, + 'params': { + 'skip_download': True, + 'extractor_args': {'youtubetab': {'skip': ['webpage']}}, + }, + 'skip': 'Query for sorting no longer works', + }, { + 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', + 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', + 'info_dict': { + 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', + 'title': 'Uploads from Royalty Free Music - Topic', + 'modified_date': r're:\d{8}', + 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', + 'description': '', + 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', + 'tags': [], + 'channel': 'Royalty Free Music - Topic', + 'view_count': int, + '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', + 'only_matching': True, + }, { + 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")', + 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', + 'info_dict': { + 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', + 'modified_date': '20220407', + 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', + 'tags': [], + '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/@pukkandan', + 'uploader_id': '@pukkandan', + 'uploader': 'pukkandan', + }, + 'playlist_mincount': 2, + }, { + 'note': 'translated tab name', + 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists', + 'info_dict': { + 'id': 'UCiu-3thuViMebBjw_5nWYrA', + 'tags': [], + 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', + 'description': 'test description', + 'title': 'cole-dlp-test-acc - 再生リスト', + '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']}}}, + 'expected_warnings': ['Preferring "ja"'], + }, { + # XXX: this should really check flat playlist entries, but the test suite doesn't support that + 'note': 'preferred lang set with playlist with translated video titles', + 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0', + 'info_dict': { + 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0', + 'tags': [], + 'view_count': int, + 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', + 'channel': 'cole-dlp-test-acc', + 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', + 'description': 'test', + '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']}}}, + 'expected_warnings': ['Preferring "ja"'], + }, { + # shorts audio pivot for 2GtVksBMYFM. + 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==', + 'info_dict': { + 'id': 'sfv_audio_pivot', + 'title': 'sfv_audio_pivot', + 'tags': [], + }, + 'playlist_mincount': 50, + + }, { + # Channel with a real live tab (not to be mistaken with streams tab) + # Do not treat like it should redirect to live stream + 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live', + 'info_dict': { + 'id': 'UCEH7P7kyJIkS_gJf93VYbmg', + 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live', + 'tags': [], + }, + 'playlist_mincount': 20, + }, { + # Tab name is not the same as tab id + 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay', + 'info_dict': { + 'id': 'UCQvWX73GQygcwXOTSf_VDVg', + 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play', + 'tags': [], + }, + 'playlist_mincount': 8, + }, { + # Home tab id is literally home. Not to get mistaken with featured + 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home', + 'info_dict': { + 'id': 'UCQvWX73GQygcwXOTSf_VDVg', + 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home', + 'tags': [], + }, + 'playlist_mincount': 8, + }, { + # Should get three playlists for videos, shorts and streams tabs + 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', + 'info_dict': { + 'id': 'UCK9V2B22uJYu3N7eR_BT9QA', + 'title': 'Polka Ch. 尾丸ポルカ', + 'channel_follower_count': int, + 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA', + 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', + 'description': 'md5:49809d8bf9da539bc48ed5d1f83c33f2', + 'channel': 'Polka Ch. 尾丸ポルカ', + 'tags': 'count:35', + 'uploader_url': 'https://www.youtube.com/@OmaruPolka', + 'uploader': 'Polka Ch. 尾丸ポルカ', + 'uploader_id': '@OmaruPolka', + 'channel_is_verified': True, + }, + '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:10', + 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A', + 'description': 'md5:5e82545b3a041345927a92d0585df247', + 'channel_follower_count': int, + 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A', + 'channel': 'Not Just Bikes', + 'uploader_url': 'https://www.youtube.com/@NotJustBikes', + 'uploader': 'Not Just Bikes', + 'uploader_id': '@NotJustBikes', + 'channel_is_verified': True, + }, + 'playlist_mincount': 10, + }, { + # Streams tab + 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams', + 'info_dict': { + 'id': 'UC3eYAvjCVwNHgkaGbXX3sig', + 'title': '中村悠一 - Live', + 'tags': 'count:7', + 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig', + 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig', + 'channel': '中村悠一', + 'channel_follower_count': int, + 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300', + 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura', + 'uploader_id': '@Yuichi-Nakamura', + 'uploader': '中村悠一', + }, + 'playlist_mincount': 60, + }, { + # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail. + # See test_youtube_lists + 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA', + 'only_matching': True, + }, { + # No uploads and no UCID given. Should fail with no uploads error + # See test_youtube_lists + 'url': 'https://www.youtube.com/news', + 'only_matching': True, + }, { + # No videos tab but has a shorts tab + 'url': 'https://www.youtube.com/c/TKFShorts', + 'info_dict': { + 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg', + 'title': 'Shorts Break - Shorts', + 'tags': 'count:48', + 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg', + 'channel': 'Shorts Break', + 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499', + 'channel_follower_count': int, + '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, + }, { + # Trending Now Tab. tab id is empty + 'url': 'https://www.youtube.com/feed/trending', + 'info_dict': { + 'id': 'trending', + 'title': 'trending - Now', + 'tags': [], + }, + 'playlist_mincount': 30, + }, { + # Trending Gaming Tab. tab id is empty + 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D', + 'info_dict': { + 'id': 'trending', + 'title': 'trending - Gaming', + 'tags': [], + }, + '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', + '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', + }, + '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', + 'title': 'SHORT short', + 'view_count': int, + 'thumbnails': list, + }, + }], + 'params': {'extract_flat': True}, + }, { + # Live video status should be extracted + 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live', + 'info_dict': { + 'id': 'UCQvWX73GQygcwXOTSf_VDVg', + 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO: should be Minecraft - Live or Minecraft - Topic - Live + 'tags': [], + }, + 'playlist': [{ + 'info_dict': { + '_type': 'url', + 'ie_key': 'Youtube', + 'url': 'startswith:https://www.youtube.com/watch?v=', + 'id': str, + 'title': str, + 'live_status': 'is_live', + 'channel_id': str, + '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'}, + 'playlist_mincount': 1, + }, { + # Channel renderer metadata. Contains number of videos on the channel + 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels', + 'info_dict': { + 'id': 'UCiu-3thuViMebBjw_5nWYrA', + 'title': 'cole-dlp-test-acc - Channels', + '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', + }, + 'playlist': [{ + 'info_dict': { + '_type': 'url', + 'ie_key': 'YoutubeTab', + 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', + 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw', + 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw', + 'title': 'PewDiePie', + 'channel': 'PewDiePie', + 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', + 'thumbnails': list, + 'channel_follower_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}, + }, { + 'url': 'https://www.youtube.com/@3blue1brown/about', + 'info_dict': { + 'id': '@3blue1brown', + 'tags': ['Mathematics'], + 'title': '3Blue1Brown', + 'channel_follower_count': int, + 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', + 'channel': '3Blue1Brown', + 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', + 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', + 'uploader_url': 'https://www.youtube.com/@3blue1brown', + 'uploader_id': '@3blue1brown', + 'uploader': '3Blue1Brown', + 'channel_is_verified': True, + }, + 'playlist_count': 0, + }, { + # Podcasts tab, with rich entry lockupViewModel + '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% Invisible - Podcasts', + 'uploader': '99% Invisible', + 'channel_follower_count': int, + 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw', + 'tags': [], + 'channel': '99% Invisible', + 'uploader_id': '@99percentinvisiblepodcast', + }, + 'playlist_count': 5, + }, { + # 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:12', + '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': r're:\d{8}', + 'title': 'Uploads from Bangy Shorts', + }, + 'playlist_mincount': 100, + 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], + }, { + 'note': 'Tags containing spaces', + 'url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ', + 'playlist_count': 3, + 'info_dict': { + 'id': 'UC7_YxT-KID8kRbqZo7MyscQ', + 'channel': 'Markiplier', + 'channel_id': 'UC7_YxT-KID8kRbqZo7MyscQ', + 'title': 'Markiplier', + 'channel_follower_count': int, + 'description': 'md5:0c010910558658824402809750dc5d97', + 'uploader_id': '@markiplier', + 'uploader_url': 'https://www.youtube.com/@markiplier', + 'uploader': 'Markiplier', + 'channel_url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ', + 'channel_is_verified': True, + 'tags': ['markiplier', 'comedy', 'gaming', 'funny videos', 'funny moments', + 'sketch comedy', 'laughing', 'lets play', 'challenge videos', 'hilarious', + 'challenges', 'sketches', 'scary games', 'funny games', 'rage games', + 'mark fischbach'], + }, + }] + + @classmethod + def suitable(cls, url): + return False if YoutubeIE.suitable(url) else super().suitable(url) + + _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$') + + def _get_url_mobj(self, url): + mobj = self._URL_RE.match(url).groupdict() + mobj.update((k, '') for k, v in mobj.items() if v is None) + return mobj + + def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'): + tab_name = (tab.get('title') or '').lower() + tab_url = urljoin(base_url, traverse_obj( + tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url'))) + + tab_id = ((tab_url and self._get_url_mobj(tab_url)['tab'][1:]) + or traverse_obj(tab, 'tabIdentifier', expected_type=str)) + if tab_id: + return { + 'TAB_ID_SPONSORSHIPS': 'membership', + }.get(tab_id, tab_id), tab_name + + # Fallback to tab name if we cannot get the tab id. + # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel + # Note that in the case of translated tab name this may result in an empty string, which we don't want. + if tab_name: + self.write_debug(f'Falling back to selected tab name: {tab_name}') + return { + 'home': 'featured', + 'live': 'streams', + }.get(tab_name, tab_name), tab_name + + def _has_tab(self, tabs, tab_id): + return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs) + + def _empty_playlist(self, item_id, data): + return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data)) + + @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data + def _real_extract(self, url, smuggled_data): + item_id = self._match_id(url) + url = urllib.parse.urlunparse( + urllib.parse.urlparse(url)._replace(netloc='www.youtube.com')) + compat_opts = self.get_param('compat_opts', []) + + mobj = self._get_url_mobj(url) + pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel'] + if is_channel and smuggled_data.get('is_music_url'): + if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist + return self.url_result( + f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:]) + elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist + mdata = self._extract_tab_endpoint( + f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music') + murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), + get_all=False, expected_type=str) + if not murl: + raise ExtractorError('Failed to resolve album to playlist') + return self.url_result(murl, YoutubeTabIE) + elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/ + return self.url_result( + f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id) + + original_tab_id, display_id = tab[1:], f'{item_id}{tab}' + if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: + url = f'{pre}/videos{post}' + if smuggled_data.get('is_music_url'): + self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}') + + # Handle both video/playlist URLs + qs = parse_qs(url) + video_id, playlist_id = (traverse_obj(qs, (key, 0)) for key in ('v', 'list')) + if not video_id and mobj['not_channel'].startswith('watch'): + if not playlist_id: + # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable + raise ExtractorError('A video URL was given without video ID', expected=True) + # Common mistake: https://www.youtube.com/watch?list=playlist_id + self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}') + return self.url_result( + f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id) + + if not self._yes_playlist(playlist_id, video_id): + return self.url_result( + f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id) + + data, ytcfg = self._extract_data(url, display_id) + + # YouTube may provide a non-standard redirect to the regional channel + # See: https://github.com/yt-dlp/yt-dlp/issues/2694 + # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects + redirect_url = traverse_obj( + data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False) + if redirect_url and 'no-youtube-channel-redirect' not in compat_opts: + redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post)) + self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}') + return self.url_result(redirect_url, YoutubeTabIE) + + tabs, extra_tabs = self._extract_tab_renderers(data), [] + if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts: + selected_tab = self._extract_selected_tab(tabs) + selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated + self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}') + + # /about is no longer a tab + if original_tab_id == 'about': + return self._empty_playlist(item_id, data) + + if not original_tab_id and selected_tab_name: + self.to_screen('Downloading all uploads of the channel. ' + 'To download only the videos in a specific tab, pass the tab\'s URL') + if self._has_tab(tabs, 'streams'): + extra_tabs.append(''.join((pre, '/streams', post))) + if self._has_tab(tabs, 'shorts'): + extra_tabs.append(''.join((pre, '/shorts', post))) + # XXX: Members-only tab should also be extracted + + if not extra_tabs and selected_tab_id != 'videos': + # Channel does not have streams, shorts or videos tabs + if item_id[:2] != 'UC': + return self._empty_playlist(item_id, data) + + # Topic channels don't have /videos. Use the equivalent playlist instead + pl_id = f'UU{item_id[2:]}' + pl_url = f'https://www.youtube.com/playlist?list={pl_id}' + try: + data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True) + except ExtractorError: + return self._empty_playlist(item_id, data) + else: + item_id, url = pl_id, pl_url + self.to_screen( + f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead') + + elif extra_tabs and selected_tab_id != 'videos': + # When there are shorts/live tabs but not videos tab + url, data = f'{pre}{post}', None + + elif (original_tab_id or 'videos') != selected_tab_id: + if original_tab_id == 'live': + # Live tab should have redirected to the video + # Except in the case the channel has an actual live tab + # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live + raise UserNotLive(video_id=item_id) + elif selected_tab_name: + raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True) + + # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg + url = f'{pre}{post}' + + # YouTube sometimes provides a button to reload playlist with unavailable videos. + if 'no-youtube-unavailable-videos' not in compat_opts: + data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data + self._extract_and_report_alerts(data, only_once=True) + + tabs, entries = self._extract_tab_renderers(data), [] + if tabs: + entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)] + entries[0].update({ + 'extractor_key': YoutubeTabIE.ie_key(), + 'extractor': YoutubeTabIE.IE_NAME, + 'webpage_url': url, + }) + if self.get_param('playlist_items') == '0': + entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs) + else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result` + entries.extend(map(self._real_extract, extra_tabs)) + + if len(entries) == 1: + return entries[0] + elif entries: + metadata = self._extract_metadata_from_tabs(item_id, data) + uploads_url = 'the Uploads (UU) playlist URL' + if try_get(metadata, lambda x: x['channel_id'].startswith('UC')): + uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}' + self.to_screen( + 'Downloading as multiple playlists, separated by tabs. ' + f'To download as a single playlist instead, pass {uploads_url}') + return self.playlist_result(entries, item_id, **metadata) + + # Inline playlist + playlist = traverse_obj( + data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict) + if playlist: + return self._extract_from_playlist(item_id, url, data, playlist, ytcfg) + + video_id = traverse_obj( + data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id + if video_id: + if tab != '/live': # live tab is expected to redirect to video + self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}') + return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id) + + raise ExtractorError('Unable to recognize tab page') + + +# xxx: This is tightly coupled to YoutubeTabBaseInfoExtractor. Should be decoupled at some point +class YoutubePlaylistIE(YoutubeBaseInfoExtractor): + IE_DESC = 'YouTube playlists' + _VALID_URL = r'''(?x)(?: + (?:https?://)? + (?:\w+\.)? + (?: + (?: + youtube(?:kids)?\.com| + {invidious} + ) + /.*?\?.*?\blist= + )? + (?P<id>{playlist_id}) + )'''.format( + playlist_id=YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, + invidious='|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), + ) + IE_NAME = 'youtube:playlist' + _TESTS = [{ + 'note': 'issue #673', + 'url': 'PLBB231211A4F62143', + 'info_dict': { + 'title': '[OLD]Team Fortress 2 (Class-based LP)', + 'id': 'PLBB231211A4F62143', + 'uploader': 'Wickman', + 'uploader_id': '@WickmanVT', + 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', + 'view_count': int, + '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/channel/UCKSpbfbl5kRQpTdL7kMc-1Q', + 'availability': 'public', + }, + 'playlist_mincount': 29, + }, { + 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', + 'info_dict': { + 'title': 'YDL_safe_search', + 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', + }, + 'playlist_count': 2, + 'skip': 'This playlist is private', + }, { + 'note': 'embedded', + 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'playlist_count': 4, + 'info_dict': { + 'title': 'JODA15', + 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'uploader': 'milan', + 'uploader_id': '@milan5503', + 'description': '', + 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', + 'tags': [], + 'modified_date': '20140919', + 'view_count': int, + 'channel': 'milan', + 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', + 'uploader_url': 'https://www.youtube.com/@milan5503', + 'availability': 'public', + }, + 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden', 'Retrying', 'Giving up'], + }, { + 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', + 'playlist_mincount': 455, + 'info_dict': { + 'title': '2018 Chinese New Singles (11/6 updated)', + 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', + 'uploader': 'LBK', + 'uploader_id': '@music_king', + 'description': 'md5:da521864744d60a198e3a88af4db0d9d', + 'channel': 'LBK', + 'view_count': int, + 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA', + 'tags': [], + 'uploader_url': 'https://www.youtube.com/@music_king', + 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', + 'modified_date': r're:\d{8}', + 'availability': 'public', + }, + 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], + }, { + 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', + 'only_matching': True, + }, { + # music album playlist + 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + if YoutubeTabIE.suitable(url): + return False + from yt_dlp.utils import parse_qs + qs = parse_qs(url) + if qs.get('v', [None])[0]: + return False + return super().suitable(url) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) + url = update_url_query( + 'https://www.youtube.com/playlist', + parse_qs(url) or {'list': playlist_id}) + if is_music_url: + url = smuggle_url(url, {'is_music_url': True}) + return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube/_video.py index ee4c98473..2b9b89700 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube/_video.py @@ -1,45 +1,43 @@ import base64 import binascii -import calendar import collections -import copy import datetime as dt -import enum import functools -import hashlib import itertools import json import math import os.path import random import re -import shlex import sys import threading import time import traceback import urllib.parse -from .common import InfoExtractor, SearchInfoExtractor -from .openload import PhantomJSwrapper -from ..jsinterp import JSInterpreter -from ..networking.exceptions import HTTPError, network_exceptions -from ..utils import ( +from ._base import ( + INNERTUBE_CLIENTS, + BadgeType, + YoutubeBaseInfoExtractor, + _PoTokenContext, + _split_innertube_client, + short_client_name, +) +from ..openload import PhantomJSwrapper +from ...jsinterp import JSInterpreter +from ...networking.exceptions import HTTPError +from ...utils import ( NO_DEFAULT, ExtractorError, LazyList, - UserNotLive, bug_reports_message, - classproperty, clean_html, datetime_from_str, filesize_from_tbr, - filter_dict, float_or_none, format_field, get_first, int_or_none, - is_html, join_nonempty, js_to_json, mimetype2ext, @@ -61,7 +59,6 @@ from ..utils import ( try_get, unescapeHTML, unified_strdate, - unified_timestamp, unsmuggle_url, update_url_query, url_or_none, @@ -74,1211 +71,6 @@ STREAMING_DATA_INITIAL_PO_TOKEN = '__yt_dlp_po_token' PO_TOKEN_GUIDE_URL = 'https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide' -class _PoTokenContext(enum.Enum): - PLAYER = 'player' - GVS = 'gvs' - - -# any clients starting with _ cannot be explicitly requested by the user -INNERTUBE_CLIENTS = { - 'web': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'WEB', - 'clientVersion': '2.20241126.01.00', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'SUPPORTS_COOKIES': True, - }, - # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats - 'web_safari': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'WEB', - 'clientVersion': '2.20241126.01.00', - 'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'SUPPORTS_COOKIES': True, - }, - 'web_embedded': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'WEB_EMBEDDED_PLAYER', - 'clientVersion': '1.20241201.00.00', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 56, - 'SUPPORTS_COOKIES': True, - }, - 'web_music': { - 'INNERTUBE_HOST': 'music.youtube.com', - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'WEB_REMIX', - 'clientVersion': '1.20241127.01.00', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'SUPPORTS_COOKIES': True, - }, - # This client now requires sign-in for every video - 'web_creator': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'WEB_CREATOR', - 'clientVersion': '1.20241203.01.00', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'REQUIRE_AUTH': True, - 'SUPPORTS_COOKIES': True, - }, - 'android': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'ANDROID', - 'clientVersion': '19.44.38', - 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.youtube/19.44.38 (Linux; U; Android 11) gzip', - 'osName': 'Android', - 'osVersion': '11', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, - 'REQUIRE_JS_PLAYER': False, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - }, - # This client now requires sign-in for every video - 'android_music': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'ANDROID_MUSIC', - 'clientVersion': '7.27.52', - 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.apps.youtube.music/7.27.52 (Linux; U; Android 11) gzip', - 'osName': 'Android', - 'osVersion': '11', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, - 'REQUIRE_JS_PLAYER': False, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'REQUIRE_AUTH': True, - }, - # This client now requires sign-in for every video - 'android_creator': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'ANDROID_CREATOR', - 'clientVersion': '24.45.100', - 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.apps.youtube.creator/24.45.100 (Linux; U; Android 11) gzip', - 'osName': 'Android', - 'osVersion': '11', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, - 'REQUIRE_JS_PLAYER': False, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'REQUIRE_AUTH': True, - }, - # YouTube Kids videos aren't returned on this client for some reason - 'android_vr': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'ANDROID_VR', - 'clientVersion': '1.60.19', - 'deviceMake': 'Oculus', - 'deviceModel': 'Quest 3', - 'androidSdkVersion': 32, - 'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.60.19 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip', - 'osName': 'Android', - 'osVersion': '12L', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 28, - 'REQUIRE_JS_PLAYER': False, - }, - # iOS clients have HLS live streams. Setting device model to get 60fps formats. - # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 - 'ios': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'IOS', - 'clientVersion': '20.03.02', - 'deviceMake': 'Apple', - 'deviceModel': 'iPhone16,2', - 'userAgent': 'com.google.ios.youtube/20.03.02 (iPhone16,2; U; CPU iOS 18_2_1 like Mac OS X;)', - 'osName': 'iPhone', - 'osVersion': '18.2.1.22C161', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'REQUIRE_JS_PLAYER': False, - }, - # This client now requires sign-in for every video - 'ios_music': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'IOS_MUSIC', - 'clientVersion': '7.27.0', - 'deviceMake': 'Apple', - 'deviceModel': 'iPhone16,2', - 'userAgent': 'com.google.ios.youtubemusic/7.27.0 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)', - 'osName': 'iPhone', - 'osVersion': '18.1.0.22B83', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, - 'REQUIRE_JS_PLAYER': False, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'REQUIRE_AUTH': True, - }, - # This client now requires sign-in for every video - 'ios_creator': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'IOS_CREATOR', - 'clientVersion': '24.45.100', - 'deviceMake': 'Apple', - 'deviceModel': 'iPhone16,2', - 'userAgent': 'com.google.ios.ytcreator/24.45.100 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)', - 'osName': 'iPhone', - 'osVersion': '18.1.0.22B83', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, - 'REQUIRE_JS_PLAYER': False, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'REQUIRE_AUTH': True, - }, - # mweb has 'ultralow' formats - # See: https://github.com/yt-dlp/yt-dlp/pull/557 - 'mweb': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'MWEB', - 'clientVersion': '2.20241202.07.00', - # mweb previously did not require PO Token with this UA - 'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 2, - 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS], - 'SUPPORTS_COOKIES': True, - }, - 'tv': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'TVHTML5', - 'clientVersion': '7.20250120.19.00', - 'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 7, - 'SUPPORTS_COOKIES': True, - }, - # This client now requires sign-in for every video - # It was previously an age-gate workaround for videos that were `playable_in_embed` - # It may still be useful if signed into an EU account that is not age-verified - 'tv_embedded': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', - 'clientVersion': '2.0', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 85, - 'REQUIRE_AUTH': True, - 'SUPPORTS_COOKIES': True, - }, -} - - -def _split_innertube_client(client_name): - variant, *base = client_name.rsplit('.', 1) - if base: - return variant, base[0], variant - base, *variant = client_name.split('_', 1) - return client_name, base, variant[0] if variant else None - - -def short_client_name(client_name): - main, *parts = _split_innertube_client(client_name)[0].split('_') - return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper() - - -def build_innertube_clients(): - THIRD_PARTY = { - 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL - } - BASE_CLIENTS = ('ios', 'web', 'tv', 'mweb', 'android') - priority = qualities(BASE_CLIENTS[::-1]) - - for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): - ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') - ytcfg.setdefault('REQUIRE_JS_PLAYER', True) - ytcfg.setdefault('PO_TOKEN_REQUIRED_CONTEXTS', []) - ytcfg.setdefault('REQUIRE_AUTH', False) - ytcfg.setdefault('SUPPORTS_COOKIES', False) - ytcfg.setdefault('PLAYER_PARAMS', None) - ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') - - _, base_client, variant = _split_innertube_client(client) - ytcfg['priority'] = 10 * priority(base_client) - - if variant == 'embedded': - ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY - ytcfg['priority'] -= 2 - elif variant: - ytcfg['priority'] -= 3 - - -build_innertube_clients() - - -class BadgeType(enum.Enum): - AVAILABILITY_UNLISTED = enum.auto() - AVAILABILITY_PRIVATE = enum.auto() - AVAILABILITY_PUBLIC = enum.auto() - AVAILABILITY_PREMIUM = enum.auto() - AVAILABILITY_SUBSCRIPTION = enum.auto() - LIVE_NOW = enum.auto() - VERIFIED = enum.auto() - - -class YoutubeBaseInfoExtractor(InfoExtractor): - """Provide base functions for Youtube extractors""" - - _RESERVED_NAMES = ( - r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|' - r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' - r'browse|oembed|get_video_info|iframe_api|s/player|source|' - r'storefront|oops|index|account|t/terms|about|upload|signin|logout') - - _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' - - # _NETRC_MACHINE = 'youtube' - - # If True it will raise an error if no login info is provided - _LOGIN_REQUIRED = False - - _INVIDIOUS_SITES = ( - # invidious-redirect websites - r'(?:www\.)?redirect\.invidious\.io', - r'(?:(?:www|dev)\.)?invidio\.us', - # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md - r'(?:www\.)?invidious\.pussthecat\.org', - r'(?:www\.)?invidious\.zee\.li', - r'(?:www\.)?invidious\.ethibox\.fr', - r'(?:www\.)?iv\.ggtyler\.dev', - r'(?:www\.)?inv\.vern\.i2p', - r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion', - r'(?:www\.)?inv\.riverside\.rocks', - r'(?:www\.)?invidious\.silur\.me', - r'(?:www\.)?inv\.bp\.projectsegfau\.lt', - r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion', - r'(?:www\.)?invidious\.slipfox\.xyz', - r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion', - r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion', - r'(?:www\.)?invidious\.tiekoetter\.com', - r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion', - r'(?:www\.)?invidious\.nerdvpn\.de', - r'(?:www\.)?invidious\.weblibre\.org', - r'(?:www\.)?inv\.odyssey346\.dev', - r'(?:www\.)?invidious\.dhusch\.de', - r'(?:www\.)?iv\.melmac\.space', - r'(?:www\.)?watch\.thekitty\.zone', - r'(?:www\.)?invidious\.privacydev\.net', - r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion', - r'(?:www\.)?invidious\.drivet\.xyz', - r'(?:www\.)?vid\.priv\.au', - r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion', - r'(?:www\.)?inv\.vern\.cc', - r'(?:www\.)?invidious\.esmailelbob\.xyz', - r'(?:www\.)?invidious\.sethforprivacy\.com', - r'(?:www\.)?yt\.oelrichsgarcia\.de', - r'(?:www\.)?yt\.artemislena\.eu', - r'(?:www\.)?invidious\.flokinet\.to', - r'(?:www\.)?invidious\.baczek\.me', - r'(?:www\.)?y\.com\.sb', - r'(?:www\.)?invidious\.epicsite\.xyz', - r'(?:www\.)?invidious\.lidarshield\.cloud', - r'(?:www\.)?yt\.funami\.tech', - r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', - r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', - r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', - # youtube-dl invidious instances list - r'(?:(?:www|no)\.)?invidiou\.sh', - r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', - r'(?:www\.)?invidious\.kabi\.tk', - r'(?:www\.)?invidious\.mastodon\.host', - r'(?:www\.)?invidious\.zapashcanon\.fr', - r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', - r'(?:www\.)?invidious\.tinfoil-hat\.net', - r'(?:www\.)?invidious\.himiko\.cloud', - r'(?:www\.)?invidious\.reallyancient\.tech', - r'(?:www\.)?invidious\.tube', - r'(?:www\.)?invidiou\.site', - r'(?:www\.)?invidious\.site', - r'(?:www\.)?invidious\.xyz', - r'(?:www\.)?invidious\.nixnet\.xyz', - r'(?:www\.)?invidious\.048596\.xyz', - r'(?:www\.)?invidious\.drycat\.fr', - r'(?:www\.)?inv\.skyn3t\.in', - r'(?:www\.)?tube\.poal\.co', - r'(?:www\.)?tube\.connect\.cafe', - r'(?:www\.)?vid\.wxzm\.sx', - r'(?:www\.)?vid\.mint\.lgbt', - r'(?:www\.)?vid\.puffyan\.us', - r'(?:www\.)?yewtu\.be', - r'(?:www\.)?yt\.elukerio\.org', - r'(?:www\.)?yt\.lelux\.fi', - r'(?:www\.)?invidious\.ggc-project\.de', - r'(?:www\.)?yt\.maisputain\.ovh', - r'(?:www\.)?ytprivate\.com', - r'(?:www\.)?invidious\.13ad\.de', - r'(?:www\.)?invidious\.toot\.koeln', - r'(?:www\.)?invidious\.fdn\.fr', - r'(?:www\.)?watch\.nettohikari\.com', - r'(?:www\.)?invidious\.namazso\.eu', - r'(?:www\.)?invidious\.silkky\.cloud', - r'(?:www\.)?invidious\.exonip\.de', - r'(?:www\.)?invidious\.riverside\.rocks', - r'(?:www\.)?invidious\.blamefran\.net', - r'(?:www\.)?invidious\.moomoo\.de', - r'(?:www\.)?ytb\.trom\.tf', - r'(?:www\.)?yt\.cyberhost\.uk', - r'(?:www\.)?kgg2m7yk5aybusll\.onion', - r'(?:www\.)?qklhadlycap4cnod\.onion', - r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', - r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', - r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', - r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', - r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', - r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', - r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', - r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', - r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', - r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', - # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances - r'(?:www\.)?piped\.kavin\.rocks', - r'(?:www\.)?piped\.tokhmi\.xyz', - r'(?:www\.)?piped\.syncpundit\.io', - r'(?:www\.)?piped\.mha\.fi', - r'(?:www\.)?watch\.whatever\.social', - r'(?:www\.)?piped\.garudalinux\.org', - r'(?:www\.)?piped\.rivo\.lol', - r'(?:www\.)?piped-libre\.kavin\.rocks', - r'(?:www\.)?yt\.jae\.fi', - r'(?:www\.)?piped\.mint\.lgbt', - r'(?:www\.)?il\.ax', - r'(?:www\.)?piped\.esmailelbob\.xyz', - r'(?:www\.)?piped\.projectsegfau\.lt', - r'(?:www\.)?piped\.privacydev\.net', - r'(?:www\.)?piped\.palveluntarjoaja\.eu', - r'(?:www\.)?piped\.smnz\.de', - r'(?:www\.)?piped\.adminforge\.de', - r'(?:www\.)?watch\.whatevertinfoil\.de', - r'(?:www\.)?piped\.qdi\.fi', - r'(?:(?:www|cf)\.)?piped\.video', - r'(?:www\.)?piped\.aeong\.one', - r'(?:www\.)?piped\.moomoo\.me', - r'(?:www\.)?piped\.chauvet\.pro', - r'(?:www\.)?watch\.leptons\.xyz', - r'(?:www\.)?pd\.vern\.cc', - r'(?:www\.)?piped\.hostux\.net', - r'(?:www\.)?piped\.lunar\.icu', - # Hyperpipe instances from https://hyperpipe.codeberg.page/ - r'(?:www\.)?hyperpipe\.surge\.sh', - r'(?:www\.)?hyperpipe\.esmailelbob\.xyz', - r'(?:www\.)?listen\.whatever\.social', - r'(?:www\.)?music\.adminforge\.de', - ) - - # extracted from account/account_menu ep - # XXX: These are the supported YouTube UI and API languages, - # which is slightly different from languages supported for translation in YouTube studio - _SUPPORTED_LANG_CODES = [ - 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es', - 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv', - 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi', - 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw', - 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml', - 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko', - ] - - _IGNORED_WARNINGS = { - 'Unavailable videos will be hidden during playback', - 'Unavailable videos are hidden', - } - - _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en - _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}' - - _NETRC_MACHINE = 'youtube' - - 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})$', urllib.parse.unquote(handle or ''), - '@-handle', default=None) - - def handle_from_url(self, url): - return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})', - urllib.parse.unquote(url or ''), '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): - """ - Returns a language code supported by YouTube for the user preferred language. - Returns None if no preferred language set. - """ - preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0] - if not preferred_lang: - return - if preferred_lang not in self._SUPPORTED_LANG_CODES: - raise ExtractorError( - f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.', - expected=True) - elif preferred_lang != 'en': - self.report_warning( - f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.') - return preferred_lang - - def _initialize_consent(self): - cookies = self._get_cookies('https://www.youtube.com/') - if cookies.get('__Secure-3PSID'): - return - 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/') - pref_cookie = cookies.get('PREF') - pref = {} - if pref_cookie: - try: - pref = dict(urllib.parse.parse_qsl(pref_cookie.value)) - except ValueError: - self.report_warning('Failed to parse user PREF cookie' + bug_reports_message()) - pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'}) - self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref)) - - def _initialize_cookie_auth(self): - yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies() - if yt_sapisid or yt_1psapisid or yt_3psapisid: - self.write_debug('Found YouTube account cookies') - - def _real_initialize(self): - self._initialize_pref() - self._initialize_consent() - self._initialize_cookie_auth() - self._check_login_required() - - def _perform_login(self, username, password): - if username.startswith('oauth'): - raise ExtractorError( - f'Login with OAuth is no longer supported. {self._youtube_login_hint}', expected=True) - - self.report_warning( - f'Login with password is not supported for YouTube. {self._youtube_login_hint}') - - @property - def _youtube_login_hint(self): - return (f'{self._login_hint(method="cookies")}. Also see ' - 'https://github.com/yt-dlp/yt-dlp/wiki/Extractors#exporting-youtube-cookies ' - 'for tips on effectively exporting YouTube cookies') - - def _check_login_required(self): - if self._LOGIN_REQUIRED and not self.is_authenticated: - self.raise_login_required( - f'Login details are needed to download this content. {self._youtube_login_hint}', method=None) - - _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=' - _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=' - - def _get_default_ytcfg(self, client='web'): - return copy.deepcopy(INNERTUBE_CLIENTS[client]) - - def _get_innertube_host(self, client='web'): - return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] - - def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): - # try_get but with fallback to default ytcfg client values when present - _func = lambda y: try_get(y, getter, expected_type) - return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) - - def _extract_client_name(self, ytcfg, default_client='web'): - return self._ytcfg_get_safe( - ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], - lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client) - - def _extract_client_version(self, ytcfg, default_client='web'): - return self._ytcfg_get_safe( - ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], - lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client) - - def _select_api_hostname(self, req_api_hostname, default_client=None): - return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0] - or req_api_hostname or self._get_innertube_host(default_client or 'web')) - - def _extract_context(self, ytcfg=None, default_client='web'): - context = get_first( - (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) - # Enforce language and tz for extraction - client_context = traverse_obj(context, 'client', expected_type=dict, default={}) - client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) - return context - - @staticmethod - def _make_sid_authorization(scheme, sid, origin, additional_parts): - timestamp = str(round(time.time())) - - hash_parts = [] - if additional_parts: - hash_parts.append(':'.join(additional_parts.values())) - hash_parts.extend([timestamp, sid, origin]) - sidhash = hashlib.sha1(' '.join(hash_parts).encode()).hexdigest() - - parts = [timestamp, sidhash] - if additional_parts: - parts.append(''.join(additional_parts)) - - return f'{scheme} {"_".join(parts)}' - - def _get_sid_cookies(self): - """ - Get SAPISID, 1PSAPISID, 3PSAPISID cookie values - @returns sapisid, 1psapisid, 3psapisid - """ - yt_cookies = self._get_cookies('https://www.youtube.com') - yt_sapisid = try_call(lambda: yt_cookies['SAPISID'].value) - yt_3papisid = try_call(lambda: yt_cookies['__Secure-3PAPISID'].value) - yt_1papisid = try_call(lambda: yt_cookies['__Secure-1PAPISID'].value) - - # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. - # YouTube also falls back to __Secure-3PAPISID if SAPISID is missing. - # See: https://github.com/yt-dlp/yt-dlp/issues/393 - - return yt_sapisid or yt_3papisid, yt_1papisid, yt_3papisid - - def _get_sid_authorization_header(self, origin='https://www.youtube.com', user_session_id=None): - """ - Generate API Session ID Authorization for Innertube requests. Assumes all requests are secure (https). - @param origin: Origin URL - @param user_session_id: Optional User Session ID - @return: Authorization header value - """ - - authorizations = [] - additional_parts = {} - if user_session_id: - additional_parts['u'] = user_session_id - - yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies() - - for scheme, sid in (('SAPISIDHASH', yt_sapisid), - ('SAPISID1PHASH', yt_1psapisid), - ('SAPISID3PHASH', yt_3psapisid)): - if sid: - authorizations.append(self._make_sid_authorization(scheme, sid, origin, additional_parts)) - - if not authorizations: - return None - - return ' '.join(authorizations) - - def _call_api(self, ep, query, video_id, fatal=True, headers=None, - note='Downloading API JSON', errnote='Unable to download API page', - context=None, api_key=None, api_hostname=None, default_client='web'): - - data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} - data.update(query) - real_headers = self.generate_api_headers(default_client=default_client) - real_headers.update({'content-type': 'application/json'}) - if headers: - real_headers.update(headers) - return self._download_json( - f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}', - video_id=video_id, fatal=fatal, note=note, errnote=errnote, - data=json.dumps(data).encode('utf8'), headers=real_headers, - query=filter_dict({ - 'key': self._configuration_arg( - 'innertube_key', [api_key], ie_key=YoutubeIE.ie_key(), casesense=True)[0], - 'prettyPrint': 'false', - }, cndn=lambda _, v: v)) - - def extract_yt_initial_data(self, item_id, webpage, fatal=True): - return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal) - - @staticmethod - def _extract_session_index(*data): - """ - Index of current account in account list. - See: https://github.com/yt-dlp/yt-dlp/pull/519 - """ - for ytcfg in data: - session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) - if session_index is not None: - return session_index - - @staticmethod - def _parse_data_sync_id(data_sync_id): - """ - Parse data_sync_id into delegated_session_id and user_session_id. - - data_sync_id is of the form "delegated_session_id||user_session_id" for secondary channel - and just "user_session_id||" for primary channel. - - @param data_sync_id: data_sync_id string - @return: Tuple of (delegated_session_id, user_session_id) - """ - if not data_sync_id: - return None, None - first, _, second = data_sync_id.partition('||') - if second: - return first, second - return None, first - - def _extract_delegated_session_id(self, *args): - """ - Extract current delegated session ID required to download private playlists of secondary channels - @params response and/or ytcfg - @return: delegated session ID - """ - # ytcfg includes channel_syncid if on secondary channel - if delegated_sid := traverse_obj(args, (..., 'DELEGATED_SESSION_ID', {str}, any)): - return delegated_sid - - data_sync_id = self._extract_data_sync_id(*args) - return self._parse_data_sync_id(data_sync_id)[0] - - def _extract_user_session_id(self, *args): - """ - Extract current user session ID - @params response and/or ytcfg - @return: user session ID - """ - if user_sid := traverse_obj(args, (..., 'USER_SESSION_ID', {str}, any)): - return user_sid - - data_sync_id = self._extract_data_sync_id(*args) - return self._parse_data_sync_id(data_sync_id)[1] - - def _extract_data_sync_id(self, *args): - """ - Extract current account dataSyncId. - In the format DELEGATED_SESSION_ID||USER_SESSION_ID or USER_SESSION_ID|| - @params response and/or ytcfg - """ - if data_sync_id := self._configuration_arg('data_sync_id', [None], ie_key=YoutubeIE, casesense=True)[0]: - return data_sync_id - - return traverse_obj( - args, (..., ('DATASYNC_ID', ('responseContext', 'mainAppWebResponseContext', 'datasyncId')), {str}, any)) - - def _extract_visitor_data(self, *args): - """ - Extracts visitorData from an API response or ytcfg - Appears to be used to track session state - """ - if visitor_data := self._configuration_arg('visitor_data', [None], ie_key=YoutubeIE, casesense=True)[0]: - return visitor_data - return get_first( - args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], - expected_type=str) - - @functools.cached_property - def is_authenticated(self): - return bool(self._get_sid_authorization_header()) - - def extract_ytcfg(self, video_id, webpage): - if not webpage: - return {} - return self._parse_json( - self._search_regex( - r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', - default='{}'), video_id, fatal=False) or {} - - def _generate_cookie_auth_headers(self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, origin=None, **kwargs): - headers = {} - delegated_session_id = delegated_session_id or self._extract_delegated_session_id(ytcfg) - if delegated_session_id: - headers['X-Goog-PageId'] = delegated_session_id - if session_index is None: - session_index = self._extract_session_index(ytcfg) - if delegated_session_id or session_index is not None: - headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 - - auth = self._get_sid_authorization_header(origin, user_session_id=user_session_id or self._extract_user_session_id(ytcfg)) - if auth is not None: - headers['Authorization'] = auth - headers['X-Origin'] = origin - - if traverse_obj(ytcfg, 'LOGGED_IN', expected_type=bool): - headers['X-Youtube-Bootstrap-Logged-In'] = 'true' - - return headers - - def generate_api_headers( - self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, - visitor_data=None, api_hostname=None, default_client='web', **kwargs): - - origin = 'https://' + (self._select_api_hostname(api_hostname, default_client)) - headers = { - 'X-YouTube-Client-Name': str( - self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), - 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), - 'Origin': origin, - 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg), - 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client), - **self._generate_cookie_auth_headers( - ytcfg=ytcfg, - delegated_session_id=delegated_session_id, - user_session_id=user_session_id, - session_index=session_index, - origin=origin), - } - return filter_dict(headers) - - def _download_webpage_with_retries(self, *args, retry_fatal=False, retry_on_status=None, **kwargs): - for retry in self.RetryManager(fatal=retry_fatal): - try: - return self._download_webpage(*args, **kwargs) - except ExtractorError as e: - if isinstance(e.cause, network_exceptions): - if not isinstance(e.cause, HTTPError) or e.cause.status not in (retry_on_status or (403, 429)): - retry.error = e - continue - self._error_or_warning(e, fatal=retry_fatal) - break - - def _download_ytcfg(self, client, video_id): - url = { - 'web': 'https://www.youtube.com', - 'web_music': 'https://music.youtube.com', - 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1', - 'tv': 'https://www.youtube.com/tv', - }.get(client) - if not url: - return {} - webpage = self._download_webpage_with_retries( - url, video_id, note=f'Downloading {client.replace("_", " ").strip()} client config', - headers=traverse_obj(self._get_default_ytcfg(client), { - 'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}), - })) - return self.extract_ytcfg(video_id, webpage) or {} - - @staticmethod - def _build_api_continuation_query(continuation, ctp=None): - query = { - 'continuation': continuation, - } - # TODO: Inconsistency with clickTrackingParams. - # Currently we have a fixed ctp contained within context (from ytcfg) - # and a ctp in root query for continuation. - if ctp: - query['clickTracking'] = {'clickTrackingParams': ctp} - return query - - @classmethod - def _extract_next_continuation_data(cls, renderer): - next_continuation = try_get( - renderer, (lambda x: x['continuations'][0]['nextContinuationData'], - lambda x: x['continuation']['reloadContinuationData']), dict) - if not next_continuation: - return - continuation = next_continuation.get('continuation') - if not continuation: - return - ctp = next_continuation.get('clickTrackingParams') - return cls._build_api_continuation_query(continuation, ctp) - - @classmethod - def _extract_continuation_ep_data(cls, continuation_ep: dict): - if isinstance(continuation_ep, dict): - continuation = try_get( - continuation_ep, lambda x: x['continuationCommand']['token'], str) - if not continuation: - return - ctp = continuation_ep.get('clickTrackingParams') - return cls._build_api_continuation_query(continuation, ctp) - - @classmethod - def _extract_continuation(cls, renderer): - next_continuation = cls._extract_next_continuation_data(renderer) - if next_continuation: - return next_continuation - - return traverse_obj(renderer, ( - ('contents', 'items', 'rows'), ..., 'continuationItemRenderer', - ('continuationEndpoint', ('button', 'buttonRenderer', 'command')), - ), get_all=False, expected_type=cls._extract_continuation_ep_data) - - @classmethod - def _extract_alerts(cls, data): - for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: - if not isinstance(alert_dict, dict): - continue - for alert in alert_dict.values(): - alert_type = alert.get('type') - if not alert_type: - continue - message = cls._get_text(alert, 'text') - if message: - yield alert_type, message - - def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): - errors, warnings = [], [] - for alert_type, alert_message in alerts: - if alert_type.lower() == 'error' and fatal: - errors.append([alert_type, alert_message]) - elif alert_message not in self._IGNORED_WARNINGS: - warnings.append([alert_type, alert_message]) - - for alert_type, alert_message in (warnings + errors[:-1]): - self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once) - if errors: - raise ExtractorError(f'YouTube said: {errors[-1][1]}', expected=expected) - - def _extract_and_report_alerts(self, data, *args, **kwargs): - return self._report_alerts(self._extract_alerts(data), *args, **kwargs) - - 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, - '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_VERIFIED': BadgeType.VERIFIED, - 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED, - } - - label_map = { - 'unlisted': BadgeType.AVAILABILITY_UNLISTED, - 'private': BadgeType.AVAILABILITY_PRIVATE, - 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION, - 'live': BadgeType.LIVE_NOW, - 'premium': BadgeType.AVAILABILITY_PREMIUM, - 'verified': BadgeType.VERIFIED, - 'official artist channel': BadgeType.VERIFIED, - } - - badges = [] - for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))): - badge_type = ( - icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str)) - or badge_style_map.get(traverse_obj(badge, 'style')) - ) - if badge_type: - badges.append({'type': badge_type}) - continue - - # fallback, won't work in some languages - 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': label_badge_type}) - break - - return badges - - @staticmethod - def _has_badge(badges, badge_type): - return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type)) - - @staticmethod - def _get_text(data, *path_list, max_runs=None): - for path in path_list or [None]: - if path is None: - obj = [data] - else: - obj = traverse_obj(data, path, default=[]) - if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): - obj = [obj] - for item in obj: - text = try_get(item, lambda x: x['simpleText'], str) - if text: - return text - runs = try_get(item, lambda x: x['runs'], list) or [] - if not runs and isinstance(item, list): - runs = item - - runs = runs[:min(len(runs), max_runs or len(runs))] - text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str)) - if text: - return text - - def _get_count(self, data, *path_list): - count_text = self._get_text(data, *path_list) or '' - count = parse_count(count_text) - if count is None: - count = str_to_int( - self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None)) - return count - - @staticmethod - def _extract_thumbnails(data, *path_list, final_key='thumbnails'): - """ - Extract thumbnails from thumbnails dict - @param path_list: path list to level that contains 'thumbnails' key - """ - thumbnails = [] - for path in path_list or [()]: - for thumbnail in traverse_obj(data, (*variadic(path), final_key, ...)): - thumbnail_url = url_or_none(thumbnail.get('url')) - if not thumbnail_url: - continue - # Sometimes youtube gives a wrong thumbnail URL. See: - # https://github.com/yt-dlp/yt-dlp/issues/233 - # https://github.com/ytdl-org/youtube-dl/issues/28023 - if 'maxresdefault' in thumbnail_url: - thumbnail_url = thumbnail_url.split('?')[0] - thumbnails.append({ - 'url': thumbnail_url, - 'height': int_or_none(thumbnail.get('height')), - 'width': int_or_none(thumbnail.get('width')), - }) - return thumbnails - - @staticmethod - 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', '8 yr ago' - """ - - # 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: - return datetime_from_str(start) - try: - return datetime_from_str('now-{}{}'.format(mobj.group('time'), mobj.group('unit'))) - except ValueError: - return None - - def _parse_time_text(self, text): - if not text: - return - dt_ = self.extract_relative_time(text) - timestamp = None - if isinstance(dt_, dt.datetime): - timestamp = calendar.timegm(dt_.timetuple()) - - if timestamp is None: - timestamp = ( - unified_timestamp(text) or unified_timestamp( - self._search_regex( - (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'), - text.lower(), 'time text', default=None))) - - if text and timestamp is None and self._preferred_lang in (None, 'en'): - self.report_warning( - f'Cannot parse localized time text "{text}"', only_once=True) - return timestamp - - 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'): - 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 its result MUST be checked if the manager is non fatal - while True: - try: - response = self._call_api( - ep=ep, fatal=True, headers=headers, - video_id=item_id, query=query, note=note, - context=self._extract_context(ytcfg, default_client), - api_hostname=api_hostname, default_client=default_client) - except ExtractorError as e: - if not isinstance(e.cause, network_exceptions): - return self._error_or_warning(e, fatal=fatal) - elif not isinstance(e.cause, HTTPError): - main_rm.error = e - next(main_retries) - continue - - 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.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 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.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'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(): - 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)): - icd_rm.error = ExtractorError('Incomplete data received', expected=True) - should_retry = next(icd_retries, None) - if not should_retry: - return None - continue - - return response - - @staticmethod - def is_music_url(url): - return re.match(r'(https?://)?music\.youtube\.com/', url) is not None - - def _extract_video(self, renderer): - video_id = renderer.get('videoId') - - reel_header_renderer = traverse_obj(renderer, ( - 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer', - 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer')) - - title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText') - description = self._get_text(renderer, 'descriptionSnippet') - - duration = int_or_none(renderer.get('lengthSeconds')) - if duration is None: - duration = parse_duration(self._get_text( - renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) - if duration is None: - # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab) - duration = parse_duration(self._search_regex( - r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$', - traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str), - video_id, default=None, group='duration')) - - channel_id = traverse_obj( - renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), - expected_type=str, get_all=False) - 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(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 '' - url = f'https://www.youtube.com/watch?v={video_id}' - if overlay_style == 'SHORTS' or '/shorts/' in navigation_url: - url = f'https://www.youtube.com/shorts/{video_id}' - - time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo') - or self._get_text(reel_header_renderer, 'timestampText') or '') - scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False)) - - live_status = ( - 'is_upcoming' if scheduled_timestamp is not None - else 'was_live' if 'streamed' in time_text.lower() - else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW) - else None) - - # videoInfo is a string like '50K views • 10 years ago'. - view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or '' - view_count = (0 if 'no views' in view_count_text.lower() - 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(), - 'id': video_id, - 'url': url, - 'title': title, - 'description': description, - 'duration': duration, - 'channel_id': channel_id, - '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) - else None), - 'release_timestamp': scheduled_timestamp, - 'availability': - 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) - else self._availability( - is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None, - needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None, - 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, - 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None, - } - - class YoutubeIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube' _VALID_URL = r'''(?x)^ @@ -2970,7 +1762,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): @classmethod def suitable(cls, url): - from ..utils import parse_qs + from yt_dlp.utils import parse_qs qs = parse_qs(url) if qs.get('list', [None])[0]: @@ -5166,2847 +3958,3 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self.mark_watched(video_id, player_responses) return info - - -class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): - @staticmethod - def passthrough_smuggled_data(func): - def _smuggle(info, smuggled_data): - if info.get('_type') not in ('url', 'url_transparent'): - return info - if smuggled_data.get('is_music_url'): - parsed_url = urllib.parse.urlparse(info['url']) - if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'): - smuggled_data.pop('is_music_url') - info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com')) - if smuggled_data: - info['url'] = smuggle_url(info['url'], smuggled_data) - return info - - @functools.wraps(func) - def wrapper(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - if self.is_music_url(url): - smuggled_data['is_music_url'] = True - info_dict = func(self, url, smuggled_data) - if smuggled_data: - _smuggle(info_dict, smuggled_data) - if info_dict.get('entries'): - info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries']) - return info_dict - return wrapper - - @staticmethod - def _extract_basic_item_renderer(item): - # Modified from _extract_grid_item_renderer - known_basic_renderers = ( - 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer', - ) - for key, renderer in item.items(): - if not isinstance(renderer, dict): - continue - elif key in known_basic_renderers: - return renderer - elif key.startswith('grid') and key.endswith('Renderer'): - return renderer - - def _extract_channel_renderer(self, renderer): - channel_id = self.ucid_or_none(renderer['channelId']) - title = self._get_text(renderer, 'title') - 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, - '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': ( - # 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): - for item in grid_renderer['items']: - if not isinstance(item, dict): - continue - if lockup_view_model := traverse_obj(item, ('lockupViewModel', {dict})): - if entry := self._extract_lockup_view_model(lockup_view_model): - yield entry - continue - renderer = self._extract_basic_item_renderer(item) - if not isinstance(renderer, dict): - continue - title = self._get_text(renderer, 'title') - - # playlist - 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=title) - continue - # video - video_id = renderer.get('videoId') - if video_id: - yield self._extract_video(renderer) - continue - # channel - channel_id = renderer.get('channelId') - if channel_id: - yield self._extract_channel_renderer(renderer) - continue - # generic endpoint URL support - ep_url = urljoin('https://www.youtube.com/', try_get( - renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], - str)) - if ep_url: - for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): - if ie.suitable(ep_url): - yield self.url_result( - ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) - break - - 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, title=title) - playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) - if playlist_id: - video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) - if video_id: - return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}', - ie=YoutubeTabIE.ie_key(), video_id=playlist_id) - return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}', - ie=YoutubeTabIE.ie_key(), video_id=playlist_id) - browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId')) - if browse_id: - return self.url_result(f'https://music.youtube.com/browse/{browse_id}', - ie=YoutubeTabIE.ie_key(), video_id=browse_id) - - def _shelf_entries_from_content(self, shelf_renderer): - content = shelf_renderer.get('content') - if not isinstance(content, dict): - return - renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') - if renderer: - # TODO: add support for nested playlists so each shelf is processed - # as separate playlist - # TODO: this includes only first N items - yield from self._grid_entries(renderer) - renderer = content.get('horizontalListRenderer') - if renderer: - # TODO: handle case - pass - - def _shelf_entries(self, shelf_renderer, skip_channels=False): - ep = try_get( - shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], - str) - shelf_url = urljoin('https://www.youtube.com', ep) - if shelf_url: - # Skipping links to another channels, note that checking for - # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL - # will not work - if skip_channels and '/channels?' in shelf_url: - return - title = self._get_text(shelf_renderer, 'title') - yield self.url_result(shelf_url, video_title=title) - # Shelf may not contain shelf URL, fallback to extraction from content - yield from self._shelf_entries_from_content(shelf_renderer) - - def _playlist_entries(self, video_list_renderer): - for content in video_list_renderer['contents']: - if not isinstance(content, dict): - continue - renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') - if not isinstance(renderer, dict): - continue - video_id = renderer.get('videoId') - if not video_id: - continue - yield self._extract_video(renderer) - - def _extract_lockup_view_model(self, view_model): - content_id = view_model.get('contentId') - if not content_id: - return - content_type = view_model.get('contentType') - if content_type not in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'): - self.report_warning( - f'Unsupported lockup view model content type "{content_type}"{bug_reports_message()}', only_once=True) - return - return self.url_result( - f'https://www.youtube.com/playlist?list={content_id}', ie=YoutubeTabIE, video_id=content_id, - title=traverse_obj(view_model, ( - 'metadata', 'lockupMetadataViewModel', 'title', 'content', {str})), - thumbnails=self._extract_thumbnails(view_model, ( - 'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image'), final_key='sources')) - - def _rich_entries(self, rich_grid_renderer): - if lockup_view_model := traverse_obj(rich_grid_renderer, ('content', 'lockupViewModel', {dict})): - if entry := self._extract_lockup_view_model(lockup_view_model): - yield entry - return - renderer = traverse_obj( - rich_grid_renderer, - ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel'), any)) or {} - video_id = renderer.get('videoId') - 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 - # shortsLockupViewModel extraction - entity_id = renderer.get('entityId') - if entity_id: - video_id = traverse_obj(renderer, ('onTap', 'innertubeCommand', 'reelWatchEndpoint', 'videoId', {str})) - if not video_id: - return - yield self.url_result( - f'https://www.youtube.com/shorts/{video_id}', - ie=YoutubeIE, video_id=video_id, - **traverse_obj(renderer, { - 'title': (( - ('overlayMetadata', 'primaryText', 'content', {str}), - ('accessibilityText', {lambda x: re.fullmatch(r'(.+), (?:[\d,.]+(?:[KM]| million)?|No) views? - play Short', x)}, 1)), any), - 'view_count': ('overlayMetadata', 'secondaryText', 'content', {parse_count}), - }), - thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources')) - return - - def _video_entry(self, video_renderer): - video_id = video_renderer.get('videoId') - if video_id: - return self._extract_video(video_renderer) - - def _hashtag_tile_entry(self, hashtag_tile_renderer): - url = urljoin('https://youtube.com', traverse_obj( - hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url'))) - if url: - return self.url_result( - url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag')) - - def _post_thread_entries(self, post_thread_renderer): - post_renderer = try_get( - post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) - if not post_renderer: - return - # video attachment - video_renderer = try_get( - post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} - video_id = video_renderer.get('videoId') - if video_id: - entry = self._extract_video(video_renderer) - if entry: - yield entry - # playlist attachment - playlist_id = try_get( - post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str) - if playlist_id: - yield self.url_result( - f'https://www.youtube.com/playlist?list={playlist_id}', - ie=YoutubeTabIE.ie_key(), video_id=playlist_id) - # inline video links - runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] - for run in runs: - if not isinstance(run, dict): - continue - ep_url = try_get( - run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str) - if not ep_url: - continue - if not YoutubeIE.suitable(ep_url): - continue - ep_video_id = YoutubeIE._match_id(ep_url) - if video_id == ep_video_id: - continue - yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) - - def _post_thread_continuation_entries(self, post_thread_continuation): - contents = post_thread_continuation.get('contents') - if not isinstance(contents, list): - return - for content in contents: - renderer = content.get('backstagePostThreadRenderer') - if isinstance(renderer, dict): - yield from self._post_thread_entries(renderer) - continue - renderer = content.get('videoRenderer') - if isinstance(renderer, dict): - yield self._video_entry(renderer) - - r''' # unused - def _rich_grid_entries(self, contents): - for content in contents: - video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) - if video_renderer: - entry = self._video_entry(video_renderer) - if entry: - yield entry - ''' - - def _report_history_entries(self, renderer): - for url in traverse_obj(renderer, ( - 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ..., - 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ..., - 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')): - yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE) - - def _extract_entries(self, parent_renderer, continuation_list): - # continuation_list is modified in-place with continuation_list = [continuation_token] - continuation_list[:] = [None] - contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] - for content in contents: - if not isinstance(content, dict): - continue - is_renderer = traverse_obj( - content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation', - expected_type=dict) - if not is_renderer: - if content.get('richItemRenderer'): - for entry in self._rich_entries(content['richItemRenderer']): - yield entry - continuation_list[0] = self._extract_continuation(parent_renderer) - elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory - table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer')) - yield from self._report_history_entries(table) - continuation_list[0] = self._extract_continuation(table) - continue - - isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] - for isr_content in isr_contents: - if not isinstance(isr_content, dict): - continue - - known_renderers = { - 'playlistVideoListRenderer': self._playlist_entries, - 'gridRenderer': self._grid_entries, - 'reelShelfRenderer': self._grid_entries, - 'shelfRenderer': self._shelf_entries, - 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)], - 'backstagePostThreadRenderer': self._post_thread_entries, - '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)], - 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list), - 'lockupViewModel': lambda x: [self._extract_lockup_view_model(x)], - } - for key, renderer in isr_content.items(): - if key not in known_renderers: - continue - for entry in known_renderers[key](renderer): - if entry: - yield entry - continuation_list[0] = self._extract_continuation(renderer) - break - - if not continuation_list[0]: - continuation_list[0] = self._extract_continuation(is_renderer) - - if not continuation_list[0]: - continuation_list[0] = self._extract_continuation(parent_renderer) - - def _entries(self, tab, item_id, ytcfg, delegated_session_id, visitor_data): - continuation_list = [None] - extract_entries = lambda x: self._extract_entries(x, continuation_list) - tab_content = try_get(tab, lambda x: x['content'], dict) - if not tab_content: - return - parent_renderer = ( - try_get(tab_content, lambda x: x['sectionListRenderer'], dict) - 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, delegated_session_id=delegated_session_id, visitor_data=visitor_data) - response = self._extract_response( - item_id=f'{item_id} page {page_num}', - query=continuation, headers=headers, ytcfg=ytcfg, - check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) - - if not response: - break - # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases - # See: https://github.com/ytdl-org/youtube-dl/issues/28702 - visitor_data = self._extract_visitor_data(response) or visitor_data - - known_renderers = { - 'videoRenderer': (self._grid_entries, 'items'), # for membership tab - 'gridPlaylistRenderer': (self._grid_entries, 'items'), - 'gridVideoRenderer': (self._grid_entries, 'items'), - 'gridChannelRenderer': (self._grid_entries, 'items'), - 'playlistVideoRenderer': (self._playlist_entries, 'contents'), - 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds - 'richItemRenderer': (extract_entries, 'contents'), # for hashtag - 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'), - 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'), - 'playlistVideoListContinuation': (self._playlist_entries, None), - 'gridContinuation': (self._grid_entries, None), - 'itemSectionContinuation': (self._post_thread_continuation_entries, None), - 'sectionListContinuation': (extract_entries, None), # for feeds - } - - continuation_items = traverse_obj(response, ( - ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ..., - 'appendContinuationItemsAction', 'continuationItems', - ), 'continuationContents', get_all=False) - continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={}) - - video_items_renderer = None - for key in continuation_item: - if key not in known_renderers: - continue - func, parent_key = known_renderers[key] - video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items - continuation_list = [None] - yield from func(video_items_renderer) - continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) - - if not video_items_renderer: - break - - @staticmethod - def _extract_selected_tab(tabs, fatal=True): - for tab_renderer in tabs: - if tab_renderer.get('selected'): - return tab_renderer - if fatal: - raise ExtractorError('Unable to find selected tab') - - @staticmethod - def _extract_tab_renderers(response): - return traverse_obj( - response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict) - - def _extract_from_tabs(self, item_id, ytcfg, data, tabs): - metadata = self._extract_metadata_from_tabs(item_id, data) - - selected_tab = self._extract_selected_tab(tabs) - metadata['title'] += format_field(selected_tab, 'title', ' - %s') - metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s') - - return self.playlist_result( - self._entries( - selected_tab, metadata['id'], ytcfg, - self._extract_delegated_session_id(ytcfg, data), - self._extract_visitor_data(data, ytcfg)), - **metadata) - - def _extract_metadata_from_tabs(self, item_id, data): - info = {'id': item_id} - - 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({ - 'channel': metadata_renderer.get('title'), - 'channel_id': channel_id, - }) - if info['channel_id']: - info['id'] = info['channel_id'] - else: - metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict) - - # pageHeaderViewModel slow rollout began April 2024 - page_header_view_model = traverse_obj(data, ( - 'header', 'pageHeaderRenderer', 'content', 'pageHeaderViewModel', {dict})) - - # We can get the uncropped banner/avatar by replacing the crop params with '=s0' - # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714 - def _get_uncropped(url): - return url_or_none((url or '').split('=')[0] + '=s0') - - avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar') - if avatar_thumbnails: - uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url']) - if uncropped_avatar: - avatar_thumbnails.append({ - 'url': uncropped_avatar, - 'id': 'avatar_uncropped', - 'preference': 1, - }) - - channel_banners = ( - self._extract_thumbnails(data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner'))) - or self._extract_thumbnails( - page_header_view_model, ('banner', 'imageBannerViewModel', 'image'), final_key='sources')) - for banner in channel_banners: - banner['preference'] = -10 - - if channel_banners: - uncropped_banner = _get_uncropped(channel_banners[0]['url']) - if uncropped_banner: - channel_banners.append({ - 'url': uncropped_banner, - 'id': 'banner_uncropped', - 'preference': -5, - }) - - # Deprecated - remove primary_sidebar_renderer when layout discontinued - primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') - playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict) - - primary_thumbnails = self._extract_thumbnails( - primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail')) - playlist_thumbnails = self._extract_thumbnails( - playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail')) - - info.update({ - 'title': (traverse_obj(metadata_renderer, 'title') - or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) - or info['id']), - 'availability': self._extract_availability(data), - 'channel_follower_count': ( - self._get_count(data, ('header', ..., 'subscriberCountText')) - or traverse_obj(page_header_view_model, ( - 'metadata', 'contentMetadataViewModel', 'metadataRows', ..., 'metadataParts', - lambda _, v: 'subscribers' in v['text']['content'], 'text', 'content', {parse_count}, any))), - 'description': try_get(metadata_renderer, lambda x: x.get('description', '')), - 'tags': (traverse_obj(data, ('microformat', 'microformatDataRenderer', 'tags', ..., {str})) - or traverse_obj(metadata_renderer, ('keywords', {lambda x: x and shlex.split(x)}, ...))), - '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( - (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), )) - - 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) - - info['view_count'] = self._get_count(playlist_stats, 1) - if info['view_count'] is None: # 0 is allowed - info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText') - if info['view_count'] is None: - info['view_count'] = self._get_count(data, ( - 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer', - 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText')) - - info['playlist_count'] = self._get_count(playlist_stats, 0) - if info['playlist_count'] is None: # 0 is allowed - info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text')) - - if not info.get('channel_id'): - owner = traverse_obj(playlist_header_renderer, 'ownerText') - if not owner: # Deprecated - owner = traverse_obj( - self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'), - ('videoOwner', 'videoOwnerRenderer', 'title')) - owner_text = self._get_text(owner) - browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {} - info.update({ - '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({ - '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): - first_id = last_id = response = None - for page_num in itertools.count(1): - videos = list(self._playlist_entries(playlist)) - if not videos: - return - start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 - if start >= len(videos): - return - yield from videos[start:] - first_id = first_id or videos[0]['id'] - last_id = videos[-1]['id'] - watch_endpoint = try_get( - playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) - headers = self.generate_api_headers( - ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data), - visitor_data=self._extract_visitor_data(response, data, ytcfg)) - query = { - 'playlistId': playlist_id, - 'videoId': watch_endpoint.get('videoId') or last_id, - 'index': watch_endpoint.get('index') or len(videos), - 'params': watch_endpoint.get('params') or 'OAE%3D', - } - response = self._extract_response( - item_id=f'{playlist_id} page {page_num}', - query=query, ep='next', headers=headers, ytcfg=ytcfg, - check_get_keys='contents', - ) - playlist = try_get( - response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) - - def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg): - title = playlist.get('title') or try_get( - data, lambda x: x['titleText']['simpleText'], str) - playlist_id = playlist.get('playlistId') or item_id - - # Delegating everything except mix playlists to regular tab-based playlist URL - playlist_url = urljoin(url, try_get( - playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], - str)) - - # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1] - # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg - is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id) - - if playlist_url and playlist_url != url and not is_known_unviewable: - return self.url_result( - playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, - video_title=title) - - return self.playlist_result( - self._extract_inline_playlist(playlist, playlist_id, data, ytcfg), - playlist_id=playlist_id, playlist_title=title) - - def _extract_availability(self, data): - """ - Gets the availability of a given playlist/tab. - Note: Unless YouTube tells us explicitly, we do not assume it is public - @param data: response - """ - sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} - playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {} - player_header_privacy = playlist_header_renderer.get('privacy') - - 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( - (playlist_header_renderer, sidebar_renderer), - ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries', - lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'), - expected_type=str) - - microformats_is_unlisted = traverse_obj( - data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool) - - return ( - 'public' if ( - self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) - or player_header_privacy == 'PUBLIC' - or privacy_setting_icon == 'PRIVACY_PUBLIC') - else self._availability( - is_private=( - self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) - or player_header_privacy == 'PRIVATE' if player_header_privacy is not None - else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None), - is_unlisted=( - self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) - or player_header_privacy == 'UNLISTED' if player_header_privacy is not None - else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None - else microformats_is_unlisted if microformats_is_unlisted is not None else None), - needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None, - needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None, - needs_auth=False)) - - @staticmethod - def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): - sidebar_renderer = try_get( - data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] - for item in sidebar_renderer: - renderer = try_get(item, lambda x: x[info_renderer], expected_type) - if renderer: - return renderer - - def _reload_with_unavailable_videos(self, item_id, data, ytcfg): - """ - Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.) - """ - is_playlist = bool(traverse_obj( - data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer'))) - if not is_playlist: - return - headers = self.generate_api_headers( - ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data), - visitor_data=self._extract_visitor_data(data, ytcfg)) - query = { - 'params': 'wgYCCAA=', - 'browseId': f'VL{item_id}', - } - return self._extract_response( - item_id=item_id, headers=headers, query=query, - check_get_keys='contents', fatal=False, ytcfg=ytcfg, - note='Redownloading playlist API JSON with unavailable videos') - - @functools.cached_property - def skip_webpage(self): - return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) - - def _extract_webpage(self, url, item_id, fatal=True): - webpage, data = None, None - for retry in self.RetryManager(fatal=fatal): - try: - webpage = self._download_webpage(url, item_id, note='Downloading webpage') - 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, HTTPError) or e.cause.status not in (403, 429): - retry.error = e - continue - self._error_or_warning(e, fatal=fatal) - break - - try: - self._extract_and_report_alerts(data) - except ExtractorError as e: - self._error_or_warning(e, fatal=fatal) - break - - # Sometimes youtube returns a webpage with incomplete ytInitialData - # See: https://github.com/yt-dlp/yt-dlp/issues/116 - if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'): - retry.error = ExtractorError('Incomplete yt initial data received') - data = None - continue - - return webpage, data - - def _report_playlist_authcheck(self, ytcfg, fatal=True): - """Use if failed to extract ytcfg (and data) from initial webpage""" - if not ytcfg and self.is_authenticated: - msg = 'Playlists that require authentication may not extract correctly without a successful webpage download' - if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal: - raise ExtractorError( - f'{msg}. If you are not downloading private content, or ' - 'your cookies are only for the first account and channel,' - ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check', - expected=True) - self.report_warning(msg, only_once=True) - - def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'): - data = None - if not self.skip_webpage: - webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal) - ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage) - # Reject webpage data if redirected to home page without explicitly requesting - selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {} - if (url != 'https://www.youtube.com/feed/recommended' - and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page - and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])): - msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page' - if fatal: - raise ExtractorError(msg, expected=True) - self.report_warning(msg, only_once=True) - if not data: - self._report_playlist_authcheck(ytcfg, fatal=fatal) - data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client) - return data, ytcfg - - def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'): - headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client) - resolve_response = self._extract_response( - item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal, - ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client) - endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'} - for ep_key, ep in endpoints.items(): - params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict) - if params: - return self._extract_response( - item_id=item_id, query=params, ep=ep, headers=headers, - ytcfg=ytcfg, fatal=fatal, default_client=default_client, - check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')) - err_note = 'Failed to resolve url (does the playlist exist?)' - if fatal: - raise ExtractorError(err_note, expected=True) - self.report_warning(err_note, item_id) - - _SEARCH_PARAMS = None - - def _search_results(self, query, params=NO_DEFAULT, default_client='web'): - data = {'query': query} - if params is NO_DEFAULT: - params = self._SEARCH_PARAMS - if params: - data['params'] = params - - content_keys = ( - ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'), - ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'), - # ytmusic search - ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'), - ('continuationContents', ), - ) - display_id = f'query "{query}"' - check_get_keys = tuple({keys[0] for keys in content_keys}) - ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {} - self._report_playlist_authcheck(ytcfg, fatal=False) - - continuation_list = [None] - search = None - for page_num in itertools.count(1): - data.update(continuation_list[0] or {}) - headers = self.generate_api_headers( - ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client) - search = self._extract_response( - item_id=f'{display_id} page {page_num}', ep='search', query=data, - default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers) - slr_contents = traverse_obj(search, *content_keys) - yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list) - if not continuation_list[0]: - break - - -class YoutubeTabIE(YoutubeTabBaseInfoExtractor): - IE_DESC = 'YouTube Tabs' - _VALID_URL = r'''(?x: - https?:// - (?!consent\.)(?:\w+\.)? - (?: - youtube(?:kids)?\.com| - {invidious} - )/ - (?: - (?P<channel_type>channel|c|user|browse)/| - (?P<not_channel> - feed/|hashtag/| - (?:playlist|watch)\?.*?\blist= - )| - (?!(?:{reserved_names})\b) # Direct URLs - ) - (?P<id>[^/?\#&]+) - )'''.format( - reserved_names=YoutubeBaseInfoExtractor._RESERVED_NAMES, - invidious='|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), - ) - IE_NAME = 'youtube:tab' - - _TESTS = [{ - 'note': 'playlists, multipage', - 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', - 'playlist_mincount': 94, - 'info_dict': { - 'id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'title': 'Igor Kleiner Ph.D. - Playlists', - 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a', - 'uploader': 'Igor Kleiner Ph.D.', - 'uploader_id': '@IgorDataScience', - 'uploader_url': 'https://www.youtube.com/@IgorDataScience', - 'channel': 'Igor Kleiner Ph.D.', - 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'], - 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', - 'channel_follower_count': int, - }, - }, { - 'note': 'playlists, multipage, different order', - 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', - 'playlist_mincount': 94, - 'info_dict': { - 'id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'title': 'Igor Kleiner Ph.D. - Playlists', - 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a', - 'uploader': 'Igor Kleiner Ph.D.', - 'uploader_id': '@IgorDataScience', - 'uploader_url': 'https://www.youtube.com/@IgorDataScience', - 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'], - 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', - 'channel': 'Igor Kleiner Ph.D.', - 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', - 'channel_follower_count': int, - }, - }, { - 'note': 'playlists, series', - 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', - 'playlist_mincount': 5, - 'info_dict': { - 'id': 'UCYO_jab_esuFRV4b17AJtAw', - 'title': '3Blue1Brown - Playlists', - 'description': 'md5:602e3789e6a0cb7d9d352186b720e395', - 'channel_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_is_verified': True, - }, - }, { - 'note': 'playlists, singlepage', - 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', - 'playlist_mincount': 4, - 'info_dict': { - 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', - 'title': 'ThirstForScience - Playlists', - 'description': 'md5:609399d937ea957b0f53cbffb747a14c', - 'uploader': 'ThirstForScience', - 'uploader_url': 'https://www.youtube.com/@ThirstForScience', - 'uploader_id': '@ThirstForScience', - 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', - 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', - 'tags': 'count:12', - 'channel': 'ThirstForScience', - 'channel_follower_count': int, - }, - }, { - 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', - 'only_matching': True, - }, { - 'note': 'basic, single video playlist', - 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', - 'info_dict': { - 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', - 'title': 'youtube-dl public playlist', - 'description': '', - 'tags': [], - 'view_count': int, - 'modified_date': '20201130', - 'channel': 'Sergey M.', - 'channel_id': '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': { - 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', - 'title': 'youtube-dl empty playlist', - 'tags': [], - 'channel': 'Sergey M.', - 'description': '', - 'modified_date': '20230921', - 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', - 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'availability': 'unlisted', - 'uploader_url': 'https://www.youtube.com/@sergeym.6173', - 'uploader_id': '@sergeym.6173', - 'uploader': 'Sergey M.', - }, - 'playlist_count': 0, - }, { - 'note': 'Home tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Home', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': '@lexwill718', - 'channel': 'lex will', - 'tags': ['bible', 'history', 'prophesy'], - 'uploader_url': 'https://www.youtube.com/@lexwill718', - 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_follower_count': int, - }, - 'playlist_mincount': 2, - }, { - 'note': 'Videos tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Videos', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': '@lexwill718', - 'tags': ['bible', 'history', 'prophesy'], - 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/@lexwill718', - 'channel': 'lex will', - 'channel_follower_count': int, - }, - 'playlist_mincount': 975, - }, { - 'note': 'Videos tab, sorted by popular', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Videos', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': '@lexwill718', - 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'uploader_url': 'https://www.youtube.com/@lexwill718', - 'channel': 'lex will', - 'tags': ['bible', 'history', 'prophesy'], - 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_follower_count': int, - }, - 'playlist_mincount': 199, - }, { - 'note': 'Playlists tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Playlists', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'uploader': 'lex will', - 'uploader_id': '@lexwill718', - 'uploader_url': 'https://www.youtube.com/@lexwill718', - 'channel': 'lex will', - 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'tags': ['bible', 'history', 'prophesy'], - 'channel_follower_count': int, - }, - 'playlist_mincount': 17, - }, { - 'note': 'Community tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Community', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'channel': 'lex will', - 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'tags': ['bible', 'history', 'prophesy'], - 'channel_follower_count': int, - 'uploader_url': 'https://www.youtube.com/@lexwill718', - 'uploader_id': '@lexwill718', - 'uploader': 'lex will', - }, - 'playlist_mincount': 18, - }, { - 'note': 'Channels tab', - 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', - 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'title': 'lex will - Channels', - 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', - 'channel': 'lex will', - 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', - 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', - 'tags': ['bible', 'history', 'prophesy'], - 'channel_follower_count': int, - 'uploader_url': 'https://www.youtube.com/@lexwill718', - 'uploader_id': '@lexwill718', - 'uploader': 'lex will', - }, - 'playlist_mincount': 12, - }, { - 'note': 'Search tab', - 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', - 'playlist_mincount': 40, - 'info_dict': { - 'id': 'UCYO_jab_esuFRV4b17AJtAw', - 'title': '3Blue1Brown - Search - linear algebra', - 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', - 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', - 'tags': ['Mathematics'], - 'channel': '3Blue1Brown', - 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', - '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', - 'only_matching': True, - }, { - 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'only_matching': True, - }, { - 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', - 'only_matching': True, - }, { - 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', - 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', - 'info_dict': { - 'title': '29C3: Not my department', - 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', - 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', - 'tags': [], - 'view_count': int, - 'modified_date': '20150605', - 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', - '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, - }, { - 'note': 'Large playlist', - 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', - 'info_dict': { - 'title': 'Uploads from Cauchemar', - 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', - 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q', - 'tags': [], - 'modified_date': r're:\d{8}', - 'channel': 'Cauchemar', - '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'], - }, { - 'note': 'even larger playlist, 8832 videos', - 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', - 'only_matching': True, - }, { - 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', - 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', - 'info_dict': { - 'title': 'Uploads from Interstellar Movie', - 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', - 'tags': [], - 'view_count': int, - 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', - '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, - }, { - 'note': 'Playlist with "show unavailable videos" button', - 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', - 'info_dict': { - 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', - 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', - 'view_count': int, - 'channel': 'Phim Siêu Nhân Nhật Bản', - 'tags': [], - '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'], - }, { - 'note': 'Playlist with unavailable videos in page 7', - 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', - 'info_dict': { - 'title': 'Uploads from BlankTV', - 'id': 'UU8l9frL61Yl5KFOl87nIm2w', - 'channel': 'BlankTV', - 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w', - 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', - 'view_count': int, - 'tags': [], - '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'], - }, { - 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', - 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'info_dict': { - 'title': 'Data Analysis with Dr Mike Pound', - 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', - 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', - 'tags': [], - 'view_count': int, - 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', - '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, - }, { - 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', - 'only_matching': True, - }, { - 'note': 'Playlist URL that does not actually serve a playlist', - 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', - 'info_dict': { - 'id': 'FqZTN594JQw', - 'ext': 'webm', - 'title': "Smiley's People 01 detective, Adventure Series, Action", - 'upload_date': '20150526', - 'license': 'Standard YouTube License', - 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', - 'categories': ['People & Blogs'], - 'tags': list, - 'view_count': int, - 'like_count': int, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'This video is not available.', - 'add_ie': [YoutubeIE.ie_key()], - }, { - 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', - 'info_dict': { - 'id': 'hGkQjiJLjWQ', # This will keep changing - 'ext': 'mp4', - 'title': str, - 'upload_date': r're:\d{8}', - 'description': str, - 'categories': ['News & Politics'], - 'tags': list, - 'like_count': int, - 'release_timestamp': int, - 'channel': 'Sky News', - 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ', - 'age_limit': 0, - 'view_count': int, - 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg', - 'playable_in_embed': True, - 'release_date': r're:\d+', - 'availability': 'public', - 'live_status': 'is_live', - '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, - }, - 'expected_warnings': ['Ignoring subtitle tracks found in '], - }, { - 'url': 'https://www.youtube.com/user/TheYoungTurks/live', - 'info_dict': { - 'id': 'a48o2S1cPoo', - 'ext': 'mp4', - 'title': 'The Young Turks - Live Main Show', - 'upload_date': '20150715', - 'license': 'Standard YouTube License', - 'description': 'md5:438179573adcdff3c97ebb1ee632b891', - 'categories': ['News & Politics'], - 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], - 'like_count': int, - }, - 'params': { - 'skip_download': True, - }, - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', - 'only_matching': True, - }, { - 'note': 'A channel that is not live. Should raise error', - 'url': 'https://www.youtube.com/user/numberphile/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/trending', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/library', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/history', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/subscriptions', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/feed/watch_later', - 'only_matching': True, - }, { - 'note': 'Recommended - redirects to home page.', - 'url': 'https://www.youtube.com/feed/recommended', - 'only_matching': True, - }, { - 'note': 'inline playlist with not always working continuations', - 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/course', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/zsecurity', - 'only_matching': True, - }, { - 'url': 'http://www.youtube.com/NASAgovVideo/videos', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/TheYoungTurks/live', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/hashtag/cctv9', - 'info_dict': { - 'id': 'cctv9', - 'title': 'cctv9 - All', - 'tags': [], - }, - 'playlist_mincount': 300, # not consistent but should be over 300 - }, { - 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', - 'only_matching': True, - }, { - 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', - 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', - 'only_matching': True, - }, { - 'note': '/browse/ should redirect to /channel/', - 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', - 'only_matching': True, - }, { - 'note': 'VLPL, should redirect to playlist?list=PL...', - 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', - 'info_dict': { - 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', - 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', - 'title': 'NCS : All Releases 💿', - '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', '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', - 'title': 'Uploads from Royalty Free Music - Topic', - 'tags': [], - 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', - 'channel': 'Royalty Free Music - Topic', - 'view_count': int, - 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', - 'modified_date': r're:\d{8}', - '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 - 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', - 'info_dict': { - 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', - 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', - 'tags': [], - }, - 'playlist_mincount': 9, - }, { - 'note': 'Youtube music Album', - 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', - 'info_dict': { - 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', - 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', - 'tags': [], - 'view_count': int, - 'description': '', - 'availability': 'unlisted', - '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': { - 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', - 'title': 'yt-dlp unlisted playlist test', - 'availability': 'unlisted', - 'tags': [], - 'modified_date': '20220418', - 'channel': 'colethedj', - 'view_count': int, - 'description': '', - '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', - 'info_dict': { - 'id': 'recommended', - 'title': 'recommended', - 'tags': [], - }, - 'playlist_mincount': 50, - 'params': { - 'skip_download': True, - 'extractor_args': {'youtubetab': {'skip': ['webpage']}}, - }, - }, { - 'note': 'API Fallback: /videos tab, sorted by oldest first', - 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', - 'info_dict': { - 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', - 'title': 'Cody\'sLab - Videos', - 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', - 'channel': 'Cody\'sLab', - 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', - 'tags': [], - 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', - 'channel_follower_count': int, - }, - 'playlist_mincount': 650, - 'params': { - 'skip_download': True, - 'extractor_args': {'youtubetab': {'skip': ['webpage']}}, - }, - 'skip': 'Query for sorting no longer works', - }, { - 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', - 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', - 'info_dict': { - 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', - 'title': 'Uploads from Royalty Free Music - Topic', - 'modified_date': r're:\d{8}', - 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', - 'description': '', - 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', - 'tags': [], - 'channel': 'Royalty Free Music - Topic', - 'view_count': int, - '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', - 'only_matching': True, - }, { - 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")', - 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', - 'info_dict': { - 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', - 'modified_date': '20220407', - 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', - 'tags': [], - '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/@pukkandan', - 'uploader_id': '@pukkandan', - 'uploader': 'pukkandan', - }, - 'playlist_mincount': 2, - }, { - 'note': 'translated tab name', - 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists', - 'info_dict': { - 'id': 'UCiu-3thuViMebBjw_5nWYrA', - 'tags': [], - 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', - 'description': 'test description', - 'title': 'cole-dlp-test-acc - 再生リスト', - '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']}}}, - 'expected_warnings': ['Preferring "ja"'], - }, { - # XXX: this should really check flat playlist entries, but the test suite doesn't support that - 'note': 'preferred lang set with playlist with translated video titles', - 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0', - 'info_dict': { - 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0', - 'tags': [], - 'view_count': int, - 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', - 'channel': 'cole-dlp-test-acc', - 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', - 'description': 'test', - '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']}}}, - 'expected_warnings': ['Preferring "ja"'], - }, { - # shorts audio pivot for 2GtVksBMYFM. - 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==', - 'info_dict': { - 'id': 'sfv_audio_pivot', - 'title': 'sfv_audio_pivot', - 'tags': [], - }, - 'playlist_mincount': 50, - - }, { - # Channel with a real live tab (not to be mistaken with streams tab) - # Do not treat like it should redirect to live stream - 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live', - 'info_dict': { - 'id': 'UCEH7P7kyJIkS_gJf93VYbmg', - 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live', - 'tags': [], - }, - 'playlist_mincount': 20, - }, { - # Tab name is not the same as tab id - 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay', - 'info_dict': { - 'id': 'UCQvWX73GQygcwXOTSf_VDVg', - 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play', - 'tags': [], - }, - 'playlist_mincount': 8, - }, { - # Home tab id is literally home. Not to get mistaken with featured - 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home', - 'info_dict': { - 'id': 'UCQvWX73GQygcwXOTSf_VDVg', - 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home', - 'tags': [], - }, - 'playlist_mincount': 8, - }, { - # Should get three playlists for videos, shorts and streams tabs - 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', - 'info_dict': { - 'id': 'UCK9V2B22uJYu3N7eR_BT9QA', - 'title': 'Polka Ch. 尾丸ポルカ', - 'channel_follower_count': int, - 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA', - 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', - 'description': 'md5:49809d8bf9da539bc48ed5d1f83c33f2', - 'channel': 'Polka Ch. 尾丸ポルカ', - 'tags': 'count:35', - 'uploader_url': 'https://www.youtube.com/@OmaruPolka', - 'uploader': 'Polka Ch. 尾丸ポルカ', - 'uploader_id': '@OmaruPolka', - 'channel_is_verified': True, - }, - '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:10', - 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A', - 'description': 'md5:5e82545b3a041345927a92d0585df247', - 'channel_follower_count': int, - 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A', - 'channel': 'Not Just Bikes', - 'uploader_url': 'https://www.youtube.com/@NotJustBikes', - 'uploader': 'Not Just Bikes', - 'uploader_id': '@NotJustBikes', - 'channel_is_verified': True, - }, - 'playlist_mincount': 10, - }, { - # Streams tab - 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams', - 'info_dict': { - 'id': 'UC3eYAvjCVwNHgkaGbXX3sig', - 'title': '中村悠一 - Live', - 'tags': 'count:7', - 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig', - 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig', - 'channel': '中村悠一', - 'channel_follower_count': int, - 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300', - 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura', - 'uploader_id': '@Yuichi-Nakamura', - 'uploader': '中村悠一', - }, - 'playlist_mincount': 60, - }, { - # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail. - # See test_youtube_lists - 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA', - 'only_matching': True, - }, { - # No uploads and no UCID given. Should fail with no uploads error - # See test_youtube_lists - 'url': 'https://www.youtube.com/news', - 'only_matching': True, - }, { - # No videos tab but has a shorts tab - 'url': 'https://www.youtube.com/c/TKFShorts', - 'info_dict': { - 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg', - 'title': 'Shorts Break - Shorts', - 'tags': 'count:48', - 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg', - 'channel': 'Shorts Break', - 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499', - 'channel_follower_count': int, - '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, - }, { - # Trending Now Tab. tab id is empty - 'url': 'https://www.youtube.com/feed/trending', - 'info_dict': { - 'id': 'trending', - 'title': 'trending - Now', - 'tags': [], - }, - 'playlist_mincount': 30, - }, { - # Trending Gaming Tab. tab id is empty - 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D', - 'info_dict': { - 'id': 'trending', - 'title': 'trending - Gaming', - 'tags': [], - }, - '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', - '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', - }, - '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', - 'title': 'SHORT short', - 'view_count': int, - 'thumbnails': list, - }, - }], - 'params': {'extract_flat': True}, - }, { - # Live video status should be extracted - 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live', - 'info_dict': { - 'id': 'UCQvWX73GQygcwXOTSf_VDVg', - 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO: should be Minecraft - Live or Minecraft - Topic - Live - 'tags': [], - }, - 'playlist': [{ - 'info_dict': { - '_type': 'url', - 'ie_key': 'Youtube', - 'url': 'startswith:https://www.youtube.com/watch?v=', - 'id': str, - 'title': str, - 'live_status': 'is_live', - 'channel_id': str, - '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'}, - 'playlist_mincount': 1, - }, { - # Channel renderer metadata. Contains number of videos on the channel - 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels', - 'info_dict': { - 'id': 'UCiu-3thuViMebBjw_5nWYrA', - 'title': 'cole-dlp-test-acc - Channels', - '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', - }, - 'playlist': [{ - 'info_dict': { - '_type': 'url', - 'ie_key': 'YoutubeTab', - 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', - 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw', - 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw', - 'title': 'PewDiePie', - 'channel': 'PewDiePie', - 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', - 'thumbnails': list, - 'channel_follower_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}, - }, { - 'url': 'https://www.youtube.com/@3blue1brown/about', - 'info_dict': { - 'id': '@3blue1brown', - 'tags': ['Mathematics'], - 'title': '3Blue1Brown', - 'channel_follower_count': int, - 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', - 'channel': '3Blue1Brown', - 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', - 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', - 'uploader_url': 'https://www.youtube.com/@3blue1brown', - 'uploader_id': '@3blue1brown', - 'uploader': '3Blue1Brown', - 'channel_is_verified': True, - }, - 'playlist_count': 0, - }, { - # Podcasts tab, with rich entry lockupViewModel - '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% Invisible - Podcasts', - 'uploader': '99% Invisible', - 'channel_follower_count': int, - 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw', - 'tags': [], - 'channel': '99% Invisible', - 'uploader_id': '@99percentinvisiblepodcast', - }, - 'playlist_count': 5, - }, { - # 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:12', - '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': r're:\d{8}', - 'title': 'Uploads from Bangy Shorts', - }, - 'playlist_mincount': 100, - 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], - }, { - 'note': 'Tags containing spaces', - 'url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ', - 'playlist_count': 3, - 'info_dict': { - 'id': 'UC7_YxT-KID8kRbqZo7MyscQ', - 'channel': 'Markiplier', - 'channel_id': 'UC7_YxT-KID8kRbqZo7MyscQ', - 'title': 'Markiplier', - 'channel_follower_count': int, - 'description': 'md5:0c010910558658824402809750dc5d97', - 'uploader_id': '@markiplier', - 'uploader_url': 'https://www.youtube.com/@markiplier', - 'uploader': 'Markiplier', - 'channel_url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ', - 'channel_is_verified': True, - 'tags': ['markiplier', 'comedy', 'gaming', 'funny videos', 'funny moments', - 'sketch comedy', 'laughing', 'lets play', 'challenge videos', 'hilarious', - 'challenges', 'sketches', 'scary games', 'funny games', 'rage games', - 'mark fischbach'], - }, - }] - - @classmethod - def suitable(cls, url): - return False if YoutubeIE.suitable(url) else super().suitable(url) - - _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$') - - def _get_url_mobj(self, url): - mobj = self._URL_RE.match(url).groupdict() - mobj.update((k, '') for k, v in mobj.items() if v is None) - return mobj - - def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'): - tab_name = (tab.get('title') or '').lower() - tab_url = urljoin(base_url, traverse_obj( - tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url'))) - - tab_id = ((tab_url and self._get_url_mobj(tab_url)['tab'][1:]) - or traverse_obj(tab, 'tabIdentifier', expected_type=str)) - if tab_id: - return { - 'TAB_ID_SPONSORSHIPS': 'membership', - }.get(tab_id, tab_id), tab_name - - # Fallback to tab name if we cannot get the tab id. - # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel - # Note that in the case of translated tab name this may result in an empty string, which we don't want. - if tab_name: - self.write_debug(f'Falling back to selected tab name: {tab_name}') - return { - 'home': 'featured', - 'live': 'streams', - }.get(tab_name, tab_name), tab_name - - def _has_tab(self, tabs, tab_id): - return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs) - - def _empty_playlist(self, item_id, data): - return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data)) - - @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data - def _real_extract(self, url, smuggled_data): - item_id = self._match_id(url) - url = urllib.parse.urlunparse( - urllib.parse.urlparse(url)._replace(netloc='www.youtube.com')) - compat_opts = self.get_param('compat_opts', []) - - mobj = self._get_url_mobj(url) - pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel'] - if is_channel and smuggled_data.get('is_music_url'): - if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist - return self.url_result( - f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:]) - elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist - mdata = self._extract_tab_endpoint( - f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music') - murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), - get_all=False, expected_type=str) - if not murl: - raise ExtractorError('Failed to resolve album to playlist') - return self.url_result(murl, YoutubeTabIE) - elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/ - return self.url_result( - f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id) - - original_tab_id, display_id = tab[1:], f'{item_id}{tab}' - if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: - url = f'{pre}/videos{post}' - if smuggled_data.get('is_music_url'): - self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}') - - # Handle both video/playlist URLs - qs = parse_qs(url) - video_id, playlist_id = (traverse_obj(qs, (key, 0)) for key in ('v', 'list')) - if not video_id and mobj['not_channel'].startswith('watch'): - if not playlist_id: - # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable - raise ExtractorError('A video URL was given without video ID', expected=True) - # Common mistake: https://www.youtube.com/watch?list=playlist_id - self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}') - return self.url_result( - f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id) - - if not self._yes_playlist(playlist_id, video_id): - return self.url_result( - f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id) - - data, ytcfg = self._extract_data(url, display_id) - - # YouTube may provide a non-standard redirect to the regional channel - # See: https://github.com/yt-dlp/yt-dlp/issues/2694 - # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects - redirect_url = traverse_obj( - data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False) - if redirect_url and 'no-youtube-channel-redirect' not in compat_opts: - redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post)) - self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}') - return self.url_result(redirect_url, YoutubeTabIE) - - tabs, extra_tabs = self._extract_tab_renderers(data), [] - if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts: - selected_tab = self._extract_selected_tab(tabs) - selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated - self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}') - - # /about is no longer a tab - if original_tab_id == 'about': - return self._empty_playlist(item_id, data) - - if not original_tab_id and selected_tab_name: - self.to_screen('Downloading all uploads of the channel. ' - 'To download only the videos in a specific tab, pass the tab\'s URL') - if self._has_tab(tabs, 'streams'): - extra_tabs.append(''.join((pre, '/streams', post))) - if self._has_tab(tabs, 'shorts'): - extra_tabs.append(''.join((pre, '/shorts', post))) - # XXX: Members-only tab should also be extracted - - if not extra_tabs and selected_tab_id != 'videos': - # Channel does not have streams, shorts or videos tabs - if item_id[:2] != 'UC': - return self._empty_playlist(item_id, data) - - # Topic channels don't have /videos. Use the equivalent playlist instead - pl_id = f'UU{item_id[2:]}' - pl_url = f'https://www.youtube.com/playlist?list={pl_id}' - try: - data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True) - except ExtractorError: - return self._empty_playlist(item_id, data) - else: - item_id, url = pl_id, pl_url - self.to_screen( - f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead') - - elif extra_tabs and selected_tab_id != 'videos': - # When there are shorts/live tabs but not videos tab - url, data = f'{pre}{post}', None - - elif (original_tab_id or 'videos') != selected_tab_id: - if original_tab_id == 'live': - # Live tab should have redirected to the video - # Except in the case the channel has an actual live tab - # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live - raise UserNotLive(video_id=item_id) - elif selected_tab_name: - raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True) - - # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg - url = f'{pre}{post}' - - # YouTube sometimes provides a button to reload playlist with unavailable videos. - if 'no-youtube-unavailable-videos' not in compat_opts: - data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data - self._extract_and_report_alerts(data, only_once=True) - - tabs, entries = self._extract_tab_renderers(data), [] - if tabs: - entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)] - entries[0].update({ - 'extractor_key': YoutubeTabIE.ie_key(), - 'extractor': YoutubeTabIE.IE_NAME, - 'webpage_url': url, - }) - if self.get_param('playlist_items') == '0': - entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs) - else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result` - entries.extend(map(self._real_extract, extra_tabs)) - - if len(entries) == 1: - return entries[0] - elif entries: - metadata = self._extract_metadata_from_tabs(item_id, data) - uploads_url = 'the Uploads (UU) playlist URL' - if try_get(metadata, lambda x: x['channel_id'].startswith('UC')): - uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}' - self.to_screen( - 'Downloading as multiple playlists, separated by tabs. ' - f'To download as a single playlist instead, pass {uploads_url}') - return self.playlist_result(entries, item_id, **metadata) - - # Inline playlist - playlist = traverse_obj( - data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict) - if playlist: - return self._extract_from_playlist(item_id, url, data, playlist, ytcfg) - - video_id = traverse_obj( - data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id - if video_id: - if tab != '/live': # live tab is expected to redirect to video - self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}') - return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id) - - raise ExtractorError('Unable to recognize tab page') - - -class YoutubePlaylistIE(YoutubeBaseInfoExtractor): - IE_DESC = 'YouTube playlists' - _VALID_URL = r'''(?x)(?: - (?:https?://)? - (?:\w+\.)? - (?: - (?: - youtube(?:kids)?\.com| - {invidious} - ) - /.*?\?.*?\blist= - )? - (?P<id>{playlist_id}) - )'''.format( - playlist_id=YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, - invidious='|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), - ) - IE_NAME = 'youtube:playlist' - _TESTS = [{ - 'note': 'issue #673', - 'url': 'PLBB231211A4F62143', - 'info_dict': { - 'title': '[OLD]Team Fortress 2 (Class-based LP)', - 'id': 'PLBB231211A4F62143', - 'uploader': 'Wickman', - 'uploader_id': '@WickmanVT', - 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', - 'view_count': int, - '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/channel/UCKSpbfbl5kRQpTdL7kMc-1Q', - 'availability': 'public', - }, - 'playlist_mincount': 29, - }, { - 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', - 'info_dict': { - 'title': 'YDL_safe_search', - 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', - }, - 'playlist_count': 2, - 'skip': 'This playlist is private', - }, { - 'note': 'embedded', - 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', - 'playlist_count': 4, - 'info_dict': { - 'title': 'JODA15', - 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', - 'uploader': 'milan', - 'uploader_id': '@milan5503', - 'description': '', - 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', - 'tags': [], - 'modified_date': '20140919', - 'view_count': int, - 'channel': 'milan', - 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', - 'uploader_url': 'https://www.youtube.com/@milan5503', - 'availability': 'public', - }, - 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden', 'Retrying', 'Giving up'], - }, { - 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', - 'playlist_mincount': 455, - 'info_dict': { - 'title': '2018 Chinese New Singles (11/6 updated)', - 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', - 'uploader': 'LBK', - 'uploader_id': '@music_king', - 'description': 'md5:da521864744d60a198e3a88af4db0d9d', - 'channel': 'LBK', - 'view_count': int, - 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA', - 'tags': [], - 'uploader_url': 'https://www.youtube.com/@music_king', - 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', - 'modified_date': r're:\d{8}', - 'availability': 'public', - }, - 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], - }, { - 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', - 'only_matching': True, - }, { - # music album playlist - 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', - 'only_matching': True, - }] - - @classmethod - def suitable(cls, url): - if YoutubeTabIE.suitable(url): - return False - from ..utils import parse_qs - qs = parse_qs(url) - if qs.get('v', [None])[0]: - return False - return super().suitable(url) - - def _real_extract(self, url): - playlist_id = self._match_id(url) - is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) - url = update_url_query( - 'https://www.youtube.com/playlist', - parse_qs(url) or {'list': playlist_id}) - if is_music_url: - url = smuggle_url(url, {'is_music_url': True}) - return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) - - -class YoutubeYtBeIE(YoutubeBaseInfoExtractor): - IE_DESC = 'youtu.be' - _VALID_URL = rf'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{{11}})/*?.*?\blist=(?P<playlist_id>{YoutubeBaseInfoExtractor._PLAYLIST_ID_RE})' - _TESTS = [{ - 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', - 'info_dict': { - 'id': 'yeWKywCrFtk', - '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/@backuspagemuseum', - 'upload_date': '20161008', - 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', - 'categories': ['Nonprofits & Activism'], - 'tags': list, - 'like_count': int, - 'age_limit': 0, - 'playable_in_embed': True, - 'thumbnail': r're:^https?://.*\.webp', - 'channel': 'Backus-Page House Museum', - 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', - 'live_status': 'not_live', - 'view_count': int, - 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw', - 'availability': 'public', - 'duration': 59, - 'comment_count': int, - 'channel_follower_count': int, - }, - 'params': { - 'noplaylist': True, - 'skip_download': True, - }, - }, { - 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - video_id = mobj.group('id') - playlist_id = mobj.group('playlist_id') - return self.url_result( - update_url_query('https://www.youtube.com/watch', { - 'v': video_id, - 'list': playlist_id, - 'feature': 'youtu.be', - }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) - - -class YoutubeLivestreamEmbedIE(YoutubeBaseInfoExtractor): - IE_DESC = 'YouTube livestream embeds' - _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)' - _TESTS = [{ - 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA', - 'only_matching': True, - }] - - def _real_extract(self, url): - channel_id = self._match_id(url) - return self.url_result( - f'https://www.youtube.com/channel/{channel_id}/live', - ie=YoutubeTabIE.ie_key(), video_id=channel_id) - - -class YoutubeYtUserIE(YoutubeBaseInfoExtractor): - IE_DESC = 'YouTube user videos; "ytuser:" prefix' - IE_NAME = 'youtube:user' - _VALID_URL = r'ytuser:(?P<id>.+)' - _TESTS = [{ - 'url': 'ytuser:phihag', - 'only_matching': True, - }] - - def _real_extract(self, url): - user_id = self._match_id(url) - return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id) - - -class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): - IE_NAME = 'youtube:favorites' - IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)' - _VALID_URL = r':ytfav(?:ou?rite)?s?' - _LOGIN_REQUIRED = True - _TESTS = [{ - 'url': ':ytfav', - 'only_matching': True, - }, { - 'url': ':ytfavorites', - 'only_matching': True, - }] - - def _real_extract(self, url): - return self.url_result( - 'https://www.youtube.com/playlist?list=LL', - ie=YoutubeTabIE.ie_key()) - - -class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor): - IE_NAME = 'youtube:notif' - IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)' - _VALID_URL = r':ytnotif(?:ication)?s?' - _LOGIN_REQUIRED = True - _TESTS = [{ - 'url': ':ytnotif', - 'only_matching': True, - }, { - 'url': ':ytnotifications', - 'only_matching': True, - }] - - def _extract_notification_menu(self, response, continuation_list): - notification_list = traverse_obj( - response, - ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'), - ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'), - expected_type=list) or [] - continuation_list[0] = None - for item in notification_list: - entry = self._extract_notification_renderer(item.get('notificationRenderer')) - if entry: - yield entry - continuation = item.get('continuationItemRenderer') - if continuation: - continuation_list[0] = continuation - - def _extract_notification_renderer(self, notification): - video_id = traverse_obj( - notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) - url = f'https://www.youtube.com/watch?v={video_id}' - channel_id = None - if not video_id: - browse_ep = traverse_obj( - notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict) - 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) - if not channel_id or not post_id: - return - # The direct /post url redirects to this in the browser - url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}' - - channel = traverse_obj( - notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'), - expected_type=str) - notification_title = self._get_text(notification, 'shortMessage') - if notification_title: - notification_title = notification_title.replace('\xad', '') # remove soft hyphens - # TODO: handle recommended videos - title = self._search_regex( - rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title, - 'video title', default=None) - timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText')) - if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE) - else None) - return { - '_type': 'url', - 'url': url, - 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(), - 'video_id': video_id, - 'title': title, - 'channel_id': channel_id, - 'channel': channel, - 'uploader': channel, - 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'), - 'timestamp': timestamp, - } - - def _notification_menu_entries(self, ytcfg): - continuation_list = [None] - response = None - for page in itertools.count(1): - ctoken = traverse_obj( - continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str) - response = self._extract_response( - item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg, - ep='notification/get_notification_menu', check_get_keys='actions', - headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))) - yield from self._extract_notification_menu(response, continuation_list) - if not continuation_list[0]: - break - - def _real_extract(self, url): - display_id = 'notifications' - ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {} - self._report_playlist_authcheck(ytcfg) - return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id) - - -class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): - IE_DESC = 'YouTube search' - IE_NAME = 'youtube:search' - _SEARCH_KEY = 'ytsearch' - _SEARCH_PARAMS = 'EgIQAfABAQ==' # Videos only - _TESTS = [{ - 'url': 'ytsearch5:youtube-dl test video', - 'playlist_count': 5, - 'info_dict': { - 'id': 'youtube-dl test video', - 'title': 'youtube-dl test video', - }, - }, { - 'note': 'Suicide/self-harm search warning', - 'url': 'ytsearch1:i hate myself and i wanna die', - 'playlist_count': 1, - 'info_dict': { - 'id': 'i hate myself and i wanna die', - 'title': 'i hate myself and i wanna die', - }, - }] - - -class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): - IE_NAME = YoutubeSearchIE.IE_NAME + ':date' - _SEARCH_KEY = 'ytsearchdate' - IE_DESC = 'YouTube search, newest videos first' - _SEARCH_PARAMS = 'CAISAhAB8AEB' # Videos only, sorted by date - _TESTS = [{ - 'url': 'ytsearchdate5:youtube-dl test video', - 'playlist_count': 5, - 'info_dict': { - 'id': 'youtube-dl test video', - 'title': 'youtube-dl test video', - }, - }] - - -class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): - IE_DESC = 'YouTube search URLs with sorting and filter support' - IE_NAME = YoutubeSearchIE.IE_NAME + '_url' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' - _TESTS = [{ - 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', - 'playlist_mincount': 5, - 'info_dict': { - 'id': 'youtube-dl test video', - 'title': 'youtube-dl test video', - }, - }, { - 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D', - 'playlist_mincount': 5, - 'info_dict': { - 'id': 'python', - 'title': 'python', - }, - }, { - 'url': 'https://www.youtube.com/results?search_query=%23cats', - 'playlist_mincount': 1, - 'info_dict': { - 'id': '#cats', - 'title': '#cats', - # The test suite does not have support for nested playlists - # 'entries': [{ - # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats', - # 'title': '#cats', - # }], - }, - }, { - # Channel results - 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D', - 'info_dict': { - 'id': 'kurzgesagt', - 'title': 'kurzgesagt', - }, - 'playlist': [{ - 'info_dict': { - '_type': 'url', - 'id': 'UCsXVk37bltHxD1rDPwtNM8Q', - 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q', - 'ie_key': 'YoutubeTab', - 'channel': 'Kurzgesagt – In a Nutshell', - 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc', - 'title': 'Kurzgesagt – In a Nutshell', - 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q', - # 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, - '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'}, - 'playlist_mincount': 1, - }, { - 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', - 'only_matching': True, - }] - - def _real_extract(self, url): - qs = parse_qs(url) - query = (qs.get('search_query') or qs.get('q'))[0] - return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) - - -class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor): - IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs' - IE_NAME = 'youtube:music:search_url' - _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' - _TESTS = [{ - 'url': 'https://music.youtube.com/search?q=royalty+free+music', - 'playlist_count': 16, - 'info_dict': { - 'id': 'royalty free music', - 'title': 'royalty free music', - }, - }, { - 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D', - 'playlist_mincount': 30, - 'info_dict': { - 'id': 'royalty free music - songs', - 'title': 'royalty free music - songs', - }, - 'params': {'extract_flat': 'in_playlist'}, - }, { - 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists', - 'playlist_mincount': 30, - 'info_dict': { - 'id': 'royalty free music - community playlists', - 'title': 'royalty free music - community playlists', - }, - 'params': {'extract_flat': 'in_playlist'}, - }] - - _SECTIONS = { - 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==', - 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==', - 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF', - 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==', - 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==', - 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==', - } - - def _real_extract(self, url): - qs = parse_qs(url) - query = (qs.get('search_query') or qs.get('q'))[0] - params = qs.get('sp', (None,))[0] - if params: - section = next((k for k, v in self._SECTIONS.items() if v == params), params) - else: - section = urllib.parse.unquote_plus(([*url.split('#'), ''])[1]).lower() - params = self._SECTIONS.get(section) - if not params: - section = None - title = join_nonempty(query, section, delim=' - ') - return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title) - - -class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): - """ - Base class for feed extractors - Subclasses must re-define the _FEED_NAME property. - """ - _LOGIN_REQUIRED = True - _FEED_NAME = 'feeds' - - @classproperty - def IE_NAME(cls): - return f'youtube:{cls._FEED_NAME}' - - def _real_extract(self, url): - return self.url_result( - f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key()) - - -class YoutubeWatchLaterIE(YoutubeBaseInfoExtractor): - IE_NAME = 'youtube:watchlater' - IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)' - _VALID_URL = r':ytwatchlater' - _TESTS = [{ - 'url': ':ytwatchlater', - 'only_matching': True, - }] - - def _real_extract(self, url): - return self.url_result( - 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) - - -class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'YouTube recommended videos; ":ytrec" keyword' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' - _FEED_NAME = 'recommended' - _LOGIN_REQUIRED = False - _TESTS = [{ - 'url': ':ytrec', - 'only_matching': True, - }, { - 'url': ':ytrecommended', - 'only_matching': True, - }, { - 'url': 'https://youtube.com', - 'only_matching': True, - }] - - -class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)' - _VALID_URL = r':ytsub(?:scription)?s?' - _FEED_NAME = 'subscriptions' - _TESTS = [{ - 'url': ':ytsubs', - 'only_matching': True, - }, { - 'url': ':ytsubscriptions', - 'only_matching': True, - }] - - -class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)' - _VALID_URL = r':ythis(?:tory)?' - _FEED_NAME = 'history' - _TESTS = [{ - 'url': ':ythistory', - 'only_matching': True, - }] - - -class YoutubeShortsAudioPivotIE(YoutubeBaseInfoExtractor): - IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)' - IE_NAME = 'youtube:shorts:pivot:audio' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts' - _TESTS = [{ - 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts', - 'only_matching': True, - }] - - @staticmethod - def _generate_audio_pivot_params(video_id): - """ - Generates sfv_audio_pivot browse params for this video id - """ - pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3) - return urllib.parse.quote(base64.b64encode(pb_params).decode()) - - def _real_extract(self, url): - video_id = self._match_id(url) - return self.url_result( - f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}', - ie=YoutubeTabIE) - - -class YoutubeTruncatedURLIE(YoutubeBaseInfoExtractor): - IE_NAME = 'youtube:truncated_url' - IE_DESC = False # Do not list - _VALID_URL = r'''(?x) - (?:https?://)? - (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ - (?:watch\?(?: - feature=[a-z_]+| - annotation_id=annotation_[^&]+| - x-yt-cl=[0-9]+| - hl=[^&]*| - t=[0-9]+ - )? - | - attribution_link\?a=[^&]+ - ) - $ - ''' - - _TESTS = [{ - 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?feature=foo', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?hl=en-GB', - 'only_matching': True, - }, { - 'url': 'https://www.youtube.com/watch?t=2372', - 'only_matching': True, - }] - - def _real_extract(self, url): - raise ExtractorError( - 'Did you forget to quote the URL? Remember that & is a meta ' - 'character in most shells, so you want to put the URL in quotes, ' - 'like yt-dlp ' - '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' - ' or simply yt-dlp BaW_jenozKc .', - expected=True) - - -class YoutubeClipIE(YoutubeTabBaseInfoExtractor): - IE_NAME = 'youtube:clip' - _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)' - _TESTS = [{ - # FIXME: Other metadata should be extracted from the clip, not from the base video - 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ', - 'info_dict': { - 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ', - 'ext': 'mp4', - 'section_start': 29.0, - 'section_end': 39.7, - 'duration': 10.7, - 'age_limit': 0, - 'availability': 'public', - 'categories': ['Gaming'], - 'channel': 'Scott The Woz', - 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ', - 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ', - 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7', - 'like_count': int, - 'playable_in_embed': True, - 'tags': 'count:17', - 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp', - 'title': 'Mobile Games on Console - Scott The Woz', - 'upload_date': '20210920', - 'uploader': 'Scott The Woz', - 'uploader_id': '@ScottTheWoz', - 'uploader_url': 'https://www.youtube.com/@ScottTheWoz', - 'view_count': int, - 'live_status': 'not_live', - 'channel_follower_count': int, - 'chapters': 'count:20', - 'comment_count': int, - 'heatmap': 'count:100', - }, - }] - - def _real_extract(self, url): - clip_id = self._match_id(url) - _, data = self._extract_webpage(url, clip_id) - - video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId')) - if not video_id: - raise ExtractorError('Unable to find video ID') - - clip_data = traverse_obj(data, ( - 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer', - 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ..., - 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command', - 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False) - - return { - '_type': 'url_transparent', - 'url': f'https://www.youtube.com/watch?v={video_id}', - 'ie_key': YoutubeIE.ie_key(), - 'id': clip_id, - 'section_start': int(clip_data['startTimeMs']) / 1000, - 'section_end': int(clip_data['endTimeMs']) / 1000, - '_format_sort_fields': ( # https protocol is prioritized for ffmpeg compatibility - 'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang'), - } - - -class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor): - IE_NAME = 'youtube:consent' - IE_DESC = False # Do not list - _VALID_URL = r'https?://consent\.youtube\.com/m\?' - _TESTS = [{ - 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1', - 'info_dict': { - 'id': 'qVv6vCqciTM', - 'ext': 'mp4', - 'age_limit': 0, - 'uploader_id': '@sana_natori', - 'comment_count': int, - 'chapters': 'count:13', - 'upload_date': '20221223', - 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg', - 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA', - 'uploader_url': 'https://www.youtube.com/@sana_natori', - 'like_count': int, - 'release_date': '20221223', - 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'], - 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】', - 'view_count': int, - 'playable_in_embed': True, - 'duration': 4438, - 'availability': 'public', - 'channel_follower_count': int, - 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA', - 'categories': ['Entertainment'], - 'live_status': 'was_live', - 'release_timestamp': 1671793345, - 'channel': 'さなちゃんねる', - 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d', - 'uploader': 'さなちゃんねる', - 'channel_is_verified': True, - 'heatmap': 'count:100', - }, - 'add_ie': ['Youtube'], - 'params': {'skip_download': 'Youtube'}, - }] - - def _real_extract(self, url): - redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1]) - if not redirect_url: - raise ExtractorError('Invalid cookie consent redirect URL', expected=True) - return self.url_result(redirect_url) - - -class YoutubeTruncatedIDIE(YoutubeBaseInfoExtractor): - IE_NAME = 'youtube:truncated_id' - IE_DESC = False # Do not list - _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' - - _TESTS = [{ - 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - raise ExtractorError( - f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.', - expected=True) |