]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/vimeo] Fix `playerConfig` extraction (#6203)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
a4894d3e 3import collections
109dd3b2 4import copy
fe93e2c4 5import datetime
c26f9b99 6import enum
a5c56234 7import hashlib
0ca96d48 8import itertools
c5e8d7af 9import json
720c3099 10import math
c4417ddb 11import os.path
d77ab8e2 12import random
c5e8d7af 13import re
46383212 14import sys
f8271158 15import threading
8a784c74 16import time
e0df6211 17import traceback
14f25df2 18import urllib.error
ac668111 19import urllib.parse
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
25836db6 22from .openload import PhantomJSwrapper
14f25df2 23from ..compat import functools
545cc85d 24from ..jsinterp import JSInterpreter
4bb4a188 25from ..utils import (
f8271158 26 NO_DEFAULT,
27 ExtractorError,
4d37720a 28 LazyList,
693f0600 29 UserNotLive,
720c3099 30 bug_reports_message,
82d02080 31 classproperty,
c5e8d7af 32 clean_html,
d92f5d5a 33 datetime_from_str,
11f9be09 34 dict_get,
7a32c70d 35 filter_dict,
2d30521a 36 float_or_none,
11f9be09 37 format_field,
ff91cf74 38 get_first,
dd27fd17 39 int_or_none,
641ad5d8 40 is_html,
34921b43 41 join_nonempty,
48416bc4 42 js_to_json,
94278f72 43 mimetype2ext,
9c0d7f49 44 network_exceptions,
11f9be09 45 orderedSet,
6310acf5 46 parse_codecs,
49bd8c66 47 parse_count,
7c80519c 48 parse_duration,
7ea65411 49 parse_iso8601,
4dfbf869 50 parse_qs,
dca3ff4a 51 qualities,
3995d37d 52 remove_start,
cf7e015f 53 smuggle_url,
dbdaaa23 54 str_or_none,
c93d53f5 55 str_to_int,
f3aa3c3f 56 strftime_or_none,
7c365c21 57 traverse_obj,
556dbe7f 58 try_get,
c5e8d7af
PH
59 unescapeHTML,
60 unified_strdate,
f0d785d3 61 unified_timestamp,
cf7e015f 62 unsmuggle_url,
8bdd16b4 63 update_url_query,
21c340b8 64 url_or_none,
fe93e2c4 65 urljoin,
7c365c21 66 variadic,
c5e8d7af
PH
67)
68
962ffcf8 69# any clients starting with _ cannot be explicitly requested by the user
000c15a4 70INNERTUBE_CLIENTS = {
71 'web': {
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
74 'client': {
75 'clientName': 'WEB',
a0c830f4 76 'clientVersion': '2.20220801.00.00',
000c15a4 77 }
78 },
79 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
80 },
81 'web_embedded': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 86 'clientVersion': '1.20220731.00.00',
000c15a4 87 },
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
90 },
91 'web_music': {
92 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
93 'INNERTUBE_HOST': 'music.youtube.com',
94 'INNERTUBE_CONTEXT': {
95 'client': {
96 'clientName': 'WEB_REMIX',
a0c830f4 97 'clientVersion': '1.20220727.01.00',
000c15a4 98 }
99 },
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
101 },
e7e94f2a 102 'web_creator': {
18c7683d 103 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_CREATOR',
a0c830f4 107 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
111 },
000c15a4 112 'android': {
18c7683d 113 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'ANDROID',
50ac0e54 117 'clientVersion': '17.31.35',
118 'androidSdkVersion': 30,
119 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 120 }
121 },
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 123 'REQUIRE_JS_PLAYER': False
000c15a4 124 },
125 'android_embedded': {
18c7683d 126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 127 'INNERTUBE_CONTEXT': {
128 'client': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 130 'clientVersion': '17.31.35',
131 'androidSdkVersion': 30,
132 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 133 },
134 },
b6de707d 135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
000c15a4 137 },
138 'android_music': {
18c7683d 139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 140 'INNERTUBE_CONTEXT': {
141 'client': {
142 'clientName': 'ANDROID_MUSIC',
a0c830f4 143 'clientVersion': '5.16.51',
50ac0e54 144 'androidSdkVersion': 30,
145 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 146 }
147 },
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 149 'REQUIRE_JS_PLAYER': False
000c15a4 150 },
e7e94f2a 151 'android_creator': {
18c7683d 152 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
153 'INNERTUBE_CONTEXT': {
154 'client': {
155 'clientName': 'ANDROID_CREATOR',
50ac0e54 156 'clientVersion': '22.30.100',
157 'androidSdkVersion': 30,
158 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
159 },
160 },
b6de707d 161 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
162 'REQUIRE_JS_PLAYER': False
e7e94f2a 163 },
18c7683d 164 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
165 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 166 'ios': {
18c7683d 167 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS',
224b5a35 171 'clientVersion': '17.33.2',
18c7683d 172 'deviceModel': 'iPhone14,3',
224b5a35 173 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 174 }
175 },
b6de707d 176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
000c15a4 178 },
179 'ios_embedded': {
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 183 'clientVersion': '17.33.2',
18c7683d 184 'deviceModel': 'iPhone14,3',
224b5a35 185 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
191 'ios_music': {
18c7683d 192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
224b5a35
SF
196 'clientVersion': '5.21',
197 'deviceModel': 'iPhone14,3',
198 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 199 },
200 },
b6de707d 201 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
202 'REQUIRE_JS_PLAYER': False
000c15a4 203 },
e7e94f2a
D
204 'ios_creator': {
205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'IOS_CREATOR',
224b5a35
SF
208 'clientVersion': '22.33.101',
209 'deviceModel': 'iPhone14,3',
210 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
211 },
212 },
b6de707d 213 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
214 'REQUIRE_JS_PLAYER': False
e7e94f2a 215 },
3619f78d 216 # mweb has 'ultralow' formats
217 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 218 'mweb': {
18c7683d 219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 220 'INNERTUBE_CONTEXT': {
221 'client': {
222 'clientName': 'MWEB',
a0c830f4 223 'clientVersion': '2.20220801.00.00',
000c15a4 224 }
225 },
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
227 },
228 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
229 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
230 'tv_embedded': {
231 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
232 'INNERTUBE_CONTEXT': {
233 'client': {
234 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
235 'clientVersion': '2.0',
236 },
237 },
238 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
239 },
000c15a4 240}
241
242
e7870111
D
243def _split_innertube_client(client_name):
244 variant, *base = client_name.rsplit('.', 1)
245 if base:
246 return variant, base[0], variant
247 base, *variant = client_name.split('_', 1)
248 return client_name, base, variant[0] if variant else None
249
250
000c15a4 251def build_innertube_clients():
2e4cacd0 252 THIRD_PARTY = {
e7870111 253 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 254 }
e7870111 255 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 256 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 257
258 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 259 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 260 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 261 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 262 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 263
e7870111 264 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 265 ytcfg['priority'] = 10 * priority(base_client)
266
e48b3875 267 if not variant:
e7870111
D
268 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
269 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
270 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
271 embedscreen['priority'] -= 3
272 elif variant == 'embedded':
e48b3875 273 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 274 ytcfg['priority'] -= 2
e48b3875 275 else:
000c15a4 276 ytcfg['priority'] -= 3
277
278
279build_innertube_clients()
280
281
c26f9b99 282class BadgeType(enum.Enum):
283 AVAILABILITY_UNLISTED = enum.auto()
284 AVAILABILITY_PRIVATE = enum.auto()
285 AVAILABILITY_PUBLIC = enum.auto()
286 AVAILABILITY_PREMIUM = enum.auto()
287 AVAILABILITY_SUBSCRIPTION = enum.auto()
288 LIVE_NOW = enum.auto()
289
290
de7f3446 291class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 292 """Provide base functions for Youtube extractors"""
e00eb564 293
3462ffa8 294 _RESERVED_NAMES = (
08e29b9f 295 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
182bda88 296 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 297 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 298 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 299
3619f78d 300 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
301
52efa4b3 302 # _NETRC_MACHINE = 'youtube'
3619f78d 303
b2e8bc1b
JMF
304 # If True it will raise an error if no login info is provided
305 _LOGIN_REQUIRED = False
306
d9190e44
RH
307 _INVIDIOUS_SITES = (
308 # invidious-redirect websites
309 r'(?:www\.)?redirect\.invidious\.io',
310 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 311 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
312 r'(?:www\.)?invidious\.pussthecat\.org',
313 r'(?:www\.)?invidious\.zee\.li',
314 r'(?:www\.)?invidious\.ethibox\.fr',
315 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
316 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
317 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
318 # youtube-dl invidious instances list
319 r'(?:(?:www|no)\.)?invidiou\.sh',
320 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
321 r'(?:www\.)?invidious\.kabi\.tk',
322 r'(?:www\.)?invidious\.mastodon\.host',
323 r'(?:www\.)?invidious\.zapashcanon\.fr',
324 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
325 r'(?:www\.)?invidious\.tinfoil-hat\.net',
326 r'(?:www\.)?invidious\.himiko\.cloud',
327 r'(?:www\.)?invidious\.reallyancient\.tech',
328 r'(?:www\.)?invidious\.tube',
329 r'(?:www\.)?invidiou\.site',
330 r'(?:www\.)?invidious\.site',
331 r'(?:www\.)?invidious\.xyz',
332 r'(?:www\.)?invidious\.nixnet\.xyz',
333 r'(?:www\.)?invidious\.048596\.xyz',
334 r'(?:www\.)?invidious\.drycat\.fr',
335 r'(?:www\.)?inv\.skyn3t\.in',
336 r'(?:www\.)?tube\.poal\.co',
337 r'(?:www\.)?tube\.connect\.cafe',
338 r'(?:www\.)?vid\.wxzm\.sx',
339 r'(?:www\.)?vid\.mint\.lgbt',
340 r'(?:www\.)?vid\.puffyan\.us',
341 r'(?:www\.)?yewtu\.be',
342 r'(?:www\.)?yt\.elukerio\.org',
343 r'(?:www\.)?yt\.lelux\.fi',
344 r'(?:www\.)?invidious\.ggc-project\.de',
345 r'(?:www\.)?yt\.maisputain\.ovh',
346 r'(?:www\.)?ytprivate\.com',
347 r'(?:www\.)?invidious\.13ad\.de',
348 r'(?:www\.)?invidious\.toot\.koeln',
349 r'(?:www\.)?invidious\.fdn\.fr',
350 r'(?:www\.)?watch\.nettohikari\.com',
351 r'(?:www\.)?invidious\.namazso\.eu',
352 r'(?:www\.)?invidious\.silkky\.cloud',
353 r'(?:www\.)?invidious\.exonip\.de',
354 r'(?:www\.)?invidious\.riverside\.rocks',
355 r'(?:www\.)?invidious\.blamefran\.net',
356 r'(?:www\.)?invidious\.moomoo\.de',
357 r'(?:www\.)?ytb\.trom\.tf',
358 r'(?:www\.)?yt\.cyberhost\.uk',
359 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
360 r'(?:www\.)?qklhadlycap4cnod\.onion',
361 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
362 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
363 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
364 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
365 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
366 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
367 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
368 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
369 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
370 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
371 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
372 r'(?:www\.)?piped\.kavin\.rocks',
d1c4f6d4 373 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 374 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 375 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
376 r'(?:www\.)?watch\.whatever\.social',
377 r'(?:www\.)?piped\.garudalinux\.org',
378 r'(?:www\.)?piped\.rivo\.lol',
379 r'(?:www\.)?piped-libre\.kavin\.rocks',
380 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 381 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
382 r'(?:www\.)?il\.ax',
383 r'(?:www\.)?piped\.esmailelbob\.xyz',
384 r'(?:www\.)?piped\.projectsegfau\.lt',
385 r'(?:www\.)?piped\.privacydev\.net',
386 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
387 r'(?:www\.)?piped\.smnz\.de',
388 r'(?:www\.)?piped\.adminforge\.de',
389 r'(?:www\.)?watch\.whatevertinfoil\.de',
390 r'(?:www\.)?piped\.qdi\.fi',
bc87dac7
B
391 r'(?:www\.)?piped\.video',
392 r'(?:www\.)?piped\.aeong\.one',
d9190e44
RH
393 )
394
c26f9b99 395 # extracted from account/account_menu ep
396 # XXX: These are the supported YouTube UI and API languages,
397 # which is slightly different from languages supported for translation in YouTube studio
398 _SUPPORTED_LANG_CODES = [
399 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
400 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
401 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
402 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
403 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
404 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
405 ]
406
a057779d 407 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
408
c26f9b99 409 @functools.cached_property
410 def _preferred_lang(self):
411 """
412 Returns a language code supported by YouTube for the user preferred language.
413 Returns None if no preferred language set.
414 """
415 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
416 if not preferred_lang:
417 return
418 if preferred_lang not in self._SUPPORTED_LANG_CODES:
419 raise ExtractorError(
420 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
421 expected=True)
422 elif preferred_lang != 'en':
423 self.report_warning(
424 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
425 return preferred_lang
426
cce889b9 427 def _initialize_consent(self):
428 cookies = self._get_cookies('https://www.youtube.com/')
429 if cookies.get('__Secure-3PSID'):
430 return
431 consent_id = None
432 consent = cookies.get('CONSENT')
433 if consent:
434 if 'YES' in consent.value:
435 return
436 consent_id = self._search_regex(
437 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
438 if not consent_id:
439 consent_id = random.randint(100, 999)
440 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 441
f3aa3c3f 442 def _initialize_pref(self):
443 cookies = self._get_cookies('https://www.youtube.com/')
444 pref_cookie = cookies.get('PREF')
445 pref = {}
446 if pref_cookie:
447 try:
14f25df2 448 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 449 except ValueError:
450 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 451 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 452 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 453
b2e8bc1b 454 def _real_initialize(self):
f3aa3c3f 455 self._initialize_pref()
cce889b9 456 self._initialize_consent()
a25bca9f 457 self._check_login_required()
458
459 def _check_login_required(self):
24146491 460 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 461 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 462
b7c47b74 463 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
464 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 465
000c15a4 466 def _get_default_ytcfg(self, client='web'):
467 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 468
000c15a4 469 def _get_innertube_host(self, client='web'):
470 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 471
000c15a4 472 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 473 # try_get but with fallback to default ytcfg client values when present
474 _func = lambda y: try_get(y, getter, expected_type)
475 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
476
000c15a4 477 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 478 return self._ytcfg_get_safe(
479 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 480 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 481
000c15a4 482 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 483 return self._ytcfg_get_safe(
484 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 485 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 486
2ae778b8 487 def _select_api_hostname(self, req_api_hostname, default_client=None):
488 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
489 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
490
000c15a4 491 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 492 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 493
000c15a4 494 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 495 context = get_first(
496 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 497 # Enforce language and tz for extraction
498 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 499 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 500 return context
501
cf87314d 502 _SAPISID = None
503
109dd3b2 504 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 505 time_now = round(time.time())
cf87314d 506 if self._SAPISID is None:
507 yt_cookies = self._get_cookies('https://www.youtube.com')
508 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
509 # See: https://github.com/yt-dlp/yt-dlp/issues/393
510 sapisid_cookie = dict_get(
511 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
512 if sapisid_cookie and sapisid_cookie.value:
513 self._SAPISID = sapisid_cookie.value
514 self.write_debug('Extracted SAPISID cookie')
515 # SAPISID cookie is required if not already present
516 if not yt_cookies.get('SAPISID'):
517 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
518 self._set_cookie(
519 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
520 else:
521 self._SAPISID = False
522 if not self._SAPISID:
523 return None
1974e99f 524 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
525 sapisidhash = hashlib.sha1(
86e5f3ed 526 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 527 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
528
529 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 530 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 531 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 532
109dd3b2 533 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 534 data.update(query)
11f9be09 535 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 536 real_headers.update({'content-type': 'application/json'})
537 if headers:
538 real_headers.update(headers)
2ae778b8 539 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
540 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 541 return self._download_json(
2ae778b8 542 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 543 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 544 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 545 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 546
65141660 547 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
548 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 549
99e9e001 550 @staticmethod
551 def _extract_session_index(*data):
552 """
553 Index of current account in account list.
554 See: https://github.com/yt-dlp/yt-dlp/pull/519
555 """
556 for ytcfg in data:
557 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
558 if session_index is not None:
559 return session_index
560
561 # Deprecated?
562 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 563 if ytcfg:
14f25df2 564 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
565 if token:
566 return token
99e9e001 567 if webpage:
568 return self._search_regex(
569 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
570 'identity token', default=None, fatal=False)
a1c5d2ca
M
571
572 @staticmethod
fe93e2c4 573 def _extract_account_syncid(*args):
8ea3f7b9 574 """
575 Extract syncId required to download private playlists of secondary channels
fe93e2c4 576 @params response and/or ytcfg
8ea3f7b9 577 """
fe93e2c4 578 for data in args:
579 # ytcfg includes channel_syncid if on secondary channel
14f25df2 580 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 581 if delegated_sid:
582 return delegated_sid
583 sync_ids = (try_get(
584 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 585 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 586 if len(sync_ids) >= 2 and sync_ids[1]:
587 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
588 # and just "user_syncid||" for primary channel. We only want the channel_syncid
589 return sync_ids[0]
a1c5d2ca 590
ac56cf38 591 @staticmethod
592 def _extract_visitor_data(*args):
593 """
594 Extracts visitorData from an API response or ytcfg
595 Appears to be used to track session state
596 """
9222c381 597 return get_first(
6c73052c 598 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 599 expected_type=str)
ac56cf38 600
2762dbb1 601 @functools.cached_property
99e9e001 602 def is_authenticated(self):
603 return bool(self._generate_sapisidhash_header())
604
11f9be09 605 def extract_ytcfg(self, video_id, webpage):
8c54a305 606 if not webpage:
607 return {}
29f7c58a 608 return self._parse_json(
609 self._search_regex(
610 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 611 default='{}'), video_id, fatal=False) or {}
612
11f9be09 613 def generate_api_headers(
99e9e001 614 self, *, ytcfg=None, account_syncid=None, session_index=None,
615 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
616
2ae778b8 617 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 618 headers = {
14f25df2 619 'X-YouTube-Client-Name': str(
11f9be09 620 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
621 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 622 'Origin': origin,
623 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
624 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 625 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
626 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 627 }
628 if session_index is None:
314ee305 629 session_index = self._extract_session_index(ytcfg)
630 if account_syncid or session_index is not None:
631 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 632
109dd3b2 633 auth = self._generate_sapisidhash_header(origin)
f4f751af 634 if auth is not None:
635 headers['Authorization'] = auth
109dd3b2 636 headers['X-Origin'] = origin
7a32c70d 637 return filter_dict(headers)
29f7c58a 638
a25bca9f 639 def _download_ytcfg(self, client, video_id):
640 url = {
641 'web': 'https://www.youtube.com',
642 'web_music': 'https://music.youtube.com',
643 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
644 }.get(client)
645 if not url:
646 return {}
647 webpage = self._download_webpage(
648 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
649 return self.extract_ytcfg(video_id, webpage) or {}
650
2d6659b9 651 @staticmethod
652 def _build_api_continuation_query(continuation, ctp=None):
653 query = {
654 'continuation': continuation
655 }
656 # TODO: Inconsistency with clickTrackingParams.
657 # Currently we have a fixed ctp contained within context (from ytcfg)
658 # and a ctp in root query for continuation.
659 if ctp:
660 query['clickTracking'] = {'clickTrackingParams': ctp}
661 return query
662
2d6659b9 663 @classmethod
664 def _extract_next_continuation_data(cls, renderer):
665 next_continuation = try_get(
666 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
667 lambda x: x['continuation']['reloadContinuationData']), dict)
668 if not next_continuation:
669 return
670 continuation = next_continuation.get('continuation')
671 if not continuation:
672 return
673 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 674 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 675
676 @classmethod
677 def _extract_continuation_ep_data(cls, continuation_ep: dict):
678 if isinstance(continuation_ep, dict):
679 continuation = try_get(
14f25df2 680 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 681 if not continuation:
682 return
683 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 684 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 685
686 @classmethod
687 def _extract_continuation(cls, renderer):
688 next_continuation = cls._extract_next_continuation_data(renderer)
689 if next_continuation:
690 return next_continuation
fe93e2c4 691
7a32c70d 692 return traverse_obj(renderer, (
693 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
694 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
695 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 696
fe93e2c4 697 @classmethod
698 def _extract_alerts(cls, data):
109dd3b2 699 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
700 if not isinstance(alert_dict, dict):
701 continue
702 for alert in alert_dict.values():
703 alert_type = alert.get('type')
704 if not alert_type:
705 continue
052e1350 706 message = cls._get_text(alert, 'text')
109dd3b2 707 if message:
708 yield alert_type, message
709
c0ac49bc 710 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 711 errors, warnings = [], []
109dd3b2 712 for alert_type, alert_message in alerts:
641ad5d8 713 if alert_type.lower() == 'error' and fatal:
109dd3b2 714 errors.append([alert_type, alert_message])
a057779d 715 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 716 warnings.append([alert_type, alert_message])
717
718 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 719 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 720 if errors:
721 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
722
723 def _extract_and_report_alerts(self, data, *args, **kwargs):
724 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
725
47193e02 726 def _extract_badges(self, renderer: dict):
c26f9b99 727 privacy_icon_map = {
728 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
729 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
730 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
731 }
732
733 badge_style_map = {
734 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
735 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
736 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
737 }
738
739 label_map = {
740 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
741 'private': BadgeType.AVAILABILITY_PRIVATE,
742 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
743 'live': BadgeType.LIVE_NOW,
744 'premium': BadgeType.AVAILABILITY_PREMIUM
745 }
746
747 badges = []
748 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer'), default=[]):
749 badge_type = (
750 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
751 or badge_style_map.get(traverse_obj(badge, 'style'))
752 )
753 if badge_type:
754 badges.append({'type': badge_type})
755 continue
756
757 # fallback, won't work in some languages
758 label = traverse_obj(badge, 'label', expected_type=str, default='')
759 for match, label_badge_type in label_map.items():
760 if match in label.lower():
761 badges.append({'type': badge_type})
762 continue
763
47193e02 764 return badges
765
c26f9b99 766 @staticmethod
767 def _has_badge(badges, badge_type):
768 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
769
47193e02 770 @staticmethod
052e1350 771 def _get_text(data, *path_list, max_runs=None):
772 for path in path_list or [None]:
773 if path is None:
774 obj = [data]
775 else:
776 obj = traverse_obj(data, path, default=[])
777 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
778 obj = [obj]
779 for item in obj:
14f25df2 780 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 781 if text:
782 return text
783 runs = try_get(item, lambda x: x['runs'], list) or []
784 if not runs and isinstance(item, list):
785 runs = item
786
787 runs = runs[:min(len(runs), max_runs or len(runs))]
788 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
789 if text:
790 return text
47193e02 791
f0d785d3 792 def _get_count(self, data, *path_list):
793 count_text = self._get_text(data, *path_list) or ''
794 count = parse_count(count_text)
795 if count is None:
796 count = str_to_int(
797 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
798 return count
799
a709d873 800 @staticmethod
801 def _extract_thumbnails(data, *path_list):
802 """
803 Extract thumbnails from thumbnails dict
804 @param path_list: path list to level that contains 'thumbnails' key
805 """
806 thumbnails = []
807 for path in path_list or [()]:
808 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
809 thumbnail_url = url_or_none(thumbnail.get('url'))
810 if not thumbnail_url:
811 continue
812 # Sometimes youtube gives a wrong thumbnail URL. See:
813 # https://github.com/yt-dlp/yt-dlp/issues/233
814 # https://github.com/ytdl-org/youtube-dl/issues/28023
815 if 'maxresdefault' in thumbnail_url:
816 thumbnail_url = thumbnail_url.split('?')[0]
817 thumbnails.append({
818 'url': thumbnail_url,
819 'height': int_or_none(thumbnail.get('height')),
820 'width': int_or_none(thumbnail.get('width')),
821 })
822 return thumbnails
823
f3aa3c3f 824 @staticmethod
825 def extract_relative_time(relative_time_text):
826 """
827 Extracts a relative time from string and converts to dt object
f0d785d3 828 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 829 """
f0d785d3 830 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
f3aa3c3f 831 if mobj:
f0d785d3 832 start = mobj.group('start')
833 if start:
834 return datetime_from_str(start)
f3aa3c3f 835 try:
f0d785d3 836 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 837 except ValueError:
838 return None
839
c26f9b99 840 def _parse_time_text(self, text):
841 if not text:
842 return
f3aa3c3f 843 dt = self.extract_relative_time(text)
844 timestamp = None
845 if isinstance(dt, datetime.datetime):
846 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 847
848 if timestamp is None:
849 timestamp = (
850 unified_timestamp(text) or unified_timestamp(
851 self._search_regex(
17322130 852 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 853 text.lower(), 'time text', default=None)))
f0d785d3 854
c26f9b99 855 if text and timestamp is None and self._preferred_lang in (None, 'en'):
856 self.report_warning(
857 f'Cannot parse localized time text "{text}"', only_once=True)
858 return timestamp
f3aa3c3f 859
109dd3b2 860 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
861 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 862 default_client='web'):
be5c1ae8 863 for retry in self.RetryManager():
109dd3b2 864 try:
865 response = self._call_api(
866 ep=ep, fatal=True, headers=headers,
be5c1ae8 867 video_id=item_id, query=query, note=note,
109dd3b2 868 context=self._extract_context(ytcfg, default_client),
869 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 870 api_hostname=api_hostname, default_client=default_client)
109dd3b2 871 except ExtractorError as e:
be5c1ae8 872 if not isinstance(e.cause, network_exceptions):
873 return self._error_or_warning(e, fatal=fatal)
874 elif not isinstance(e.cause, urllib.error.HTTPError):
875 retry.error = e
876 continue
109dd3b2 877
be5c1ae8 878 first_bytes = e.cause.read(512)
879 if not is_html(first_bytes):
880 yt_error = try_get(
881 self._parse_json(
882 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
883 lambda x: x['error']['message'], str)
884 if yt_error:
885 self._report_alerts([('ERROR', yt_error)], fatal=False)
886 # Downloading page may result in intermittent 5xx HTTP error
887 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
888 # We also want to catch all other network exceptions since errors in later pages can be troublesome
889 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
890 if e.cause.code not in (403, 429):
891 retry.error = e
892 continue
893 return self._error_or_warning(e, fatal=fatal)
894
895 try:
896 self._extract_and_report_alerts(response, only_once=True)
897 except ExtractorError as e:
898 # YouTube servers may return errors we want to retry on in a 200 OK response
899 # See: https://github.com/yt-dlp/yt-dlp/issues/839
900 if 'unknown error' in e.msg.lower():
901 retry.error = e
902 continue
903 return self._error_or_warning(e, fatal=fatal)
904 # Youtube sometimes sends incomplete data
905 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
906 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 907 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 908 continue
909
910 return response
109dd3b2 911
9297939e 912 @staticmethod
913 def is_music_url(url):
914 return re.match(r'https?://music\.youtube\.com/', url) is not None
915
30a074c2 916 def _extract_video(self, renderer):
917 video_id = renderer.get('videoId')
4dc23a80
M
918
919 reel_header_renderer = traverse_obj(renderer, (
920 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
921 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
922
923 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 924 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
925
926 duration = int_or_none(renderer.get('lengthSeconds'))
927 if duration is None:
928 duration = parse_duration(self._get_text(
929 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 930 if duration is None:
4dc23a80 931 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 932 duration = parse_duration(self._search_regex(
933 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
934 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
935 video_id, default=None, group='duration'))
936
f3aa3c3f 937 channel_id = traverse_obj(
a44ca5a4 938 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
939 expected_type=str, get_all=False)
4dc23a80
M
940 if not channel_id:
941 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
942
f3aa3c3f 943 overlay_style = traverse_obj(
a44ca5a4 944 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
945 get_all=False, expected_type=str)
f3aa3c3f 946 badges = self._extract_badges(renderer)
4dc23a80 947
fd2ad7cb 948 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 949 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
950 expected_type=str)) or ''
fd2ad7cb 951 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 952 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 953 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 954
4dc23a80
M
955 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
956 or self._get_text(reel_header_renderer, 'timestampText') or '')
957 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
958
867c66ff
M
959 live_status = (
960 'is_upcoming' if scheduled_timestamp is not None
961 else 'was_live' if 'streamed' in time_text.lower()
962 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
963 else None)
964
4dc23a80
M
965 # videoInfo is a string like '50K views • 10 years ago'.
966 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
967 view_count = (0 if 'no views' in view_count_text.lower()
968 else self._get_count({'simpleText': view_count_text}))
969 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
970
30a074c2 971 return {
39ed931e 972 '_type': 'url',
30a074c2 973 'ie_key': YoutubeIE.ie_key(),
974 'id': video_id,
fd2ad7cb 975 'url': url,
30a074c2 976 'title': title,
977 'description': description,
978 'duration': duration,
f3aa3c3f 979 'channel_id': channel_id,
4dc23a80
M
980 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
981 or self._get_text(reel_header_renderer, 'channelTitleText')),
982 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
983 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 984 'timestamp': (self._parse_time_text(time_text)
985 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
986 else None),
f3aa3c3f 987 'release_timestamp': scheduled_timestamp,
c26f9b99 988 'availability':
989 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
990 else self._availability(
991 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
992 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
993 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 994 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 995 view_count_field: view_count,
e63faa10 996 'live_status': live_status
30a074c2 997 }
998
0c148415 999
360e1ca5 1000class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1001 IE_DESC = 'YouTube'
cb7dfeea 1002 _VALID_URL = r"""(?x)^
c5e8d7af 1003 (
edb53e2d 1004 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1005 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1006 (?:www\.)?deturl\.com/www\.youtube\.com|
1007 (?:www\.)?pwnyoutube\.com|
1008 (?:www\.)?hooktube\.com|
1009 (?:www\.)?yourepeat\.com|
1010 tube\.majestyc\.net|
1011 %(invidious)s|
1012 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1013 (?:.*?\#/)? # handle anchor (#/) redirect urls
1014 (?: # the various things that can precede the ID:
dad2210c 1015 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1016 |(?: # or the v= param in all its forms
f7000f3a 1017 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1018 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1019 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1020 v=
1021 )
f4b05232 1022 ))
cbaed4bb
S
1023 |(?:
1024 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1025 vid\.plus| # or vid.plus/xxxx
1026 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1027 %(invidious)s
cbaed4bb 1028 )/
edb53e2d 1029 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1030 )
c5e8d7af 1031 )? # all until now is optional -> you can pass the naked ID
201c1459 1032 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1033 (?(1).+)? # if we found the ID, everything can follow
9297939e 1034 (?:\#|$)""" % {
d9190e44 1035 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1036 }
7c6eb424 1037 _EMBED_REGEX = [
1038 r'''(?x)
1039 (?:
0ca0f881 1040 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1041 data-video-url=|
1042 <embed[^>]+?src=|
1043 embedSWF\(?:\s*|
1044 <object[^>]+data=|
1045 new\s+SWFObject\(
1046 )
1047 (["\'])
1048 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1049 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1050 \1''',
1051 # https://wordpress.org/plugins/lazy-load-for-videos/
1052 r'''(?xs)
1053 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1054 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1055 ]
6368e2e6 1056 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1057
e40c758c 1058 _PLAYER_INFO_RE = (
cc2db878 1059 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1060 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 1061 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1062 )
2c62dc26 1063 _formats = {
c2d3cb4c 1064 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1065 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1066 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1067 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1068 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1069 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1070 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1071 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1072 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1073 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1074 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1075 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1076 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1077 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1078 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1079 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1080 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1081 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1082
1083
1084 # 3D videos
c2d3cb4c 1085 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1086 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1087 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1088 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1089 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1090 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1091 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1092
96fb5605 1093 # Apple HTTP Live Streaming
11f12195 1094 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1095 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1096 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1097 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1098 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1099 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1100 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1101 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1102
1103 # DASH mp4 video
d23028a8
S
1104 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1105 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1106 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1107 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1108 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1109 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1110 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1111 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1112 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1113 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1114 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1115 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1116
f6f1fc92 1117 # Dash mp4 audio
d23028a8
S
1118 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1119 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1120 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1121 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1122 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1123 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1124 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1125
1126 # Dash webm
d23028a8
S
1127 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1128 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1129 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1130 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1131 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1132 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1133 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1134 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1135 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1136 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1137 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1138 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1139 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1140 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1141 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1142 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1143 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1144 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1145 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1146 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1147 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1148 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1149
1150 # Dash webm audio
d23028a8
S
1151 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1152 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1153
0857baad 1154 # Dash webm audio with opus inside
d23028a8
S
1155 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1156 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1157 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1158
ce6b9a2d
PH
1159 # RTMP (unnamed)
1160 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1161
1162 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1163 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1164 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1165 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1166 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1167 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1168 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1169 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1170 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1171 }
29f7c58a 1172 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1173
fd5c4aab
S
1174 _GEO_BYPASS = False
1175
78caa52a 1176 IE_NAME = 'youtube'
2eb88d95
PH
1177 _TESTS = [
1178 {
2d3d2997 1179 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1180 'info_dict': {
1181 'id': 'BaW_jenozKc',
1182 'ext': 'mp4',
3867038a 1183 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1184 'uploader': 'Philipp Hagemeister',
1185 'uploader_id': 'phihag',
ec85ded8 1186 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1187 'channel': 'Philipp Hagemeister',
dd4c4492
S
1188 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1189 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1190 'upload_date': '20121002',
ff9f925b 1191 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1192 'categories': ['Science & Technology'],
3867038a 1193 'tags': ['youtube-dl'],
556dbe7f 1194 'duration': 10,
dbdaaa23 1195 'view_count': int,
3e7c1224 1196 'like_count': int,
ff9f925b 1197 'availability': 'public',
1198 'playable_in_embed': True,
1199 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1200 'live_status': 'not_live',
1201 'age_limit': 0,
7c80519c 1202 'start_time': 1,
297a564b 1203 'end_time': 9,
12a1b225 1204 'comment_count': int,
6c73052c 1205 'channel_follower_count': int
2eb88d95 1206 }
0e853ca4 1207 },
fccd3771 1208 {
4bc3a23e
PH
1209 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1210 'note': 'Embed-only video (#1746)',
1211 'info_dict': {
1212 'id': 'yZIXLfi8CZQ',
1213 'ext': 'mp4',
1214 'upload_date': '20120608',
1215 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1216 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1217 'uploader': 'SET India',
94bfcd23 1218 'uploader_id': 'setindia',
ec85ded8 1219 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1220 'age_limit': 18,
545cc85d 1221 },
1222 'skip': 'Private video',
fccd3771 1223 },
11b56058 1224 {
8bdd16b4 1225 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1226 'note': 'Use the first video ID in the URL',
1227 'info_dict': {
1228 'id': 'BaW_jenozKc',
1229 'ext': 'mp4',
3867038a 1230 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1231 'uploader': 'Philipp Hagemeister',
1232 'uploader_id': 'phihag',
ec85ded8 1233 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1234 'channel': 'Philipp Hagemeister',
1235 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1236 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1237 'upload_date': '20121002',
976ae3ea 1238 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1239 'categories': ['Science & Technology'],
3867038a 1240 'tags': ['youtube-dl'],
556dbe7f 1241 'duration': 10,
dbdaaa23 1242 'view_count': int,
11b56058 1243 'like_count': int,
976ae3ea 1244 'availability': 'public',
1245 'playable_in_embed': True,
1246 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1247 'live_status': 'not_live',
1248 'age_limit': 0,
12a1b225 1249 'comment_count': int,
6c73052c 1250 'channel_follower_count': int
34a7de29
S
1251 },
1252 'params': {
1253 'skip_download': True,
1254 },
11b56058 1255 },
dd27fd17 1256 {
2d3d2997 1257 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1258 'note': '256k DASH audio (format 141) via DASH manifest',
1259 'info_dict': {
1260 'id': 'a9LDPn-MO4I',
1261 'ext': 'm4a',
1262 'upload_date': '20121002',
1263 'uploader_id': '8KVIDEO',
ec85ded8 1264 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1265 'description': '',
1266 'uploader': '8KVIDEO',
1267 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1268 },
4bc3a23e
PH
1269 'params': {
1270 'youtube_include_dash_manifest': True,
1271 'format': '141',
4919603f 1272 },
de3c7fe0 1273 'skip': 'format 141 not served anymore',
dd27fd17 1274 },
8bdd16b4 1275 # DASH manifest with encrypted signature
1276 {
1277 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1278 'info_dict': {
1279 'id': 'IB3lcPjvWLA',
1280 'ext': 'm4a',
1281 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1282 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1283 'duration': 244,
1284 'uploader': 'AfrojackVEVO',
1285 'uploader_id': 'AfrojackVEVO',
1286 'upload_date': '20131011',
cc2db878 1287 'abr': 129.495,
976ae3ea 1288 'like_count': int,
1289 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1290 'playable_in_embed': True,
1291 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1292 'view_count': int,
1293 'track': 'The Spark',
1294 'live_status': 'not_live',
1295 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1296 'channel': 'Afrojack',
1297 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1298 'tags': 'count:19',
1299 'availability': 'public',
1300 'categories': ['Music'],
1301 'age_limit': 0,
1302 'alt_title': 'The Spark',
6c73052c 1303 'channel_follower_count': int
8bdd16b4 1304 },
1305 'params': {
1306 'youtube_include_dash_manifest': True,
1307 'format': '141/bestaudio[ext=m4a]',
1308 },
1309 },
65c2fde2 1310 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1311 {
65c2fde2 1312 'note': 'Embed allowed age-gate video',
2d3d2997 1313 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1314 'info_dict': {
1315 'id': 'HtVdAasjOgU',
1316 'ext': 'mp4',
1317 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1318 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1319 'duration': 142,
c522adb1
JMF
1320 'uploader': 'The Witcher',
1321 'uploader_id': 'WitcherGame',
ec85ded8 1322 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1323 'upload_date': '20140605',
34952f09 1324 'age_limit': 18,
976ae3ea 1325 'categories': ['Gaming'],
1326 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1327 'availability': 'needs_auth',
1328 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1329 'like_count': int,
1330 'channel': 'The Witcher',
1331 'live_status': 'not_live',
1332 'tags': 'count:17',
1333 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1334 'playable_in_embed': True,
1335 'view_count': int,
6c73052c 1336 'channel_follower_count': int
c522adb1
JMF
1337 },
1338 },
65c2fde2 1339 {
1340 'note': 'Age-gate video with embed allowed in public site',
1341 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1342 'info_dict': {
1343 'id': 'HsUATh_Nc2U',
1344 'ext': 'mp4',
1345 'title': 'Godzilla 2 (Official Video)',
1346 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1347 'upload_date': '20200408',
1348 'uploader_id': 'FlyingKitty900',
1349 'uploader': 'FlyingKitty',
1350 'age_limit': 18,
976ae3ea 1351 'availability': 'needs_auth',
1352 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1353 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1354 'channel': 'FlyingKitty',
1355 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1356 'view_count': int,
1357 'categories': ['Entertainment'],
1358 'live_status': 'not_live',
1359 'tags': ['Flyingkitty', 'godzilla 2'],
1360 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1361 'like_count': int,
1362 'duration': 177,
1363 'playable_in_embed': True,
6c73052c 1364 'channel_follower_count': int
65c2fde2 1365 },
1366 },
1367 {
1368 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1369 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1370 'info_dict': {
1371 'id': 'Tq92D6wQ1mg',
1372 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1373 'ext': 'mp4',
17322130 1374 'upload_date': '20191228',
65c2fde2 1375 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1376 'uploader': 'Projekt Melody',
1377 'description': 'md5:17eccca93a786d51bc67646756894066',
1378 'age_limit': 18,
976ae3ea 1379 'like_count': int,
1380 'availability': 'needs_auth',
1381 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1382 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1383 'view_count': int,
1384 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1385 'channel': 'Projekt Melody',
1386 'live_status': 'not_live',
1387 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1388 'playable_in_embed': True,
1389 'categories': ['Entertainment'],
1390 'duration': 106,
1391 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1392 'comment_count': int,
6c73052c 1393 'channel_follower_count': int
65c2fde2 1394 },
1395 },
1396 {
1397 'note': 'Non-Agegated non-embeddable video',
1398 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1399 'info_dict': {
1400 'id': 'MeJVWBSsPAY',
1401 'ext': 'mp4',
1402 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1403 'uploader': 'Herr Lurik',
1404 'uploader_id': 'st3in234',
1405 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1406 'upload_date': '20130730',
976ae3ea 1407 'track': 'Such mich find mich',
1408 'age_limit': 0,
1409 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1410 'like_count': int,
1411 'playable_in_embed': False,
1412 'creator': 'OOMPH!',
1413 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1414 'view_count': int,
1415 'alt_title': 'Such mich find mich',
1416 'duration': 210,
1417 'channel': 'Herr Lurik',
1418 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1419 'categories': ['Music'],
1420 'availability': 'public',
1421 'uploader_url': 'http://www.youtube.com/user/st3in234',
1422 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1423 'live_status': 'not_live',
1424 'artist': 'OOMPH!',
6c73052c 1425 'channel_follower_count': int
65c2fde2 1426 },
1427 },
1428 {
1429 'note': 'Non-bypassable age-gated video',
1430 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1431 'only_matching': True,
1432 },
8bdd16b4 1433 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1434 # YouTube Red ad is not captured for creator
1435 {
1436 'url': '__2ABJjxzNo',
1437 'info_dict': {
1438 'id': '__2ABJjxzNo',
1439 'ext': 'mp4',
1440 'duration': 266,
1441 'upload_date': '20100430',
1442 'uploader_id': 'deadmau5',
1443 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1444 'creator': 'deadmau5',
1445 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1446 'uploader': 'deadmau5',
1447 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1448 'alt_title': 'Some Chords',
976ae3ea 1449 'availability': 'public',
1450 'tags': 'count:14',
1451 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1452 'view_count': int,
1453 'live_status': 'not_live',
1454 'channel': 'deadmau5',
1455 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1456 'like_count': int,
1457 'track': 'Some Chords',
1458 'artist': 'deadmau5',
1459 'playable_in_embed': True,
1460 'age_limit': 0,
1461 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1462 'categories': ['Music'],
1463 'album': 'Some Chords',
6c73052c 1464 'channel_follower_count': int
8bdd16b4 1465 },
1466 'expected_warnings': [
1467 'DASH manifest missing',
1468 ]
1469 },
067aa17e 1470 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1471 {
1472 'url': 'lqQg6PlCWgI',
1473 'info_dict': {
1474 'id': 'lqQg6PlCWgI',
1475 'ext': 'mp4',
556dbe7f 1476 'duration': 6085,
90227264 1477 'upload_date': '20150827',
cbe2bd91 1478 'uploader_id': 'olympic',
ec85ded8 1479 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1480 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1481 'uploader': 'Olympics',
cbe2bd91 1482 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1483 'like_count': int,
1484 'release_timestamp': 1343767800,
1485 'playable_in_embed': True,
1486 'categories': ['Sports'],
1487 'release_date': '20120731',
1488 'channel': 'Olympics',
1489 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1490 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1491 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1492 'age_limit': 0,
1493 'availability': 'public',
1494 'live_status': 'was_live',
1495 'view_count': int,
1496 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1497 'channel_follower_count': int
cbe2bd91
PH
1498 },
1499 'params': {
1500 'skip_download': 'requires avconv',
e52a40ab 1501 }
cbe2bd91 1502 },
6271f1ca
PH
1503 # Non-square pixels
1504 {
1505 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1506 'info_dict': {
1507 'id': '_b-2C3KPAM0',
1508 'ext': 'mp4',
1509 'stretched_ratio': 16 / 9.,
556dbe7f 1510 'duration': 85,
6271f1ca
PH
1511 'upload_date': '20110310',
1512 'uploader_id': 'AllenMeow',
ec85ded8 1513 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1514 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
eb6793ba 1515 'uploader': '孫ᄋᄅ',
6271f1ca 1516 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1517 'playable_in_embed': True,
1518 'channel': '孫ᄋᄅ',
1519 'age_limit': 0,
1520 'tags': 'count:11',
1521 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1522 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1523 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1524 'view_count': int,
1525 'categories': ['People & Blogs'],
1526 'like_count': int,
1527 'live_status': 'not_live',
1528 'availability': 'unlisted',
12a1b225 1529 'comment_count': int,
6c73052c 1530 'channel_follower_count': int
6271f1ca 1531 },
06b491eb
S
1532 },
1533 # url_encoded_fmt_stream_map is empty string
1534 {
1535 'url': 'qEJwOuvDf7I',
1536 'info_dict': {
1537 'id': 'qEJwOuvDf7I',
f57b7835 1538 'ext': 'webm',
06b491eb
S
1539 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1540 'description': '',
1541 'upload_date': '20150404',
1542 'uploader_id': 'spbelect',
1543 'uploader': 'Наблюдатели Петербурга',
1544 },
1545 'params': {
1546 'skip_download': 'requires avconv',
e323cf3f
S
1547 },
1548 'skip': 'This live event has ended.',
06b491eb 1549 },
067aa17e 1550 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1551 {
1552 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1553 'info_dict': {
1554 'id': 'FIl7x6_3R5Y',
eb6793ba 1555 'ext': 'webm',
da77d856
S
1556 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1557 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1558 'duration': 220,
da77d856
S
1559 'upload_date': '20150625',
1560 'uploader_id': 'dorappi2000',
ec85ded8 1561 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1562 'uploader': 'dorappi2000',
eb6793ba 1563 'formats': 'mincount:31',
da77d856 1564 },
eb6793ba 1565 'skip': 'not actual anymore',
2ee8f5d8 1566 },
8a1a26ce
YCH
1567 # DASH manifest with segment_list
1568 {
1569 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1570 'md5': '8ce563a1d667b599d21064e982ab9e31',
1571 'info_dict': {
1572 'id': 'CsmdDsKjzN8',
1573 'ext': 'mp4',
17ee98e1 1574 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1575 'uploader': 'Airtek',
1576 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1577 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1578 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1579 },
1580 'params': {
1581 'youtube_include_dash_manifest': True,
1582 'format': '135', # bestvideo
be49068d
S
1583 },
1584 'skip': 'This live event has ended.',
2ee8f5d8 1585 },
cf7e015f 1586 {
6368e2e6 1587 # Multifeed videos (multiple cameras), URL can be of any Camera
1588 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1589 'info_dict': {
6368e2e6 1590 'id': 'zaPI8MvL8pg',
1591 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1592 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1593 },
1594 'playlist': [{
1595 'info_dict': {
6368e2e6 1596 'id': 'j5yGuxZ8lLU',
cf7e015f 1597 'ext': 'mp4',
6368e2e6 1598 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
1599 'uploader': 'WiiLikeToPlay',
1600 'description': 'md5:563ccbc698b39298481ca3c571169519',
1601 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1602 'duration': 10120,
1603 'channel_follower_count': int,
1604 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1605 'availability': 'public',
1606 'playable_in_embed': True,
1607 'upload_date': '20131105',
1608 'uploader_id': 'WiiRikeToPray',
1609 'categories': ['Gaming'],
1610 'live_status': 'was_live',
1611 'tags': 'count:24',
1612 'release_timestamp': 1383701910,
1613 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1614 'comment_count': int,
1615 'age_limit': 0,
1616 'like_count': int,
1617 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1618 'channel': 'WiiLikeToPlay',
1619 'view_count': int,
1620 'release_date': '20131106',
cf7e015f
S
1621 },
1622 }, {
1623 'info_dict': {
6368e2e6 1624 'id': 'zaPI8MvL8pg',
cf7e015f 1625 'ext': 'mp4',
6368e2e6 1626 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
1627 'uploader_id': 'WiiRikeToPray',
1628 'availability': 'public',
1629 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1630 'channel': 'WiiLikeToPlay',
1631 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1632 'channel_follower_count': int,
1633 'description': 'md5:563ccbc698b39298481ca3c571169519',
1634 'duration': 10108,
1635 'age_limit': 0,
1636 'like_count': int,
1637 'tags': 'count:24',
1638 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1639 'uploader': 'WiiLikeToPlay',
1640 'release_timestamp': 1383701915,
1641 'comment_count': int,
1642 'upload_date': '20131105',
1643 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1644 'release_date': '20131106',
1645 'playable_in_embed': True,
1646 'live_status': 'was_live',
1647 'categories': ['Gaming'],
1648 'view_count': int,
cf7e015f
S
1649 },
1650 }, {
1651 'info_dict': {
6368e2e6 1652 'id': 'R7r3vfO7Hao',
cf7e015f 1653 'ext': 'mp4',
6368e2e6 1654 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1655 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1656 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1657 'like_count': int,
1658 'availability': 'public',
1659 'playable_in_embed': True,
1660 'upload_date': '20131105',
1661 'description': 'md5:563ccbc698b39298481ca3c571169519',
1662 'uploader_id': 'WiiRikeToPray',
1663 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1664 'channel_follower_count': int,
1665 'tags': 'count:24',
1666 'release_date': '20131106',
1667 'uploader': 'WiiLikeToPlay',
1668 'comment_count': int,
1669 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1670 'channel': 'WiiLikeToPlay',
1671 'categories': ['Gaming'],
1672 'release_timestamp': 1383701914,
1673 'live_status': 'was_live',
1674 'age_limit': 0,
1675 'duration': 10128,
1676 'view_count': int,
cf7e015f
S
1677 },
1678 }],
6368e2e6 1679 'params': {'skip_download': True},
cbaed4bb 1680 },
f9f49d87 1681 {
067aa17e 1682 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1683 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1684 'info_dict': {
1685 'id': 'gVfLd0zydlo',
1686 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1687 },
1688 'playlist_count': 2,
be49068d 1689 'skip': 'Not multifeed anymore',
f9f49d87 1690 },
cbaed4bb 1691 {
2d3d2997 1692 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1693 'only_matching': True,
0e49d9a6 1694 },
6d4fc66b 1695 {
2d3d2997 1696 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1697 'only_matching': True,
1698 },
0e49d9a6 1699 {
067aa17e 1700 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1701 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1702 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1703 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1704 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1705 'info_dict': {
1706 'id': 'lsguqyKfVQg',
1707 'ext': 'mp4',
1708 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1709 'alt_title': 'Dark Walk',
0e49d9a6 1710 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1711 'duration': 133,
0e49d9a6
LL
1712 'upload_date': '20151119',
1713 'uploader_id': 'IronSoulElf',
ec85ded8 1714 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1715 'uploader': 'IronSoulElf',
11f9be09 1716 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1717 'track': 'Dark Walk',
1718 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1719 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1720 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1721 'categories': ['Film & Animation'],
1722 'view_count': int,
1723 'live_status': 'not_live',
1724 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1725 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1726 'tags': 'count:13',
1727 'availability': 'public',
1728 'channel': 'IronSoulElf',
1729 'playable_in_embed': True,
1730 'like_count': int,
1731 'age_limit': 0,
6c73052c 1732 'channel_follower_count': int
0e49d9a6
LL
1733 },
1734 'params': {
1735 'skip_download': True,
1736 },
1737 },
61f92af1 1738 {
067aa17e 1739 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1740 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1741 'only_matching': True,
1742 },
313dfc45
LL
1743 {
1744 # Video with yt:stretch=17:0
1745 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1746 'info_dict': {
1747 'id': 'Q39EVAstoRM',
1748 'ext': 'mp4',
1749 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1750 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1751 'upload_date': '20151107',
1752 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1753 'uploader': 'CH GAMER DROID',
1754 },
1755 'params': {
1756 'skip_download': True,
1757 },
be49068d 1758 'skip': 'This video does not exist.',
313dfc45 1759 },
201c1459 1760 {
1761 # Video with incomplete 'yt:stretch=16:'
1762 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1763 'only_matching': True,
1764 },
7caf9830
S
1765 {
1766 # Video licensed under Creative Commons
1767 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1768 'info_dict': {
1769 'id': 'M4gD1WSo5mA',
1770 'ext': 'mp4',
1771 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1772 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1773 'duration': 721,
17322130 1774 'upload_date': '20150128',
7caf9830 1775 'uploader_id': 'BerkmanCenter',
ec85ded8 1776 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1777 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1778 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1779 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1780 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1781 'like_count': int,
1782 'age_limit': 0,
1783 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1784 'channel': 'The Berkman Klein Center for Internet & Society',
1785 'availability': 'public',
1786 'view_count': int,
1787 'categories': ['Education'],
1788 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1789 'live_status': 'not_live',
1790 'playable_in_embed': True,
12a1b225 1791 'comment_count': int,
d5d1df8a 1792 'channel_follower_count': int,
1793 'chapters': list,
7caf9830
S
1794 },
1795 'params': {
1796 'skip_download': True,
1797 },
1798 },
fd050249
S
1799 {
1800 # Channel-like uploader_url
1801 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1802 'info_dict': {
1803 'id': 'eQcmzGIKrzg',
1804 'ext': 'mp4',
1805 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1806 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1807 'duration': 4060,
17322130 1808 'upload_date': '20151120',
eb6793ba 1809 'uploader': 'Bernie Sanders',
fd050249 1810 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1811 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1812 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1813 'playable_in_embed': True,
1814 'tags': 'count:12',
1815 'like_count': int,
1816 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1817 'age_limit': 0,
1818 'availability': 'public',
1819 'categories': ['News & Politics'],
1820 'channel': 'Bernie Sanders',
1821 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1822 'view_count': int,
1823 'live_status': 'not_live',
1824 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1825 'comment_count': int,
d5d1df8a 1826 'channel_follower_count': int,
1827 'chapters': list,
fd050249
S
1828 },
1829 'params': {
1830 'skip_download': True,
1831 },
1832 },
040ac686
S
1833 {
1834 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1835 'only_matching': True,
7f29cf54
S
1836 },
1837 {
067aa17e 1838 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1839 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1840 'only_matching': True,
6496ccb4
S
1841 },
1842 {
1843 # Rental video preview
1844 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1845 'info_dict': {
1846 'id': 'uGpuVWrhIzE',
1847 'ext': 'mp4',
1848 'title': 'Piku - Trailer',
1849 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1850 'upload_date': '20150811',
1851 'uploader': 'FlixMatrix',
1852 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1853 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1854 'license': 'Standard YouTube License',
1855 },
1856 'params': {
1857 'skip_download': True,
1858 },
eb6793ba 1859 'skip': 'This video is not available.',
022a5d66 1860 },
12afdc2a
S
1861 {
1862 # YouTube Red video with episode data
1863 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1864 'info_dict': {
1865 'id': 'iqKdEhx-dD4',
1866 'ext': 'mp4',
1867 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1868 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1869 'duration': 2085,
12afdc2a
S
1870 'upload_date': '20170118',
1871 'uploader': 'Vsauce',
1872 'uploader_id': 'Vsauce',
1873 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1874 'series': 'Mind Field',
1875 'season_number': 1,
1876 'episode_number': 1,
976ae3ea 1877 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1878 'tags': 'count:12',
1879 'view_count': int,
1880 'availability': 'public',
1881 'age_limit': 0,
1882 'channel': 'Vsauce',
1883 'episode': 'Episode 1',
1884 'categories': ['Entertainment'],
1885 'season': 'Season 1',
1886 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1887 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1888 'like_count': int,
1889 'playable_in_embed': True,
1890 'live_status': 'not_live',
6c73052c 1891 'channel_follower_count': int
12afdc2a
S
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 'expected_warnings': [
1897 'Skipping DASH manifest',
1898 ],
1899 },
c7121fa7
S
1900 {
1901 # The following content has been identified by the YouTube community
1902 # as inappropriate or offensive to some audiences.
1903 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1904 'info_dict': {
1905 'id': '6SJNVb0GnPI',
1906 'ext': 'mp4',
1907 'title': 'Race Differences in Intelligence',
1908 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1909 'duration': 965,
1910 'upload_date': '20140124',
1911 'uploader': 'New Century Foundation',
1912 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1913 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1914 },
1915 'params': {
1916 'skip_download': True,
1917 },
545cc85d 1918 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1919 },
022a5d66
S
1920 {
1921 # itag 212
1922 'url': '1t24XAntNCY',
1923 'only_matching': True,
fd5c4aab
S
1924 },
1925 {
1926 # geo restricted to JP
1927 'url': 'sJL6WA-aGkQ',
1928 'only_matching': True,
1929 },
cd5a74a2
S
1930 {
1931 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1932 'only_matching': True,
1933 },
bc2ca1bb 1934 {
1935 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1936 'only_matching': True,
1937 },
1938 {
1939 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1940 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1941 'only_matching': True,
1942 },
825cd268
RA
1943 {
1944 # DRM protected
1945 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1946 'only_matching': True,
4fe54c12
S
1947 },
1948 {
1949 # Video with unsupported adaptive stream type formats
1950 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1951 'info_dict': {
1952 'id': 'Z4Vy8R84T1U',
1953 'ext': 'mp4',
1954 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1955 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1956 'duration': 433,
1957 'upload_date': '20130923',
1958 'uploader': 'Amelia Putri Harwita',
1959 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1960 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1961 'formats': 'maxcount:10',
1962 },
1963 'params': {
1964 'skip_download': True,
1965 'youtube_include_dash_manifest': False,
1966 },
5429d6a9 1967 'skip': 'not actual anymore',
5caabd3c 1968 },
1969 {
822b9d9c 1970 # Youtube Music Auto-generated description
5caabd3c 1971 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1972 'info_dict': {
1973 'id': 'MgNrAu2pzNs',
1974 'ext': 'mp4',
1975 'title': 'Voyeur Girl',
1976 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1977 'upload_date': '20190312',
5429d6a9
S
1978 'uploader': 'Stephen - Topic',
1979 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1980 'artist': 'Stephen',
1981 'track': 'Voyeur Girl',
1982 'album': 'it\'s too much love to know my dear',
1983 'release_date': '20190313',
1984 'release_year': 2019,
976ae3ea 1985 'alt_title': 'Voyeur Girl',
1986 'view_count': int,
1987 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1988 'playable_in_embed': True,
1989 'like_count': int,
1990 'categories': ['Music'],
1991 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1992 'channel': 'Stephen',
1993 'availability': 'public',
1994 'creator': 'Stephen',
1995 'duration': 169,
1996 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1997 'age_limit': 0,
1998 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1999 'tags': 'count:11',
2000 'live_status': 'not_live',
6c73052c 2001 'channel_follower_count': int
5caabd3c 2002 },
2003 'params': {
2004 'skip_download': True,
2005 },
2006 },
66b48727
RA
2007 {
2008 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2009 'only_matching': True,
2010 },
011e75e6
S
2011 {
2012 # invalid -> valid video id redirection
2013 'url': 'DJztXj2GPfl',
2014 'info_dict': {
2015 'id': 'DJztXj2GPfk',
2016 'ext': 'mp4',
2017 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2018 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2019 'upload_date': '20090125',
2020 'uploader': 'Prochorowka',
2021 'uploader_id': 'Prochorowka',
2022 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
2023 'artist': 'Panjabi MC',
2024 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2025 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2026 },
2027 'params': {
2028 'skip_download': True,
2029 },
545cc85d 2030 'skip': 'Video unavailable',
ea74e00b
DP
2031 },
2032 {
2033 # empty description results in an empty string
2034 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2035 'info_dict': {
2036 'id': 'x41yOUIvK2k',
2037 'ext': 'mp4',
2038 'title': 'IMG 3456',
2039 'description': '',
2040 'upload_date': '20170613',
2041 'uploader_id': 'ElevageOrVert',
2042 'uploader': 'ElevageOrVert',
976ae3ea 2043 'view_count': int,
2044 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2045 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2046 'like_count': int,
2047 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2048 'tags': [],
2049 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2050 'availability': 'public',
2051 'age_limit': 0,
2052 'categories': ['Pets & Animals'],
2053 'duration': 7,
2054 'playable_in_embed': True,
2055 'live_status': 'not_live',
2056 'channel': 'ElevageOrVert',
6c73052c 2057 'channel_follower_count': int
ea74e00b
DP
2058 },
2059 'params': {
2060 'skip_download': True,
2061 },
2062 },
a0566bbf 2063 {
29f7c58a 2064 # with '};' inside yt initial data (see [1])
2065 # see [2] for an example with '};' inside ytInitialPlayerResponse
2066 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2067 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2068 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2069 'info_dict': {
2070 'id': 'CHqg6qOn4no',
2071 'ext': 'mp4',
2072 'title': 'Part 77 Sort a list of simple types in c#',
2073 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2074 'upload_date': '20130831',
2075 'uploader_id': 'kudvenkat',
2076 'uploader': 'kudvenkat',
976ae3ea 2077 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2078 'like_count': int,
2079 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2080 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2081 'live_status': 'not_live',
2082 'categories': ['Education'],
2083 'availability': 'public',
2084 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2085 'tags': 'count:12',
2086 'playable_in_embed': True,
2087 'age_limit': 0,
2088 'view_count': int,
2089 'duration': 522,
2090 'channel': 'kudvenkat',
12a1b225 2091 'comment_count': int,
d5d1df8a 2092 'channel_follower_count': int,
2093 'chapters': list,
a0566bbf 2094 },
2095 'params': {
2096 'skip_download': True,
2097 },
2098 },
29f7c58a 2099 {
2100 # another example of '};' in ytInitialData
2101 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2102 'only_matching': True,
2103 },
2104 {
2105 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2106 'only_matching': True,
2107 },
545cc85d 2108 {
cc2db878 2109 # https://github.com/ytdl-org/youtube-dl/pull/28094
2110 'url': 'OtqTfy26tG0',
2111 'info_dict': {
2112 'id': 'OtqTfy26tG0',
2113 'ext': 'mp4',
2114 'title': 'Burn Out',
2115 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2116 'upload_date': '20141120',
2117 'uploader': 'The Cinematic Orchestra - Topic',
2118 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2119 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2120 'artist': 'The Cinematic Orchestra',
2121 'track': 'Burn Out',
2122 'album': 'Every Day',
976ae3ea 2123 'like_count': int,
2124 'live_status': 'not_live',
2125 'alt_title': 'Burn Out',
2126 'duration': 614,
2127 'age_limit': 0,
2128 'view_count': int,
2129 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2130 'creator': 'The Cinematic Orchestra',
2131 'channel': 'The Cinematic Orchestra',
2132 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2133 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2134 'availability': 'public',
2135 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2136 'categories': ['Music'],
2137 'playable_in_embed': True,
6c73052c 2138 'channel_follower_count': int
cc2db878 2139 },
2140 'params': {
2141 'skip_download': True,
2142 },
545cc85d 2143 },
bc2ca1bb 2144 {
2145 # controversial video, only works with bpctr when authenticated with cookies
2146 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2147 'only_matching': True,
2148 },
a1a7907b 2149 {
2150 # controversial video, requires bpctr/contentCheckOk
2151 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2152 'info_dict': {
2153 'id': 'SZJvDhaSDnc',
2154 'ext': 'mp4',
2155 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2156 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2157 'uploader': 'CBS Mornings',
11f9be09 2158 'uploader_id': 'CBSThisMorning',
a1a7907b 2159 'upload_date': '20140716',
976ae3ea 2160 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2161 'duration': 170,
2162 'categories': ['News & Politics'],
2163 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2164 'view_count': int,
2165 'channel': 'CBS Mornings',
2166 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2167 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2168 'age_limit': 18,
2169 'availability': 'needs_auth',
2170 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2171 'like_count': int,
2172 'live_status': 'not_live',
2173 'playable_in_embed': True,
6c73052c 2174 'channel_follower_count': int
a1a7907b 2175 }
2176 },
f7ad7160 2177 {
2178 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2179 'url': 'cBvYw8_A0vQ',
2180 'info_dict': {
2181 'id': 'cBvYw8_A0vQ',
2182 'ext': 'mp4',
2183 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2184 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2185 'upload_date': '20201120',
2186 'uploader': 'Walk around Japan',
2187 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2188 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2189 'duration': 1456,
2190 'categories': ['Travel & Events'],
2191 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2192 'view_count': int,
2193 'channel': 'Walk around Japan',
2194 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2195 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2196 'age_limit': 0,
2197 'availability': 'public',
2198 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2199 'live_status': 'not_live',
2200 'playable_in_embed': True,
6c73052c 2201 'channel_follower_count': int
f7ad7160 2202 },
2203 'params': {
2204 'skip_download': True,
2205 },
0fb983f6 2206 }, {
2207 # Has multiple audio streams
2208 'url': 'WaOKSUlf4TM',
2209 'only_matching': True
9297939e 2210 }, {
2211 # Requires Premium: has format 141 when requested using YTM url
2212 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2213 'only_matching': True
2214 }, {
120916da 2215 # multiple subtitles with same lang_code
2216 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2217 'only_matching': True,
109dd3b2 2218 }, {
2219 # Force use android client fallback
2220 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2221 'info_dict': {
2222 'id': 'YOelRv7fMxY',
11f9be09 2223 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2224 'ext': '3gp',
2225 'upload_date': '20210624',
2226 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2227 'uploader': 'colinfurze',
11f9be09 2228 'uploader_id': 'colinfurze',
109dd3b2 2229 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2230 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2231 'duration': 596,
2232 'categories': ['Entertainment'],
2233 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2234 'view_count': int,
2235 'channel': 'colinfurze',
2236 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2237 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2238 'age_limit': 0,
2239 'availability': 'public',
2240 'like_count': int,
2241 'live_status': 'not_live',
2242 'playable_in_embed': True,
d5d1df8a 2243 'channel_follower_count': int,
2244 'chapters': list,
109dd3b2 2245 },
2246 'params': {
2247 'format': '17', # 3gp format available on android
2248 'extractor_args': {'youtube': {'player_client': ['android']}},
2249 },
120916da 2250 },
109dd3b2 2251 {
2252 # Skip download of additional client configs (remix client config in this case)
2253 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2254 'only_matching': True,
2255 'params': {
2256 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2257 },
8fc54b12 2258 }, {
2259 # shorts
2260 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2261 'only_matching': True,
9222c381 2262 }, {
2263 'note': 'Storyboards',
2264 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2265 'info_dict': {
2266 'id': '5KLPxDtMqe8',
2267 'ext': 'mhtml',
2268 'format_id': 'sb0',
2269 'title': 'Your Brain is Plastic',
2270 'uploader_id': 'scishow',
2271 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2272 'upload_date': '20140324',
2273 'uploader': 'SciShow',
976ae3ea 2274 'like_count': int,
2275 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2276 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2277 'view_count': int,
2278 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2279 'playable_in_embed': True,
2280 'tags': 'count:12',
2281 'uploader_url': 'http://www.youtube.com/user/scishow',
2282 'availability': 'public',
2283 'channel': 'SciShow',
2284 'live_status': 'not_live',
2285 'duration': 248,
2286 'categories': ['Education'],
2287 'age_limit': 0,
d5d1df8a 2288 'channel_follower_count': int,
2289 'chapters': list,
9222c381 2290 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2291 }, {
2292 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2293 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2294 'info_dict': {
2295 'id': '2NUZ8W2llS4',
2296 'ext': 'mp4',
2297 'title': 'The NP that test your phone performance 🙂',
2298 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2299 'uploader': 'Leon Nguyen',
2300 'uploader_id': 'VNSXIII',
2301 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2302 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2303 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2304 'duration': 21,
2305 'view_count': int,
2306 'age_limit': 0,
2307 'categories': ['Gaming'],
2308 'tags': 'count:23',
2309 'playable_in_embed': True,
2310 'live_status': 'not_live',
2311 'upload_date': '20220103',
2312 'like_count': int,
2313 'availability': 'public',
2314 'channel': 'Leon Nguyen',
2315 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2316 'comment_count': int,
992f9a73 2317 'channel_follower_count': int
2318 }
1ff88b7a 2319 }, {
2320 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2321 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2322 'info_dict': {
2323 'id': '2NUZ8W2llS4',
2324 'ext': 'mp4',
2325 'title': 'The NP that test your phone performance 🙂',
2326 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2327 'uploader': 'Leon Nguyen',
2328 'uploader_id': 'VNSXIII',
2329 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2330 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2331 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2332 'duration': 21,
2333 'view_count': int,
2334 'age_limit': 0,
2335 'categories': ['Gaming'],
2336 'tags': 'count:23',
2337 'playable_in_embed': True,
2338 'live_status': 'not_live',
2339 'upload_date': '20220102',
2340 'like_count': int,
2341 'availability': 'public',
2342 'channel': 'Leon Nguyen',
2343 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2344 'comment_count': int,
2345 'channel_follower_count': int
2346 },
2347 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2348 }, {
2349 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2350 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2351 'info_dict': {
2352 'id': 'mzZzzBU6lrM',
2353 'ext': 'mp4',
2354 'title': 'I Met GeorgeNotFound In Real Life...',
2355 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2356 'uploader': 'Quackity',
2357 'uploader_id': 'QuackityHQ',
2358 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2359 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2360 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2361 'duration': 955,
2362 'view_count': int,
2363 'age_limit': 0,
2364 'categories': ['Entertainment'],
2365 'tags': 'count:26',
2366 'playable_in_embed': True,
2367 'live_status': 'not_live',
2368 'release_timestamp': 1641172509,
2369 'release_date': '20220103',
2370 'upload_date': '20220103',
2371 'like_count': int,
2372 'availability': 'public',
2373 'channel': 'Quackity',
2374 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2375 'channel_follower_count': int
2376 }
2377 },
2378 { # continuous livestream. Microformat upload date should be preferred.
2379 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2380 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2381 'info_dict': {
2382 'id': 'kgx4WGK0oNU',
2383 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2384 'ext': 'mp4',
2385 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2386 'availability': 'public',
2387 'age_limit': 0,
2388 'release_timestamp': 1637975704,
2389 'upload_date': '20210619',
2390 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2391 'live_status': 'is_live',
2392 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2393 'uploader': '阿鲍Abao',
2394 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2395 'channel': 'Abao in Tokyo',
2396 'channel_follower_count': int,
2397 'release_date': '20211127',
2398 'tags': 'count:39',
2399 'categories': ['People & Blogs'],
2400 'like_count': int,
2401 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2402 'view_count': int,
2403 'playable_in_embed': True,
2404 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2405 'concurrent_view_count': int,
992f9a73 2406 },
2407 'params': {'skip_download': True}
6e634cbe 2408 }, {
2409 # Story. Requires specific player params to work.
ee27297f 2410 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2411 'info_dict': {
ee27297f 2412 'id': 'vv8qTUWmulI',
6e634cbe 2413 'ext': 'mp4',
ee27297f 2414 'availability': 'unlisted',
2415 'view_count': int,
2416 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2417 'upload_date': '20220526',
2418 'categories': ['Education'],
2419 'title': 'Story',
2420 'channel': 'IT\'S HISTORY',
2421 'description': '',
2422 'uploader_id': 'BlastfromthePast',
2423 'duration': 12,
2424 'uploader': 'IT\'S HISTORY',
6e634cbe 2425 'playable_in_embed': True,
6e634cbe 2426 'age_limit': 0,
6e634cbe 2427 'live_status': 'not_live',
ee27297f 2428 'tags': [],
2429 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2430 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2431 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2432 },
2433 'skip': 'stories get removed after some period of time',
ee27297f 2434 }, {
2435 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2436 'info_dict': {
2437 'id': 'tjjjtzRLHvA',
2438 'ext': 'mp4',
2439 'title': 'ハッシュタグ無し };if window.ytcsi',
2440 'upload_date': '20220323',
2441 'like_count': int,
2442 'availability': 'unlisted',
2443 'channel': 'nao20010128nao',
2444 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2445 'age_limit': 0,
2446 'uploader': 'nao20010128nao',
2447 'uploader_id': 'nao20010128nao',
2448 'categories': ['Music'],
6e634cbe 2449 'view_count': int,
2450 'description': '',
ee27297f 2451 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2452 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2453 'live_status': 'not_live',
2454 'playable_in_embed': True,
2455 'channel_follower_count': int,
2456 'duration': 6,
2457 'tags': [],
2458 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2459 }
c26f9b99 2460 }, {
2461 # Prefer primary title+description language metadata by default
2462 # Do not prefer translated description if primary is empty
2463 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2464 'info_dict': {
2465 'id': 'el3E4MbxRqQ',
2466 'ext': 'mp4',
2467 'title': 'dlp test video 2 - primary sv no desc',
2468 'description': '',
2469 'channel': 'cole-dlp-test-acc',
2470 'tags': [],
2471 'view_count': int,
2472 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2473 'like_count': int,
2474 'playable_in_embed': True,
2475 'availability': 'unlisted',
2476 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2477 'age_limit': 0,
2478 'duration': 5,
2479 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2480 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2481 'live_status': 'not_live',
2482 'upload_date': '20220908',
2483 'categories': ['People & Blogs'],
2484 'uploader': 'cole-dlp-test-acc',
2485 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2486 },
2487 'params': {'skip_download': True}
2488 }, {
2489 # Extractor argument: prefer translated title+description
2490 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2491 'info_dict': {
2492 'id': 'gHKT4uU8Zng',
2493 'ext': 'mp4',
2494 'channel': 'cole-dlp-test-acc',
2495 'tags': [],
2496 'duration': 5,
2497 'live_status': 'not_live',
2498 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2499 'upload_date': '20220728',
2500 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2501 'view_count': int,
2502 'categories': ['People & Blogs'],
2503 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2504 'title': 'dlp test video title translated (fr)',
2505 'availability': 'public',
2506 'uploader': 'cole-dlp-test-acc',
2507 'age_limit': 0,
2508 'description': 'dlp test video description translated (fr)',
2509 'playable_in_embed': True,
2510 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2511 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2512 },
2513 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2514 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2515 }, {
2516 'note': '6 channel audio',
2517 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2518 'only_matching': True,
a4894d3e 2519 }, {
2520 'note': 'Multiple HLS formats with same itag',
2521 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2522 'info_dict': {
2523 'id': 'kX3nB4PpJko',
2524 'ext': 'mp4',
2525 'categories': ['Entertainment'],
2526 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
2527 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
2528 'live_status': 'not_live',
2529 'duration': 937,
2530 'channel_follower_count': int,
2531 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2532 'title': 'Last To Take Hand Off Jet, Keeps It!',
2533 'channel': 'MrBeast',
2534 'playable_in_embed': True,
2535 'view_count': int,
2536 'upload_date': '20221112',
2537 'uploader': 'MrBeast',
2538 'uploader_id': 'MrBeast6000',
2539 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2540 'age_limit': 0,
2541 'availability': 'public',
2542 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2543 'like_count': int,
2544 'tags': [],
2545 },
2546 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2547 }, {
2548 'note': 'Audio formats with Dynamic Range Compression',
2549 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2550 'info_dict': {
2551 'id': 'Tq92D6wQ1mg',
2552 'ext': 'weba',
2553 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2554 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2555 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2556 'channel_follower_count': int,
2557 'description': 'md5:17eccca93a786d51bc67646756894066',
2558 'upload_date': '20191228',
2559 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2560 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2561 'playable_in_embed': True,
2562 'like_count': int,
2563 'categories': ['Entertainment'],
2564 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2565 'age_limit': 18,
2566 'channel': 'Projekt Melody',
2567 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2568 'view_count': int,
2569 'availability': 'needs_auth',
2570 'comment_count': int,
2571 'live_status': 'not_live',
2572 'uploader': 'Projekt Melody',
2573 'duration': 106,
2574 },
2575 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2576 },
2577 {
2578 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2579 'info_dict': {
2580 'id': 'qVv6vCqciTM',
2581 'ext': 'mp4',
2582 'age_limit': 0,
2583 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2584 'comment_count': int,
2585 'chapters': 'count:13',
2586 'upload_date': '20221223',
2587 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2588 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2589 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2590 'like_count': int,
2591 'release_date': '20221223',
2592 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2593 '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】',
2594 'view_count': int,
2595 'playable_in_embed': True,
2596 'duration': 4438,
2597 'availability': 'public',
2598 'channel_follower_count': int,
2599 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2600 'categories': ['Entertainment'],
2601 'live_status': 'was_live',
2602 'release_timestamp': 1671793345,
2603 'channel': 'さなちゃんねる',
2604 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2605 'uploader': 'さなちゃんねる',
2606 },
2607 },
2eb88d95
PH
2608 ]
2609
f2e8dbcc 2610 _WEBPAGE_TESTS = [
2611 # YouTube <object> embed
2612 {
2613 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2614 'md5': '873c81d308b979f0e23ee7e620b312a3',
2615 'info_dict': {
2616 'id': 'msN87y-iEx0',
2617 'ext': 'mp4',
2618 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2619 'upload_date': '20080526',
2620 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2621 'uploader': 'Christopher Sykes',
2622 'uploader_id': 'ChristopherJSykes',
2623 'age_limit': 0,
2624 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2625 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2626 'playable_in_embed': True,
2627 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2628 'like_count': int,
2629 'comment_count': int,
2630 'channel': 'Christopher Sykes',
2631 'live_status': 'not_live',
2632 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2633 'availability': 'public',
2634 'duration': 195,
2635 'view_count': int,
2636 'categories': ['Science & Technology'],
2637 'channel_follower_count': int,
2638 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2639 },
2640 'params': {
2641 'skip_download': True,
2642 }
2643 },
2644 ]
2645
201c1459 2646 @classmethod
2647 def suitable(cls, url):
4dfbf869 2648 from ..utils import parse_qs
2649
201c1459 2650 qs = parse_qs(url)
2651 if qs.get('list', [None])[0]:
2652 return False
86e5f3ed 2653 return super().suitable(url)
201c1459 2654
e0df6211 2655 def __init__(self, *args, **kwargs):
86e5f3ed 2656 super().__init__(*args, **kwargs)
545cc85d 2657 self._code_cache = {}
83799698 2658 self._player_cache = {}
e0df6211 2659
4d37720a 2660 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2661 lock = threading.Lock()
185bf310 2662 start_time = time.time()
adbc4ec4
THD
2663 formats = [f for f in formats if f.get('is_from_start')]
2664
185bf310 2665 def refetch_manifest(format_id, delay):
2666 nonlocal formats, start_time, is_live
2667 if time.time() <= start_time + delay:
adbc4ec4
THD
2668 return
2669
2670 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2671 video_details = traverse_obj(
2672 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2673 microformats = traverse_obj(
2674 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2675 expected_type=dict, default=[])
4d37720a
L
2676 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2677 is_live = live_status == 'is_live'
185bf310 2678 start_time = time.time()
adbc4ec4 2679
185bf310 2680 def mpd_feed(format_id, delay):
adbc4ec4
THD
2681 """
2682 @returns (manifest_url, manifest_stream_number, is_live) or None
2683 """
253ac4ba 2684 for retry in self.RetryManager(fatal=False):
2685 with lock:
2686 refetch_manifest(format_id, delay)
2687
2688 f = next((f for f in formats if f['format_id'] == format_id), None)
2689 if not f:
2690 if not is_live:
2691 retry.error = f'{video_id}: Video is no longer live'
2692 else:
2693 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2694 continue
2695 return f['manifest_url'], f['manifest_stream_number'], is_live
2696 return None
adbc4ec4
THD
2697
2698 for f in formats:
4d37720a
L
2699 f['is_live'] = is_live
2700 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2701 live_start_time, mpd_feed, not is_live and f.copy())
2702 if is_live:
2703 f['fragments'] = gen
2704 f['protocol'] = 'http_dash_segments_generator'
2705 else:
2706 f['fragments'] = LazyList(gen({}))
2707 del f['is_from_start']
adbc4ec4 2708
4d37720a 2709 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2710 FETCH_SPAN, MAX_DURATION = 5, 432000
2711
2712 mpd_url, stream_number, is_live = None, None, True
2713
2714 begin_index = 0
2715 download_start_time = ctx.get('start') or time.time()
2716
2717 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2718 if lack_early_segments:
2719 self.report_warning(bug_reports_message(
2720 'Starting download from the last 120 hours of the live stream since '
2721 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2722 lack_early_segments = True
2723
2724 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2725 fragments, fragment_base_url = None, None
2726
a539f065 2727 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2728 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2729 # Obtain from MPD's maximum seq value
2730 old_mpd_url = mpd_url
185bf310 2731 last_error = ctx.pop('last_error', None)
14f25df2 2732 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2733 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2734 or (mpd_url, stream_number, False))
2735 if not refresh_sequence:
2736 if expire_fast and not is_live:
2737 return False, last_seq
2738 elif old_mpd_url == mpd_url:
2739 return True, last_seq
4d37720a
L
2740 if manifestless_orig_fmt:
2741 fmt_info = manifestless_orig_fmt
2742 else:
2743 try:
2744 fmts, _ = self._extract_mpd_formats_and_subtitles(
2745 mpd_url, None, note=False, errnote=False, fatal=False)
2746 except ExtractorError:
2747 fmts = None
2748 if not fmts:
2749 no_fragment_score += 2
2750 return False, last_seq
2751 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2752 fragments = fmt_info['fragments']
2753 fragment_base_url = fmt_info['fragment_base_url']
2754 assert fragment_base_url
2755
2756 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2757 return True, _last_seq
2758
4d37720a 2759 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2760 while is_live:
2761 fetch_time = time.time()
2762 if no_fragment_score > 30:
2763 return
2764 if last_segment_url:
2765 # Obtain from "X-Head-Seqnum" header value from each segment
2766 try:
2767 urlh = self._request_webpage(
2768 last_segment_url, None, note=False, errnote=False, fatal=False)
2769 except ExtractorError:
2770 urlh = None
2771 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2772 if last_seq is None:
a539f065 2773 no_fragment_score += 2
adbc4ec4
THD
2774 last_segment_url = None
2775 continue
2776 else:
a539f065
LNO
2777 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2778 no_fragment_score += 2
185bf310 2779 if not should_continue:
adbc4ec4
THD
2780 continue
2781
2782 if known_idx > last_seq:
2783 last_segment_url = None
2784 continue
2785
2786 last_seq += 1
2787
2788 if begin_index < 0 and known_idx < 0:
2789 # skip from the start when it's negative value
2790 known_idx = last_seq + begin_index
2791 if lack_early_segments:
2792 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2793 try:
2794 for idx in range(known_idx, last_seq):
2795 # do not update sequence here or you'll get skipped some part of it
a539f065 2796 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2797 if not should_continue:
adbc4ec4
THD
2798 known_idx = idx - 1
2799 raise ExtractorError('breaking out of outer loop')
2800 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2801 yield {
2802 'url': last_segment_url,
36195c44 2803 'fragment_count': last_seq,
adbc4ec4
THD
2804 }
2805 if known_idx == last_seq:
2806 no_fragment_score += 5
2807 else:
2808 no_fragment_score = 0
2809 known_idx = last_seq
2810 except ExtractorError:
2811 continue
2812
4d37720a
L
2813 if manifestless_orig_fmt:
2814 # Stop at the first iteration if running for post-live manifestless;
2815 # fragment count no longer increase since it starts
2816 break
2817
adbc4ec4
THD
2818 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2819
b6de707d 2820 def _extract_player_url(self, *ytcfgs, webpage=None):
2821 player_url = traverse_obj(
2822 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2823 get_all=False, expected_type=str)
11f9be09 2824 if not player_url:
b6de707d 2825 return
60f393e4 2826 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2827
b6de707d 2828 def _download_player_url(self, video_id, fatal=False):
2829 res = self._download_webpage(
2830 'https://www.youtube.com/iframe_api',
2831 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2832 if res:
2833 player_version = self._search_regex(
2834 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2835 if player_version:
2836 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2837
60064c53
PH
2838 def _signature_cache_id(self, example_sig):
2839 """ Return a string representation of a signature """
14f25df2 2840 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2841
e40c758c
S
2842 @classmethod
2843 def _extract_player_info(cls, player_url):
2844 for player_re in cls._PLAYER_INFO_RE:
2845 id_m = re.search(player_re, player_url)
2846 if id_m:
2847 break
2848 else:
c081b35c 2849 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2850 return id_m.group('id')
e40c758c 2851
404f611f 2852 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2853 player_id = self._extract_player_info(player_url)
2854 if player_id not in self._code_cache:
1276a43a 2855 code = self._download_webpage(
109dd3b2 2856 player_url, video_id, fatal=fatal,
2857 note='Downloading player ' + player_id,
2858 errnote='Download of %s failed' % player_url)
1276a43a 2859 if code:
2860 self._code_cache[player_id] = code
404f611f 2861 return self._code_cache.get(player_id)
109dd3b2 2862
e40c758c 2863 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2864 player_id = self._extract_player_info(player_url)
e0df6211 2865
c4417ddb 2866 # Read from filesystem cache
86e5f3ed 2867 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2868 assert os.path.basename(func_id) == func_id
a0e07d31 2869
ae61d108 2870 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2871 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2872
580ce007 2873 if not cache_spec:
2874 code = self._load_player(video_id, player_url)
404f611f 2875 if code:
109dd3b2 2876 res = self._parse_sig_js(code)
ac668111 2877 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2878 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2879 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2880
2881 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2882
60064c53 2883 def _print_sig_code(self, func, example_sig):
404f611f 2884 if not self.get_param('youtube_print_sig_code'):
2885 return
2886
edf3e38e
PH
2887 def gen_sig_code(idxs):
2888 def _genslice(start, end, step):
78caa52a 2889 starts = '' if start == 0 else str(start)
8bcc8756 2890 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2891 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2892 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2893
2894 step = None
7af808a5
PH
2895 # Quelch pyflakes warnings - start will be set when step is set
2896 start = '(Never used)'
edf3e38e
PH
2897 for i, prev in zip(idxs[1:], idxs[:-1]):
2898 if step is not None:
2899 if i - prev == step:
2900 continue
2901 yield _genslice(start, prev, step)
2902 step = None
2903 continue
2904 if i - prev in [-1, 1]:
2905 step = i - prev
2906 start = prev
2907 continue
2908 else:
78caa52a 2909 yield 's[%d]' % prev
edf3e38e 2910 if step is None:
78caa52a 2911 yield 's[%d]' % i
edf3e38e
PH
2912 else:
2913 yield _genslice(start, i, step)
2914
ac668111 2915 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2916 cache_res = func(test_string)
edf3e38e 2917 cache_spec = [ord(c) for c in cache_res]
78caa52a 2918 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2919 signature_id_tuple = '(%s)' % (
14f25df2 2920 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2921 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2922 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2923 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2924
e0df6211
PH
2925 def _parse_sig_js(self, jscode):
2926 funcname = self._search_regex(
abefc03f
S
2927 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2928 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
858a65ec
P
2929 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2930 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2931 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
2932 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 2933 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2934 # Obsolete patterns
2935 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2936 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2937 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2938 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2939 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2940 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2941 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2942 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2943 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2944
2945 jsi = JSInterpreter(jscode)
2946 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2947 return lambda s: initial_function([s])
2948
580ce007 2949 def _cached(self, func, *cache_id):
2950 def inner(*args, **kwargs):
2951 if cache_id not in self._player_cache:
2952 try:
2953 self._player_cache[cache_id] = func(*args, **kwargs)
2954 except ExtractorError as e:
2955 self._player_cache[cache_id] = e
2956 except Exception as e:
2957 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2958
2959 ret = self._player_cache[cache_id]
2960 if isinstance(ret, Exception):
2961 raise ret
2962 return ret
2963 return inner
2964
545cc85d 2965 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2966 """Turn the encrypted s field into a working signature"""
580ce007 2967 extract_sig = self._cached(
2968 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2969 func = extract_sig(video_id, player_url, s)
2970 self._print_sig_code(func, s)
2971 return func(s)
404f611f 2972
2973 def _decrypt_nsig(self, s, video_id, player_url):
2974 """Turn the encrypted n field into a working signature"""
2975 if player_url is None:
2976 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2977 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2978
b505e851 2979 try:
2980 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2981 except ExtractorError as e:
2982 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 2983 if self.get_param('youtube_print_sig_code'):
2984 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2985
25836db6 2986 try:
2987 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2988 ret = extract_nsig(jsi, func_code)(s)
2989 except JSInterpreter.Exception as e:
2990 try:
992dc6b4 2991 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2992 except ExtractorError:
2993 raise e
2994 self.report_warning(
2995 f'Native nsig extraction failed: Trying with PhantomJS\n'
2996 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 2997 self.write_debug(e, only_once=True)
25836db6 2998
2999 args, func_body = func_code
3000 ret = jsi.execute(
3001 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3002 video_id=video_id, note='Executing signature code').strip()
580ce007 3003
3004 self.write_debug(f'Decrypted nsig {s} => {ret}')
3005 return ret
3006
90a1df30 3007 def _extract_n_function_name(self, jscode):
3008 funcname, idx = self._search_regex(
3009 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3010 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3011 if not idx:
3012 return funcname
3013
3014 return json.loads(js_to_json(self._search_regex(
3015 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3016 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3017
580ce007 3018 def _extract_n_function_code(self, video_id, player_url):
404f611f 3019 player_id = self._extract_player_info(player_url)
05deb747 3020 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3021 jscode = func_code or self._load_player(video_id, player_url)
3022 jsi = JSInterpreter(jscode)
404f611f 3023
3024 if func_code:
580ce007 3025 return jsi, player_id, func_code
404f611f 3026
b505e851 3027 func_name = self._extract_n_function_name(jscode)
3028
3029 # For redundancy
3030 func_code = self._search_regex(
3031 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3032 # NB: The end of the regex is intentionally kept strict
3033 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3034 jscode, 'nsig function', group=('var', 'code'), default=None)
3035 if func_code:
3036 func_code = ([func_code[0]], func_code[1])
3037 else:
3038 self.write_debug('Extracting nsig function with jsinterp')
3039 func_code = jsi.extract_function_code(func_name)
3040
580ce007 3041 self.cache.store('youtube-nsig', player_id, func_code)
3042 return jsi, player_id, func_code
3043
3044 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3045 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3046
580ce007 3047 def extract_nsig(s):
25836db6 3048 try:
3049 ret = func([s])
3050 except JSInterpreter.Exception:
3051 raise
3052 except Exception as e:
3053 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3054
f6ca640b 3055 if ret.startswith('enhanced_except_'):
25836db6 3056 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3057 return ret
580ce007 3058
3059 return extract_nsig
e0df6211 3060
109dd3b2 3061 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3062 """
3063 Extract signatureTimestamp (sts)
3064 Required to tell API what sig/player version is in use.
3065 """
3066 sts = None
3067 if isinstance(ytcfg, dict):
3068 sts = int_or_none(ytcfg.get('STS'))
3069
3070 if not sts:
3071 # Attempt to extract from player
3072 if player_url is None:
3073 error_msg = 'Cannot extract signature timestamp without player_url.'
3074 if fatal:
3075 raise ExtractorError(error_msg)
3076 self.report_warning(error_msg)
3077 return
404f611f 3078 code = self._load_player(video_id, player_url, fatal=fatal)
3079 if code:
109dd3b2 3080 sts = int_or_none(self._search_regex(
3081 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3082 'JS player signature timestamp', group='sts', fatal=fatal))
3083 return sts
3084
11f9be09 3085 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3086 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3087 label = 'fully ' if is_full else ''
3088 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3089 expected_type=url_or_none)
3090 if not url:
3091 self.report_warning(f'Unable to mark {label}watched')
3092 return
14f25df2 3093 parsed_url = urllib.parse.urlparse(url)
3094 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3095
3096 # cpn generation algorithm is reverse engineered from base.js.
3097 # In fact it works even with dummy cpn.
3098 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3099 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3100
3101 # # more consistent results setting it to right before the end
3102 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3103
3104 qs.update({
3105 'ver': ['2'],
3106 'cpn': [cpn],
3107 'cmt': video_length,
3108 'el': 'detailpage', # otherwise defaults to "shorts"
3109 })
3110
3111 if is_full:
3112 # these seem to mark watchtime "history" in the real world
3113 # they're required, so send in a single value
3114 qs.update({
5318156f 3115 'st': 0,
06cc8f10
B
3116 'et': video_length,
3117 })
3118
14f25df2 3119 url = urllib.parse.urlunparse(
3120 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3121
3122 self._download_webpage(
3123 url, video_id, f'Marking {label}watched',
3124 'Unable to mark watched', fatal=False)
d77ab8e2 3125
bfd973ec 3126 @classmethod
3127 def _extract_from_webpage(cls, url, webpage):
3128 # Invidious Instances
3129 # https://github.com/yt-dlp/yt-dlp/issues/195
3130 # https://github.com/iv-org/invidious/pull/1730
3131 mobj = re.search(
3132 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3133 webpage)
3134 if mobj:
3135 yield cls.url_result(mobj.group('url'), cls)
3136 raise cls.StopExtraction()
3137
3138 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3139
3140 # lazyYT YouTube embed
bfd973ec 3141 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3142 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3143
3144 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3145 for m in re.findall(r'''(?x)<div[^>]+
3146 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3147 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3148 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3149
97665381
PH
3150 @classmethod
3151 def extract_id(cls, url):
ae61d108 3152 video_id = cls.get_temp_id(url)
3153 if not video_id:
3154 raise ExtractorError(f'Invalid URL: {url}')
3155 return video_id
c5e8d7af 3156
7c365c21 3157 def _extract_chapters_from_json(self, data, duration):
3158 chapter_list = traverse_obj(
3159 data, (
3160 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3161 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3162 ), expected_type=list)
3163
3164 return self._extract_chapters(
3165 chapter_list,
3166 chapter_time=lambda chapter: float_or_none(
3167 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3168 chapter_title=lambda chapter: traverse_obj(
3169 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3170 duration=duration)
3171
3172 def _extract_chapters_from_engagement_panel(self, data, duration):
3173 content_list = traverse_obj(
8bdd16b4 3174 data,
7c365c21 3175 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 3176 expected_type=list, default=[])
052e1350 3177 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3178 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3179
1890fc63 3180 return next(filter(None, (
3181 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3182 chapter_time, chapter_title, duration)
3183 for contents in content_list)), [])
7c365c21 3184
1890fc63 3185 def _extract_chapters_from_description(self, description, duration):
2e30b46f 3186 duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
3187 sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
1890fc63 3188 return self._extract_chapters(
2e30b46f 3189 re.findall(sep_re % (duration_re, r'.+?'), description or ''),
1890fc63 3190 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2e30b46f 3191 duration=duration, strict=False) or self._extract_chapters(
3192 re.findall(sep_re % (r'.+?', duration_re), description or ''),
3193 chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
1890fc63 3194 duration=duration, strict=False)
84213ea8 3195
1890fc63 3196 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3197 if not duration:
3198 return
3199 chapter_list = [{
3200 'start_time': chapter_time(chapter),
3201 'title': chapter_title(chapter),
3202 } for chapter in chapter_list or []]
3203 if not strict:
3204 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3205
a3976e07 3206 chapters = [{'start_time': 0}]
1890fc63 3207 for idx, chapter in enumerate(chapter_list):
a3976e07 3208 if chapter['start_time'] is None:
1890fc63 3209 self.report_warning(f'Incomplete chapter {idx}')
3210 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3211 chapters.append(chapter)
709ee214 3212 elif chapter not in chapters:
3213 self.report_warning(
3214 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3215 return chapters[1:]
84213ea8 3216
a1c5d2ca
M
3217 def _extract_comment(self, comment_renderer, parent=None):
3218 comment_id = comment_renderer.get('commentId')
3219 if not comment_id:
3220 return
fe93e2c4 3221
052e1350 3222 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3223
c26f9b99 3224 # Timestamp is an estimate calculated from the current time and time_text
3225 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3226 timestamp = self._parse_time_text(time_text)
3227
052e1350 3228 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3229 author_id = try_get(comment_renderer,
14f25df2 3230 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3231
49bd8c66 3232 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3233 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3234 author_thumbnail = try_get(comment_renderer,
14f25df2 3235 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3236
3237 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3238 is_favorited = 'creatorHeart' in (try_get(
3239 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3240 return {
3241 'id': comment_id,
3242 'text': text,
d92f5d5a 3243 'timestamp': timestamp,
a1c5d2ca
M
3244 'time_text': time_text,
3245 'like_count': votes,
97524332 3246 'is_favorited': is_favorited,
a1c5d2ca
M
3247 'author': author,
3248 'author_id': author_id,
3249 'author_thumbnail': author_thumbnail,
3250 'author_is_uploader': author_is_uploader,
3251 'parent': parent or 'root'
3252 }
3253
46383212 3254 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3255
3256 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3257
3258 def extract_header(contents):
2d6659b9 3259 _continuation = None
3260 for content in contents:
46383212 3261 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3262 expected_comment_count = self._get_count(
3263 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3264
2d6659b9 3265 if expected_comment_count:
46383212 3266 tracker['est_total'] = expected_comment_count
3267 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3268 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3269
3270 sort_menu_item = try_get(
3271 comments_header_renderer,
3272 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3273 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3274
3275 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3276 if not _continuation:
3277 continue
3278
46383212 3279 sort_text = str_or_none(sort_menu_item.get('title'))
3280 if not sort_text:
2d6659b9 3281 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3282 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3283 break
a2160aa4 3284 return _continuation
a1c5d2ca 3285
2d6659b9 3286 def extract_thread(contents):
a1c5d2ca 3287 if not parent:
46383212 3288 tracker['current_page_thread'] = 0
a1c5d2ca 3289 for content in contents:
46383212 3290 if not parent and tracker['total_parent_comments'] >= max_parents:
3291 yield
a1c5d2ca 3292 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3293 comment_renderer = get_first(
3294 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3295 expected_type=dict, default={})
a1c5d2ca 3296
a1c5d2ca
M
3297 comment = self._extract_comment(comment_renderer, parent)
3298 if not comment:
3299 continue
46383212 3300
3301 tracker['running_total'] += 1
3302 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3303 yield comment
46383212 3304
a1c5d2ca
M
3305 # Attempt to get the replies
3306 comment_replies_renderer = try_get(
3307 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3308
3309 if comment_replies_renderer:
46383212 3310 tracker['current_page_thread'] += 1
a1c5d2ca 3311 comment_entries_iter = self._comment_entries(
99e9e001 3312 comment_replies_renderer, ytcfg, video_id,
46383212 3313 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3314 yield from itertools.islice(comment_entries_iter, min(
3315 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3316
46383212 3317 # Keeps track of counts across recursive calls
3318 if not tracker:
3319 tracker = dict(
3320 running_total=0,
3321 est_total=0,
3322 current_page_thread=0,
3323 total_parent_comments=0,
3324 total_reply_comments=0)
3325
3326 # TODO: Deprecated
2d6659b9 3327 # YouTube comments have a max depth of 2
46383212 3328 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3329 if max_depth:
da4db748 3330 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3331 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3332 if max_depth == 1 and parent:
3333 return
a1c5d2ca 3334
46383212 3335 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3336 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3337
46383212 3338 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3339
46383212 3340 response = None
6e634cbe 3341 is_forced_continuation = False
2d6659b9 3342 is_first_continuation = parent is None
6e634cbe 3343 if is_first_continuation and not continuation:
3344 # Sometimes you can get comments by generating the continuation yourself,
3345 # even if YouTube initially reports them being disabled - e.g. stories comments.
3346 # Note: if the comment section is actually disabled, YouTube may return a response with
3347 # required check_get_keys missing. So we will disable that check initially in this case.
3348 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3349 is_forced_continuation = True
a1c5d2ca
M
3350
3351 for page_num in itertools.count(0):
3352 if not continuation:
3353 break
46383212 3354 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3355 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3356 if page_num == 0:
3357 if is_first_continuation:
3358 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3359 else:
2d6659b9 3360 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3361 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3362 else:
3363 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3364 ' ' if parent else '', ' replies' if parent else '',
3365 page_num, comment_prog_str)
e72e48c5
M
3366 try:
3367 response = self._extract_response(
3368 item_id=None, query=continuation,
3369 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3370 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3371 except ExtractorError as e:
3372 # Ignore incomplete data error for replies if retries didn't work.
3373 # This is to allow any other parent comments and comment threads to be downloaded.
3374 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3375 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3376 self.report_warning(
3377 'Received incomplete data for a comment reply thread and retrying did not help. '
3378 'Ignoring to let other comments be downloaded.')
3379 else:
3380 raise
6e634cbe 3381 is_forced_continuation = False
46383212 3382 continuation_contents = traverse_obj(
3383 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3384
2d6659b9 3385 continuation = None
46383212 3386 for continuation_section in continuation_contents:
3387 continuation_items = traverse_obj(
3388 continuation_section,
3389 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3390 get_all=False, expected_type=list) or []
3391 if is_first_continuation:
3392 continuation = extract_header(continuation_items)
3393 is_first_continuation = False
2d6659b9 3394 if continuation:
a1c5d2ca 3395 break
46383212 3396 continue
a1c5d2ca 3397
46383212 3398 for entry in extract_thread(continuation_items):
3399 if not entry:
3400 return
3401 yield entry
3402 continuation = self._extract_continuation({'contents': continuation_items})
3403 if continuation:
2d6659b9 3404 break
a1c5d2ca 3405
6e634cbe 3406 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3407 if message and not parent and tracker['running_total'] == 0:
3408 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3409 raise self.CommentsDisabled
6e634cbe 3410
3411 @staticmethod
3412 def _generate_comment_continuation(video_id):
3413 """
3414 Generates initial comment section continuation token from given video id
3415 """
3416 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3417 return base64.b64encode(token.encode()).decode()
3418
a2160aa4 3419 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3420 """Entry for comment extraction"""
2d6659b9 3421 def _real_comment_extract(contents):
aae16f6e 3422 renderer = next((
3423 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3424 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3425 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3426
a2160aa4 3427 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3428 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3429
109dd3b2 3430 @staticmethod
99e9e001 3431 def _get_checkok_params():
3432 return {'contentCheckOk': True, 'racyCheckOk': True}
3433
3434 @classmethod
3435 def _generate_player_context(cls, sts=None):
109dd3b2 3436 context = {
3437 'html5Preference': 'HTML5_PREF_WANTS',
3438 }
3439 if sts is not None:
3440 context['signatureTimestamp'] = sts
3441 return {
3442 'playbackContext': {
3443 'contentPlaybackContext': context
a1a7907b 3444 },
99e9e001 3445 **cls._get_checkok_params()
109dd3b2 3446 }
3447
e7e94f2a
D
3448 @staticmethod
3449 def _is_agegated(player_response):
3450 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3451 return True
e7e94f2a
D
3452
3453 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3454 AGE_GATE_REASONS = (
3455 'confirm your age', 'age-restricted', 'inappropriate', # reason
3456 'age_verification_required', 'age_check_required', # status
3457 )
3458 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3459
3460 @staticmethod
3461 def _is_unplayable(player_response):
3462 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3463
50ac0e54 3464 _STORY_PLAYER_PARAMS = '8AEB'
3465
3466 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3467
11f9be09 3468 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3469 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3470 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3471 headers = self.generate_api_headers(
99e9e001 3472 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3473
6e634cbe 3474 yt_query = {
3475 'videoId': video_id,
6e634cbe 3476 }
50ac0e54 3477 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3478 yt_query['params'] = self._STORY_PLAYER_PARAMS
3479
11f9be09 3480 yt_query.update(self._generate_player_context(sts))
3481 return self._extract_response(
3482 item_id=video_id, ep='player', query=yt_query,
379e44ed 3483 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3484 default_client=client,
11f9be09 3485 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3486 ) or None
3487
11f9be09 3488 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3489 requested_clients = []
d0d012d4 3490 default = ['android', 'web']
000c15a4 3491 allowed_clients = sorted(
86e5f3ed 3492 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3493 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3494 for client in self._configuration_arg('player_client'):
3495 if client in allowed_clients:
3496 requested_clients.append(client)
d0d012d4 3497 elif client == 'default':
3498 requested_clients.extend(default)
b4c055ba 3499 elif client == 'all':
3500 requested_clients.extend(allowed_clients)
3501 else:
3502 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3503 if not requested_clients:
d0d012d4 3504 requested_clients = default
cf7e015f 3505
11f9be09 3506 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3507 requested_clients.extend(
e7e94f2a 3508 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3509
11f9be09 3510 return orderedSet(requested_clients)
cf7e015f 3511
50ac0e54 3512 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3513 initial_pr = None
3514 if webpage:
b7c47b74 3515 initial_pr = self._search_json(
3516 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3517
ae729626 3518 all_clients = set(clients)
c0bc527b 3519 clients = clients[::-1]
b6de707d 3520 prs = []
e7e94f2a 3521
ae729626 3522 def append_client(*client_names):
e7870111 3523 """ Append the first client name that exists but not already used """
ae729626 3524 for client_name in client_names:
e7870111
D
3525 actual_client = _split_innertube_client(client_name)[0]
3526 if actual_client in INNERTUBE_CLIENTS:
3527 if actual_client not in all_clients:
ae729626 3528 clients.append(client_name)
e7870111
D
3529 all_clients.add(actual_client)
3530 return
e7e94f2a 3531
379e44ed 3532 # Android player_response does not have microFormats which are needed for
3533 # extraction of some data. So we return the initial_pr with formats
3534 # stripped out even if not requested by the user
3535 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3536 if initial_pr:
3537 pr = dict(initial_pr)
3538 pr['streamingData'] = None
b6de707d 3539 prs.append(pr)
379e44ed 3540
3541 last_error = None
b6de707d 3542 tried_iframe_fallback = False
3543 player_url = None
c0bc527b 3544 while clients:
e7870111 3545 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3546 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3547 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3548 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3549
b6de707d 3550 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3551 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3552 if 'js' in self._configuration_arg('player_skip'):
3553 require_js_player = False
3554 player_url = None
3555
3556 if not player_url and not tried_iframe_fallback and require_js_player:
3557 player_url = self._download_player_url(video_id)
3558 tried_iframe_fallback = True
3559
379e44ed 3560 try:
3561 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3562 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3563 except ExtractorError as e:
3564 if last_error:
3565 self.report_warning(last_error)
3566 last_error = e
3567 continue
3568
11f9be09 3569 if pr:
a3e96421 3570 # YouTube may return a different video player response than expected.
3571 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3572 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3573 if pr_video_id and pr_video_id != video_id:
3574 self.report_warning(
c7dcf0b3 3575 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3576 else:
3577 prs.append(pr)
c0bc527b 3578
e7e94f2a 3579 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3580 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3581 append_client(f'{base_client}_creator')
e7e94f2a 3582 elif self._is_agegated(pr):
e7870111
D
3583 if variant == 'tv_embedded':
3584 append_client(f'{base_client}_embedded')
3585 elif not variant:
3586 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3587
379e44ed 3588 if last_error:
b6de707d 3589 if not len(prs):
379e44ed 3590 raise last_error
3591 self.report_warning(last_error)
b6de707d 3592 return prs, player_url
11f9be09 3593
4d37720a
L
3594 def _needs_live_processing(self, live_status, duration):
3595 if (live_status == 'is_live' and self.get_param('live_from_start')
3596 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3597 return live_status
3598
3599 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a4894d3e 3600 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3601 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3602 q = qualities([
2a9c6dcd 3603 # Normally tiny is the smallest video-only formats. But
3604 # audio-only formats with unknown quality may get tagged as tiny
3605 'tiny',
3606 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3607 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3608 ])
11f9be09 3609 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3610
545cc85d 3611 for fmt in streaming_formats:
727029c5 3612 if fmt.get('targetDurationSec'):
545cc85d 3613 continue
321bf820 3614
cc2db878 3615 itag = str_or_none(fmt.get('itag'))
9297939e 3616 audio_track = fmt.get('audioTrack') or {}
9bb85699 3617 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
9297939e 3618 if stream_id in stream_ids:
3619 continue
3620
cc2db878 3621 quality = fmt.get('quality')
2a9c6dcd 3622 height = int_or_none(fmt.get('height'))
d3fc8074 3623 if quality == 'tiny' or not quality:
3624 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3625 # The 3gp format (17) in android client has a quality of "small",
3626 # but is actually worse than other formats
3627 if itag == '17':
3628 quality = 'tiny'
3629 if quality:
3630 if itag:
3631 itag_qualities[itag] = quality
3632 if height:
3633 res_qualities[height] = quality
cc2db878 3634 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3635 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3636 # number of fragment that would subsequently requested with (`&sq=N`)
3637 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3638 continue
3639
545cc85d 3640 fmt_url = fmt.get('url')
3641 if not fmt_url:
14f25df2 3642 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3643 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3644 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3645 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3646 continue
52023f12 3647 try:
3648 fmt_url += '&%s=%s' % (
3649 traverse_obj(sc, ('sp', -1)) or 'signature',
3650 self._decrypt_signature(encrypted_sig, video_id, player_url)
3651 )
3652 except ExtractorError as e:
580ce007 3653 self.report_warning('Signature extraction failed: Some formats may be missing',
3654 video_id=video_id, only_once=True)
52023f12 3655 self.write_debug(e, only_once=True)
201e9eaa 3656 continue
545cc85d 3657
404f611f 3658 query = parse_qs(fmt_url)
3659 throttled = False
b2916526 3660 if query.get('n'):
404f611f 3661 try:
580ce007 3662 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3663 fmt_url = update_url_query(fmt_url, {
580ce007 3664 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3665 })
404f611f 3666 except ExtractorError as e:
25836db6 3667 phantomjs_hint = ''
3668 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3669 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3670 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3671 if player_url:
3672 self.report_warning(
3673 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3674 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3675 self.write_debug(e, only_once=True)
3676 else:
3677 self.report_warning(
3678 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3679 video_id=video_id, only_once=True)
404f611f 3680 throttled = True
3681
0ad92dfb 3682 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3683 language_preference = (
3684 10 if audio_track.get('audioIsDefault') and 10
3685 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3686 else -1)
0ad92dfb 3687 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3688 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3689 # Make sure to avoid false positives with small duration differences.
62b58c09 3690 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3691 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3692 if is_damaged:
0f06bcd7 3693 self.report_warning(
3694 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3695 dct = {
3696 'asr': int_or_none(fmt.get('audioSampleRate')),
3697 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3698 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3699 'format_note': join_nonempty(
26e8e044 3700 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3701 ' (default)' if language_preference > 0 else ''),
404f611f 3702 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
9bb85699 3703 'DRC' if fmt.get('isDrc') else None,
a4166234 3704 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3705 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3706 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3707 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3708 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3709 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3710 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3711 'height': height,
9bb85699 3712 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3713 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3714 'tbr': tbr,
545cc85d 3715 'url': fmt_url,
2a9c6dcd 3716 'width': int_or_none(fmt.get('width')),
ab6df717 3717 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3718 'desc' if language_preference < -1 else '') or None,
ab6df717 3719 'language_preference': language_preference,
a405b38f 3720 # Strictly de-prioritize damaged and 3gp formats
3721 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3722 }
60bdb7bd 3723 mime_mobj = re.match(
3724 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3725 if mime_mobj:
3726 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3727 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3728 no_audio = dct.get('acodec') == 'none'
3729 no_video = dct.get('vcodec') == 'none'
3730 if no_audio:
3731 dct['vbr'] = tbr
3732 if no_video:
3733 dct['abr'] = tbr
3734 if no_audio or no_video:
545cc85d 3735 dct['downloader_options'] = {
3736 # Youtube throttles chunks >~10M
3737 'http_chunk_size': 10485760,
bf1317d2 3738 }
7c60c33e 3739 if dct.get('ext'):
3740 dct['container'] = dct['ext'] + '_dash'
a4894d3e 3741
3742 if itag:
3743 itags[itag].add(('https', dct.get('language')))
3744 stream_ids.append(stream_id)
11f9be09 3745 yield dct
545cc85d 3746
4d37720a
L
3747 needs_live_processing = self._needs_live_processing(live_status, duration)
3748 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3749
3750 skip_manifests = set(self._configuration_arg('skip'))
3751 if (not self.get_param('youtube_include_hls_manifest', True)
3752 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3753 or needs_live_processing and skip_bad_formats):
3754 skip_manifests.add('hls')
3755
0f06bcd7 3756 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3757 skip_manifests.add('dash')
3758 if self._configuration_arg('include_live_dash'):
3759 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3760 'Use include_incomplete_formats extractor argument instead')
3761 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3762 skip_manifests.add('dash')
5d3a0e79 3763
a0bb6ce5 3764 def process_manifest_format(f, proto, itag):
a4894d3e 3765 key = (proto, f.get('language'))
3766 if key in itags[itag]:
3767 return False
3768 itags[itag].add(key)
3769
3770 if any(p != proto for p, _ in itags[itag]):
3771 f['format_id'] = f'{itag}-{proto}'
3772 elif itag:
a0bb6ce5 3773 f['format_id'] = itag
a0bb6ce5 3774
b25cac65 3775 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3776 if f['quality'] == -1 and f.get('height'):
3777 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3778 return True
2a9c6dcd 3779
c646d76f 3780 subtitles = {}
11f9be09 3781 for sd in streaming_data:
4d37720a 3782 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3783 if hls_manifest_url:
4d37720a
L
3784 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3785 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3786 subtitles = self._merge_subtitles(subs, subtitles)
3787 for f in fmts:
a0bb6ce5 3788 if process_manifest_format(f, 'hls', self._search_regex(
3789 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3790 yield f
545cc85d 3791
4d37720a 3792 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3793 if dash_manifest_url:
c646d76f 3794 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3795 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3796 for f in formats:
a0bb6ce5 3797 if process_manifest_format(f, 'dash', f['format_id']):
3798 f['filesize'] = int_or_none(self._search_regex(
3799 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3800 if needs_live_processing:
adbc4ec4
THD
3801 f['is_from_start'] = True
3802
a0bb6ce5 3803 yield f
c646d76f 3804 yield subtitles
11f9be09 3805
720c3099 3806 def _extract_storyboard(self, player_responses, duration):
3807 spec = get_first(
3808 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3809 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3810 if not base_url:
720c3099 3811 return
720c3099 3812 L = len(spec) - 1
3813 for i, args in enumerate(spec):
3814 args = args.split('#')
3815 counts = list(map(int_or_none, args[:5]))
3816 if len(args) != 8 or not all(counts):
3817 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3818 continue
3819 width, height, frame_count, cols, rows = counts
3820 N, sigh = args[6:]
3821
3822 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3823 fragment_count = frame_count / (cols * rows)
3824 fragment_duration = duration / fragment_count
3825 yield {
3826 'format_id': f'sb{i}',
3827 'format_note': 'storyboard',
3828 'ext': 'mhtml',
3829 'protocol': 'mhtml',
3830 'acodec': 'none',
3831 'vcodec': 'none',
3832 'url': url,
3833 'width': width,
3834 'height': height,
45e8a04e 3835 'fps': frame_count / duration,
3836 'rows': rows,
3837 'columns': cols,
720c3099 3838 'fragments': [{
b3edc806 3839 'url': url.replace('$M', str(j)),
720c3099 3840 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3841 } for j in range(math.ceil(fragment_count))],
3842 }
3843
adbc4ec4 3844 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3845 webpage = None
3846 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3847 query = {'bpctr': '9999999999', 'has_verified': '1'}
3848 if smuggled_data.get('is_story'):
3849 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3850 webpage = self._download_webpage(
50ac0e54 3851 webpage_url, video_id, fatal=False, query=query)
11f9be09 3852
3853 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3854
b6de707d 3855 player_responses, player_url = self._extract_player_responses(
11f9be09 3856 self._get_requested_clients(url, smuggled_data),
50ac0e54 3857 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3858
adbc4ec4
THD
3859 return webpage, master_ytcfg, player_responses, player_url
3860
a1b2d843 3861 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3862 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3863 is_live = get_first(video_details, 'isLive')
3864 if is_live is None:
3865 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3866 live_content = get_first(video_details, 'isLiveContent')
3867 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3868 post_live = get_first(video_details, 'isPostLiveDvr')
3869 live_status = ('post_live' if post_live
3870 else 'is_live' if is_live
3871 else 'is_upcoming' if is_upcoming
6678a4f0 3872 else 'was_live' if live_content
3873 else 'not_live' if False in (is_live, live_content)
3874 else None)
adbc4ec4 3875 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3876 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3877
4d37720a 3878 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3879
3880 def _real_extract(self, url):
3881 url, smuggled_data = unsmuggle_url(url, {})
3882 video_id = self._match_id(url)
3883
3884 base_url = self.http_scheme() + '//www.youtube.com/'
3885 webpage_url = base_url + 'watch?v=' + video_id
3886
3887 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3888
11f9be09 3889 playability_statuses = traverse_obj(
3890 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3891
3892 trailer_video_id = get_first(
3893 playability_statuses,
3894 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3895 expected_type=str)
3896 if trailer_video_id:
3897 return self.url_result(
3898 trailer_video_id, self.ie_key(), trailer_video_id)
3899
3900 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3901 if webpage else (lambda x: None))
3902
3903 video_details = traverse_obj(
3904 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3905 microformats = traverse_obj(
3906 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3907 expected_type=dict, default=[])
c26f9b99 3908
3909 translated_title = self._get_text(microformats, (..., 'title'))
3910 video_title = (self._preferred_lang and translated_title
3911 or get_first(video_details, 'title') # primary
3912 or translated_title
3913 or search_meta(['og:title', 'twitter:title', 'title']))
3914 translated_description = self._get_text(microformats, (..., 'description'))
3915 original_description = get_first(video_details, 'shortDescription')
3916 video_description = (
3917 self._preferred_lang and translated_description
3918 # If original description is blank, it will be an empty string.
3919 # Do not prefer translated description in this case.
3920 or original_description if original_description is not None else translated_description)
11f9be09 3921
d89257f3 3922 multifeed_metadata_list = get_first(
3923 player_responses,
3924 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3925 expected_type=str)
3926 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3927 if self.get_param('noplaylist'):
11f9be09 3928 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3929 else:
3930 entries = []
3931 feed_ids = []
3932 for feed in multifeed_metadata_list.split(','):
3933 # Unquote should take place before split on comma (,) since textual
3934 # fields may contain comma as well (see
3935 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3936 feed_data = urllib.parse.parse_qs(
ac668111 3937 urllib.parse.unquote_plus(feed))
d89257f3 3938
3939 def feed_entry(name):
3940 return try_get(
14f25df2 3941 feed_data, lambda x: x[name][0], str)
d89257f3 3942
3943 feed_id = feed_entry('id')
3944 if not feed_id:
3945 continue
3946 feed_title = feed_entry('title')
3947 title = video_title
3948 if feed_title:
3949 title += ' (%s)' % feed_title
3950 entries.append({
3951 '_type': 'url_transparent',
3952 'ie_key': 'Youtube',
3953 'url': smuggle_url(
3954 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3955 {'force_singlefeed': True}),
3956 'title': title,
3957 })
3958 feed_ids.append(feed_id)
3959 self.to_screen(
3960 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3961 % (', '.join(feed_ids), video_id))
3962 return self.playlist_result(
3963 entries, video_id, video_title, video_description)
11f9be09 3964
9da6612b 3965 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
3966 or int_or_none(get_first(microformats, 'lengthSeconds'))
3967 or parse_duration(search_meta('duration')) or None)
a1b2d843 3968
4d37720a
L
3969 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3970 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3971 if live_status == 'post_live':
3972 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3973
545cc85d 3974 if not formats:
11f9be09 3975 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3976 self.report_drm(video_id)
11f9be09 3977 pemr = get_first(
3978 playability_statuses,
3979 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3980 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3981 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3982 if subreason:
545cc85d 3983 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3984 countries = get_first(microformats, 'availableCountries')
545cc85d 3985 if not countries:
3986 regions_allowed = search_meta('regionsAllowed')
3987 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3988 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3989 reason += f'. {subreason}'
545cc85d 3990 if reason:
b7da73eb 3991 self.raise_no_formats(reason, expected=True)
bf1317d2 3992
11f9be09 3993 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3994 if not keywords and webpage:
3995 keywords = [
3996 unescapeHTML(m.group('content'))
3997 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3998 for keyword in keywords:
3999 if keyword.startswith('yt:stretch='):
201c1459 4000 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4001 if mobj:
4002 # NB: float is intentional for forcing float division
4003 w, h = (float(v) for v in mobj.groups())
4004 if w > 0 and h > 0:
4005 ratio = w / h
4006 for f in formats:
4007 if f.get('vcodec') != 'none':
4008 f['stretched_ratio'] = ratio
4009 break
a709d873 4010 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4011 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4012 if thumbnail_url:
4013 thumbnails.append({
4014 'url': thumbnail_url,
ff2751ac 4015 })
fccf5021 4016 original_thumbnails = thumbnails.copy()
4017
0ba692ac 4018 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4019 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4020 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4021 thumbnail_names = [
962ffcf8 4022 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4023 # in resolution, these are not the custom thumbnail. So de-prioritize them
4024 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4025 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4026 ]
cca80fe6 4027 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4028 thumbnails.extend({
4029 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4030 video_id=video_id, name=name, ext=ext,
4d37720a 4031 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4032 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4033 for thumb in thumbnails:
cca80fe6 4034 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4035 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4036 self._remove_duplicate_formats(thumbnails)
fccf5021 4037 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4038
7ea65411 4039 category = get_first(microformats, 'category') or search_meta('genre')
4040 channel_id = str_or_none(
4041 get_first(video_details, 'channelId')
4042 or get_first(microformats, 'externalChannelId')
4043 or search_meta('channelId'))
7ea65411 4044 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4045
adbc4ec4
THD
4046 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4047 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4048 if not duration and live_end_time and live_start_time:
4049 duration = live_end_time - live_start_time
4050
4d37720a
L
4051 needs_live_processing = self._needs_live_processing(live_status, duration)
4052
4053 def is_bad_format(fmt):
4054 if needs_live_processing and not fmt.get('is_from_start'):
4055 return True
4056 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4057 and fmt.get('protocol') == 'http_dash_segments'):
4058 return True
4059
4060 for fmt in filter(is_bad_format, formats):
4061 fmt['preference'] = (fmt.get('preference') or -1) - 10
4062 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4063
4064 if needs_live_processing:
4065 self._prepare_live_from_start_formats(
4066 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4067
720c3099 4068 formats.extend(self._extract_storyboard(player_responses, duration))
4069
545cc85d 4070 info = {
4071 'id': video_id,
39ca3b5c 4072 'title': video_title,
545cc85d 4073 'formats': formats,
4074 'thumbnails': thumbnails,
fccf5021 4075 # The best thumbnail that we are sure exists. Prevents unnecessary
4076 # URL checking if user don't care about getting the best possible thumbnail
4077 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4078 'description': video_description,
11f9be09 4079 'uploader': get_first(video_details, 'author'),
545cc85d 4080 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
4081 'uploader_url': owner_profile_url,
4082 'channel_id': channel_id,
a70635b8 4083 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 4084 'duration': duration,
4085 'view_count': int_or_none(
11f9be09 4086 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4087 or search_meta('interactionCount')),
11f9be09 4088 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4089 'age_limit': 18 if (
11f9be09 4090 get_first(microformats, 'isFamilySafe') is False
545cc85d 4091 or search_meta('isFamilyFriendly') == 'false'
4092 or search_meta('og:restrictions:age') == '18+') else 0,
4093 'webpage_url': webpage_url,
4094 'categories': [category] if category else None,
4095 'tags': keywords,
11f9be09 4096 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4097 'live_status': live_status,
adbc4ec4 4098 'release_timestamp': live_start_time,
9f14daf2 4099 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4100 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4101 }
b477fc13 4102
c646d76f 4103 subtitles = {}
3944e7af 4104 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4105 if pctr:
ecdc9049 4106 def get_lang_code(track):
4107 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4108 or track.get('languageCode'))
4109
4110 # Converted into dicts to remove duplicates
4111 captions = {
4112 get_lang_code(sub): sub
4113 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
4114 translation_languages = {
4115 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4116 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
4117
774d79cc 4118 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4119 lang_subs = container.setdefault(lang_code, [])
545cc85d 4120 for fmt in self._SUBTITLE_FORMATS:
4121 query.update({
4122 'fmt': fmt,
4123 })
4124 lang_subs.append({
4125 'ext': fmt,
60f393e4 4126 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4127 'name': sub_name,
545cc85d 4128 })
7e72694b 4129
07b47084 4130 # NB: Constructing the full subtitle dictionary is slow
4131 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4132 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4133 for lang_code, caption_track in captions.items():
4134 base_url = caption_track.get('baseUrl')
1235d333 4135 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4136 if not base_url:
4137 continue
ecdc9049 4138 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4139 if caption_track.get('kind') != 'asr':
545cc85d 4140 if not lang_code:
4141 continue
4142 process_language(
ecdc9049 4143 subtitles, base_url, lang_code, lang_name, {})
4144 if not caption_track.get('isTranslatable'):
4145 continue
3944e7af 4146 for trans_code, trans_name in translation_languages.items():
4147 if not trans_code:
545cc85d 4148 continue
1235d333 4149 orig_trans_code = trans_code
71eb82d1 4150 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4151 if not get_translated_subs:
18e49408 4152 continue
ecdc9049 4153 trans_code += f'-{lang_code}'
a70635b8 4154 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 4155 # Add an "-orig" label to the original language so that it can be distinguished.
4156 # The subs are returned without "-orig" as well for compatibility
1235d333 4157 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 4158 process_language(
d49669ac 4159 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4160 # Setting tlang=lang returns damaged subtitles.
d49669ac 4161 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4162 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4163
4164 info['automatic_captions'] = automatic_captions
4165 info['subtitles'] = subtitles
7e72694b 4166
14f25df2 4167 parsed_url = urllib.parse.urlparse(url)
545cc85d 4168 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4169 query = urllib.parse.parse_qs(component)
545cc85d 4170 for k, v in query.items():
4171 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4172 d_k += '_time'
4173 if d_k not in info and k in s_ks:
4174 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4175
4176 # Youtube Music Auto-generated description
822b9d9c 4177 if video_description:
1890fc63 4178 mobj = re.search(
4179 r'''(?xs)
4180 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4181 (?P<album>[^\n]+)
4182 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4183 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4184 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4185 .+\nAuto-generated\ by\ YouTube\.\s*$
4186 ''', video_description)
822b9d9c 4187 if mobj:
822b9d9c
RA
4188 release_year = mobj.group('release_year')
4189 release_date = mobj.group('release_date')
4190 if release_date:
4191 release_date = release_date.replace('-', '')
4192 if not release_year:
545cc85d 4193 release_year = release_date[:4]
4194 info.update({
4195 'album': mobj.group('album'.strip()),
4196 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4197 'track': mobj.group('track').strip(),
4198 'release_date': release_date,
cc2db878 4199 'release_year': int_or_none(release_year),
545cc85d 4200 })
7e72694b 4201
545cc85d 4202 initial_data = None
4203 if webpage:
56ba69e4 4204 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4205 if not initial_data:
99e9e001 4206 query = {'videoId': video_id}
4207 query.update(self._get_checkok_params())
109dd3b2 4208 initial_data = self._extract_response(
4209 item_id=video_id, ep='next', fatal=False,
99e9e001 4210 ytcfg=master_ytcfg, query=query,
4211 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4212 note='Downloading initial data API JSON')
545cc85d 4213
0df111a3 4214 info['comment_count'] = traverse_obj(initial_data, (
4215 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4216 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4217 ), (
4218 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4219 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4220 ), expected_type=int_or_none, get_all=False)
4221
19a03940 4222 try: # This will error if there is no livechat
c60ee3a2 4223 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4224 except (KeyError, IndexError, TypeError):
4225 pass
4226 else:
ecdc9049 4227 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4228 # url is needed to set cookies
4229 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4230 'video_id': video_id,
4231 'ext': 'json',
4d37720a
L
4232 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4233 else 'youtube_live_chat_replay'),
c60ee3a2 4234 }]
545cc85d 4235
4236 if initial_data:
7c365c21 4237 info['chapters'] = (
4238 self._extract_chapters_from_json(initial_data, duration)
4239 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4240 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4241 or None)
545cc85d 4242
17322130 4243 contents = traverse_obj(
4244 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4245 expected_type=list, default=[])
4246
4247 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4248 if vpir:
4249 stl = vpir.get('superTitleLink')
4250 if stl:
4251 stl = self._get_text(stl)
4252 if try_get(
4253 vpir,
4254 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4255 info['location'] = stl
4256 else:
affc4fef 4257 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4258 if mobj:
545cc85d 4259 info.update({
17322130 4260 'series': mobj.group(1),
4261 'season_number': int(mobj.group(2)),
4262 'episode_number': int(mobj.group(3)),
545cc85d 4263 })
17322130 4264 for tlb in (try_get(
4265 vpir,
4266 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4267 list) or []):
3ffb2f5b 4268 tbrs = variadic(
4269 traverse_obj(
4270 tlb, 'toggleButtonRenderer',
4271 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4272 default=[]))
4273 for tbr in tbrs:
4274 for getter, regex in [(
4275 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4276 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4277 lambda x: x['accessibility'],
4278 lambda x: x['accessibilityData']['accessibilityData'],
4279 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4280 label = (try_get(tbr, getter, dict) or {}).get('label')
4281 if label:
4282 mobj = re.match(regex, label)
4283 if mobj:
4284 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4285 break
17322130 4286 sbr_tooltip = try_get(
4287 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4288 if sbr_tooltip:
4289 like_count, dislike_count = sbr_tooltip.split(' / ')
4290 info.update({
4291 'like_count': str_to_int(like_count),
4292 'dislike_count': str_to_int(dislike_count),
4293 })
867c66ff
M
4294 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4295 if vcr:
4296 vc = self._get_count(vcr, 'viewCount')
4297 # Upcoming premieres with waiting count are treated as live here
4298 if vcr.get('isLive'):
4299 info['concurrent_view_count'] = vc
4300 elif info.get('view_count') is None:
4301 info['view_count'] = vc
4302
17322130 4303 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4304 if vsir:
4305 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4306 info.update({
4307 'channel': self._get_text(vor, 'title'),
4308 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4309
4310 rows = try_get(
4311 vsir,
4312 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4313 list) or []
4314 multiple_songs = False
4315 for row in rows:
4316 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4317 multiple_songs = True
4318 break
4319 for row in rows:
4320 mrr = row.get('metadataRowRenderer') or {}
4321 mrr_title = mrr.get('title')
4322 if not mrr_title:
4323 continue
4324 mrr_title = self._get_text(mrr, 'title')
4325 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4326 if mrr_title == 'License':
4327 info['license'] = mrr_contents_text
4328 elif not multiple_songs:
4329 if mrr_title == 'Album':
4330 info['album'] = mrr_contents_text
4331 elif mrr_title == 'Artist':
4332 info['artist'] = mrr_contents_text
4333 elif mrr_title == 'Song':
4334 info['track'] = mrr_contents_text
545cc85d 4335
4336 fallbacks = {
4337 'channel': 'uploader',
4338 'channel_id': 'uploader_id',
4339 'channel_url': 'uploader_url',
4340 }
992f9a73 4341
17322130 4342 # The upload date for scheduled, live and past live streams / premieres in microformats
4343 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4344 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4345 upload_date = (
4346 unified_strdate(get_first(microformats, 'uploadDate'))
4347 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4348 if not upload_date or (
4d37720a 4349 live_status in ('not_live', None)
1ff88b7a 4350 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4351 ):
c26f9b99 4352 upload_date = strftime_or_none(
4353 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4354 info['upload_date'] = upload_date
992f9a73 4355
545cc85d 4356 for to, frm in fallbacks.items():
4357 if not info.get(to):
4358 info[to] = info.get(frm)
4359
4360 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4361 v = info.get(s_k)
4362 if v:
4363 info[d_k] = v
b84071c0 4364
c26f9b99 4365 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4366
4367 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4368 or get_first(video_details, 'isPrivate', expected_type=bool))
4369
4370 info['availability'] = (
4371 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4372 else self._availability(
4373 is_private=is_private,
4374 needs_premium=(
4375 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4376 or False if initial_data and is_private is not None else None),
4377 needs_subscription=(
4378 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4379 or False if initial_data and is_private is not None else None),
4380 needs_auth=info['age_limit'] >= 18,
4381 is_unlisted=None if is_private is None else (
4382 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4383 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4384
a2160aa4 4385 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4386
11f9be09 4387 self.mark_watched(video_id, player_responses)
d77ab8e2 4388
545cc85d 4389 return info
c5e8d7af 4390
a61fd4cf 4391
a6213a49 4392class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4393 @staticmethod
4394 def passthrough_smuggled_data(func):
bd7e919a 4395 def _smuggle(info, smuggled_data):
4396 if info.get('_type') not in ('url', 'url_transparent'):
4397 return info
4398 if smuggled_data.get('is_music_url'):
4399 parsed_url = urllib.parse.urlparse(info['url'])
4400 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4401 smuggled_data.pop('is_music_url')
4402 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4403 if smuggled_data:
4404 info['url'] = smuggle_url(info['url'], smuggled_data)
4405 return info
182bda88 4406
4407 @functools.wraps(func)
4408 def wrapper(self, url):
4409 url, smuggled_data = unsmuggle_url(url, {})
4410 if self.is_music_url(url):
4411 smuggled_data['is_music_url'] = True
4412 info_dict = func(self, url, smuggled_data)
bd7e919a 4413 if smuggled_data:
4414 _smuggle(info_dict, smuggled_data)
4415 if info_dict.get('entries'):
a8c754cc 4416 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4417 return info_dict
4418 return wrapper
4419
a6213a49 4420 def _extract_channel_id(self, webpage):
4421 channel_id = self._html_search_meta(
4422 'channelId', webpage, 'channel id', default=None)
4423 if channel_id:
4424 return channel_id
4425 channel_url = self._html_search_meta(
4426 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4427 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4428 'twitter:app:url:googleplay'), webpage, 'channel url')
4429 return self._search_regex(
4430 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4431 channel_url, 'channel id')
15f6397c 4432
8bdd16b4 4433 @staticmethod
cd7c66cf 4434 def _extract_basic_item_renderer(item):
4435 # Modified from _extract_grid_item_renderer
201c1459 4436 known_basic_renderers = (
a17526e4 4437 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4438 )
4439 for key, renderer in item.items():
201c1459 4440 if not isinstance(renderer, dict):
cd7c66cf 4441 continue
201c1459 4442 elif key in known_basic_renderers:
4443 return renderer
4444 elif key.startswith('grid') and key.endswith('Renderer'):
4445 return renderer
8bdd16b4 4446
c7335551
M
4447 def _extract_channel_renderer(self, renderer):
4448 channel_id = renderer['channelId']
4449 title = self._get_text(renderer, 'title')
4450 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4451 return {
4452 '_type': 'url',
4453 'url': channel_url,
4454 'id': channel_id,
4455 'ie_key': YoutubeTabIE.ie_key(),
4456 'channel': title,
4457 'channel_id': channel_id,
4458 'channel_url': channel_url,
4459 'title': title,
4460 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4461 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4462 'playlist_count': self._get_count(renderer, 'videoCountText'),
4463 'description': self._get_text(renderer, 'descriptionSnippet'),
4464 }
4465
8bdd16b4 4466 def _grid_entries(self, grid_renderer):
4467 for item in grid_renderer['items']:
4468 if not isinstance(item, dict):
39b62db1 4469 continue
cd7c66cf 4470 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4471 if not isinstance(renderer, dict):
4472 continue
052e1350 4473 title = self._get_text(renderer, 'title')
fe93e2c4 4474
8bdd16b4 4475 # playlist
4476 playlist_id = renderer.get('playlistId')
4477 if playlist_id:
4478 yield self.url_result(
4479 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4480 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4481 video_title=title)
201c1459 4482 continue
8bdd16b4 4483 # video
4484 video_id = renderer.get('videoId')
4485 if video_id:
4486 yield self._extract_video(renderer)
201c1459 4487 continue
8bdd16b4 4488 # channel
4489 channel_id = renderer.get('channelId')
4490 if channel_id:
c7335551 4491 yield self._extract_channel_renderer(renderer)
201c1459 4492 continue
4493 # generic endpoint URL support
4494 ep_url = urljoin('https://www.youtube.com/', try_get(
4495 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4496 str))
201c1459 4497 if ep_url:
4498 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4499 if ie.suitable(ep_url):
4500 yield self.url_result(
4501 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4502 break
8bdd16b4 4503
16aa9ea4 4504 def _music_reponsive_list_entry(self, renderer):
4505 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4506 if video_id:
4507 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4508 ie=YoutubeIE.ie_key(), video_id=video_id)
4509 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4510 if playlist_id:
4511 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4512 if video_id:
4513 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4514 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4515 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4516 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4517 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4518 if browse_id:
4519 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4520 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4521
3d3dddc9 4522 def _shelf_entries_from_content(self, shelf_renderer):
4523 content = shelf_renderer.get('content')
4524 if not isinstance(content, dict):
8bdd16b4 4525 return
cd7c66cf 4526 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4527 if renderer:
4528 # TODO: add support for nested playlists so each shelf is processed
4529 # as separate playlist
4530 # TODO: this includes only first N items
86e5f3ed 4531 yield from self._grid_entries(renderer)
3d3dddc9 4532 renderer = content.get('horizontalListRenderer')
4533 if renderer:
4534 # TODO
4535 pass
8bdd16b4 4536
29f7c58a 4537 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4538 ep = try_get(
4539 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4540 str)
8bdd16b4 4541 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4542 if shelf_url:
29f7c58a 4543 # Skipping links to another channels, note that checking for
4544 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4545 # will not work
4546 if skip_channels and '/channels?' in shelf_url:
4547 return
052e1350 4548 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4549 yield self.url_result(shelf_url, video_title=title)
4550 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4551 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4552
8bdd16b4 4553 def _playlist_entries(self, video_list_renderer):
4554 for content in video_list_renderer['contents']:
4555 if not isinstance(content, dict):
4556 continue
4557 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4558 if not isinstance(renderer, dict):
4559 continue
4560 video_id = renderer.get('videoId')
4561 if not video_id:
4562 continue
4563 yield self._extract_video(renderer)
07aeced6 4564
3462ffa8 4565 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4566 renderer = traverse_obj(
4567 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4568 video_id = renderer.get('videoId')
4569 if not video_id:
4570 return
4571 yield self._extract_video(renderer)
4572
8bdd16b4 4573 def _video_entry(self, video_renderer):
4574 video_id = video_renderer.get('videoId')
4575 if video_id:
4576 return self._extract_video(video_renderer)
dacb3a86 4577
ad210f4f 4578 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4579 url = urljoin('https://youtube.com', traverse_obj(
4580 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4581 if url:
4582 return self.url_result(
4583 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4584
8bdd16b4 4585 def _post_thread_entries(self, post_thread_renderer):
4586 post_renderer = try_get(
4587 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4588 if not post_renderer:
4589 return
4590 # video attachment
4591 video_renderer = try_get(
895b0931 4592 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4593 video_id = video_renderer.get('videoId')
4594 if video_id:
4595 entry = self._extract_video(video_renderer)
8bdd16b4 4596 if entry:
4597 yield entry
895b0931 4598 # playlist attachment
4599 playlist_id = try_get(
14f25df2 4600 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4601 if playlist_id:
4602 yield self.url_result(
e28f1c0a 4603 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4604 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4605 # inline video links
4606 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4607 for run in runs:
4608 if not isinstance(run, dict):
4609 continue
4610 ep_url = try_get(
14f25df2 4611 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4612 if not ep_url:
4613 continue
4614 if not YoutubeIE.suitable(ep_url):
4615 continue
4616 ep_video_id = YoutubeIE._match_id(ep_url)
4617 if video_id == ep_video_id:
4618 continue
895b0931 4619 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4620
8bdd16b4 4621 def _post_thread_continuation_entries(self, post_thread_continuation):
4622 contents = post_thread_continuation.get('contents')
4623 if not isinstance(contents, list):
4624 return
4625 for content in contents:
4626 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4627 if isinstance(renderer, dict):
4628 yield from self._post_thread_entries(renderer)
8bdd16b4 4629 continue
6b0b0a28 4630 renderer = content.get('videoRenderer')
4631 if isinstance(renderer, dict):
4632 yield self._video_entry(renderer)
07aeced6 4633
39ed931e 4634 r''' # unused
4635 def _rich_grid_entries(self, contents):
4636 for content in contents:
4637 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4638 if video_renderer:
4639 entry = self._video_entry(video_renderer)
4640 if entry:
4641 yield entry
4642 '''
52efa4b3 4643
0a5095fe 4644 def _report_history_entries(self, renderer):
4645 for url in traverse_obj(renderer, (
7a32c70d 4646 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4647 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4648 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4649 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4650
a6213a49 4651 def _extract_entries(self, parent_renderer, continuation_list):
4652 # continuation_list is modified in-place with continuation_list = [continuation_token]
4653 continuation_list[:] = [None]
4654 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4655 for content in contents:
4656 if not isinstance(content, dict):
4657 continue
16aa9ea4 4658 is_renderer = traverse_obj(
4659 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4660 expected_type=dict)
a6213a49 4661 if not is_renderer:
0a5095fe 4662 if content.get('richItemRenderer'):
4663 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4664 yield entry
4665 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4666 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4667 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4668 yield from self._report_history_entries(table)
4669 continuation_list[0] = self._extract_continuation(table)
a6213a49 4670 continue
0a5095fe 4671
a6213a49 4672 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4673 for isr_content in isr_contents:
4674 if not isinstance(isr_content, dict):
8bdd16b4 4675 continue
69184e41 4676
a6213a49 4677 known_renderers = {
4678 'playlistVideoListRenderer': self._playlist_entries,
4679 'gridRenderer': self._grid_entries,
a17526e4 4680 'reelShelfRenderer': self._grid_entries,
4681 'shelfRenderer': self._shelf_entries,
16aa9ea4 4682 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4683 'backstagePostThreadRenderer': self._post_thread_entries,
4684 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4685 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4686 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4687 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4688 }
4689 for key, renderer in isr_content.items():
4690 if key not in known_renderers:
4691 continue
4692 for entry in known_renderers[key](renderer):
4693 if entry:
4694 yield entry
4695 continuation_list[0] = self._extract_continuation(renderer)
4696 break
70d5c17b 4697
4698 if not continuation_list[0]:
a6213a49 4699 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4700
a6213a49 4701 if not continuation_list[0]:
4702 continuation_list[0] = self._extract_continuation(parent_renderer)
4703
4704 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4705 continuation_list = [None]
4706 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4707 tab_content = try_get(tab, lambda x: x['content'], dict)
4708 if not tab_content:
4709 return
3462ffa8 4710 parent_renderer = (
29f7c58a 4711 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4712 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4713 yield from extract_entries(parent_renderer)
3462ffa8 4714 continuation = continuation_list[0]
d069eca7 4715
8bdd16b4 4716 for page_num in itertools.count(1):
4717 if not continuation:
4718 break
99e9e001 4719 headers = self.generate_api_headers(
4720 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4721 response = self._extract_response(
86e5f3ed 4722 item_id=f'{item_id} page {page_num}',
fe93e2c4 4723 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4724 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4725
4726 if not response:
8bdd16b4 4727 break
ac56cf38 4728 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4729 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4730 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4731
a1b535bd 4732 known_renderers = {
e4b98809 4733 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4734 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4735 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4736 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4737 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4738 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4739 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4740 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4741 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4742 'playlistVideoListContinuation': (self._playlist_entries, None),
4743 'gridContinuation': (self._grid_entries, None),
4744 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4745 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4746 }
1fb53b94 4747
4748 continuation_items = traverse_obj(response, (
4749 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4750 'appendContinuationItemsAction', 'continuationItems'
4751 ), 'continuationContents', get_all=False)
4752 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4753
a1b535bd 4754 video_items_renderer = None
1fb53b94 4755 for key in continuation_item.keys():
a1b535bd 4756 if key not in known_renderers:
8bdd16b4 4757 continue
1fb53b94 4758 func, parent_key = known_renderers[key]
4759 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4760 continuation_list = [None]
1fb53b94 4761 yield from func(video_items_renderer)
9ba5705a 4762 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4763
4764 if not video_items_renderer:
a1b535bd 4765 break
9558dcec 4766
8bdd16b4 4767 @staticmethod
7c219ea6 4768 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4769 for tab_renderer in tabs:
4770 if tab_renderer.get('selected'):
4771 return tab_renderer
4772 if fatal:
4773 raise ExtractorError('Unable to find selected tab')
4774
4775 @staticmethod
4776 def _extract_tab_renderers(response):
4777 return traverse_obj(
4778 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4779
ac56cf38 4780 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 4781 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 4782
8bdd16b4 4783 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 4784 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4785 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4786
4787 return self.playlist_result(
4788 self._entries(
4789 selected_tab, metadata['id'], ytcfg,
4790 self._extract_account_syncid(ytcfg, data),
4791 self._extract_visitor_data(data, ytcfg)),
4792 **metadata)
39ed931e 4793
bd7e919a 4794 def _extract_metadata_from_tabs(self, item_id, data):
4795 info = {'id': item_id}
4796
4797 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 4798 if metadata_renderer:
bd7e919a 4799 info.update({
4800 'uploader': metadata_renderer.get('title'),
4801 'uploader_id': metadata_renderer.get('externalId'),
4802 'uploader_url': metadata_renderer.get('channelUrl'),
4803 })
4804 if info['uploader_id']:
4805 info['id'] = info['uploader_id']
4806 else:
4807 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 4808
301d07fc 4809 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4810 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4811 def _get_uncropped(url):
4812 return url_or_none((url or '').split('=')[0] + '=s0')
4813
6141346d 4814 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 4815 if avatar_thumbnails:
4816 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4817 if uncropped_avatar:
4818 avatar_thumbnails.append({
4819 'url': uncropped_avatar,
4820 'id': 'avatar_uncropped',
4821 'preference': 1
4822 })
4823
4824 channel_banners = self._extract_thumbnails(
bd7e919a 4825 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 4826 for banner in channel_banners:
4827 banner['preference'] = -10
4828
4829 if channel_banners:
4830 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4831 if uncropped_banner:
4832 channel_banners.append({
4833 'url': uncropped_banner,
4834 'id': 'banner_uncropped',
4835 'preference': -5
4836 })
4837
bd7e919a 4838 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4839 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4840 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4841
301d07fc 4842 primary_thumbnails = self._extract_thumbnails(
a17526e4 4843 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
4844 playlist_thumbnails = self._extract_thumbnails(
4845 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4846
bd7e919a 4847 info.update({
4848 'title': (traverse_obj(metadata_renderer, 'title')
4849 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4850 or info['id']),
4851 'availability': self._extract_availability(data),
4852 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4853 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4854 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4855 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4856 })
f0d785d3 4857
6141346d
M
4858 # Playlist stats is a text runs array containing [video count, view count, last updated].
4859 # last updated or (view count and last updated) may be missing.
4860 playlist_stats = get_first(
bd7e919a 4861 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4862
6141346d
M
4863 last_updated_unix = self._parse_time_text(
4864 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4865 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
bd7e919a 4866 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
6141346d 4867
bd7e919a 4868 info['view_count'] = self._get_count(playlist_stats, 1)
4869 if info['view_count'] is None: # 0 is allowed
4870 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4871
4872 info['playlist_count'] = self._get_count(playlist_stats, 0)
4873 if info['playlist_count'] is None: # 0 is allowed
4874 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4875
4876 if not info.get('uploader_id'):
6141346d 4877 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 4878 if not owner: # Deprecated
6141346d
M
4879 owner = traverse_obj(
4880 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4881 ('videoOwner', 'videoOwnerRenderer', 'title'))
4882 owner_text = self._get_text(owner)
4883 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 4884 info.update({
6141346d
M
4885 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4886 'uploader_id': browse_ep.get('browseId'),
4887 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
bd7e919a 4888 })
6141346d 4889
bd7e919a 4890 info.update({
4891 'channel': info['uploader'],
4892 'channel_id': info['uploader_id'],
4893 'channel_url': info['uploader_url']
4894 })
4895 return info
73c4ac2c 4896
6e634cbe 4897 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4898 first_id = last_id = response = None
2be71994 4899 for page_num in itertools.count(1):
cd7c66cf 4900 videos = list(self._playlist_entries(playlist))
4901 if not videos:
4902 return
2be71994 4903 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4904 if start >= len(videos):
4905 return
24146491 4906 yield from videos[start:]
2be71994 4907 first_id = first_id or videos[0]['id']
4908 last_id = videos[-1]['id']
79360d99 4909 watch_endpoint = try_get(
4910 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4911 headers = self.generate_api_headers(
4912 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4913 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4914 query = {
4915 'playlistId': playlist_id,
4916 'videoId': watch_endpoint.get('videoId') or last_id,
4917 'index': watch_endpoint.get('index') or len(videos),
4918 'params': watch_endpoint.get('params') or 'OAE%3D'
4919 }
4920 response = self._extract_response(
4921 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4922 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4923 check_get_keys='contents'
4924 )
cd7c66cf 4925 playlist = try_get(
79360d99 4926 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4927
ac56cf38 4928 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4929 title = playlist.get('title') or try_get(
14f25df2 4930 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4931 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4932
4933 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4934 playlist_url = urljoin(url, try_get(
4935 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4936 str))
6e634cbe 4937
4938 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4939 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4940 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4941
4942 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4943 return self.url_result(
4944 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4945 video_title=title)
cd7c66cf 4946
8bdd16b4 4947 return self.playlist_result(
6e634cbe 4948 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4949 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4950
47193e02 4951 def _extract_availability(self, data):
4952 """
4953 Gets the availability of a given playlist/tab.
4954 Note: Unless YouTube tells us explicitly, we do not assume it is public
4955 @param data: response
4956 """
6141346d
M
4957 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4958 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4959 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 4960
6141346d 4961 badges = self._extract_badges(sidebar_renderer)
47193e02 4962
4963 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
4964 privacy_setting_icon = get_first(
4965 (playlist_header_renderer, sidebar_renderer),
4966 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4967 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4968 expected_type=str)
4969
4970 microformats_is_unlisted = traverse_obj(
4971 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 4972
c26f9b99 4973 return (
4974 'public' if (
4975 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4976 or player_header_privacy == 'PUBLIC'
4977 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4978 else self._availability(
4979 is_private=(
4980 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4981 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4982 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4983 is_unlisted=(
4984 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4985 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
4986 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
4987 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 4988 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4989 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4990 needs_auth=False))
47193e02 4991
4992 @staticmethod
4993 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4994 sidebar_renderer = try_get(
4995 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4996 for item in sidebar_renderer:
4997 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4998 if renderer:
4999 return renderer
5000
ac56cf38 5001 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5002 """
6141346d 5003 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5004 """
6141346d
M
5005 is_playlist = bool(traverse_obj(
5006 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5007 if not is_playlist:
47193e02 5008 return
11f9be09 5009 headers = self.generate_api_headers(
99e9e001 5010 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5011 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5012 query = {
6141346d
M
5013 'params': 'wgYCCAA=',
5014 'browseId': f'VL{item_id}'
47193e02 5015 }
5016 return self._extract_response(
5017 item_id=item_id, headers=headers, query=query,
fe93e2c4 5018 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5019 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5020
2762dbb1 5021 @functools.cached_property
a25bca9f 5022 def skip_webpage(self):
5023 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5024
ac56cf38 5025 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5026 webpage, data = None, None
5027 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5028 try:
be5c1ae8 5029 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5030 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5031 except ExtractorError as e:
5032 if isinstance(e.cause, network_exceptions):
14f25df2 5033 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 5034 retry.error = e
5035 continue
5036 self._error_or_warning(e, fatal=fatal)
14fdfea9 5037 break
ac56cf38 5038
be5c1ae8 5039 try:
5040 self._extract_and_report_alerts(data)
5041 except ExtractorError as e:
5042 self._error_or_warning(e, fatal=fatal)
5043 break
ac56cf38 5044
be5c1ae8 5045 # Sometimes youtube returns a webpage with incomplete ytInitialData
5046 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5047 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5048 retry.error = ExtractorError('Incomplete yt initial data received')
5049 continue
ac56cf38 5050
cd7c66cf 5051 return webpage, data
5052
a25bca9f 5053 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5054 """Use if failed to extract ytcfg (and data) from initial webpage"""
5055 if not ytcfg and self.is_authenticated:
5056 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5057 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5058 raise ExtractorError(
5059 f'{msg}. If you are not downloading private content, or '
5060 'your cookies are only for the first account and channel,'
5061 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5062 expected=True)
5063 self.report_warning(msg, only_once=True)
5064
ac56cf38 5065 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5066 data = None
a25bca9f 5067 if not self.skip_webpage:
ac56cf38 5068 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5069 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5070 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5071 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5072 if (url != 'https://www.youtube.com/feed/recommended'
5073 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5074 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5075 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5076 if fatal:
5077 raise ExtractorError(msg, expected=True)
5078 self.report_warning(msg, only_once=True)
ac56cf38 5079 if not data:
a25bca9f 5080 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5081 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5082 return data, ytcfg
5083
5084 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5085 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5086 resolve_response = self._extract_response(
5087 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5088 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5089 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5090 for ep_key, ep in endpoints.items():
5091 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5092 if params:
5093 return self._extract_response(
5094 item_id=item_id, query=params, ep=ep, headers=headers,
5095 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5096 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5097 err_note = 'Failed to resolve url (does the playlist exist?)'
5098 if fatal:
5099 raise ExtractorError(err_note, expected=True)
5100 self.report_warning(err_note, item_id)
5101
a6213a49 5102 _SEARCH_PARAMS = None
5103
af5c1c55 5104 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5105 data = {'query': query}
5106 if params is NO_DEFAULT:
5107 params = self._SEARCH_PARAMS
5108 if params:
5109 data['params'] = params
16aa9ea4 5110
5111 content_keys = (
5112 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5113 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5114 # ytmusic search
5115 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5116 ('continuationContents', ),
5117 )
a25bca9f 5118 display_id = f'query "{query}"'
86e5f3ed 5119 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5120 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5121 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5122
a61fd4cf 5123 continuation_list = [None]
a25bca9f 5124 search = None
a6213a49 5125 for page_num in itertools.count(1):
a61fd4cf 5126 data.update(continuation_list[0] or {})
a25bca9f 5127 headers = self.generate_api_headers(
5128 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5129 search = self._extract_response(
a25bca9f 5130 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5131 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5132 slr_contents = traverse_obj(search, *content_keys)
5133 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5134 if not continuation_list[0]:
a6213a49 5135 break
5136
5137
5138class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5139 IE_DESC = 'YouTube Tabs'
5140 _VALID_URL = r'''(?x:
5141 https?://
b032ff0f 5142 (?!consent\.)(?:\w+\.)?
a6213a49 5143 (?:
5144 youtube(?:kids)?\.com|
5145 %(invidious)s
5146 )/
5147 (?:
5148 (?P<channel_type>channel|c|user|browse)/|
5149 (?P<not_channel>
5150 feed/|hashtag/|
5151 (?:playlist|watch)\?.*?\blist=
5152 )|
5153 (?!(?:%(reserved_names)s)\b) # Direct URLs
5154 )
5155 (?P<id>[^/?\#&]+)
5156 )''' % {
5157 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5158 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5159 }
5160 IE_NAME = 'youtube:tab'
5161
5162 _TESTS = [{
5163 'note': 'playlists, multipage',
5164 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5165 'playlist_mincount': 94,
5166 'info_dict': {
5167 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5168 'title': 'Igor Kleiner - Playlists',
a6213a49 5169 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5170 'uploader': 'Igor Kleiner',
a6213a49 5171 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5172 'channel': 'Igor Kleiner',
5173 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5174 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5175 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5176 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5177 'channel_follower_count': int
a6213a49 5178 },
5179 }, {
5180 'note': 'playlists, multipage, different order',
5181 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5182 'playlist_mincount': 94,
5183 'info_dict': {
5184 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5185 'title': 'Igor Kleiner - Playlists',
a6213a49 5186 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5187 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5188 'uploader': 'Igor Kleiner',
5189 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5190 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5191 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5192 'channel': 'Igor Kleiner',
5193 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5194 'channel_follower_count': int
a6213a49 5195 },
5196 }, {
5197 'note': 'playlists, series',
5198 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5199 'playlist_mincount': 5,
5200 'info_dict': {
5201 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5202 'title': '3Blue1Brown - Playlists',
5203 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5204 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5205 'uploader': '3Blue1Brown',
976ae3ea 5206 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5207 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5208 'channel': '3Blue1Brown',
5209 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5210 'tags': ['Mathematics'],
6c73052c 5211 'channel_follower_count': int
a6213a49 5212 },
5213 }, {
5214 'note': 'playlists, singlepage',
5215 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5216 'playlist_mincount': 4,
5217 'info_dict': {
5218 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5219 'title': 'ThirstForScience - Playlists',
5220 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5221 'uploader': 'ThirstForScience',
5222 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5223 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5224 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5225 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5226 'tags': 'count:13',
5227 'channel': 'ThirstForScience',
6c73052c 5228 'channel_follower_count': int
a6213a49 5229 }
5230 }, {
5231 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5232 'only_matching': True,
5233 }, {
5234 'note': 'basic, single video playlist',
5235 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5236 'info_dict': {
5237 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5238 'uploader': 'Sergey M.',
5239 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5240 'title': 'youtube-dl public playlist',
976ae3ea 5241 'description': '',
5242 'tags': [],
5243 'view_count': int,
5244 'modified_date': '20201130',
5245 'channel': 'Sergey M.',
5246 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5247 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5248 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5249 'availability': 'public',
a6213a49 5250 },
5251 'playlist_count': 1,
5252 }, {
5253 'note': 'empty playlist',
5254 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5255 'info_dict': {
5256 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5257 'uploader': 'Sergey M.',
5258 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5259 'title': 'youtube-dl empty playlist',
976ae3ea 5260 'tags': [],
5261 'channel': 'Sergey M.',
5262 'description': '',
5263 'modified_date': '20160902',
5264 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5265 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5266 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5267 'availability': 'public',
a6213a49 5268 },
5269 'playlist_count': 0,
5270 }, {
5271 'note': 'Home tab',
5272 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5273 'info_dict': {
5274 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5275 'title': 'lex will - Home',
5276 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5277 'uploader': 'lex will',
5278 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5279 'channel': 'lex will',
5280 'tags': ['bible', 'history', 'prophesy'],
5281 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5282 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5283 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5284 'channel_follower_count': int
a6213a49 5285 },
5286 'playlist_mincount': 2,
5287 }, {
5288 'note': 'Videos tab',
5289 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5290 'info_dict': {
5291 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5292 'title': 'lex will - Videos',
5293 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5294 'uploader': 'lex will',
5295 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5296 'tags': ['bible', 'history', 'prophesy'],
5297 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5298 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5299 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5300 'channel': 'lex will',
6c73052c 5301 'channel_follower_count': int
a6213a49 5302 },
5303 'playlist_mincount': 975,
5304 }, {
5305 'note': 'Videos tab, sorted by popular',
5306 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5307 'info_dict': {
5308 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5309 'title': 'lex will - Videos',
5310 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5311 'uploader': 'lex will',
5312 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5313 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5314 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5315 'channel': 'lex will',
5316 'tags': ['bible', 'history', 'prophesy'],
5317 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5318 'channel_follower_count': int
a6213a49 5319 },
5320 'playlist_mincount': 199,
5321 }, {
5322 'note': 'Playlists tab',
5323 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5324 'info_dict': {
5325 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5326 'title': 'lex will - Playlists',
5327 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5328 'uploader': 'lex will',
5329 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5330 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5331 'channel': 'lex will',
5332 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5333 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5334 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5335 'channel_follower_count': int
a6213a49 5336 },
5337 'playlist_mincount': 17,
5338 }, {
5339 'note': 'Community tab',
5340 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5341 'info_dict': {
5342 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5343 'title': 'lex will - Community',
5344 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5345 'uploader': 'lex will',
5346 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5347 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5348 'channel': 'lex will',
5349 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5350 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5351 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5352 'channel_follower_count': int
a6213a49 5353 },
5354 'playlist_mincount': 18,
5355 }, {
5356 'note': 'Channels tab',
5357 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5358 'info_dict': {
5359 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5360 'title': 'lex will - Channels',
5361 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5362 'uploader': 'lex will',
5363 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5364 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5365 'channel': 'lex will',
5366 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5367 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5368 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5369 'channel_follower_count': int
a6213a49 5370 },
5371 'playlist_mincount': 12,
5372 }, {
5373 'note': 'Search tab',
5374 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5375 'playlist_mincount': 40,
5376 'info_dict': {
5377 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5378 'title': '3Blue1Brown - Search - linear algebra',
5379 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5380 'uploader': '3Blue1Brown',
5381 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5382 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5383 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5384 'tags': ['Mathematics'],
5385 'channel': '3Blue1Brown',
5386 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5387 'channel_follower_count': int
a6213a49 5388 },
5389 }, {
5390 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5391 'only_matching': True,
5392 }, {
5393 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5394 'only_matching': True,
5395 }, {
5396 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5397 'only_matching': True,
5398 }, {
5399 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5400 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5401 'info_dict': {
5402 'title': '29C3: Not my department',
5403 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5404 'uploader': 'Christiaan008',
5405 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5406 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5407 'tags': [],
5408 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5409 'view_count': int,
5410 'modified_date': '20150605',
5411 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5412 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5413 'channel': 'Christiaan008',
c26f9b99 5414 'availability': 'public',
a6213a49 5415 },
5416 'playlist_count': 96,
5417 }, {
5418 'note': 'Large playlist',
5419 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5420 'info_dict': {
5421 'title': 'Uploads from Cauchemar',
5422 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5423 'uploader': 'Cauchemar',
5424 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5425 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5426 'tags': [],
5427 'modified_date': r're:\d{8}',
5428 'channel': 'Cauchemar',
5429 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5430 'view_count': int,
5431 'description': '',
5432 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5433 'availability': 'public',
a6213a49 5434 },
5435 'playlist_mincount': 1123,
976ae3ea 5436 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5437 }, {
5438 'note': 'even larger playlist, 8832 videos',
5439 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5440 'only_matching': True,
5441 }, {
5442 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5443 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5444 'info_dict': {
5445 'title': 'Uploads from Interstellar Movie',
5446 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5447 'uploader': 'Interstellar Movie',
5448 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5449 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5450 'tags': [],
5451 'view_count': int,
5452 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5453 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5454 'channel': 'Interstellar Movie',
5455 'description': '',
5456 'modified_date': r're:\d{8}',
c26f9b99 5457 'availability': 'public',
a6213a49 5458 },
5459 'playlist_mincount': 21,
5460 }, {
5461 'note': 'Playlist with "show unavailable videos" button',
5462 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5463 'info_dict': {
5464 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5465 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5466 'uploader': 'Phim Siêu Nhân Nhật Bản',
5467 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5468 'view_count': int,
5469 'channel': 'Phim Siêu Nhân Nhật Bản',
5470 'tags': [],
5471 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5472 'description': '',
5473 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5474 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5475 'modified_date': r're:\d{8}',
c26f9b99 5476 'availability': 'public',
a6213a49 5477 },
5478 'playlist_mincount': 200,
976ae3ea 5479 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5480 }, {
5481 'note': 'Playlist with unavailable videos in page 7',
5482 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5483 'info_dict': {
5484 'title': 'Uploads from BlankTV',
5485 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5486 'uploader': 'BlankTV',
5487 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5488 'channel': 'BlankTV',
5489 'channel_url': 'https://www.youtube.com/c/blanktv',
5490 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5491 'view_count': int,
5492 'tags': [],
5493 'uploader_url': 'https://www.youtube.com/c/blanktv',
5494 'modified_date': r're:\d{8}',
5495 'description': '',
c26f9b99 5496 'availability': 'public',
a6213a49 5497 },
5498 'playlist_mincount': 1000,
976ae3ea 5499 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5500 }, {
5501 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5502 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5503 'info_dict': {
5504 'title': 'Data Analysis with Dr Mike Pound',
5505 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5506 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5507 'uploader': 'Computerphile',
5508 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5509 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5510 'tags': [],
5511 'view_count': int,
5512 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5513 'channel_url': 'https://www.youtube.com/user/Computerphile',
5514 'channel': 'Computerphile',
c26f9b99 5515 'availability': 'public',
6141346d 5516 'modified_date': '20190712',
a6213a49 5517 },
5518 'playlist_mincount': 11,
5519 }, {
5520 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5521 'only_matching': True,
5522 }, {
5523 'note': 'Playlist URL that does not actually serve a playlist',
5524 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5525 'info_dict': {
5526 'id': 'FqZTN594JQw',
5527 'ext': 'webm',
5528 'title': "Smiley's People 01 detective, Adventure Series, Action",
5529 'uploader': 'STREEM',
5530 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5531 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5532 'upload_date': '20150526',
5533 'license': 'Standard YouTube License',
5534 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5535 'categories': ['People & Blogs'],
5536 'tags': list,
5537 'view_count': int,
5538 'like_count': int,
a6213a49 5539 },
5540 'params': {
5541 'skip_download': True,
5542 },
5543 'skip': 'This video is not available.',
5544 'add_ie': [YoutubeIE.ie_key()],
5545 }, {
5546 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5547 'only_matching': True,
5548 }, {
5549 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5550 'only_matching': True,
5551 }, {
5552 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5553 'info_dict': {
12a1b225 5554 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5555 'ext': 'mp4',
976ae3ea 5556 'title': str,
a6213a49 5557 'uploader': 'Sky News',
5558 'uploader_id': 'skynews',
5559 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5560 'upload_date': r're:\d{8}',
976ae3ea 5561 'description': str,
a6213a49 5562 'categories': ['News & Politics'],
5563 'tags': list,
5564 'like_count': int,
86973308 5565 'release_timestamp': int,
976ae3ea 5566 'channel': 'Sky News',
5567 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5568 'age_limit': 0,
5569 'view_count': int,
86973308 5570 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5571 'playable_in_embed': True,
86973308 5572 'release_date': r're:\d+',
976ae3ea 5573 'availability': 'public',
5574 'live_status': 'is_live',
5575 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5576 'channel_follower_count': int,
5577 'concurrent_view_count': int,
a6213a49 5578 },
5579 'params': {
5580 'skip_download': True,
5581 },
976ae3ea 5582 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5583 }, {
5584 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5585 'info_dict': {
5586 'id': 'a48o2S1cPoo',
5587 'ext': 'mp4',
5588 'title': 'The Young Turks - Live Main Show',
5589 'uploader': 'The Young Turks',
5590 'uploader_id': 'TheYoungTurks',
5591 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5592 'upload_date': '20150715',
5593 'license': 'Standard YouTube License',
5594 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5595 'categories': ['News & Politics'],
5596 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5597 'like_count': int,
a6213a49 5598 },
5599 'params': {
5600 'skip_download': True,
5601 },
5602 'only_matching': True,
5603 }, {
5604 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5605 'only_matching': True,
5606 }, {
5607 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5608 'only_matching': True,
5609 }, {
5610 'note': 'A channel that is not live. Should raise error',
5611 'url': 'https://www.youtube.com/user/numberphile/live',
5612 'only_matching': True,
5613 }, {
5614 'url': 'https://www.youtube.com/feed/trending',
5615 'only_matching': True,
5616 }, {
5617 'url': 'https://www.youtube.com/feed/library',
5618 'only_matching': True,
5619 }, {
5620 'url': 'https://www.youtube.com/feed/history',
5621 'only_matching': True,
5622 }, {
5623 'url': 'https://www.youtube.com/feed/subscriptions',
5624 'only_matching': True,
5625 }, {
5626 'url': 'https://www.youtube.com/feed/watch_later',
5627 'only_matching': True,
5628 }, {
5629 'note': 'Recommended - redirects to home page.',
5630 'url': 'https://www.youtube.com/feed/recommended',
5631 'only_matching': True,
5632 }, {
5633 'note': 'inline playlist with not always working continuations',
5634 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5635 'only_matching': True,
5636 }, {
5637 'url': 'https://www.youtube.com/course',
5638 'only_matching': True,
5639 }, {
5640 'url': 'https://www.youtube.com/zsecurity',
5641 'only_matching': True,
5642 }, {
5643 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5644 'only_matching': True,
5645 }, {
5646 'url': 'https://www.youtube.com/TheYoungTurks/live',
5647 'only_matching': True,
5648 }, {
5649 'url': 'https://www.youtube.com/hashtag/cctv9',
5650 'info_dict': {
5651 'id': 'cctv9',
5652 'title': '#cctv9',
976ae3ea 5653 'tags': [],
a6213a49 5654 },
4dc23a80 5655 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5656 }, {
5657 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5658 'only_matching': True,
5659 }, {
5660 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5661 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5662 'only_matching': True
5663 }, {
5664 'note': '/browse/ should redirect to /channel/',
5665 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5666 'only_matching': True
5667 }, {
5668 'note': 'VLPL, should redirect to playlist?list=PL...',
5669 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5670 'info_dict': {
5671 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5672 'uploader': 'NoCopyrightSounds',
5673 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5674 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5675 'title': 'NCS : All Releases 💿',
976ae3ea 5676 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5677 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5678 'modified_date': r're:\d{8}',
5679 'view_count': int,
5680 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5681 'tags': [],
5682 'channel': 'NoCopyrightSounds',
c26f9b99 5683 'availability': 'public',
a6213a49 5684 },
5685 'playlist_mincount': 166,
976ae3ea 5686 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5687 }, {
5688 'note': 'Topic, should redirect to playlist?list=UU...',
5689 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5690 'info_dict': {
5691 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5692 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5693 'title': 'Uploads from Royalty Free Music - Topic',
5694 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5695 'tags': [],
5696 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5697 'channel': 'Royalty Free Music - Topic',
5698 'view_count': int,
5699 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5700 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5701 'modified_date': r're:\d{8}',
5702 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5703 'description': '',
c26f9b99 5704 'availability': 'public',
a6213a49 5705 },
a6213a49 5706 'playlist_mincount': 101,
5707 }, {
86973308
M
5708 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5709 # Treat as a general feed
a6213a49 5710 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5711 'info_dict': {
5712 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5713 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5714 'tags': [],
a6213a49 5715 },
a6213a49 5716 'playlist_mincount': 9,
5717 }, {
5718 'note': 'Youtube music Album',
5719 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5720 'info_dict': {
5721 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5722 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5723 'tags': [],
5724 'view_count': int,
5725 'description': '',
5726 'availability': 'unlisted',
5727 'modified_date': r're:\d{8}',
a6213a49 5728 },
5729 'playlist_count': 50,
5730 }, {
5731 'note': 'unlisted single video playlist',
5732 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5733 'info_dict': {
5734 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5735 'uploader': 'colethedj',
5736 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5737 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5738 'availability': 'unlisted',
5739 'tags': [],
12a1b225 5740 'modified_date': '20220418',
976ae3ea 5741 'channel': 'colethedj',
5742 'view_count': int,
5743 'description': '',
5744 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5745 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5746 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5747 },
5748 'playlist_count': 1,
5749 }, {
5750 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5751 'url': 'https://www.youtube.com/feed/recommended',
5752 'info_dict': {
5753 'id': 'recommended',
5754 'title': 'recommended',
6c73052c 5755 'tags': [],
a6213a49 5756 },
5757 'playlist_mincount': 50,
5758 'params': {
5759 'skip_download': True,
5760 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5761 },
5762 }, {
5763 'note': 'API Fallback: /videos tab, sorted by oldest first',
5764 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5765 'info_dict': {
5766 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5767 'title': 'Cody\'sLab - Videos',
5768 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5769 'uploader': 'Cody\'sLab',
5770 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5771 'channel': 'Cody\'sLab',
5772 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5773 'tags': [],
5774 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5775 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5776 'channel_follower_count': int
a6213a49 5777 },
5778 'playlist_mincount': 650,
5779 'params': {
5780 'skip_download': True,
5781 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5782 },
86973308 5783 'skip': 'Query for sorting no longer works',
a6213a49 5784 }, {
5785 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5786 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5787 'info_dict': {
5788 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5789 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5790 'title': 'Uploads from Royalty Free Music - Topic',
5791 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5792 'modified_date': r're:\d{8}',
5793 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5794 'description': '',
5795 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5796 'tags': [],
5797 'channel': 'Royalty Free Music - Topic',
5798 'view_count': int,
5799 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5800 'availability': 'public',
a6213a49 5801 },
a6213a49 5802 'playlist_mincount': 101,
5803 'params': {
5804 'skip_download': True,
5805 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5806 },
7c219ea6 5807 }, {
5808 'note': 'non-standard redirect to regional channel',
5809 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5810 'only_matching': True
61d3665d 5811 }, {
5812 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5813 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5814 'info_dict': {
5815 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5816 'modified_date': '20220407',
5817 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5818 'tags': [],
5819 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5820 'uploader': 'pukkandan',
5821 'availability': 'unlisted',
5822 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5823 'channel': 'pukkandan',
5824 'description': 'Test for collaborative playlist',
5825 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5826 'view_count': int,
61d3665d 5827 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5828 },
5829 'playlist_mincount': 2
c26f9b99 5830 }, {
5831 'note': 'translated tab name',
5832 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5833 'info_dict': {
5834 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5835 'tags': [],
5836 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5837 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 5838 'description': 'test description',
c26f9b99 5839 'title': 'cole-dlp-test-acc - 再生リスト',
5840 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5841 'uploader': 'cole-dlp-test-acc',
5842 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5843 'channel': 'cole-dlp-test-acc',
5844 },
5845 'playlist_mincount': 1,
5846 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5847 'expected_warnings': ['Preferring "ja"'],
5848 }, {
5849 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5850 'note': 'preferred lang set with playlist with translated video titles',
5851 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5852 'info_dict': {
5853 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5854 'tags': [],
5855 'view_count': int,
5856 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5857 'uploader': 'cole-dlp-test-acc',
5858 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5859 'channel': 'cole-dlp-test-acc',
5860 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5861 'description': 'test',
5862 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5863 'title': 'dlp test playlist',
5864 'availability': 'public',
5865 },
5866 'playlist_mincount': 1,
5867 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5868 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5869 }, {
5870 # shorts audio pivot for 2GtVksBMYFM.
5871 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5872 'info_dict': {
5873 'id': 'sfv_audio_pivot',
5874 'title': 'sfv_audio_pivot',
5875 'tags': [],
5876 },
5877 'playlist_mincount': 50,
5878
86973308
M
5879 }, {
5880 # Channel with a real live tab (not to be mistaken with streams tab)
5881 # Do not treat like it should redirect to live stream
5882 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5883 'info_dict': {
5884 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5885 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5886 'tags': [],
5887 },
5888 'playlist_mincount': 20,
5889 }, {
5890 # Tab name is not the same as tab id
5891 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5892 'info_dict': {
5893 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5894 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5895 'tags': [],
5896 },
5897 'playlist_mincount': 8,
5898 }, {
5899 # Home tab id is literally home. Not to get mistaken with featured
5900 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5901 'info_dict': {
5902 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5903 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5904 'tags': [],
5905 },
5906 'playlist_mincount': 8,
5907 }, {
5908 # Should get three playlists for videos, shorts and streams tabs
5909 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5910 'info_dict': {
5911 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 5912 'title': 'Polka Ch. 尾丸ポルカ',
5913 'channel_follower_count': int,
5914 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5915 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5916 'uploader': 'Polka Ch. 尾丸ポルカ',
5917 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5918 'channel': 'Polka Ch. 尾丸ポルカ',
5919 'tags': 'count:35',
5920 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5921 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
86973308
M
5922 },
5923 'playlist_count': 3,
5924 }, {
5925 # Shorts tab with channel with handle
5926 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5927 'info_dict': {
5928 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5929 'title': 'Not Just Bikes - Shorts',
5930 'tags': 'count:12',
5931 'uploader': 'Not Just Bikes',
5932 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5933 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5934 'channel_follower_count': int,
5935 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5936 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5937 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5938 'channel': 'Not Just Bikes',
5939 },
5940 'playlist_mincount': 10,
5941 }, {
5942 # Streams tab
5943 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5944 'info_dict': {
5945 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5946 'title': '中村悠一 - Live',
5947 'tags': 'count:7',
5948 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5949 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5950 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5951 'channel': '中村悠一',
5952 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5953 'channel_follower_count': int,
5954 'uploader': '中村悠一',
5955 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5956 },
5957 'playlist_mincount': 60,
5958 }, {
5959 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5960 # See test_youtube_lists
5961 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5962 'only_matching': True,
5963 }, {
5964 # No uploads and no UCID given. Should fail with no uploads error
5965 # See test_youtube_lists
5966 'url': 'https://www.youtube.com/news',
5967 'only_matching': True
5968 }, {
5969 # No videos tab but has a shorts tab
5970 'url': 'https://www.youtube.com/c/TKFShorts',
5971 'info_dict': {
5972 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5973 'title': 'Shorts Break - Shorts',
5974 'tags': 'count:32',
5975 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5976 'channel': 'Shorts Break',
5977 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5978 'uploader': 'Shorts Break',
5979 'channel_follower_count': int,
5980 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5981 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5982 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5983 },
5984 'playlist_mincount': 30,
5985 }, {
5986 # Trending Now Tab. tab id is empty
5987 'url': 'https://www.youtube.com/feed/trending',
5988 'info_dict': {
5989 'id': 'trending',
5990 'title': 'trending - Now',
5991 'tags': [],
5992 },
5993 'playlist_mincount': 30,
5994 }, {
5995 # Trending Gaming Tab. tab id is empty
5996 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
5997 'info_dict': {
5998 'id': 'trending',
5999 'title': 'trending - Gaming',
6000 'tags': [],
6001 },
6002 'playlist_mincount': 30,
4dc23a80
M
6003 }, {
6004 # Shorts url result in shorts tab
6005 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6006 'info_dict': {
6007 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6008 'title': 'cole-dlp-test-acc - Shorts',
6009 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6010 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6011 'description': 'test description',
6012 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6013 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6014 'tags': [],
6015 'uploader': 'cole-dlp-test-acc',
6016 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6017
6018 },
6019 'playlist': [{
6020 'info_dict': {
6021 '_type': 'url',
6022 'ie_key': 'Youtube',
6023 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6024 'id': 'sSM9J5YH_60',
6025 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6026 'title': 'SHORT short',
6027 'channel': 'cole-dlp-test-acc',
6028 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6029 'view_count': int,
6030 'thumbnails': list,
6031 }
6032 }],
6033 'params': {'extract_flat': True},
6034 }, {
6035 # Live video status should be extracted
6036 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6037 'info_dict': {
6038 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6039 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6040 'tags': []
6041 },
6042 'playlist': [{
6043 'info_dict': {
6044 '_type': 'url',
6045 'ie_key': 'Youtube',
6046 'url': 'startswith:https://www.youtube.com/watch?v=',
6047 'id': str,
6048 'title': str,
6049 'live_status': 'is_live',
6050 'channel_id': str,
6051 'channel_url': str,
6052 'concurrent_view_count': int,
6053 'channel': str,
6054 }
6055 }],
c7335551 6056 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6057 'playlist_mincount': 1
c7335551
M
6058 }, {
6059 # Channel renderer metadata. Contains number of videos on the channel
6060 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6061 'info_dict': {
6062 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6063 'title': 'cole-dlp-test-acc - Channels',
6064 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6065 'channel': 'cole-dlp-test-acc',
6066 'description': 'test description',
6067 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6068 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6069 'tags': [],
6070 'uploader': 'cole-dlp-test-acc',
6071 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6072
6073 },
6074 'playlist': [{
6075 'info_dict': {
6076 '_type': 'url',
6077 'ie_key': 'YoutubeTab',
6078 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6079 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6080 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6081 'title': 'PewDiePie',
6082 'channel': 'PewDiePie',
6083 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6084 'thumbnails': list,
6085 'channel_follower_count': int,
6086 'playlist_count': int
6087 }
6088 }],
6089 'params': {'extract_flat': True},
a6213a49 6090 }]
6091
6092 @classmethod
6093 def suitable(cls, url):
86e5f3ed 6094 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6095
86973308
M
6096 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6097
6098 def _get_url_mobj(self, url):
6099 mobj = self._URL_RE.match(url).groupdict()
6100 mobj.update((k, '') for k, v in mobj.items() if v is None)
6101 return mobj
6102
6103 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6104 tab_name = (tab.get('title') or '').lower()
6105 tab_url = urljoin(base_url, traverse_obj(
6106 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6107
bd7e919a 6108 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6109 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6110 if tab_id:
bd7e919a 6111 return {
6112 'TAB_ID_SPONSORSHIPS': 'membership',
6113 }.get(tab_id, tab_id), tab_name
86973308
M
6114
6115 # Fallback to tab name if we cannot get the tab id.
6116 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6117 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6118 if tab_name:
6119 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6120 return {
6121 'home': 'featured',
6122 'live': 'streams',
6123 }.get(tab_name, tab_name), tab_name
6124
6125 def _has_tab(self, tabs, tab_id):
6126 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6127
182bda88 6128 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6129 def _real_extract(self, url, smuggled_data):
cd7c66cf 6130 item_id = self._match_id(url)
14f25df2 6131 url = urllib.parse.urlunparse(
6132 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6133 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6134
86973308
M
6135 mobj = self._get_url_mobj(url)
6136 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6137 if is_channel and smuggled_data.get('is_music_url'):
6138 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6139 return self.url_result(
6140 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6141 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6142 mdata = self._extract_tab_endpoint(
6143 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6144 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6145 get_all=False, expected_type=str)
6146 if not murl:
6147 raise ExtractorError('Failed to resolve album to playlist')
6148 return self.url_result(murl, YoutubeTabIE)
6149 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6150 return self.url_result(
6151 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6152
6153 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6154 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6155 url = f'{pre}/videos{post}'
cd7c66cf 6156
6157 # Handle both video/playlist URLs
201c1459 6158 qs = parse_qs(url)
bd7e919a 6159 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6160 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6161 if not playlist_id:
fe03a6cd 6162 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6163 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6164 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6165 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6166 return self.url_result(
6167 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6168
86973308
M
6169 if not self._yes_playlist(playlist_id, video_id):
6170 return self.url_result(
6171 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6172
bd7e919a 6173 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6174
7c219ea6 6175 # YouTube may provide a non-standard redirect to the regional channel
6176 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6177 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6178 redirect_url = traverse_obj(
6179 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6180 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6181 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6182 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6183 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6184
bd7e919a 6185 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6186 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6187 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6188 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6189 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6190
6191 if not original_tab_id and selected_tab_name:
bd7e919a 6192 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6193 'To download only the videos in a specific tab, pass the tab\'s URL')
6194 if self._has_tab(tabs, 'streams'):
bd7e919a 6195 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6196 if self._has_tab(tabs, 'shorts'):
bd7e919a 6197 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6198 # XXX: Members-only tab should also be extracted
6199
bd7e919a 6200 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6201 # Channel does not have streams, shorts or videos tabs
6202 if item_id[:2] != 'UC':
6203 raise ExtractorError('This channel has no uploads', expected=True)
6204
6205 # Topic channels don't have /videos. Use the equivalent playlist instead
6206 pl_id = f'UU{item_id[2:]}'
6207 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6208 try:
6209 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6210 except ExtractorError:
6211 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6212 else:
86973308
M
6213 item_id, url = pl_id, pl_url
6214 self.to_screen(
6215 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6216
bd7e919a 6217 elif extra_tabs and selected_tab_id != 'videos':
86973308 6218 # When there are shorts/live tabs but not videos tab
bd7e919a 6219 url, data = f'{pre}{post}', None
86973308
M
6220
6221 elif (original_tab_id or 'videos') != selected_tab_id:
6222 if original_tab_id == 'live':
6223 # Live tab should have redirected to the video
6224 # Except in the case the channel has an actual live tab
6225 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6226 raise UserNotLive(video_id=item_id)
86973308
M
6227 elif selected_tab_name:
6228 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6229
6230 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6231 url = f'{pre}{post}'
18db7548 6232
358de58c 6233 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6234 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6235 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6236 self._extract_and_report_alerts(data, only_once=True)
86973308 6237
bd7e919a 6238 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6239 if tabs:
bd7e919a 6240 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6241 entries[0].update({
86973308
M
6242 'extractor_key': YoutubeTabIE.ie_key(),
6243 'extractor': YoutubeTabIE.IE_NAME,
6244 'webpage_url': url,
6245 })
bd7e919a 6246 if self.get_param('playlist_items') == '0':
6247 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6248 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6249 entries.extend(map(self._real_extract, extra_tabs))
6250
6251 if len(entries) == 1:
6252 return entries[0]
6253 elif entries:
6254 metadata = self._extract_metadata_from_tabs(item_id, data)
6255 uploads_url = 'the Uploads (UU) playlist URL'
6256 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6257 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6258 self.to_screen(
6259 'Downloading as multiple playlists, separated by tabs. '
6260 f'To download as a single playlist instead, pass {uploads_url}')
6261 return self.playlist_result(entries, item_id, **metadata)
6262
6263 # Inline playlist
37e57a9f 6264 playlist = traverse_obj(
6265 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6266 if playlist:
ac56cf38 6267 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6268
37e57a9f 6269 video_id = traverse_obj(
6270 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6271 if video_id:
bd7e919a 6272 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6273 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6274 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6275
8bdd16b4 6276 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6277
c5e8d7af 6278
8bdd16b4 6279class YoutubePlaylistIE(InfoExtractor):
96565c7e 6280 IE_DESC = 'YouTube playlists'
8bdd16b4 6281 _VALID_URL = r'''(?x)(?:
6282 (?:https?://)?
6283 (?:\w+\.)?
6284 (?:
6285 (?:
6286 youtube(?:kids)?\.com|
d9190e44 6287 %(invidious)s
8bdd16b4 6288 )
6289 /.*?\?.*?\blist=
6290 )?
6291 (?P<id>%(playlist_id)s)
d9190e44
RH
6292 )''' % {
6293 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6294 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6295 }
8bdd16b4 6296 IE_NAME = 'youtube:playlist'
cdc628a4 6297 _TESTS = [{
8bdd16b4 6298 'note': 'issue #673',
6299 'url': 'PLBB231211A4F62143',
cdc628a4 6300 'info_dict': {
8bdd16b4 6301 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6302 'id': 'PLBB231211A4F62143',
976ae3ea 6303 'uploader': 'Wickman',
8bdd16b4 6304 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 6305 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6306 'view_count': int,
86973308 6307 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
976ae3ea 6308 'modified_date': r're:\d{8}',
6309 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6310 'channel': 'Wickman',
6311 'tags': [],
86973308
M
6312 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6313 'availability': 'public',
8bdd16b4 6314 },
6315 'playlist_mincount': 29,
6316 }, {
6317 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6318 'info_dict': {
6319 'title': 'YDL_safe_search',
6320 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6321 },
6322 'playlist_count': 2,
6323 'skip': 'This playlist is private',
9558dcec 6324 }, {
8bdd16b4 6325 'note': 'embedded',
6326 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6327 'playlist_count': 4,
9558dcec 6328 'info_dict': {
8bdd16b4 6329 'title': 'JODA15',
6330 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6331 'uploader': 'milan',
6332 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 6333 'description': '',
6334 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6335 'tags': [],
6336 'modified_date': '20140919',
6337 'view_count': int,
6338 'channel': 'milan',
6339 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6340 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 6341 'availability': 'public',
976ae3ea 6342 },
86973308 6343 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6344 }, {
8bdd16b4 6345 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6346 'playlist_mincount': 455,
8bdd16b4 6347 'info_dict': {
6348 'title': '2018 Chinese New Singles (11/6 updated)',
6349 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6350 'uploader': 'LBK',
6351 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 6352 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6353 'channel': 'LBK',
6354 'view_count': int,
6355 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6356 'tags': [],
6357 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6358 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6359 'modified_date': r're:\d{8}',
c26f9b99 6360 'availability': 'public',
976ae3ea 6361 },
6362 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6363 }, {
29f7c58a 6364 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6365 'only_matching': True,
6366 }, {
6367 # music album playlist
6368 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6369 'only_matching': True,
6370 }]
6371
6372 @classmethod
6373 def suitable(cls, url):
201c1459 6374 if YoutubeTabIE.suitable(url):
6375 return False
49a57e70 6376 from ..utils import parse_qs
201c1459 6377 qs = parse_qs(url)
6378 if qs.get('v', [None])[0]:
6379 return False
86e5f3ed 6380 return super().suitable(url)
29f7c58a 6381
6382 def _real_extract(self, url):
6383 playlist_id = self._match_id(url)
46953e7e 6384 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6385 url = update_url_query(
6386 'https://www.youtube.com/playlist',
6387 parse_qs(url) or {'list': playlist_id})
6388 if is_music_url:
6389 url = smuggle_url(url, {'is_music_url': True})
6390 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6391
6392
6393class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6394 IE_DESC = 'youtu.be'
29f7c58a 6395 _VALID_URL = r'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
6396 _TESTS = [{
8bdd16b4 6397 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6398 'info_dict': {
6399 'id': 'yeWKywCrFtk',
6400 'ext': 'mp4',
6401 'title': 'Small Scale Baler and Braiding Rugs',
6402 'uploader': 'Backus-Page House Museum',
6403 'uploader_id': 'backuspagemuseum',
6404 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6405 'upload_date': '20161008',
6406 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6407 'categories': ['Nonprofits & Activism'],
6408 'tags': list,
6409 'like_count': int,
976ae3ea 6410 'age_limit': 0,
6411 'playable_in_embed': True,
6412 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6413 'channel': 'Backus-Page House Museum',
6414 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6415 'live_status': 'not_live',
6416 'view_count': int,
6417 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6418 'availability': 'public',
6419 'duration': 59,
12a1b225
A
6420 'comment_count': int,
6421 'channel_follower_count': int
8bdd16b4 6422 },
6423 'params': {
6424 'noplaylist': True,
6425 'skip_download': True,
6426 },
39e7107d 6427 }, {
8bdd16b4 6428 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6429 'only_matching': True,
cdc628a4
PH
6430 }]
6431
8bdd16b4 6432 def _real_extract(self, url):
5ad28e7f 6433 mobj = self._match_valid_url(url)
29f7c58a 6434 video_id = mobj.group('id')
6435 playlist_id = mobj.group('playlist_id')
8bdd16b4 6436 return self.url_result(
29f7c58a 6437 update_url_query('https://www.youtube.com/watch', {
6438 'v': video_id,
6439 'list': playlist_id,
6440 'feature': 'youtu.be',
6441 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6442
6443
b6ce9bb0 6444class YoutubeLivestreamEmbedIE(InfoExtractor):
6445 IE_DESC = 'YouTube livestream embeds'
6446 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6447 _TESTS = [{
6448 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6449 'only_matching': True,
6450 }]
6451
6452 def _real_extract(self, url):
6453 channel_id = self._match_id(url)
6454 return self.url_result(
6455 f'https://www.youtube.com/channel/{channel_id}/live',
6456 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6457
6458
8bdd16b4 6459class YoutubeYtUserIE(InfoExtractor):
96565c7e 6460 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6461 IE_NAME = 'youtube:user'
8bdd16b4 6462 _VALID_URL = r'ytuser:(?P<id>.+)'
6463 _TESTS = [{
6464 'url': 'ytuser:phihag',
6465 'only_matching': True,
6466 }]
6467
6468 def _real_extract(self, url):
6469 user_id = self._match_id(url)
08270da5 6470 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6471
b05654f0 6472
3d3dddc9 6473class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6474 IE_NAME = 'youtube:favorites'
96565c7e 6475 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6476 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6477 _LOGIN_REQUIRED = True
6478 _TESTS = [{
6479 'url': ':ytfav',
6480 'only_matching': True,
6481 }, {
6482 'url': ':ytfavorites',
6483 'only_matching': True,
6484 }]
6485
6486 def _real_extract(self, url):
6487 return self.url_result(
6488 'https://www.youtube.com/playlist?list=LL',
6489 ie=YoutubeTabIE.ie_key())
6490
6491
ca5300c7 6492class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6493 IE_NAME = 'youtube:notif'
6494 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6495 _VALID_URL = r':ytnotif(?:ication)?s?'
6496 _LOGIN_REQUIRED = True
6497 _TESTS = [{
6498 'url': ':ytnotif',
6499 'only_matching': True,
6500 }, {
6501 'url': ':ytnotifications',
6502 'only_matching': True,
6503 }]
6504
6505 def _extract_notification_menu(self, response, continuation_list):
6506 notification_list = traverse_obj(
6507 response,
6508 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6509 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6510 expected_type=list) or []
6511 continuation_list[0] = None
6512 for item in notification_list:
6513 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6514 if entry:
6515 yield entry
6516 continuation = item.get('continuationItemRenderer')
6517 if continuation:
6518 continuation_list[0] = continuation
6519
6520 def _extract_notification_renderer(self, notification):
6521 video_id = traverse_obj(
6522 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6523 url = f'https://www.youtube.com/watch?v={video_id}'
6524 channel_id = None
6525 if not video_id:
6526 browse_ep = traverse_obj(
6527 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6528 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6529 post_id = self._search_regex(
6530 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6531 'post id', default=None)
6532 if not channel_id or not post_id:
6533 return
6534 # The direct /post url redirects to this in the browser
6535 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6536
6537 channel = traverse_obj(
6538 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6539 expected_type=str)
c7a7baaa 6540 notification_title = self._get_text(notification, 'shortMessage')
6541 if notification_title:
6542 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6543 # TODO: handle recommended videos
ca5300c7 6544 title = self._search_regex(
c7a7baaa 6545 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6546 'video title', default=None)
5225df50 6547 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6548 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6549 else None)
ca5300c7 6550 return {
6551 '_type': 'url',
6552 'url': url,
6553 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6554 'video_id': video_id,
6555 'title': title,
6556 'channel_id': channel_id,
6557 'channel': channel,
6558 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6559 'timestamp': timestamp,
ca5300c7 6560 }
6561
6562 def _notification_menu_entries(self, ytcfg):
6563 continuation_list = [None]
6564 response = None
6565 for page in itertools.count(1):
6566 ctoken = traverse_obj(
6567 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6568 response = self._extract_response(
6569 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6570 ep='notification/get_notification_menu', check_get_keys='actions',
6571 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6572 yield from self._extract_notification_menu(response, continuation_list)
6573 if not continuation_list[0]:
6574 break
6575
6576 def _real_extract(self, url):
6577 display_id = 'notifications'
6578 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6579 self._report_playlist_authcheck(ytcfg)
6580 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6581
6582
a6213a49 6583class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6584 IE_DESC = 'YouTube search'
78caa52a 6585 IE_NAME = 'youtube:search'
b05654f0 6586 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6587 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6588 _TESTS = [{
6589 'url': 'ytsearch5:youtube-dl test video',
6590 'playlist_count': 5,
6591 'info_dict': {
6592 'id': 'youtube-dl test video',
6593 'title': 'youtube-dl test video',
6594 }
6595 }]
b05654f0 6596
a61fd4cf 6597
5f7cb91a 6598class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6599 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6600 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6601 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6602 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6603 _TESTS = [{
6604 'url': 'ytsearchdate5:youtube-dl test video',
6605 'playlist_count': 5,
6606 'info_dict': {
6607 'id': 'youtube-dl test video',
6608 'title': 'youtube-dl test video',
6609 }
6610 }]
75dff0ee 6611
c9ae7b95 6612
a6213a49 6613class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6614 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6615 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6616 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6617 _TESTS = [{
6618 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6619 'playlist_mincount': 5,
6620 'info_dict': {
11f9be09 6621 'id': 'youtube-dl test video',
3462ffa8 6622 'title': 'youtube-dl test video',
6623 }
a61fd4cf 6624 }, {
6625 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6626 'playlist_mincount': 5,
6627 'info_dict': {
6628 'id': 'python',
6629 'title': 'python',
6630 }
ad210f4f 6631 }, {
6632 'url': 'https://www.youtube.com/results?search_query=%23cats',
6633 'playlist_mincount': 1,
6634 'info_dict': {
6635 'id': '#cats',
6636 'title': '#cats',
12a1b225
A
6637 # The test suite does not have support for nested playlists
6638 # 'entries': [{
6639 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6640 # 'title': '#cats',
6641 # }],
ad210f4f 6642 },
c7335551
M
6643 }, {
6644 # Channel results
6645 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6646 'info_dict': {
6647 'id': 'kurzgesagt',
6648 'title': 'kurzgesagt',
6649 },
6650 'playlist': [{
6651 'info_dict': {
6652 '_type': 'url',
6653 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6654 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6655 'ie_key': 'YoutubeTab',
6656 'channel': 'Kurzgesagt – In a Nutshell',
6657 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6658 'title': 'Kurzgesagt – In a Nutshell',
6659 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6660 'playlist_count': int, # XXX: should have a way of saying > 1
6661 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6662 'thumbnails': list
6663 }
6664 }],
6665 'params': {'extract_flat': True, 'playlist_items': '1'},
6666 'playlist_mincount': 1,
3462ffa8 6667 }, {
6668 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6669 'only_matching': True,
6670 }]
6671
6672 def _real_extract(self, url):
4dfbf869 6673 qs = parse_qs(url)
386e1dd9 6674 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6675 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6676
6677
16aa9ea4 6678class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6679 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6680 IE_NAME = 'youtube:music:search_url'
6681 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6682 _TESTS = [{
6683 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6684 'playlist_count': 16,
6685 'info_dict': {
6686 'id': 'royalty free music',
6687 'title': 'royalty free music',
6688 }
6689 }, {
6690 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6691 'playlist_mincount': 30,
6692 'info_dict': {
6693 'id': 'royalty free music - songs',
6694 'title': 'royalty free music - songs',
6695 },
6696 'params': {'extract_flat': 'in_playlist'}
6697 }, {
6698 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6699 'playlist_mincount': 30,
6700 'info_dict': {
6701 'id': 'royalty free music - community playlists',
6702 'title': 'royalty free music - community playlists',
6703 },
6704 'params': {'extract_flat': 'in_playlist'}
6705 }]
6706
6707 _SECTIONS = {
6708 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6709 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6710 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6711 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6712 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6713 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6714 }
6715
6716 def _real_extract(self, url):
6717 qs = parse_qs(url)
6718 query = (qs.get('search_query') or qs.get('q'))[0]
6719 params = qs.get('sp', (None,))[0]
6720 if params:
6721 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6722 else:
ac668111 6723 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6724 params = self._SECTIONS.get(section)
6725 if not params:
6726 section = None
6727 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6728 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6729
6730
182bda88 6731class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6732 """
25f14e9f 6733 Base class for feed extractors
82d02080 6734 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6735 """
b2e8bc1b 6736 _LOGIN_REQUIRED = True
82d02080 6737 _FEED_NAME = 'feeds'
a25bca9f 6738
6739 def _real_initialize(self):
6740 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6741
82d02080 6742 @classproperty
d7ae0639 6743 def IE_NAME(self):
82d02080 6744 return f'youtube:{self._FEED_NAME}'
04cc9617 6745
3853309f 6746 def _real_extract(self, url):
3d3dddc9 6747 return self.url_result(
182bda88 6748 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6749
6750
ef2f3c7f 6751class YoutubeWatchLaterIE(InfoExtractor):
6752 IE_NAME = 'youtube:watchlater'
96565c7e 6753 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6754 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6755 _TESTS = [{
8bdd16b4 6756 'url': ':ytwatchlater',
bc7a9cd8
S
6757 'only_matching': True,
6758 }]
25f14e9f
S
6759
6760 def _real_extract(self, url):
ef2f3c7f 6761 return self.url_result(
6762 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6763
6764
25f14e9f 6765class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6766 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6767 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6768 _FEED_NAME = 'recommended'
45db527f 6769 _LOGIN_REQUIRED = False
3d3dddc9 6770 _TESTS = [{
6771 'url': ':ytrec',
6772 'only_matching': True,
6773 }, {
6774 'url': ':ytrecommended',
6775 'only_matching': True,
6776 }, {
6777 'url': 'https://youtube.com',
6778 'only_matching': True,
6779 }]
1ed5b5c9 6780
1ed5b5c9 6781
25f14e9f 6782class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6783 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6784 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6785 _FEED_NAME = 'subscriptions'
3d3dddc9 6786 _TESTS = [{
6787 'url': ':ytsubs',
6788 'only_matching': True,
6789 }, {
6790 'url': ':ytsubscriptions',
6791 'only_matching': True,
6792 }]
1ed5b5c9 6793
1ed5b5c9 6794
25f14e9f 6795class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6796 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6797 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6798 _FEED_NAME = 'history'
3d3dddc9 6799 _TESTS = [{
6800 'url': ':ythistory',
6801 'only_matching': True,
6802 }]
1ed5b5c9
JMF
6803
6804
6e634cbe 6805class YoutubeStoriesIE(InfoExtractor):
6806 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6807 IE_NAME = 'youtube:stories'
6808 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6809 _TESTS = [{
6810 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6811 'only_matching': True,
6812 }]
6813
6814 def _real_extract(self, url):
6815 playlist_id = f'RLTD{self._match_id(url)}'
6816 return self.url_result(
50ac0e54 6817 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6818 ie=YoutubeTabIE, video_id=playlist_id)
6819
6820
80eb0bd9 6821class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6822 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6823 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6824 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6825 _TESTS = [{
1dd18a88 6826 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6827 'only_matching': True,
6828 }]
6829
6830 @staticmethod
6831 def _generate_audio_pivot_params(video_id):
6832 """
6833 Generates sfv_audio_pivot browse params for this video id
6834 """
6835 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6836 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6837
6838 def _real_extract(self, url):
6839 video_id = self._match_id(url)
6840 return self.url_result(
6841 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6842 ie=YoutubeTabIE)
6843
6844
15870e90
PH
6845class YoutubeTruncatedURLIE(InfoExtractor):
6846 IE_NAME = 'youtube:truncated_url'
6847 IE_DESC = False # Do not list
975d35db 6848 _VALID_URL = r'''(?x)
b95aab84
PH
6849 (?:https?://)?
6850 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6851 (?:watch\?(?:
c4808c60 6852 feature=[a-z_]+|
b95aab84
PH
6853 annotation_id=annotation_[^&]+|
6854 x-yt-cl=[0-9]+|
c1708b89 6855 hl=[^&]*|
287be8c6 6856 t=[0-9]+
b95aab84
PH
6857 )?
6858 |
6859 attribution_link\?a=[^&]+
6860 )
6861 $
975d35db 6862 '''
15870e90 6863
c4808c60 6864 _TESTS = [{
2d3d2997 6865 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6866 'only_matching': True,
dc2fc736 6867 }, {
2d3d2997 6868 'url': 'https://www.youtube.com/watch?',
dc2fc736 6869 'only_matching': True,
b95aab84
PH
6870 }, {
6871 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6872 'only_matching': True,
6873 }, {
6874 'url': 'https://www.youtube.com/watch?feature=foo',
6875 'only_matching': True,
c1708b89
PH
6876 }, {
6877 'url': 'https://www.youtube.com/watch?hl=en-GB',
6878 'only_matching': True,
287be8c6
PH
6879 }, {
6880 'url': 'https://www.youtube.com/watch?t=2372',
6881 'only_matching': True,
c4808c60
PH
6882 }]
6883
15870e90
PH
6884 def _real_extract(self, url):
6885 raise ExtractorError(
78caa52a
PH
6886 'Did you forget to quote the URL? Remember that & is a meta '
6887 'character in most shells, so you want to put the URL in quotes, '
3867038a 6888 'like youtube-dl '
2d3d2997 6889 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6890 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6891 expected=True)
772fd5cc
PH
6892
6893
471d0367 6894class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6895 IE_NAME = 'youtube:clip'
471d0367 6896 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6897 _TESTS = [{
6898 # FIXME: Other metadata should be extracted from the clip, not from the base video
6899 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6900 'info_dict': {
6901 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6902 'ext': 'mp4',
6903 'section_start': 29.0,
6904 'section_end': 39.7,
6905 'duration': 10.7,
12a1b225
A
6906 'age_limit': 0,
6907 'availability': 'public',
6908 'categories': ['Gaming'],
6909 'channel': 'Scott The Woz',
6910 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6911 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6912 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6913 'like_count': int,
6914 'playable_in_embed': True,
6915 'tags': 'count:17',
6916 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6917 'title': 'Mobile Games on Console - Scott The Woz',
6918 'upload_date': '20210920',
6919 'uploader': 'Scott The Woz',
6920 'uploader_id': 'scottthewoz',
6921 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6922 'view_count': int,
6923 'live_status': 'not_live',
6924 'channel_follower_count': int
471d0367 6925 }
6926 }]
3cd786db 6927
6928 def _real_extract(self, url):
471d0367 6929 clip_id = self._match_id(url)
6930 _, data = self._extract_webpage(url, clip_id)
6931
6932 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6933 if not video_id:
6934 raise ExtractorError('Unable to find video ID')
6935
6936 clip_data = traverse_obj(data, (
6937 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6938 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6939 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6940 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6941
6942 return {
6943 '_type': 'url_transparent',
6944 'url': f'https://www.youtube.com/watch?v={video_id}',
6945 'ie_key': YoutubeIE.ie_key(),
6946 'id': clip_id,
6947 'section_start': int(clip_data['startTimeMs']) / 1000,
6948 'section_end': int(clip_data['endTimeMs']) / 1000,
6949 }
3cd786db 6950
6951
b032ff0f 6952class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
6953 IE_NAME = 'youtube:consent'
6954 IE_DESC = False # Do not list
6955 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
6956 _TESTS = [{
6957 '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',
6958 'info_dict': {
6959 'id': 'qVv6vCqciTM',
6960 'ext': 'mp4',
6961 'age_limit': 0,
6962 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
6963 'comment_count': int,
6964 'chapters': 'count:13',
6965 'upload_date': '20221223',
6966 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
6967 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
6968 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
6969 'like_count': int,
6970 'release_date': '20221223',
6971 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
6972 '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】',
6973 'view_count': int,
6974 'playable_in_embed': True,
6975 'duration': 4438,
6976 'availability': 'public',
6977 'channel_follower_count': int,
6978 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
6979 'categories': ['Entertainment'],
6980 'live_status': 'was_live',
6981 'release_timestamp': 1671793345,
6982 'channel': 'さなちゃんねる',
6983 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
6984 'uploader': 'さなちゃんねる',
6985 },
6986 'add_ie': ['Youtube'],
6987 'params': {'skip_download': 'Youtube'},
6988 }]
6989
6990 def _real_extract(self, url):
6991 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
6992 if not redirect_url:
6993 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
6994 return self.url_result(redirect_url)
6995
6996
772fd5cc
PH
6997class YoutubeTruncatedIDIE(InfoExtractor):
6998 IE_NAME = 'youtube:truncated_id'
6999 IE_DESC = False # Do not list
b95aab84 7000 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7001
7002 _TESTS = [{
7003 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7004 'only_matching': True,
7005 }]
7006
7007 def _real_extract(self, url):
7008 video_id = self._match_id(url)
7009 raise ExtractorError(
86e5f3ed 7010 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7011 expected=True)