]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/freesound] Workaround invalid URL in webpage (#6147)
[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:
b6ce9bb0 1015 (?:(?:v|embed|e|shorts)/(?!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'},
6e634cbe 2576 }
2eb88d95
PH
2577 ]
2578
f2e8dbcc 2579 _WEBPAGE_TESTS = [
2580 # YouTube <object> embed
2581 {
2582 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2583 'md5': '873c81d308b979f0e23ee7e620b312a3',
2584 'info_dict': {
2585 'id': 'msN87y-iEx0',
2586 'ext': 'mp4',
2587 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2588 'upload_date': '20080526',
2589 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2590 'uploader': 'Christopher Sykes',
2591 'uploader_id': 'ChristopherJSykes',
2592 'age_limit': 0,
2593 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2594 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2595 'playable_in_embed': True,
2596 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2597 'like_count': int,
2598 'comment_count': int,
2599 'channel': 'Christopher Sykes',
2600 'live_status': 'not_live',
2601 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2602 'availability': 'public',
2603 'duration': 195,
2604 'view_count': int,
2605 'categories': ['Science & Technology'],
2606 'channel_follower_count': int,
2607 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2608 },
2609 'params': {
2610 'skip_download': True,
2611 }
2612 },
2613 ]
2614
201c1459 2615 @classmethod
2616 def suitable(cls, url):
4dfbf869 2617 from ..utils import parse_qs
2618
201c1459 2619 qs = parse_qs(url)
2620 if qs.get('list', [None])[0]:
2621 return False
86e5f3ed 2622 return super().suitable(url)
201c1459 2623
e0df6211 2624 def __init__(self, *args, **kwargs):
86e5f3ed 2625 super().__init__(*args, **kwargs)
545cc85d 2626 self._code_cache = {}
83799698 2627 self._player_cache = {}
e0df6211 2628
4d37720a 2629 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2630 lock = threading.Lock()
185bf310 2631 start_time = time.time()
adbc4ec4
THD
2632 formats = [f for f in formats if f.get('is_from_start')]
2633
185bf310 2634 def refetch_manifest(format_id, delay):
2635 nonlocal formats, start_time, is_live
2636 if time.time() <= start_time + delay:
adbc4ec4
THD
2637 return
2638
2639 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2640 video_details = traverse_obj(
2641 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2642 microformats = traverse_obj(
2643 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2644 expected_type=dict, default=[])
4d37720a
L
2645 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2646 is_live = live_status == 'is_live'
185bf310 2647 start_time = time.time()
adbc4ec4 2648
185bf310 2649 def mpd_feed(format_id, delay):
adbc4ec4
THD
2650 """
2651 @returns (manifest_url, manifest_stream_number, is_live) or None
2652 """
253ac4ba 2653 for retry in self.RetryManager(fatal=False):
2654 with lock:
2655 refetch_manifest(format_id, delay)
2656
2657 f = next((f for f in formats if f['format_id'] == format_id), None)
2658 if not f:
2659 if not is_live:
2660 retry.error = f'{video_id}: Video is no longer live'
2661 else:
2662 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2663 continue
2664 return f['manifest_url'], f['manifest_stream_number'], is_live
2665 return None
adbc4ec4
THD
2666
2667 for f in formats:
4d37720a
L
2668 f['is_live'] = is_live
2669 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2670 live_start_time, mpd_feed, not is_live and f.copy())
2671 if is_live:
2672 f['fragments'] = gen
2673 f['protocol'] = 'http_dash_segments_generator'
2674 else:
2675 f['fragments'] = LazyList(gen({}))
2676 del f['is_from_start']
adbc4ec4 2677
4d37720a 2678 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2679 FETCH_SPAN, MAX_DURATION = 5, 432000
2680
2681 mpd_url, stream_number, is_live = None, None, True
2682
2683 begin_index = 0
2684 download_start_time = ctx.get('start') or time.time()
2685
2686 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2687 if lack_early_segments:
2688 self.report_warning(bug_reports_message(
2689 'Starting download from the last 120 hours of the live stream since '
2690 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2691 lack_early_segments = True
2692
2693 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2694 fragments, fragment_base_url = None, None
2695
a539f065 2696 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2697 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2698 # Obtain from MPD's maximum seq value
2699 old_mpd_url = mpd_url
185bf310 2700 last_error = ctx.pop('last_error', None)
14f25df2 2701 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2702 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2703 or (mpd_url, stream_number, False))
2704 if not refresh_sequence:
2705 if expire_fast and not is_live:
2706 return False, last_seq
2707 elif old_mpd_url == mpd_url:
2708 return True, last_seq
4d37720a
L
2709 if manifestless_orig_fmt:
2710 fmt_info = manifestless_orig_fmt
2711 else:
2712 try:
2713 fmts, _ = self._extract_mpd_formats_and_subtitles(
2714 mpd_url, None, note=False, errnote=False, fatal=False)
2715 except ExtractorError:
2716 fmts = None
2717 if not fmts:
2718 no_fragment_score += 2
2719 return False, last_seq
2720 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2721 fragments = fmt_info['fragments']
2722 fragment_base_url = fmt_info['fragment_base_url']
2723 assert fragment_base_url
2724
2725 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2726 return True, _last_seq
2727
4d37720a 2728 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2729 while is_live:
2730 fetch_time = time.time()
2731 if no_fragment_score > 30:
2732 return
2733 if last_segment_url:
2734 # Obtain from "X-Head-Seqnum" header value from each segment
2735 try:
2736 urlh = self._request_webpage(
2737 last_segment_url, None, note=False, errnote=False, fatal=False)
2738 except ExtractorError:
2739 urlh = None
2740 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2741 if last_seq is None:
a539f065 2742 no_fragment_score += 2
adbc4ec4
THD
2743 last_segment_url = None
2744 continue
2745 else:
a539f065
LNO
2746 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2747 no_fragment_score += 2
185bf310 2748 if not should_continue:
adbc4ec4
THD
2749 continue
2750
2751 if known_idx > last_seq:
2752 last_segment_url = None
2753 continue
2754
2755 last_seq += 1
2756
2757 if begin_index < 0 and known_idx < 0:
2758 # skip from the start when it's negative value
2759 known_idx = last_seq + begin_index
2760 if lack_early_segments:
2761 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2762 try:
2763 for idx in range(known_idx, last_seq):
2764 # do not update sequence here or you'll get skipped some part of it
a539f065 2765 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2766 if not should_continue:
adbc4ec4
THD
2767 known_idx = idx - 1
2768 raise ExtractorError('breaking out of outer loop')
2769 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2770 yield {
2771 'url': last_segment_url,
36195c44 2772 'fragment_count': last_seq,
adbc4ec4
THD
2773 }
2774 if known_idx == last_seq:
2775 no_fragment_score += 5
2776 else:
2777 no_fragment_score = 0
2778 known_idx = last_seq
2779 except ExtractorError:
2780 continue
2781
4d37720a
L
2782 if manifestless_orig_fmt:
2783 # Stop at the first iteration if running for post-live manifestless;
2784 # fragment count no longer increase since it starts
2785 break
2786
adbc4ec4
THD
2787 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2788
b6de707d 2789 def _extract_player_url(self, *ytcfgs, webpage=None):
2790 player_url = traverse_obj(
2791 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2792 get_all=False, expected_type=str)
11f9be09 2793 if not player_url:
b6de707d 2794 return
60f393e4 2795 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2796
b6de707d 2797 def _download_player_url(self, video_id, fatal=False):
2798 res = self._download_webpage(
2799 'https://www.youtube.com/iframe_api',
2800 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2801 if res:
2802 player_version = self._search_regex(
2803 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2804 if player_version:
2805 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2806
60064c53
PH
2807 def _signature_cache_id(self, example_sig):
2808 """ Return a string representation of a signature """
14f25df2 2809 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2810
e40c758c
S
2811 @classmethod
2812 def _extract_player_info(cls, player_url):
2813 for player_re in cls._PLAYER_INFO_RE:
2814 id_m = re.search(player_re, player_url)
2815 if id_m:
2816 break
2817 else:
c081b35c 2818 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2819 return id_m.group('id')
e40c758c 2820
404f611f 2821 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2822 player_id = self._extract_player_info(player_url)
2823 if player_id not in self._code_cache:
1276a43a 2824 code = self._download_webpage(
109dd3b2 2825 player_url, video_id, fatal=fatal,
2826 note='Downloading player ' + player_id,
2827 errnote='Download of %s failed' % player_url)
1276a43a 2828 if code:
2829 self._code_cache[player_id] = code
404f611f 2830 return self._code_cache.get(player_id)
109dd3b2 2831
e40c758c 2832 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2833 player_id = self._extract_player_info(player_url)
e0df6211 2834
c4417ddb 2835 # Read from filesystem cache
86e5f3ed 2836 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2837 assert os.path.basename(func_id) == func_id
a0e07d31 2838
ae61d108 2839 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2840 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2841
580ce007 2842 if not cache_spec:
2843 code = self._load_player(video_id, player_url)
404f611f 2844 if code:
109dd3b2 2845 res = self._parse_sig_js(code)
ac668111 2846 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2847 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2848 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2849
2850 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2851
60064c53 2852 def _print_sig_code(self, func, example_sig):
404f611f 2853 if not self.get_param('youtube_print_sig_code'):
2854 return
2855
edf3e38e
PH
2856 def gen_sig_code(idxs):
2857 def _genslice(start, end, step):
78caa52a 2858 starts = '' if start == 0 else str(start)
8bcc8756 2859 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2860 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2861 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2862
2863 step = None
7af808a5
PH
2864 # Quelch pyflakes warnings - start will be set when step is set
2865 start = '(Never used)'
edf3e38e
PH
2866 for i, prev in zip(idxs[1:], idxs[:-1]):
2867 if step is not None:
2868 if i - prev == step:
2869 continue
2870 yield _genslice(start, prev, step)
2871 step = None
2872 continue
2873 if i - prev in [-1, 1]:
2874 step = i - prev
2875 start = prev
2876 continue
2877 else:
78caa52a 2878 yield 's[%d]' % prev
edf3e38e 2879 if step is None:
78caa52a 2880 yield 's[%d]' % i
edf3e38e
PH
2881 else:
2882 yield _genslice(start, i, step)
2883
ac668111 2884 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2885 cache_res = func(test_string)
edf3e38e 2886 cache_spec = [ord(c) for c in cache_res]
78caa52a 2887 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2888 signature_id_tuple = '(%s)' % (
14f25df2 2889 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2890 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2891 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2892 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2893
e0df6211
PH
2894 def _parse_sig_js(self, jscode):
2895 funcname = self._search_regex(
abefc03f
S
2896 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2897 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
2898 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2899 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2900 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}\(a,\d+\)',
2901 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 2902 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2903 # Obsolete patterns
2904 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2905 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2906 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2907 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2908 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2909 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2910 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2911 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2912 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2913
2914 jsi = JSInterpreter(jscode)
2915 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2916 return lambda s: initial_function([s])
2917
580ce007 2918 def _cached(self, func, *cache_id):
2919 def inner(*args, **kwargs):
2920 if cache_id not in self._player_cache:
2921 try:
2922 self._player_cache[cache_id] = func(*args, **kwargs)
2923 except ExtractorError as e:
2924 self._player_cache[cache_id] = e
2925 except Exception as e:
2926 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2927
2928 ret = self._player_cache[cache_id]
2929 if isinstance(ret, Exception):
2930 raise ret
2931 return ret
2932 return inner
2933
545cc85d 2934 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2935 """Turn the encrypted s field into a working signature"""
580ce007 2936 extract_sig = self._cached(
2937 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2938 func = extract_sig(video_id, player_url, s)
2939 self._print_sig_code(func, s)
2940 return func(s)
404f611f 2941
2942 def _decrypt_nsig(self, s, video_id, player_url):
2943 """Turn the encrypted n field into a working signature"""
2944 if player_url is None:
2945 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2946 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2947
b505e851 2948 try:
2949 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2950 except ExtractorError as e:
2951 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 2952 if self.get_param('youtube_print_sig_code'):
2953 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2954
25836db6 2955 try:
2956 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2957 ret = extract_nsig(jsi, func_code)(s)
2958 except JSInterpreter.Exception as e:
2959 try:
992dc6b4 2960 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2961 except ExtractorError:
2962 raise e
2963 self.report_warning(
2964 f'Native nsig extraction failed: Trying with PhantomJS\n'
2965 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 2966 self.write_debug(e, only_once=True)
25836db6 2967
2968 args, func_body = func_code
2969 ret = jsi.execute(
2970 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2971 video_id=video_id, note='Executing signature code').strip()
580ce007 2972
2973 self.write_debug(f'Decrypted nsig {s} => {ret}')
2974 return ret
2975
90a1df30 2976 def _extract_n_function_name(self, jscode):
2977 funcname, idx = self._search_regex(
2978 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2979 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2980 if not idx:
2981 return funcname
2982
2983 return json.loads(js_to_json(self._search_regex(
2984 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2985 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2986
580ce007 2987 def _extract_n_function_code(self, video_id, player_url):
404f611f 2988 player_id = self._extract_player_info(player_url)
05deb747 2989 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 2990 jscode = func_code or self._load_player(video_id, player_url)
2991 jsi = JSInterpreter(jscode)
404f611f 2992
2993 if func_code:
580ce007 2994 return jsi, player_id, func_code
404f611f 2995
b505e851 2996 func_name = self._extract_n_function_name(jscode)
2997
2998 # For redundancy
2999 func_code = self._search_regex(
3000 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3001 # NB: The end of the regex is intentionally kept strict
3002 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3003 jscode, 'nsig function', group=('var', 'code'), default=None)
3004 if func_code:
3005 func_code = ([func_code[0]], func_code[1])
3006 else:
3007 self.write_debug('Extracting nsig function with jsinterp')
3008 func_code = jsi.extract_function_code(func_name)
3009
580ce007 3010 self.cache.store('youtube-nsig', player_id, func_code)
3011 return jsi, player_id, func_code
3012
3013 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3014 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3015
580ce007 3016 def extract_nsig(s):
25836db6 3017 try:
3018 ret = func([s])
3019 except JSInterpreter.Exception:
3020 raise
3021 except Exception as e:
3022 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3023
f6ca640b 3024 if ret.startswith('enhanced_except_'):
25836db6 3025 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3026 return ret
580ce007 3027
3028 return extract_nsig
e0df6211 3029
109dd3b2 3030 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3031 """
3032 Extract signatureTimestamp (sts)
3033 Required to tell API what sig/player version is in use.
3034 """
3035 sts = None
3036 if isinstance(ytcfg, dict):
3037 sts = int_or_none(ytcfg.get('STS'))
3038
3039 if not sts:
3040 # Attempt to extract from player
3041 if player_url is None:
3042 error_msg = 'Cannot extract signature timestamp without player_url.'
3043 if fatal:
3044 raise ExtractorError(error_msg)
3045 self.report_warning(error_msg)
3046 return
404f611f 3047 code = self._load_player(video_id, player_url, fatal=fatal)
3048 if code:
109dd3b2 3049 sts = int_or_none(self._search_regex(
3050 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3051 'JS player signature timestamp', group='sts', fatal=fatal))
3052 return sts
3053
11f9be09 3054 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3055 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3056 label = 'fully ' if is_full else ''
3057 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3058 expected_type=url_or_none)
3059 if not url:
3060 self.report_warning(f'Unable to mark {label}watched')
3061 return
14f25df2 3062 parsed_url = urllib.parse.urlparse(url)
3063 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3064
3065 # cpn generation algorithm is reverse engineered from base.js.
3066 # In fact it works even with dummy cpn.
3067 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3068 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3069
3070 # # more consistent results setting it to right before the end
3071 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3072
3073 qs.update({
3074 'ver': ['2'],
3075 'cpn': [cpn],
3076 'cmt': video_length,
3077 'el': 'detailpage', # otherwise defaults to "shorts"
3078 })
3079
3080 if is_full:
3081 # these seem to mark watchtime "history" in the real world
3082 # they're required, so send in a single value
3083 qs.update({
5318156f 3084 'st': 0,
06cc8f10
B
3085 'et': video_length,
3086 })
3087
14f25df2 3088 url = urllib.parse.urlunparse(
3089 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3090
3091 self._download_webpage(
3092 url, video_id, f'Marking {label}watched',
3093 'Unable to mark watched', fatal=False)
d77ab8e2 3094
bfd973ec 3095 @classmethod
3096 def _extract_from_webpage(cls, url, webpage):
3097 # Invidious Instances
3098 # https://github.com/yt-dlp/yt-dlp/issues/195
3099 # https://github.com/iv-org/invidious/pull/1730
3100 mobj = re.search(
3101 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3102 webpage)
3103 if mobj:
3104 yield cls.url_result(mobj.group('url'), cls)
3105 raise cls.StopExtraction()
3106
3107 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3108
3109 # lazyYT YouTube embed
bfd973ec 3110 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3111 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3112
3113 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3114 for m in re.findall(r'''(?x)<div[^>]+
3115 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3116 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3117 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3118
97665381
PH
3119 @classmethod
3120 def extract_id(cls, url):
ae61d108 3121 video_id = cls.get_temp_id(url)
3122 if not video_id:
3123 raise ExtractorError(f'Invalid URL: {url}')
3124 return video_id
c5e8d7af 3125
7c365c21 3126 def _extract_chapters_from_json(self, data, duration):
3127 chapter_list = traverse_obj(
3128 data, (
3129 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3130 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3131 ), expected_type=list)
3132
3133 return self._extract_chapters(
3134 chapter_list,
3135 chapter_time=lambda chapter: float_or_none(
3136 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3137 chapter_title=lambda chapter: traverse_obj(
3138 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3139 duration=duration)
3140
3141 def _extract_chapters_from_engagement_panel(self, data, duration):
3142 content_list = traverse_obj(
8bdd16b4 3143 data,
7c365c21 3144 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 3145 expected_type=list, default=[])
052e1350 3146 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3147 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3148
1890fc63 3149 return next(filter(None, (
3150 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3151 chapter_time, chapter_title, duration)
3152 for contents in content_list)), [])
7c365c21 3153
1890fc63 3154 def _extract_chapters_from_description(self, description, duration):
2e30b46f 3155 duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
3156 sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
1890fc63 3157 return self._extract_chapters(
2e30b46f 3158 re.findall(sep_re % (duration_re, r'.+?'), description or ''),
1890fc63 3159 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2e30b46f 3160 duration=duration, strict=False) or self._extract_chapters(
3161 re.findall(sep_re % (r'.+?', duration_re), description or ''),
3162 chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
1890fc63 3163 duration=duration, strict=False)
84213ea8 3164
1890fc63 3165 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3166 if not duration:
3167 return
3168 chapter_list = [{
3169 'start_time': chapter_time(chapter),
3170 'title': chapter_title(chapter),
3171 } for chapter in chapter_list or []]
3172 if not strict:
3173 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3174
a3976e07 3175 chapters = [{'start_time': 0}]
1890fc63 3176 for idx, chapter in enumerate(chapter_list):
a3976e07 3177 if chapter['start_time'] is None:
1890fc63 3178 self.report_warning(f'Incomplete chapter {idx}')
3179 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3180 chapters.append(chapter)
709ee214 3181 elif chapter not in chapters:
3182 self.report_warning(
3183 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3184 return chapters[1:]
84213ea8 3185
a1c5d2ca
M
3186 def _extract_comment(self, comment_renderer, parent=None):
3187 comment_id = comment_renderer.get('commentId')
3188 if not comment_id:
3189 return
fe93e2c4 3190
052e1350 3191 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3192
c26f9b99 3193 # Timestamp is an estimate calculated from the current time and time_text
3194 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3195 timestamp = self._parse_time_text(time_text)
3196
052e1350 3197 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3198 author_id = try_get(comment_renderer,
14f25df2 3199 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3200
49bd8c66 3201 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3202 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3203 author_thumbnail = try_get(comment_renderer,
14f25df2 3204 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3205
3206 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3207 is_favorited = 'creatorHeart' in (try_get(
3208 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3209 return {
3210 'id': comment_id,
3211 'text': text,
d92f5d5a 3212 'timestamp': timestamp,
a1c5d2ca
M
3213 'time_text': time_text,
3214 'like_count': votes,
97524332 3215 'is_favorited': is_favorited,
a1c5d2ca
M
3216 'author': author,
3217 'author_id': author_id,
3218 'author_thumbnail': author_thumbnail,
3219 'author_is_uploader': author_is_uploader,
3220 'parent': parent or 'root'
3221 }
3222
46383212 3223 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3224
3225 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3226
3227 def extract_header(contents):
2d6659b9 3228 _continuation = None
3229 for content in contents:
46383212 3230 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3231 expected_comment_count = self._get_count(
3232 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3233
2d6659b9 3234 if expected_comment_count:
46383212 3235 tracker['est_total'] = expected_comment_count
3236 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3237 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3238
3239 sort_menu_item = try_get(
3240 comments_header_renderer,
3241 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3242 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3243
3244 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3245 if not _continuation:
3246 continue
3247
46383212 3248 sort_text = str_or_none(sort_menu_item.get('title'))
3249 if not sort_text:
2d6659b9 3250 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3251 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3252 break
a2160aa4 3253 return _continuation
a1c5d2ca 3254
2d6659b9 3255 def extract_thread(contents):
a1c5d2ca 3256 if not parent:
46383212 3257 tracker['current_page_thread'] = 0
a1c5d2ca 3258 for content in contents:
46383212 3259 if not parent and tracker['total_parent_comments'] >= max_parents:
3260 yield
a1c5d2ca 3261 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3262 comment_renderer = get_first(
3263 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3264 expected_type=dict, default={})
a1c5d2ca 3265
a1c5d2ca
M
3266 comment = self._extract_comment(comment_renderer, parent)
3267 if not comment:
3268 continue
46383212 3269
3270 tracker['running_total'] += 1
3271 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3272 yield comment
46383212 3273
a1c5d2ca
M
3274 # Attempt to get the replies
3275 comment_replies_renderer = try_get(
3276 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3277
3278 if comment_replies_renderer:
46383212 3279 tracker['current_page_thread'] += 1
a1c5d2ca 3280 comment_entries_iter = self._comment_entries(
99e9e001 3281 comment_replies_renderer, ytcfg, video_id,
46383212 3282 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3283 yield from itertools.islice(comment_entries_iter, min(
3284 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3285
46383212 3286 # Keeps track of counts across recursive calls
3287 if not tracker:
3288 tracker = dict(
3289 running_total=0,
3290 est_total=0,
3291 current_page_thread=0,
3292 total_parent_comments=0,
3293 total_reply_comments=0)
3294
3295 # TODO: Deprecated
2d6659b9 3296 # YouTube comments have a max depth of 2
46383212 3297 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3298 if max_depth:
da4db748 3299 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3300 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3301 if max_depth == 1 and parent:
3302 return
a1c5d2ca 3303
46383212 3304 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3305 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3306
46383212 3307 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3308
46383212 3309 response = None
6e634cbe 3310 is_forced_continuation = False
2d6659b9 3311 is_first_continuation = parent is None
6e634cbe 3312 if is_first_continuation and not continuation:
3313 # Sometimes you can get comments by generating the continuation yourself,
3314 # even if YouTube initially reports them being disabled - e.g. stories comments.
3315 # Note: if the comment section is actually disabled, YouTube may return a response with
3316 # required check_get_keys missing. So we will disable that check initially in this case.
3317 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3318 is_forced_continuation = True
a1c5d2ca
M
3319
3320 for page_num in itertools.count(0):
3321 if not continuation:
3322 break
46383212 3323 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3324 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3325 if page_num == 0:
3326 if is_first_continuation:
3327 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3328 else:
2d6659b9 3329 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3330 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3331 else:
3332 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3333 ' ' if parent else '', ' replies' if parent else '',
3334 page_num, comment_prog_str)
e72e48c5
M
3335 try:
3336 response = self._extract_response(
3337 item_id=None, query=continuation,
3338 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3339 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3340 except ExtractorError as e:
3341 # Ignore incomplete data error for replies if retries didn't work.
3342 # This is to allow any other parent comments and comment threads to be downloaded.
3343 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3344 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3345 self.report_warning(
3346 'Received incomplete data for a comment reply thread and retrying did not help. '
3347 'Ignoring to let other comments be downloaded.')
3348 else:
3349 raise
6e634cbe 3350 is_forced_continuation = False
46383212 3351 continuation_contents = traverse_obj(
3352 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3353
2d6659b9 3354 continuation = None
46383212 3355 for continuation_section in continuation_contents:
3356 continuation_items = traverse_obj(
3357 continuation_section,
3358 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3359 get_all=False, expected_type=list) or []
3360 if is_first_continuation:
3361 continuation = extract_header(continuation_items)
3362 is_first_continuation = False
2d6659b9 3363 if continuation:
a1c5d2ca 3364 break
46383212 3365 continue
a1c5d2ca 3366
46383212 3367 for entry in extract_thread(continuation_items):
3368 if not entry:
3369 return
3370 yield entry
3371 continuation = self._extract_continuation({'contents': continuation_items})
3372 if continuation:
2d6659b9 3373 break
a1c5d2ca 3374
6e634cbe 3375 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3376 if message and not parent and tracker['running_total'] == 0:
3377 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3378 raise self.CommentsDisabled
6e634cbe 3379
3380 @staticmethod
3381 def _generate_comment_continuation(video_id):
3382 """
3383 Generates initial comment section continuation token from given video id
3384 """
3385 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3386 return base64.b64encode(token.encode()).decode()
3387
a2160aa4 3388 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3389 """Entry for comment extraction"""
2d6659b9 3390 def _real_comment_extract(contents):
aae16f6e 3391 renderer = next((
3392 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3393 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3394 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3395
a2160aa4 3396 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3397 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3398
109dd3b2 3399 @staticmethod
99e9e001 3400 def _get_checkok_params():
3401 return {'contentCheckOk': True, 'racyCheckOk': True}
3402
3403 @classmethod
3404 def _generate_player_context(cls, sts=None):
109dd3b2 3405 context = {
3406 'html5Preference': 'HTML5_PREF_WANTS',
3407 }
3408 if sts is not None:
3409 context['signatureTimestamp'] = sts
3410 return {
3411 'playbackContext': {
3412 'contentPlaybackContext': context
a1a7907b 3413 },
99e9e001 3414 **cls._get_checkok_params()
109dd3b2 3415 }
3416
e7e94f2a
D
3417 @staticmethod
3418 def _is_agegated(player_response):
3419 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3420 return True
e7e94f2a
D
3421
3422 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3423 AGE_GATE_REASONS = (
3424 'confirm your age', 'age-restricted', 'inappropriate', # reason
3425 'age_verification_required', 'age_check_required', # status
3426 )
3427 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3428
3429 @staticmethod
3430 def _is_unplayable(player_response):
3431 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3432
50ac0e54 3433 _STORY_PLAYER_PARAMS = '8AEB'
3434
3435 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3436
11f9be09 3437 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3438 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3439 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3440 headers = self.generate_api_headers(
99e9e001 3441 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3442
6e634cbe 3443 yt_query = {
3444 'videoId': video_id,
6e634cbe 3445 }
50ac0e54 3446 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3447 yt_query['params'] = self._STORY_PLAYER_PARAMS
3448
11f9be09 3449 yt_query.update(self._generate_player_context(sts))
3450 return self._extract_response(
3451 item_id=video_id, ep='player', query=yt_query,
379e44ed 3452 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3453 default_client=client,
11f9be09 3454 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3455 ) or None
3456
11f9be09 3457 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3458 requested_clients = []
d0d012d4 3459 default = ['android', 'web']
000c15a4 3460 allowed_clients = sorted(
86e5f3ed 3461 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3462 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3463 for client in self._configuration_arg('player_client'):
3464 if client in allowed_clients:
3465 requested_clients.append(client)
d0d012d4 3466 elif client == 'default':
3467 requested_clients.extend(default)
b4c055ba 3468 elif client == 'all':
3469 requested_clients.extend(allowed_clients)
3470 else:
3471 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3472 if not requested_clients:
d0d012d4 3473 requested_clients = default
cf7e015f 3474
11f9be09 3475 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3476 requested_clients.extend(
e7e94f2a 3477 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3478
11f9be09 3479 return orderedSet(requested_clients)
cf7e015f 3480
50ac0e54 3481 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3482 initial_pr = None
3483 if webpage:
b7c47b74 3484 initial_pr = self._search_json(
3485 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3486
ae729626 3487 all_clients = set(clients)
c0bc527b 3488 clients = clients[::-1]
b6de707d 3489 prs = []
e7e94f2a 3490
ae729626 3491 def append_client(*client_names):
e7870111 3492 """ Append the first client name that exists but not already used """
ae729626 3493 for client_name in client_names:
e7870111
D
3494 actual_client = _split_innertube_client(client_name)[0]
3495 if actual_client in INNERTUBE_CLIENTS:
3496 if actual_client not in all_clients:
ae729626 3497 clients.append(client_name)
e7870111
D
3498 all_clients.add(actual_client)
3499 return
e7e94f2a 3500
379e44ed 3501 # Android player_response does not have microFormats which are needed for
3502 # extraction of some data. So we return the initial_pr with formats
3503 # stripped out even if not requested by the user
3504 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3505 if initial_pr:
3506 pr = dict(initial_pr)
3507 pr['streamingData'] = None
b6de707d 3508 prs.append(pr)
379e44ed 3509
3510 last_error = None
b6de707d 3511 tried_iframe_fallback = False
3512 player_url = None
c0bc527b 3513 while clients:
e7870111 3514 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3515 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3516 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3517 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3518
b6de707d 3519 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3520 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3521 if 'js' in self._configuration_arg('player_skip'):
3522 require_js_player = False
3523 player_url = None
3524
3525 if not player_url and not tried_iframe_fallback and require_js_player:
3526 player_url = self._download_player_url(video_id)
3527 tried_iframe_fallback = True
3528
379e44ed 3529 try:
3530 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3531 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3532 except ExtractorError as e:
3533 if last_error:
3534 self.report_warning(last_error)
3535 last_error = e
3536 continue
3537
11f9be09 3538 if pr:
a3e96421 3539 # YouTube may return a different video player response than expected.
3540 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3541 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3542 if pr_video_id and pr_video_id != video_id:
3543 self.report_warning(
c7dcf0b3 3544 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3545 else:
3546 prs.append(pr)
c0bc527b 3547
e7e94f2a 3548 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3549 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3550 append_client(f'{base_client}_creator')
e7e94f2a 3551 elif self._is_agegated(pr):
e7870111
D
3552 if variant == 'tv_embedded':
3553 append_client(f'{base_client}_embedded')
3554 elif not variant:
3555 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3556
379e44ed 3557 if last_error:
b6de707d 3558 if not len(prs):
379e44ed 3559 raise last_error
3560 self.report_warning(last_error)
b6de707d 3561 return prs, player_url
11f9be09 3562
4d37720a
L
3563 def _needs_live_processing(self, live_status, duration):
3564 if (live_status == 'is_live' and self.get_param('live_from_start')
3565 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3566 return live_status
3567
3568 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a4894d3e 3569 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3570 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3571 q = qualities([
2a9c6dcd 3572 # Normally tiny is the smallest video-only formats. But
3573 # audio-only formats with unknown quality may get tagged as tiny
3574 'tiny',
3575 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3576 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3577 ])
11f9be09 3578 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3579
545cc85d 3580 for fmt in streaming_formats:
727029c5 3581 if fmt.get('targetDurationSec'):
545cc85d 3582 continue
321bf820 3583
cc2db878 3584 itag = str_or_none(fmt.get('itag'))
9297939e 3585 audio_track = fmt.get('audioTrack') or {}
9bb85699 3586 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
9297939e 3587 if stream_id in stream_ids:
3588 continue
3589
cc2db878 3590 quality = fmt.get('quality')
2a9c6dcd 3591 height = int_or_none(fmt.get('height'))
d3fc8074 3592 if quality == 'tiny' or not quality:
3593 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3594 # The 3gp format (17) in android client has a quality of "small",
3595 # but is actually worse than other formats
3596 if itag == '17':
3597 quality = 'tiny'
3598 if quality:
3599 if itag:
3600 itag_qualities[itag] = quality
3601 if height:
3602 res_qualities[height] = quality
cc2db878 3603 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3604 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3605 # number of fragment that would subsequently requested with (`&sq=N`)
3606 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3607 continue
3608
545cc85d 3609 fmt_url = fmt.get('url')
3610 if not fmt_url:
14f25df2 3611 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3612 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3613 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3614 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3615 continue
52023f12 3616 try:
3617 fmt_url += '&%s=%s' % (
3618 traverse_obj(sc, ('sp', -1)) or 'signature',
3619 self._decrypt_signature(encrypted_sig, video_id, player_url)
3620 )
3621 except ExtractorError as e:
580ce007 3622 self.report_warning('Signature extraction failed: Some formats may be missing',
3623 video_id=video_id, only_once=True)
52023f12 3624 self.write_debug(e, only_once=True)
201e9eaa 3625 continue
545cc85d 3626
404f611f 3627 query = parse_qs(fmt_url)
3628 throttled = False
b2916526 3629 if query.get('n'):
404f611f 3630 try:
580ce007 3631 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3632 fmt_url = update_url_query(fmt_url, {
580ce007 3633 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3634 })
404f611f 3635 except ExtractorError as e:
25836db6 3636 phantomjs_hint = ''
3637 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3638 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3639 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3640 if player_url:
3641 self.report_warning(
3642 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3643 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3644 self.write_debug(e, only_once=True)
3645 else:
3646 self.report_warning(
3647 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3648 video_id=video_id, only_once=True)
404f611f 3649 throttled = True
3650
0ad92dfb 3651 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3652 language_preference = (
3653 10 if audio_track.get('audioIsDefault') and 10
3654 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3655 else -1)
0ad92dfb 3656 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3657 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3658 # Make sure to avoid false positives with small duration differences.
62b58c09 3659 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3660 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3661 if is_damaged:
0f06bcd7 3662 self.report_warning(
3663 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3664 dct = {
3665 'asr': int_or_none(fmt.get('audioSampleRate')),
3666 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3667 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3668 'format_note': join_nonempty(
26e8e044 3669 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3670 ' (default)' if language_preference > 0 else ''),
404f611f 3671 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
9bb85699 3672 'DRC' if fmt.get('isDrc') else None,
a4166234 3673 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3674 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3675 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3676 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3677 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3678 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3679 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3680 'height': height,
9bb85699 3681 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3682 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3683 'tbr': tbr,
545cc85d 3684 'url': fmt_url,
2a9c6dcd 3685 'width': int_or_none(fmt.get('width')),
ab6df717 3686 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3687 'desc' if language_preference < -1 else '') or None,
ab6df717 3688 'language_preference': language_preference,
a405b38f 3689 # Strictly de-prioritize damaged and 3gp formats
3690 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3691 }
60bdb7bd 3692 mime_mobj = re.match(
3693 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3694 if mime_mobj:
3695 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3696 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3697 no_audio = dct.get('acodec') == 'none'
3698 no_video = dct.get('vcodec') == 'none'
3699 if no_audio:
3700 dct['vbr'] = tbr
3701 if no_video:
3702 dct['abr'] = tbr
3703 if no_audio or no_video:
545cc85d 3704 dct['downloader_options'] = {
3705 # Youtube throttles chunks >~10M
3706 'http_chunk_size': 10485760,
bf1317d2 3707 }
7c60c33e 3708 if dct.get('ext'):
3709 dct['container'] = dct['ext'] + '_dash'
a4894d3e 3710
3711 if itag:
3712 itags[itag].add(('https', dct.get('language')))
3713 stream_ids.append(stream_id)
11f9be09 3714 yield dct
545cc85d 3715
4d37720a
L
3716 needs_live_processing = self._needs_live_processing(live_status, duration)
3717 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3718
3719 skip_manifests = set(self._configuration_arg('skip'))
3720 if (not self.get_param('youtube_include_hls_manifest', True)
3721 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3722 or needs_live_processing and skip_bad_formats):
3723 skip_manifests.add('hls')
3724
0f06bcd7 3725 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3726 skip_manifests.add('dash')
3727 if self._configuration_arg('include_live_dash'):
3728 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3729 'Use include_incomplete_formats extractor argument instead')
3730 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3731 skip_manifests.add('dash')
5d3a0e79 3732
a0bb6ce5 3733 def process_manifest_format(f, proto, itag):
a4894d3e 3734 key = (proto, f.get('language'))
3735 if key in itags[itag]:
3736 return False
3737 itags[itag].add(key)
3738
3739 if any(p != proto for p, _ in itags[itag]):
3740 f['format_id'] = f'{itag}-{proto}'
3741 elif itag:
a0bb6ce5 3742 f['format_id'] = itag
a0bb6ce5 3743
b25cac65 3744 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3745 if f['quality'] == -1 and f.get('height'):
3746 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3747 return True
2a9c6dcd 3748
c646d76f 3749 subtitles = {}
11f9be09 3750 for sd in streaming_data:
4d37720a 3751 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3752 if hls_manifest_url:
4d37720a
L
3753 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3754 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3755 subtitles = self._merge_subtitles(subs, subtitles)
3756 for f in fmts:
a0bb6ce5 3757 if process_manifest_format(f, 'hls', self._search_regex(
3758 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3759 yield f
545cc85d 3760
4d37720a 3761 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3762 if dash_manifest_url:
c646d76f 3763 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3764 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3765 for f in formats:
a0bb6ce5 3766 if process_manifest_format(f, 'dash', f['format_id']):
3767 f['filesize'] = int_or_none(self._search_regex(
3768 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3769 if needs_live_processing:
adbc4ec4
THD
3770 f['is_from_start'] = True
3771
a0bb6ce5 3772 yield f
c646d76f 3773 yield subtitles
11f9be09 3774
720c3099 3775 def _extract_storyboard(self, player_responses, duration):
3776 spec = get_first(
3777 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3778 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3779 if not base_url:
720c3099 3780 return
720c3099 3781 L = len(spec) - 1
3782 for i, args in enumerate(spec):
3783 args = args.split('#')
3784 counts = list(map(int_or_none, args[:5]))
3785 if len(args) != 8 or not all(counts):
3786 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3787 continue
3788 width, height, frame_count, cols, rows = counts
3789 N, sigh = args[6:]
3790
3791 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3792 fragment_count = frame_count / (cols * rows)
3793 fragment_duration = duration / fragment_count
3794 yield {
3795 'format_id': f'sb{i}',
3796 'format_note': 'storyboard',
3797 'ext': 'mhtml',
3798 'protocol': 'mhtml',
3799 'acodec': 'none',
3800 'vcodec': 'none',
3801 'url': url,
3802 'width': width,
3803 'height': height,
45e8a04e 3804 'fps': frame_count / duration,
3805 'rows': rows,
3806 'columns': cols,
720c3099 3807 'fragments': [{
b3edc806 3808 'url': url.replace('$M', str(j)),
720c3099 3809 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3810 } for j in range(math.ceil(fragment_count))],
3811 }
3812
adbc4ec4 3813 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3814 webpage = None
3815 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3816 query = {'bpctr': '9999999999', 'has_verified': '1'}
3817 if smuggled_data.get('is_story'):
3818 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3819 webpage = self._download_webpage(
50ac0e54 3820 webpage_url, video_id, fatal=False, query=query)
11f9be09 3821
3822 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3823
b6de707d 3824 player_responses, player_url = self._extract_player_responses(
11f9be09 3825 self._get_requested_clients(url, smuggled_data),
50ac0e54 3826 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3827
adbc4ec4
THD
3828 return webpage, master_ytcfg, player_responses, player_url
3829
a1b2d843 3830 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3831 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3832 is_live = get_first(video_details, 'isLive')
3833 if is_live is None:
3834 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3835 live_content = get_first(video_details, 'isLiveContent')
3836 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3837 post_live = get_first(video_details, 'isPostLiveDvr')
3838 live_status = ('post_live' if post_live
3839 else 'is_live' if is_live
3840 else 'is_upcoming' if is_upcoming
6678a4f0 3841 else 'was_live' if live_content
3842 else 'not_live' if False in (is_live, live_content)
3843 else None)
adbc4ec4 3844 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3845 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3846
4d37720a 3847 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3848
3849 def _real_extract(self, url):
3850 url, smuggled_data = unsmuggle_url(url, {})
3851 video_id = self._match_id(url)
3852
3853 base_url = self.http_scheme() + '//www.youtube.com/'
3854 webpage_url = base_url + 'watch?v=' + video_id
3855
3856 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3857
11f9be09 3858 playability_statuses = traverse_obj(
3859 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3860
3861 trailer_video_id = get_first(
3862 playability_statuses,
3863 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3864 expected_type=str)
3865 if trailer_video_id:
3866 return self.url_result(
3867 trailer_video_id, self.ie_key(), trailer_video_id)
3868
3869 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3870 if webpage else (lambda x: None))
3871
3872 video_details = traverse_obj(
3873 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3874 microformats = traverse_obj(
3875 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3876 expected_type=dict, default=[])
c26f9b99 3877
3878 translated_title = self._get_text(microformats, (..., 'title'))
3879 video_title = (self._preferred_lang and translated_title
3880 or get_first(video_details, 'title') # primary
3881 or translated_title
3882 or search_meta(['og:title', 'twitter:title', 'title']))
3883 translated_description = self._get_text(microformats, (..., 'description'))
3884 original_description = get_first(video_details, 'shortDescription')
3885 video_description = (
3886 self._preferred_lang and translated_description
3887 # If original description is blank, it will be an empty string.
3888 # Do not prefer translated description in this case.
3889 or original_description if original_description is not None else translated_description)
11f9be09 3890
d89257f3 3891 multifeed_metadata_list = get_first(
3892 player_responses,
3893 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3894 expected_type=str)
3895 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3896 if self.get_param('noplaylist'):
11f9be09 3897 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3898 else:
3899 entries = []
3900 feed_ids = []
3901 for feed in multifeed_metadata_list.split(','):
3902 # Unquote should take place before split on comma (,) since textual
3903 # fields may contain comma as well (see
3904 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3905 feed_data = urllib.parse.parse_qs(
ac668111 3906 urllib.parse.unquote_plus(feed))
d89257f3 3907
3908 def feed_entry(name):
3909 return try_get(
14f25df2 3910 feed_data, lambda x: x[name][0], str)
d89257f3 3911
3912 feed_id = feed_entry('id')
3913 if not feed_id:
3914 continue
3915 feed_title = feed_entry('title')
3916 title = video_title
3917 if feed_title:
3918 title += ' (%s)' % feed_title
3919 entries.append({
3920 '_type': 'url_transparent',
3921 'ie_key': 'Youtube',
3922 'url': smuggle_url(
3923 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3924 {'force_singlefeed': True}),
3925 'title': title,
3926 })
3927 feed_ids.append(feed_id)
3928 self.to_screen(
3929 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3930 % (', '.join(feed_ids), video_id))
3931 return self.playlist_result(
3932 entries, video_id, video_title, video_description)
11f9be09 3933
9da6612b 3934 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
3935 or int_or_none(get_first(microformats, 'lengthSeconds'))
3936 or parse_duration(search_meta('duration')) or None)
a1b2d843 3937
4d37720a
L
3938 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3939 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3940 if live_status == 'post_live':
3941 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3942
545cc85d 3943 if not formats:
11f9be09 3944 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3945 self.report_drm(video_id)
11f9be09 3946 pemr = get_first(
3947 playability_statuses,
3948 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3949 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3950 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3951 if subreason:
545cc85d 3952 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3953 countries = get_first(microformats, 'availableCountries')
545cc85d 3954 if not countries:
3955 regions_allowed = search_meta('regionsAllowed')
3956 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3957 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3958 reason += f'. {subreason}'
545cc85d 3959 if reason:
b7da73eb 3960 self.raise_no_formats(reason, expected=True)
bf1317d2 3961
11f9be09 3962 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3963 if not keywords and webpage:
3964 keywords = [
3965 unescapeHTML(m.group('content'))
3966 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3967 for keyword in keywords:
3968 if keyword.startswith('yt:stretch='):
201c1459 3969 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3970 if mobj:
3971 # NB: float is intentional for forcing float division
3972 w, h = (float(v) for v in mobj.groups())
3973 if w > 0 and h > 0:
3974 ratio = w / h
3975 for f in formats:
3976 if f.get('vcodec') != 'none':
3977 f['stretched_ratio'] = ratio
3978 break
a709d873 3979 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3980 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3981 if thumbnail_url:
3982 thumbnails.append({
3983 'url': thumbnail_url,
ff2751ac 3984 })
fccf5021 3985 original_thumbnails = thumbnails.copy()
3986
0ba692ac 3987 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3988 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3989 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3990 thumbnail_names = [
962ffcf8 3991 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3992 # in resolution, these are not the custom thumbnail. So de-prioritize them
3993 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3994 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3995 ]
cca80fe6 3996 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3997 thumbnails.extend({
3998 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3999 video_id=video_id, name=name, ext=ext,
4d37720a 4000 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4001 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4002 for thumb in thumbnails:
cca80fe6 4003 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4004 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4005 self._remove_duplicate_formats(thumbnails)
fccf5021 4006 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4007
7ea65411 4008 category = get_first(microformats, 'category') or search_meta('genre')
4009 channel_id = str_or_none(
4010 get_first(video_details, 'channelId')
4011 or get_first(microformats, 'externalChannelId')
4012 or search_meta('channelId'))
7ea65411 4013 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4014
adbc4ec4
THD
4015 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4016 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4017 if not duration and live_end_time and live_start_time:
4018 duration = live_end_time - live_start_time
4019
4d37720a
L
4020 needs_live_processing = self._needs_live_processing(live_status, duration)
4021
4022 def is_bad_format(fmt):
4023 if needs_live_processing and not fmt.get('is_from_start'):
4024 return True
4025 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4026 and fmt.get('protocol') == 'http_dash_segments'):
4027 return True
4028
4029 for fmt in filter(is_bad_format, formats):
4030 fmt['preference'] = (fmt.get('preference') or -1) - 10
4031 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4032
4033 if needs_live_processing:
4034 self._prepare_live_from_start_formats(
4035 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4036
720c3099 4037 formats.extend(self._extract_storyboard(player_responses, duration))
4038
545cc85d 4039 info = {
4040 'id': video_id,
39ca3b5c 4041 'title': video_title,
545cc85d 4042 'formats': formats,
4043 'thumbnails': thumbnails,
fccf5021 4044 # The best thumbnail that we are sure exists. Prevents unnecessary
4045 # URL checking if user don't care about getting the best possible thumbnail
4046 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4047 'description': video_description,
11f9be09 4048 'uploader': get_first(video_details, 'author'),
545cc85d 4049 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
4050 'uploader_url': owner_profile_url,
4051 'channel_id': channel_id,
a70635b8 4052 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 4053 'duration': duration,
4054 'view_count': int_or_none(
11f9be09 4055 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4056 or search_meta('interactionCount')),
11f9be09 4057 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4058 'age_limit': 18 if (
11f9be09 4059 get_first(microformats, 'isFamilySafe') is False
545cc85d 4060 or search_meta('isFamilyFriendly') == 'false'
4061 or search_meta('og:restrictions:age') == '18+') else 0,
4062 'webpage_url': webpage_url,
4063 'categories': [category] if category else None,
4064 'tags': keywords,
11f9be09 4065 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4066 'live_status': live_status,
adbc4ec4 4067 'release_timestamp': live_start_time,
9f14daf2 4068 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4069 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4070 }
b477fc13 4071
c646d76f 4072 subtitles = {}
3944e7af 4073 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4074 if pctr:
ecdc9049 4075 def get_lang_code(track):
4076 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4077 or track.get('languageCode'))
4078
4079 # Converted into dicts to remove duplicates
4080 captions = {
4081 get_lang_code(sub): sub
4082 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
4083 translation_languages = {
4084 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4085 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
4086
774d79cc 4087 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4088 lang_subs = container.setdefault(lang_code, [])
545cc85d 4089 for fmt in self._SUBTITLE_FORMATS:
4090 query.update({
4091 'fmt': fmt,
4092 })
4093 lang_subs.append({
4094 'ext': fmt,
60f393e4 4095 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4096 'name': sub_name,
545cc85d 4097 })
7e72694b 4098
07b47084 4099 # NB: Constructing the full subtitle dictionary is slow
4100 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4101 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4102 for lang_code, caption_track in captions.items():
4103 base_url = caption_track.get('baseUrl')
1235d333 4104 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4105 if not base_url:
4106 continue
ecdc9049 4107 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4108 if caption_track.get('kind') != 'asr':
545cc85d 4109 if not lang_code:
4110 continue
4111 process_language(
ecdc9049 4112 subtitles, base_url, lang_code, lang_name, {})
4113 if not caption_track.get('isTranslatable'):
4114 continue
3944e7af 4115 for trans_code, trans_name in translation_languages.items():
4116 if not trans_code:
545cc85d 4117 continue
1235d333 4118 orig_trans_code = trans_code
71eb82d1 4119 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4120 if not get_translated_subs:
18e49408 4121 continue
ecdc9049 4122 trans_code += f'-{lang_code}'
a70635b8 4123 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 4124 # Add an "-orig" label to the original language so that it can be distinguished.
4125 # The subs are returned without "-orig" as well for compatibility
1235d333 4126 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 4127 process_language(
d49669ac 4128 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4129 # Setting tlang=lang returns damaged subtitles.
d49669ac 4130 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4131 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4132
4133 info['automatic_captions'] = automatic_captions
4134 info['subtitles'] = subtitles
7e72694b 4135
14f25df2 4136 parsed_url = urllib.parse.urlparse(url)
545cc85d 4137 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4138 query = urllib.parse.parse_qs(component)
545cc85d 4139 for k, v in query.items():
4140 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4141 d_k += '_time'
4142 if d_k not in info and k in s_ks:
4143 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4144
4145 # Youtube Music Auto-generated description
822b9d9c 4146 if video_description:
1890fc63 4147 mobj = re.search(
4148 r'''(?xs)
4149 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4150 (?P<album>[^\n]+)
4151 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4152 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4153 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4154 .+\nAuto-generated\ by\ YouTube\.\s*$
4155 ''', video_description)
822b9d9c 4156 if mobj:
822b9d9c
RA
4157 release_year = mobj.group('release_year')
4158 release_date = mobj.group('release_date')
4159 if release_date:
4160 release_date = release_date.replace('-', '')
4161 if not release_year:
545cc85d 4162 release_year = release_date[:4]
4163 info.update({
4164 'album': mobj.group('album'.strip()),
4165 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4166 'track': mobj.group('track').strip(),
4167 'release_date': release_date,
cc2db878 4168 'release_year': int_or_none(release_year),
545cc85d 4169 })
7e72694b 4170
545cc85d 4171 initial_data = None
4172 if webpage:
56ba69e4 4173 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4174 if not initial_data:
99e9e001 4175 query = {'videoId': video_id}
4176 query.update(self._get_checkok_params())
109dd3b2 4177 initial_data = self._extract_response(
4178 item_id=video_id, ep='next', fatal=False,
99e9e001 4179 ytcfg=master_ytcfg, query=query,
4180 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4181 note='Downloading initial data API JSON')
545cc85d 4182
0df111a3 4183 info['comment_count'] = traverse_obj(initial_data, (
4184 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4185 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4186 ), (
4187 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4188 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4189 ), expected_type=int_or_none, get_all=False)
4190
19a03940 4191 try: # This will error if there is no livechat
c60ee3a2 4192 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4193 except (KeyError, IndexError, TypeError):
4194 pass
4195 else:
ecdc9049 4196 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4197 # url is needed to set cookies
4198 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4199 'video_id': video_id,
4200 'ext': 'json',
4d37720a
L
4201 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4202 else 'youtube_live_chat_replay'),
c60ee3a2 4203 }]
545cc85d 4204
4205 if initial_data:
7c365c21 4206 info['chapters'] = (
4207 self._extract_chapters_from_json(initial_data, duration)
4208 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4209 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4210 or None)
545cc85d 4211
17322130 4212 contents = traverse_obj(
4213 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4214 expected_type=list, default=[])
4215
4216 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4217 if vpir:
4218 stl = vpir.get('superTitleLink')
4219 if stl:
4220 stl = self._get_text(stl)
4221 if try_get(
4222 vpir,
4223 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4224 info['location'] = stl
4225 else:
affc4fef 4226 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4227 if mobj:
545cc85d 4228 info.update({
17322130 4229 'series': mobj.group(1),
4230 'season_number': int(mobj.group(2)),
4231 'episode_number': int(mobj.group(3)),
545cc85d 4232 })
17322130 4233 for tlb in (try_get(
4234 vpir,
4235 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4236 list) or []):
3ffb2f5b 4237 tbrs = variadic(
4238 traverse_obj(
4239 tlb, 'toggleButtonRenderer',
4240 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4241 default=[]))
4242 for tbr in tbrs:
4243 for getter, regex in [(
4244 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4245 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4246 lambda x: x['accessibility'],
4247 lambda x: x['accessibilityData']['accessibilityData'],
4248 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4249 label = (try_get(tbr, getter, dict) or {}).get('label')
4250 if label:
4251 mobj = re.match(regex, label)
4252 if mobj:
4253 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4254 break
17322130 4255 sbr_tooltip = try_get(
4256 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4257 if sbr_tooltip:
4258 like_count, dislike_count = sbr_tooltip.split(' / ')
4259 info.update({
4260 'like_count': str_to_int(like_count),
4261 'dislike_count': str_to_int(dislike_count),
4262 })
867c66ff
M
4263 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4264 if vcr:
4265 vc = self._get_count(vcr, 'viewCount')
4266 # Upcoming premieres with waiting count are treated as live here
4267 if vcr.get('isLive'):
4268 info['concurrent_view_count'] = vc
4269 elif info.get('view_count') is None:
4270 info['view_count'] = vc
4271
17322130 4272 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4273 if vsir:
4274 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4275 info.update({
4276 'channel': self._get_text(vor, 'title'),
4277 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4278
4279 rows = try_get(
4280 vsir,
4281 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4282 list) or []
4283 multiple_songs = False
4284 for row in rows:
4285 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4286 multiple_songs = True
4287 break
4288 for row in rows:
4289 mrr = row.get('metadataRowRenderer') or {}
4290 mrr_title = mrr.get('title')
4291 if not mrr_title:
4292 continue
4293 mrr_title = self._get_text(mrr, 'title')
4294 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4295 if mrr_title == 'License':
4296 info['license'] = mrr_contents_text
4297 elif not multiple_songs:
4298 if mrr_title == 'Album':
4299 info['album'] = mrr_contents_text
4300 elif mrr_title == 'Artist':
4301 info['artist'] = mrr_contents_text
4302 elif mrr_title == 'Song':
4303 info['track'] = mrr_contents_text
545cc85d 4304
4305 fallbacks = {
4306 'channel': 'uploader',
4307 'channel_id': 'uploader_id',
4308 'channel_url': 'uploader_url',
4309 }
992f9a73 4310
17322130 4311 # The upload date for scheduled, live and past live streams / premieres in microformats
4312 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4313 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4314 upload_date = (
4315 unified_strdate(get_first(microformats, 'uploadDate'))
4316 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4317 if not upload_date or (
4d37720a 4318 live_status in ('not_live', None)
1ff88b7a 4319 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4320 ):
c26f9b99 4321 upload_date = strftime_or_none(
4322 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4323 info['upload_date'] = upload_date
992f9a73 4324
545cc85d 4325 for to, frm in fallbacks.items():
4326 if not info.get(to):
4327 info[to] = info.get(frm)
4328
4329 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4330 v = info.get(s_k)
4331 if v:
4332 info[d_k] = v
b84071c0 4333
c26f9b99 4334 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4335
4336 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4337 or get_first(video_details, 'isPrivate', expected_type=bool))
4338
4339 info['availability'] = (
4340 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4341 else self._availability(
4342 is_private=is_private,
4343 needs_premium=(
4344 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4345 or False if initial_data and is_private is not None else None),
4346 needs_subscription=(
4347 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4348 or False if initial_data and is_private is not None else None),
4349 needs_auth=info['age_limit'] >= 18,
4350 is_unlisted=None if is_private is None else (
4351 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4352 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4353
a2160aa4 4354 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4355
11f9be09 4356 self.mark_watched(video_id, player_responses)
d77ab8e2 4357
545cc85d 4358 return info
c5e8d7af 4359
a61fd4cf 4360
a6213a49 4361class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4362 @staticmethod
4363 def passthrough_smuggled_data(func):
bd7e919a 4364 def _smuggle(info, smuggled_data):
4365 if info.get('_type') not in ('url', 'url_transparent'):
4366 return info
4367 if smuggled_data.get('is_music_url'):
4368 parsed_url = urllib.parse.urlparse(info['url'])
4369 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4370 smuggled_data.pop('is_music_url')
4371 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4372 if smuggled_data:
4373 info['url'] = smuggle_url(info['url'], smuggled_data)
4374 return info
182bda88 4375
4376 @functools.wraps(func)
4377 def wrapper(self, url):
4378 url, smuggled_data = unsmuggle_url(url, {})
4379 if self.is_music_url(url):
4380 smuggled_data['is_music_url'] = True
4381 info_dict = func(self, url, smuggled_data)
bd7e919a 4382 if smuggled_data:
4383 _smuggle(info_dict, smuggled_data)
4384 if info_dict.get('entries'):
a8c754cc 4385 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4386 return info_dict
4387 return wrapper
4388
a6213a49 4389 def _extract_channel_id(self, webpage):
4390 channel_id = self._html_search_meta(
4391 'channelId', webpage, 'channel id', default=None)
4392 if channel_id:
4393 return channel_id
4394 channel_url = self._html_search_meta(
4395 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4396 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4397 'twitter:app:url:googleplay'), webpage, 'channel url')
4398 return self._search_regex(
4399 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4400 channel_url, 'channel id')
15f6397c 4401
8bdd16b4 4402 @staticmethod
cd7c66cf 4403 def _extract_basic_item_renderer(item):
4404 # Modified from _extract_grid_item_renderer
201c1459 4405 known_basic_renderers = (
a17526e4 4406 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4407 )
4408 for key, renderer in item.items():
201c1459 4409 if not isinstance(renderer, dict):
cd7c66cf 4410 continue
201c1459 4411 elif key in known_basic_renderers:
4412 return renderer
4413 elif key.startswith('grid') and key.endswith('Renderer'):
4414 return renderer
8bdd16b4 4415
c7335551
M
4416 def _extract_channel_renderer(self, renderer):
4417 channel_id = renderer['channelId']
4418 title = self._get_text(renderer, 'title')
4419 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4420 return {
4421 '_type': 'url',
4422 'url': channel_url,
4423 'id': channel_id,
4424 'ie_key': YoutubeTabIE.ie_key(),
4425 'channel': title,
4426 'channel_id': channel_id,
4427 'channel_url': channel_url,
4428 'title': title,
4429 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4430 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4431 'playlist_count': self._get_count(renderer, 'videoCountText'),
4432 'description': self._get_text(renderer, 'descriptionSnippet'),
4433 }
4434
8bdd16b4 4435 def _grid_entries(self, grid_renderer):
4436 for item in grid_renderer['items']:
4437 if not isinstance(item, dict):
39b62db1 4438 continue
cd7c66cf 4439 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4440 if not isinstance(renderer, dict):
4441 continue
052e1350 4442 title = self._get_text(renderer, 'title')
fe93e2c4 4443
8bdd16b4 4444 # playlist
4445 playlist_id = renderer.get('playlistId')
4446 if playlist_id:
4447 yield self.url_result(
4448 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4449 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4450 video_title=title)
201c1459 4451 continue
8bdd16b4 4452 # video
4453 video_id = renderer.get('videoId')
4454 if video_id:
4455 yield self._extract_video(renderer)
201c1459 4456 continue
8bdd16b4 4457 # channel
4458 channel_id = renderer.get('channelId')
4459 if channel_id:
c7335551 4460 yield self._extract_channel_renderer(renderer)
201c1459 4461 continue
4462 # generic endpoint URL support
4463 ep_url = urljoin('https://www.youtube.com/', try_get(
4464 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4465 str))
201c1459 4466 if ep_url:
4467 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4468 if ie.suitable(ep_url):
4469 yield self.url_result(
4470 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4471 break
8bdd16b4 4472
16aa9ea4 4473 def _music_reponsive_list_entry(self, renderer):
4474 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4475 if video_id:
4476 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4477 ie=YoutubeIE.ie_key(), video_id=video_id)
4478 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4479 if playlist_id:
4480 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4481 if video_id:
4482 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4483 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4484 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4485 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4486 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4487 if browse_id:
4488 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4489 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4490
3d3dddc9 4491 def _shelf_entries_from_content(self, shelf_renderer):
4492 content = shelf_renderer.get('content')
4493 if not isinstance(content, dict):
8bdd16b4 4494 return
cd7c66cf 4495 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4496 if renderer:
4497 # TODO: add support for nested playlists so each shelf is processed
4498 # as separate playlist
4499 # TODO: this includes only first N items
86e5f3ed 4500 yield from self._grid_entries(renderer)
3d3dddc9 4501 renderer = content.get('horizontalListRenderer')
4502 if renderer:
4503 # TODO
4504 pass
8bdd16b4 4505
29f7c58a 4506 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4507 ep = try_get(
4508 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4509 str)
8bdd16b4 4510 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4511 if shelf_url:
29f7c58a 4512 # Skipping links to another channels, note that checking for
4513 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4514 # will not work
4515 if skip_channels and '/channels?' in shelf_url:
4516 return
052e1350 4517 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4518 yield self.url_result(shelf_url, video_title=title)
4519 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4520 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4521
8bdd16b4 4522 def _playlist_entries(self, video_list_renderer):
4523 for content in video_list_renderer['contents']:
4524 if not isinstance(content, dict):
4525 continue
4526 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4527 if not isinstance(renderer, dict):
4528 continue
4529 video_id = renderer.get('videoId')
4530 if not video_id:
4531 continue
4532 yield self._extract_video(renderer)
07aeced6 4533
3462ffa8 4534 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4535 renderer = traverse_obj(
4536 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4537 video_id = renderer.get('videoId')
4538 if not video_id:
4539 return
4540 yield self._extract_video(renderer)
4541
8bdd16b4 4542 def _video_entry(self, video_renderer):
4543 video_id = video_renderer.get('videoId')
4544 if video_id:
4545 return self._extract_video(video_renderer)
dacb3a86 4546
ad210f4f 4547 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4548 url = urljoin('https://youtube.com', traverse_obj(
4549 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4550 if url:
4551 return self.url_result(
4552 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4553
8bdd16b4 4554 def _post_thread_entries(self, post_thread_renderer):
4555 post_renderer = try_get(
4556 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4557 if not post_renderer:
4558 return
4559 # video attachment
4560 video_renderer = try_get(
895b0931 4561 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4562 video_id = video_renderer.get('videoId')
4563 if video_id:
4564 entry = self._extract_video(video_renderer)
8bdd16b4 4565 if entry:
4566 yield entry
895b0931 4567 # playlist attachment
4568 playlist_id = try_get(
14f25df2 4569 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4570 if playlist_id:
4571 yield self.url_result(
e28f1c0a 4572 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4573 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4574 # inline video links
4575 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4576 for run in runs:
4577 if not isinstance(run, dict):
4578 continue
4579 ep_url = try_get(
14f25df2 4580 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4581 if not ep_url:
4582 continue
4583 if not YoutubeIE.suitable(ep_url):
4584 continue
4585 ep_video_id = YoutubeIE._match_id(ep_url)
4586 if video_id == ep_video_id:
4587 continue
895b0931 4588 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4589
8bdd16b4 4590 def _post_thread_continuation_entries(self, post_thread_continuation):
4591 contents = post_thread_continuation.get('contents')
4592 if not isinstance(contents, list):
4593 return
4594 for content in contents:
4595 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4596 if isinstance(renderer, dict):
4597 yield from self._post_thread_entries(renderer)
8bdd16b4 4598 continue
6b0b0a28 4599 renderer = content.get('videoRenderer')
4600 if isinstance(renderer, dict):
4601 yield self._video_entry(renderer)
07aeced6 4602
39ed931e 4603 r''' # unused
4604 def _rich_grid_entries(self, contents):
4605 for content in contents:
4606 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4607 if video_renderer:
4608 entry = self._video_entry(video_renderer)
4609 if entry:
4610 yield entry
4611 '''
52efa4b3 4612
0a5095fe 4613 def _report_history_entries(self, renderer):
4614 for url in traverse_obj(renderer, (
7a32c70d 4615 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4616 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4617 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4618 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4619
a6213a49 4620 def _extract_entries(self, parent_renderer, continuation_list):
4621 # continuation_list is modified in-place with continuation_list = [continuation_token]
4622 continuation_list[:] = [None]
4623 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4624 for content in contents:
4625 if not isinstance(content, dict):
4626 continue
16aa9ea4 4627 is_renderer = traverse_obj(
4628 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4629 expected_type=dict)
a6213a49 4630 if not is_renderer:
0a5095fe 4631 if content.get('richItemRenderer'):
4632 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4633 yield entry
4634 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4635 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4636 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4637 yield from self._report_history_entries(table)
4638 continuation_list[0] = self._extract_continuation(table)
a6213a49 4639 continue
0a5095fe 4640
a6213a49 4641 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4642 for isr_content in isr_contents:
4643 if not isinstance(isr_content, dict):
8bdd16b4 4644 continue
69184e41 4645
a6213a49 4646 known_renderers = {
4647 'playlistVideoListRenderer': self._playlist_entries,
4648 'gridRenderer': self._grid_entries,
a17526e4 4649 'reelShelfRenderer': self._grid_entries,
4650 'shelfRenderer': self._shelf_entries,
16aa9ea4 4651 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4652 'backstagePostThreadRenderer': self._post_thread_entries,
4653 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4654 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4655 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4656 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4657 }
4658 for key, renderer in isr_content.items():
4659 if key not in known_renderers:
4660 continue
4661 for entry in known_renderers[key](renderer):
4662 if entry:
4663 yield entry
4664 continuation_list[0] = self._extract_continuation(renderer)
4665 break
70d5c17b 4666
4667 if not continuation_list[0]:
a6213a49 4668 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4669
a6213a49 4670 if not continuation_list[0]:
4671 continuation_list[0] = self._extract_continuation(parent_renderer)
4672
4673 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4674 continuation_list = [None]
4675 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4676 tab_content = try_get(tab, lambda x: x['content'], dict)
4677 if not tab_content:
4678 return
3462ffa8 4679 parent_renderer = (
29f7c58a 4680 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4681 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4682 yield from extract_entries(parent_renderer)
3462ffa8 4683 continuation = continuation_list[0]
d069eca7 4684
8bdd16b4 4685 for page_num in itertools.count(1):
4686 if not continuation:
4687 break
99e9e001 4688 headers = self.generate_api_headers(
4689 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4690 response = self._extract_response(
86e5f3ed 4691 item_id=f'{item_id} page {page_num}',
fe93e2c4 4692 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4693 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4694
4695 if not response:
8bdd16b4 4696 break
ac56cf38 4697 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4698 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4699 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4700
a1b535bd 4701 known_renderers = {
e4b98809 4702 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4703 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4704 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4705 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4706 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4707 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4708 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4709 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4710 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4711 'playlistVideoListContinuation': (self._playlist_entries, None),
4712 'gridContinuation': (self._grid_entries, None),
4713 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4714 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4715 }
1fb53b94 4716
4717 continuation_items = traverse_obj(response, (
4718 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4719 'appendContinuationItemsAction', 'continuationItems'
4720 ), 'continuationContents', get_all=False)
4721 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4722
a1b535bd 4723 video_items_renderer = None
1fb53b94 4724 for key in continuation_item.keys():
a1b535bd 4725 if key not in known_renderers:
8bdd16b4 4726 continue
1fb53b94 4727 func, parent_key = known_renderers[key]
4728 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4729 continuation_list = [None]
1fb53b94 4730 yield from func(video_items_renderer)
9ba5705a 4731 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4732
4733 if not video_items_renderer:
a1b535bd 4734 break
9558dcec 4735
8bdd16b4 4736 @staticmethod
7c219ea6 4737 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4738 for tab_renderer in tabs:
4739 if tab_renderer.get('selected'):
4740 return tab_renderer
4741 if fatal:
4742 raise ExtractorError('Unable to find selected tab')
4743
4744 @staticmethod
4745 def _extract_tab_renderers(response):
4746 return traverse_obj(
4747 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4748
ac56cf38 4749 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 4750 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 4751
8bdd16b4 4752 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 4753 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4754 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4755
4756 return self.playlist_result(
4757 self._entries(
4758 selected_tab, metadata['id'], ytcfg,
4759 self._extract_account_syncid(ytcfg, data),
4760 self._extract_visitor_data(data, ytcfg)),
4761 **metadata)
39ed931e 4762
bd7e919a 4763 def _extract_metadata_from_tabs(self, item_id, data):
4764 info = {'id': item_id}
4765
4766 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 4767 if metadata_renderer:
bd7e919a 4768 info.update({
4769 'uploader': metadata_renderer.get('title'),
4770 'uploader_id': metadata_renderer.get('externalId'),
4771 'uploader_url': metadata_renderer.get('channelUrl'),
4772 })
4773 if info['uploader_id']:
4774 info['id'] = info['uploader_id']
4775 else:
4776 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 4777
301d07fc 4778 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4779 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4780 def _get_uncropped(url):
4781 return url_or_none((url or '').split('=')[0] + '=s0')
4782
6141346d 4783 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 4784 if avatar_thumbnails:
4785 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4786 if uncropped_avatar:
4787 avatar_thumbnails.append({
4788 'url': uncropped_avatar,
4789 'id': 'avatar_uncropped',
4790 'preference': 1
4791 })
4792
4793 channel_banners = self._extract_thumbnails(
bd7e919a 4794 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 4795 for banner in channel_banners:
4796 banner['preference'] = -10
4797
4798 if channel_banners:
4799 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4800 if uncropped_banner:
4801 channel_banners.append({
4802 'url': uncropped_banner,
4803 'id': 'banner_uncropped',
4804 'preference': -5
4805 })
4806
bd7e919a 4807 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4808 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4809 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4810
301d07fc 4811 primary_thumbnails = self._extract_thumbnails(
a17526e4 4812 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
4813 playlist_thumbnails = self._extract_thumbnails(
4814 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4815
bd7e919a 4816 info.update({
4817 'title': (traverse_obj(metadata_renderer, 'title')
4818 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4819 or info['id']),
4820 'availability': self._extract_availability(data),
4821 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4822 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4823 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4824 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4825 })
f0d785d3 4826
6141346d
M
4827 # Playlist stats is a text runs array containing [video count, view count, last updated].
4828 # last updated or (view count and last updated) may be missing.
4829 playlist_stats = get_first(
bd7e919a 4830 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4831
6141346d
M
4832 last_updated_unix = self._parse_time_text(
4833 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4834 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
bd7e919a 4835 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
6141346d 4836
bd7e919a 4837 info['view_count'] = self._get_count(playlist_stats, 1)
4838 if info['view_count'] is None: # 0 is allowed
4839 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4840
4841 info['playlist_count'] = self._get_count(playlist_stats, 0)
4842 if info['playlist_count'] is None: # 0 is allowed
4843 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4844
4845 if not info.get('uploader_id'):
6141346d 4846 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 4847 if not owner: # Deprecated
6141346d
M
4848 owner = traverse_obj(
4849 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4850 ('videoOwner', 'videoOwnerRenderer', 'title'))
4851 owner_text = self._get_text(owner)
4852 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 4853 info.update({
6141346d
M
4854 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4855 'uploader_id': browse_ep.get('browseId'),
4856 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
bd7e919a 4857 })
6141346d 4858
bd7e919a 4859 info.update({
4860 'channel': info['uploader'],
4861 'channel_id': info['uploader_id'],
4862 'channel_url': info['uploader_url']
4863 })
4864 return info
73c4ac2c 4865
6e634cbe 4866 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4867 first_id = last_id = response = None
2be71994 4868 for page_num in itertools.count(1):
cd7c66cf 4869 videos = list(self._playlist_entries(playlist))
4870 if not videos:
4871 return
2be71994 4872 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4873 if start >= len(videos):
4874 return
24146491 4875 yield from videos[start:]
2be71994 4876 first_id = first_id or videos[0]['id']
4877 last_id = videos[-1]['id']
79360d99 4878 watch_endpoint = try_get(
4879 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4880 headers = self.generate_api_headers(
4881 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4882 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4883 query = {
4884 'playlistId': playlist_id,
4885 'videoId': watch_endpoint.get('videoId') or last_id,
4886 'index': watch_endpoint.get('index') or len(videos),
4887 'params': watch_endpoint.get('params') or 'OAE%3D'
4888 }
4889 response = self._extract_response(
4890 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4891 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4892 check_get_keys='contents'
4893 )
cd7c66cf 4894 playlist = try_get(
79360d99 4895 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4896
ac56cf38 4897 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4898 title = playlist.get('title') or try_get(
14f25df2 4899 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4900 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4901
4902 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4903 playlist_url = urljoin(url, try_get(
4904 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4905 str))
6e634cbe 4906
4907 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4908 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4909 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4910
4911 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4912 return self.url_result(
4913 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4914 video_title=title)
cd7c66cf 4915
8bdd16b4 4916 return self.playlist_result(
6e634cbe 4917 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4918 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4919
47193e02 4920 def _extract_availability(self, data):
4921 """
4922 Gets the availability of a given playlist/tab.
4923 Note: Unless YouTube tells us explicitly, we do not assume it is public
4924 @param data: response
4925 """
6141346d
M
4926 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4927 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4928 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 4929
6141346d 4930 badges = self._extract_badges(sidebar_renderer)
47193e02 4931
4932 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
4933 privacy_setting_icon = get_first(
4934 (playlist_header_renderer, sidebar_renderer),
4935 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4936 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4937 expected_type=str)
4938
4939 microformats_is_unlisted = traverse_obj(
4940 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 4941
c26f9b99 4942 return (
4943 'public' if (
4944 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4945 or player_header_privacy == 'PUBLIC'
4946 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4947 else self._availability(
4948 is_private=(
4949 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4950 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4951 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4952 is_unlisted=(
4953 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4954 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
4955 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
4956 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 4957 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4958 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4959 needs_auth=False))
47193e02 4960
4961 @staticmethod
4962 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4963 sidebar_renderer = try_get(
4964 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4965 for item in sidebar_renderer:
4966 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4967 if renderer:
4968 return renderer
4969
ac56cf38 4970 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4971 """
6141346d 4972 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 4973 """
6141346d
M
4974 is_playlist = bool(traverse_obj(
4975 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
4976 if not is_playlist:
47193e02 4977 return
11f9be09 4978 headers = self.generate_api_headers(
99e9e001 4979 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4980 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4981 query = {
6141346d
M
4982 'params': 'wgYCCAA=',
4983 'browseId': f'VL{item_id}'
47193e02 4984 }
4985 return self._extract_response(
4986 item_id=item_id, headers=headers, query=query,
fe93e2c4 4987 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 4988 note='Redownloading playlist API JSON with unavailable videos')
358de58c 4989
2762dbb1 4990 @functools.cached_property
a25bca9f 4991 def skip_webpage(self):
4992 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4993
ac56cf38 4994 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4995 webpage, data = None, None
4996 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4997 try:
be5c1ae8 4998 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4999 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5000 except ExtractorError as e:
5001 if isinstance(e.cause, network_exceptions):
14f25df2 5002 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 5003 retry.error = e
5004 continue
5005 self._error_or_warning(e, fatal=fatal)
14fdfea9 5006 break
ac56cf38 5007
be5c1ae8 5008 try:
5009 self._extract_and_report_alerts(data)
5010 except ExtractorError as e:
5011 self._error_or_warning(e, fatal=fatal)
5012 break
ac56cf38 5013
be5c1ae8 5014 # Sometimes youtube returns a webpage with incomplete ytInitialData
5015 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5016 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5017 retry.error = ExtractorError('Incomplete yt initial data received')
5018 continue
ac56cf38 5019
cd7c66cf 5020 return webpage, data
5021
a25bca9f 5022 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5023 """Use if failed to extract ytcfg (and data) from initial webpage"""
5024 if not ytcfg and self.is_authenticated:
5025 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5026 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5027 raise ExtractorError(
5028 f'{msg}. If you are not downloading private content, or '
5029 'your cookies are only for the first account and channel,'
5030 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5031 expected=True)
5032 self.report_warning(msg, only_once=True)
5033
ac56cf38 5034 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5035 data = None
a25bca9f 5036 if not self.skip_webpage:
ac56cf38 5037 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5038 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5039 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5040 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5041 if (url != 'https://www.youtube.com/feed/recommended'
5042 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5043 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5044 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5045 if fatal:
5046 raise ExtractorError(msg, expected=True)
5047 self.report_warning(msg, only_once=True)
ac56cf38 5048 if not data:
a25bca9f 5049 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5050 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5051 return data, ytcfg
5052
5053 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5054 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5055 resolve_response = self._extract_response(
5056 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5057 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5058 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5059 for ep_key, ep in endpoints.items():
5060 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5061 if params:
5062 return self._extract_response(
5063 item_id=item_id, query=params, ep=ep, headers=headers,
5064 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5065 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5066 err_note = 'Failed to resolve url (does the playlist exist?)'
5067 if fatal:
5068 raise ExtractorError(err_note, expected=True)
5069 self.report_warning(err_note, item_id)
5070
a6213a49 5071 _SEARCH_PARAMS = None
5072
af5c1c55 5073 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5074 data = {'query': query}
5075 if params is NO_DEFAULT:
5076 params = self._SEARCH_PARAMS
5077 if params:
5078 data['params'] = params
16aa9ea4 5079
5080 content_keys = (
5081 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5082 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5083 # ytmusic search
5084 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5085 ('continuationContents', ),
5086 )
a25bca9f 5087 display_id = f'query "{query}"'
86e5f3ed 5088 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5089 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5090 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5091
a61fd4cf 5092 continuation_list = [None]
a25bca9f 5093 search = None
a6213a49 5094 for page_num in itertools.count(1):
a61fd4cf 5095 data.update(continuation_list[0] or {})
a25bca9f 5096 headers = self.generate_api_headers(
5097 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5098 search = self._extract_response(
a25bca9f 5099 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5100 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5101 slr_contents = traverse_obj(search, *content_keys)
5102 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5103 if not continuation_list[0]:
a6213a49 5104 break
5105
5106
5107class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5108 IE_DESC = 'YouTube Tabs'
5109 _VALID_URL = r'''(?x:
5110 https?://
5111 (?:\w+\.)?
5112 (?:
5113 youtube(?:kids)?\.com|
5114 %(invidious)s
5115 )/
5116 (?:
5117 (?P<channel_type>channel|c|user|browse)/|
5118 (?P<not_channel>
5119 feed/|hashtag/|
5120 (?:playlist|watch)\?.*?\blist=
5121 )|
5122 (?!(?:%(reserved_names)s)\b) # Direct URLs
5123 )
5124 (?P<id>[^/?\#&]+)
5125 )''' % {
5126 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5127 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5128 }
5129 IE_NAME = 'youtube:tab'
5130
5131 _TESTS = [{
5132 'note': 'playlists, multipage',
5133 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5134 'playlist_mincount': 94,
5135 'info_dict': {
5136 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5137 'title': 'Igor Kleiner - Playlists',
a6213a49 5138 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5139 'uploader': 'Igor Kleiner',
a6213a49 5140 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5141 'channel': 'Igor Kleiner',
5142 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5143 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5144 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5145 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5146 'channel_follower_count': int
a6213a49 5147 },
5148 }, {
5149 'note': 'playlists, multipage, different order',
5150 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5151 'playlist_mincount': 94,
5152 'info_dict': {
5153 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5154 'title': 'Igor Kleiner - Playlists',
a6213a49 5155 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5156 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5157 'uploader': 'Igor Kleiner',
5158 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5159 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5160 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5161 'channel': 'Igor Kleiner',
5162 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5163 'channel_follower_count': int
a6213a49 5164 },
5165 }, {
5166 'note': 'playlists, series',
5167 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5168 'playlist_mincount': 5,
5169 'info_dict': {
5170 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5171 'title': '3Blue1Brown - Playlists',
5172 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5173 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5174 'uploader': '3Blue1Brown',
976ae3ea 5175 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5176 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5177 'channel': '3Blue1Brown',
5178 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5179 'tags': ['Mathematics'],
6c73052c 5180 'channel_follower_count': int
a6213a49 5181 },
5182 }, {
5183 'note': 'playlists, singlepage',
5184 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5185 'playlist_mincount': 4,
5186 'info_dict': {
5187 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5188 'title': 'ThirstForScience - Playlists',
5189 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5190 'uploader': 'ThirstForScience',
5191 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5192 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5193 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5194 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5195 'tags': 'count:13',
5196 'channel': 'ThirstForScience',
6c73052c 5197 'channel_follower_count': int
a6213a49 5198 }
5199 }, {
5200 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5201 'only_matching': True,
5202 }, {
5203 'note': 'basic, single video playlist',
5204 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5205 'info_dict': {
5206 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5207 'uploader': 'Sergey M.',
5208 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5209 'title': 'youtube-dl public playlist',
976ae3ea 5210 'description': '',
5211 'tags': [],
5212 'view_count': int,
5213 'modified_date': '20201130',
5214 'channel': 'Sergey M.',
5215 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5216 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5217 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5218 'availability': 'public',
a6213a49 5219 },
5220 'playlist_count': 1,
5221 }, {
5222 'note': 'empty playlist',
5223 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5224 'info_dict': {
5225 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5226 'uploader': 'Sergey M.',
5227 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5228 'title': 'youtube-dl empty playlist',
976ae3ea 5229 'tags': [],
5230 'channel': 'Sergey M.',
5231 'description': '',
5232 'modified_date': '20160902',
5233 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5234 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5235 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5236 'availability': 'public',
a6213a49 5237 },
5238 'playlist_count': 0,
5239 }, {
5240 'note': 'Home tab',
5241 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5242 'info_dict': {
5243 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5244 'title': 'lex will - Home',
5245 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5246 'uploader': 'lex will',
5247 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5248 'channel': 'lex will',
5249 'tags': ['bible', 'history', 'prophesy'],
5250 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5251 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5252 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5253 'channel_follower_count': int
a6213a49 5254 },
5255 'playlist_mincount': 2,
5256 }, {
5257 'note': 'Videos tab',
5258 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5259 'info_dict': {
5260 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5261 'title': 'lex will - Videos',
5262 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5263 'uploader': 'lex will',
5264 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5265 'tags': ['bible', 'history', 'prophesy'],
5266 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5267 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5268 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5269 'channel': 'lex will',
6c73052c 5270 'channel_follower_count': int
a6213a49 5271 },
5272 'playlist_mincount': 975,
5273 }, {
5274 'note': 'Videos tab, sorted by popular',
5275 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5276 'info_dict': {
5277 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5278 'title': 'lex will - Videos',
5279 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5280 'uploader': 'lex will',
5281 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5282 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5283 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5284 'channel': 'lex will',
5285 'tags': ['bible', 'history', 'prophesy'],
5286 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5287 'channel_follower_count': int
a6213a49 5288 },
5289 'playlist_mincount': 199,
5290 }, {
5291 'note': 'Playlists tab',
5292 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5293 'info_dict': {
5294 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5295 'title': 'lex will - Playlists',
5296 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5297 'uploader': 'lex will',
5298 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5299 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5300 'channel': 'lex will',
5301 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5302 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5303 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5304 'channel_follower_count': int
a6213a49 5305 },
5306 'playlist_mincount': 17,
5307 }, {
5308 'note': 'Community tab',
5309 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5310 'info_dict': {
5311 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5312 'title': 'lex will - Community',
5313 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5314 'uploader': 'lex will',
5315 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5316 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5317 'channel': 'lex will',
5318 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5319 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5320 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5321 'channel_follower_count': int
a6213a49 5322 },
5323 'playlist_mincount': 18,
5324 }, {
5325 'note': 'Channels tab',
5326 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5327 'info_dict': {
5328 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5329 'title': 'lex will - Channels',
5330 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5331 'uploader': 'lex will',
5332 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5333 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5334 'channel': 'lex will',
5335 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5336 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5337 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5338 'channel_follower_count': int
a6213a49 5339 },
5340 'playlist_mincount': 12,
5341 }, {
5342 'note': 'Search tab',
5343 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5344 'playlist_mincount': 40,
5345 'info_dict': {
5346 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5347 'title': '3Blue1Brown - Search - linear algebra',
5348 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5349 'uploader': '3Blue1Brown',
5350 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5351 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5352 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5353 'tags': ['Mathematics'],
5354 'channel': '3Blue1Brown',
5355 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5356 'channel_follower_count': int
a6213a49 5357 },
5358 }, {
5359 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5360 'only_matching': True,
5361 }, {
5362 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5363 'only_matching': True,
5364 }, {
5365 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5366 'only_matching': True,
5367 }, {
5368 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5369 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5370 'info_dict': {
5371 'title': '29C3: Not my department',
5372 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5373 'uploader': 'Christiaan008',
5374 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5375 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5376 'tags': [],
5377 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5378 'view_count': int,
5379 'modified_date': '20150605',
5380 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5381 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5382 'channel': 'Christiaan008',
c26f9b99 5383 'availability': 'public',
a6213a49 5384 },
5385 'playlist_count': 96,
5386 }, {
5387 'note': 'Large playlist',
5388 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5389 'info_dict': {
5390 'title': 'Uploads from Cauchemar',
5391 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5392 'uploader': 'Cauchemar',
5393 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5394 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5395 'tags': [],
5396 'modified_date': r're:\d{8}',
5397 'channel': 'Cauchemar',
5398 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5399 'view_count': int,
5400 'description': '',
5401 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5402 'availability': 'public',
a6213a49 5403 },
5404 'playlist_mincount': 1123,
976ae3ea 5405 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5406 }, {
5407 'note': 'even larger playlist, 8832 videos',
5408 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5409 'only_matching': True,
5410 }, {
5411 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5412 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5413 'info_dict': {
5414 'title': 'Uploads from Interstellar Movie',
5415 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5416 'uploader': 'Interstellar Movie',
5417 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5418 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5419 'tags': [],
5420 'view_count': int,
5421 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5422 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5423 'channel': 'Interstellar Movie',
5424 'description': '',
5425 'modified_date': r're:\d{8}',
c26f9b99 5426 'availability': 'public',
a6213a49 5427 },
5428 'playlist_mincount': 21,
5429 }, {
5430 'note': 'Playlist with "show unavailable videos" button',
5431 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5432 'info_dict': {
5433 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5434 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5435 'uploader': 'Phim Siêu Nhân Nhật Bản',
5436 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5437 'view_count': int,
5438 'channel': 'Phim Siêu Nhân Nhật Bản',
5439 'tags': [],
5440 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5441 'description': '',
5442 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5443 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5444 'modified_date': r're:\d{8}',
c26f9b99 5445 'availability': 'public',
a6213a49 5446 },
5447 'playlist_mincount': 200,
976ae3ea 5448 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5449 }, {
5450 'note': 'Playlist with unavailable videos in page 7',
5451 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5452 'info_dict': {
5453 'title': 'Uploads from BlankTV',
5454 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5455 'uploader': 'BlankTV',
5456 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5457 'channel': 'BlankTV',
5458 'channel_url': 'https://www.youtube.com/c/blanktv',
5459 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5460 'view_count': int,
5461 'tags': [],
5462 'uploader_url': 'https://www.youtube.com/c/blanktv',
5463 'modified_date': r're:\d{8}',
5464 'description': '',
c26f9b99 5465 'availability': 'public',
a6213a49 5466 },
5467 'playlist_mincount': 1000,
976ae3ea 5468 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5469 }, {
5470 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5471 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5472 'info_dict': {
5473 'title': 'Data Analysis with Dr Mike Pound',
5474 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5475 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5476 'uploader': 'Computerphile',
5477 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5478 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5479 'tags': [],
5480 'view_count': int,
5481 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5482 'channel_url': 'https://www.youtube.com/user/Computerphile',
5483 'channel': 'Computerphile',
c26f9b99 5484 'availability': 'public',
6141346d 5485 'modified_date': '20190712',
a6213a49 5486 },
5487 'playlist_mincount': 11,
5488 }, {
5489 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5490 'only_matching': True,
5491 }, {
5492 'note': 'Playlist URL that does not actually serve a playlist',
5493 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5494 'info_dict': {
5495 'id': 'FqZTN594JQw',
5496 'ext': 'webm',
5497 'title': "Smiley's People 01 detective, Adventure Series, Action",
5498 'uploader': 'STREEM',
5499 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5500 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5501 'upload_date': '20150526',
5502 'license': 'Standard YouTube License',
5503 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5504 'categories': ['People & Blogs'],
5505 'tags': list,
5506 'view_count': int,
5507 'like_count': int,
a6213a49 5508 },
5509 'params': {
5510 'skip_download': True,
5511 },
5512 'skip': 'This video is not available.',
5513 'add_ie': [YoutubeIE.ie_key()],
5514 }, {
5515 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5516 'only_matching': True,
5517 }, {
5518 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5519 'only_matching': True,
5520 }, {
5521 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5522 'info_dict': {
12a1b225 5523 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5524 'ext': 'mp4',
976ae3ea 5525 'title': str,
a6213a49 5526 'uploader': 'Sky News',
5527 'uploader_id': 'skynews',
5528 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5529 'upload_date': r're:\d{8}',
976ae3ea 5530 'description': str,
a6213a49 5531 'categories': ['News & Politics'],
5532 'tags': list,
5533 'like_count': int,
86973308 5534 'release_timestamp': int,
976ae3ea 5535 'channel': 'Sky News',
5536 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5537 'age_limit': 0,
5538 'view_count': int,
86973308 5539 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5540 'playable_in_embed': True,
86973308 5541 'release_date': r're:\d+',
976ae3ea 5542 'availability': 'public',
5543 'live_status': 'is_live',
5544 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5545 'channel_follower_count': int,
5546 'concurrent_view_count': int,
a6213a49 5547 },
5548 'params': {
5549 'skip_download': True,
5550 },
976ae3ea 5551 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5552 }, {
5553 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5554 'info_dict': {
5555 'id': 'a48o2S1cPoo',
5556 'ext': 'mp4',
5557 'title': 'The Young Turks - Live Main Show',
5558 'uploader': 'The Young Turks',
5559 'uploader_id': 'TheYoungTurks',
5560 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5561 'upload_date': '20150715',
5562 'license': 'Standard YouTube License',
5563 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5564 'categories': ['News & Politics'],
5565 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5566 'like_count': int,
a6213a49 5567 },
5568 'params': {
5569 'skip_download': True,
5570 },
5571 'only_matching': True,
5572 }, {
5573 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5574 'only_matching': True,
5575 }, {
5576 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5577 'only_matching': True,
5578 }, {
5579 'note': 'A channel that is not live. Should raise error',
5580 'url': 'https://www.youtube.com/user/numberphile/live',
5581 'only_matching': True,
5582 }, {
5583 'url': 'https://www.youtube.com/feed/trending',
5584 'only_matching': True,
5585 }, {
5586 'url': 'https://www.youtube.com/feed/library',
5587 'only_matching': True,
5588 }, {
5589 'url': 'https://www.youtube.com/feed/history',
5590 'only_matching': True,
5591 }, {
5592 'url': 'https://www.youtube.com/feed/subscriptions',
5593 'only_matching': True,
5594 }, {
5595 'url': 'https://www.youtube.com/feed/watch_later',
5596 'only_matching': True,
5597 }, {
5598 'note': 'Recommended - redirects to home page.',
5599 'url': 'https://www.youtube.com/feed/recommended',
5600 'only_matching': True,
5601 }, {
5602 'note': 'inline playlist with not always working continuations',
5603 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5604 'only_matching': True,
5605 }, {
5606 'url': 'https://www.youtube.com/course',
5607 'only_matching': True,
5608 }, {
5609 'url': 'https://www.youtube.com/zsecurity',
5610 'only_matching': True,
5611 }, {
5612 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5613 'only_matching': True,
5614 }, {
5615 'url': 'https://www.youtube.com/TheYoungTurks/live',
5616 'only_matching': True,
5617 }, {
5618 'url': 'https://www.youtube.com/hashtag/cctv9',
5619 'info_dict': {
5620 'id': 'cctv9',
5621 'title': '#cctv9',
976ae3ea 5622 'tags': [],
a6213a49 5623 },
4dc23a80 5624 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5625 }, {
5626 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5627 'only_matching': True,
5628 }, {
5629 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5630 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5631 'only_matching': True
5632 }, {
5633 'note': '/browse/ should redirect to /channel/',
5634 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5635 'only_matching': True
5636 }, {
5637 'note': 'VLPL, should redirect to playlist?list=PL...',
5638 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5639 'info_dict': {
5640 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5641 'uploader': 'NoCopyrightSounds',
5642 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5643 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5644 'title': 'NCS : All Releases 💿',
976ae3ea 5645 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5646 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5647 'modified_date': r're:\d{8}',
5648 'view_count': int,
5649 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5650 'tags': [],
5651 'channel': 'NoCopyrightSounds',
c26f9b99 5652 'availability': 'public',
a6213a49 5653 },
5654 'playlist_mincount': 166,
976ae3ea 5655 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5656 }, {
5657 'note': 'Topic, should redirect to playlist?list=UU...',
5658 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5659 'info_dict': {
5660 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5661 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5662 'title': 'Uploads from Royalty Free Music - Topic',
5663 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5664 'tags': [],
5665 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5666 'channel': 'Royalty Free Music - Topic',
5667 'view_count': int,
5668 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5669 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5670 'modified_date': r're:\d{8}',
5671 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5672 'description': '',
c26f9b99 5673 'availability': 'public',
a6213a49 5674 },
a6213a49 5675 'playlist_mincount': 101,
5676 }, {
86973308
M
5677 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5678 # Treat as a general feed
a6213a49 5679 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5680 'info_dict': {
5681 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5682 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5683 'tags': [],
a6213a49 5684 },
a6213a49 5685 'playlist_mincount': 9,
5686 }, {
5687 'note': 'Youtube music Album',
5688 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5689 'info_dict': {
5690 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5691 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5692 'tags': [],
5693 'view_count': int,
5694 'description': '',
5695 'availability': 'unlisted',
5696 'modified_date': r're:\d{8}',
a6213a49 5697 },
5698 'playlist_count': 50,
5699 }, {
5700 'note': 'unlisted single video playlist',
5701 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5702 'info_dict': {
5703 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5704 'uploader': 'colethedj',
5705 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5706 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5707 'availability': 'unlisted',
5708 'tags': [],
12a1b225 5709 'modified_date': '20220418',
976ae3ea 5710 'channel': 'colethedj',
5711 'view_count': int,
5712 'description': '',
5713 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5714 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5715 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5716 },
5717 'playlist_count': 1,
5718 }, {
5719 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5720 'url': 'https://www.youtube.com/feed/recommended',
5721 'info_dict': {
5722 'id': 'recommended',
5723 'title': 'recommended',
6c73052c 5724 'tags': [],
a6213a49 5725 },
5726 'playlist_mincount': 50,
5727 'params': {
5728 'skip_download': True,
5729 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5730 },
5731 }, {
5732 'note': 'API Fallback: /videos tab, sorted by oldest first',
5733 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5734 'info_dict': {
5735 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5736 'title': 'Cody\'sLab - Videos',
5737 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5738 'uploader': 'Cody\'sLab',
5739 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5740 'channel': 'Cody\'sLab',
5741 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5742 'tags': [],
5743 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5744 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5745 'channel_follower_count': int
a6213a49 5746 },
5747 'playlist_mincount': 650,
5748 'params': {
5749 'skip_download': True,
5750 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5751 },
86973308 5752 'skip': 'Query for sorting no longer works',
a6213a49 5753 }, {
5754 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5755 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5756 'info_dict': {
5757 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5758 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5759 'title': 'Uploads from Royalty Free Music - Topic',
5760 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5761 'modified_date': r're:\d{8}',
5762 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5763 'description': '',
5764 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5765 'tags': [],
5766 'channel': 'Royalty Free Music - Topic',
5767 'view_count': int,
5768 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5769 'availability': 'public',
a6213a49 5770 },
a6213a49 5771 'playlist_mincount': 101,
5772 'params': {
5773 'skip_download': True,
5774 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5775 },
7c219ea6 5776 }, {
5777 'note': 'non-standard redirect to regional channel',
5778 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5779 'only_matching': True
61d3665d 5780 }, {
5781 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5782 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5783 'info_dict': {
5784 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5785 'modified_date': '20220407',
5786 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5787 'tags': [],
5788 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5789 'uploader': 'pukkandan',
5790 'availability': 'unlisted',
5791 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5792 'channel': 'pukkandan',
5793 'description': 'Test for collaborative playlist',
5794 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5795 'view_count': int,
61d3665d 5796 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5797 },
5798 'playlist_mincount': 2
c26f9b99 5799 }, {
5800 'note': 'translated tab name',
5801 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5802 'info_dict': {
5803 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5804 'tags': [],
5805 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5806 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 5807 'description': 'test description',
c26f9b99 5808 'title': 'cole-dlp-test-acc - 再生リスト',
5809 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5810 'uploader': 'cole-dlp-test-acc',
5811 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5812 'channel': 'cole-dlp-test-acc',
5813 },
5814 'playlist_mincount': 1,
5815 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5816 'expected_warnings': ['Preferring "ja"'],
5817 }, {
5818 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5819 'note': 'preferred lang set with playlist with translated video titles',
5820 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5821 'info_dict': {
5822 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5823 'tags': [],
5824 'view_count': int,
5825 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5826 'uploader': 'cole-dlp-test-acc',
5827 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5828 'channel': 'cole-dlp-test-acc',
5829 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5830 'description': 'test',
5831 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5832 'title': 'dlp test playlist',
5833 'availability': 'public',
5834 },
5835 'playlist_mincount': 1,
5836 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5837 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5838 }, {
5839 # shorts audio pivot for 2GtVksBMYFM.
5840 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5841 'info_dict': {
5842 'id': 'sfv_audio_pivot',
5843 'title': 'sfv_audio_pivot',
5844 'tags': [],
5845 },
5846 'playlist_mincount': 50,
5847
86973308
M
5848 }, {
5849 # Channel with a real live tab (not to be mistaken with streams tab)
5850 # Do not treat like it should redirect to live stream
5851 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5852 'info_dict': {
5853 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5854 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5855 'tags': [],
5856 },
5857 'playlist_mincount': 20,
5858 }, {
5859 # Tab name is not the same as tab id
5860 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5861 'info_dict': {
5862 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5863 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5864 'tags': [],
5865 },
5866 'playlist_mincount': 8,
5867 }, {
5868 # Home tab id is literally home. Not to get mistaken with featured
5869 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5870 'info_dict': {
5871 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5872 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5873 'tags': [],
5874 },
5875 'playlist_mincount': 8,
5876 }, {
5877 # Should get three playlists for videos, shorts and streams tabs
5878 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5879 'info_dict': {
5880 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 5881 'title': 'Polka Ch. 尾丸ポルカ',
5882 'channel_follower_count': int,
5883 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5884 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5885 'uploader': 'Polka Ch. 尾丸ポルカ',
5886 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5887 'channel': 'Polka Ch. 尾丸ポルカ',
5888 'tags': 'count:35',
5889 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5890 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
86973308
M
5891 },
5892 'playlist_count': 3,
5893 }, {
5894 # Shorts tab with channel with handle
5895 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5896 'info_dict': {
5897 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5898 'title': 'Not Just Bikes - Shorts',
5899 'tags': 'count:12',
5900 'uploader': 'Not Just Bikes',
5901 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5902 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5903 'channel_follower_count': int,
5904 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5905 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5906 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5907 'channel': 'Not Just Bikes',
5908 },
5909 'playlist_mincount': 10,
5910 }, {
5911 # Streams tab
5912 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5913 'info_dict': {
5914 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5915 'title': '中村悠一 - Live',
5916 'tags': 'count:7',
5917 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5918 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5919 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5920 'channel': '中村悠一',
5921 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5922 'channel_follower_count': int,
5923 'uploader': '中村悠一',
5924 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5925 },
5926 'playlist_mincount': 60,
5927 }, {
5928 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5929 # See test_youtube_lists
5930 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5931 'only_matching': True,
5932 }, {
5933 # No uploads and no UCID given. Should fail with no uploads error
5934 # See test_youtube_lists
5935 'url': 'https://www.youtube.com/news',
5936 'only_matching': True
5937 }, {
5938 # No videos tab but has a shorts tab
5939 'url': 'https://www.youtube.com/c/TKFShorts',
5940 'info_dict': {
5941 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5942 'title': 'Shorts Break - Shorts',
5943 'tags': 'count:32',
5944 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5945 'channel': 'Shorts Break',
5946 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5947 'uploader': 'Shorts Break',
5948 'channel_follower_count': int,
5949 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5950 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5951 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5952 },
5953 'playlist_mincount': 30,
5954 }, {
5955 # Trending Now Tab. tab id is empty
5956 'url': 'https://www.youtube.com/feed/trending',
5957 'info_dict': {
5958 'id': 'trending',
5959 'title': 'trending - Now',
5960 'tags': [],
5961 },
5962 'playlist_mincount': 30,
5963 }, {
5964 # Trending Gaming Tab. tab id is empty
5965 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
5966 'info_dict': {
5967 'id': 'trending',
5968 'title': 'trending - Gaming',
5969 'tags': [],
5970 },
5971 'playlist_mincount': 30,
4dc23a80
M
5972 }, {
5973 # Shorts url result in shorts tab
5974 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
5975 'info_dict': {
5976 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5977 'title': 'cole-dlp-test-acc - Shorts',
5978 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5979 'channel': 'cole-dlp-test-acc',
4dc23a80
M
5980 'description': 'test description',
5981 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5982 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5983 'tags': [],
5984 'uploader': 'cole-dlp-test-acc',
5985 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5986
5987 },
5988 'playlist': [{
5989 'info_dict': {
5990 '_type': 'url',
5991 'ie_key': 'Youtube',
5992 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
5993 'id': 'sSM9J5YH_60',
5994 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5995 'title': 'SHORT short',
5996 'channel': 'cole-dlp-test-acc',
5997 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5998 'view_count': int,
5999 'thumbnails': list,
6000 }
6001 }],
6002 'params': {'extract_flat': True},
6003 }, {
6004 # Live video status should be extracted
6005 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6006 'info_dict': {
6007 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6008 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6009 'tags': []
6010 },
6011 'playlist': [{
6012 'info_dict': {
6013 '_type': 'url',
6014 'ie_key': 'Youtube',
6015 'url': 'startswith:https://www.youtube.com/watch?v=',
6016 'id': str,
6017 'title': str,
6018 'live_status': 'is_live',
6019 'channel_id': str,
6020 'channel_url': str,
6021 'concurrent_view_count': int,
6022 'channel': str,
6023 }
6024 }],
c7335551 6025 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6026 'playlist_mincount': 1
c7335551
M
6027 }, {
6028 # Channel renderer metadata. Contains number of videos on the channel
6029 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6030 'info_dict': {
6031 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6032 'title': 'cole-dlp-test-acc - Channels',
6033 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6034 'channel': 'cole-dlp-test-acc',
6035 'description': 'test description',
6036 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6037 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6038 'tags': [],
6039 'uploader': 'cole-dlp-test-acc',
6040 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6041
6042 },
6043 'playlist': [{
6044 'info_dict': {
6045 '_type': 'url',
6046 'ie_key': 'YoutubeTab',
6047 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6048 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6049 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6050 'title': 'PewDiePie',
6051 'channel': 'PewDiePie',
6052 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6053 'thumbnails': list,
6054 'channel_follower_count': int,
6055 'playlist_count': int
6056 }
6057 }],
6058 'params': {'extract_flat': True},
a6213a49 6059 }]
6060
6061 @classmethod
6062 def suitable(cls, url):
86e5f3ed 6063 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6064
86973308
M
6065 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6066
6067 def _get_url_mobj(self, url):
6068 mobj = self._URL_RE.match(url).groupdict()
6069 mobj.update((k, '') for k, v in mobj.items() if v is None)
6070 return mobj
6071
6072 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6073 tab_name = (tab.get('title') or '').lower()
6074 tab_url = urljoin(base_url, traverse_obj(
6075 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6076
bd7e919a 6077 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6078 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6079 if tab_id:
bd7e919a 6080 return {
6081 'TAB_ID_SPONSORSHIPS': 'membership',
6082 }.get(tab_id, tab_id), tab_name
86973308
M
6083
6084 # Fallback to tab name if we cannot get the tab id.
6085 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6086 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6087 if tab_name:
6088 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6089 return {
6090 'home': 'featured',
6091 'live': 'streams',
6092 }.get(tab_name, tab_name), tab_name
6093
6094 def _has_tab(self, tabs, tab_id):
6095 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6096
182bda88 6097 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6098 def _real_extract(self, url, smuggled_data):
cd7c66cf 6099 item_id = self._match_id(url)
14f25df2 6100 url = urllib.parse.urlunparse(
6101 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6102 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6103
86973308
M
6104 mobj = self._get_url_mobj(url)
6105 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6106 if is_channel and smuggled_data.get('is_music_url'):
6107 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6108 return self.url_result(
6109 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6110 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6111 mdata = self._extract_tab_endpoint(
6112 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6113 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6114 get_all=False, expected_type=str)
6115 if not murl:
6116 raise ExtractorError('Failed to resolve album to playlist')
6117 return self.url_result(murl, YoutubeTabIE)
6118 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6119 return self.url_result(
6120 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6121
6122 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6123 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6124 url = f'{pre}/videos{post}'
cd7c66cf 6125
6126 # Handle both video/playlist URLs
201c1459 6127 qs = parse_qs(url)
bd7e919a 6128 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6129 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6130 if not playlist_id:
fe03a6cd 6131 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6132 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6133 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6134 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6135 return self.url_result(
6136 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6137
86973308
M
6138 if not self._yes_playlist(playlist_id, video_id):
6139 return self.url_result(
6140 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6141
bd7e919a 6142 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6143
7c219ea6 6144 # YouTube may provide a non-standard redirect to the regional channel
6145 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6146 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6147 redirect_url = traverse_obj(
6148 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6149 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6150 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6151 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6152 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6153
bd7e919a 6154 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6155 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6156 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6157 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6158 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6159
6160 if not original_tab_id and selected_tab_name:
bd7e919a 6161 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6162 'To download only the videos in a specific tab, pass the tab\'s URL')
6163 if self._has_tab(tabs, 'streams'):
bd7e919a 6164 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6165 if self._has_tab(tabs, 'shorts'):
bd7e919a 6166 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6167 # XXX: Members-only tab should also be extracted
6168
bd7e919a 6169 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6170 # Channel does not have streams, shorts or videos tabs
6171 if item_id[:2] != 'UC':
6172 raise ExtractorError('This channel has no uploads', expected=True)
6173
6174 # Topic channels don't have /videos. Use the equivalent playlist instead
6175 pl_id = f'UU{item_id[2:]}'
6176 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6177 try:
6178 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6179 except ExtractorError:
6180 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6181 else:
86973308
M
6182 item_id, url = pl_id, pl_url
6183 self.to_screen(
6184 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6185
bd7e919a 6186 elif extra_tabs and selected_tab_id != 'videos':
86973308 6187 # When there are shorts/live tabs but not videos tab
bd7e919a 6188 url, data = f'{pre}{post}', None
86973308
M
6189
6190 elif (original_tab_id or 'videos') != selected_tab_id:
6191 if original_tab_id == 'live':
6192 # Live tab should have redirected to the video
6193 # Except in the case the channel has an actual live tab
6194 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6195 raise UserNotLive(video_id=item_id)
86973308
M
6196 elif selected_tab_name:
6197 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6198
6199 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6200 url = f'{pre}{post}'
18db7548 6201
358de58c 6202 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6203 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6204 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6205 self._extract_and_report_alerts(data, only_once=True)
86973308 6206
bd7e919a 6207 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6208 if tabs:
bd7e919a 6209 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6210 entries[0].update({
86973308
M
6211 'extractor_key': YoutubeTabIE.ie_key(),
6212 'extractor': YoutubeTabIE.IE_NAME,
6213 'webpage_url': url,
6214 })
bd7e919a 6215 if self.get_param('playlist_items') == '0':
6216 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6217 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6218 entries.extend(map(self._real_extract, extra_tabs))
6219
6220 if len(entries) == 1:
6221 return entries[0]
6222 elif entries:
6223 metadata = self._extract_metadata_from_tabs(item_id, data)
6224 uploads_url = 'the Uploads (UU) playlist URL'
6225 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6226 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6227 self.to_screen(
6228 'Downloading as multiple playlists, separated by tabs. '
6229 f'To download as a single playlist instead, pass {uploads_url}')
6230 return self.playlist_result(entries, item_id, **metadata)
6231
6232 # Inline playlist
37e57a9f 6233 playlist = traverse_obj(
6234 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6235 if playlist:
ac56cf38 6236 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6237
37e57a9f 6238 video_id = traverse_obj(
6239 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6240 if video_id:
bd7e919a 6241 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6242 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6243 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6244
8bdd16b4 6245 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6246
c5e8d7af 6247
8bdd16b4 6248class YoutubePlaylistIE(InfoExtractor):
96565c7e 6249 IE_DESC = 'YouTube playlists'
8bdd16b4 6250 _VALID_URL = r'''(?x)(?:
6251 (?:https?://)?
6252 (?:\w+\.)?
6253 (?:
6254 (?:
6255 youtube(?:kids)?\.com|
d9190e44 6256 %(invidious)s
8bdd16b4 6257 )
6258 /.*?\?.*?\blist=
6259 )?
6260 (?P<id>%(playlist_id)s)
d9190e44
RH
6261 )''' % {
6262 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6263 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6264 }
8bdd16b4 6265 IE_NAME = 'youtube:playlist'
cdc628a4 6266 _TESTS = [{
8bdd16b4 6267 'note': 'issue #673',
6268 'url': 'PLBB231211A4F62143',
cdc628a4 6269 'info_dict': {
8bdd16b4 6270 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6271 'id': 'PLBB231211A4F62143',
976ae3ea 6272 'uploader': 'Wickman',
8bdd16b4 6273 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 6274 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6275 'view_count': int,
86973308 6276 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
976ae3ea 6277 'modified_date': r're:\d{8}',
6278 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6279 'channel': 'Wickman',
6280 'tags': [],
86973308
M
6281 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6282 'availability': 'public',
8bdd16b4 6283 },
6284 'playlist_mincount': 29,
6285 }, {
6286 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6287 'info_dict': {
6288 'title': 'YDL_safe_search',
6289 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6290 },
6291 'playlist_count': 2,
6292 'skip': 'This playlist is private',
9558dcec 6293 }, {
8bdd16b4 6294 'note': 'embedded',
6295 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6296 'playlist_count': 4,
9558dcec 6297 'info_dict': {
8bdd16b4 6298 'title': 'JODA15',
6299 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6300 'uploader': 'milan',
6301 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 6302 'description': '',
6303 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6304 'tags': [],
6305 'modified_date': '20140919',
6306 'view_count': int,
6307 'channel': 'milan',
6308 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6309 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 6310 'availability': 'public',
976ae3ea 6311 },
86973308 6312 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6313 }, {
8bdd16b4 6314 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6315 'playlist_mincount': 455,
8bdd16b4 6316 'info_dict': {
6317 'title': '2018 Chinese New Singles (11/6 updated)',
6318 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6319 'uploader': 'LBK',
6320 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 6321 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6322 'channel': 'LBK',
6323 'view_count': int,
6324 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6325 'tags': [],
6326 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6327 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6328 'modified_date': r're:\d{8}',
c26f9b99 6329 'availability': 'public',
976ae3ea 6330 },
6331 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6332 }, {
29f7c58a 6333 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6334 'only_matching': True,
6335 }, {
6336 # music album playlist
6337 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6338 'only_matching': True,
6339 }]
6340
6341 @classmethod
6342 def suitable(cls, url):
201c1459 6343 if YoutubeTabIE.suitable(url):
6344 return False
49a57e70 6345 from ..utils import parse_qs
201c1459 6346 qs = parse_qs(url)
6347 if qs.get('v', [None])[0]:
6348 return False
86e5f3ed 6349 return super().suitable(url)
29f7c58a 6350
6351 def _real_extract(self, url):
6352 playlist_id = self._match_id(url)
46953e7e 6353 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6354 url = update_url_query(
6355 'https://www.youtube.com/playlist',
6356 parse_qs(url) or {'list': playlist_id})
6357 if is_music_url:
6358 url = smuggle_url(url, {'is_music_url': True})
6359 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6360
6361
6362class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6363 IE_DESC = 'youtu.be'
29f7c58a 6364 _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}
6365 _TESTS = [{
8bdd16b4 6366 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6367 'info_dict': {
6368 'id': 'yeWKywCrFtk',
6369 'ext': 'mp4',
6370 'title': 'Small Scale Baler and Braiding Rugs',
6371 'uploader': 'Backus-Page House Museum',
6372 'uploader_id': 'backuspagemuseum',
6373 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6374 'upload_date': '20161008',
6375 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6376 'categories': ['Nonprofits & Activism'],
6377 'tags': list,
6378 'like_count': int,
976ae3ea 6379 'age_limit': 0,
6380 'playable_in_embed': True,
6381 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6382 'channel': 'Backus-Page House Museum',
6383 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6384 'live_status': 'not_live',
6385 'view_count': int,
6386 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6387 'availability': 'public',
6388 'duration': 59,
12a1b225
A
6389 'comment_count': int,
6390 'channel_follower_count': int
8bdd16b4 6391 },
6392 'params': {
6393 'noplaylist': True,
6394 'skip_download': True,
6395 },
39e7107d 6396 }, {
8bdd16b4 6397 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6398 'only_matching': True,
cdc628a4
PH
6399 }]
6400
8bdd16b4 6401 def _real_extract(self, url):
5ad28e7f 6402 mobj = self._match_valid_url(url)
29f7c58a 6403 video_id = mobj.group('id')
6404 playlist_id = mobj.group('playlist_id')
8bdd16b4 6405 return self.url_result(
29f7c58a 6406 update_url_query('https://www.youtube.com/watch', {
6407 'v': video_id,
6408 'list': playlist_id,
6409 'feature': 'youtu.be',
6410 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6411
6412
b6ce9bb0 6413class YoutubeLivestreamEmbedIE(InfoExtractor):
6414 IE_DESC = 'YouTube livestream embeds'
6415 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6416 _TESTS = [{
6417 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6418 'only_matching': True,
6419 }]
6420
6421 def _real_extract(self, url):
6422 channel_id = self._match_id(url)
6423 return self.url_result(
6424 f'https://www.youtube.com/channel/{channel_id}/live',
6425 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6426
6427
8bdd16b4 6428class YoutubeYtUserIE(InfoExtractor):
96565c7e 6429 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6430 IE_NAME = 'youtube:user'
8bdd16b4 6431 _VALID_URL = r'ytuser:(?P<id>.+)'
6432 _TESTS = [{
6433 'url': 'ytuser:phihag',
6434 'only_matching': True,
6435 }]
6436
6437 def _real_extract(self, url):
6438 user_id = self._match_id(url)
08270da5 6439 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6440
b05654f0 6441
3d3dddc9 6442class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6443 IE_NAME = 'youtube:favorites'
96565c7e 6444 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6445 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6446 _LOGIN_REQUIRED = True
6447 _TESTS = [{
6448 'url': ':ytfav',
6449 'only_matching': True,
6450 }, {
6451 'url': ':ytfavorites',
6452 'only_matching': True,
6453 }]
6454
6455 def _real_extract(self, url):
6456 return self.url_result(
6457 'https://www.youtube.com/playlist?list=LL',
6458 ie=YoutubeTabIE.ie_key())
6459
6460
ca5300c7 6461class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6462 IE_NAME = 'youtube:notif'
6463 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6464 _VALID_URL = r':ytnotif(?:ication)?s?'
6465 _LOGIN_REQUIRED = True
6466 _TESTS = [{
6467 'url': ':ytnotif',
6468 'only_matching': True,
6469 }, {
6470 'url': ':ytnotifications',
6471 'only_matching': True,
6472 }]
6473
6474 def _extract_notification_menu(self, response, continuation_list):
6475 notification_list = traverse_obj(
6476 response,
6477 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6478 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6479 expected_type=list) or []
6480 continuation_list[0] = None
6481 for item in notification_list:
6482 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6483 if entry:
6484 yield entry
6485 continuation = item.get('continuationItemRenderer')
6486 if continuation:
6487 continuation_list[0] = continuation
6488
6489 def _extract_notification_renderer(self, notification):
6490 video_id = traverse_obj(
6491 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6492 url = f'https://www.youtube.com/watch?v={video_id}'
6493 channel_id = None
6494 if not video_id:
6495 browse_ep = traverse_obj(
6496 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6497 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6498 post_id = self._search_regex(
6499 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6500 'post id', default=None)
6501 if not channel_id or not post_id:
6502 return
6503 # The direct /post url redirects to this in the browser
6504 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6505
6506 channel = traverse_obj(
6507 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6508 expected_type=str)
c7a7baaa 6509 notification_title = self._get_text(notification, 'shortMessage')
6510 if notification_title:
6511 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6512 # TODO: handle recommended videos
ca5300c7 6513 title = self._search_regex(
c7a7baaa 6514 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6515 'video title', default=None)
5225df50 6516 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6517 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6518 else None)
ca5300c7 6519 return {
6520 '_type': 'url',
6521 'url': url,
6522 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6523 'video_id': video_id,
6524 'title': title,
6525 'channel_id': channel_id,
6526 'channel': channel,
6527 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6528 'timestamp': timestamp,
ca5300c7 6529 }
6530
6531 def _notification_menu_entries(self, ytcfg):
6532 continuation_list = [None]
6533 response = None
6534 for page in itertools.count(1):
6535 ctoken = traverse_obj(
6536 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6537 response = self._extract_response(
6538 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6539 ep='notification/get_notification_menu', check_get_keys='actions',
6540 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6541 yield from self._extract_notification_menu(response, continuation_list)
6542 if not continuation_list[0]:
6543 break
6544
6545 def _real_extract(self, url):
6546 display_id = 'notifications'
6547 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6548 self._report_playlist_authcheck(ytcfg)
6549 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6550
6551
a6213a49 6552class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6553 IE_DESC = 'YouTube search'
78caa52a 6554 IE_NAME = 'youtube:search'
b05654f0 6555 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6556 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6557 _TESTS = [{
6558 'url': 'ytsearch5:youtube-dl test video',
6559 'playlist_count': 5,
6560 'info_dict': {
6561 'id': 'youtube-dl test video',
6562 'title': 'youtube-dl test video',
6563 }
6564 }]
b05654f0 6565
a61fd4cf 6566
5f7cb91a 6567class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6568 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6569 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6570 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6571 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6572 _TESTS = [{
6573 'url': 'ytsearchdate5:youtube-dl test video',
6574 'playlist_count': 5,
6575 'info_dict': {
6576 'id': 'youtube-dl test video',
6577 'title': 'youtube-dl test video',
6578 }
6579 }]
75dff0ee 6580
c9ae7b95 6581
a6213a49 6582class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6583 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6584 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6585 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6586 _TESTS = [{
6587 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6588 'playlist_mincount': 5,
6589 'info_dict': {
11f9be09 6590 'id': 'youtube-dl test video',
3462ffa8 6591 'title': 'youtube-dl test video',
6592 }
a61fd4cf 6593 }, {
6594 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6595 'playlist_mincount': 5,
6596 'info_dict': {
6597 'id': 'python',
6598 'title': 'python',
6599 }
ad210f4f 6600 }, {
6601 'url': 'https://www.youtube.com/results?search_query=%23cats',
6602 'playlist_mincount': 1,
6603 'info_dict': {
6604 'id': '#cats',
6605 'title': '#cats',
12a1b225
A
6606 # The test suite does not have support for nested playlists
6607 # 'entries': [{
6608 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6609 # 'title': '#cats',
6610 # }],
ad210f4f 6611 },
c7335551
M
6612 }, {
6613 # Channel results
6614 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6615 'info_dict': {
6616 'id': 'kurzgesagt',
6617 'title': 'kurzgesagt',
6618 },
6619 'playlist': [{
6620 'info_dict': {
6621 '_type': 'url',
6622 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6623 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6624 'ie_key': 'YoutubeTab',
6625 'channel': 'Kurzgesagt – In a Nutshell',
6626 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6627 'title': 'Kurzgesagt – In a Nutshell',
6628 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6629 'playlist_count': int, # XXX: should have a way of saying > 1
6630 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6631 'thumbnails': list
6632 }
6633 }],
6634 'params': {'extract_flat': True, 'playlist_items': '1'},
6635 'playlist_mincount': 1,
3462ffa8 6636 }, {
6637 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6638 'only_matching': True,
6639 }]
6640
6641 def _real_extract(self, url):
4dfbf869 6642 qs = parse_qs(url)
386e1dd9 6643 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6644 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6645
6646
16aa9ea4 6647class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6648 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6649 IE_NAME = 'youtube:music:search_url'
6650 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6651 _TESTS = [{
6652 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6653 'playlist_count': 16,
6654 'info_dict': {
6655 'id': 'royalty free music',
6656 'title': 'royalty free music',
6657 }
6658 }, {
6659 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6660 'playlist_mincount': 30,
6661 'info_dict': {
6662 'id': 'royalty free music - songs',
6663 'title': 'royalty free music - songs',
6664 },
6665 'params': {'extract_flat': 'in_playlist'}
6666 }, {
6667 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6668 'playlist_mincount': 30,
6669 'info_dict': {
6670 'id': 'royalty free music - community playlists',
6671 'title': 'royalty free music - community playlists',
6672 },
6673 'params': {'extract_flat': 'in_playlist'}
6674 }]
6675
6676 _SECTIONS = {
6677 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6678 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6679 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6680 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6681 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6682 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6683 }
6684
6685 def _real_extract(self, url):
6686 qs = parse_qs(url)
6687 query = (qs.get('search_query') or qs.get('q'))[0]
6688 params = qs.get('sp', (None,))[0]
6689 if params:
6690 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6691 else:
ac668111 6692 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6693 params = self._SECTIONS.get(section)
6694 if not params:
6695 section = None
6696 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6697 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6698
6699
182bda88 6700class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6701 """
25f14e9f 6702 Base class for feed extractors
82d02080 6703 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6704 """
b2e8bc1b 6705 _LOGIN_REQUIRED = True
82d02080 6706 _FEED_NAME = 'feeds'
a25bca9f 6707
6708 def _real_initialize(self):
6709 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6710
82d02080 6711 @classproperty
d7ae0639 6712 def IE_NAME(self):
82d02080 6713 return f'youtube:{self._FEED_NAME}'
04cc9617 6714
3853309f 6715 def _real_extract(self, url):
3d3dddc9 6716 return self.url_result(
182bda88 6717 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6718
6719
ef2f3c7f 6720class YoutubeWatchLaterIE(InfoExtractor):
6721 IE_NAME = 'youtube:watchlater'
96565c7e 6722 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6723 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6724 _TESTS = [{
8bdd16b4 6725 'url': ':ytwatchlater',
bc7a9cd8
S
6726 'only_matching': True,
6727 }]
25f14e9f
S
6728
6729 def _real_extract(self, url):
ef2f3c7f 6730 return self.url_result(
6731 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6732
6733
25f14e9f 6734class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6735 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6736 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6737 _FEED_NAME = 'recommended'
45db527f 6738 _LOGIN_REQUIRED = False
3d3dddc9 6739 _TESTS = [{
6740 'url': ':ytrec',
6741 'only_matching': True,
6742 }, {
6743 'url': ':ytrecommended',
6744 'only_matching': True,
6745 }, {
6746 'url': 'https://youtube.com',
6747 'only_matching': True,
6748 }]
1ed5b5c9 6749
1ed5b5c9 6750
25f14e9f 6751class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6752 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6753 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6754 _FEED_NAME = 'subscriptions'
3d3dddc9 6755 _TESTS = [{
6756 'url': ':ytsubs',
6757 'only_matching': True,
6758 }, {
6759 'url': ':ytsubscriptions',
6760 'only_matching': True,
6761 }]
1ed5b5c9 6762
1ed5b5c9 6763
25f14e9f 6764class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6765 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6766 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6767 _FEED_NAME = 'history'
3d3dddc9 6768 _TESTS = [{
6769 'url': ':ythistory',
6770 'only_matching': True,
6771 }]
1ed5b5c9
JMF
6772
6773
6e634cbe 6774class YoutubeStoriesIE(InfoExtractor):
6775 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6776 IE_NAME = 'youtube:stories'
6777 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6778 _TESTS = [{
6779 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6780 'only_matching': True,
6781 }]
6782
6783 def _real_extract(self, url):
6784 playlist_id = f'RLTD{self._match_id(url)}'
6785 return self.url_result(
50ac0e54 6786 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6787 ie=YoutubeTabIE, video_id=playlist_id)
6788
6789
80eb0bd9 6790class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6791 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6792 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6793 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6794 _TESTS = [{
1dd18a88 6795 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6796 'only_matching': True,
6797 }]
6798
6799 @staticmethod
6800 def _generate_audio_pivot_params(video_id):
6801 """
6802 Generates sfv_audio_pivot browse params for this video id
6803 """
6804 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6805 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6806
6807 def _real_extract(self, url):
6808 video_id = self._match_id(url)
6809 return self.url_result(
6810 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6811 ie=YoutubeTabIE)
6812
6813
15870e90
PH
6814class YoutubeTruncatedURLIE(InfoExtractor):
6815 IE_NAME = 'youtube:truncated_url'
6816 IE_DESC = False # Do not list
975d35db 6817 _VALID_URL = r'''(?x)
b95aab84
PH
6818 (?:https?://)?
6819 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6820 (?:watch\?(?:
c4808c60 6821 feature=[a-z_]+|
b95aab84
PH
6822 annotation_id=annotation_[^&]+|
6823 x-yt-cl=[0-9]+|
c1708b89 6824 hl=[^&]*|
287be8c6 6825 t=[0-9]+
b95aab84
PH
6826 )?
6827 |
6828 attribution_link\?a=[^&]+
6829 )
6830 $
975d35db 6831 '''
15870e90 6832
c4808c60 6833 _TESTS = [{
2d3d2997 6834 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6835 'only_matching': True,
dc2fc736 6836 }, {
2d3d2997 6837 'url': 'https://www.youtube.com/watch?',
dc2fc736 6838 'only_matching': True,
b95aab84
PH
6839 }, {
6840 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6841 'only_matching': True,
6842 }, {
6843 'url': 'https://www.youtube.com/watch?feature=foo',
6844 'only_matching': True,
c1708b89
PH
6845 }, {
6846 'url': 'https://www.youtube.com/watch?hl=en-GB',
6847 'only_matching': True,
287be8c6
PH
6848 }, {
6849 'url': 'https://www.youtube.com/watch?t=2372',
6850 'only_matching': True,
c4808c60
PH
6851 }]
6852
15870e90
PH
6853 def _real_extract(self, url):
6854 raise ExtractorError(
78caa52a
PH
6855 'Did you forget to quote the URL? Remember that & is a meta '
6856 'character in most shells, so you want to put the URL in quotes, '
3867038a 6857 'like youtube-dl '
2d3d2997 6858 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6859 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6860 expected=True)
772fd5cc
PH
6861
6862
471d0367 6863class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6864 IE_NAME = 'youtube:clip'
471d0367 6865 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6866 _TESTS = [{
6867 # FIXME: Other metadata should be extracted from the clip, not from the base video
6868 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6869 'info_dict': {
6870 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6871 'ext': 'mp4',
6872 'section_start': 29.0,
6873 'section_end': 39.7,
6874 'duration': 10.7,
12a1b225
A
6875 'age_limit': 0,
6876 'availability': 'public',
6877 'categories': ['Gaming'],
6878 'channel': 'Scott The Woz',
6879 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6880 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6881 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6882 'like_count': int,
6883 'playable_in_embed': True,
6884 'tags': 'count:17',
6885 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6886 'title': 'Mobile Games on Console - Scott The Woz',
6887 'upload_date': '20210920',
6888 'uploader': 'Scott The Woz',
6889 'uploader_id': 'scottthewoz',
6890 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6891 'view_count': int,
6892 'live_status': 'not_live',
6893 'channel_follower_count': int
471d0367 6894 }
6895 }]
3cd786db 6896
6897 def _real_extract(self, url):
471d0367 6898 clip_id = self._match_id(url)
6899 _, data = self._extract_webpage(url, clip_id)
6900
6901 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6902 if not video_id:
6903 raise ExtractorError('Unable to find video ID')
6904
6905 clip_data = traverse_obj(data, (
6906 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6907 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6908 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6909 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6910
6911 return {
6912 '_type': 'url_transparent',
6913 'url': f'https://www.youtube.com/watch?v={video_id}',
6914 'ie_key': YoutubeIE.ie_key(),
6915 'id': clip_id,
6916 'section_start': int(clip_data['startTimeMs']) / 1000,
6917 'section_end': int(clip_data['endTimeMs']) / 1000,
6918 }
3cd786db 6919
6920
772fd5cc
PH
6921class YoutubeTruncatedIDIE(InfoExtractor):
6922 IE_NAME = 'youtube:truncated_id'
6923 IE_DESC = False # Do not list
b95aab84 6924 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6925
6926 _TESTS = [{
6927 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6928 'only_matching': True,
6929 }]
6930
6931 def _real_extract(self, url):
6932 video_id = self._match_id(url)
6933 raise ExtractorError(
86e5f3ed 6934 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6935 expected=True)