]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[extractor/rutube] Extract chapters from description (#6345)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
1 import base64
2 import calendar
3 import collections
4 import copy
5 import datetime
6 import enum
7 import hashlib
8 import itertools
9 import json
10 import math
11 import os.path
12 import random
13 import re
14 import sys
15 import threading
16 import time
17 import traceback
18 import urllib.error
19 import urllib.parse
20
21 from .common import InfoExtractor, SearchInfoExtractor
22 from .openload import PhantomJSwrapper
23 from ..compat import functools
24 from ..jsinterp import JSInterpreter
25 from ..utils import (
26 NO_DEFAULT,
27 ExtractorError,
28 LazyList,
29 UserNotLive,
30 bug_reports_message,
31 classproperty,
32 clean_html,
33 datetime_from_str,
34 dict_get,
35 filter_dict,
36 float_or_none,
37 format_field,
38 get_first,
39 int_or_none,
40 is_html,
41 join_nonempty,
42 js_to_json,
43 mimetype2ext,
44 network_exceptions,
45 orderedSet,
46 parse_codecs,
47 parse_count,
48 parse_duration,
49 parse_iso8601,
50 parse_qs,
51 qualities,
52 remove_start,
53 smuggle_url,
54 str_or_none,
55 str_to_int,
56 strftime_or_none,
57 traverse_obj,
58 try_get,
59 unescapeHTML,
60 unified_strdate,
61 unified_timestamp,
62 unsmuggle_url,
63 update_url_query,
64 url_or_none,
65 urljoin,
66 variadic,
67 )
68
69 # any clients starting with _ cannot be explicitly requested by the user
70 INNERTUBE_CLIENTS = {
71 'web': {
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
74 'client': {
75 'clientName': 'WEB',
76 'clientVersion': '2.20220801.00.00',
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',
86 'clientVersion': '1.20220731.00.00',
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',
97 'clientVersion': '1.20220727.01.00',
98 }
99 },
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
101 },
102 'web_creator': {
103 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_CREATOR',
107 'clientVersion': '1.20220726.00.00',
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
111 },
112 'android': {
113 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'ANDROID',
117 'clientVersion': '17.31.35',
118 'androidSdkVersion': 30,
119 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
120 }
121 },
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
123 'REQUIRE_JS_PLAYER': False
124 },
125 'android_embedded': {
126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
127 'INNERTUBE_CONTEXT': {
128 'client': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
130 'clientVersion': '17.31.35',
131 'androidSdkVersion': 30,
132 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
133 },
134 },
135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
137 },
138 'android_music': {
139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
140 'INNERTUBE_CONTEXT': {
141 'client': {
142 'clientName': 'ANDROID_MUSIC',
143 'clientVersion': '5.16.51',
144 'androidSdkVersion': 30,
145 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
146 }
147 },
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
149 'REQUIRE_JS_PLAYER': False
150 },
151 'android_creator': {
152 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
153 'INNERTUBE_CONTEXT': {
154 'client': {
155 'clientName': 'ANDROID_CREATOR',
156 'clientVersion': '22.30.100',
157 'androidSdkVersion': 30,
158 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
159 },
160 },
161 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
162 'REQUIRE_JS_PLAYER': False
163 },
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
166 'ios': {
167 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS',
171 'clientVersion': '17.33.2',
172 'deviceModel': 'iPhone14,3',
173 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
174 }
175 },
176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
178 },
179 'ios_embedded': {
180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
183 'clientVersion': '17.33.2',
184 'deviceModel': 'iPhone14,3',
185 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
186 },
187 },
188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
190 },
191 'ios_music': {
192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
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)'
199 },
200 },
201 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
202 'REQUIRE_JS_PLAYER': False
203 },
204 'ios_creator': {
205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'IOS_CREATOR',
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)'
211 },
212 },
213 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
214 'REQUIRE_JS_PLAYER': False
215 },
216 # mweb has 'ultralow' formats
217 # See: https://github.com/yt-dlp/yt-dlp/pull/557
218 'mweb': {
219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
220 'INNERTUBE_CONTEXT': {
221 'client': {
222 'clientName': 'MWEB',
223 'clientVersion': '2.20220801.00.00',
224 }
225 },
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
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 },
240 }
241
242
243 def _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
251 def build_innertube_clients():
252 THIRD_PARTY = {
253 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
254 }
255 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
256 priority = qualities(BASE_CLIENTS[::-1])
257
258 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
259 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
260 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
261 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
262 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
263
264 _, base_client, variant = _split_innertube_client(client)
265 ytcfg['priority'] = 10 * priority(base_client)
266
267 if not variant:
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':
273 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
274 ytcfg['priority'] -= 2
275 else:
276 ytcfg['priority'] -= 3
277
278
279 build_innertube_clients()
280
281
282 class 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
291 class YoutubeBaseInfoExtractor(InfoExtractor):
292 """Provide base functions for Youtube extractors"""
293
294 _RESERVED_NAMES = (
295 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
296 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
297 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
298 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
299
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
302 # _NETRC_MACHINE = 'youtube'
303
304 # If True it will raise an error if no login info is provided
305 _LOGIN_REQUIRED = False
306
307 _INVIDIOUS_SITES = (
308 # invidious-redirect websites
309 r'(?:www\.)?redirect\.invidious\.io',
310 r'(?:(?:www|dev)\.)?invidio\.us',
311 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
312 r'(?:www\.)?invidious\.pussthecat\.org',
313 r'(?:www\.)?invidious\.zee\.li',
314 r'(?:www\.)?invidious\.ethibox\.fr',
315 r'(?:www\.)?iv\.ggtyler\.dev',
316 r'(?:www\.)?inv\.vern\.i2p',
317 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
318 r'(?:www\.)?inv\.riverside\.rocks',
319 r'(?:www\.)?invidious\.silur\.me',
320 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
321 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
322 r'(?:www\.)?invidious\.slipfox\.xyz',
323 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
324 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
325 r'(?:www\.)?invidious\.tiekoetter\.com',
326 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
327 r'(?:www\.)?invidious\.nerdvpn\.de',
328 r'(?:www\.)?invidious\.weblibre\.org',
329 r'(?:www\.)?inv\.odyssey346\.dev',
330 r'(?:www\.)?invidious\.dhusch\.de',
331 r'(?:www\.)?iv\.melmac\.space',
332 r'(?:www\.)?watch\.thekitty\.zone',
333 r'(?:www\.)?invidious\.privacydev\.net',
334 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
335 r'(?:www\.)?invidious\.drivet\.xyz',
336 r'(?:www\.)?vid\.priv\.au',
337 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
338 r'(?:www\.)?inv\.vern\.cc',
339 r'(?:www\.)?invidious\.esmailelbob\.xyz',
340 r'(?:www\.)?invidious\.sethforprivacy\.com',
341 r'(?:www\.)?yt\.oelrichsgarcia\.de',
342 r'(?:www\.)?yt\.artemislena\.eu',
343 r'(?:www\.)?invidious\.flokinet\.to',
344 r'(?:www\.)?invidious\.baczek\.me',
345 r'(?:www\.)?y\.com\.sb',
346 r'(?:www\.)?invidious\.epicsite\.xyz',
347 r'(?:www\.)?invidious\.lidarshield\.cloud',
348 r'(?:www\.)?yt\.funami\.tech',
349 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
350 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
351 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
352 # youtube-dl invidious instances list
353 r'(?:(?:www|no)\.)?invidiou\.sh',
354 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
355 r'(?:www\.)?invidious\.kabi\.tk',
356 r'(?:www\.)?invidious\.mastodon\.host',
357 r'(?:www\.)?invidious\.zapashcanon\.fr',
358 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
359 r'(?:www\.)?invidious\.tinfoil-hat\.net',
360 r'(?:www\.)?invidious\.himiko\.cloud',
361 r'(?:www\.)?invidious\.reallyancient\.tech',
362 r'(?:www\.)?invidious\.tube',
363 r'(?:www\.)?invidiou\.site',
364 r'(?:www\.)?invidious\.site',
365 r'(?:www\.)?invidious\.xyz',
366 r'(?:www\.)?invidious\.nixnet\.xyz',
367 r'(?:www\.)?invidious\.048596\.xyz',
368 r'(?:www\.)?invidious\.drycat\.fr',
369 r'(?:www\.)?inv\.skyn3t\.in',
370 r'(?:www\.)?tube\.poal\.co',
371 r'(?:www\.)?tube\.connect\.cafe',
372 r'(?:www\.)?vid\.wxzm\.sx',
373 r'(?:www\.)?vid\.mint\.lgbt',
374 r'(?:www\.)?vid\.puffyan\.us',
375 r'(?:www\.)?yewtu\.be',
376 r'(?:www\.)?yt\.elukerio\.org',
377 r'(?:www\.)?yt\.lelux\.fi',
378 r'(?:www\.)?invidious\.ggc-project\.de',
379 r'(?:www\.)?yt\.maisputain\.ovh',
380 r'(?:www\.)?ytprivate\.com',
381 r'(?:www\.)?invidious\.13ad\.de',
382 r'(?:www\.)?invidious\.toot\.koeln',
383 r'(?:www\.)?invidious\.fdn\.fr',
384 r'(?:www\.)?watch\.nettohikari\.com',
385 r'(?:www\.)?invidious\.namazso\.eu',
386 r'(?:www\.)?invidious\.silkky\.cloud',
387 r'(?:www\.)?invidious\.exonip\.de',
388 r'(?:www\.)?invidious\.riverside\.rocks',
389 r'(?:www\.)?invidious\.blamefran\.net',
390 r'(?:www\.)?invidious\.moomoo\.de',
391 r'(?:www\.)?ytb\.trom\.tf',
392 r'(?:www\.)?yt\.cyberhost\.uk',
393 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
394 r'(?:www\.)?qklhadlycap4cnod\.onion',
395 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
396 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
397 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
398 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
399 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
400 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
401 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
402 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
403 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
404 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
405 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
406 r'(?:www\.)?piped\.kavin\.rocks',
407 r'(?:www\.)?piped\.tokhmi\.xyz',
408 r'(?:www\.)?piped\.syncpundit\.io',
409 r'(?:www\.)?piped\.mha\.fi',
410 r'(?:www\.)?watch\.whatever\.social',
411 r'(?:www\.)?piped\.garudalinux\.org',
412 r'(?:www\.)?piped\.rivo\.lol',
413 r'(?:www\.)?piped-libre\.kavin\.rocks',
414 r'(?:www\.)?yt\.jae\.fi',
415 r'(?:www\.)?piped\.mint\.lgbt',
416 r'(?:www\.)?il\.ax',
417 r'(?:www\.)?piped\.esmailelbob\.xyz',
418 r'(?:www\.)?piped\.projectsegfau\.lt',
419 r'(?:www\.)?piped\.privacydev\.net',
420 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
421 r'(?:www\.)?piped\.smnz\.de',
422 r'(?:www\.)?piped\.adminforge\.de',
423 r'(?:www\.)?watch\.whatevertinfoil\.de',
424 r'(?:www\.)?piped\.qdi\.fi',
425 r'(?:www\.)?piped\.video',
426 r'(?:www\.)?piped\.aeong\.one',
427 r'(?:www\.)?piped\.moomoo\.me',
428 r'(?:www\.)?piped\.chauvet\.pro',
429 r'(?:www\.)?watch\.leptons\.xyz',
430 r'(?:www\.)?pd\.vern\.cc',
431 r'(?:www\.)?piped\.hostux\.net',
432 r'(?:www\.)?piped\.lunar\.icu',
433 # Hyperpipe instances from https://hyperpipe.codeberg.page/
434 r'(?:www\.)?hyperpipe\.surge\.sh',
435 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
436 r'(?:www\.)?listen\.whatever\.social',
437 r'(?:www\.)?music\.adminforge\.de',
438 )
439
440 # extracted from account/account_menu ep
441 # XXX: These are the supported YouTube UI and API languages,
442 # which is slightly different from languages supported for translation in YouTube studio
443 _SUPPORTED_LANG_CODES = [
444 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
445 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
446 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
447 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
448 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
449 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
450 ]
451
452 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
453
454 @functools.cached_property
455 def _preferred_lang(self):
456 """
457 Returns a language code supported by YouTube for the user preferred language.
458 Returns None if no preferred language set.
459 """
460 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
461 if not preferred_lang:
462 return
463 if preferred_lang not in self._SUPPORTED_LANG_CODES:
464 raise ExtractorError(
465 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
466 expected=True)
467 elif preferred_lang != 'en':
468 self.report_warning(
469 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
470 return preferred_lang
471
472 def _initialize_consent(self):
473 cookies = self._get_cookies('https://www.youtube.com/')
474 if cookies.get('__Secure-3PSID'):
475 return
476 consent_id = None
477 consent = cookies.get('CONSENT')
478 if consent:
479 if 'YES' in consent.value:
480 return
481 consent_id = self._search_regex(
482 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
483 if not consent_id:
484 consent_id = random.randint(100, 999)
485 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
486
487 def _initialize_pref(self):
488 cookies = self._get_cookies('https://www.youtube.com/')
489 pref_cookie = cookies.get('PREF')
490 pref = {}
491 if pref_cookie:
492 try:
493 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
494 except ValueError:
495 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
496 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
497 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
498
499 def _real_initialize(self):
500 self._initialize_pref()
501 self._initialize_consent()
502 self._check_login_required()
503
504 def _check_login_required(self):
505 if self._LOGIN_REQUIRED and not self._cookies_passed:
506 self.raise_login_required('Login details are needed to download this content', method='cookies')
507
508 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
509 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
510
511 def _get_default_ytcfg(self, client='web'):
512 return copy.deepcopy(INNERTUBE_CLIENTS[client])
513
514 def _get_innertube_host(self, client='web'):
515 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
516
517 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
518 # try_get but with fallback to default ytcfg client values when present
519 _func = lambda y: try_get(y, getter, expected_type)
520 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
521
522 def _extract_client_name(self, ytcfg, default_client='web'):
523 return self._ytcfg_get_safe(
524 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
525 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
526
527 def _extract_client_version(self, ytcfg, default_client='web'):
528 return self._ytcfg_get_safe(
529 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
530 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
531
532 def _select_api_hostname(self, req_api_hostname, default_client=None):
533 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
534 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
535
536 def _extract_api_key(self, ytcfg=None, default_client='web'):
537 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
538
539 def _extract_context(self, ytcfg=None, default_client='web'):
540 context = get_first(
541 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
542 # Enforce language and tz for extraction
543 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
544 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
545 return context
546
547 _SAPISID = None
548
549 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
550 time_now = round(time.time())
551 if self._SAPISID is None:
552 yt_cookies = self._get_cookies('https://www.youtube.com')
553 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
554 # See: https://github.com/yt-dlp/yt-dlp/issues/393
555 sapisid_cookie = dict_get(
556 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
557 if sapisid_cookie and sapisid_cookie.value:
558 self._SAPISID = sapisid_cookie.value
559 self.write_debug('Extracted SAPISID cookie')
560 # SAPISID cookie is required if not already present
561 if not yt_cookies.get('SAPISID'):
562 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
563 self._set_cookie(
564 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
565 else:
566 self._SAPISID = False
567 if not self._SAPISID:
568 return None
569 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
570 sapisidhash = hashlib.sha1(
571 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
572 return f'SAPISIDHASH {time_now}_{sapisidhash}'
573
574 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
575 note='Downloading API JSON', errnote='Unable to download API page',
576 context=None, api_key=None, api_hostname=None, default_client='web'):
577
578 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
579 data.update(query)
580 real_headers = self.generate_api_headers(default_client=default_client)
581 real_headers.update({'content-type': 'application/json'})
582 if headers:
583 real_headers.update(headers)
584 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
585 or api_key or self._extract_api_key(default_client=default_client))
586 return self._download_json(
587 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
588 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
589 data=json.dumps(data).encode('utf8'), headers=real_headers,
590 query={'key': api_key, 'prettyPrint': 'false'})
591
592 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
593 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
594
595 @staticmethod
596 def _extract_session_index(*data):
597 """
598 Index of current account in account list.
599 See: https://github.com/yt-dlp/yt-dlp/pull/519
600 """
601 for ytcfg in data:
602 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
603 if session_index is not None:
604 return session_index
605
606 # Deprecated?
607 def _extract_identity_token(self, ytcfg=None, webpage=None):
608 if ytcfg:
609 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
610 if token:
611 return token
612 if webpage:
613 return self._search_regex(
614 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
615 'identity token', default=None, fatal=False)
616
617 @staticmethod
618 def _extract_account_syncid(*args):
619 """
620 Extract syncId required to download private playlists of secondary channels
621 @params response and/or ytcfg
622 """
623 for data in args:
624 # ytcfg includes channel_syncid if on secondary channel
625 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
626 if delegated_sid:
627 return delegated_sid
628 sync_ids = (try_get(
629 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
630 lambda x: x['DATASYNC_ID']), str) or '').split('||')
631 if len(sync_ids) >= 2 and sync_ids[1]:
632 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
633 # and just "user_syncid||" for primary channel. We only want the channel_syncid
634 return sync_ids[0]
635
636 @staticmethod
637 def _extract_visitor_data(*args):
638 """
639 Extracts visitorData from an API response or ytcfg
640 Appears to be used to track session state
641 """
642 return get_first(
643 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
644 expected_type=str)
645
646 @functools.cached_property
647 def is_authenticated(self):
648 return bool(self._generate_sapisidhash_header())
649
650 def extract_ytcfg(self, video_id, webpage):
651 if not webpage:
652 return {}
653 return self._parse_json(
654 self._search_regex(
655 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
656 default='{}'), video_id, fatal=False) or {}
657
658 def generate_api_headers(
659 self, *, ytcfg=None, account_syncid=None, session_index=None,
660 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
661
662 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
663 headers = {
664 'X-YouTube-Client-Name': str(
665 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
666 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
667 'Origin': origin,
668 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
669 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
670 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
671 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
672 }
673 if session_index is None:
674 session_index = self._extract_session_index(ytcfg)
675 if account_syncid or session_index is not None:
676 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
677
678 auth = self._generate_sapisidhash_header(origin)
679 if auth is not None:
680 headers['Authorization'] = auth
681 headers['X-Origin'] = origin
682 return filter_dict(headers)
683
684 def _download_ytcfg(self, client, video_id):
685 url = {
686 'web': 'https://www.youtube.com',
687 'web_music': 'https://music.youtube.com',
688 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
689 }.get(client)
690 if not url:
691 return {}
692 webpage = self._download_webpage(
693 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
694 return self.extract_ytcfg(video_id, webpage) or {}
695
696 @staticmethod
697 def _build_api_continuation_query(continuation, ctp=None):
698 query = {
699 'continuation': continuation
700 }
701 # TODO: Inconsistency with clickTrackingParams.
702 # Currently we have a fixed ctp contained within context (from ytcfg)
703 # and a ctp in root query for continuation.
704 if ctp:
705 query['clickTracking'] = {'clickTrackingParams': ctp}
706 return query
707
708 @classmethod
709 def _extract_next_continuation_data(cls, renderer):
710 next_continuation = try_get(
711 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
712 lambda x: x['continuation']['reloadContinuationData']), dict)
713 if not next_continuation:
714 return
715 continuation = next_continuation.get('continuation')
716 if not continuation:
717 return
718 ctp = next_continuation.get('clickTrackingParams')
719 return cls._build_api_continuation_query(continuation, ctp)
720
721 @classmethod
722 def _extract_continuation_ep_data(cls, continuation_ep: dict):
723 if isinstance(continuation_ep, dict):
724 continuation = try_get(
725 continuation_ep, lambda x: x['continuationCommand']['token'], str)
726 if not continuation:
727 return
728 ctp = continuation_ep.get('clickTrackingParams')
729 return cls._build_api_continuation_query(continuation, ctp)
730
731 @classmethod
732 def _extract_continuation(cls, renderer):
733 next_continuation = cls._extract_next_continuation_data(renderer)
734 if next_continuation:
735 return next_continuation
736
737 return traverse_obj(renderer, (
738 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
739 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
740 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
741
742 @classmethod
743 def _extract_alerts(cls, data):
744 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
745 if not isinstance(alert_dict, dict):
746 continue
747 for alert in alert_dict.values():
748 alert_type = alert.get('type')
749 if not alert_type:
750 continue
751 message = cls._get_text(alert, 'text')
752 if message:
753 yield alert_type, message
754
755 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
756 errors, warnings = [], []
757 for alert_type, alert_message in alerts:
758 if alert_type.lower() == 'error' and fatal:
759 errors.append([alert_type, alert_message])
760 elif alert_message not in self._IGNORED_WARNINGS:
761 warnings.append([alert_type, alert_message])
762
763 for alert_type, alert_message in (warnings + errors[:-1]):
764 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
765 if errors:
766 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
767
768 def _extract_and_report_alerts(self, data, *args, **kwargs):
769 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
770
771 def _extract_badges(self, renderer: dict):
772 privacy_icon_map = {
773 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
774 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
775 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
776 }
777
778 badge_style_map = {
779 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
780 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
781 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
782 }
783
784 label_map = {
785 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
786 'private': BadgeType.AVAILABILITY_PRIVATE,
787 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
788 'live': BadgeType.LIVE_NOW,
789 'premium': BadgeType.AVAILABILITY_PREMIUM
790 }
791
792 badges = []
793 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')):
794 badge_type = (
795 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
796 or badge_style_map.get(traverse_obj(badge, 'style'))
797 )
798 if badge_type:
799 badges.append({'type': badge_type})
800 continue
801
802 # fallback, won't work in some languages
803 label = traverse_obj(badge, 'label', expected_type=str, default='')
804 for match, label_badge_type in label_map.items():
805 if match in label.lower():
806 badges.append({'type': badge_type})
807 continue
808
809 return badges
810
811 @staticmethod
812 def _has_badge(badges, badge_type):
813 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
814
815 @staticmethod
816 def _get_text(data, *path_list, max_runs=None):
817 for path in path_list or [None]:
818 if path is None:
819 obj = [data]
820 else:
821 obj = traverse_obj(data, path, default=[])
822 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
823 obj = [obj]
824 for item in obj:
825 text = try_get(item, lambda x: x['simpleText'], str)
826 if text:
827 return text
828 runs = try_get(item, lambda x: x['runs'], list) or []
829 if not runs and isinstance(item, list):
830 runs = item
831
832 runs = runs[:min(len(runs), max_runs or len(runs))]
833 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
834 if text:
835 return text
836
837 def _get_count(self, data, *path_list):
838 count_text = self._get_text(data, *path_list) or ''
839 count = parse_count(count_text)
840 if count is None:
841 count = str_to_int(
842 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
843 return count
844
845 @staticmethod
846 def _extract_thumbnails(data, *path_list):
847 """
848 Extract thumbnails from thumbnails dict
849 @param path_list: path list to level that contains 'thumbnails' key
850 """
851 thumbnails = []
852 for path in path_list or [()]:
853 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
854 thumbnail_url = url_or_none(thumbnail.get('url'))
855 if not thumbnail_url:
856 continue
857 # Sometimes youtube gives a wrong thumbnail URL. See:
858 # https://github.com/yt-dlp/yt-dlp/issues/233
859 # https://github.com/ytdl-org/youtube-dl/issues/28023
860 if 'maxresdefault' in thumbnail_url:
861 thumbnail_url = thumbnail_url.split('?')[0]
862 thumbnails.append({
863 'url': thumbnail_url,
864 'height': int_or_none(thumbnail.get('height')),
865 'width': int_or_none(thumbnail.get('width')),
866 })
867 return thumbnails
868
869 @staticmethod
870 def extract_relative_time(relative_time_text):
871 """
872 Extracts a relative time from string and converts to dt object
873 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
874 """
875 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)
876 if mobj:
877 start = mobj.group('start')
878 if start:
879 return datetime_from_str(start)
880 try:
881 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
882 except ValueError:
883 return None
884
885 def _parse_time_text(self, text):
886 if not text:
887 return
888 dt = self.extract_relative_time(text)
889 timestamp = None
890 if isinstance(dt, datetime.datetime):
891 timestamp = calendar.timegm(dt.timetuple())
892
893 if timestamp is None:
894 timestamp = (
895 unified_timestamp(text) or unified_timestamp(
896 self._search_regex(
897 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
898 text.lower(), 'time text', default=None)))
899
900 if text and timestamp is None and self._preferred_lang in (None, 'en'):
901 self.report_warning(
902 f'Cannot parse localized time text "{text}"', only_once=True)
903 return timestamp
904
905 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
906 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
907 default_client='web'):
908 for retry in self.RetryManager():
909 try:
910 response = self._call_api(
911 ep=ep, fatal=True, headers=headers,
912 video_id=item_id, query=query, note=note,
913 context=self._extract_context(ytcfg, default_client),
914 api_key=self._extract_api_key(ytcfg, default_client),
915 api_hostname=api_hostname, default_client=default_client)
916 except ExtractorError as e:
917 if not isinstance(e.cause, network_exceptions):
918 return self._error_or_warning(e, fatal=fatal)
919 elif not isinstance(e.cause, urllib.error.HTTPError):
920 retry.error = e
921 continue
922
923 first_bytes = e.cause.read(512)
924 if not is_html(first_bytes):
925 yt_error = try_get(
926 self._parse_json(
927 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
928 lambda x: x['error']['message'], str)
929 if yt_error:
930 self._report_alerts([('ERROR', yt_error)], fatal=False)
931 # Downloading page may result in intermittent 5xx HTTP error
932 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
933 # We also want to catch all other network exceptions since errors in later pages can be troublesome
934 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
935 if e.cause.code not in (403, 429):
936 retry.error = e
937 continue
938 return self._error_or_warning(e, fatal=fatal)
939
940 try:
941 self._extract_and_report_alerts(response, only_once=True)
942 except ExtractorError as e:
943 # YouTube servers may return errors we want to retry on in a 200 OK response
944 # See: https://github.com/yt-dlp/yt-dlp/issues/839
945 if 'unknown error' in e.msg.lower():
946 retry.error = e
947 continue
948 return self._error_or_warning(e, fatal=fatal)
949 # Youtube sometimes sends incomplete data
950 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
951 if not traverse_obj(response, *variadic(check_get_keys)):
952 retry.error = ExtractorError('Incomplete data received', expected=True)
953 continue
954
955 return response
956
957 @staticmethod
958 def is_music_url(url):
959 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
960
961 def _extract_video(self, renderer):
962 video_id = renderer.get('videoId')
963
964 reel_header_renderer = traverse_obj(renderer, (
965 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
966 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
967
968 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
969 description = self._get_text(renderer, 'descriptionSnippet')
970
971 duration = int_or_none(renderer.get('lengthSeconds'))
972 if duration is None:
973 duration = parse_duration(self._get_text(
974 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
975 if duration is None:
976 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
977 duration = parse_duration(self._search_regex(
978 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
979 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
980 video_id, default=None, group='duration'))
981
982 channel_id = traverse_obj(
983 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
984 expected_type=str, get_all=False)
985 if not channel_id:
986 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
987
988 overlay_style = traverse_obj(
989 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
990 get_all=False, expected_type=str)
991 badges = self._extract_badges(renderer)
992
993 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
994 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
995 expected_type=str)) or ''
996 url = f'https://www.youtube.com/watch?v={video_id}'
997 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
998 url = f'https://www.youtube.com/shorts/{video_id}'
999
1000 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1001 or self._get_text(reel_header_renderer, 'timestampText') or '')
1002 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1003
1004 live_status = (
1005 'is_upcoming' if scheduled_timestamp is not None
1006 else 'was_live' if 'streamed' in time_text.lower()
1007 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1008 else None)
1009
1010 # videoInfo is a string like '50K views • 10 years ago'.
1011 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1012 view_count = (0 if 'no views' in view_count_text.lower()
1013 else self._get_count({'simpleText': view_count_text}))
1014 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1015
1016 return {
1017 '_type': 'url',
1018 'ie_key': YoutubeIE.ie_key(),
1019 'id': video_id,
1020 'url': url,
1021 'title': title,
1022 'description': description,
1023 'duration': duration,
1024 'channel_id': channel_id,
1025 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
1026 or self._get_text(reel_header_renderer, 'channelTitleText')),
1027 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
1028 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
1029 'timestamp': (self._parse_time_text(time_text)
1030 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1031 else None),
1032 'release_timestamp': scheduled_timestamp,
1033 'availability':
1034 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1035 else self._availability(
1036 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1037 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1038 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
1039 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
1040 view_count_field: view_count,
1041 'live_status': live_status
1042 }
1043
1044
1045 class YoutubeIE(YoutubeBaseInfoExtractor):
1046 IE_DESC = 'YouTube'
1047 _VALID_URL = r"""(?x)^
1048 (
1049 (?:https?://|//) # http(s):// or protocol-independent URL
1050 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1051 (?:www\.)?deturl\.com/www\.youtube\.com|
1052 (?:www\.)?pwnyoutube\.com|
1053 (?:www\.)?hooktube\.com|
1054 (?:www\.)?yourepeat\.com|
1055 tube\.majestyc\.net|
1056 %(invidious)s|
1057 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
1058 (?:.*?\#/)? # handle anchor (#/) redirect urls
1059 (?: # the various things that can precede the ID:
1060 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
1061 |(?: # or the v= param in all its forms
1062 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
1063 (?:\?|\#!?) # the params delimiter ? or # or #!
1064 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
1065 v=
1066 )
1067 ))
1068 |(?:
1069 youtu\.be| # just youtu.be/xxxx
1070 vid\.plus| # or vid.plus/xxxx
1071 zwearz\.com/watch| # or zwearz.com/watch/xxxx
1072 %(invidious)s
1073 )/
1074 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
1075 )
1076 )? # all until now is optional -> you can pass the naked ID
1077 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
1078 (?(1).+)? # if we found the ID, everything can follow
1079 (?:\#|$)""" % {
1080 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
1081 }
1082 _EMBED_REGEX = [
1083 r'''(?x)
1084 (?:
1085 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
1086 data-video-url=|
1087 <embed[^>]+?src=|
1088 embedSWF\(?:\s*|
1089 <object[^>]+data=|
1090 new\s+SWFObject\(
1091 )
1092 (["\'])
1093 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1094 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1095 \1''',
1096 # https://wordpress.org/plugins/lazy-load-for-videos/
1097 r'''(?xs)
1098 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1099 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1100 ]
1101 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
1102
1103 _PLAYER_INFO_RE = (
1104 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1105 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$',
1106 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
1107 )
1108 _formats = {
1109 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1110 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1111 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1112 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1113 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1114 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1115 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1116 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1117 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
1118 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1119 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1120 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1121 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1122 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1123 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1124 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1125 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1126 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1127
1128
1129 # 3D videos
1130 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1131 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1132 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1133 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1134 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1135 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1136 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1137
1138 # Apple HTTP Live Streaming
1139 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1140 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1141 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1142 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1143 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1144 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1145 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1146 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
1147
1148 # DASH mp4 video
1149 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1150 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1151 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1152 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1153 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
1154 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
1155 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1156 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1157 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1158 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1159 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1160 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1161
1162 # Dash mp4 audio
1163 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1164 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1165 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1166 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1167 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1168 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1169 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1170
1171 # Dash webm
1172 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1173 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1174 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1175 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1176 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1177 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1178 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1179 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1180 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1181 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1182 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1183 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1184 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1185 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1186 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1187 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1188 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1189 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1190 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1191 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1192 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1193 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1194
1195 # Dash webm audio
1196 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1197 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1198
1199 # Dash webm audio with opus inside
1200 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1201 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1202 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1203
1204 # RTMP (unnamed)
1205 '_rtmp': {'protocol': 'rtmp'},
1206
1207 # av01 video only formats sometimes served with "unknown" codecs
1208 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1209 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1210 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1211 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1212 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1213 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1214 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1215 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1216 }
1217 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1218
1219 _GEO_BYPASS = False
1220
1221 IE_NAME = 'youtube'
1222 _TESTS = [
1223 {
1224 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1225 'info_dict': {
1226 'id': 'BaW_jenozKc',
1227 'ext': 'mp4',
1228 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1229 'uploader': 'Philipp Hagemeister',
1230 'uploader_id': 'phihag',
1231 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1232 'channel': 'Philipp Hagemeister',
1233 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1234 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1235 'upload_date': '20121002',
1236 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1237 'categories': ['Science & Technology'],
1238 'tags': ['youtube-dl'],
1239 'duration': 10,
1240 'view_count': int,
1241 'like_count': int,
1242 'availability': 'public',
1243 'playable_in_embed': True,
1244 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1245 'live_status': 'not_live',
1246 'age_limit': 0,
1247 'start_time': 1,
1248 'end_time': 9,
1249 'comment_count': int,
1250 'channel_follower_count': int
1251 }
1252 },
1253 {
1254 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1255 'note': 'Embed-only video (#1746)',
1256 'info_dict': {
1257 'id': 'yZIXLfi8CZQ',
1258 'ext': 'mp4',
1259 'upload_date': '20120608',
1260 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1261 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1262 'uploader': 'SET India',
1263 'uploader_id': 'setindia',
1264 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1265 'age_limit': 18,
1266 },
1267 'skip': 'Private video',
1268 },
1269 {
1270 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1271 'note': 'Use the first video ID in the URL',
1272 'info_dict': {
1273 'id': 'BaW_jenozKc',
1274 'ext': 'mp4',
1275 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1276 'uploader': 'Philipp Hagemeister',
1277 'uploader_id': 'phihag',
1278 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1279 'channel': 'Philipp Hagemeister',
1280 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1281 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1282 'upload_date': '20121002',
1283 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1284 'categories': ['Science & Technology'],
1285 'tags': ['youtube-dl'],
1286 'duration': 10,
1287 'view_count': int,
1288 'like_count': int,
1289 'availability': 'public',
1290 'playable_in_embed': True,
1291 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1292 'live_status': 'not_live',
1293 'age_limit': 0,
1294 'comment_count': int,
1295 'channel_follower_count': int
1296 },
1297 'params': {
1298 'skip_download': True,
1299 },
1300 },
1301 {
1302 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1303 'note': '256k DASH audio (format 141) via DASH manifest',
1304 'info_dict': {
1305 'id': 'a9LDPn-MO4I',
1306 'ext': 'm4a',
1307 'upload_date': '20121002',
1308 'uploader_id': '8KVIDEO',
1309 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1310 'description': '',
1311 'uploader': '8KVIDEO',
1312 'title': 'UHDTV TEST 8K VIDEO.mp4'
1313 },
1314 'params': {
1315 'youtube_include_dash_manifest': True,
1316 'format': '141',
1317 },
1318 'skip': 'format 141 not served anymore',
1319 },
1320 # DASH manifest with encrypted signature
1321 {
1322 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1323 'info_dict': {
1324 'id': 'IB3lcPjvWLA',
1325 'ext': 'm4a',
1326 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1327 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1328 'duration': 244,
1329 'uploader': 'AfrojackVEVO',
1330 'uploader_id': 'AfrojackVEVO',
1331 'upload_date': '20131011',
1332 'abr': 129.495,
1333 'like_count': int,
1334 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1335 'playable_in_embed': True,
1336 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1337 'view_count': int,
1338 'track': 'The Spark',
1339 'live_status': 'not_live',
1340 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1341 'channel': 'Afrojack',
1342 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1343 'tags': 'count:19',
1344 'availability': 'public',
1345 'categories': ['Music'],
1346 'age_limit': 0,
1347 'alt_title': 'The Spark',
1348 'channel_follower_count': int
1349 },
1350 'params': {
1351 'youtube_include_dash_manifest': True,
1352 'format': '141/bestaudio[ext=m4a]',
1353 },
1354 },
1355 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1356 {
1357 'note': 'Embed allowed age-gate video',
1358 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1359 'info_dict': {
1360 'id': 'HtVdAasjOgU',
1361 'ext': 'mp4',
1362 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1363 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1364 'duration': 142,
1365 'uploader': 'The Witcher',
1366 'uploader_id': 'WitcherGame',
1367 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1368 'upload_date': '20140605',
1369 'age_limit': 18,
1370 'categories': ['Gaming'],
1371 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1372 'availability': 'needs_auth',
1373 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1374 'like_count': int,
1375 'channel': 'The Witcher',
1376 'live_status': 'not_live',
1377 'tags': 'count:17',
1378 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1379 'playable_in_embed': True,
1380 'view_count': int,
1381 'channel_follower_count': int
1382 },
1383 },
1384 {
1385 'note': 'Age-gate video with embed allowed in public site',
1386 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1387 'info_dict': {
1388 'id': 'HsUATh_Nc2U',
1389 'ext': 'mp4',
1390 'title': 'Godzilla 2 (Official Video)',
1391 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1392 'upload_date': '20200408',
1393 'uploader_id': 'FlyingKitty900',
1394 'uploader': 'FlyingKitty',
1395 'age_limit': 18,
1396 'availability': 'needs_auth',
1397 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1398 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1399 'channel': 'FlyingKitty',
1400 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1401 'view_count': int,
1402 'categories': ['Entertainment'],
1403 'live_status': 'not_live',
1404 'tags': ['Flyingkitty', 'godzilla 2'],
1405 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1406 'like_count': int,
1407 'duration': 177,
1408 'playable_in_embed': True,
1409 'channel_follower_count': int
1410 },
1411 },
1412 {
1413 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1414 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1415 'info_dict': {
1416 'id': 'Tq92D6wQ1mg',
1417 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1418 'ext': 'mp4',
1419 'upload_date': '20191228',
1420 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1421 'uploader': 'Projekt Melody',
1422 'description': 'md5:17eccca93a786d51bc67646756894066',
1423 'age_limit': 18,
1424 'like_count': int,
1425 'availability': 'needs_auth',
1426 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1427 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1428 'view_count': int,
1429 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1430 'channel': 'Projekt Melody',
1431 'live_status': 'not_live',
1432 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1433 'playable_in_embed': True,
1434 'categories': ['Entertainment'],
1435 'duration': 106,
1436 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1437 'comment_count': int,
1438 'channel_follower_count': int
1439 },
1440 },
1441 {
1442 'note': 'Non-Agegated non-embeddable video',
1443 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1444 'info_dict': {
1445 'id': 'MeJVWBSsPAY',
1446 'ext': 'mp4',
1447 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1448 'uploader': 'Herr Lurik',
1449 'uploader_id': 'st3in234',
1450 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1451 'upload_date': '20130730',
1452 'track': 'Such mich find mich',
1453 'age_limit': 0,
1454 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1455 'like_count': int,
1456 'playable_in_embed': False,
1457 'creator': 'OOMPH!',
1458 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1459 'view_count': int,
1460 'alt_title': 'Such mich find mich',
1461 'duration': 210,
1462 'channel': 'Herr Lurik',
1463 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1464 'categories': ['Music'],
1465 'availability': 'public',
1466 'uploader_url': 'http://www.youtube.com/user/st3in234',
1467 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1468 'live_status': 'not_live',
1469 'artist': 'OOMPH!',
1470 'channel_follower_count': int
1471 },
1472 },
1473 {
1474 'note': 'Non-bypassable age-gated video',
1475 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1476 'only_matching': True,
1477 },
1478 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1479 # YouTube Red ad is not captured for creator
1480 {
1481 'url': '__2ABJjxzNo',
1482 'info_dict': {
1483 'id': '__2ABJjxzNo',
1484 'ext': 'mp4',
1485 'duration': 266,
1486 'upload_date': '20100430',
1487 'uploader_id': 'deadmau5',
1488 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1489 'creator': 'deadmau5',
1490 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1491 'uploader': 'deadmau5',
1492 'title': 'Deadmau5 - Some Chords (HD)',
1493 'alt_title': 'Some Chords',
1494 'availability': 'public',
1495 'tags': 'count:14',
1496 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1497 'view_count': int,
1498 'live_status': 'not_live',
1499 'channel': 'deadmau5',
1500 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1501 'like_count': int,
1502 'track': 'Some Chords',
1503 'artist': 'deadmau5',
1504 'playable_in_embed': True,
1505 'age_limit': 0,
1506 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1507 'categories': ['Music'],
1508 'album': 'Some Chords',
1509 'channel_follower_count': int
1510 },
1511 'expected_warnings': [
1512 'DASH manifest missing',
1513 ]
1514 },
1515 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1516 {
1517 'url': 'lqQg6PlCWgI',
1518 'info_dict': {
1519 'id': 'lqQg6PlCWgI',
1520 'ext': 'mp4',
1521 'duration': 6085,
1522 'upload_date': '20150827',
1523 'uploader_id': 'olympic',
1524 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1525 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1526 'uploader': 'Olympics',
1527 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1528 'like_count': int,
1529 'release_timestamp': 1343767800,
1530 'playable_in_embed': True,
1531 'categories': ['Sports'],
1532 'release_date': '20120731',
1533 'channel': 'Olympics',
1534 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1535 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1536 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1537 'age_limit': 0,
1538 'availability': 'public',
1539 'live_status': 'was_live',
1540 'view_count': int,
1541 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1542 'channel_follower_count': int
1543 },
1544 'params': {
1545 'skip_download': 'requires avconv',
1546 }
1547 },
1548 # Non-square pixels
1549 {
1550 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1551 'info_dict': {
1552 'id': '_b-2C3KPAM0',
1553 'ext': 'mp4',
1554 'stretched_ratio': 16 / 9.,
1555 'duration': 85,
1556 'upload_date': '20110310',
1557 'uploader_id': 'AllenMeow',
1558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1559 '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',
1560 'uploader': '孫ᄋᄅ',
1561 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1562 'playable_in_embed': True,
1563 'channel': '孫ᄋᄅ',
1564 'age_limit': 0,
1565 'tags': 'count:11',
1566 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1567 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1568 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1569 'view_count': int,
1570 'categories': ['People & Blogs'],
1571 'like_count': int,
1572 'live_status': 'not_live',
1573 'availability': 'unlisted',
1574 'comment_count': int,
1575 'channel_follower_count': int
1576 },
1577 },
1578 # url_encoded_fmt_stream_map is empty string
1579 {
1580 'url': 'qEJwOuvDf7I',
1581 'info_dict': {
1582 'id': 'qEJwOuvDf7I',
1583 'ext': 'webm',
1584 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1585 'description': '',
1586 'upload_date': '20150404',
1587 'uploader_id': 'spbelect',
1588 'uploader': 'Наблюдатели Петербурга',
1589 },
1590 'params': {
1591 'skip_download': 'requires avconv',
1592 },
1593 'skip': 'This live event has ended.',
1594 },
1595 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1596 {
1597 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1598 'info_dict': {
1599 'id': 'FIl7x6_3R5Y',
1600 'ext': 'webm',
1601 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1602 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1603 'duration': 220,
1604 'upload_date': '20150625',
1605 'uploader_id': 'dorappi2000',
1606 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1607 'uploader': 'dorappi2000',
1608 'formats': 'mincount:31',
1609 },
1610 'skip': 'not actual anymore',
1611 },
1612 # DASH manifest with segment_list
1613 {
1614 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1615 'md5': '8ce563a1d667b599d21064e982ab9e31',
1616 'info_dict': {
1617 'id': 'CsmdDsKjzN8',
1618 'ext': 'mp4',
1619 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1620 'uploader': 'Airtek',
1621 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1622 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1623 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1624 },
1625 'params': {
1626 'youtube_include_dash_manifest': True,
1627 'format': '135', # bestvideo
1628 },
1629 'skip': 'This live event has ended.',
1630 },
1631 {
1632 # Multifeed videos (multiple cameras), URL can be of any Camera
1633 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
1634 'info_dict': {
1635 'id': 'zaPI8MvL8pg',
1636 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1637 'description': 'md5:563ccbc698b39298481ca3c571169519',
1638 },
1639 'playlist': [{
1640 'info_dict': {
1641 'id': 'j5yGuxZ8lLU',
1642 'ext': 'mp4',
1643 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
1644 'uploader': 'WiiLikeToPlay',
1645 'description': 'md5:563ccbc698b39298481ca3c571169519',
1646 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1647 'duration': 10120,
1648 'channel_follower_count': int,
1649 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1650 'availability': 'public',
1651 'playable_in_embed': True,
1652 'upload_date': '20131105',
1653 'uploader_id': 'WiiRikeToPray',
1654 'categories': ['Gaming'],
1655 'live_status': 'was_live',
1656 'tags': 'count:24',
1657 'release_timestamp': 1383701910,
1658 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1659 'comment_count': int,
1660 'age_limit': 0,
1661 'like_count': int,
1662 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1663 'channel': 'WiiLikeToPlay',
1664 'view_count': int,
1665 'release_date': '20131106',
1666 },
1667 }, {
1668 'info_dict': {
1669 'id': 'zaPI8MvL8pg',
1670 'ext': 'mp4',
1671 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
1672 'uploader_id': 'WiiRikeToPray',
1673 'availability': 'public',
1674 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1675 'channel': 'WiiLikeToPlay',
1676 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1677 'channel_follower_count': int,
1678 'description': 'md5:563ccbc698b39298481ca3c571169519',
1679 'duration': 10108,
1680 'age_limit': 0,
1681 'like_count': int,
1682 'tags': 'count:24',
1683 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1684 'uploader': 'WiiLikeToPlay',
1685 'release_timestamp': 1383701915,
1686 'comment_count': int,
1687 'upload_date': '20131105',
1688 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1689 'release_date': '20131106',
1690 'playable_in_embed': True,
1691 'live_status': 'was_live',
1692 'categories': ['Gaming'],
1693 'view_count': int,
1694 },
1695 }, {
1696 'info_dict': {
1697 'id': 'R7r3vfO7Hao',
1698 'ext': 'mp4',
1699 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1700 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1701 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1702 'like_count': int,
1703 'availability': 'public',
1704 'playable_in_embed': True,
1705 'upload_date': '20131105',
1706 'description': 'md5:563ccbc698b39298481ca3c571169519',
1707 'uploader_id': 'WiiRikeToPray',
1708 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1709 'channel_follower_count': int,
1710 'tags': 'count:24',
1711 'release_date': '20131106',
1712 'uploader': 'WiiLikeToPlay',
1713 'comment_count': int,
1714 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1715 'channel': 'WiiLikeToPlay',
1716 'categories': ['Gaming'],
1717 'release_timestamp': 1383701914,
1718 'live_status': 'was_live',
1719 'age_limit': 0,
1720 'duration': 10128,
1721 'view_count': int,
1722 },
1723 }],
1724 'params': {'skip_download': True},
1725 },
1726 {
1727 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1728 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1729 'info_dict': {
1730 'id': 'gVfLd0zydlo',
1731 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1732 },
1733 'playlist_count': 2,
1734 'skip': 'Not multifeed anymore',
1735 },
1736 {
1737 'url': 'https://vid.plus/FlRa-iH7PGw',
1738 'only_matching': True,
1739 },
1740 {
1741 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1742 'only_matching': True,
1743 },
1744 {
1745 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1746 # Also tests cut-off URL expansion in video description (see
1747 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1748 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1749 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1750 'info_dict': {
1751 'id': 'lsguqyKfVQg',
1752 'ext': 'mp4',
1753 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1754 'alt_title': 'Dark Walk',
1755 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1756 'duration': 133,
1757 'upload_date': '20151119',
1758 'uploader_id': 'IronSoulElf',
1759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1760 'uploader': 'IronSoulElf',
1761 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1762 'track': 'Dark Walk',
1763 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1764 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1765 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1766 'categories': ['Film & Animation'],
1767 'view_count': int,
1768 'live_status': 'not_live',
1769 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1770 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1771 'tags': 'count:13',
1772 'availability': 'public',
1773 'channel': 'IronSoulElf',
1774 'playable_in_embed': True,
1775 'like_count': int,
1776 'age_limit': 0,
1777 'channel_follower_count': int
1778 },
1779 'params': {
1780 'skip_download': True,
1781 },
1782 },
1783 {
1784 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1785 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1786 'only_matching': True,
1787 },
1788 {
1789 # Video with yt:stretch=17:0
1790 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1791 'info_dict': {
1792 'id': 'Q39EVAstoRM',
1793 'ext': 'mp4',
1794 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1795 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1796 'upload_date': '20151107',
1797 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1798 'uploader': 'CH GAMER DROID',
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 'skip': 'This video does not exist.',
1804 },
1805 {
1806 # Video with incomplete 'yt:stretch=16:'
1807 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1808 'only_matching': True,
1809 },
1810 {
1811 # Video licensed under Creative Commons
1812 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1813 'info_dict': {
1814 'id': 'M4gD1WSo5mA',
1815 'ext': 'mp4',
1816 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1817 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1818 'duration': 721,
1819 'upload_date': '20150128',
1820 'uploader_id': 'BerkmanCenter',
1821 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1822 'uploader': 'The Berkman Klein Center for Internet & Society',
1823 'license': 'Creative Commons Attribution license (reuse allowed)',
1824 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1825 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1826 'like_count': int,
1827 'age_limit': 0,
1828 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1829 'channel': 'The Berkman Klein Center for Internet & Society',
1830 'availability': 'public',
1831 'view_count': int,
1832 'categories': ['Education'],
1833 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1834 'live_status': 'not_live',
1835 'playable_in_embed': True,
1836 'comment_count': int,
1837 'channel_follower_count': int,
1838 'chapters': list,
1839 },
1840 'params': {
1841 'skip_download': True,
1842 },
1843 },
1844 {
1845 # Channel-like uploader_url
1846 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1847 'info_dict': {
1848 'id': 'eQcmzGIKrzg',
1849 'ext': 'mp4',
1850 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1851 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1852 'duration': 4060,
1853 'upload_date': '20151120',
1854 'uploader': 'Bernie Sanders',
1855 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1857 'license': 'Creative Commons Attribution license (reuse allowed)',
1858 'playable_in_embed': True,
1859 'tags': 'count:12',
1860 'like_count': int,
1861 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1862 'age_limit': 0,
1863 'availability': 'public',
1864 'categories': ['News & Politics'],
1865 'channel': 'Bernie Sanders',
1866 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1867 'view_count': int,
1868 'live_status': 'not_live',
1869 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1870 'comment_count': int,
1871 'channel_follower_count': int,
1872 'chapters': list,
1873 },
1874 'params': {
1875 'skip_download': True,
1876 },
1877 },
1878 {
1879 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1880 'only_matching': True,
1881 },
1882 {
1883 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1884 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1885 'only_matching': True,
1886 },
1887 {
1888 # Rental video preview
1889 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1890 'info_dict': {
1891 'id': 'uGpuVWrhIzE',
1892 'ext': 'mp4',
1893 'title': 'Piku - Trailer',
1894 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1895 'upload_date': '20150811',
1896 'uploader': 'FlixMatrix',
1897 'uploader_id': 'FlixMatrixKaravan',
1898 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1899 'license': 'Standard YouTube License',
1900 },
1901 'params': {
1902 'skip_download': True,
1903 },
1904 'skip': 'This video is not available.',
1905 },
1906 {
1907 # YouTube Red video with episode data
1908 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1909 'info_dict': {
1910 'id': 'iqKdEhx-dD4',
1911 'ext': 'mp4',
1912 'title': 'Isolation - Mind Field (Ep 1)',
1913 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1914 'duration': 2085,
1915 'upload_date': '20170118',
1916 'uploader': 'Vsauce',
1917 'uploader_id': 'Vsauce',
1918 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1919 'series': 'Mind Field',
1920 'season_number': 1,
1921 'episode_number': 1,
1922 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1923 'tags': 'count:12',
1924 'view_count': int,
1925 'availability': 'public',
1926 'age_limit': 0,
1927 'channel': 'Vsauce',
1928 'episode': 'Episode 1',
1929 'categories': ['Entertainment'],
1930 'season': 'Season 1',
1931 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1932 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1933 'like_count': int,
1934 'playable_in_embed': True,
1935 'live_status': 'not_live',
1936 'channel_follower_count': int
1937 },
1938 'params': {
1939 'skip_download': True,
1940 },
1941 'expected_warnings': [
1942 'Skipping DASH manifest',
1943 ],
1944 },
1945 {
1946 # The following content has been identified by the YouTube community
1947 # as inappropriate or offensive to some audiences.
1948 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1949 'info_dict': {
1950 'id': '6SJNVb0GnPI',
1951 'ext': 'mp4',
1952 'title': 'Race Differences in Intelligence',
1953 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1954 'duration': 965,
1955 'upload_date': '20140124',
1956 'uploader': 'New Century Foundation',
1957 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1958 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1959 },
1960 'params': {
1961 'skip_download': True,
1962 },
1963 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1964 },
1965 {
1966 # itag 212
1967 'url': '1t24XAntNCY',
1968 'only_matching': True,
1969 },
1970 {
1971 # geo restricted to JP
1972 'url': 'sJL6WA-aGkQ',
1973 'only_matching': True,
1974 },
1975 {
1976 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1977 'only_matching': True,
1978 },
1979 {
1980 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1981 'only_matching': True,
1982 },
1983 {
1984 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1985 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1986 'only_matching': True,
1987 },
1988 {
1989 # DRM protected
1990 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1991 'only_matching': True,
1992 },
1993 {
1994 # Video with unsupported adaptive stream type formats
1995 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1996 'info_dict': {
1997 'id': 'Z4Vy8R84T1U',
1998 'ext': 'mp4',
1999 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2000 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2001 'duration': 433,
2002 'upload_date': '20130923',
2003 'uploader': 'Amelia Putri Harwita',
2004 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
2005 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
2006 'formats': 'maxcount:10',
2007 },
2008 'params': {
2009 'skip_download': True,
2010 'youtube_include_dash_manifest': False,
2011 },
2012 'skip': 'not actual anymore',
2013 },
2014 {
2015 # Youtube Music Auto-generated description
2016 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2017 'info_dict': {
2018 'id': 'MgNrAu2pzNs',
2019 'ext': 'mp4',
2020 'title': 'Voyeur Girl',
2021 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2022 'upload_date': '20190312',
2023 'uploader': 'Stephen - Topic',
2024 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2025 'artist': 'Stephen',
2026 'track': 'Voyeur Girl',
2027 'album': 'it\'s too much love to know my dear',
2028 'release_date': '20190313',
2029 'release_year': 2019,
2030 'alt_title': 'Voyeur Girl',
2031 'view_count': int,
2032 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2033 'playable_in_embed': True,
2034 'like_count': int,
2035 'categories': ['Music'],
2036 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2037 'channel': 'Stephen',
2038 'availability': 'public',
2039 'creator': 'Stephen',
2040 'duration': 169,
2041 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2042 'age_limit': 0,
2043 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2044 'tags': 'count:11',
2045 'live_status': 'not_live',
2046 'channel_follower_count': int
2047 },
2048 'params': {
2049 'skip_download': True,
2050 },
2051 },
2052 {
2053 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2054 'only_matching': True,
2055 },
2056 {
2057 # invalid -> valid video id redirection
2058 'url': 'DJztXj2GPfl',
2059 'info_dict': {
2060 'id': 'DJztXj2GPfk',
2061 'ext': 'mp4',
2062 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2063 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2064 'upload_date': '20090125',
2065 'uploader': 'Prochorowka',
2066 'uploader_id': 'Prochorowka',
2067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
2068 'artist': 'Panjabi MC',
2069 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2070 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2071 },
2072 'params': {
2073 'skip_download': True,
2074 },
2075 'skip': 'Video unavailable',
2076 },
2077 {
2078 # empty description results in an empty string
2079 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2080 'info_dict': {
2081 'id': 'x41yOUIvK2k',
2082 'ext': 'mp4',
2083 'title': 'IMG 3456',
2084 'description': '',
2085 'upload_date': '20170613',
2086 'uploader_id': 'ElevageOrVert',
2087 'uploader': 'ElevageOrVert',
2088 'view_count': int,
2089 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2090 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2091 'like_count': int,
2092 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2093 'tags': [],
2094 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2095 'availability': 'public',
2096 'age_limit': 0,
2097 'categories': ['Pets & Animals'],
2098 'duration': 7,
2099 'playable_in_embed': True,
2100 'live_status': 'not_live',
2101 'channel': 'ElevageOrVert',
2102 'channel_follower_count': int
2103 },
2104 'params': {
2105 'skip_download': True,
2106 },
2107 },
2108 {
2109 # with '};' inside yt initial data (see [1])
2110 # see [2] for an example with '};' inside ytInitialPlayerResponse
2111 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2112 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
2113 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2114 'info_dict': {
2115 'id': 'CHqg6qOn4no',
2116 'ext': 'mp4',
2117 'title': 'Part 77 Sort a list of simple types in c#',
2118 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2119 'upload_date': '20130831',
2120 'uploader_id': 'kudvenkat',
2121 'uploader': 'kudvenkat',
2122 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2123 'like_count': int,
2124 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2125 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2126 'live_status': 'not_live',
2127 'categories': ['Education'],
2128 'availability': 'public',
2129 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2130 'tags': 'count:12',
2131 'playable_in_embed': True,
2132 'age_limit': 0,
2133 'view_count': int,
2134 'duration': 522,
2135 'channel': 'kudvenkat',
2136 'comment_count': int,
2137 'channel_follower_count': int,
2138 'chapters': list,
2139 },
2140 'params': {
2141 'skip_download': True,
2142 },
2143 },
2144 {
2145 # another example of '};' in ytInitialData
2146 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2147 'only_matching': True,
2148 },
2149 {
2150 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2151 'only_matching': True,
2152 },
2153 {
2154 # https://github.com/ytdl-org/youtube-dl/pull/28094
2155 'url': 'OtqTfy26tG0',
2156 'info_dict': {
2157 'id': 'OtqTfy26tG0',
2158 'ext': 'mp4',
2159 'title': 'Burn Out',
2160 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2161 'upload_date': '20141120',
2162 'uploader': 'The Cinematic Orchestra - Topic',
2163 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2164 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2165 'artist': 'The Cinematic Orchestra',
2166 'track': 'Burn Out',
2167 'album': 'Every Day',
2168 'like_count': int,
2169 'live_status': 'not_live',
2170 'alt_title': 'Burn Out',
2171 'duration': 614,
2172 'age_limit': 0,
2173 'view_count': int,
2174 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2175 'creator': 'The Cinematic Orchestra',
2176 'channel': 'The Cinematic Orchestra',
2177 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2178 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2179 'availability': 'public',
2180 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2181 'categories': ['Music'],
2182 'playable_in_embed': True,
2183 'channel_follower_count': int
2184 },
2185 'params': {
2186 'skip_download': True,
2187 },
2188 },
2189 {
2190 # controversial video, only works with bpctr when authenticated with cookies
2191 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2192 'only_matching': True,
2193 },
2194 {
2195 # controversial video, requires bpctr/contentCheckOk
2196 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2197 'info_dict': {
2198 'id': 'SZJvDhaSDnc',
2199 'ext': 'mp4',
2200 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2201 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2202 'uploader': 'CBS Mornings',
2203 'uploader_id': 'CBSThisMorning',
2204 'upload_date': '20140716',
2205 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2206 'duration': 170,
2207 'categories': ['News & Politics'],
2208 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2209 'view_count': int,
2210 'channel': 'CBS Mornings',
2211 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2212 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2213 'age_limit': 18,
2214 'availability': 'needs_auth',
2215 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2216 'like_count': int,
2217 'live_status': 'not_live',
2218 'playable_in_embed': True,
2219 'channel_follower_count': int
2220 }
2221 },
2222 {
2223 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2224 'url': 'cBvYw8_A0vQ',
2225 'info_dict': {
2226 'id': 'cBvYw8_A0vQ',
2227 'ext': 'mp4',
2228 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2229 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2230 'upload_date': '20201120',
2231 'uploader': 'Walk around Japan',
2232 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2233 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2234 'duration': 1456,
2235 'categories': ['Travel & Events'],
2236 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2237 'view_count': int,
2238 'channel': 'Walk around Japan',
2239 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2240 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2241 'age_limit': 0,
2242 'availability': 'public',
2243 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2244 'live_status': 'not_live',
2245 'playable_in_embed': True,
2246 'channel_follower_count': int
2247 },
2248 'params': {
2249 'skip_download': True,
2250 },
2251 }, {
2252 # Has multiple audio streams
2253 'url': 'WaOKSUlf4TM',
2254 'only_matching': True
2255 }, {
2256 # Requires Premium: has format 141 when requested using YTM url
2257 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2258 'only_matching': True
2259 }, {
2260 # multiple subtitles with same lang_code
2261 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2262 'only_matching': True,
2263 }, {
2264 # Force use android client fallback
2265 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2266 'info_dict': {
2267 'id': 'YOelRv7fMxY',
2268 'title': 'DIGGING A SECRET TUNNEL Part 1',
2269 'ext': '3gp',
2270 'upload_date': '20210624',
2271 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2272 'uploader': 'colinfurze',
2273 'uploader_id': 'colinfurze',
2274 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2275 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2276 'duration': 596,
2277 'categories': ['Entertainment'],
2278 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2279 'view_count': int,
2280 'channel': 'colinfurze',
2281 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2282 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2283 'age_limit': 0,
2284 'availability': 'public',
2285 'like_count': int,
2286 'live_status': 'not_live',
2287 'playable_in_embed': True,
2288 'channel_follower_count': int,
2289 'chapters': list,
2290 },
2291 'params': {
2292 'format': '17', # 3gp format available on android
2293 'extractor_args': {'youtube': {'player_client': ['android']}},
2294 },
2295 },
2296 {
2297 # Skip download of additional client configs (remix client config in this case)
2298 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2299 'only_matching': True,
2300 'params': {
2301 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2302 },
2303 }, {
2304 # shorts
2305 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2306 'only_matching': True,
2307 }, {
2308 'note': 'Storyboards',
2309 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2310 'info_dict': {
2311 'id': '5KLPxDtMqe8',
2312 'ext': 'mhtml',
2313 'format_id': 'sb0',
2314 'title': 'Your Brain is Plastic',
2315 'uploader_id': 'scishow',
2316 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2317 'upload_date': '20140324',
2318 'uploader': 'SciShow',
2319 'like_count': int,
2320 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2321 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2322 'view_count': int,
2323 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2324 'playable_in_embed': True,
2325 'tags': 'count:12',
2326 'uploader_url': 'http://www.youtube.com/user/scishow',
2327 'availability': 'public',
2328 'channel': 'SciShow',
2329 'live_status': 'not_live',
2330 'duration': 248,
2331 'categories': ['Education'],
2332 'age_limit': 0,
2333 'channel_follower_count': int,
2334 'chapters': list,
2335 }, 'params': {'format': 'mhtml', 'skip_download': True}
2336 }, {
2337 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2338 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2339 'info_dict': {
2340 'id': '2NUZ8W2llS4',
2341 'ext': 'mp4',
2342 'title': 'The NP that test your phone performance 🙂',
2343 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2344 'uploader': 'Leon Nguyen',
2345 'uploader_id': 'VNSXIII',
2346 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2347 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2348 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2349 'duration': 21,
2350 'view_count': int,
2351 'age_limit': 0,
2352 'categories': ['Gaming'],
2353 'tags': 'count:23',
2354 'playable_in_embed': True,
2355 'live_status': 'not_live',
2356 'upload_date': '20220103',
2357 'like_count': int,
2358 'availability': 'public',
2359 'channel': 'Leon Nguyen',
2360 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2361 'comment_count': int,
2362 'channel_follower_count': int
2363 }
2364 }, {
2365 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2366 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2367 'info_dict': {
2368 'id': '2NUZ8W2llS4',
2369 'ext': 'mp4',
2370 'title': 'The NP that test your phone performance 🙂',
2371 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2372 'uploader': 'Leon Nguyen',
2373 'uploader_id': 'VNSXIII',
2374 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2375 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2376 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2377 'duration': 21,
2378 'view_count': int,
2379 'age_limit': 0,
2380 'categories': ['Gaming'],
2381 'tags': 'count:23',
2382 'playable_in_embed': True,
2383 'live_status': 'not_live',
2384 'upload_date': '20220102',
2385 'like_count': int,
2386 'availability': 'public',
2387 'channel': 'Leon Nguyen',
2388 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2389 'comment_count': int,
2390 'channel_follower_count': int
2391 },
2392 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2393 }, {
2394 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2395 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2396 'info_dict': {
2397 'id': 'mzZzzBU6lrM',
2398 'ext': 'mp4',
2399 'title': 'I Met GeorgeNotFound In Real Life...',
2400 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2401 'uploader': 'Quackity',
2402 'uploader_id': 'QuackityHQ',
2403 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2404 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2405 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2406 'duration': 955,
2407 'view_count': int,
2408 'age_limit': 0,
2409 'categories': ['Entertainment'],
2410 'tags': 'count:26',
2411 'playable_in_embed': True,
2412 'live_status': 'not_live',
2413 'release_timestamp': 1641172509,
2414 'release_date': '20220103',
2415 'upload_date': '20220103',
2416 'like_count': int,
2417 'availability': 'public',
2418 'channel': 'Quackity',
2419 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2420 'channel_follower_count': int
2421 }
2422 },
2423 { # continuous livestream. Microformat upload date should be preferred.
2424 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2425 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2426 'info_dict': {
2427 'id': 'kgx4WGK0oNU',
2428 '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}',
2429 'ext': 'mp4',
2430 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2431 'availability': 'public',
2432 'age_limit': 0,
2433 'release_timestamp': 1637975704,
2434 'upload_date': '20210619',
2435 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2436 'live_status': 'is_live',
2437 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2438 'uploader': '阿鲍Abao',
2439 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2440 'channel': 'Abao in Tokyo',
2441 'channel_follower_count': int,
2442 'release_date': '20211127',
2443 'tags': 'count:39',
2444 'categories': ['People & Blogs'],
2445 'like_count': int,
2446 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2447 'view_count': int,
2448 'playable_in_embed': True,
2449 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2450 'concurrent_view_count': int,
2451 },
2452 'params': {'skip_download': True}
2453 }, {
2454 # Story. Requires specific player params to work.
2455 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2456 'info_dict': {
2457 'id': 'vv8qTUWmulI',
2458 'ext': 'mp4',
2459 'availability': 'unlisted',
2460 'view_count': int,
2461 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2462 'upload_date': '20220526',
2463 'categories': ['Education'],
2464 'title': 'Story',
2465 'channel': 'IT\'S HISTORY',
2466 'description': '',
2467 'uploader_id': 'BlastfromthePast',
2468 'duration': 12,
2469 'uploader': 'IT\'S HISTORY',
2470 'playable_in_embed': True,
2471 'age_limit': 0,
2472 'live_status': 'not_live',
2473 'tags': [],
2474 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2475 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2476 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2477 },
2478 'skip': 'stories get removed after some period of time',
2479 }, {
2480 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2481 'info_dict': {
2482 'id': 'tjjjtzRLHvA',
2483 'ext': 'mp4',
2484 'title': 'ハッシュタグ無し };if window.ytcsi',
2485 'upload_date': '20220323',
2486 'like_count': int,
2487 'availability': 'unlisted',
2488 'channel': 'nao20010128nao',
2489 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2490 'age_limit': 0,
2491 'uploader': 'nao20010128nao',
2492 'uploader_id': 'nao20010128nao',
2493 'categories': ['Music'],
2494 'view_count': int,
2495 'description': '',
2496 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2497 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2498 'live_status': 'not_live',
2499 'playable_in_embed': True,
2500 'channel_follower_count': int,
2501 'duration': 6,
2502 'tags': [],
2503 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2504 }
2505 }, {
2506 # Prefer primary title+description language metadata by default
2507 # Do not prefer translated description if primary is empty
2508 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2509 'info_dict': {
2510 'id': 'el3E4MbxRqQ',
2511 'ext': 'mp4',
2512 'title': 'dlp test video 2 - primary sv no desc',
2513 'description': '',
2514 'channel': 'cole-dlp-test-acc',
2515 'tags': [],
2516 'view_count': int,
2517 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2518 'like_count': int,
2519 'playable_in_embed': True,
2520 'availability': 'unlisted',
2521 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2522 'age_limit': 0,
2523 'duration': 5,
2524 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2525 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2526 'live_status': 'not_live',
2527 'upload_date': '20220908',
2528 'categories': ['People & Blogs'],
2529 'uploader': 'cole-dlp-test-acc',
2530 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2531 },
2532 'params': {'skip_download': True}
2533 }, {
2534 # Extractor argument: prefer translated title+description
2535 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2536 'info_dict': {
2537 'id': 'gHKT4uU8Zng',
2538 'ext': 'mp4',
2539 'channel': 'cole-dlp-test-acc',
2540 'tags': [],
2541 'duration': 5,
2542 'live_status': 'not_live',
2543 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2544 'upload_date': '20220728',
2545 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2546 'view_count': int,
2547 'categories': ['People & Blogs'],
2548 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2549 'title': 'dlp test video title translated (fr)',
2550 'availability': 'public',
2551 'uploader': 'cole-dlp-test-acc',
2552 'age_limit': 0,
2553 'description': 'dlp test video description translated (fr)',
2554 'playable_in_embed': True,
2555 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2556 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2557 },
2558 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2559 'expected_warnings': [r'Preferring "fr" translated fields'],
2560 }, {
2561 'note': '6 channel audio',
2562 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2563 'only_matching': True,
2564 }, {
2565 'note': 'Multiple HLS formats with same itag',
2566 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2567 'info_dict': {
2568 'id': 'kX3nB4PpJko',
2569 'ext': 'mp4',
2570 'categories': ['Entertainment'],
2571 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
2572 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
2573 'live_status': 'not_live',
2574 'duration': 937,
2575 'channel_follower_count': int,
2576 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2577 'title': 'Last To Take Hand Off Jet, Keeps It!',
2578 'channel': 'MrBeast',
2579 'playable_in_embed': True,
2580 'view_count': int,
2581 'upload_date': '20221112',
2582 'uploader': 'MrBeast',
2583 'uploader_id': 'MrBeast6000',
2584 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2585 'age_limit': 0,
2586 'availability': 'public',
2587 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2588 'like_count': int,
2589 'tags': [],
2590 },
2591 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
2592 }, {
2593 'note': 'Audio formats with Dynamic Range Compression',
2594 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2595 'info_dict': {
2596 'id': 'Tq92D6wQ1mg',
2597 'ext': 'weba',
2598 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2599 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2600 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2601 'channel_follower_count': int,
2602 'description': 'md5:17eccca93a786d51bc67646756894066',
2603 'upload_date': '20191228',
2604 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2605 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2606 'playable_in_embed': True,
2607 'like_count': int,
2608 'categories': ['Entertainment'],
2609 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2610 'age_limit': 18,
2611 'channel': 'Projekt Melody',
2612 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2613 'view_count': int,
2614 'availability': 'needs_auth',
2615 'comment_count': int,
2616 'live_status': 'not_live',
2617 'uploader': 'Projekt Melody',
2618 'duration': 106,
2619 },
2620 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
2621 },
2622 {
2623 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2624 'info_dict': {
2625 'id': 'qVv6vCqciTM',
2626 'ext': 'mp4',
2627 'age_limit': 0,
2628 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2629 'comment_count': int,
2630 'chapters': 'count:13',
2631 'upload_date': '20221223',
2632 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2633 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2634 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2635 'like_count': int,
2636 'release_date': '20221223',
2637 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2638 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
2639 'view_count': int,
2640 'playable_in_embed': True,
2641 'duration': 4438,
2642 'availability': 'public',
2643 'channel_follower_count': int,
2644 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2645 'categories': ['Entertainment'],
2646 'live_status': 'was_live',
2647 'release_timestamp': 1671793345,
2648 'channel': 'さなちゃんねる',
2649 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2650 'uploader': 'さなちゃんねる',
2651 },
2652 },
2653 ]
2654
2655 _WEBPAGE_TESTS = [
2656 # YouTube <object> embed
2657 {
2658 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2659 'md5': '873c81d308b979f0e23ee7e620b312a3',
2660 'info_dict': {
2661 'id': 'msN87y-iEx0',
2662 'ext': 'mp4',
2663 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2664 'upload_date': '20080526',
2665 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2666 'uploader': 'Christopher Sykes',
2667 'uploader_id': 'ChristopherJSykes',
2668 'age_limit': 0,
2669 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2670 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2671 'playable_in_embed': True,
2672 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2673 'like_count': int,
2674 'comment_count': int,
2675 'channel': 'Christopher Sykes',
2676 'live_status': 'not_live',
2677 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2678 'availability': 'public',
2679 'duration': 195,
2680 'view_count': int,
2681 'categories': ['Science & Technology'],
2682 'channel_follower_count': int,
2683 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2684 },
2685 'params': {
2686 'skip_download': True,
2687 }
2688 },
2689 ]
2690
2691 @classmethod
2692 def suitable(cls, url):
2693 from ..utils import parse_qs
2694
2695 qs = parse_qs(url)
2696 if qs.get('list', [None])[0]:
2697 return False
2698 return super().suitable(url)
2699
2700 def __init__(self, *args, **kwargs):
2701 super().__init__(*args, **kwargs)
2702 self._code_cache = {}
2703 self._player_cache = {}
2704
2705 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
2706 lock = threading.Lock()
2707 start_time = time.time()
2708 formats = [f for f in formats if f.get('is_from_start')]
2709
2710 def refetch_manifest(format_id, delay):
2711 nonlocal formats, start_time, is_live
2712 if time.time() <= start_time + delay:
2713 return
2714
2715 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2716 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
2717 microformats = traverse_obj(
2718 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2719 expected_type=dict)
2720 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2721 is_live = live_status == 'is_live'
2722 start_time = time.time()
2723
2724 def mpd_feed(format_id, delay):
2725 """
2726 @returns (manifest_url, manifest_stream_number, is_live) or None
2727 """
2728 for retry in self.RetryManager(fatal=False):
2729 with lock:
2730 refetch_manifest(format_id, delay)
2731
2732 f = next((f for f in formats if f['format_id'] == format_id), None)
2733 if not f:
2734 if not is_live:
2735 retry.error = f'{video_id}: Video is no longer live'
2736 else:
2737 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2738 continue
2739 return f['manifest_url'], f['manifest_stream_number'], is_live
2740 return None
2741
2742 for f in formats:
2743 f['is_live'] = is_live
2744 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2745 live_start_time, mpd_feed, not is_live and f.copy())
2746 if is_live:
2747 f['fragments'] = gen
2748 f['protocol'] = 'http_dash_segments_generator'
2749 else:
2750 f['fragments'] = LazyList(gen({}))
2751 del f['is_from_start']
2752
2753 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
2754 FETCH_SPAN, MAX_DURATION = 5, 432000
2755
2756 mpd_url, stream_number, is_live = None, None, True
2757
2758 begin_index = 0
2759 download_start_time = ctx.get('start') or time.time()
2760
2761 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2762 if lack_early_segments:
2763 self.report_warning(bug_reports_message(
2764 'Starting download from the last 120 hours of the live stream since '
2765 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2766 lack_early_segments = True
2767
2768 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2769 fragments, fragment_base_url = None, None
2770
2771 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2772 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2773 # Obtain from MPD's maximum seq value
2774 old_mpd_url = mpd_url
2775 last_error = ctx.pop('last_error', None)
2776 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2777 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2778 or (mpd_url, stream_number, False))
2779 if not refresh_sequence:
2780 if expire_fast and not is_live:
2781 return False, last_seq
2782 elif old_mpd_url == mpd_url:
2783 return True, last_seq
2784 if manifestless_orig_fmt:
2785 fmt_info = manifestless_orig_fmt
2786 else:
2787 try:
2788 fmts, _ = self._extract_mpd_formats_and_subtitles(
2789 mpd_url, None, note=False, errnote=False, fatal=False)
2790 except ExtractorError:
2791 fmts = None
2792 if not fmts:
2793 no_fragment_score += 2
2794 return False, last_seq
2795 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2796 fragments = fmt_info['fragments']
2797 fragment_base_url = fmt_info['fragment_base_url']
2798 assert fragment_base_url
2799
2800 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2801 return True, _last_seq
2802
2803 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
2804 while is_live:
2805 fetch_time = time.time()
2806 if no_fragment_score > 30:
2807 return
2808 if last_segment_url:
2809 # Obtain from "X-Head-Seqnum" header value from each segment
2810 try:
2811 urlh = self._request_webpage(
2812 last_segment_url, None, note=False, errnote=False, fatal=False)
2813 except ExtractorError:
2814 urlh = None
2815 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2816 if last_seq is None:
2817 no_fragment_score += 2
2818 last_segment_url = None
2819 continue
2820 else:
2821 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2822 no_fragment_score += 2
2823 if not should_continue:
2824 continue
2825
2826 if known_idx > last_seq:
2827 last_segment_url = None
2828 continue
2829
2830 last_seq += 1
2831
2832 if begin_index < 0 and known_idx < 0:
2833 # skip from the start when it's negative value
2834 known_idx = last_seq + begin_index
2835 if lack_early_segments:
2836 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2837 try:
2838 for idx in range(known_idx, last_seq):
2839 # do not update sequence here or you'll get skipped some part of it
2840 should_continue, _ = _extract_sequence_from_mpd(False, False)
2841 if not should_continue:
2842 known_idx = idx - 1
2843 raise ExtractorError('breaking out of outer loop')
2844 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2845 yield {
2846 'url': last_segment_url,
2847 'fragment_count': last_seq,
2848 }
2849 if known_idx == last_seq:
2850 no_fragment_score += 5
2851 else:
2852 no_fragment_score = 0
2853 known_idx = last_seq
2854 except ExtractorError:
2855 continue
2856
2857 if manifestless_orig_fmt:
2858 # Stop at the first iteration if running for post-live manifestless;
2859 # fragment count no longer increase since it starts
2860 break
2861
2862 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2863
2864 def _extract_player_url(self, *ytcfgs, webpage=None):
2865 player_url = traverse_obj(
2866 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2867 get_all=False, expected_type=str)
2868 if not player_url:
2869 return
2870 return urljoin('https://www.youtube.com', player_url)
2871
2872 def _download_player_url(self, video_id, fatal=False):
2873 res = self._download_webpage(
2874 'https://www.youtube.com/iframe_api',
2875 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2876 if res:
2877 player_version = self._search_regex(
2878 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2879 if player_version:
2880 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2881
2882 def _signature_cache_id(self, example_sig):
2883 """ Return a string representation of a signature """
2884 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2885
2886 @classmethod
2887 def _extract_player_info(cls, player_url):
2888 for player_re in cls._PLAYER_INFO_RE:
2889 id_m = re.search(player_re, player_url)
2890 if id_m:
2891 break
2892 else:
2893 raise ExtractorError('Cannot identify player %r' % player_url)
2894 return id_m.group('id')
2895
2896 def _load_player(self, video_id, player_url, fatal=True):
2897 player_id = self._extract_player_info(player_url)
2898 if player_id not in self._code_cache:
2899 code = self._download_webpage(
2900 player_url, video_id, fatal=fatal,
2901 note='Downloading player ' + player_id,
2902 errnote='Download of %s failed' % player_url)
2903 if code:
2904 self._code_cache[player_id] = code
2905 return self._code_cache.get(player_id)
2906
2907 def _extract_signature_function(self, video_id, player_url, example_sig):
2908 player_id = self._extract_player_info(player_url)
2909
2910 # Read from filesystem cache
2911 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2912 assert os.path.basename(func_id) == func_id
2913
2914 self.write_debug(f'Extracting signature function {func_id}')
2915 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2916
2917 if not cache_spec:
2918 code = self._load_player(video_id, player_url)
2919 if code:
2920 res = self._parse_sig_js(code)
2921 test_string = ''.join(map(chr, range(len(example_sig))))
2922 cache_spec = [ord(c) for c in res(test_string)]
2923 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2924
2925 return lambda s: ''.join(s[i] for i in cache_spec)
2926
2927 def _print_sig_code(self, func, example_sig):
2928 if not self.get_param('youtube_print_sig_code'):
2929 return
2930
2931 def gen_sig_code(idxs):
2932 def _genslice(start, end, step):
2933 starts = '' if start == 0 else str(start)
2934 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2935 steps = '' if step == 1 else (':%d' % step)
2936 return f's[{starts}{ends}{steps}]'
2937
2938 step = None
2939 # Quelch pyflakes warnings - start will be set when step is set
2940 start = '(Never used)'
2941 for i, prev in zip(idxs[1:], idxs[:-1]):
2942 if step is not None:
2943 if i - prev == step:
2944 continue
2945 yield _genslice(start, prev, step)
2946 step = None
2947 continue
2948 if i - prev in [-1, 1]:
2949 step = i - prev
2950 start = prev
2951 continue
2952 else:
2953 yield 's[%d]' % prev
2954 if step is None:
2955 yield 's[%d]' % i
2956 else:
2957 yield _genslice(start, i, step)
2958
2959 test_string = ''.join(map(chr, range(len(example_sig))))
2960 cache_res = func(test_string)
2961 cache_spec = [ord(c) for c in cache_res]
2962 expr_code = ' + '.join(gen_sig_code(cache_spec))
2963 signature_id_tuple = '(%s)' % (
2964 ', '.join(str(len(p)) for p in example_sig.split('.')))
2965 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2966 ' return %s\n') % (signature_id_tuple, expr_code)
2967 self.to_screen('Extracted signature function:\n' + code)
2968
2969 def _parse_sig_js(self, jscode):
2970 funcname = self._search_regex(
2971 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2972 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2973 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2974 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2975 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}\(a,\d+\)',
2976 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\(\s*""\s*\)',
2977 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2978 # Obsolete patterns
2979 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2980 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2981 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2982 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2983 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2984 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2985 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2986 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2987 jscode, 'Initial JS player signature function name', group='sig')
2988
2989 jsi = JSInterpreter(jscode)
2990 initial_function = jsi.extract_function(funcname)
2991 return lambda s: initial_function([s])
2992
2993 def _cached(self, func, *cache_id):
2994 def inner(*args, **kwargs):
2995 if cache_id not in self._player_cache:
2996 try:
2997 self._player_cache[cache_id] = func(*args, **kwargs)
2998 except ExtractorError as e:
2999 self._player_cache[cache_id] = e
3000 except Exception as e:
3001 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3002
3003 ret = self._player_cache[cache_id]
3004 if isinstance(ret, Exception):
3005 raise ret
3006 return ret
3007 return inner
3008
3009 def _decrypt_signature(self, s, video_id, player_url):
3010 """Turn the encrypted s field into a working signature"""
3011 extract_sig = self._cached(
3012 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3013 func = extract_sig(video_id, player_url, s)
3014 self._print_sig_code(func, s)
3015 return func(s)
3016
3017 def _decrypt_nsig(self, s, video_id, player_url):
3018 """Turn the encrypted n field into a working signature"""
3019 if player_url is None:
3020 raise ExtractorError('Cannot decrypt nsig without player_url')
3021 player_url = urljoin('https://www.youtube.com', player_url)
3022
3023 try:
3024 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3025 except ExtractorError as e:
3026 raise ExtractorError('Unable to extract nsig function code', cause=e)
3027 if self.get_param('youtube_print_sig_code'):
3028 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
3029
3030 try:
3031 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3032 ret = extract_nsig(jsi, func_code)(s)
3033 except JSInterpreter.Exception as e:
3034 try:
3035 jsi = PhantomJSwrapper(self, timeout=5000)
3036 except ExtractorError:
3037 raise e
3038 self.report_warning(
3039 f'Native nsig extraction failed: Trying with PhantomJS\n'
3040 f' n = {s} ; player = {player_url}', video_id)
3041 self.write_debug(e, only_once=True)
3042
3043 args, func_body = func_code
3044 ret = jsi.execute(
3045 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3046 video_id=video_id, note='Executing signature code').strip()
3047
3048 self.write_debug(f'Decrypted nsig {s} => {ret}')
3049 return ret
3050
3051 def _extract_n_function_name(self, jscode):
3052 funcname, idx = self._search_regex(
3053 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3054 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3055 if not idx:
3056 return funcname
3057
3058 return json.loads(js_to_json(self._search_regex(
3059 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3060 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3061
3062 def _extract_n_function_code(self, video_id, player_url):
3063 player_id = self._extract_player_info(player_url)
3064 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
3065 jscode = func_code or self._load_player(video_id, player_url)
3066 jsi = JSInterpreter(jscode)
3067
3068 if func_code:
3069 return jsi, player_id, func_code
3070
3071 func_name = self._extract_n_function_name(jscode)
3072
3073 # For redundancy
3074 func_code = self._search_regex(
3075 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3076 # NB: The end of the regex is intentionally kept strict
3077 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3078 jscode, 'nsig function', group=('var', 'code'), default=None)
3079 if func_code:
3080 func_code = ([func_code[0]], func_code[1])
3081 else:
3082 self.write_debug('Extracting nsig function with jsinterp')
3083 func_code = jsi.extract_function_code(func_name)
3084
3085 self.cache.store('youtube-nsig', player_id, func_code)
3086 return jsi, player_id, func_code
3087
3088 def _extract_n_function_from_code(self, jsi, func_code):
3089 func = jsi.extract_function_from_code(*func_code)
3090
3091 def extract_nsig(s):
3092 try:
3093 ret = func([s])
3094 except JSInterpreter.Exception:
3095 raise
3096 except Exception as e:
3097 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3098
3099 if ret.startswith('enhanced_except_'):
3100 raise JSInterpreter.Exception('Signature function returned an exception')
3101 return ret
3102
3103 return extract_nsig
3104
3105 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3106 """
3107 Extract signatureTimestamp (sts)
3108 Required to tell API what sig/player version is in use.
3109 """
3110 sts = None
3111 if isinstance(ytcfg, dict):
3112 sts = int_or_none(ytcfg.get('STS'))
3113
3114 if not sts:
3115 # Attempt to extract from player
3116 if player_url is None:
3117 error_msg = 'Cannot extract signature timestamp without player_url.'
3118 if fatal:
3119 raise ExtractorError(error_msg)
3120 self.report_warning(error_msg)
3121 return
3122 code = self._load_player(video_id, player_url, fatal=fatal)
3123 if code:
3124 sts = int_or_none(self._search_regex(
3125 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3126 'JS player signature timestamp', group='sts', fatal=fatal))
3127 return sts
3128
3129 def _mark_watched(self, video_id, player_responses):
3130 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3131 label = 'fully ' if is_full else ''
3132 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3133 expected_type=url_or_none)
3134 if not url:
3135 self.report_warning(f'Unable to mark {label}watched')
3136 return
3137 parsed_url = urllib.parse.urlparse(url)
3138 qs = urllib.parse.parse_qs(parsed_url.query)
3139
3140 # cpn generation algorithm is reverse engineered from base.js.
3141 # In fact it works even with dummy cpn.
3142 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3143 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3144
3145 # # more consistent results setting it to right before the end
3146 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3147
3148 qs.update({
3149 'ver': ['2'],
3150 'cpn': [cpn],
3151 'cmt': video_length,
3152 'el': 'detailpage', # otherwise defaults to "shorts"
3153 })
3154
3155 if is_full:
3156 # these seem to mark watchtime "history" in the real world
3157 # they're required, so send in a single value
3158 qs.update({
3159 'st': 0,
3160 'et': video_length,
3161 })
3162
3163 url = urllib.parse.urlunparse(
3164 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
3165
3166 self._download_webpage(
3167 url, video_id, f'Marking {label}watched',
3168 'Unable to mark watched', fatal=False)
3169
3170 @classmethod
3171 def _extract_from_webpage(cls, url, webpage):
3172 # Invidious Instances
3173 # https://github.com/yt-dlp/yt-dlp/issues/195
3174 # https://github.com/iv-org/invidious/pull/1730
3175 mobj = re.search(
3176 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3177 webpage)
3178 if mobj:
3179 yield cls.url_result(mobj.group('url'), cls)
3180 raise cls.StopExtraction()
3181
3182 yield from super()._extract_from_webpage(url, webpage)
3183
3184 # lazyYT YouTube embed
3185 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3186 yield cls.url_result(unescapeHTML(id_), cls, id_)
3187
3188 # Wordpress "YouTube Video Importer" plugin
3189 for m in re.findall(r'''(?x)<div[^>]+
3190 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3191 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3192 yield cls.url_result(m[-1], cls, m[-1])
3193
3194 @classmethod
3195 def extract_id(cls, url):
3196 video_id = cls.get_temp_id(url)
3197 if not video_id:
3198 raise ExtractorError(f'Invalid URL: {url}')
3199 return video_id
3200
3201 def _extract_chapters_from_json(self, data, duration):
3202 chapter_list = traverse_obj(
3203 data, (
3204 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3205 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3206 ), expected_type=list)
3207
3208 return self._extract_chapters_helper(
3209 chapter_list,
3210 start_function=lambda chapter: float_or_none(
3211 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3212 title_function=lambda chapter: traverse_obj(
3213 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3214 duration=duration)
3215
3216 def _extract_chapters_from_engagement_panel(self, data, duration):
3217 content_list = traverse_obj(
3218 data,
3219 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
3220 expected_type=list)
3221 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3222 chapter_title = lambda chapter: self._get_text(chapter, 'title')
3223
3224 return next(filter(None, (
3225 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3226 chapter_time, chapter_title, duration)
3227 for contents in content_list)), [])
3228
3229 def _extract_comment(self, comment_renderer, parent=None):
3230 comment_id = comment_renderer.get('commentId')
3231 if not comment_id:
3232 return
3233
3234 text = self._get_text(comment_renderer, 'contentText')
3235
3236 # Timestamp is an estimate calculated from the current time and time_text
3237 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3238 timestamp = self._parse_time_text(time_text)
3239
3240 author = self._get_text(comment_renderer, 'authorText')
3241 author_id = try_get(comment_renderer,
3242 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3243
3244 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3245 lambda x: x['likeCount']), str)) or 0
3246 author_thumbnail = try_get(comment_renderer,
3247 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3248
3249 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3250 is_favorited = 'creatorHeart' in (try_get(
3251 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3252 return {
3253 'id': comment_id,
3254 'text': text,
3255 'timestamp': timestamp,
3256 'time_text': time_text,
3257 'like_count': votes,
3258 'is_favorited': is_favorited,
3259 'author': author,
3260 'author_id': author_id,
3261 'author_thumbnail': author_thumbnail,
3262 'author_is_uploader': author_is_uploader,
3263 'parent': parent or 'root'
3264 }
3265
3266 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3267
3268 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3269
3270 def extract_header(contents):
3271 _continuation = None
3272 for content in contents:
3273 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3274 expected_comment_count = self._get_count(
3275 comments_header_renderer, 'countText', 'commentsCount')
3276
3277 if expected_comment_count:
3278 tracker['est_total'] = expected_comment_count
3279 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3280 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3281
3282 sort_menu_item = try_get(
3283 comments_header_renderer,
3284 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3285 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3286
3287 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3288 if not _continuation:
3289 continue
3290
3291 sort_text = str_or_none(sort_menu_item.get('title'))
3292 if not sort_text:
3293 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3294 self.to_screen('Sorting comments by %s' % sort_text.lower())
3295 break
3296 return _continuation
3297
3298 def extract_thread(contents):
3299 if not parent:
3300 tracker['current_page_thread'] = 0
3301 for content in contents:
3302 if not parent and tracker['total_parent_comments'] >= max_parents:
3303 yield
3304 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3305 comment_renderer = get_first(
3306 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3307 expected_type=dict, default={})
3308
3309 comment = self._extract_comment(comment_renderer, parent)
3310 if not comment:
3311 continue
3312 # Sometimes YouTube may break and give us infinite looping comments.
3313 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
3314 if comment['id'] in tracker['seen_comment_ids']:
3315 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3316 yield
3317 else:
3318 tracker['seen_comment_ids'].add(comment['id'])
3319
3320 tracker['running_total'] += 1
3321 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3322 yield comment
3323
3324 # Attempt to get the replies
3325 comment_replies_renderer = try_get(
3326 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3327
3328 if comment_replies_renderer:
3329 tracker['current_page_thread'] += 1
3330 comment_entries_iter = self._comment_entries(
3331 comment_replies_renderer, ytcfg, video_id,
3332 parent=comment.get('id'), tracker=tracker)
3333 yield from itertools.islice(comment_entries_iter, min(
3334 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3335
3336 # Keeps track of counts across recursive calls
3337 if not tracker:
3338 tracker = dict(
3339 running_total=0,
3340 est_total=0,
3341 current_page_thread=0,
3342 total_parent_comments=0,
3343 total_reply_comments=0,
3344 seen_comment_ids=set())
3345
3346 # TODO: Deprecated
3347 # YouTube comments have a max depth of 2
3348 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3349 if max_depth:
3350 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3351 'Set max replies in the max-comments extractor argument instead')
3352 if max_depth == 1 and parent:
3353 return
3354
3355 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3356 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3357
3358 continuation = self._extract_continuation(root_continuation_data)
3359
3360 response = None
3361 is_forced_continuation = False
3362 is_first_continuation = parent is None
3363 if is_first_continuation and not continuation:
3364 # Sometimes you can get comments by generating the continuation yourself,
3365 # even if YouTube initially reports them being disabled - e.g. stories comments.
3366 # Note: if the comment section is actually disabled, YouTube may return a response with
3367 # required check_get_keys missing. So we will disable that check initially in this case.
3368 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3369 is_forced_continuation = True
3370
3371 for page_num in itertools.count(0):
3372 if not continuation:
3373 break
3374 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3375 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
3376 if page_num == 0:
3377 if is_first_continuation:
3378 note_prefix = 'Downloading comment section API JSON'
3379 else:
3380 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3381 tracker['current_page_thread'], comment_prog_str)
3382 else:
3383 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3384 ' ' if parent else '', ' replies' if parent else '',
3385 page_num, comment_prog_str)
3386 try:
3387 response = self._extract_response(
3388 item_id=None, query=continuation,
3389 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3390 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3391 except ExtractorError as e:
3392 # Ignore incomplete data error for replies if retries didn't work.
3393 # This is to allow any other parent comments and comment threads to be downloaded.
3394 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3395 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3396 self.report_warning(
3397 'Received incomplete data for a comment reply thread and retrying did not help. '
3398 'Ignoring to let other comments be downloaded.')
3399 else:
3400 raise
3401 is_forced_continuation = False
3402 continuation_contents = traverse_obj(
3403 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3404
3405 continuation = None
3406 for continuation_section in continuation_contents:
3407 continuation_items = traverse_obj(
3408 continuation_section,
3409 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3410 get_all=False, expected_type=list) or []
3411 if is_first_continuation:
3412 continuation = extract_header(continuation_items)
3413 is_first_continuation = False
3414 if continuation:
3415 break
3416 continue
3417
3418 for entry in extract_thread(continuation_items):
3419 if not entry:
3420 return
3421 yield entry
3422 continuation = self._extract_continuation({'contents': continuation_items})
3423 if continuation:
3424 break
3425
3426 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3427 if message and not parent and tracker['running_total'] == 0:
3428 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3429 raise self.CommentsDisabled
3430
3431 @staticmethod
3432 def _generate_comment_continuation(video_id):
3433 """
3434 Generates initial comment section continuation token from given video id
3435 """
3436 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3437 return base64.b64encode(token.encode()).decode()
3438
3439 def _get_comments(self, ytcfg, video_id, contents, webpage):
3440 """Entry for comment extraction"""
3441 def _real_comment_extract(contents):
3442 renderer = next((
3443 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3444 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3445 yield from self._comment_entries(renderer, ytcfg, video_id)
3446
3447 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3448 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3449
3450 @staticmethod
3451 def _get_checkok_params():
3452 return {'contentCheckOk': True, 'racyCheckOk': True}
3453
3454 @classmethod
3455 def _generate_player_context(cls, sts=None):
3456 context = {
3457 'html5Preference': 'HTML5_PREF_WANTS',
3458 }
3459 if sts is not None:
3460 context['signatureTimestamp'] = sts
3461 return {
3462 'playbackContext': {
3463 'contentPlaybackContext': context
3464 },
3465 **cls._get_checkok_params()
3466 }
3467
3468 @staticmethod
3469 def _is_agegated(player_response):
3470 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3471 return True
3472
3473 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
3474 AGE_GATE_REASONS = (
3475 'confirm your age', 'age-restricted', 'inappropriate', # reason
3476 'age_verification_required', 'age_check_required', # status
3477 )
3478 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3479
3480 @staticmethod
3481 def _is_unplayable(player_response):
3482 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3483
3484 _STORY_PLAYER_PARAMS = '8AEB'
3485
3486 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3487
3488 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3489 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3490 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3491 headers = self.generate_api_headers(
3492 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3493
3494 yt_query = {
3495 'videoId': video_id,
3496 }
3497 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3498 yt_query['params'] = self._STORY_PLAYER_PARAMS
3499
3500 yt_query.update(self._generate_player_context(sts))
3501 return self._extract_response(
3502 item_id=video_id, ep='player', query=yt_query,
3503 ytcfg=player_ytcfg, headers=headers, fatal=True,
3504 default_client=client,
3505 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3506 ) or None
3507
3508 def _get_requested_clients(self, url, smuggled_data):
3509 requested_clients = []
3510 default = ['android', 'web']
3511 allowed_clients = sorted(
3512 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3513 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3514 for client in self._configuration_arg('player_client'):
3515 if client in allowed_clients:
3516 requested_clients.append(client)
3517 elif client == 'default':
3518 requested_clients.extend(default)
3519 elif client == 'all':
3520 requested_clients.extend(allowed_clients)
3521 else:
3522 self.report_warning(f'Skipping unsupported client {client}')
3523 if not requested_clients:
3524 requested_clients = default
3525
3526 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3527 requested_clients.extend(
3528 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3529
3530 return orderedSet(requested_clients)
3531
3532 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3533 initial_pr = None
3534 if webpage:
3535 initial_pr = self._search_json(
3536 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3537
3538 all_clients = set(clients)
3539 clients = clients[::-1]
3540 prs = []
3541
3542 def append_client(*client_names):
3543 """ Append the first client name that exists but not already used """
3544 for client_name in client_names:
3545 actual_client = _split_innertube_client(client_name)[0]
3546 if actual_client in INNERTUBE_CLIENTS:
3547 if actual_client not in all_clients:
3548 clients.append(client_name)
3549 all_clients.add(actual_client)
3550 return
3551
3552 # Android player_response does not have microFormats which are needed for
3553 # extraction of some data. So we return the initial_pr with formats
3554 # stripped out even if not requested by the user
3555 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3556 if initial_pr:
3557 pr = dict(initial_pr)
3558 pr['streamingData'] = None
3559 prs.append(pr)
3560
3561 last_error = None
3562 tried_iframe_fallback = False
3563 player_url = None
3564 while clients:
3565 client, base_client, variant = _split_innertube_client(clients.pop())
3566 player_ytcfg = master_ytcfg if client == 'web' else {}
3567 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3568 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3569
3570 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3571 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3572 if 'js' in self._configuration_arg('player_skip'):
3573 require_js_player = False
3574 player_url = None
3575
3576 if not player_url and not tried_iframe_fallback and require_js_player:
3577 player_url = self._download_player_url(video_id)
3578 tried_iframe_fallback = True
3579
3580 try:
3581 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3582 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3583 except ExtractorError as e:
3584 if last_error:
3585 self.report_warning(last_error)
3586 last_error = e
3587 continue
3588
3589 if pr:
3590 # YouTube may return a different video player response than expected.
3591 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3592 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3593 if pr_video_id and pr_video_id != video_id:
3594 self.report_warning(
3595 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
3596 else:
3597 prs.append(pr)
3598
3599 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3600 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3601 append_client(f'{base_client}_creator')
3602 elif self._is_agegated(pr):
3603 if variant == 'tv_embedded':
3604 append_client(f'{base_client}_embedded')
3605 elif not variant:
3606 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3607
3608 if last_error:
3609 if not len(prs):
3610 raise last_error
3611 self.report_warning(last_error)
3612 return prs, player_url
3613
3614 def _needs_live_processing(self, live_status, duration):
3615 if (live_status == 'is_live' and self.get_param('live_from_start')
3616 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3617 return live_status
3618
3619 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3620 itags, stream_ids = collections.defaultdict(set), []
3621 itag_qualities, res_qualities = {}, {0: None}
3622 q = qualities([
3623 # Normally tiny is the smallest video-only formats. But
3624 # audio-only formats with unknown quality may get tagged as tiny
3625 'tiny',
3626 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3627 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3628 ])
3629 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
3630
3631 for fmt in streaming_formats:
3632 if fmt.get('targetDurationSec'):
3633 continue
3634
3635 itag = str_or_none(fmt.get('itag'))
3636 audio_track = fmt.get('audioTrack') or {}
3637 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
3638 if stream_id in stream_ids:
3639 continue
3640
3641 quality = fmt.get('quality')
3642 height = int_or_none(fmt.get('height'))
3643 if quality == 'tiny' or not quality:
3644 quality = fmt.get('audioQuality', '').lower() or quality
3645 # The 3gp format (17) in android client has a quality of "small",
3646 # but is actually worse than other formats
3647 if itag == '17':
3648 quality = 'tiny'
3649 if quality:
3650 if itag:
3651 itag_qualities[itag] = quality
3652 if height:
3653 res_qualities[height] = quality
3654 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3655 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3656 # number of fragment that would subsequently requested with (`&sq=N`)
3657 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3658 continue
3659
3660 fmt_url = fmt.get('url')
3661 if not fmt_url:
3662 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3663 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3664 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3665 if not all((sc, fmt_url, player_url, encrypted_sig)):
3666 continue
3667 try:
3668 fmt_url += '&%s=%s' % (
3669 traverse_obj(sc, ('sp', -1)) or 'signature',
3670 self._decrypt_signature(encrypted_sig, video_id, player_url)
3671 )
3672 except ExtractorError as e:
3673 self.report_warning('Signature extraction failed: Some formats may be missing',
3674 video_id=video_id, only_once=True)
3675 self.write_debug(e, only_once=True)
3676 continue
3677
3678 query = parse_qs(fmt_url)
3679 throttled = False
3680 if query.get('n'):
3681 try:
3682 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3683 fmt_url = update_url_query(fmt_url, {
3684 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3685 })
3686 except ExtractorError as e:
3687 phantomjs_hint = ''
3688 if isinstance(e, JSInterpreter.Exception):
3689 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3690 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3691 if player_url:
3692 self.report_warning(
3693 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3694 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3695 self.write_debug(e, only_once=True)
3696 else:
3697 self.report_warning(
3698 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3699 video_id=video_id, only_once=True)
3700 throttled = True
3701
3702 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3703 language_preference = (
3704 10 if audio_track.get('audioIsDefault') and 10
3705 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3706 else -1)
3707 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3708 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3709 # Make sure to avoid false positives with small duration differences.
3710 # E.g. __2ABJjxzNo, ySuUZEjARPY
3711 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3712 if is_damaged:
3713 self.report_warning(
3714 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3715 dct = {
3716 'asr': int_or_none(fmt.get('audioSampleRate')),
3717 'filesize': int_or_none(fmt.get('contentLength')),
3718 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
3719 'format_note': join_nonempty(
3720 '%s%s' % (audio_track.get('displayName') or '',
3721 ' (default)' if language_preference > 0 else ''),
3722 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3723 'DRC' if fmt.get('isDrc') else None,
3724 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3725 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3726 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3727 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3728 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3729 'fps': int_or_none(fmt.get('fps')) or None,
3730 'audio_channels': fmt.get('audioChannels'),
3731 'height': height,
3732 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
3733 'has_drm': bool(fmt.get('drmFamilies')),
3734 'tbr': tbr,
3735 'url': fmt_url,
3736 'width': int_or_none(fmt.get('width')),
3737 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3738 'desc' if language_preference < -1 else '') or None,
3739 'language_preference': language_preference,
3740 # Strictly de-prioritize damaged and 3gp formats
3741 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3742 }
3743 mime_mobj = re.match(
3744 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3745 if mime_mobj:
3746 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3747 dct.update(parse_codecs(mime_mobj.group(2)))
3748 no_audio = dct.get('acodec') == 'none'
3749 no_video = dct.get('vcodec') == 'none'
3750 if no_audio:
3751 dct['vbr'] = tbr
3752 if no_video:
3753 dct['abr'] = tbr
3754 if no_audio or no_video:
3755 CHUNK_SIZE = 10 << 20
3756 dct.update({
3757 'protocol': 'http_dash_segments',
3758 'fragments': [{
3759 'url': update_url_query(dct['url'], {
3760 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, dct["filesize"])}'
3761 })
3762 } for range_start in range(0, dct['filesize'], CHUNK_SIZE)]
3763 } if dct['filesize'] else {
3764 'downloader_options': {'http_chunk_size': CHUNK_SIZE} # No longer useful?
3765 })
3766
3767 if dct.get('ext'):
3768 dct['container'] = dct['ext'] + '_dash'
3769
3770 if itag:
3771 itags[itag].add(('https', dct.get('language')))
3772 stream_ids.append(stream_id)
3773 yield dct
3774
3775 needs_live_processing = self._needs_live_processing(live_status, duration)
3776 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3777
3778 skip_manifests = set(self._configuration_arg('skip'))
3779 if (not self.get_param('youtube_include_hls_manifest', True)
3780 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3781 or needs_live_processing and skip_bad_formats):
3782 skip_manifests.add('hls')
3783
3784 if not self.get_param('youtube_include_dash_manifest', True):
3785 skip_manifests.add('dash')
3786 if self._configuration_arg('include_live_dash'):
3787 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3788 'Use include_incomplete_formats extractor argument instead')
3789 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3790 skip_manifests.add('dash')
3791
3792 def process_manifest_format(f, proto, itag):
3793 key = (proto, f.get('language'))
3794 if key in itags[itag]:
3795 return False
3796 itags[itag].add(key)
3797
3798 if any(p != proto for p, _ in itags[itag]):
3799 f['format_id'] = f'{itag}-{proto}'
3800 elif itag:
3801 f['format_id'] = itag
3802
3803 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3804 if f['quality'] == -1 and f.get('height'):
3805 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3806 return True
3807
3808 subtitles = {}
3809 for sd in streaming_data:
3810 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3811 if hls_manifest_url:
3812 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3813 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3814 subtitles = self._merge_subtitles(subs, subtitles)
3815 for f in fmts:
3816 if process_manifest_format(f, 'hls', self._search_regex(
3817 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3818 yield f
3819
3820 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3821 if dash_manifest_url:
3822 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3823 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3824 for f in formats:
3825 if process_manifest_format(f, 'dash', f['format_id']):
3826 f['filesize'] = int_or_none(self._search_regex(
3827 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3828 if needs_live_processing:
3829 f['is_from_start'] = True
3830
3831 yield f
3832 yield subtitles
3833
3834 def _extract_storyboard(self, player_responses, duration):
3835 spec = get_first(
3836 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3837 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3838 if not base_url:
3839 return
3840 L = len(spec) - 1
3841 for i, args in enumerate(spec):
3842 args = args.split('#')
3843 counts = list(map(int_or_none, args[:5]))
3844 if len(args) != 8 or not all(counts):
3845 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3846 continue
3847 width, height, frame_count, cols, rows = counts
3848 N, sigh = args[6:]
3849
3850 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3851 fragment_count = frame_count / (cols * rows)
3852 fragment_duration = duration / fragment_count
3853 yield {
3854 'format_id': f'sb{i}',
3855 'format_note': 'storyboard',
3856 'ext': 'mhtml',
3857 'protocol': 'mhtml',
3858 'acodec': 'none',
3859 'vcodec': 'none',
3860 'url': url,
3861 'width': width,
3862 'height': height,
3863 'fps': frame_count / duration,
3864 'rows': rows,
3865 'columns': cols,
3866 'fragments': [{
3867 'url': url.replace('$M', str(j)),
3868 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3869 } for j in range(math.ceil(fragment_count))],
3870 }
3871
3872 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3873 webpage = None
3874 if 'webpage' not in self._configuration_arg('player_skip'):
3875 query = {'bpctr': '9999999999', 'has_verified': '1'}
3876 if smuggled_data.get('is_story'):
3877 query['pp'] = self._STORY_PLAYER_PARAMS
3878 webpage = self._download_webpage(
3879 webpage_url, video_id, fatal=False, query=query)
3880
3881 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3882
3883 player_responses, player_url = self._extract_player_responses(
3884 self._get_requested_clients(url, smuggled_data),
3885 video_id, webpage, master_ytcfg, smuggled_data)
3886
3887 return webpage, master_ytcfg, player_responses, player_url
3888
3889 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3890 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3891 is_live = get_first(video_details, 'isLive')
3892 if is_live is None:
3893 is_live = get_first(live_broadcast_details, 'isLiveNow')
3894 live_content = get_first(video_details, 'isLiveContent')
3895 is_upcoming = get_first(video_details, 'isUpcoming')
3896 post_live = get_first(video_details, 'isPostLiveDvr')
3897 live_status = ('post_live' if post_live
3898 else 'is_live' if is_live
3899 else 'is_upcoming' if is_upcoming
3900 else 'was_live' if live_content
3901 else 'not_live' if False in (is_live, live_content)
3902 else None)
3903 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
3904 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3905
3906 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3907
3908 def _real_extract(self, url):
3909 url, smuggled_data = unsmuggle_url(url, {})
3910 video_id = self._match_id(url)
3911
3912 base_url = self.http_scheme() + '//www.youtube.com/'
3913 webpage_url = base_url + 'watch?v=' + video_id
3914
3915 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3916
3917 playability_statuses = traverse_obj(
3918 player_responses, (..., 'playabilityStatus'), expected_type=dict)
3919
3920 trailer_video_id = get_first(
3921 playability_statuses,
3922 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3923 expected_type=str)
3924 if trailer_video_id:
3925 return self.url_result(
3926 trailer_video_id, self.ie_key(), trailer_video_id)
3927
3928 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3929 if webpage else (lambda x: None))
3930
3931 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
3932 microformats = traverse_obj(
3933 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3934 expected_type=dict)
3935
3936 translated_title = self._get_text(microformats, (..., 'title'))
3937 video_title = (self._preferred_lang and translated_title
3938 or get_first(video_details, 'title') # primary
3939 or translated_title
3940 or search_meta(['og:title', 'twitter:title', 'title']))
3941 translated_description = self._get_text(microformats, (..., 'description'))
3942 original_description = get_first(video_details, 'shortDescription')
3943 video_description = (
3944 self._preferred_lang and translated_description
3945 # If original description is blank, it will be an empty string.
3946 # Do not prefer translated description in this case.
3947 or original_description if original_description is not None else translated_description)
3948
3949 multifeed_metadata_list = get_first(
3950 player_responses,
3951 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3952 expected_type=str)
3953 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3954 if self.get_param('noplaylist'):
3955 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3956 else:
3957 entries = []
3958 feed_ids = []
3959 for feed in multifeed_metadata_list.split(','):
3960 # Unquote should take place before split on comma (,) since textual
3961 # fields may contain comma as well (see
3962 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3963 feed_data = urllib.parse.parse_qs(
3964 urllib.parse.unquote_plus(feed))
3965
3966 def feed_entry(name):
3967 return try_get(
3968 feed_data, lambda x: x[name][0], str)
3969
3970 feed_id = feed_entry('id')
3971 if not feed_id:
3972 continue
3973 feed_title = feed_entry('title')
3974 title = video_title
3975 if feed_title:
3976 title += ' (%s)' % feed_title
3977 entries.append({
3978 '_type': 'url_transparent',
3979 'ie_key': 'Youtube',
3980 'url': smuggle_url(
3981 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3982 {'force_singlefeed': True}),
3983 'title': title,
3984 })
3985 feed_ids.append(feed_id)
3986 self.to_screen(
3987 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3988 % (', '.join(feed_ids), video_id))
3989 return self.playlist_result(
3990 entries, video_id, video_title, video_description)
3991
3992 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
3993 or int_or_none(get_first(microformats, 'lengthSeconds'))
3994 or parse_duration(search_meta('duration')) or None)
3995
3996 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3997 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3998 if live_status == 'post_live':
3999 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
4000
4001 if not formats:
4002 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
4003 self.report_drm(video_id)
4004 pemr = get_first(
4005 playability_statuses,
4006 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4007 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4008 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
4009 if subreason:
4010 if subreason == 'The uploader has not made this video available in your country.':
4011 countries = get_first(microformats, 'availableCountries')
4012 if not countries:
4013 regions_allowed = search_meta('regionsAllowed')
4014 countries = regions_allowed.split(',') if regions_allowed else None
4015 self.raise_geo_restricted(subreason, countries, metadata_available=True)
4016 reason += f'. {subreason}'
4017 if reason:
4018 self.raise_no_formats(reason, expected=True)
4019
4020 keywords = get_first(video_details, 'keywords', expected_type=list) or []
4021 if not keywords and webpage:
4022 keywords = [
4023 unescapeHTML(m.group('content'))
4024 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4025 for keyword in keywords:
4026 if keyword.startswith('yt:stretch='):
4027 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4028 if mobj:
4029 # NB: float is intentional for forcing float division
4030 w, h = (float(v) for v in mobj.groups())
4031 if w > 0 and h > 0:
4032 ratio = w / h
4033 for f in formats:
4034 if f.get('vcodec') != 'none':
4035 f['stretched_ratio'] = ratio
4036 break
4037 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
4038 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4039 if thumbnail_url:
4040 thumbnails.append({
4041 'url': thumbnail_url,
4042 })
4043 original_thumbnails = thumbnails.copy()
4044
4045 # The best resolution thumbnails sometimes does not appear in the webpage
4046 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4047 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4048 thumbnail_names = [
4049 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4050 # in resolution, these are not the custom thumbnail. So de-prioritize them
4051 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4052 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4053 ]
4054 n_thumbnail_names = len(thumbnail_names)
4055 thumbnails.extend({
4056 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4057 video_id=video_id, name=name, ext=ext,
4058 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
4059 } for name in thumbnail_names for ext in ('webp', 'jpg'))
4060 for thumb in thumbnails:
4061 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
4062 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
4063 self._remove_duplicate_formats(thumbnails)
4064 self._downloader._sort_thumbnails(original_thumbnails)
4065
4066 category = get_first(microformats, 'category') or search_meta('genre')
4067 channel_id = str_or_none(
4068 get_first(video_details, 'channelId')
4069 or get_first(microformats, 'externalChannelId')
4070 or search_meta('channelId'))
4071 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4072
4073 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4074 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4075 if not duration and live_end_time and live_start_time:
4076 duration = live_end_time - live_start_time
4077
4078 needs_live_processing = self._needs_live_processing(live_status, duration)
4079
4080 def is_bad_format(fmt):
4081 if needs_live_processing and not fmt.get('is_from_start'):
4082 return True
4083 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4084 and fmt.get('protocol') == 'http_dash_segments'):
4085 return True
4086
4087 for fmt in filter(is_bad_format, formats):
4088 fmt['preference'] = (fmt.get('preference') or -1) - 10
4089 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4090
4091 if needs_live_processing:
4092 self._prepare_live_from_start_formats(
4093 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
4094
4095 formats.extend(self._extract_storyboard(player_responses, duration))
4096
4097 info = {
4098 'id': video_id,
4099 'title': video_title,
4100 'formats': formats,
4101 'thumbnails': thumbnails,
4102 # The best thumbnail that we are sure exists. Prevents unnecessary
4103 # URL checking if user don't care about getting the best possible thumbnail
4104 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
4105 'description': video_description,
4106 'uploader': get_first(video_details, 'author'),
4107 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
4108 'uploader_url': owner_profile_url,
4109 'channel_id': channel_id,
4110 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
4111 'duration': duration,
4112 'view_count': int_or_none(
4113 get_first((video_details, microformats), (..., 'viewCount'))
4114 or search_meta('interactionCount')),
4115 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
4116 'age_limit': 18 if (
4117 get_first(microformats, 'isFamilySafe') is False
4118 or search_meta('isFamilyFriendly') == 'false'
4119 or search_meta('og:restrictions:age') == '18+') else 0,
4120 'webpage_url': webpage_url,
4121 'categories': [category] if category else None,
4122 'tags': keywords,
4123 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4124 'live_status': live_status,
4125 'release_timestamp': live_start_time,
4126 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4127 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4128 }
4129
4130 subtitles = {}
4131 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
4132 if pctr:
4133 def get_lang_code(track):
4134 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4135 or track.get('languageCode'))
4136
4137 # Converted into dicts to remove duplicates
4138 captions = {
4139 get_lang_code(sub): sub
4140 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
4141 translation_languages = {
4142 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4143 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
4144
4145 def process_language(container, base_url, lang_code, sub_name, query):
4146 lang_subs = container.setdefault(lang_code, [])
4147 for fmt in self._SUBTITLE_FORMATS:
4148 query.update({
4149 'fmt': fmt,
4150 })
4151 lang_subs.append({
4152 'ext': fmt,
4153 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
4154 'name': sub_name,
4155 })
4156
4157 # NB: Constructing the full subtitle dictionary is slow
4158 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4159 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
4160 for lang_code, caption_track in captions.items():
4161 base_url = caption_track.get('baseUrl')
4162 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
4163 if not base_url:
4164 continue
4165 lang_name = self._get_text(caption_track, 'name', max_runs=1)
4166 if caption_track.get('kind') != 'asr':
4167 if not lang_code:
4168 continue
4169 process_language(
4170 subtitles, base_url, lang_code, lang_name, {})
4171 if not caption_track.get('isTranslatable'):
4172 continue
4173 for trans_code, trans_name in translation_languages.items():
4174 if not trans_code:
4175 continue
4176 orig_trans_code = trans_code
4177 if caption_track.get('kind') != 'asr' and trans_code != 'und':
4178 if not get_translated_subs:
4179 continue
4180 trans_code += f'-{lang_code}'
4181 trans_name += format_field(lang_name, None, ' from %s')
4182 # Add an "-orig" label to the original language so that it can be distinguished.
4183 # The subs are returned without "-orig" as well for compatibility
4184 if lang_code == f'a-{orig_trans_code}':
4185 process_language(
4186 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4187 # Setting tlang=lang returns damaged subtitles.
4188 process_language(automatic_captions, base_url, trans_code, trans_name,
4189 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
4190
4191 info['automatic_captions'] = automatic_captions
4192 info['subtitles'] = subtitles
4193
4194 parsed_url = urllib.parse.urlparse(url)
4195 for component in [parsed_url.fragment, parsed_url.query]:
4196 query = urllib.parse.parse_qs(component)
4197 for k, v in query.items():
4198 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4199 d_k += '_time'
4200 if d_k not in info and k in s_ks:
4201 info[d_k] = parse_duration(query[k][0])
4202
4203 # Youtube Music Auto-generated description
4204 if video_description:
4205 mobj = re.search(
4206 r'''(?xs)
4207 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4208 (?P<album>[^\n]+)
4209 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4210 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4211 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4212 .+\nAuto-generated\ by\ YouTube\.\s*$
4213 ''', video_description)
4214 if mobj:
4215 release_year = mobj.group('release_year')
4216 release_date = mobj.group('release_date')
4217 if release_date:
4218 release_date = release_date.replace('-', '')
4219 if not release_year:
4220 release_year = release_date[:4]
4221 info.update({
4222 'album': mobj.group('album'.strip()),
4223 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4224 'track': mobj.group('track').strip(),
4225 'release_date': release_date,
4226 'release_year': int_or_none(release_year),
4227 })
4228
4229 initial_data = None
4230 if webpage:
4231 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4232 if not initial_data:
4233 query = {'videoId': video_id}
4234 query.update(self._get_checkok_params())
4235 initial_data = self._extract_response(
4236 item_id=video_id, ep='next', fatal=False,
4237 ytcfg=master_ytcfg, query=query,
4238 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4239 note='Downloading initial data API JSON')
4240
4241 info['comment_count'] = traverse_obj(initial_data, (
4242 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4243 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4244 ), (
4245 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4246 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4247 ), expected_type=int_or_none, get_all=False)
4248
4249 try: # This will error if there is no livechat
4250 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4251 except (KeyError, IndexError, TypeError):
4252 pass
4253 else:
4254 info.setdefault('subtitles', {})['live_chat'] = [{
4255 # url is needed to set cookies
4256 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4257 'video_id': video_id,
4258 'ext': 'json',
4259 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4260 else 'youtube_live_chat_replay'),
4261 }]
4262
4263 if initial_data:
4264 info['chapters'] = (
4265 self._extract_chapters_from_json(initial_data, duration)
4266 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4267 or self._extract_chapters_from_description(video_description, duration)
4268 or None)
4269
4270 contents = traverse_obj(
4271 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4272 expected_type=list, default=[])
4273
4274 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4275 if vpir:
4276 stl = vpir.get('superTitleLink')
4277 if stl:
4278 stl = self._get_text(stl)
4279 if try_get(
4280 vpir,
4281 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4282 info['location'] = stl
4283 else:
4284 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4285 if mobj:
4286 info.update({
4287 'series': mobj.group(1),
4288 'season_number': int(mobj.group(2)),
4289 'episode_number': int(mobj.group(3)),
4290 })
4291 for tlb in (try_get(
4292 vpir,
4293 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4294 list) or []):
4295 tbrs = variadic(
4296 traverse_obj(
4297 tlb, ('toggleButtonRenderer', ...),
4298 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4299 for tbr in tbrs:
4300 for getter, regex in [(
4301 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4302 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4303 lambda x: x['accessibility'],
4304 lambda x: x['accessibilityData']['accessibilityData'],
4305 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4306 label = (try_get(tbr, getter, dict) or {}).get('label')
4307 if label:
4308 mobj = re.match(regex, label)
4309 if mobj:
4310 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4311 break
4312 sbr_tooltip = try_get(
4313 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4314 if sbr_tooltip:
4315 like_count, dislike_count = sbr_tooltip.split(' / ')
4316 info.update({
4317 'like_count': str_to_int(like_count),
4318 'dislike_count': str_to_int(dislike_count),
4319 })
4320 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4321 if vcr:
4322 vc = self._get_count(vcr, 'viewCount')
4323 # Upcoming premieres with waiting count are treated as live here
4324 if vcr.get('isLive'):
4325 info['concurrent_view_count'] = vc
4326 elif info.get('view_count') is None:
4327 info['view_count'] = vc
4328
4329 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4330 if vsir:
4331 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4332 info.update({
4333 'channel': self._get_text(vor, 'title'),
4334 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4335
4336 rows = try_get(
4337 vsir,
4338 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4339 list) or []
4340 multiple_songs = False
4341 for row in rows:
4342 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4343 multiple_songs = True
4344 break
4345 for row in rows:
4346 mrr = row.get('metadataRowRenderer') or {}
4347 mrr_title = mrr.get('title')
4348 if not mrr_title:
4349 continue
4350 mrr_title = self._get_text(mrr, 'title')
4351 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4352 if mrr_title == 'License':
4353 info['license'] = mrr_contents_text
4354 elif not multiple_songs:
4355 if mrr_title == 'Album':
4356 info['album'] = mrr_contents_text
4357 elif mrr_title == 'Artist':
4358 info['artist'] = mrr_contents_text
4359 elif mrr_title == 'Song':
4360 info['track'] = mrr_contents_text
4361
4362 fallbacks = {
4363 'channel': 'uploader',
4364 'channel_id': 'uploader_id',
4365 'channel_url': 'uploader_url',
4366 }
4367
4368 # The upload date for scheduled, live and past live streams / premieres in microformats
4369 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4370 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4371 upload_date = (
4372 unified_strdate(get_first(microformats, 'uploadDate'))
4373 or unified_strdate(search_meta('uploadDate')))
4374 if not upload_date or (
4375 live_status in ('not_live', None)
4376 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4377 ):
4378 upload_date = strftime_or_none(
4379 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4380 info['upload_date'] = upload_date
4381
4382 for to, frm in fallbacks.items():
4383 if not info.get(to):
4384 info[to] = info.get(frm)
4385
4386 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4387 v = info.get(s_k)
4388 if v:
4389 info[d_k] = v
4390
4391 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4392
4393 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4394 or get_first(video_details, 'isPrivate', expected_type=bool))
4395
4396 info['availability'] = (
4397 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4398 else self._availability(
4399 is_private=is_private,
4400 needs_premium=(
4401 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4402 or False if initial_data and is_private is not None else None),
4403 needs_subscription=(
4404 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4405 or False if initial_data and is_private is not None else None),
4406 needs_auth=info['age_limit'] >= 18,
4407 is_unlisted=None if is_private is None else (
4408 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4409 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4410
4411 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4412
4413 self.mark_watched(video_id, player_responses)
4414
4415 return info
4416
4417
4418 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4419 @staticmethod
4420 def passthrough_smuggled_data(func):
4421 def _smuggle(info, smuggled_data):
4422 if info.get('_type') not in ('url', 'url_transparent'):
4423 return info
4424 if smuggled_data.get('is_music_url'):
4425 parsed_url = urllib.parse.urlparse(info['url'])
4426 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4427 smuggled_data.pop('is_music_url')
4428 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4429 if smuggled_data:
4430 info['url'] = smuggle_url(info['url'], smuggled_data)
4431 return info
4432
4433 @functools.wraps(func)
4434 def wrapper(self, url):
4435 url, smuggled_data = unsmuggle_url(url, {})
4436 if self.is_music_url(url):
4437 smuggled_data['is_music_url'] = True
4438 info_dict = func(self, url, smuggled_data)
4439 if smuggled_data:
4440 _smuggle(info_dict, smuggled_data)
4441 if info_dict.get('entries'):
4442 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
4443 return info_dict
4444 return wrapper
4445
4446 @staticmethod
4447 def _extract_basic_item_renderer(item):
4448 # Modified from _extract_grid_item_renderer
4449 known_basic_renderers = (
4450 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4451 )
4452 for key, renderer in item.items():
4453 if not isinstance(renderer, dict):
4454 continue
4455 elif key in known_basic_renderers:
4456 return renderer
4457 elif key.startswith('grid') and key.endswith('Renderer'):
4458 return renderer
4459
4460 def _extract_channel_renderer(self, renderer):
4461 channel_id = renderer['channelId']
4462 title = self._get_text(renderer, 'title')
4463 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4464 return {
4465 '_type': 'url',
4466 'url': channel_url,
4467 'id': channel_id,
4468 'ie_key': YoutubeTabIE.ie_key(),
4469 'channel': title,
4470 'channel_id': channel_id,
4471 'channel_url': channel_url,
4472 'title': title,
4473 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4474 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4475 'playlist_count': self._get_count(renderer, 'videoCountText'),
4476 'description': self._get_text(renderer, 'descriptionSnippet'),
4477 }
4478
4479 def _grid_entries(self, grid_renderer):
4480 for item in grid_renderer['items']:
4481 if not isinstance(item, dict):
4482 continue
4483 renderer = self._extract_basic_item_renderer(item)
4484 if not isinstance(renderer, dict):
4485 continue
4486 title = self._get_text(renderer, 'title')
4487
4488 # playlist
4489 playlist_id = renderer.get('playlistId')
4490 if playlist_id:
4491 yield self.url_result(
4492 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4493 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4494 video_title=title)
4495 continue
4496 # video
4497 video_id = renderer.get('videoId')
4498 if video_id:
4499 yield self._extract_video(renderer)
4500 continue
4501 # channel
4502 channel_id = renderer.get('channelId')
4503 if channel_id:
4504 yield self._extract_channel_renderer(renderer)
4505 continue
4506 # generic endpoint URL support
4507 ep_url = urljoin('https://www.youtube.com/', try_get(
4508 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4509 str))
4510 if ep_url:
4511 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4512 if ie.suitable(ep_url):
4513 yield self.url_result(
4514 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4515 break
4516
4517 def _music_reponsive_list_entry(self, renderer):
4518 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4519 if video_id:
4520 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4521 ie=YoutubeIE.ie_key(), video_id=video_id)
4522 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4523 if playlist_id:
4524 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4525 if video_id:
4526 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4527 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4528 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4529 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4530 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4531 if browse_id:
4532 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4533 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4534
4535 def _shelf_entries_from_content(self, shelf_renderer):
4536 content = shelf_renderer.get('content')
4537 if not isinstance(content, dict):
4538 return
4539 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4540 if renderer:
4541 # TODO: add support for nested playlists so each shelf is processed
4542 # as separate playlist
4543 # TODO: this includes only first N items
4544 yield from self._grid_entries(renderer)
4545 renderer = content.get('horizontalListRenderer')
4546 if renderer:
4547 # TODO
4548 pass
4549
4550 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4551 ep = try_get(
4552 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4553 str)
4554 shelf_url = urljoin('https://www.youtube.com', ep)
4555 if shelf_url:
4556 # Skipping links to another channels, note that checking for
4557 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4558 # will not work
4559 if skip_channels and '/channels?' in shelf_url:
4560 return
4561 title = self._get_text(shelf_renderer, 'title')
4562 yield self.url_result(shelf_url, video_title=title)
4563 # Shelf may not contain shelf URL, fallback to extraction from content
4564 yield from self._shelf_entries_from_content(shelf_renderer)
4565
4566 def _playlist_entries(self, video_list_renderer):
4567 for content in video_list_renderer['contents']:
4568 if not isinstance(content, dict):
4569 continue
4570 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4571 if not isinstance(renderer, dict):
4572 continue
4573 video_id = renderer.get('videoId')
4574 if not video_id:
4575 continue
4576 yield self._extract_video(renderer)
4577
4578 def _rich_entries(self, rich_grid_renderer):
4579 renderer = traverse_obj(
4580 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4581 video_id = renderer.get('videoId')
4582 if not video_id:
4583 return
4584 yield self._extract_video(renderer)
4585
4586 def _video_entry(self, video_renderer):
4587 video_id = video_renderer.get('videoId')
4588 if video_id:
4589 return self._extract_video(video_renderer)
4590
4591 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4592 url = urljoin('https://youtube.com', traverse_obj(
4593 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4594 if url:
4595 return self.url_result(
4596 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4597
4598 def _post_thread_entries(self, post_thread_renderer):
4599 post_renderer = try_get(
4600 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4601 if not post_renderer:
4602 return
4603 # video attachment
4604 video_renderer = try_get(
4605 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4606 video_id = video_renderer.get('videoId')
4607 if video_id:
4608 entry = self._extract_video(video_renderer)
4609 if entry:
4610 yield entry
4611 # playlist attachment
4612 playlist_id = try_get(
4613 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4614 if playlist_id:
4615 yield self.url_result(
4616 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4617 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4618 # inline video links
4619 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4620 for run in runs:
4621 if not isinstance(run, dict):
4622 continue
4623 ep_url = try_get(
4624 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4625 if not ep_url:
4626 continue
4627 if not YoutubeIE.suitable(ep_url):
4628 continue
4629 ep_video_id = YoutubeIE._match_id(ep_url)
4630 if video_id == ep_video_id:
4631 continue
4632 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4633
4634 def _post_thread_continuation_entries(self, post_thread_continuation):
4635 contents = post_thread_continuation.get('contents')
4636 if not isinstance(contents, list):
4637 return
4638 for content in contents:
4639 renderer = content.get('backstagePostThreadRenderer')
4640 if isinstance(renderer, dict):
4641 yield from self._post_thread_entries(renderer)
4642 continue
4643 renderer = content.get('videoRenderer')
4644 if isinstance(renderer, dict):
4645 yield self._video_entry(renderer)
4646
4647 r''' # unused
4648 def _rich_grid_entries(self, contents):
4649 for content in contents:
4650 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4651 if video_renderer:
4652 entry = self._video_entry(video_renderer)
4653 if entry:
4654 yield entry
4655 '''
4656
4657 def _report_history_entries(self, renderer):
4658 for url in traverse_obj(renderer, (
4659 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4660 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4661 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4662 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4663
4664 def _extract_entries(self, parent_renderer, continuation_list):
4665 # continuation_list is modified in-place with continuation_list = [continuation_token]
4666 continuation_list[:] = [None]
4667 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4668 for content in contents:
4669 if not isinstance(content, dict):
4670 continue
4671 is_renderer = traverse_obj(
4672 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4673 expected_type=dict)
4674 if not is_renderer:
4675 if content.get('richItemRenderer'):
4676 for entry in self._rich_entries(content['richItemRenderer']):
4677 yield entry
4678 continuation_list[0] = self._extract_continuation(parent_renderer)
4679 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4680 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4681 yield from self._report_history_entries(table)
4682 continuation_list[0] = self._extract_continuation(table)
4683 continue
4684
4685 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4686 for isr_content in isr_contents:
4687 if not isinstance(isr_content, dict):
4688 continue
4689
4690 known_renderers = {
4691 'playlistVideoListRenderer': self._playlist_entries,
4692 'gridRenderer': self._grid_entries,
4693 'reelShelfRenderer': self._grid_entries,
4694 'shelfRenderer': self._shelf_entries,
4695 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4696 'backstagePostThreadRenderer': self._post_thread_entries,
4697 'videoRenderer': lambda x: [self._video_entry(x)],
4698 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4699 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4700 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4701 }
4702 for key, renderer in isr_content.items():
4703 if key not in known_renderers:
4704 continue
4705 for entry in known_renderers[key](renderer):
4706 if entry:
4707 yield entry
4708 continuation_list[0] = self._extract_continuation(renderer)
4709 break
4710
4711 if not continuation_list[0]:
4712 continuation_list[0] = self._extract_continuation(is_renderer)
4713
4714 if not continuation_list[0]:
4715 continuation_list[0] = self._extract_continuation(parent_renderer)
4716
4717 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4718 continuation_list = [None]
4719 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4720 tab_content = try_get(tab, lambda x: x['content'], dict)
4721 if not tab_content:
4722 return
4723 parent_renderer = (
4724 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4725 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4726 yield from extract_entries(parent_renderer)
4727 continuation = continuation_list[0]
4728
4729 for page_num in itertools.count(1):
4730 if not continuation:
4731 break
4732 headers = self.generate_api_headers(
4733 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4734 response = self._extract_response(
4735 item_id=f'{item_id} page {page_num}',
4736 query=continuation, headers=headers, ytcfg=ytcfg,
4737 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4738
4739 if not response:
4740 break
4741 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4742 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4743 visitor_data = self._extract_visitor_data(response) or visitor_data
4744
4745 known_renderers = {
4746 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4747 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4748 'gridVideoRenderer': (self._grid_entries, 'items'),
4749 'gridChannelRenderer': (self._grid_entries, 'items'),
4750 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4751 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4752 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4753 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4754 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4755 'playlistVideoListContinuation': (self._playlist_entries, None),
4756 'gridContinuation': (self._grid_entries, None),
4757 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4758 'sectionListContinuation': (extract_entries, None), # for feeds
4759 }
4760
4761 continuation_items = traverse_obj(response, (
4762 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4763 'appendContinuationItemsAction', 'continuationItems'
4764 ), 'continuationContents', get_all=False)
4765 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4766
4767 video_items_renderer = None
4768 for key in continuation_item.keys():
4769 if key not in known_renderers:
4770 continue
4771 func, parent_key = known_renderers[key]
4772 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4773 continuation_list = [None]
4774 yield from func(video_items_renderer)
4775 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4776
4777 if not video_items_renderer:
4778 break
4779
4780 @staticmethod
4781 def _extract_selected_tab(tabs, fatal=True):
4782 for tab_renderer in tabs:
4783 if tab_renderer.get('selected'):
4784 return tab_renderer
4785 if fatal:
4786 raise ExtractorError('Unable to find selected tab')
4787
4788 @staticmethod
4789 def _extract_tab_renderers(response):
4790 return traverse_obj(
4791 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
4792
4793 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4794 metadata = self._extract_metadata_from_tabs(item_id, data)
4795
4796 selected_tab = self._extract_selected_tab(tabs)
4797 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4798 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4799
4800 return self.playlist_result(
4801 self._entries(
4802 selected_tab, metadata['id'], ytcfg,
4803 self._extract_account_syncid(ytcfg, data),
4804 self._extract_visitor_data(data, ytcfg)),
4805 **metadata)
4806
4807 def _extract_metadata_from_tabs(self, item_id, data):
4808 info = {'id': item_id}
4809
4810 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
4811 if metadata_renderer:
4812 info.update({
4813 'uploader': metadata_renderer.get('title'),
4814 'uploader_id': metadata_renderer.get('externalId'),
4815 'uploader_url': metadata_renderer.get('channelUrl'),
4816 })
4817 if info['uploader_id']:
4818 info['id'] = info['uploader_id']
4819 else:
4820 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
4821
4822 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4823 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4824 def _get_uncropped(url):
4825 return url_or_none((url or '').split('=')[0] + '=s0')
4826
4827 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
4828 if avatar_thumbnails:
4829 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4830 if uncropped_avatar:
4831 avatar_thumbnails.append({
4832 'url': uncropped_avatar,
4833 'id': 'avatar_uncropped',
4834 'preference': 1
4835 })
4836
4837 channel_banners = self._extract_thumbnails(
4838 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4839 for banner in channel_banners:
4840 banner['preference'] = -10
4841
4842 if channel_banners:
4843 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4844 if uncropped_banner:
4845 channel_banners.append({
4846 'url': uncropped_banner,
4847 'id': 'banner_uncropped',
4848 'preference': -5
4849 })
4850
4851 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4852 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4853 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4854
4855 primary_thumbnails = self._extract_thumbnails(
4856 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4857 playlist_thumbnails = self._extract_thumbnails(
4858 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4859
4860 info.update({
4861 'title': (traverse_obj(metadata_renderer, 'title')
4862 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4863 or info['id']),
4864 'availability': self._extract_availability(data),
4865 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4866 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4867 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4868 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4869 })
4870
4871 # Playlist stats is a text runs array containing [video count, view count, last updated].
4872 # last updated or (view count and last updated) may be missing.
4873 playlist_stats = get_first(
4874 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4875
4876 last_updated_unix = self._parse_time_text(
4877 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4878 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4879 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
4880
4881 info['view_count'] = self._get_count(playlist_stats, 1)
4882 if info['view_count'] is None: # 0 is allowed
4883 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4884 if info['view_count'] is None:
4885 info['view_count'] = self._get_count(data, (
4886 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4887 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4888
4889 info['playlist_count'] = self._get_count(playlist_stats, 0)
4890 if info['playlist_count'] is None: # 0 is allowed
4891 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4892
4893 if not info.get('uploader_id'):
4894 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4895 if not owner: # Deprecated
4896 owner = traverse_obj(
4897 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4898 ('videoOwner', 'videoOwnerRenderer', 'title'))
4899 owner_text = self._get_text(owner)
4900 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4901 info.update({
4902 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4903 'uploader_id': browse_ep.get('browseId'),
4904 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4905 })
4906
4907 info.update({
4908 'channel': info['uploader'],
4909 'channel_id': info['uploader_id'],
4910 'channel_url': info['uploader_url']
4911 })
4912 return info
4913
4914 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4915 first_id = last_id = response = None
4916 for page_num in itertools.count(1):
4917 videos = list(self._playlist_entries(playlist))
4918 if not videos:
4919 return
4920 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4921 if start >= len(videos):
4922 return
4923 yield from videos[start:]
4924 first_id = first_id or videos[0]['id']
4925 last_id = videos[-1]['id']
4926 watch_endpoint = try_get(
4927 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4928 headers = self.generate_api_headers(
4929 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4930 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4931 query = {
4932 'playlistId': playlist_id,
4933 'videoId': watch_endpoint.get('videoId') or last_id,
4934 'index': watch_endpoint.get('index') or len(videos),
4935 'params': watch_endpoint.get('params') or 'OAE%3D'
4936 }
4937 response = self._extract_response(
4938 item_id='%s page %d' % (playlist_id, page_num),
4939 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4940 check_get_keys='contents'
4941 )
4942 playlist = try_get(
4943 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4944
4945 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4946 title = playlist.get('title') or try_get(
4947 data, lambda x: x['titleText']['simpleText'], str)
4948 playlist_id = playlist.get('playlistId') or item_id
4949
4950 # Delegating everything except mix playlists to regular tab-based playlist URL
4951 playlist_url = urljoin(url, try_get(
4952 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4953 str))
4954
4955 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4956 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4957 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4958
4959 if playlist_url and playlist_url != url and not is_known_unviewable:
4960 return self.url_result(
4961 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4962 video_title=title)
4963
4964 return self.playlist_result(
4965 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4966 playlist_id=playlist_id, playlist_title=title)
4967
4968 def _extract_availability(self, data):
4969 """
4970 Gets the availability of a given playlist/tab.
4971 Note: Unless YouTube tells us explicitly, we do not assume it is public
4972 @param data: response
4973 """
4974 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4975 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4976 player_header_privacy = playlist_header_renderer.get('privacy')
4977
4978 badges = self._extract_badges(sidebar_renderer)
4979
4980 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4981 privacy_setting_icon = get_first(
4982 (playlist_header_renderer, sidebar_renderer),
4983 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4984 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4985 expected_type=str)
4986
4987 microformats_is_unlisted = traverse_obj(
4988 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
4989
4990 return (
4991 'public' if (
4992 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4993 or player_header_privacy == 'PUBLIC'
4994 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4995 else self._availability(
4996 is_private=(
4997 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4998 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4999 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5000 is_unlisted=(
5001 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5002 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
5003 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5004 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
5005 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5006 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5007 needs_auth=False))
5008
5009 @staticmethod
5010 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5011 sidebar_renderer = try_get(
5012 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5013 for item in sidebar_renderer:
5014 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5015 if renderer:
5016 return renderer
5017
5018 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
5019 """
5020 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5021 """
5022 is_playlist = bool(traverse_obj(
5023 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5024 if not is_playlist:
5025 return
5026 headers = self.generate_api_headers(
5027 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5028 visitor_data=self._extract_visitor_data(data, ytcfg))
5029 query = {
5030 'params': 'wgYCCAA=',
5031 'browseId': f'VL{item_id}'
5032 }
5033 return self._extract_response(
5034 item_id=item_id, headers=headers, query=query,
5035 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
5036 note='Redownloading playlist API JSON with unavailable videos')
5037
5038 @functools.cached_property
5039 def skip_webpage(self):
5040 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5041
5042 def _extract_webpage(self, url, item_id, fatal=True):
5043 webpage, data = None, None
5044 for retry in self.RetryManager(fatal=fatal):
5045 try:
5046 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
5047 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5048 except ExtractorError as e:
5049 if isinstance(e.cause, network_exceptions):
5050 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
5051 retry.error = e
5052 continue
5053 self._error_or_warning(e, fatal=fatal)
5054 break
5055
5056 try:
5057 self._extract_and_report_alerts(data)
5058 except ExtractorError as e:
5059 self._error_or_warning(e, fatal=fatal)
5060 break
5061
5062 # Sometimes youtube returns a webpage with incomplete ytInitialData
5063 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5064 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5065 retry.error = ExtractorError('Incomplete yt initial data received')
5066 continue
5067
5068 return webpage, data
5069
5070 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5071 """Use if failed to extract ytcfg (and data) from initial webpage"""
5072 if not ytcfg and self.is_authenticated:
5073 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5074 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5075 raise ExtractorError(
5076 f'{msg}. If you are not downloading private content, or '
5077 'your cookies are only for the first account and channel,'
5078 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5079 expected=True)
5080 self.report_warning(msg, only_once=True)
5081
5082 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5083 data = None
5084 if not self.skip_webpage:
5085 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5086 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
5087 # Reject webpage data if redirected to home page without explicitly requesting
5088 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
5089 if (url != 'https://www.youtube.com/feed/recommended'
5090 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5091 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5092 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5093 if fatal:
5094 raise ExtractorError(msg, expected=True)
5095 self.report_warning(msg, only_once=True)
5096 if not data:
5097 self._report_playlist_authcheck(ytcfg, fatal=fatal)
5098 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5099 return data, ytcfg
5100
5101 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5102 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5103 resolve_response = self._extract_response(
5104 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5105 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5106 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5107 for ep_key, ep in endpoints.items():
5108 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5109 if params:
5110 return self._extract_response(
5111 item_id=item_id, query=params, ep=ep, headers=headers,
5112 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
5113 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5114 err_note = 'Failed to resolve url (does the playlist exist?)'
5115 if fatal:
5116 raise ExtractorError(err_note, expected=True)
5117 self.report_warning(err_note, item_id)
5118
5119 _SEARCH_PARAMS = None
5120
5121 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
5122 data = {'query': query}
5123 if params is NO_DEFAULT:
5124 params = self._SEARCH_PARAMS
5125 if params:
5126 data['params'] = params
5127
5128 content_keys = (
5129 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5130 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5131 # ytmusic search
5132 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5133 ('continuationContents', ),
5134 )
5135 display_id = f'query "{query}"'
5136 check_get_keys = tuple({keys[0] for keys in content_keys})
5137 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5138 self._report_playlist_authcheck(ytcfg, fatal=False)
5139
5140 continuation_list = [None]
5141 search = None
5142 for page_num in itertools.count(1):
5143 data.update(continuation_list[0] or {})
5144 headers = self.generate_api_headers(
5145 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
5146 search = self._extract_response(
5147 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5148 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
5149 slr_contents = traverse_obj(search, *content_keys)
5150 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
5151 if not continuation_list[0]:
5152 break
5153
5154
5155 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5156 IE_DESC = 'YouTube Tabs'
5157 _VALID_URL = r'''(?x:
5158 https?://
5159 (?!consent\.)(?:\w+\.)?
5160 (?:
5161 youtube(?:kids)?\.com|
5162 %(invidious)s
5163 )/
5164 (?:
5165 (?P<channel_type>channel|c|user|browse)/|
5166 (?P<not_channel>
5167 feed/|hashtag/|
5168 (?:playlist|watch)\?.*?\blist=
5169 )|
5170 (?!(?:%(reserved_names)s)\b) # Direct URLs
5171 )
5172 (?P<id>[^/?\#&]+)
5173 )''' % {
5174 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5175 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5176 }
5177 IE_NAME = 'youtube:tab'
5178
5179 _TESTS = [{
5180 'note': 'playlists, multipage',
5181 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5182 'playlist_mincount': 94,
5183 'info_dict': {
5184 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5185 'title': 'Igor Kleiner - Playlists',
5186 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5187 'uploader': 'Igor Kleiner',
5188 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5189 'channel': 'Igor Kleiner',
5190 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5191 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5192 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5193 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5194 'channel_follower_count': int
5195 },
5196 }, {
5197 'note': 'playlists, multipage, different order',
5198 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5199 'playlist_mincount': 94,
5200 'info_dict': {
5201 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5202 'title': 'Igor Kleiner - Playlists',
5203 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5204 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5205 'uploader': 'Igor Kleiner',
5206 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5207 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5208 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5209 'channel': 'Igor Kleiner',
5210 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5211 'channel_follower_count': int
5212 },
5213 }, {
5214 'note': 'playlists, series',
5215 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5216 'playlist_mincount': 5,
5217 'info_dict': {
5218 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5219 'title': '3Blue1Brown - Playlists',
5220 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5221 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5222 'uploader': '3Blue1Brown',
5223 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5224 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5225 'channel': '3Blue1Brown',
5226 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5227 'tags': ['Mathematics'],
5228 'channel_follower_count': int
5229 },
5230 }, {
5231 'note': 'playlists, singlepage',
5232 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5233 'playlist_mincount': 4,
5234 'info_dict': {
5235 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5236 'title': 'ThirstForScience - Playlists',
5237 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5238 'uploader': 'ThirstForScience',
5239 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5240 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5241 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5242 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5243 'tags': 'count:13',
5244 'channel': 'ThirstForScience',
5245 'channel_follower_count': int
5246 }
5247 }, {
5248 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5249 'only_matching': True,
5250 }, {
5251 'note': 'basic, single video playlist',
5252 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5253 'info_dict': {
5254 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5255 'uploader': 'Sergey M.',
5256 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5257 'title': 'youtube-dl public playlist',
5258 'description': '',
5259 'tags': [],
5260 'view_count': int,
5261 'modified_date': '20201130',
5262 'channel': 'Sergey M.',
5263 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5264 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5265 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5266 'availability': 'public',
5267 },
5268 'playlist_count': 1,
5269 }, {
5270 'note': 'empty playlist',
5271 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5272 'info_dict': {
5273 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5274 'uploader': 'Sergey M.',
5275 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5276 'title': 'youtube-dl empty playlist',
5277 'tags': [],
5278 'channel': 'Sergey M.',
5279 'description': '',
5280 'modified_date': '20160902',
5281 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5282 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5283 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5284 'availability': 'public',
5285 },
5286 'playlist_count': 0,
5287 }, {
5288 'note': 'Home tab',
5289 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5290 'info_dict': {
5291 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5292 'title': 'lex will - Home',
5293 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5294 'uploader': 'lex will',
5295 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5296 'channel': 'lex will',
5297 'tags': ['bible', 'history', 'prophesy'],
5298 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5299 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5300 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5301 'channel_follower_count': int
5302 },
5303 'playlist_mincount': 2,
5304 }, {
5305 'note': 'Videos tab',
5306 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5307 'info_dict': {
5308 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5309 'title': 'lex will - Videos',
5310 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5311 'uploader': 'lex will',
5312 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5313 'tags': ['bible', 'history', 'prophesy'],
5314 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5315 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5316 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5317 'channel': 'lex will',
5318 'channel_follower_count': int
5319 },
5320 'playlist_mincount': 975,
5321 }, {
5322 'note': 'Videos tab, sorted by popular',
5323 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5324 'info_dict': {
5325 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5326 'title': 'lex will - Videos',
5327 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5328 'uploader': 'lex will',
5329 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5330 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5331 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5332 'channel': 'lex will',
5333 'tags': ['bible', 'history', 'prophesy'],
5334 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5335 'channel_follower_count': int
5336 },
5337 'playlist_mincount': 199,
5338 }, {
5339 'note': 'Playlists tab',
5340 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5341 'info_dict': {
5342 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5343 'title': 'lex will - Playlists',
5344 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5345 'uploader': 'lex will',
5346 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5347 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5348 'channel': 'lex will',
5349 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5350 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5351 'tags': ['bible', 'history', 'prophesy'],
5352 'channel_follower_count': int
5353 },
5354 'playlist_mincount': 17,
5355 }, {
5356 'note': 'Community tab',
5357 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5358 'info_dict': {
5359 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5360 'title': 'lex will - Community',
5361 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5362 'uploader': 'lex will',
5363 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5364 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5365 'channel': 'lex will',
5366 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5367 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5368 'tags': ['bible', 'history', 'prophesy'],
5369 'channel_follower_count': int
5370 },
5371 'playlist_mincount': 18,
5372 }, {
5373 'note': 'Channels tab',
5374 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5375 'info_dict': {
5376 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5377 'title': 'lex will - Channels',
5378 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5379 'uploader': 'lex will',
5380 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5381 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5382 'channel': 'lex will',
5383 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5384 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5385 'tags': ['bible', 'history', 'prophesy'],
5386 'channel_follower_count': int
5387 },
5388 'playlist_mincount': 12,
5389 }, {
5390 'note': 'Search tab',
5391 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5392 'playlist_mincount': 40,
5393 'info_dict': {
5394 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5395 'title': '3Blue1Brown - Search - linear algebra',
5396 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5397 'uploader': '3Blue1Brown',
5398 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5399 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5400 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5401 'tags': ['Mathematics'],
5402 'channel': '3Blue1Brown',
5403 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5404 'channel_follower_count': int
5405 },
5406 }, {
5407 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5408 'only_matching': True,
5409 }, {
5410 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5411 'only_matching': True,
5412 }, {
5413 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5414 'only_matching': True,
5415 }, {
5416 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5417 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5418 'info_dict': {
5419 'title': '29C3: Not my department',
5420 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5421 'uploader': 'Christiaan008',
5422 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5423 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5424 'tags': [],
5425 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5426 'view_count': int,
5427 'modified_date': '20150605',
5428 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5429 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5430 'channel': 'Christiaan008',
5431 'availability': 'public',
5432 },
5433 'playlist_count': 96,
5434 }, {
5435 'note': 'Large playlist',
5436 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5437 'info_dict': {
5438 'title': 'Uploads from Cauchemar',
5439 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5440 'uploader': 'Cauchemar',
5441 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5442 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5443 'tags': [],
5444 'modified_date': r're:\d{8}',
5445 'channel': 'Cauchemar',
5446 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5447 'view_count': int,
5448 'description': '',
5449 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5450 'availability': 'public',
5451 },
5452 'playlist_mincount': 1123,
5453 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5454 }, {
5455 'note': 'even larger playlist, 8832 videos',
5456 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5457 'only_matching': True,
5458 }, {
5459 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5460 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5461 'info_dict': {
5462 'title': 'Uploads from Interstellar Movie',
5463 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5464 'uploader': 'Interstellar Movie',
5465 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5466 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5467 'tags': [],
5468 'view_count': int,
5469 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5470 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5471 'channel': 'Interstellar Movie',
5472 'description': '',
5473 'modified_date': r're:\d{8}',
5474 'availability': 'public',
5475 },
5476 'playlist_mincount': 21,
5477 }, {
5478 'note': 'Playlist with "show unavailable videos" button',
5479 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5480 'info_dict': {
5481 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5482 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5483 'uploader': 'Phim Siêu Nhân Nhật Bản',
5484 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5485 'view_count': int,
5486 'channel': 'Phim Siêu Nhân Nhật Bản',
5487 'tags': [],
5488 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5489 'description': '',
5490 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5491 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5492 'modified_date': r're:\d{8}',
5493 'availability': 'public',
5494 },
5495 'playlist_mincount': 200,
5496 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5497 }, {
5498 'note': 'Playlist with unavailable videos in page 7',
5499 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5500 'info_dict': {
5501 'title': 'Uploads from BlankTV',
5502 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5503 'uploader': 'BlankTV',
5504 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5505 'channel': 'BlankTV',
5506 'channel_url': 'https://www.youtube.com/c/blanktv',
5507 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5508 'view_count': int,
5509 'tags': [],
5510 'uploader_url': 'https://www.youtube.com/c/blanktv',
5511 'modified_date': r're:\d{8}',
5512 'description': '',
5513 'availability': 'public',
5514 },
5515 'playlist_mincount': 1000,
5516 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5517 }, {
5518 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5519 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5520 'info_dict': {
5521 'title': 'Data Analysis with Dr Mike Pound',
5522 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5523 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5524 'uploader': 'Computerphile',
5525 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5526 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5527 'tags': [],
5528 'view_count': int,
5529 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5530 'channel_url': 'https://www.youtube.com/user/Computerphile',
5531 'channel': 'Computerphile',
5532 'availability': 'public',
5533 'modified_date': '20190712',
5534 },
5535 'playlist_mincount': 11,
5536 }, {
5537 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5538 'only_matching': True,
5539 }, {
5540 'note': 'Playlist URL that does not actually serve a playlist',
5541 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5542 'info_dict': {
5543 'id': 'FqZTN594JQw',
5544 'ext': 'webm',
5545 'title': "Smiley's People 01 detective, Adventure Series, Action",
5546 'uploader': 'STREEM',
5547 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5548 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5549 'upload_date': '20150526',
5550 'license': 'Standard YouTube License',
5551 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5552 'categories': ['People & Blogs'],
5553 'tags': list,
5554 'view_count': int,
5555 'like_count': int,
5556 },
5557 'params': {
5558 'skip_download': True,
5559 },
5560 'skip': 'This video is not available.',
5561 'add_ie': [YoutubeIE.ie_key()],
5562 }, {
5563 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5564 'only_matching': True,
5565 }, {
5566 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5567 'only_matching': True,
5568 }, {
5569 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5570 'info_dict': {
5571 'id': 'Wq15eF5vCbI', # This will keep changing
5572 'ext': 'mp4',
5573 'title': str,
5574 'uploader': 'Sky News',
5575 'uploader_id': 'skynews',
5576 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5577 'upload_date': r're:\d{8}',
5578 'description': str,
5579 'categories': ['News & Politics'],
5580 'tags': list,
5581 'like_count': int,
5582 'release_timestamp': int,
5583 'channel': 'Sky News',
5584 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5585 'age_limit': 0,
5586 'view_count': int,
5587 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5588 'playable_in_embed': True,
5589 'release_date': r're:\d+',
5590 'availability': 'public',
5591 'live_status': 'is_live',
5592 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5593 'channel_follower_count': int,
5594 'concurrent_view_count': int,
5595 },
5596 'params': {
5597 'skip_download': True,
5598 },
5599 'expected_warnings': ['Ignoring subtitle tracks found in '],
5600 }, {
5601 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5602 'info_dict': {
5603 'id': 'a48o2S1cPoo',
5604 'ext': 'mp4',
5605 'title': 'The Young Turks - Live Main Show',
5606 'uploader': 'The Young Turks',
5607 'uploader_id': 'TheYoungTurks',
5608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5609 'upload_date': '20150715',
5610 'license': 'Standard YouTube License',
5611 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5612 'categories': ['News & Politics'],
5613 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5614 'like_count': int,
5615 },
5616 'params': {
5617 'skip_download': True,
5618 },
5619 'only_matching': True,
5620 }, {
5621 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5622 'only_matching': True,
5623 }, {
5624 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5625 'only_matching': True,
5626 }, {
5627 'note': 'A channel that is not live. Should raise error',
5628 'url': 'https://www.youtube.com/user/numberphile/live',
5629 'only_matching': True,
5630 }, {
5631 'url': 'https://www.youtube.com/feed/trending',
5632 'only_matching': True,
5633 }, {
5634 'url': 'https://www.youtube.com/feed/library',
5635 'only_matching': True,
5636 }, {
5637 'url': 'https://www.youtube.com/feed/history',
5638 'only_matching': True,
5639 }, {
5640 'url': 'https://www.youtube.com/feed/subscriptions',
5641 'only_matching': True,
5642 }, {
5643 'url': 'https://www.youtube.com/feed/watch_later',
5644 'only_matching': True,
5645 }, {
5646 'note': 'Recommended - redirects to home page.',
5647 'url': 'https://www.youtube.com/feed/recommended',
5648 'only_matching': True,
5649 }, {
5650 'note': 'inline playlist with not always working continuations',
5651 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5652 'only_matching': True,
5653 }, {
5654 'url': 'https://www.youtube.com/course',
5655 'only_matching': True,
5656 }, {
5657 'url': 'https://www.youtube.com/zsecurity',
5658 'only_matching': True,
5659 }, {
5660 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5661 'only_matching': True,
5662 }, {
5663 'url': 'https://www.youtube.com/TheYoungTurks/live',
5664 'only_matching': True,
5665 }, {
5666 'url': 'https://www.youtube.com/hashtag/cctv9',
5667 'info_dict': {
5668 'id': 'cctv9',
5669 'title': '#cctv9',
5670 'tags': [],
5671 },
5672 'playlist_mincount': 300, # not consistent but should be over 300
5673 }, {
5674 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5675 'only_matching': True,
5676 }, {
5677 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5678 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5679 'only_matching': True
5680 }, {
5681 'note': '/browse/ should redirect to /channel/',
5682 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5683 'only_matching': True
5684 }, {
5685 'note': 'VLPL, should redirect to playlist?list=PL...',
5686 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5687 'info_dict': {
5688 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5689 'uploader': 'NoCopyrightSounds',
5690 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5691 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5692 'title': 'NCS : All Releases 💿',
5693 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5694 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5695 'modified_date': r're:\d{8}',
5696 'view_count': int,
5697 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5698 'tags': [],
5699 'channel': 'NoCopyrightSounds',
5700 'availability': 'public',
5701 },
5702 'playlist_mincount': 166,
5703 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5704 }, {
5705 'note': 'Topic, should redirect to playlist?list=UU...',
5706 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5707 'info_dict': {
5708 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5709 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5710 'title': 'Uploads from Royalty Free Music - Topic',
5711 'uploader': 'Royalty Free Music - Topic',
5712 'tags': [],
5713 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5714 'channel': 'Royalty Free Music - Topic',
5715 'view_count': int,
5716 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5717 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5718 'modified_date': r're:\d{8}',
5719 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5720 'description': '',
5721 'availability': 'public',
5722 },
5723 'playlist_mincount': 101,
5724 }, {
5725 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5726 # Treat as a general feed
5727 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5728 'info_dict': {
5729 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5730 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5731 'tags': [],
5732 },
5733 'playlist_mincount': 9,
5734 }, {
5735 'note': 'Youtube music Album',
5736 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5737 'info_dict': {
5738 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5739 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5740 'tags': [],
5741 'view_count': int,
5742 'description': '',
5743 'availability': 'unlisted',
5744 'modified_date': r're:\d{8}',
5745 },
5746 'playlist_count': 50,
5747 }, {
5748 'note': 'unlisted single video playlist',
5749 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5750 'info_dict': {
5751 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5752 'uploader': 'colethedj',
5753 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5754 'title': 'yt-dlp unlisted playlist test',
5755 'availability': 'unlisted',
5756 'tags': [],
5757 'modified_date': '20220418',
5758 'channel': 'colethedj',
5759 'view_count': int,
5760 'description': '',
5761 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5762 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5763 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5764 },
5765 'playlist_count': 1,
5766 }, {
5767 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5768 'url': 'https://www.youtube.com/feed/recommended',
5769 'info_dict': {
5770 'id': 'recommended',
5771 'title': 'recommended',
5772 'tags': [],
5773 },
5774 'playlist_mincount': 50,
5775 'params': {
5776 'skip_download': True,
5777 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5778 },
5779 }, {
5780 'note': 'API Fallback: /videos tab, sorted by oldest first',
5781 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5782 'info_dict': {
5783 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5784 'title': 'Cody\'sLab - Videos',
5785 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5786 'uploader': 'Cody\'sLab',
5787 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5788 'channel': 'Cody\'sLab',
5789 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5790 'tags': [],
5791 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5792 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5793 'channel_follower_count': int
5794 },
5795 'playlist_mincount': 650,
5796 'params': {
5797 'skip_download': True,
5798 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5799 },
5800 'skip': 'Query for sorting no longer works',
5801 }, {
5802 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5803 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5804 'info_dict': {
5805 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5806 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5807 'title': 'Uploads from Royalty Free Music - Topic',
5808 'uploader': 'Royalty Free Music - Topic',
5809 'modified_date': r're:\d{8}',
5810 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5811 'description': '',
5812 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5813 'tags': [],
5814 'channel': 'Royalty Free Music - Topic',
5815 'view_count': int,
5816 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5817 'availability': 'public',
5818 },
5819 'playlist_mincount': 101,
5820 'params': {
5821 'skip_download': True,
5822 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5823 },
5824 }, {
5825 'note': 'non-standard redirect to regional channel',
5826 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5827 'only_matching': True
5828 }, {
5829 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5830 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5831 'info_dict': {
5832 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5833 'modified_date': '20220407',
5834 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5835 'tags': [],
5836 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5837 'uploader': 'pukkandan',
5838 'availability': 'unlisted',
5839 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5840 'channel': 'pukkandan',
5841 'description': 'Test for collaborative playlist',
5842 'title': 'yt-dlp test - collaborative playlist',
5843 'view_count': int,
5844 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5845 },
5846 'playlist_mincount': 2
5847 }, {
5848 'note': 'translated tab name',
5849 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5850 'info_dict': {
5851 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5852 'tags': [],
5853 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5854 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5855 'description': 'test description',
5856 'title': 'cole-dlp-test-acc - 再生リスト',
5857 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5858 'uploader': 'cole-dlp-test-acc',
5859 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5860 'channel': 'cole-dlp-test-acc',
5861 },
5862 'playlist_mincount': 1,
5863 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5864 'expected_warnings': ['Preferring "ja"'],
5865 }, {
5866 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5867 'note': 'preferred lang set with playlist with translated video titles',
5868 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5869 'info_dict': {
5870 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5871 'tags': [],
5872 'view_count': int,
5873 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5874 'uploader': 'cole-dlp-test-acc',
5875 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5876 'channel': 'cole-dlp-test-acc',
5877 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5878 'description': 'test',
5879 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5880 'title': 'dlp test playlist',
5881 'availability': 'public',
5882 },
5883 'playlist_mincount': 1,
5884 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5885 'expected_warnings': ['Preferring "ja"'],
5886 }, {
5887 # shorts audio pivot for 2GtVksBMYFM.
5888 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5889 'info_dict': {
5890 'id': 'sfv_audio_pivot',
5891 'title': 'sfv_audio_pivot',
5892 'tags': [],
5893 },
5894 'playlist_mincount': 50,
5895
5896 }, {
5897 # Channel with a real live tab (not to be mistaken with streams tab)
5898 # Do not treat like it should redirect to live stream
5899 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5900 'info_dict': {
5901 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5902 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5903 'tags': [],
5904 },
5905 'playlist_mincount': 20,
5906 }, {
5907 # Tab name is not the same as tab id
5908 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5909 'info_dict': {
5910 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5911 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5912 'tags': [],
5913 },
5914 'playlist_mincount': 8,
5915 }, {
5916 # Home tab id is literally home. Not to get mistaken with featured
5917 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5918 'info_dict': {
5919 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5920 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5921 'tags': [],
5922 },
5923 'playlist_mincount': 8,
5924 }, {
5925 # Should get three playlists for videos, shorts and streams tabs
5926 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5927 'info_dict': {
5928 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5929 'title': 'Polka Ch. 尾丸ポルカ',
5930 'channel_follower_count': int,
5931 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5932 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5933 'uploader': 'Polka Ch. 尾丸ポルカ',
5934 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5935 'channel': 'Polka Ch. 尾丸ポルカ',
5936 'tags': 'count:35',
5937 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5938 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5939 },
5940 'playlist_count': 3,
5941 }, {
5942 # Shorts tab with channel with handle
5943 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5944 'info_dict': {
5945 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5946 'title': 'Not Just Bikes - Shorts',
5947 'tags': 'count:12',
5948 'uploader': 'Not Just Bikes',
5949 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5950 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5951 'channel_follower_count': int,
5952 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5953 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5954 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5955 'channel': 'Not Just Bikes',
5956 },
5957 'playlist_mincount': 10,
5958 }, {
5959 # Streams tab
5960 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5961 'info_dict': {
5962 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5963 'title': '中村悠一 - Live',
5964 'tags': 'count:7',
5965 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5966 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5967 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5968 'channel': '中村悠一',
5969 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5970 'channel_follower_count': int,
5971 'uploader': '中村悠一',
5972 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5973 },
5974 'playlist_mincount': 60,
5975 }, {
5976 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5977 # See test_youtube_lists
5978 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5979 'only_matching': True,
5980 }, {
5981 # No uploads and no UCID given. Should fail with no uploads error
5982 # See test_youtube_lists
5983 'url': 'https://www.youtube.com/news',
5984 'only_matching': True
5985 }, {
5986 # No videos tab but has a shorts tab
5987 'url': 'https://www.youtube.com/c/TKFShorts',
5988 'info_dict': {
5989 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5990 'title': 'Shorts Break - Shorts',
5991 'tags': 'count:32',
5992 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5993 'channel': 'Shorts Break',
5994 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5995 'uploader': 'Shorts Break',
5996 'channel_follower_count': int,
5997 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5998 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5999 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6000 },
6001 'playlist_mincount': 30,
6002 }, {
6003 # Trending Now Tab. tab id is empty
6004 'url': 'https://www.youtube.com/feed/trending',
6005 'info_dict': {
6006 'id': 'trending',
6007 'title': 'trending - Now',
6008 'tags': [],
6009 },
6010 'playlist_mincount': 30,
6011 }, {
6012 # Trending Gaming Tab. tab id is empty
6013 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6014 'info_dict': {
6015 'id': 'trending',
6016 'title': 'trending - Gaming',
6017 'tags': [],
6018 },
6019 'playlist_mincount': 30,
6020 }, {
6021 # Shorts url result in shorts tab
6022 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6023 'info_dict': {
6024 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6025 'title': 'cole-dlp-test-acc - Shorts',
6026 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6027 'channel': 'cole-dlp-test-acc',
6028 'description': 'test description',
6029 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6030 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6031 'tags': [],
6032 'uploader': 'cole-dlp-test-acc',
6033 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6034
6035 },
6036 'playlist': [{
6037 'info_dict': {
6038 '_type': 'url',
6039 'ie_key': 'Youtube',
6040 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6041 'id': 'sSM9J5YH_60',
6042 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6043 'title': 'SHORT short',
6044 'channel': 'cole-dlp-test-acc',
6045 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6046 'view_count': int,
6047 'thumbnails': list,
6048 }
6049 }],
6050 'params': {'extract_flat': True},
6051 }, {
6052 # Live video status should be extracted
6053 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6054 'info_dict': {
6055 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6056 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6057 'tags': []
6058 },
6059 'playlist': [{
6060 'info_dict': {
6061 '_type': 'url',
6062 'ie_key': 'Youtube',
6063 'url': 'startswith:https://www.youtube.com/watch?v=',
6064 'id': str,
6065 'title': str,
6066 'live_status': 'is_live',
6067 'channel_id': str,
6068 'channel_url': str,
6069 'concurrent_view_count': int,
6070 'channel': str,
6071 }
6072 }],
6073 'params': {'extract_flat': True, 'playlist_items': '1'},
6074 'playlist_mincount': 1
6075 }, {
6076 # Channel renderer metadata. Contains number of videos on the channel
6077 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6078 'info_dict': {
6079 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6080 'title': 'cole-dlp-test-acc - Channels',
6081 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6082 'channel': 'cole-dlp-test-acc',
6083 'description': 'test description',
6084 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6085 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6086 'tags': [],
6087 'uploader': 'cole-dlp-test-acc',
6088 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6089
6090 },
6091 'playlist': [{
6092 'info_dict': {
6093 '_type': 'url',
6094 'ie_key': 'YoutubeTab',
6095 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6096 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6097 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6098 'title': 'PewDiePie',
6099 'channel': 'PewDiePie',
6100 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6101 'thumbnails': list,
6102 'channel_follower_count': int,
6103 'playlist_count': int
6104 }
6105 }],
6106 'params': {'extract_flat': True},
6107 }, {
6108 'url': 'https://www.youtube.com/@3blue1brown/about',
6109 'info_dict': {
6110 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6111 'tags': ['Mathematics'],
6112 'title': '3Blue1Brown - About',
6113 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6114 'channel_follower_count': int,
6115 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6116 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6117 'channel': '3Blue1Brown',
6118 'uploader': '3Blue1Brown',
6119 'view_count': int,
6120 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6121 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6122 },
6123 'playlist_count': 0,
6124 }]
6125
6126 @classmethod
6127 def suitable(cls, url):
6128 return False if YoutubeIE.suitable(url) else super().suitable(url)
6129
6130 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6131
6132 def _get_url_mobj(self, url):
6133 mobj = self._URL_RE.match(url).groupdict()
6134 mobj.update((k, '') for k, v in mobj.items() if v is None)
6135 return mobj
6136
6137 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6138 tab_name = (tab.get('title') or '').lower()
6139 tab_url = urljoin(base_url, traverse_obj(
6140 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6141
6142 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6143 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
6144 if tab_id:
6145 return {
6146 'TAB_ID_SPONSORSHIPS': 'membership',
6147 }.get(tab_id, tab_id), tab_name
6148
6149 # Fallback to tab name if we cannot get the tab id.
6150 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6151 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6152 if tab_name:
6153 self.write_debug(f'Falling back to selected tab name: {tab_name}')
6154 return {
6155 'home': 'featured',
6156 'live': 'streams',
6157 }.get(tab_name, tab_name), tab_name
6158
6159 def _has_tab(self, tabs, tab_id):
6160 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
6161
6162 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6163 def _real_extract(self, url, smuggled_data):
6164 item_id = self._match_id(url)
6165 url = urllib.parse.urlunparse(
6166 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
6167 compat_opts = self.get_param('compat_opts', [])
6168
6169 mobj = self._get_url_mobj(url)
6170 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
6171 if is_channel and smuggled_data.get('is_music_url'):
6172 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6173 return self.url_result(
6174 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6175 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6176 mdata = self._extract_tab_endpoint(
6177 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6178 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6179 get_all=False, expected_type=str)
6180 if not murl:
6181 raise ExtractorError('Failed to resolve album to playlist')
6182 return self.url_result(murl, YoutubeTabIE)
6183 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6184 return self.url_result(
6185 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6186
6187 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
6188 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
6189 url = f'{pre}/videos{post}'
6190 if smuggled_data.get('is_music_url'):
6191 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
6192
6193 # Handle both video/playlist URLs
6194 qs = parse_qs(url)
6195 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
6196 if not video_id and mobj['not_channel'].startswith('watch'):
6197 if not playlist_id:
6198 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6199 raise ExtractorError('A video URL was given without video ID', expected=True)
6200 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6201 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6202 return self.url_result(
6203 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
6204
6205 if not self._yes_playlist(playlist_id, video_id):
6206 return self.url_result(
6207 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6208
6209 data, ytcfg = self._extract_data(url, display_id)
6210
6211 # YouTube may provide a non-standard redirect to the regional channel
6212 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6213 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6214 redirect_url = traverse_obj(
6215 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6216 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
6217 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
6218 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6219 return self.url_result(redirect_url, YoutubeTabIE)
6220
6221 tabs, extra_tabs = self._extract_tab_renderers(data), []
6222 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
6223 selected_tab = self._extract_selected_tab(tabs)
6224 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6225 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6226
6227 if not original_tab_id and selected_tab_name:
6228 self.to_screen('Downloading all uploads of the channel. '
6229 'To download only the videos in a specific tab, pass the tab\'s URL')
6230 if self._has_tab(tabs, 'streams'):
6231 extra_tabs.append(''.join((pre, '/streams', post)))
6232 if self._has_tab(tabs, 'shorts'):
6233 extra_tabs.append(''.join((pre, '/shorts', post)))
6234 # XXX: Members-only tab should also be extracted
6235
6236 if not extra_tabs and selected_tab_id != 'videos':
6237 # Channel does not have streams, shorts or videos tabs
6238 if item_id[:2] != 'UC':
6239 raise ExtractorError('This channel has no uploads', expected=True)
6240
6241 # Topic channels don't have /videos. Use the equivalent playlist instead
6242 pl_id = f'UU{item_id[2:]}'
6243 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6244 try:
6245 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6246 except ExtractorError:
6247 raise ExtractorError('This channel has no uploads', expected=True)
6248 else:
6249 item_id, url = pl_id, pl_url
6250 self.to_screen(
6251 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6252
6253 elif extra_tabs and selected_tab_id != 'videos':
6254 # When there are shorts/live tabs but not videos tab
6255 url, data = f'{pre}{post}', None
6256
6257 elif (original_tab_id or 'videos') != selected_tab_id:
6258 if original_tab_id == 'live':
6259 # Live tab should have redirected to the video
6260 # Except in the case the channel has an actual live tab
6261 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6262 raise UserNotLive(video_id=item_id)
6263 elif selected_tab_name:
6264 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6265
6266 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6267 url = f'{pre}{post}'
6268
6269 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6270 if 'no-youtube-unavailable-videos' not in compat_opts:
6271 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
6272 self._extract_and_report_alerts(data, only_once=True)
6273
6274 tabs, entries = self._extract_tab_renderers(data), []
6275 if tabs:
6276 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6277 entries[0].update({
6278 'extractor_key': YoutubeTabIE.ie_key(),
6279 'extractor': YoutubeTabIE.IE_NAME,
6280 'webpage_url': url,
6281 })
6282 if self.get_param('playlist_items') == '0':
6283 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6284 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6285 entries.extend(map(self._real_extract, extra_tabs))
6286
6287 if len(entries) == 1:
6288 return entries[0]
6289 elif entries:
6290 metadata = self._extract_metadata_from_tabs(item_id, data)
6291 uploads_url = 'the Uploads (UU) playlist URL'
6292 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6293 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6294 self.to_screen(
6295 'Downloading as multiple playlists, separated by tabs. '
6296 f'To download as a single playlist instead, pass {uploads_url}')
6297 return self.playlist_result(entries, item_id, **metadata)
6298
6299 # Inline playlist
6300 playlist = traverse_obj(
6301 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
6302 if playlist:
6303 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
6304
6305 video_id = traverse_obj(
6306 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
6307 if video_id:
6308 if tab != '/live': # live tab is expected to redirect to video
6309 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
6310 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6311
6312 raise ExtractorError('Unable to recognize tab page')
6313
6314
6315 class YoutubePlaylistIE(InfoExtractor):
6316 IE_DESC = 'YouTube playlists'
6317 _VALID_URL = r'''(?x)(?:
6318 (?:https?://)?
6319 (?:\w+\.)?
6320 (?:
6321 (?:
6322 youtube(?:kids)?\.com|
6323 %(invidious)s
6324 )
6325 /.*?\?.*?\blist=
6326 )?
6327 (?P<id>%(playlist_id)s)
6328 )''' % {
6329 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6330 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6331 }
6332 IE_NAME = 'youtube:playlist'
6333 _TESTS = [{
6334 'note': 'issue #673',
6335 'url': 'PLBB231211A4F62143',
6336 'info_dict': {
6337 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6338 'id': 'PLBB231211A4F62143',
6339 'uploader': 'Wickman',
6340 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6341 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6342 'view_count': int,
6343 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6344 'modified_date': r're:\d{8}',
6345 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6346 'channel': 'Wickman',
6347 'tags': [],
6348 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6349 'availability': 'public',
6350 },
6351 'playlist_mincount': 29,
6352 }, {
6353 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6354 'info_dict': {
6355 'title': 'YDL_safe_search',
6356 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6357 },
6358 'playlist_count': 2,
6359 'skip': 'This playlist is private',
6360 }, {
6361 'note': 'embedded',
6362 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6363 'playlist_count': 4,
6364 'info_dict': {
6365 'title': 'JODA15',
6366 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6367 'uploader': 'milan',
6368 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6369 'description': '',
6370 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6371 'tags': [],
6372 'modified_date': '20140919',
6373 'view_count': int,
6374 'channel': 'milan',
6375 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6376 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6377 'availability': 'public',
6378 },
6379 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
6380 }, {
6381 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6382 'playlist_mincount': 455,
6383 'info_dict': {
6384 'title': '2018 Chinese New Singles (11/6 updated)',
6385 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6386 'uploader': 'LBK',
6387 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6388 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6389 'channel': 'LBK',
6390 'view_count': int,
6391 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6392 'tags': [],
6393 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6394 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6395 'modified_date': r're:\d{8}',
6396 'availability': 'public',
6397 },
6398 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
6399 }, {
6400 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6401 'only_matching': True,
6402 }, {
6403 # music album playlist
6404 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6405 'only_matching': True,
6406 }]
6407
6408 @classmethod
6409 def suitable(cls, url):
6410 if YoutubeTabIE.suitable(url):
6411 return False
6412 from ..utils import parse_qs
6413 qs = parse_qs(url)
6414 if qs.get('v', [None])[0]:
6415 return False
6416 return super().suitable(url)
6417
6418 def _real_extract(self, url):
6419 playlist_id = self._match_id(url)
6420 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
6421 url = update_url_query(
6422 'https://www.youtube.com/playlist',
6423 parse_qs(url) or {'list': playlist_id})
6424 if is_music_url:
6425 url = smuggle_url(url, {'is_music_url': True})
6426 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6427
6428
6429 class YoutubeYtBeIE(InfoExtractor):
6430 IE_DESC = 'youtu.be'
6431 _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}
6432 _TESTS = [{
6433 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6434 'info_dict': {
6435 'id': 'yeWKywCrFtk',
6436 'ext': 'mp4',
6437 'title': 'Small Scale Baler and Braiding Rugs',
6438 'uploader': 'Backus-Page House Museum',
6439 'uploader_id': 'backuspagemuseum',
6440 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6441 'upload_date': '20161008',
6442 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6443 'categories': ['Nonprofits & Activism'],
6444 'tags': list,
6445 'like_count': int,
6446 'age_limit': 0,
6447 'playable_in_embed': True,
6448 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6449 'channel': 'Backus-Page House Museum',
6450 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6451 'live_status': 'not_live',
6452 'view_count': int,
6453 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6454 'availability': 'public',
6455 'duration': 59,
6456 'comment_count': int,
6457 'channel_follower_count': int
6458 },
6459 'params': {
6460 'noplaylist': True,
6461 'skip_download': True,
6462 },
6463 }, {
6464 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6465 'only_matching': True,
6466 }]
6467
6468 def _real_extract(self, url):
6469 mobj = self._match_valid_url(url)
6470 video_id = mobj.group('id')
6471 playlist_id = mobj.group('playlist_id')
6472 return self.url_result(
6473 update_url_query('https://www.youtube.com/watch', {
6474 'v': video_id,
6475 'list': playlist_id,
6476 'feature': 'youtu.be',
6477 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6478
6479
6480 class YoutubeLivestreamEmbedIE(InfoExtractor):
6481 IE_DESC = 'YouTube livestream embeds'
6482 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6483 _TESTS = [{
6484 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6485 'only_matching': True,
6486 }]
6487
6488 def _real_extract(self, url):
6489 channel_id = self._match_id(url)
6490 return self.url_result(
6491 f'https://www.youtube.com/channel/{channel_id}/live',
6492 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6493
6494
6495 class YoutubeYtUserIE(InfoExtractor):
6496 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6497 IE_NAME = 'youtube:user'
6498 _VALID_URL = r'ytuser:(?P<id>.+)'
6499 _TESTS = [{
6500 'url': 'ytuser:phihag',
6501 'only_matching': True,
6502 }]
6503
6504 def _real_extract(self, url):
6505 user_id = self._match_id(url)
6506 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
6507
6508
6509 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6510 IE_NAME = 'youtube:favorites'
6511 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6512 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6513 _LOGIN_REQUIRED = True
6514 _TESTS = [{
6515 'url': ':ytfav',
6516 'only_matching': True,
6517 }, {
6518 'url': ':ytfavorites',
6519 'only_matching': True,
6520 }]
6521
6522 def _real_extract(self, url):
6523 return self.url_result(
6524 'https://www.youtube.com/playlist?list=LL',
6525 ie=YoutubeTabIE.ie_key())
6526
6527
6528 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6529 IE_NAME = 'youtube:notif'
6530 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6531 _VALID_URL = r':ytnotif(?:ication)?s?'
6532 _LOGIN_REQUIRED = True
6533 _TESTS = [{
6534 'url': ':ytnotif',
6535 'only_matching': True,
6536 }, {
6537 'url': ':ytnotifications',
6538 'only_matching': True,
6539 }]
6540
6541 def _extract_notification_menu(self, response, continuation_list):
6542 notification_list = traverse_obj(
6543 response,
6544 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6545 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6546 expected_type=list) or []
6547 continuation_list[0] = None
6548 for item in notification_list:
6549 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6550 if entry:
6551 yield entry
6552 continuation = item.get('continuationItemRenderer')
6553 if continuation:
6554 continuation_list[0] = continuation
6555
6556 def _extract_notification_renderer(self, notification):
6557 video_id = traverse_obj(
6558 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6559 url = f'https://www.youtube.com/watch?v={video_id}'
6560 channel_id = None
6561 if not video_id:
6562 browse_ep = traverse_obj(
6563 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6564 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6565 post_id = self._search_regex(
6566 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6567 'post id', default=None)
6568 if not channel_id or not post_id:
6569 return
6570 # The direct /post url redirects to this in the browser
6571 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6572
6573 channel = traverse_obj(
6574 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6575 expected_type=str)
6576 notification_title = self._get_text(notification, 'shortMessage')
6577 if notification_title:
6578 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6579 # TODO: handle recommended videos
6580 title = self._search_regex(
6581 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6582 'video title', default=None)
6583 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6584 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6585 else None)
6586 return {
6587 '_type': 'url',
6588 'url': url,
6589 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6590 'video_id': video_id,
6591 'title': title,
6592 'channel_id': channel_id,
6593 'channel': channel,
6594 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6595 'timestamp': timestamp,
6596 }
6597
6598 def _notification_menu_entries(self, ytcfg):
6599 continuation_list = [None]
6600 response = None
6601 for page in itertools.count(1):
6602 ctoken = traverse_obj(
6603 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6604 response = self._extract_response(
6605 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6606 ep='notification/get_notification_menu', check_get_keys='actions',
6607 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6608 yield from self._extract_notification_menu(response, continuation_list)
6609 if not continuation_list[0]:
6610 break
6611
6612 def _real_extract(self, url):
6613 display_id = 'notifications'
6614 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6615 self._report_playlist_authcheck(ytcfg)
6616 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6617
6618
6619 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6620 IE_DESC = 'YouTube search'
6621 IE_NAME = 'youtube:search'
6622 _SEARCH_KEY = 'ytsearch'
6623 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6624 _TESTS = [{
6625 'url': 'ytsearch5:youtube-dl test video',
6626 'playlist_count': 5,
6627 'info_dict': {
6628 'id': 'youtube-dl test video',
6629 'title': 'youtube-dl test video',
6630 }
6631 }]
6632
6633
6634 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6635 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6636 _SEARCH_KEY = 'ytsearchdate'
6637 IE_DESC = 'YouTube search, newest videos first'
6638 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6639 _TESTS = [{
6640 'url': 'ytsearchdate5:youtube-dl test video',
6641 'playlist_count': 5,
6642 'info_dict': {
6643 'id': 'youtube-dl test video',
6644 'title': 'youtube-dl test video',
6645 }
6646 }]
6647
6648
6649 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6650 IE_DESC = 'YouTube search URLs with sorting and filter support'
6651 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6652 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6653 _TESTS = [{
6654 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6655 'playlist_mincount': 5,
6656 'info_dict': {
6657 'id': 'youtube-dl test video',
6658 'title': 'youtube-dl test video',
6659 }
6660 }, {
6661 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6662 'playlist_mincount': 5,
6663 'info_dict': {
6664 'id': 'python',
6665 'title': 'python',
6666 }
6667 }, {
6668 'url': 'https://www.youtube.com/results?search_query=%23cats',
6669 'playlist_mincount': 1,
6670 'info_dict': {
6671 'id': '#cats',
6672 'title': '#cats',
6673 # The test suite does not have support for nested playlists
6674 # 'entries': [{
6675 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6676 # 'title': '#cats',
6677 # }],
6678 },
6679 }, {
6680 # Channel results
6681 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6682 'info_dict': {
6683 'id': 'kurzgesagt',
6684 'title': 'kurzgesagt',
6685 },
6686 'playlist': [{
6687 'info_dict': {
6688 '_type': 'url',
6689 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6690 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6691 'ie_key': 'YoutubeTab',
6692 'channel': 'Kurzgesagt – In a Nutshell',
6693 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6694 'title': 'Kurzgesagt – In a Nutshell',
6695 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6696 'playlist_count': int, # XXX: should have a way of saying > 1
6697 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6698 'thumbnails': list
6699 }
6700 }],
6701 'params': {'extract_flat': True, 'playlist_items': '1'},
6702 'playlist_mincount': 1,
6703 }, {
6704 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6705 'only_matching': True,
6706 }]
6707
6708 def _real_extract(self, url):
6709 qs = parse_qs(url)
6710 query = (qs.get('search_query') or qs.get('q'))[0]
6711 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6712
6713
6714 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6715 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6716 IE_NAME = 'youtube:music:search_url'
6717 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6718 _TESTS = [{
6719 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6720 'playlist_count': 16,
6721 'info_dict': {
6722 'id': 'royalty free music',
6723 'title': 'royalty free music',
6724 }
6725 }, {
6726 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6727 'playlist_mincount': 30,
6728 'info_dict': {
6729 'id': 'royalty free music - songs',
6730 'title': 'royalty free music - songs',
6731 },
6732 'params': {'extract_flat': 'in_playlist'}
6733 }, {
6734 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6735 'playlist_mincount': 30,
6736 'info_dict': {
6737 'id': 'royalty free music - community playlists',
6738 'title': 'royalty free music - community playlists',
6739 },
6740 'params': {'extract_flat': 'in_playlist'}
6741 }]
6742
6743 _SECTIONS = {
6744 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6745 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6746 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6747 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6748 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6749 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6750 }
6751
6752 def _real_extract(self, url):
6753 qs = parse_qs(url)
6754 query = (qs.get('search_query') or qs.get('q'))[0]
6755 params = qs.get('sp', (None,))[0]
6756 if params:
6757 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6758 else:
6759 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6760 params = self._SECTIONS.get(section)
6761 if not params:
6762 section = None
6763 title = join_nonempty(query, section, delim=' - ')
6764 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6765
6766
6767 class YoutubeFeedsInfoExtractor(InfoExtractor):
6768 """
6769 Base class for feed extractors
6770 Subclasses must re-define the _FEED_NAME property.
6771 """
6772 _LOGIN_REQUIRED = True
6773 _FEED_NAME = 'feeds'
6774
6775 def _real_initialize(self):
6776 YoutubeBaseInfoExtractor._check_login_required(self)
6777
6778 @classproperty
6779 def IE_NAME(self):
6780 return f'youtube:{self._FEED_NAME}'
6781
6782 def _real_extract(self, url):
6783 return self.url_result(
6784 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6785
6786
6787 class YoutubeWatchLaterIE(InfoExtractor):
6788 IE_NAME = 'youtube:watchlater'
6789 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6790 _VALID_URL = r':ytwatchlater'
6791 _TESTS = [{
6792 'url': ':ytwatchlater',
6793 'only_matching': True,
6794 }]
6795
6796 def _real_extract(self, url):
6797 return self.url_result(
6798 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6799
6800
6801 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6802 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6803 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6804 _FEED_NAME = 'recommended'
6805 _LOGIN_REQUIRED = False
6806 _TESTS = [{
6807 'url': ':ytrec',
6808 'only_matching': True,
6809 }, {
6810 'url': ':ytrecommended',
6811 'only_matching': True,
6812 }, {
6813 'url': 'https://youtube.com',
6814 'only_matching': True,
6815 }]
6816
6817
6818 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6819 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6820 _VALID_URL = r':ytsub(?:scription)?s?'
6821 _FEED_NAME = 'subscriptions'
6822 _TESTS = [{
6823 'url': ':ytsubs',
6824 'only_matching': True,
6825 }, {
6826 'url': ':ytsubscriptions',
6827 'only_matching': True,
6828 }]
6829
6830
6831 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6832 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6833 _VALID_URL = r':ythis(?:tory)?'
6834 _FEED_NAME = 'history'
6835 _TESTS = [{
6836 'url': ':ythistory',
6837 'only_matching': True,
6838 }]
6839
6840
6841 class YoutubeStoriesIE(InfoExtractor):
6842 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6843 IE_NAME = 'youtube:stories'
6844 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6845 _TESTS = [{
6846 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6847 'only_matching': True,
6848 }]
6849
6850 def _real_extract(self, url):
6851 playlist_id = f'RLTD{self._match_id(url)}'
6852 return self.url_result(
6853 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6854 ie=YoutubeTabIE, video_id=playlist_id)
6855
6856
6857 class YoutubeShortsAudioPivotIE(InfoExtractor):
6858 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6859 IE_NAME = 'youtube:shorts:pivot:audio'
6860 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6861 _TESTS = [{
6862 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6863 'only_matching': True,
6864 }]
6865
6866 @staticmethod
6867 def _generate_audio_pivot_params(video_id):
6868 """
6869 Generates sfv_audio_pivot browse params for this video id
6870 """
6871 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6872 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6873
6874 def _real_extract(self, url):
6875 video_id = self._match_id(url)
6876 return self.url_result(
6877 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6878 ie=YoutubeTabIE)
6879
6880
6881 class YoutubeTruncatedURLIE(InfoExtractor):
6882 IE_NAME = 'youtube:truncated_url'
6883 IE_DESC = False # Do not list
6884 _VALID_URL = r'''(?x)
6885 (?:https?://)?
6886 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6887 (?:watch\?(?:
6888 feature=[a-z_]+|
6889 annotation_id=annotation_[^&]+|
6890 x-yt-cl=[0-9]+|
6891 hl=[^&]*|
6892 t=[0-9]+
6893 )?
6894 |
6895 attribution_link\?a=[^&]+
6896 )
6897 $
6898 '''
6899
6900 _TESTS = [{
6901 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6902 'only_matching': True,
6903 }, {
6904 'url': 'https://www.youtube.com/watch?',
6905 'only_matching': True,
6906 }, {
6907 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6908 'only_matching': True,
6909 }, {
6910 'url': 'https://www.youtube.com/watch?feature=foo',
6911 'only_matching': True,
6912 }, {
6913 'url': 'https://www.youtube.com/watch?hl=en-GB',
6914 'only_matching': True,
6915 }, {
6916 'url': 'https://www.youtube.com/watch?t=2372',
6917 'only_matching': True,
6918 }]
6919
6920 def _real_extract(self, url):
6921 raise ExtractorError(
6922 'Did you forget to quote the URL? Remember that & is a meta '
6923 'character in most shells, so you want to put the URL in quotes, '
6924 'like youtube-dl '
6925 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6926 ' or simply youtube-dl BaW_jenozKc .',
6927 expected=True)
6928
6929
6930 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6931 IE_NAME = 'youtube:clip'
6932 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6933 _TESTS = [{
6934 # FIXME: Other metadata should be extracted from the clip, not from the base video
6935 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6936 'info_dict': {
6937 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6938 'ext': 'mp4',
6939 'section_start': 29.0,
6940 'section_end': 39.7,
6941 'duration': 10.7,
6942 'age_limit': 0,
6943 'availability': 'public',
6944 'categories': ['Gaming'],
6945 'channel': 'Scott The Woz',
6946 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6947 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6948 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6949 'like_count': int,
6950 'playable_in_embed': True,
6951 'tags': 'count:17',
6952 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6953 'title': 'Mobile Games on Console - Scott The Woz',
6954 'upload_date': '20210920',
6955 'uploader': 'Scott The Woz',
6956 'uploader_id': 'scottthewoz',
6957 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6958 'view_count': int,
6959 'live_status': 'not_live',
6960 'channel_follower_count': int
6961 }
6962 }]
6963
6964 def _real_extract(self, url):
6965 clip_id = self._match_id(url)
6966 _, data = self._extract_webpage(url, clip_id)
6967
6968 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6969 if not video_id:
6970 raise ExtractorError('Unable to find video ID')
6971
6972 clip_data = traverse_obj(data, (
6973 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6974 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6975 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6976 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6977
6978 return {
6979 '_type': 'url_transparent',
6980 'url': f'https://www.youtube.com/watch?v={video_id}',
6981 'ie_key': YoutubeIE.ie_key(),
6982 'id': clip_id,
6983 'section_start': int(clip_data['startTimeMs']) / 1000,
6984 'section_end': int(clip_data['endTimeMs']) / 1000,
6985 }
6986
6987
6988 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
6989 IE_NAME = 'youtube:consent'
6990 IE_DESC = False # Do not list
6991 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
6992 _TESTS = [{
6993 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1',
6994 'info_dict': {
6995 'id': 'qVv6vCqciTM',
6996 'ext': 'mp4',
6997 'age_limit': 0,
6998 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
6999 'comment_count': int,
7000 'chapters': 'count:13',
7001 'upload_date': '20221223',
7002 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7003 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7004 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7005 'like_count': int,
7006 'release_date': '20221223',
7007 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7008 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
7009 'view_count': int,
7010 'playable_in_embed': True,
7011 'duration': 4438,
7012 'availability': 'public',
7013 'channel_follower_count': int,
7014 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7015 'categories': ['Entertainment'],
7016 'live_status': 'was_live',
7017 'release_timestamp': 1671793345,
7018 'channel': 'さなちゃんねる',
7019 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7020 'uploader': 'さなちゃんねる',
7021 },
7022 'add_ie': ['Youtube'],
7023 'params': {'skip_download': 'Youtube'},
7024 }]
7025
7026 def _real_extract(self, url):
7027 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7028 if not redirect_url:
7029 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7030 return self.url_result(redirect_url)
7031
7032
7033 class YoutubeTruncatedIDIE(InfoExtractor):
7034 IE_NAME = 'youtube:truncated_id'
7035 IE_DESC = False # Do not list
7036 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7037
7038 _TESTS = [{
7039 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7040 'only_matching': True,
7041 }]
7042
7043 def _real_extract(self, url):
7044 video_id = self._match_id(url)
7045 raise ExtractorError(
7046 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
7047 expected=True)