]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
6e6abd65b1c295d7518864f8a002822f486d195f
[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 join_nonempty(audio_track.get('displayName'),
3721 language_preference > 0 and ' (default)', delim=''),
3722 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3723 fmt.get('isDrc') and 'DRC',
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
3749 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3750 if single_stream and dct.get('ext'):
3751 dct['container'] = dct['ext'] + '_dash'
3752 if single_stream or itag == '17':
3753 CHUNK_SIZE = 10 << 20
3754 dct.update({
3755 'protocol': 'http_dash_segments',
3756 'fragments': [{
3757 'url': update_url_query(dct['url'], {
3758 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, dct["filesize"])}'
3759 })
3760 } for range_start in range(0, dct['filesize'], CHUNK_SIZE)]
3761 } if itag != '17' and dct['filesize'] else {
3762 'downloader_options': {'http_chunk_size': CHUNK_SIZE}
3763 })
3764
3765 if itag:
3766 itags[itag].add(('https', dct.get('language')))
3767 stream_ids.append(stream_id)
3768 yield dct
3769
3770 needs_live_processing = self._needs_live_processing(live_status, duration)
3771 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3772
3773 skip_manifests = set(self._configuration_arg('skip'))
3774 if (not self.get_param('youtube_include_hls_manifest', True)
3775 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3776 or needs_live_processing and skip_bad_formats):
3777 skip_manifests.add('hls')
3778
3779 if not self.get_param('youtube_include_dash_manifest', True):
3780 skip_manifests.add('dash')
3781 if self._configuration_arg('include_live_dash'):
3782 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3783 'Use include_incomplete_formats extractor argument instead')
3784 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3785 skip_manifests.add('dash')
3786
3787 def process_manifest_format(f, proto, itag):
3788 key = (proto, f.get('language'))
3789 if key in itags[itag]:
3790 return False
3791 itags[itag].add(key)
3792
3793 if any(p != proto for p, _ in itags[itag]):
3794 f['format_id'] = f'{itag}-{proto}'
3795 elif itag:
3796 f['format_id'] = itag
3797
3798 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3799 if f['quality'] == -1 and f.get('height'):
3800 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3801 return True
3802
3803 subtitles = {}
3804 for sd in streaming_data:
3805 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3806 if hls_manifest_url:
3807 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3808 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3809 subtitles = self._merge_subtitles(subs, subtitles)
3810 for f in fmts:
3811 if process_manifest_format(f, 'hls', self._search_regex(
3812 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3813 yield f
3814
3815 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3816 if dash_manifest_url:
3817 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3818 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3819 for f in formats:
3820 if process_manifest_format(f, 'dash', f['format_id']):
3821 f['filesize'] = int_or_none(self._search_regex(
3822 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3823 if needs_live_processing:
3824 f['is_from_start'] = True
3825
3826 yield f
3827 yield subtitles
3828
3829 def _extract_storyboard(self, player_responses, duration):
3830 spec = get_first(
3831 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3832 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3833 if not base_url:
3834 return
3835 L = len(spec) - 1
3836 for i, args in enumerate(spec):
3837 args = args.split('#')
3838 counts = list(map(int_or_none, args[:5]))
3839 if len(args) != 8 or not all(counts):
3840 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3841 continue
3842 width, height, frame_count, cols, rows = counts
3843 N, sigh = args[6:]
3844
3845 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3846 fragment_count = frame_count / (cols * rows)
3847 fragment_duration = duration / fragment_count
3848 yield {
3849 'format_id': f'sb{i}',
3850 'format_note': 'storyboard',
3851 'ext': 'mhtml',
3852 'protocol': 'mhtml',
3853 'acodec': 'none',
3854 'vcodec': 'none',
3855 'url': url,
3856 'width': width,
3857 'height': height,
3858 'fps': frame_count / duration,
3859 'rows': rows,
3860 'columns': cols,
3861 'fragments': [{
3862 'url': url.replace('$M', str(j)),
3863 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3864 } for j in range(math.ceil(fragment_count))],
3865 }
3866
3867 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3868 webpage = None
3869 if 'webpage' not in self._configuration_arg('player_skip'):
3870 query = {'bpctr': '9999999999', 'has_verified': '1'}
3871 if smuggled_data.get('is_story'):
3872 query['pp'] = self._STORY_PLAYER_PARAMS
3873 webpage = self._download_webpage(
3874 webpage_url, video_id, fatal=False, query=query)
3875
3876 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3877
3878 player_responses, player_url = self._extract_player_responses(
3879 self._get_requested_clients(url, smuggled_data),
3880 video_id, webpage, master_ytcfg, smuggled_data)
3881
3882 return webpage, master_ytcfg, player_responses, player_url
3883
3884 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3885 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3886 is_live = get_first(video_details, 'isLive')
3887 if is_live is None:
3888 is_live = get_first(live_broadcast_details, 'isLiveNow')
3889 live_content = get_first(video_details, 'isLiveContent')
3890 is_upcoming = get_first(video_details, 'isUpcoming')
3891 post_live = get_first(video_details, 'isPostLiveDvr')
3892 live_status = ('post_live' if post_live
3893 else 'is_live' if is_live
3894 else 'is_upcoming' if is_upcoming
3895 else 'was_live' if live_content
3896 else 'not_live' if False in (is_live, live_content)
3897 else None)
3898 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
3899 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3900
3901 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3902
3903 def _real_extract(self, url):
3904 url, smuggled_data = unsmuggle_url(url, {})
3905 video_id = self._match_id(url)
3906
3907 base_url = self.http_scheme() + '//www.youtube.com/'
3908 webpage_url = base_url + 'watch?v=' + video_id
3909
3910 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3911
3912 playability_statuses = traverse_obj(
3913 player_responses, (..., 'playabilityStatus'), expected_type=dict)
3914
3915 trailer_video_id = get_first(
3916 playability_statuses,
3917 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3918 expected_type=str)
3919 if trailer_video_id:
3920 return self.url_result(
3921 trailer_video_id, self.ie_key(), trailer_video_id)
3922
3923 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3924 if webpage else (lambda x: None))
3925
3926 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
3927 microformats = traverse_obj(
3928 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3929 expected_type=dict)
3930
3931 translated_title = self._get_text(microformats, (..., 'title'))
3932 video_title = (self._preferred_lang and translated_title
3933 or get_first(video_details, 'title') # primary
3934 or translated_title
3935 or search_meta(['og:title', 'twitter:title', 'title']))
3936 translated_description = self._get_text(microformats, (..., 'description'))
3937 original_description = get_first(video_details, 'shortDescription')
3938 video_description = (
3939 self._preferred_lang and translated_description
3940 # If original description is blank, it will be an empty string.
3941 # Do not prefer translated description in this case.
3942 or original_description if original_description is not None else translated_description)
3943
3944 multifeed_metadata_list = get_first(
3945 player_responses,
3946 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3947 expected_type=str)
3948 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3949 if self.get_param('noplaylist'):
3950 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3951 else:
3952 entries = []
3953 feed_ids = []
3954 for feed in multifeed_metadata_list.split(','):
3955 # Unquote should take place before split on comma (,) since textual
3956 # fields may contain comma as well (see
3957 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3958 feed_data = urllib.parse.parse_qs(
3959 urllib.parse.unquote_plus(feed))
3960
3961 def feed_entry(name):
3962 return try_get(
3963 feed_data, lambda x: x[name][0], str)
3964
3965 feed_id = feed_entry('id')
3966 if not feed_id:
3967 continue
3968 feed_title = feed_entry('title')
3969 title = video_title
3970 if feed_title:
3971 title += ' (%s)' % feed_title
3972 entries.append({
3973 '_type': 'url_transparent',
3974 'ie_key': 'Youtube',
3975 'url': smuggle_url(
3976 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3977 {'force_singlefeed': True}),
3978 'title': title,
3979 })
3980 feed_ids.append(feed_id)
3981 self.to_screen(
3982 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3983 % (', '.join(feed_ids), video_id))
3984 return self.playlist_result(
3985 entries, video_id, video_title, video_description)
3986
3987 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
3988 or int_or_none(get_first(microformats, 'lengthSeconds'))
3989 or parse_duration(search_meta('duration')) or None)
3990
3991 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3992 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3993 if live_status == 'post_live':
3994 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
3995
3996 if not formats:
3997 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3998 self.report_drm(video_id)
3999 pemr = get_first(
4000 playability_statuses,
4001 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4002 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4003 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
4004 if subreason:
4005 if subreason == 'The uploader has not made this video available in your country.':
4006 countries = get_first(microformats, 'availableCountries')
4007 if not countries:
4008 regions_allowed = search_meta('regionsAllowed')
4009 countries = regions_allowed.split(',') if regions_allowed else None
4010 self.raise_geo_restricted(subreason, countries, metadata_available=True)
4011 reason += f'. {subreason}'
4012 if reason:
4013 self.raise_no_formats(reason, expected=True)
4014
4015 keywords = get_first(video_details, 'keywords', expected_type=list) or []
4016 if not keywords and webpage:
4017 keywords = [
4018 unescapeHTML(m.group('content'))
4019 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4020 for keyword in keywords:
4021 if keyword.startswith('yt:stretch='):
4022 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4023 if mobj:
4024 # NB: float is intentional for forcing float division
4025 w, h = (float(v) for v in mobj.groups())
4026 if w > 0 and h > 0:
4027 ratio = w / h
4028 for f in formats:
4029 if f.get('vcodec') != 'none':
4030 f['stretched_ratio'] = ratio
4031 break
4032 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
4033 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4034 if thumbnail_url:
4035 thumbnails.append({
4036 'url': thumbnail_url,
4037 })
4038 original_thumbnails = thumbnails.copy()
4039
4040 # The best resolution thumbnails sometimes does not appear in the webpage
4041 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4042 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4043 thumbnail_names = [
4044 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4045 # in resolution, these are not the custom thumbnail. So de-prioritize them
4046 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4047 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4048 ]
4049 n_thumbnail_names = len(thumbnail_names)
4050 thumbnails.extend({
4051 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4052 video_id=video_id, name=name, ext=ext,
4053 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
4054 } for name in thumbnail_names for ext in ('webp', 'jpg'))
4055 for thumb in thumbnails:
4056 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
4057 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
4058 self._remove_duplicate_formats(thumbnails)
4059 self._downloader._sort_thumbnails(original_thumbnails)
4060
4061 category = get_first(microformats, 'category') or search_meta('genre')
4062 channel_id = str_or_none(
4063 get_first(video_details, 'channelId')
4064 or get_first(microformats, 'externalChannelId')
4065 or search_meta('channelId'))
4066 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4067
4068 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4069 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4070 if not duration and live_end_time and live_start_time:
4071 duration = live_end_time - live_start_time
4072
4073 needs_live_processing = self._needs_live_processing(live_status, duration)
4074
4075 def is_bad_format(fmt):
4076 if needs_live_processing and not fmt.get('is_from_start'):
4077 return True
4078 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4079 and fmt.get('protocol') == 'http_dash_segments'):
4080 return True
4081
4082 for fmt in filter(is_bad_format, formats):
4083 fmt['preference'] = (fmt.get('preference') or -1) - 10
4084 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4085
4086 if needs_live_processing:
4087 self._prepare_live_from_start_formats(
4088 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
4089
4090 formats.extend(self._extract_storyboard(player_responses, duration))
4091
4092 info = {
4093 'id': video_id,
4094 'title': video_title,
4095 'formats': formats,
4096 'thumbnails': thumbnails,
4097 # The best thumbnail that we are sure exists. Prevents unnecessary
4098 # URL checking if user don't care about getting the best possible thumbnail
4099 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
4100 'description': video_description,
4101 'uploader': get_first(video_details, 'author'),
4102 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
4103 'uploader_url': owner_profile_url,
4104 'channel_id': channel_id,
4105 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
4106 'duration': duration,
4107 'view_count': int_or_none(
4108 get_first((video_details, microformats), (..., 'viewCount'))
4109 or search_meta('interactionCount')),
4110 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
4111 'age_limit': 18 if (
4112 get_first(microformats, 'isFamilySafe') is False
4113 or search_meta('isFamilyFriendly') == 'false'
4114 or search_meta('og:restrictions:age') == '18+') else 0,
4115 'webpage_url': webpage_url,
4116 'categories': [category] if category else None,
4117 'tags': keywords,
4118 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4119 'live_status': live_status,
4120 'release_timestamp': live_start_time,
4121 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4122 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4123 }
4124
4125 subtitles = {}
4126 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
4127 if pctr:
4128 def get_lang_code(track):
4129 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4130 or track.get('languageCode'))
4131
4132 # Converted into dicts to remove duplicates
4133 captions = {
4134 get_lang_code(sub): sub
4135 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
4136 translation_languages = {
4137 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4138 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
4139
4140 def process_language(container, base_url, lang_code, sub_name, query):
4141 lang_subs = container.setdefault(lang_code, [])
4142 for fmt in self._SUBTITLE_FORMATS:
4143 query.update({
4144 'fmt': fmt,
4145 })
4146 lang_subs.append({
4147 'ext': fmt,
4148 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
4149 'name': sub_name,
4150 })
4151
4152 # NB: Constructing the full subtitle dictionary is slow
4153 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4154 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
4155 for lang_code, caption_track in captions.items():
4156 base_url = caption_track.get('baseUrl')
4157 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
4158 if not base_url:
4159 continue
4160 lang_name = self._get_text(caption_track, 'name', max_runs=1)
4161 if caption_track.get('kind') != 'asr':
4162 if not lang_code:
4163 continue
4164 process_language(
4165 subtitles, base_url, lang_code, lang_name, {})
4166 if not caption_track.get('isTranslatable'):
4167 continue
4168 for trans_code, trans_name in translation_languages.items():
4169 if not trans_code:
4170 continue
4171 orig_trans_code = trans_code
4172 if caption_track.get('kind') != 'asr' and trans_code != 'und':
4173 if not get_translated_subs:
4174 continue
4175 trans_code += f'-{lang_code}'
4176 trans_name += format_field(lang_name, None, ' from %s')
4177 # Add an "-orig" label to the original language so that it can be distinguished.
4178 # The subs are returned without "-orig" as well for compatibility
4179 if lang_code == f'a-{orig_trans_code}':
4180 process_language(
4181 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4182 # Setting tlang=lang returns damaged subtitles.
4183 process_language(automatic_captions, base_url, trans_code, trans_name,
4184 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
4185
4186 info['automatic_captions'] = automatic_captions
4187 info['subtitles'] = subtitles
4188
4189 parsed_url = urllib.parse.urlparse(url)
4190 for component in [parsed_url.fragment, parsed_url.query]:
4191 query = urllib.parse.parse_qs(component)
4192 for k, v in query.items():
4193 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4194 d_k += '_time'
4195 if d_k not in info and k in s_ks:
4196 info[d_k] = parse_duration(query[k][0])
4197
4198 # Youtube Music Auto-generated description
4199 if video_description:
4200 mobj = re.search(
4201 r'''(?xs)
4202 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4203 (?P<album>[^\n]+)
4204 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4205 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4206 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4207 .+\nAuto-generated\ by\ YouTube\.\s*$
4208 ''', video_description)
4209 if mobj:
4210 release_year = mobj.group('release_year')
4211 release_date = mobj.group('release_date')
4212 if release_date:
4213 release_date = release_date.replace('-', '')
4214 if not release_year:
4215 release_year = release_date[:4]
4216 info.update({
4217 'album': mobj.group('album'.strip()),
4218 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4219 'track': mobj.group('track').strip(),
4220 'release_date': release_date,
4221 'release_year': int_or_none(release_year),
4222 })
4223
4224 initial_data = None
4225 if webpage:
4226 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4227 if not initial_data:
4228 query = {'videoId': video_id}
4229 query.update(self._get_checkok_params())
4230 initial_data = self._extract_response(
4231 item_id=video_id, ep='next', fatal=False,
4232 ytcfg=master_ytcfg, query=query,
4233 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4234 note='Downloading initial data API JSON')
4235
4236 info['comment_count'] = traverse_obj(initial_data, (
4237 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4238 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4239 ), (
4240 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4241 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4242 ), expected_type=int_or_none, get_all=False)
4243
4244 try: # This will error if there is no livechat
4245 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4246 except (KeyError, IndexError, TypeError):
4247 pass
4248 else:
4249 info.setdefault('subtitles', {})['live_chat'] = [{
4250 # url is needed to set cookies
4251 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4252 'video_id': video_id,
4253 'ext': 'json',
4254 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4255 else 'youtube_live_chat_replay'),
4256 }]
4257
4258 if initial_data:
4259 info['chapters'] = (
4260 self._extract_chapters_from_json(initial_data, duration)
4261 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4262 or self._extract_chapters_from_description(video_description, duration)
4263 or None)
4264
4265 contents = traverse_obj(
4266 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4267 expected_type=list, default=[])
4268
4269 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4270 if vpir:
4271 stl = vpir.get('superTitleLink')
4272 if stl:
4273 stl = self._get_text(stl)
4274 if try_get(
4275 vpir,
4276 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4277 info['location'] = stl
4278 else:
4279 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4280 if mobj:
4281 info.update({
4282 'series': mobj.group(1),
4283 'season_number': int(mobj.group(2)),
4284 'episode_number': int(mobj.group(3)),
4285 })
4286 for tlb in (try_get(
4287 vpir,
4288 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4289 list) or []):
4290 tbrs = variadic(
4291 traverse_obj(
4292 tlb, ('toggleButtonRenderer', ...),
4293 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4294 for tbr in tbrs:
4295 for getter, regex in [(
4296 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4297 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4298 lambda x: x['accessibility'],
4299 lambda x: x['accessibilityData']['accessibilityData'],
4300 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4301 label = (try_get(tbr, getter, dict) or {}).get('label')
4302 if label:
4303 mobj = re.match(regex, label)
4304 if mobj:
4305 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4306 break
4307 sbr_tooltip = try_get(
4308 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4309 if sbr_tooltip:
4310 like_count, dislike_count = sbr_tooltip.split(' / ')
4311 info.update({
4312 'like_count': str_to_int(like_count),
4313 'dislike_count': str_to_int(dislike_count),
4314 })
4315 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4316 if vcr:
4317 vc = self._get_count(vcr, 'viewCount')
4318 # Upcoming premieres with waiting count are treated as live here
4319 if vcr.get('isLive'):
4320 info['concurrent_view_count'] = vc
4321 elif info.get('view_count') is None:
4322 info['view_count'] = vc
4323
4324 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4325 if vsir:
4326 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4327 info.update({
4328 'channel': self._get_text(vor, 'title'),
4329 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4330
4331 rows = try_get(
4332 vsir,
4333 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4334 list) or []
4335 multiple_songs = False
4336 for row in rows:
4337 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4338 multiple_songs = True
4339 break
4340 for row in rows:
4341 mrr = row.get('metadataRowRenderer') or {}
4342 mrr_title = mrr.get('title')
4343 if not mrr_title:
4344 continue
4345 mrr_title = self._get_text(mrr, 'title')
4346 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4347 if mrr_title == 'License':
4348 info['license'] = mrr_contents_text
4349 elif not multiple_songs:
4350 if mrr_title == 'Album':
4351 info['album'] = mrr_contents_text
4352 elif mrr_title == 'Artist':
4353 info['artist'] = mrr_contents_text
4354 elif mrr_title == 'Song':
4355 info['track'] = mrr_contents_text
4356
4357 fallbacks = {
4358 'channel': 'uploader',
4359 'channel_id': 'uploader_id',
4360 'channel_url': 'uploader_url',
4361 }
4362
4363 # The upload date for scheduled, live and past live streams / premieres in microformats
4364 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4365 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4366 upload_date = (
4367 unified_strdate(get_first(microformats, 'uploadDate'))
4368 or unified_strdate(search_meta('uploadDate')))
4369 if not upload_date or (
4370 live_status in ('not_live', None)
4371 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4372 ):
4373 upload_date = strftime_or_none(
4374 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4375 info['upload_date'] = upload_date
4376
4377 for to, frm in fallbacks.items():
4378 if not info.get(to):
4379 info[to] = info.get(frm)
4380
4381 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4382 v = info.get(s_k)
4383 if v:
4384 info[d_k] = v
4385
4386 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4387
4388 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4389 or get_first(video_details, 'isPrivate', expected_type=bool))
4390
4391 info['availability'] = (
4392 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4393 else self._availability(
4394 is_private=is_private,
4395 needs_premium=(
4396 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4397 or False if initial_data and is_private is not None else None),
4398 needs_subscription=(
4399 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4400 or False if initial_data and is_private is not None else None),
4401 needs_auth=info['age_limit'] >= 18,
4402 is_unlisted=None if is_private is None else (
4403 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4404 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4405
4406 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4407
4408 self.mark_watched(video_id, player_responses)
4409
4410 return info
4411
4412
4413 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4414 @staticmethod
4415 def passthrough_smuggled_data(func):
4416 def _smuggle(info, smuggled_data):
4417 if info.get('_type') not in ('url', 'url_transparent'):
4418 return info
4419 if smuggled_data.get('is_music_url'):
4420 parsed_url = urllib.parse.urlparse(info['url'])
4421 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4422 smuggled_data.pop('is_music_url')
4423 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4424 if smuggled_data:
4425 info['url'] = smuggle_url(info['url'], smuggled_data)
4426 return info
4427
4428 @functools.wraps(func)
4429 def wrapper(self, url):
4430 url, smuggled_data = unsmuggle_url(url, {})
4431 if self.is_music_url(url):
4432 smuggled_data['is_music_url'] = True
4433 info_dict = func(self, url, smuggled_data)
4434 if smuggled_data:
4435 _smuggle(info_dict, smuggled_data)
4436 if info_dict.get('entries'):
4437 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
4438 return info_dict
4439 return wrapper
4440
4441 @staticmethod
4442 def _extract_basic_item_renderer(item):
4443 # Modified from _extract_grid_item_renderer
4444 known_basic_renderers = (
4445 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4446 )
4447 for key, renderer in item.items():
4448 if not isinstance(renderer, dict):
4449 continue
4450 elif key in known_basic_renderers:
4451 return renderer
4452 elif key.startswith('grid') and key.endswith('Renderer'):
4453 return renderer
4454
4455 def _extract_channel_renderer(self, renderer):
4456 channel_id = renderer['channelId']
4457 title = self._get_text(renderer, 'title')
4458 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4459 return {
4460 '_type': 'url',
4461 'url': channel_url,
4462 'id': channel_id,
4463 'ie_key': YoutubeTabIE.ie_key(),
4464 'channel': title,
4465 'channel_id': channel_id,
4466 'channel_url': channel_url,
4467 'title': title,
4468 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4469 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4470 'playlist_count': self._get_count(renderer, 'videoCountText'),
4471 'description': self._get_text(renderer, 'descriptionSnippet'),
4472 }
4473
4474 def _grid_entries(self, grid_renderer):
4475 for item in grid_renderer['items']:
4476 if not isinstance(item, dict):
4477 continue
4478 renderer = self._extract_basic_item_renderer(item)
4479 if not isinstance(renderer, dict):
4480 continue
4481 title = self._get_text(renderer, 'title')
4482
4483 # playlist
4484 playlist_id = renderer.get('playlistId')
4485 if playlist_id:
4486 yield self.url_result(
4487 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4488 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4489 video_title=title)
4490 continue
4491 # video
4492 video_id = renderer.get('videoId')
4493 if video_id:
4494 yield self._extract_video(renderer)
4495 continue
4496 # channel
4497 channel_id = renderer.get('channelId')
4498 if channel_id:
4499 yield self._extract_channel_renderer(renderer)
4500 continue
4501 # generic endpoint URL support
4502 ep_url = urljoin('https://www.youtube.com/', try_get(
4503 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4504 str))
4505 if ep_url:
4506 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4507 if ie.suitable(ep_url):
4508 yield self.url_result(
4509 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4510 break
4511
4512 def _music_reponsive_list_entry(self, renderer):
4513 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4514 if video_id:
4515 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4516 ie=YoutubeIE.ie_key(), video_id=video_id)
4517 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4518 if playlist_id:
4519 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4520 if video_id:
4521 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4522 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4523 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4524 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4525 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4526 if browse_id:
4527 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4528 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4529
4530 def _shelf_entries_from_content(self, shelf_renderer):
4531 content = shelf_renderer.get('content')
4532 if not isinstance(content, dict):
4533 return
4534 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4535 if renderer:
4536 # TODO: add support for nested playlists so each shelf is processed
4537 # as separate playlist
4538 # TODO: this includes only first N items
4539 yield from self._grid_entries(renderer)
4540 renderer = content.get('horizontalListRenderer')
4541 if renderer:
4542 # TODO
4543 pass
4544
4545 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4546 ep = try_get(
4547 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4548 str)
4549 shelf_url = urljoin('https://www.youtube.com', ep)
4550 if shelf_url:
4551 # Skipping links to another channels, note that checking for
4552 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4553 # will not work
4554 if skip_channels and '/channels?' in shelf_url:
4555 return
4556 title = self._get_text(shelf_renderer, 'title')
4557 yield self.url_result(shelf_url, video_title=title)
4558 # Shelf may not contain shelf URL, fallback to extraction from content
4559 yield from self._shelf_entries_from_content(shelf_renderer)
4560
4561 def _playlist_entries(self, video_list_renderer):
4562 for content in video_list_renderer['contents']:
4563 if not isinstance(content, dict):
4564 continue
4565 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4566 if not isinstance(renderer, dict):
4567 continue
4568 video_id = renderer.get('videoId')
4569 if not video_id:
4570 continue
4571 yield self._extract_video(renderer)
4572
4573 def _rich_entries(self, rich_grid_renderer):
4574 renderer = traverse_obj(
4575 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4576 video_id = renderer.get('videoId')
4577 if not video_id:
4578 return
4579 yield self._extract_video(renderer)
4580
4581 def _video_entry(self, video_renderer):
4582 video_id = video_renderer.get('videoId')
4583 if video_id:
4584 return self._extract_video(video_renderer)
4585
4586 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4587 url = urljoin('https://youtube.com', traverse_obj(
4588 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4589 if url:
4590 return self.url_result(
4591 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4592
4593 def _post_thread_entries(self, post_thread_renderer):
4594 post_renderer = try_get(
4595 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4596 if not post_renderer:
4597 return
4598 # video attachment
4599 video_renderer = try_get(
4600 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4601 video_id = video_renderer.get('videoId')
4602 if video_id:
4603 entry = self._extract_video(video_renderer)
4604 if entry:
4605 yield entry
4606 # playlist attachment
4607 playlist_id = try_get(
4608 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4609 if playlist_id:
4610 yield self.url_result(
4611 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4612 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4613 # inline video links
4614 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4615 for run in runs:
4616 if not isinstance(run, dict):
4617 continue
4618 ep_url = try_get(
4619 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4620 if not ep_url:
4621 continue
4622 if not YoutubeIE.suitable(ep_url):
4623 continue
4624 ep_video_id = YoutubeIE._match_id(ep_url)
4625 if video_id == ep_video_id:
4626 continue
4627 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4628
4629 def _post_thread_continuation_entries(self, post_thread_continuation):
4630 contents = post_thread_continuation.get('contents')
4631 if not isinstance(contents, list):
4632 return
4633 for content in contents:
4634 renderer = content.get('backstagePostThreadRenderer')
4635 if isinstance(renderer, dict):
4636 yield from self._post_thread_entries(renderer)
4637 continue
4638 renderer = content.get('videoRenderer')
4639 if isinstance(renderer, dict):
4640 yield self._video_entry(renderer)
4641
4642 r''' # unused
4643 def _rich_grid_entries(self, contents):
4644 for content in contents:
4645 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4646 if video_renderer:
4647 entry = self._video_entry(video_renderer)
4648 if entry:
4649 yield entry
4650 '''
4651
4652 def _report_history_entries(self, renderer):
4653 for url in traverse_obj(renderer, (
4654 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4655 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4656 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4657 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4658
4659 def _extract_entries(self, parent_renderer, continuation_list):
4660 # continuation_list is modified in-place with continuation_list = [continuation_token]
4661 continuation_list[:] = [None]
4662 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4663 for content in contents:
4664 if not isinstance(content, dict):
4665 continue
4666 is_renderer = traverse_obj(
4667 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4668 expected_type=dict)
4669 if not is_renderer:
4670 if content.get('richItemRenderer'):
4671 for entry in self._rich_entries(content['richItemRenderer']):
4672 yield entry
4673 continuation_list[0] = self._extract_continuation(parent_renderer)
4674 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4675 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4676 yield from self._report_history_entries(table)
4677 continuation_list[0] = self._extract_continuation(table)
4678 continue
4679
4680 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4681 for isr_content in isr_contents:
4682 if not isinstance(isr_content, dict):
4683 continue
4684
4685 known_renderers = {
4686 'playlistVideoListRenderer': self._playlist_entries,
4687 'gridRenderer': self._grid_entries,
4688 'reelShelfRenderer': self._grid_entries,
4689 'shelfRenderer': self._shelf_entries,
4690 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4691 'backstagePostThreadRenderer': self._post_thread_entries,
4692 'videoRenderer': lambda x: [self._video_entry(x)],
4693 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4694 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4695 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4696 }
4697 for key, renderer in isr_content.items():
4698 if key not in known_renderers:
4699 continue
4700 for entry in known_renderers[key](renderer):
4701 if entry:
4702 yield entry
4703 continuation_list[0] = self._extract_continuation(renderer)
4704 break
4705
4706 if not continuation_list[0]:
4707 continuation_list[0] = self._extract_continuation(is_renderer)
4708
4709 if not continuation_list[0]:
4710 continuation_list[0] = self._extract_continuation(parent_renderer)
4711
4712 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4713 continuation_list = [None]
4714 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4715 tab_content = try_get(tab, lambda x: x['content'], dict)
4716 if not tab_content:
4717 return
4718 parent_renderer = (
4719 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4720 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4721 yield from extract_entries(parent_renderer)
4722 continuation = continuation_list[0]
4723
4724 for page_num in itertools.count(1):
4725 if not continuation:
4726 break
4727 headers = self.generate_api_headers(
4728 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4729 response = self._extract_response(
4730 item_id=f'{item_id} page {page_num}',
4731 query=continuation, headers=headers, ytcfg=ytcfg,
4732 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4733
4734 if not response:
4735 break
4736 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4737 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4738 visitor_data = self._extract_visitor_data(response) or visitor_data
4739
4740 known_renderers = {
4741 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4742 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4743 'gridVideoRenderer': (self._grid_entries, 'items'),
4744 'gridChannelRenderer': (self._grid_entries, 'items'),
4745 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4746 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4747 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4748 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4749 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4750 'playlistVideoListContinuation': (self._playlist_entries, None),
4751 'gridContinuation': (self._grid_entries, None),
4752 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4753 'sectionListContinuation': (extract_entries, None), # for feeds
4754 }
4755
4756 continuation_items = traverse_obj(response, (
4757 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4758 'appendContinuationItemsAction', 'continuationItems'
4759 ), 'continuationContents', get_all=False)
4760 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4761
4762 video_items_renderer = None
4763 for key in continuation_item.keys():
4764 if key not in known_renderers:
4765 continue
4766 func, parent_key = known_renderers[key]
4767 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4768 continuation_list = [None]
4769 yield from func(video_items_renderer)
4770 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4771
4772 if not video_items_renderer:
4773 break
4774
4775 @staticmethod
4776 def _extract_selected_tab(tabs, fatal=True):
4777 for tab_renderer in tabs:
4778 if tab_renderer.get('selected'):
4779 return tab_renderer
4780 if fatal:
4781 raise ExtractorError('Unable to find selected tab')
4782
4783 @staticmethod
4784 def _extract_tab_renderers(response):
4785 return traverse_obj(
4786 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
4787
4788 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4789 metadata = self._extract_metadata_from_tabs(item_id, data)
4790
4791 selected_tab = self._extract_selected_tab(tabs)
4792 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4793 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4794
4795 return self.playlist_result(
4796 self._entries(
4797 selected_tab, metadata['id'], ytcfg,
4798 self._extract_account_syncid(ytcfg, data),
4799 self._extract_visitor_data(data, ytcfg)),
4800 **metadata)
4801
4802 def _extract_metadata_from_tabs(self, item_id, data):
4803 info = {'id': item_id}
4804
4805 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
4806 if metadata_renderer:
4807 info.update({
4808 'uploader': metadata_renderer.get('title'),
4809 'uploader_id': metadata_renderer.get('externalId'),
4810 'uploader_url': metadata_renderer.get('channelUrl'),
4811 })
4812 if info['uploader_id']:
4813 info['id'] = info['uploader_id']
4814 else:
4815 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
4816
4817 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4818 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4819 def _get_uncropped(url):
4820 return url_or_none((url or '').split('=')[0] + '=s0')
4821
4822 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
4823 if avatar_thumbnails:
4824 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4825 if uncropped_avatar:
4826 avatar_thumbnails.append({
4827 'url': uncropped_avatar,
4828 'id': 'avatar_uncropped',
4829 'preference': 1
4830 })
4831
4832 channel_banners = self._extract_thumbnails(
4833 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4834 for banner in channel_banners:
4835 banner['preference'] = -10
4836
4837 if channel_banners:
4838 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4839 if uncropped_banner:
4840 channel_banners.append({
4841 'url': uncropped_banner,
4842 'id': 'banner_uncropped',
4843 'preference': -5
4844 })
4845
4846 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4847 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4848 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4849
4850 primary_thumbnails = self._extract_thumbnails(
4851 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4852 playlist_thumbnails = self._extract_thumbnails(
4853 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4854
4855 info.update({
4856 'title': (traverse_obj(metadata_renderer, 'title')
4857 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4858 or info['id']),
4859 'availability': self._extract_availability(data),
4860 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4861 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4862 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4863 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4864 })
4865
4866 # Playlist stats is a text runs array containing [video count, view count, last updated].
4867 # last updated or (view count and last updated) may be missing.
4868 playlist_stats = get_first(
4869 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4870
4871 last_updated_unix = self._parse_time_text(
4872 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4873 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4874 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
4875
4876 info['view_count'] = self._get_count(playlist_stats, 1)
4877 if info['view_count'] is None: # 0 is allowed
4878 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4879 if info['view_count'] is None:
4880 info['view_count'] = self._get_count(data, (
4881 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4882 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4883
4884 info['playlist_count'] = self._get_count(playlist_stats, 0)
4885 if info['playlist_count'] is None: # 0 is allowed
4886 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4887
4888 if not info.get('uploader_id'):
4889 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4890 if not owner: # Deprecated
4891 owner = traverse_obj(
4892 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4893 ('videoOwner', 'videoOwnerRenderer', 'title'))
4894 owner_text = self._get_text(owner)
4895 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4896 info.update({
4897 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4898 'uploader_id': browse_ep.get('browseId'),
4899 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4900 })
4901
4902 info.update({
4903 'channel': info['uploader'],
4904 'channel_id': info['uploader_id'],
4905 'channel_url': info['uploader_url']
4906 })
4907 return info
4908
4909 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4910 first_id = last_id = response = None
4911 for page_num in itertools.count(1):
4912 videos = list(self._playlist_entries(playlist))
4913 if not videos:
4914 return
4915 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4916 if start >= len(videos):
4917 return
4918 yield from videos[start:]
4919 first_id = first_id or videos[0]['id']
4920 last_id = videos[-1]['id']
4921 watch_endpoint = try_get(
4922 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4923 headers = self.generate_api_headers(
4924 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4925 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4926 query = {
4927 'playlistId': playlist_id,
4928 'videoId': watch_endpoint.get('videoId') or last_id,
4929 'index': watch_endpoint.get('index') or len(videos),
4930 'params': watch_endpoint.get('params') or 'OAE%3D'
4931 }
4932 response = self._extract_response(
4933 item_id='%s page %d' % (playlist_id, page_num),
4934 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4935 check_get_keys='contents'
4936 )
4937 playlist = try_get(
4938 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4939
4940 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4941 title = playlist.get('title') or try_get(
4942 data, lambda x: x['titleText']['simpleText'], str)
4943 playlist_id = playlist.get('playlistId') or item_id
4944
4945 # Delegating everything except mix playlists to regular tab-based playlist URL
4946 playlist_url = urljoin(url, try_get(
4947 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4948 str))
4949
4950 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4951 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4952 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4953
4954 if playlist_url and playlist_url != url and not is_known_unviewable:
4955 return self.url_result(
4956 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4957 video_title=title)
4958
4959 return self.playlist_result(
4960 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4961 playlist_id=playlist_id, playlist_title=title)
4962
4963 def _extract_availability(self, data):
4964 """
4965 Gets the availability of a given playlist/tab.
4966 Note: Unless YouTube tells us explicitly, we do not assume it is public
4967 @param data: response
4968 """
4969 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4970 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4971 player_header_privacy = playlist_header_renderer.get('privacy')
4972
4973 badges = self._extract_badges(sidebar_renderer)
4974
4975 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4976 privacy_setting_icon = get_first(
4977 (playlist_header_renderer, sidebar_renderer),
4978 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4979 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4980 expected_type=str)
4981
4982 microformats_is_unlisted = traverse_obj(
4983 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
4984
4985 return (
4986 'public' if (
4987 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4988 or player_header_privacy == 'PUBLIC'
4989 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4990 else self._availability(
4991 is_private=(
4992 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4993 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4994 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4995 is_unlisted=(
4996 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4997 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
4998 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
4999 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
5000 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5001 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5002 needs_auth=False))
5003
5004 @staticmethod
5005 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5006 sidebar_renderer = try_get(
5007 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5008 for item in sidebar_renderer:
5009 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5010 if renderer:
5011 return renderer
5012
5013 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
5014 """
5015 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5016 """
5017 is_playlist = bool(traverse_obj(
5018 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5019 if not is_playlist:
5020 return
5021 headers = self.generate_api_headers(
5022 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5023 visitor_data=self._extract_visitor_data(data, ytcfg))
5024 query = {
5025 'params': 'wgYCCAA=',
5026 'browseId': f'VL{item_id}'
5027 }
5028 return self._extract_response(
5029 item_id=item_id, headers=headers, query=query,
5030 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
5031 note='Redownloading playlist API JSON with unavailable videos')
5032
5033 @functools.cached_property
5034 def skip_webpage(self):
5035 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5036
5037 def _extract_webpage(self, url, item_id, fatal=True):
5038 webpage, data = None, None
5039 for retry in self.RetryManager(fatal=fatal):
5040 try:
5041 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
5042 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5043 except ExtractorError as e:
5044 if isinstance(e.cause, network_exceptions):
5045 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
5046 retry.error = e
5047 continue
5048 self._error_or_warning(e, fatal=fatal)
5049 break
5050
5051 try:
5052 self._extract_and_report_alerts(data)
5053 except ExtractorError as e:
5054 self._error_or_warning(e, fatal=fatal)
5055 break
5056
5057 # Sometimes youtube returns a webpage with incomplete ytInitialData
5058 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5059 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5060 retry.error = ExtractorError('Incomplete yt initial data received')
5061 continue
5062
5063 return webpage, data
5064
5065 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5066 """Use if failed to extract ytcfg (and data) from initial webpage"""
5067 if not ytcfg and self.is_authenticated:
5068 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5069 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5070 raise ExtractorError(
5071 f'{msg}. If you are not downloading private content, or '
5072 'your cookies are only for the first account and channel,'
5073 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5074 expected=True)
5075 self.report_warning(msg, only_once=True)
5076
5077 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5078 data = None
5079 if not self.skip_webpage:
5080 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5081 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
5082 # Reject webpage data if redirected to home page without explicitly requesting
5083 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
5084 if (url != 'https://www.youtube.com/feed/recommended'
5085 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5086 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5087 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5088 if fatal:
5089 raise ExtractorError(msg, expected=True)
5090 self.report_warning(msg, only_once=True)
5091 if not data:
5092 self._report_playlist_authcheck(ytcfg, fatal=fatal)
5093 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5094 return data, ytcfg
5095
5096 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5097 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5098 resolve_response = self._extract_response(
5099 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5100 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5101 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5102 for ep_key, ep in endpoints.items():
5103 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5104 if params:
5105 return self._extract_response(
5106 item_id=item_id, query=params, ep=ep, headers=headers,
5107 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
5108 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5109 err_note = 'Failed to resolve url (does the playlist exist?)'
5110 if fatal:
5111 raise ExtractorError(err_note, expected=True)
5112 self.report_warning(err_note, item_id)
5113
5114 _SEARCH_PARAMS = None
5115
5116 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
5117 data = {'query': query}
5118 if params is NO_DEFAULT:
5119 params = self._SEARCH_PARAMS
5120 if params:
5121 data['params'] = params
5122
5123 content_keys = (
5124 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5125 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5126 # ytmusic search
5127 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5128 ('continuationContents', ),
5129 )
5130 display_id = f'query "{query}"'
5131 check_get_keys = tuple({keys[0] for keys in content_keys})
5132 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5133 self._report_playlist_authcheck(ytcfg, fatal=False)
5134
5135 continuation_list = [None]
5136 search = None
5137 for page_num in itertools.count(1):
5138 data.update(continuation_list[0] or {})
5139 headers = self.generate_api_headers(
5140 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
5141 search = self._extract_response(
5142 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5143 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
5144 slr_contents = traverse_obj(search, *content_keys)
5145 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
5146 if not continuation_list[0]:
5147 break
5148
5149
5150 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5151 IE_DESC = 'YouTube Tabs'
5152 _VALID_URL = r'''(?x:
5153 https?://
5154 (?!consent\.)(?:\w+\.)?
5155 (?:
5156 youtube(?:kids)?\.com|
5157 %(invidious)s
5158 )/
5159 (?:
5160 (?P<channel_type>channel|c|user|browse)/|
5161 (?P<not_channel>
5162 feed/|hashtag/|
5163 (?:playlist|watch)\?.*?\blist=
5164 )|
5165 (?!(?:%(reserved_names)s)\b) # Direct URLs
5166 )
5167 (?P<id>[^/?\#&]+)
5168 )''' % {
5169 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5170 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5171 }
5172 IE_NAME = 'youtube:tab'
5173
5174 _TESTS = [{
5175 'note': 'playlists, multipage',
5176 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5177 'playlist_mincount': 94,
5178 'info_dict': {
5179 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5180 'title': 'Igor Kleiner - Playlists',
5181 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5182 'uploader': 'Igor Kleiner',
5183 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5184 'channel': 'Igor Kleiner',
5185 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5186 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5187 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5188 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5189 'channel_follower_count': int
5190 },
5191 }, {
5192 'note': 'playlists, multipage, different order',
5193 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5194 'playlist_mincount': 94,
5195 'info_dict': {
5196 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5197 'title': 'Igor Kleiner - Playlists',
5198 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5199 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5200 'uploader': 'Igor Kleiner',
5201 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5202 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5203 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5204 'channel': 'Igor Kleiner',
5205 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5206 'channel_follower_count': int
5207 },
5208 }, {
5209 'note': 'playlists, series',
5210 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5211 'playlist_mincount': 5,
5212 'info_dict': {
5213 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5214 'title': '3Blue1Brown - Playlists',
5215 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5216 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5217 'uploader': '3Blue1Brown',
5218 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5219 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5220 'channel': '3Blue1Brown',
5221 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5222 'tags': ['Mathematics'],
5223 'channel_follower_count': int
5224 },
5225 }, {
5226 'note': 'playlists, singlepage',
5227 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5228 'playlist_mincount': 4,
5229 'info_dict': {
5230 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5231 'title': 'ThirstForScience - Playlists',
5232 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5233 'uploader': 'ThirstForScience',
5234 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5235 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5236 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5237 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5238 'tags': 'count:13',
5239 'channel': 'ThirstForScience',
5240 'channel_follower_count': int
5241 }
5242 }, {
5243 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5244 'only_matching': True,
5245 }, {
5246 'note': 'basic, single video playlist',
5247 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5248 'info_dict': {
5249 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5250 'uploader': 'Sergey M.',
5251 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5252 'title': 'youtube-dl public playlist',
5253 'description': '',
5254 'tags': [],
5255 'view_count': int,
5256 'modified_date': '20201130',
5257 'channel': 'Sergey M.',
5258 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5259 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5260 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5261 'availability': 'public',
5262 },
5263 'playlist_count': 1,
5264 }, {
5265 'note': 'empty playlist',
5266 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5267 'info_dict': {
5268 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5269 'uploader': 'Sergey M.',
5270 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5271 'title': 'youtube-dl empty playlist',
5272 'tags': [],
5273 'channel': 'Sergey M.',
5274 'description': '',
5275 'modified_date': '20160902',
5276 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5277 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5278 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5279 'availability': 'public',
5280 },
5281 'playlist_count': 0,
5282 }, {
5283 'note': 'Home tab',
5284 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5285 'info_dict': {
5286 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5287 'title': 'lex will - Home',
5288 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5289 'uploader': 'lex will',
5290 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5291 'channel': 'lex will',
5292 'tags': ['bible', 'history', 'prophesy'],
5293 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5294 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5295 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5296 'channel_follower_count': int
5297 },
5298 'playlist_mincount': 2,
5299 }, {
5300 'note': 'Videos tab',
5301 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5302 'info_dict': {
5303 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5304 'title': 'lex will - Videos',
5305 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5306 'uploader': 'lex will',
5307 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5308 'tags': ['bible', 'history', 'prophesy'],
5309 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5310 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5311 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5312 'channel': 'lex will',
5313 'channel_follower_count': int
5314 },
5315 'playlist_mincount': 975,
5316 }, {
5317 'note': 'Videos tab, sorted by popular',
5318 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5319 'info_dict': {
5320 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5321 'title': 'lex will - Videos',
5322 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5323 'uploader': 'lex will',
5324 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5325 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5326 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5327 'channel': 'lex will',
5328 'tags': ['bible', 'history', 'prophesy'],
5329 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5330 'channel_follower_count': int
5331 },
5332 'playlist_mincount': 199,
5333 }, {
5334 'note': 'Playlists tab',
5335 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5336 'info_dict': {
5337 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5338 'title': 'lex will - Playlists',
5339 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5340 'uploader': 'lex will',
5341 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5342 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5343 'channel': 'lex will',
5344 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5345 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5346 'tags': ['bible', 'history', 'prophesy'],
5347 'channel_follower_count': int
5348 },
5349 'playlist_mincount': 17,
5350 }, {
5351 'note': 'Community tab',
5352 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5353 'info_dict': {
5354 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5355 'title': 'lex will - Community',
5356 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5357 'uploader': 'lex will',
5358 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5359 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5360 'channel': 'lex will',
5361 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5362 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5363 'tags': ['bible', 'history', 'prophesy'],
5364 'channel_follower_count': int
5365 },
5366 'playlist_mincount': 18,
5367 }, {
5368 'note': 'Channels tab',
5369 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5370 'info_dict': {
5371 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5372 'title': 'lex will - Channels',
5373 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5374 'uploader': 'lex will',
5375 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5376 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5377 'channel': 'lex will',
5378 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5379 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5380 'tags': ['bible', 'history', 'prophesy'],
5381 'channel_follower_count': int
5382 },
5383 'playlist_mincount': 12,
5384 }, {
5385 'note': 'Search tab',
5386 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5387 'playlist_mincount': 40,
5388 'info_dict': {
5389 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5390 'title': '3Blue1Brown - Search - linear algebra',
5391 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5392 'uploader': '3Blue1Brown',
5393 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5394 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5395 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5396 'tags': ['Mathematics'],
5397 'channel': '3Blue1Brown',
5398 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5399 'channel_follower_count': int
5400 },
5401 }, {
5402 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5403 'only_matching': True,
5404 }, {
5405 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5406 'only_matching': True,
5407 }, {
5408 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5409 'only_matching': True,
5410 }, {
5411 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5412 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5413 'info_dict': {
5414 'title': '29C3: Not my department',
5415 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5416 'uploader': 'Christiaan008',
5417 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5418 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5419 'tags': [],
5420 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5421 'view_count': int,
5422 'modified_date': '20150605',
5423 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5424 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5425 'channel': 'Christiaan008',
5426 'availability': 'public',
5427 },
5428 'playlist_count': 96,
5429 }, {
5430 'note': 'Large playlist',
5431 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5432 'info_dict': {
5433 'title': 'Uploads from Cauchemar',
5434 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5435 'uploader': 'Cauchemar',
5436 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5437 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5438 'tags': [],
5439 'modified_date': r're:\d{8}',
5440 'channel': 'Cauchemar',
5441 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5442 'view_count': int,
5443 'description': '',
5444 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5445 'availability': 'public',
5446 },
5447 'playlist_mincount': 1123,
5448 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5449 }, {
5450 'note': 'even larger playlist, 8832 videos',
5451 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5452 'only_matching': True,
5453 }, {
5454 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5455 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5456 'info_dict': {
5457 'title': 'Uploads from Interstellar Movie',
5458 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5459 'uploader': 'Interstellar Movie',
5460 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5461 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5462 'tags': [],
5463 'view_count': int,
5464 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5465 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5466 'channel': 'Interstellar Movie',
5467 'description': '',
5468 'modified_date': r're:\d{8}',
5469 'availability': 'public',
5470 },
5471 'playlist_mincount': 21,
5472 }, {
5473 'note': 'Playlist with "show unavailable videos" button',
5474 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5475 'info_dict': {
5476 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5477 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5478 'uploader': 'Phim Siêu Nhân Nhật Bản',
5479 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5480 'view_count': int,
5481 'channel': 'Phim Siêu Nhân Nhật Bản',
5482 'tags': [],
5483 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5484 'description': '',
5485 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5486 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5487 'modified_date': r're:\d{8}',
5488 'availability': 'public',
5489 },
5490 'playlist_mincount': 200,
5491 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5492 }, {
5493 'note': 'Playlist with unavailable videos in page 7',
5494 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5495 'info_dict': {
5496 'title': 'Uploads from BlankTV',
5497 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5498 'uploader': 'BlankTV',
5499 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5500 'channel': 'BlankTV',
5501 'channel_url': 'https://www.youtube.com/c/blanktv',
5502 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5503 'view_count': int,
5504 'tags': [],
5505 'uploader_url': 'https://www.youtube.com/c/blanktv',
5506 'modified_date': r're:\d{8}',
5507 'description': '',
5508 'availability': 'public',
5509 },
5510 'playlist_mincount': 1000,
5511 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5512 }, {
5513 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5514 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5515 'info_dict': {
5516 'title': 'Data Analysis with Dr Mike Pound',
5517 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5518 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5519 'uploader': 'Computerphile',
5520 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5521 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5522 'tags': [],
5523 'view_count': int,
5524 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5525 'channel_url': 'https://www.youtube.com/user/Computerphile',
5526 'channel': 'Computerphile',
5527 'availability': 'public',
5528 'modified_date': '20190712',
5529 },
5530 'playlist_mincount': 11,
5531 }, {
5532 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5533 'only_matching': True,
5534 }, {
5535 'note': 'Playlist URL that does not actually serve a playlist',
5536 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5537 'info_dict': {
5538 'id': 'FqZTN594JQw',
5539 'ext': 'webm',
5540 'title': "Smiley's People 01 detective, Adventure Series, Action",
5541 'uploader': 'STREEM',
5542 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5543 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5544 'upload_date': '20150526',
5545 'license': 'Standard YouTube License',
5546 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5547 'categories': ['People & Blogs'],
5548 'tags': list,
5549 'view_count': int,
5550 'like_count': int,
5551 },
5552 'params': {
5553 'skip_download': True,
5554 },
5555 'skip': 'This video is not available.',
5556 'add_ie': [YoutubeIE.ie_key()],
5557 }, {
5558 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5559 'only_matching': True,
5560 }, {
5561 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5562 'only_matching': True,
5563 }, {
5564 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5565 'info_dict': {
5566 'id': 'Wq15eF5vCbI', # This will keep changing
5567 'ext': 'mp4',
5568 'title': str,
5569 'uploader': 'Sky News',
5570 'uploader_id': 'skynews',
5571 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5572 'upload_date': r're:\d{8}',
5573 'description': str,
5574 'categories': ['News & Politics'],
5575 'tags': list,
5576 'like_count': int,
5577 'release_timestamp': int,
5578 'channel': 'Sky News',
5579 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5580 'age_limit': 0,
5581 'view_count': int,
5582 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5583 'playable_in_embed': True,
5584 'release_date': r're:\d+',
5585 'availability': 'public',
5586 'live_status': 'is_live',
5587 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5588 'channel_follower_count': int,
5589 'concurrent_view_count': int,
5590 },
5591 'params': {
5592 'skip_download': True,
5593 },
5594 'expected_warnings': ['Ignoring subtitle tracks found in '],
5595 }, {
5596 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5597 'info_dict': {
5598 'id': 'a48o2S1cPoo',
5599 'ext': 'mp4',
5600 'title': 'The Young Turks - Live Main Show',
5601 'uploader': 'The Young Turks',
5602 'uploader_id': 'TheYoungTurks',
5603 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5604 'upload_date': '20150715',
5605 'license': 'Standard YouTube License',
5606 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5607 'categories': ['News & Politics'],
5608 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5609 'like_count': int,
5610 },
5611 'params': {
5612 'skip_download': True,
5613 },
5614 'only_matching': True,
5615 }, {
5616 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5617 'only_matching': True,
5618 }, {
5619 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5620 'only_matching': True,
5621 }, {
5622 'note': 'A channel that is not live. Should raise error',
5623 'url': 'https://www.youtube.com/user/numberphile/live',
5624 'only_matching': True,
5625 }, {
5626 'url': 'https://www.youtube.com/feed/trending',
5627 'only_matching': True,
5628 }, {
5629 'url': 'https://www.youtube.com/feed/library',
5630 'only_matching': True,
5631 }, {
5632 'url': 'https://www.youtube.com/feed/history',
5633 'only_matching': True,
5634 }, {
5635 'url': 'https://www.youtube.com/feed/subscriptions',
5636 'only_matching': True,
5637 }, {
5638 'url': 'https://www.youtube.com/feed/watch_later',
5639 'only_matching': True,
5640 }, {
5641 'note': 'Recommended - redirects to home page.',
5642 'url': 'https://www.youtube.com/feed/recommended',
5643 'only_matching': True,
5644 }, {
5645 'note': 'inline playlist with not always working continuations',
5646 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5647 'only_matching': True,
5648 }, {
5649 'url': 'https://www.youtube.com/course',
5650 'only_matching': True,
5651 }, {
5652 'url': 'https://www.youtube.com/zsecurity',
5653 'only_matching': True,
5654 }, {
5655 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5656 'only_matching': True,
5657 }, {
5658 'url': 'https://www.youtube.com/TheYoungTurks/live',
5659 'only_matching': True,
5660 }, {
5661 'url': 'https://www.youtube.com/hashtag/cctv9',
5662 'info_dict': {
5663 'id': 'cctv9',
5664 'title': '#cctv9',
5665 'tags': [],
5666 },
5667 'playlist_mincount': 300, # not consistent but should be over 300
5668 }, {
5669 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5670 'only_matching': True,
5671 }, {
5672 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5673 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5674 'only_matching': True
5675 }, {
5676 'note': '/browse/ should redirect to /channel/',
5677 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5678 'only_matching': True
5679 }, {
5680 'note': 'VLPL, should redirect to playlist?list=PL...',
5681 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5682 'info_dict': {
5683 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5684 'uploader': 'NoCopyrightSounds',
5685 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5686 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5687 'title': 'NCS : All Releases 💿',
5688 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5689 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5690 'modified_date': r're:\d{8}',
5691 'view_count': int,
5692 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5693 'tags': [],
5694 'channel': 'NoCopyrightSounds',
5695 'availability': 'public',
5696 },
5697 'playlist_mincount': 166,
5698 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5699 }, {
5700 'note': 'Topic, should redirect to playlist?list=UU...',
5701 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5702 'info_dict': {
5703 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5704 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5705 'title': 'Uploads from Royalty Free Music - Topic',
5706 'uploader': 'Royalty Free Music - Topic',
5707 'tags': [],
5708 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5709 'channel': 'Royalty Free Music - Topic',
5710 'view_count': int,
5711 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5712 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5713 'modified_date': r're:\d{8}',
5714 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5715 'description': '',
5716 'availability': 'public',
5717 },
5718 'playlist_mincount': 101,
5719 }, {
5720 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5721 # Treat as a general feed
5722 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5723 'info_dict': {
5724 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5725 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5726 'tags': [],
5727 },
5728 'playlist_mincount': 9,
5729 }, {
5730 'note': 'Youtube music Album',
5731 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5732 'info_dict': {
5733 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5734 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5735 'tags': [],
5736 'view_count': int,
5737 'description': '',
5738 'availability': 'unlisted',
5739 'modified_date': r're:\d{8}',
5740 },
5741 'playlist_count': 50,
5742 }, {
5743 'note': 'unlisted single video playlist',
5744 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5745 'info_dict': {
5746 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5747 'uploader': 'colethedj',
5748 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5749 'title': 'yt-dlp unlisted playlist test',
5750 'availability': 'unlisted',
5751 'tags': [],
5752 'modified_date': '20220418',
5753 'channel': 'colethedj',
5754 'view_count': int,
5755 'description': '',
5756 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5757 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5758 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5759 },
5760 'playlist_count': 1,
5761 }, {
5762 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5763 'url': 'https://www.youtube.com/feed/recommended',
5764 'info_dict': {
5765 'id': 'recommended',
5766 'title': 'recommended',
5767 'tags': [],
5768 },
5769 'playlist_mincount': 50,
5770 'params': {
5771 'skip_download': True,
5772 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5773 },
5774 }, {
5775 'note': 'API Fallback: /videos tab, sorted by oldest first',
5776 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5777 'info_dict': {
5778 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5779 'title': 'Cody\'sLab - Videos',
5780 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5781 'uploader': 'Cody\'sLab',
5782 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5783 'channel': 'Cody\'sLab',
5784 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5785 'tags': [],
5786 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5787 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5788 'channel_follower_count': int
5789 },
5790 'playlist_mincount': 650,
5791 'params': {
5792 'skip_download': True,
5793 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5794 },
5795 'skip': 'Query for sorting no longer works',
5796 }, {
5797 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5798 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5799 'info_dict': {
5800 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5801 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5802 'title': 'Uploads from Royalty Free Music - Topic',
5803 'uploader': 'Royalty Free Music - Topic',
5804 'modified_date': r're:\d{8}',
5805 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5806 'description': '',
5807 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5808 'tags': [],
5809 'channel': 'Royalty Free Music - Topic',
5810 'view_count': int,
5811 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5812 'availability': 'public',
5813 },
5814 'playlist_mincount': 101,
5815 'params': {
5816 'skip_download': True,
5817 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5818 },
5819 }, {
5820 'note': 'non-standard redirect to regional channel',
5821 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5822 'only_matching': True
5823 }, {
5824 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5825 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5826 'info_dict': {
5827 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5828 'modified_date': '20220407',
5829 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5830 'tags': [],
5831 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5832 'uploader': 'pukkandan',
5833 'availability': 'unlisted',
5834 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5835 'channel': 'pukkandan',
5836 'description': 'Test for collaborative playlist',
5837 'title': 'yt-dlp test - collaborative playlist',
5838 'view_count': int,
5839 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5840 },
5841 'playlist_mincount': 2
5842 }, {
5843 'note': 'translated tab name',
5844 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5845 'info_dict': {
5846 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5847 'tags': [],
5848 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5849 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5850 'description': 'test description',
5851 'title': 'cole-dlp-test-acc - 再生リスト',
5852 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5853 'uploader': 'cole-dlp-test-acc',
5854 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5855 'channel': 'cole-dlp-test-acc',
5856 },
5857 'playlist_mincount': 1,
5858 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5859 'expected_warnings': ['Preferring "ja"'],
5860 }, {
5861 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5862 'note': 'preferred lang set with playlist with translated video titles',
5863 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5864 'info_dict': {
5865 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5866 'tags': [],
5867 'view_count': int,
5868 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5869 'uploader': 'cole-dlp-test-acc',
5870 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5871 'channel': 'cole-dlp-test-acc',
5872 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5873 'description': 'test',
5874 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5875 'title': 'dlp test playlist',
5876 'availability': 'public',
5877 },
5878 'playlist_mincount': 1,
5879 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5880 'expected_warnings': ['Preferring "ja"'],
5881 }, {
5882 # shorts audio pivot for 2GtVksBMYFM.
5883 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5884 'info_dict': {
5885 'id': 'sfv_audio_pivot',
5886 'title': 'sfv_audio_pivot',
5887 'tags': [],
5888 },
5889 'playlist_mincount': 50,
5890
5891 }, {
5892 # Channel with a real live tab (not to be mistaken with streams tab)
5893 # Do not treat like it should redirect to live stream
5894 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5895 'info_dict': {
5896 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5897 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5898 'tags': [],
5899 },
5900 'playlist_mincount': 20,
5901 }, {
5902 # Tab name is not the same as tab id
5903 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5904 'info_dict': {
5905 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5906 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5907 'tags': [],
5908 },
5909 'playlist_mincount': 8,
5910 }, {
5911 # Home tab id is literally home. Not to get mistaken with featured
5912 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5913 'info_dict': {
5914 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5915 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5916 'tags': [],
5917 },
5918 'playlist_mincount': 8,
5919 }, {
5920 # Should get three playlists for videos, shorts and streams tabs
5921 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5922 'info_dict': {
5923 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5924 'title': 'Polka Ch. 尾丸ポルカ',
5925 'channel_follower_count': int,
5926 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5927 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5928 'uploader': 'Polka Ch. 尾丸ポルカ',
5929 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5930 'channel': 'Polka Ch. 尾丸ポルカ',
5931 'tags': 'count:35',
5932 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5933 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5934 },
5935 'playlist_count': 3,
5936 }, {
5937 # Shorts tab with channel with handle
5938 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5939 'info_dict': {
5940 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5941 'title': 'Not Just Bikes - Shorts',
5942 'tags': 'count:12',
5943 'uploader': 'Not Just Bikes',
5944 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5945 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5946 'channel_follower_count': int,
5947 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5948 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5949 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5950 'channel': 'Not Just Bikes',
5951 },
5952 'playlist_mincount': 10,
5953 }, {
5954 # Streams tab
5955 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5956 'info_dict': {
5957 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5958 'title': '中村悠一 - Live',
5959 'tags': 'count:7',
5960 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5961 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5962 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5963 'channel': '中村悠一',
5964 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5965 'channel_follower_count': int,
5966 'uploader': '中村悠一',
5967 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5968 },
5969 'playlist_mincount': 60,
5970 }, {
5971 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5972 # See test_youtube_lists
5973 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5974 'only_matching': True,
5975 }, {
5976 # No uploads and no UCID given. Should fail with no uploads error
5977 # See test_youtube_lists
5978 'url': 'https://www.youtube.com/news',
5979 'only_matching': True
5980 }, {
5981 # No videos tab but has a shorts tab
5982 'url': 'https://www.youtube.com/c/TKFShorts',
5983 'info_dict': {
5984 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5985 'title': 'Shorts Break - Shorts',
5986 'tags': 'count:32',
5987 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5988 'channel': 'Shorts Break',
5989 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5990 'uploader': 'Shorts Break',
5991 'channel_follower_count': int,
5992 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5993 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5994 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5995 },
5996 'playlist_mincount': 30,
5997 }, {
5998 # Trending Now Tab. tab id is empty
5999 'url': 'https://www.youtube.com/feed/trending',
6000 'info_dict': {
6001 'id': 'trending',
6002 'title': 'trending - Now',
6003 'tags': [],
6004 },
6005 'playlist_mincount': 30,
6006 }, {
6007 # Trending Gaming Tab. tab id is empty
6008 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6009 'info_dict': {
6010 'id': 'trending',
6011 'title': 'trending - Gaming',
6012 'tags': [],
6013 },
6014 'playlist_mincount': 30,
6015 }, {
6016 # Shorts url result in shorts tab
6017 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6018 'info_dict': {
6019 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6020 'title': 'cole-dlp-test-acc - Shorts',
6021 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6022 'channel': 'cole-dlp-test-acc',
6023 'description': 'test description',
6024 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6025 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6026 'tags': [],
6027 'uploader': 'cole-dlp-test-acc',
6028 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6029
6030 },
6031 'playlist': [{
6032 'info_dict': {
6033 '_type': 'url',
6034 'ie_key': 'Youtube',
6035 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6036 'id': 'sSM9J5YH_60',
6037 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6038 'title': 'SHORT short',
6039 'channel': 'cole-dlp-test-acc',
6040 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6041 'view_count': int,
6042 'thumbnails': list,
6043 }
6044 }],
6045 'params': {'extract_flat': True},
6046 }, {
6047 # Live video status should be extracted
6048 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6049 'info_dict': {
6050 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6051 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6052 'tags': []
6053 },
6054 'playlist': [{
6055 'info_dict': {
6056 '_type': 'url',
6057 'ie_key': 'Youtube',
6058 'url': 'startswith:https://www.youtube.com/watch?v=',
6059 'id': str,
6060 'title': str,
6061 'live_status': 'is_live',
6062 'channel_id': str,
6063 'channel_url': str,
6064 'concurrent_view_count': int,
6065 'channel': str,
6066 }
6067 }],
6068 'params': {'extract_flat': True, 'playlist_items': '1'},
6069 'playlist_mincount': 1
6070 }, {
6071 # Channel renderer metadata. Contains number of videos on the channel
6072 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6073 'info_dict': {
6074 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6075 'title': 'cole-dlp-test-acc - Channels',
6076 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6077 'channel': 'cole-dlp-test-acc',
6078 'description': 'test description',
6079 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6080 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6081 'tags': [],
6082 'uploader': 'cole-dlp-test-acc',
6083 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6084
6085 },
6086 'playlist': [{
6087 'info_dict': {
6088 '_type': 'url',
6089 'ie_key': 'YoutubeTab',
6090 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6091 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6092 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6093 'title': 'PewDiePie',
6094 'channel': 'PewDiePie',
6095 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6096 'thumbnails': list,
6097 'channel_follower_count': int,
6098 'playlist_count': int
6099 }
6100 }],
6101 'params': {'extract_flat': True},
6102 }, {
6103 'url': 'https://www.youtube.com/@3blue1brown/about',
6104 'info_dict': {
6105 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6106 'tags': ['Mathematics'],
6107 'title': '3Blue1Brown - About',
6108 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6109 'channel_follower_count': int,
6110 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6111 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6112 'channel': '3Blue1Brown',
6113 'uploader': '3Blue1Brown',
6114 'view_count': int,
6115 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6116 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6117 },
6118 'playlist_count': 0,
6119 }]
6120
6121 @classmethod
6122 def suitable(cls, url):
6123 return False if YoutubeIE.suitable(url) else super().suitable(url)
6124
6125 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6126
6127 def _get_url_mobj(self, url):
6128 mobj = self._URL_RE.match(url).groupdict()
6129 mobj.update((k, '') for k, v in mobj.items() if v is None)
6130 return mobj
6131
6132 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6133 tab_name = (tab.get('title') or '').lower()
6134 tab_url = urljoin(base_url, traverse_obj(
6135 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6136
6137 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6138 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
6139 if tab_id:
6140 return {
6141 'TAB_ID_SPONSORSHIPS': 'membership',
6142 }.get(tab_id, tab_id), tab_name
6143
6144 # Fallback to tab name if we cannot get the tab id.
6145 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6146 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6147 if tab_name:
6148 self.write_debug(f'Falling back to selected tab name: {tab_name}')
6149 return {
6150 'home': 'featured',
6151 'live': 'streams',
6152 }.get(tab_name, tab_name), tab_name
6153
6154 def _has_tab(self, tabs, tab_id):
6155 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
6156
6157 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6158 def _real_extract(self, url, smuggled_data):
6159 item_id = self._match_id(url)
6160 url = urllib.parse.urlunparse(
6161 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
6162 compat_opts = self.get_param('compat_opts', [])
6163
6164 mobj = self._get_url_mobj(url)
6165 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
6166 if is_channel and smuggled_data.get('is_music_url'):
6167 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6168 return self.url_result(
6169 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6170 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6171 mdata = self._extract_tab_endpoint(
6172 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6173 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6174 get_all=False, expected_type=str)
6175 if not murl:
6176 raise ExtractorError('Failed to resolve album to playlist')
6177 return self.url_result(murl, YoutubeTabIE)
6178 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6179 return self.url_result(
6180 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6181
6182 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
6183 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
6184 url = f'{pre}/videos{post}'
6185 if smuggled_data.get('is_music_url'):
6186 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
6187
6188 # Handle both video/playlist URLs
6189 qs = parse_qs(url)
6190 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
6191 if not video_id and mobj['not_channel'].startswith('watch'):
6192 if not playlist_id:
6193 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6194 raise ExtractorError('A video URL was given without video ID', expected=True)
6195 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6196 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6197 return self.url_result(
6198 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
6199
6200 if not self._yes_playlist(playlist_id, video_id):
6201 return self.url_result(
6202 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6203
6204 data, ytcfg = self._extract_data(url, display_id)
6205
6206 # YouTube may provide a non-standard redirect to the regional channel
6207 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6208 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6209 redirect_url = traverse_obj(
6210 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6211 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
6212 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
6213 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6214 return self.url_result(redirect_url, YoutubeTabIE)
6215
6216 tabs, extra_tabs = self._extract_tab_renderers(data), []
6217 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
6218 selected_tab = self._extract_selected_tab(tabs)
6219 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6220 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6221
6222 if not original_tab_id and selected_tab_name:
6223 self.to_screen('Downloading all uploads of the channel. '
6224 'To download only the videos in a specific tab, pass the tab\'s URL')
6225 if self._has_tab(tabs, 'streams'):
6226 extra_tabs.append(''.join((pre, '/streams', post)))
6227 if self._has_tab(tabs, 'shorts'):
6228 extra_tabs.append(''.join((pre, '/shorts', post)))
6229 # XXX: Members-only tab should also be extracted
6230
6231 if not extra_tabs and selected_tab_id != 'videos':
6232 # Channel does not have streams, shorts or videos tabs
6233 if item_id[:2] != 'UC':
6234 raise ExtractorError('This channel has no uploads', expected=True)
6235
6236 # Topic channels don't have /videos. Use the equivalent playlist instead
6237 pl_id = f'UU{item_id[2:]}'
6238 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6239 try:
6240 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6241 except ExtractorError:
6242 raise ExtractorError('This channel has no uploads', expected=True)
6243 else:
6244 item_id, url = pl_id, pl_url
6245 self.to_screen(
6246 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6247
6248 elif extra_tabs and selected_tab_id != 'videos':
6249 # When there are shorts/live tabs but not videos tab
6250 url, data = f'{pre}{post}', None
6251
6252 elif (original_tab_id or 'videos') != selected_tab_id:
6253 if original_tab_id == 'live':
6254 # Live tab should have redirected to the video
6255 # Except in the case the channel has an actual live tab
6256 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6257 raise UserNotLive(video_id=item_id)
6258 elif selected_tab_name:
6259 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6260
6261 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6262 url = f'{pre}{post}'
6263
6264 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6265 if 'no-youtube-unavailable-videos' not in compat_opts:
6266 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
6267 self._extract_and_report_alerts(data, only_once=True)
6268
6269 tabs, entries = self._extract_tab_renderers(data), []
6270 if tabs:
6271 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6272 entries[0].update({
6273 'extractor_key': YoutubeTabIE.ie_key(),
6274 'extractor': YoutubeTabIE.IE_NAME,
6275 'webpage_url': url,
6276 })
6277 if self.get_param('playlist_items') == '0':
6278 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6279 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6280 entries.extend(map(self._real_extract, extra_tabs))
6281
6282 if len(entries) == 1:
6283 return entries[0]
6284 elif entries:
6285 metadata = self._extract_metadata_from_tabs(item_id, data)
6286 uploads_url = 'the Uploads (UU) playlist URL'
6287 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6288 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6289 self.to_screen(
6290 'Downloading as multiple playlists, separated by tabs. '
6291 f'To download as a single playlist instead, pass {uploads_url}')
6292 return self.playlist_result(entries, item_id, **metadata)
6293
6294 # Inline playlist
6295 playlist = traverse_obj(
6296 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
6297 if playlist:
6298 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
6299
6300 video_id = traverse_obj(
6301 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
6302 if video_id:
6303 if tab != '/live': # live tab is expected to redirect to video
6304 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
6305 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6306
6307 raise ExtractorError('Unable to recognize tab page')
6308
6309
6310 class YoutubePlaylistIE(InfoExtractor):
6311 IE_DESC = 'YouTube playlists'
6312 _VALID_URL = r'''(?x)(?:
6313 (?:https?://)?
6314 (?:\w+\.)?
6315 (?:
6316 (?:
6317 youtube(?:kids)?\.com|
6318 %(invidious)s
6319 )
6320 /.*?\?.*?\blist=
6321 )?
6322 (?P<id>%(playlist_id)s)
6323 )''' % {
6324 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6325 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6326 }
6327 IE_NAME = 'youtube:playlist'
6328 _TESTS = [{
6329 'note': 'issue #673',
6330 'url': 'PLBB231211A4F62143',
6331 'info_dict': {
6332 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6333 'id': 'PLBB231211A4F62143',
6334 'uploader': 'Wickman',
6335 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6336 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6337 'view_count': int,
6338 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6339 'modified_date': r're:\d{8}',
6340 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6341 'channel': 'Wickman',
6342 'tags': [],
6343 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6344 'availability': 'public',
6345 },
6346 'playlist_mincount': 29,
6347 }, {
6348 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6349 'info_dict': {
6350 'title': 'YDL_safe_search',
6351 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6352 },
6353 'playlist_count': 2,
6354 'skip': 'This playlist is private',
6355 }, {
6356 'note': 'embedded',
6357 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6358 'playlist_count': 4,
6359 'info_dict': {
6360 'title': 'JODA15',
6361 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6362 'uploader': 'milan',
6363 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6364 'description': '',
6365 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6366 'tags': [],
6367 'modified_date': '20140919',
6368 'view_count': int,
6369 'channel': 'milan',
6370 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6371 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6372 'availability': 'public',
6373 },
6374 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
6375 }, {
6376 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6377 'playlist_mincount': 455,
6378 'info_dict': {
6379 'title': '2018 Chinese New Singles (11/6 updated)',
6380 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6381 'uploader': 'LBK',
6382 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6383 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6384 'channel': 'LBK',
6385 'view_count': int,
6386 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6387 'tags': [],
6388 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6389 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6390 'modified_date': r're:\d{8}',
6391 'availability': 'public',
6392 },
6393 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
6394 }, {
6395 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6396 'only_matching': True,
6397 }, {
6398 # music album playlist
6399 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6400 'only_matching': True,
6401 }]
6402
6403 @classmethod
6404 def suitable(cls, url):
6405 if YoutubeTabIE.suitable(url):
6406 return False
6407 from ..utils import parse_qs
6408 qs = parse_qs(url)
6409 if qs.get('v', [None])[0]:
6410 return False
6411 return super().suitable(url)
6412
6413 def _real_extract(self, url):
6414 playlist_id = self._match_id(url)
6415 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
6416 url = update_url_query(
6417 'https://www.youtube.com/playlist',
6418 parse_qs(url) or {'list': playlist_id})
6419 if is_music_url:
6420 url = smuggle_url(url, {'is_music_url': True})
6421 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6422
6423
6424 class YoutubeYtBeIE(InfoExtractor):
6425 IE_DESC = 'youtu.be'
6426 _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}
6427 _TESTS = [{
6428 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6429 'info_dict': {
6430 'id': 'yeWKywCrFtk',
6431 'ext': 'mp4',
6432 'title': 'Small Scale Baler and Braiding Rugs',
6433 'uploader': 'Backus-Page House Museum',
6434 'uploader_id': 'backuspagemuseum',
6435 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6436 'upload_date': '20161008',
6437 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6438 'categories': ['Nonprofits & Activism'],
6439 'tags': list,
6440 'like_count': int,
6441 'age_limit': 0,
6442 'playable_in_embed': True,
6443 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6444 'channel': 'Backus-Page House Museum',
6445 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6446 'live_status': 'not_live',
6447 'view_count': int,
6448 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6449 'availability': 'public',
6450 'duration': 59,
6451 'comment_count': int,
6452 'channel_follower_count': int
6453 },
6454 'params': {
6455 'noplaylist': True,
6456 'skip_download': True,
6457 },
6458 }, {
6459 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6460 'only_matching': True,
6461 }]
6462
6463 def _real_extract(self, url):
6464 mobj = self._match_valid_url(url)
6465 video_id = mobj.group('id')
6466 playlist_id = mobj.group('playlist_id')
6467 return self.url_result(
6468 update_url_query('https://www.youtube.com/watch', {
6469 'v': video_id,
6470 'list': playlist_id,
6471 'feature': 'youtu.be',
6472 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6473
6474
6475 class YoutubeLivestreamEmbedIE(InfoExtractor):
6476 IE_DESC = 'YouTube livestream embeds'
6477 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6478 _TESTS = [{
6479 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6480 'only_matching': True,
6481 }]
6482
6483 def _real_extract(self, url):
6484 channel_id = self._match_id(url)
6485 return self.url_result(
6486 f'https://www.youtube.com/channel/{channel_id}/live',
6487 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6488
6489
6490 class YoutubeYtUserIE(InfoExtractor):
6491 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6492 IE_NAME = 'youtube:user'
6493 _VALID_URL = r'ytuser:(?P<id>.+)'
6494 _TESTS = [{
6495 'url': 'ytuser:phihag',
6496 'only_matching': True,
6497 }]
6498
6499 def _real_extract(self, url):
6500 user_id = self._match_id(url)
6501 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
6502
6503
6504 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6505 IE_NAME = 'youtube:favorites'
6506 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6507 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6508 _LOGIN_REQUIRED = True
6509 _TESTS = [{
6510 'url': ':ytfav',
6511 'only_matching': True,
6512 }, {
6513 'url': ':ytfavorites',
6514 'only_matching': True,
6515 }]
6516
6517 def _real_extract(self, url):
6518 return self.url_result(
6519 'https://www.youtube.com/playlist?list=LL',
6520 ie=YoutubeTabIE.ie_key())
6521
6522
6523 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6524 IE_NAME = 'youtube:notif'
6525 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6526 _VALID_URL = r':ytnotif(?:ication)?s?'
6527 _LOGIN_REQUIRED = True
6528 _TESTS = [{
6529 'url': ':ytnotif',
6530 'only_matching': True,
6531 }, {
6532 'url': ':ytnotifications',
6533 'only_matching': True,
6534 }]
6535
6536 def _extract_notification_menu(self, response, continuation_list):
6537 notification_list = traverse_obj(
6538 response,
6539 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6540 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6541 expected_type=list) or []
6542 continuation_list[0] = None
6543 for item in notification_list:
6544 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6545 if entry:
6546 yield entry
6547 continuation = item.get('continuationItemRenderer')
6548 if continuation:
6549 continuation_list[0] = continuation
6550
6551 def _extract_notification_renderer(self, notification):
6552 video_id = traverse_obj(
6553 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6554 url = f'https://www.youtube.com/watch?v={video_id}'
6555 channel_id = None
6556 if not video_id:
6557 browse_ep = traverse_obj(
6558 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6559 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6560 post_id = self._search_regex(
6561 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6562 'post id', default=None)
6563 if not channel_id or not post_id:
6564 return
6565 # The direct /post url redirects to this in the browser
6566 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6567
6568 channel = traverse_obj(
6569 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6570 expected_type=str)
6571 notification_title = self._get_text(notification, 'shortMessage')
6572 if notification_title:
6573 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6574 # TODO: handle recommended videos
6575 title = self._search_regex(
6576 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6577 'video title', default=None)
6578 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6579 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6580 else None)
6581 return {
6582 '_type': 'url',
6583 'url': url,
6584 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6585 'video_id': video_id,
6586 'title': title,
6587 'channel_id': channel_id,
6588 'channel': channel,
6589 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6590 'timestamp': timestamp,
6591 }
6592
6593 def _notification_menu_entries(self, ytcfg):
6594 continuation_list = [None]
6595 response = None
6596 for page in itertools.count(1):
6597 ctoken = traverse_obj(
6598 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6599 response = self._extract_response(
6600 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6601 ep='notification/get_notification_menu', check_get_keys='actions',
6602 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6603 yield from self._extract_notification_menu(response, continuation_list)
6604 if not continuation_list[0]:
6605 break
6606
6607 def _real_extract(self, url):
6608 display_id = 'notifications'
6609 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6610 self._report_playlist_authcheck(ytcfg)
6611 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6612
6613
6614 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6615 IE_DESC = 'YouTube search'
6616 IE_NAME = 'youtube:search'
6617 _SEARCH_KEY = 'ytsearch'
6618 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6619 _TESTS = [{
6620 'url': 'ytsearch5:youtube-dl test video',
6621 'playlist_count': 5,
6622 'info_dict': {
6623 'id': 'youtube-dl test video',
6624 'title': 'youtube-dl test video',
6625 }
6626 }]
6627
6628
6629 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6630 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6631 _SEARCH_KEY = 'ytsearchdate'
6632 IE_DESC = 'YouTube search, newest videos first'
6633 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6634 _TESTS = [{
6635 'url': 'ytsearchdate5:youtube-dl test video',
6636 'playlist_count': 5,
6637 'info_dict': {
6638 'id': 'youtube-dl test video',
6639 'title': 'youtube-dl test video',
6640 }
6641 }]
6642
6643
6644 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6645 IE_DESC = 'YouTube search URLs with sorting and filter support'
6646 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6647 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6648 _TESTS = [{
6649 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6650 'playlist_mincount': 5,
6651 'info_dict': {
6652 'id': 'youtube-dl test video',
6653 'title': 'youtube-dl test video',
6654 }
6655 }, {
6656 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6657 'playlist_mincount': 5,
6658 'info_dict': {
6659 'id': 'python',
6660 'title': 'python',
6661 }
6662 }, {
6663 'url': 'https://www.youtube.com/results?search_query=%23cats',
6664 'playlist_mincount': 1,
6665 'info_dict': {
6666 'id': '#cats',
6667 'title': '#cats',
6668 # The test suite does not have support for nested playlists
6669 # 'entries': [{
6670 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6671 # 'title': '#cats',
6672 # }],
6673 },
6674 }, {
6675 # Channel results
6676 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6677 'info_dict': {
6678 'id': 'kurzgesagt',
6679 'title': 'kurzgesagt',
6680 },
6681 'playlist': [{
6682 'info_dict': {
6683 '_type': 'url',
6684 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6685 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6686 'ie_key': 'YoutubeTab',
6687 'channel': 'Kurzgesagt – In a Nutshell',
6688 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6689 'title': 'Kurzgesagt – In a Nutshell',
6690 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6691 'playlist_count': int, # XXX: should have a way of saying > 1
6692 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6693 'thumbnails': list
6694 }
6695 }],
6696 'params': {'extract_flat': True, 'playlist_items': '1'},
6697 'playlist_mincount': 1,
6698 }, {
6699 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6700 'only_matching': True,
6701 }]
6702
6703 def _real_extract(self, url):
6704 qs = parse_qs(url)
6705 query = (qs.get('search_query') or qs.get('q'))[0]
6706 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6707
6708
6709 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6710 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6711 IE_NAME = 'youtube:music:search_url'
6712 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6713 _TESTS = [{
6714 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6715 'playlist_count': 16,
6716 'info_dict': {
6717 'id': 'royalty free music',
6718 'title': 'royalty free music',
6719 }
6720 }, {
6721 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6722 'playlist_mincount': 30,
6723 'info_dict': {
6724 'id': 'royalty free music - songs',
6725 'title': 'royalty free music - songs',
6726 },
6727 'params': {'extract_flat': 'in_playlist'}
6728 }, {
6729 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6730 'playlist_mincount': 30,
6731 'info_dict': {
6732 'id': 'royalty free music - community playlists',
6733 'title': 'royalty free music - community playlists',
6734 },
6735 'params': {'extract_flat': 'in_playlist'}
6736 }]
6737
6738 _SECTIONS = {
6739 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6740 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6741 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6742 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6743 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6744 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6745 }
6746
6747 def _real_extract(self, url):
6748 qs = parse_qs(url)
6749 query = (qs.get('search_query') or qs.get('q'))[0]
6750 params = qs.get('sp', (None,))[0]
6751 if params:
6752 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6753 else:
6754 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6755 params = self._SECTIONS.get(section)
6756 if not params:
6757 section = None
6758 title = join_nonempty(query, section, delim=' - ')
6759 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6760
6761
6762 class YoutubeFeedsInfoExtractor(InfoExtractor):
6763 """
6764 Base class for feed extractors
6765 Subclasses must re-define the _FEED_NAME property.
6766 """
6767 _LOGIN_REQUIRED = True
6768 _FEED_NAME = 'feeds'
6769
6770 def _real_initialize(self):
6771 YoutubeBaseInfoExtractor._check_login_required(self)
6772
6773 @classproperty
6774 def IE_NAME(self):
6775 return f'youtube:{self._FEED_NAME}'
6776
6777 def _real_extract(self, url):
6778 return self.url_result(
6779 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6780
6781
6782 class YoutubeWatchLaterIE(InfoExtractor):
6783 IE_NAME = 'youtube:watchlater'
6784 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6785 _VALID_URL = r':ytwatchlater'
6786 _TESTS = [{
6787 'url': ':ytwatchlater',
6788 'only_matching': True,
6789 }]
6790
6791 def _real_extract(self, url):
6792 return self.url_result(
6793 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6794
6795
6796 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6797 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6798 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6799 _FEED_NAME = 'recommended'
6800 _LOGIN_REQUIRED = False
6801 _TESTS = [{
6802 'url': ':ytrec',
6803 'only_matching': True,
6804 }, {
6805 'url': ':ytrecommended',
6806 'only_matching': True,
6807 }, {
6808 'url': 'https://youtube.com',
6809 'only_matching': True,
6810 }]
6811
6812
6813 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6814 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6815 _VALID_URL = r':ytsub(?:scription)?s?'
6816 _FEED_NAME = 'subscriptions'
6817 _TESTS = [{
6818 'url': ':ytsubs',
6819 'only_matching': True,
6820 }, {
6821 'url': ':ytsubscriptions',
6822 'only_matching': True,
6823 }]
6824
6825
6826 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6827 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6828 _VALID_URL = r':ythis(?:tory)?'
6829 _FEED_NAME = 'history'
6830 _TESTS = [{
6831 'url': ':ythistory',
6832 'only_matching': True,
6833 }]
6834
6835
6836 class YoutubeStoriesIE(InfoExtractor):
6837 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6838 IE_NAME = 'youtube:stories'
6839 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6840 _TESTS = [{
6841 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6842 'only_matching': True,
6843 }]
6844
6845 def _real_extract(self, url):
6846 playlist_id = f'RLTD{self._match_id(url)}'
6847 return self.url_result(
6848 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6849 ie=YoutubeTabIE, video_id=playlist_id)
6850
6851
6852 class YoutubeShortsAudioPivotIE(InfoExtractor):
6853 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6854 IE_NAME = 'youtube:shorts:pivot:audio'
6855 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6856 _TESTS = [{
6857 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6858 'only_matching': True,
6859 }]
6860
6861 @staticmethod
6862 def _generate_audio_pivot_params(video_id):
6863 """
6864 Generates sfv_audio_pivot browse params for this video id
6865 """
6866 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6867 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6868
6869 def _real_extract(self, url):
6870 video_id = self._match_id(url)
6871 return self.url_result(
6872 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6873 ie=YoutubeTabIE)
6874
6875
6876 class YoutubeTruncatedURLIE(InfoExtractor):
6877 IE_NAME = 'youtube:truncated_url'
6878 IE_DESC = False # Do not list
6879 _VALID_URL = r'''(?x)
6880 (?:https?://)?
6881 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6882 (?:watch\?(?:
6883 feature=[a-z_]+|
6884 annotation_id=annotation_[^&]+|
6885 x-yt-cl=[0-9]+|
6886 hl=[^&]*|
6887 t=[0-9]+
6888 )?
6889 |
6890 attribution_link\?a=[^&]+
6891 )
6892 $
6893 '''
6894
6895 _TESTS = [{
6896 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6897 'only_matching': True,
6898 }, {
6899 'url': 'https://www.youtube.com/watch?',
6900 'only_matching': True,
6901 }, {
6902 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6903 'only_matching': True,
6904 }, {
6905 'url': 'https://www.youtube.com/watch?feature=foo',
6906 'only_matching': True,
6907 }, {
6908 'url': 'https://www.youtube.com/watch?hl=en-GB',
6909 'only_matching': True,
6910 }, {
6911 'url': 'https://www.youtube.com/watch?t=2372',
6912 'only_matching': True,
6913 }]
6914
6915 def _real_extract(self, url):
6916 raise ExtractorError(
6917 'Did you forget to quote the URL? Remember that & is a meta '
6918 'character in most shells, so you want to put the URL in quotes, '
6919 'like youtube-dl '
6920 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6921 ' or simply youtube-dl BaW_jenozKc .',
6922 expected=True)
6923
6924
6925 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6926 IE_NAME = 'youtube:clip'
6927 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6928 _TESTS = [{
6929 # FIXME: Other metadata should be extracted from the clip, not from the base video
6930 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6931 'info_dict': {
6932 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6933 'ext': 'mp4',
6934 'section_start': 29.0,
6935 'section_end': 39.7,
6936 'duration': 10.7,
6937 'age_limit': 0,
6938 'availability': 'public',
6939 'categories': ['Gaming'],
6940 'channel': 'Scott The Woz',
6941 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6942 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6943 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6944 'like_count': int,
6945 'playable_in_embed': True,
6946 'tags': 'count:17',
6947 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6948 'title': 'Mobile Games on Console - Scott The Woz',
6949 'upload_date': '20210920',
6950 'uploader': 'Scott The Woz',
6951 'uploader_id': 'scottthewoz',
6952 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6953 'view_count': int,
6954 'live_status': 'not_live',
6955 'channel_follower_count': int
6956 }
6957 }]
6958
6959 def _real_extract(self, url):
6960 clip_id = self._match_id(url)
6961 _, data = self._extract_webpage(url, clip_id)
6962
6963 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6964 if not video_id:
6965 raise ExtractorError('Unable to find video ID')
6966
6967 clip_data = traverse_obj(data, (
6968 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6969 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6970 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6971 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6972
6973 return {
6974 '_type': 'url_transparent',
6975 'url': f'https://www.youtube.com/watch?v={video_id}',
6976 'ie_key': YoutubeIE.ie_key(),
6977 'id': clip_id,
6978 'section_start': int(clip_data['startTimeMs']) / 1000,
6979 'section_end': int(clip_data['endTimeMs']) / 1000,
6980 }
6981
6982
6983 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
6984 IE_NAME = 'youtube:consent'
6985 IE_DESC = False # Do not list
6986 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
6987 _TESTS = [{
6988 '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',
6989 'info_dict': {
6990 'id': 'qVv6vCqciTM',
6991 'ext': 'mp4',
6992 'age_limit': 0,
6993 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
6994 'comment_count': int,
6995 'chapters': 'count:13',
6996 'upload_date': '20221223',
6997 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
6998 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
6999 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7000 'like_count': int,
7001 'release_date': '20221223',
7002 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7003 '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】',
7004 'view_count': int,
7005 'playable_in_embed': True,
7006 'duration': 4438,
7007 'availability': 'public',
7008 'channel_follower_count': int,
7009 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7010 'categories': ['Entertainment'],
7011 'live_status': 'was_live',
7012 'release_timestamp': 1671793345,
7013 'channel': 'さなちゃんねる',
7014 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7015 'uploader': 'さなちゃんねる',
7016 },
7017 'add_ie': ['Youtube'],
7018 'params': {'skip_download': 'Youtube'},
7019 }]
7020
7021 def _real_extract(self, url):
7022 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7023 if not redirect_url:
7024 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7025 return self.url_result(redirect_url)
7026
7027
7028 class YoutubeTruncatedIDIE(InfoExtractor):
7029 IE_NAME = 'youtube:truncated_id'
7030 IE_DESC = False # Do not list
7031 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7032
7033 _TESTS = [{
7034 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7035 'only_matching': True,
7036 }]
7037
7038 def _real_extract(self, url):
7039 video_id = self._match_id(url)
7040 raise ExtractorError(
7041 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
7042 expected=True)