]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[build] Only archive if `vars.ARCHIVE_REPO` is set
[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(
3209 chapter_list,
3210 chapter_time=lambda chapter: float_or_none(
3211 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3212 chapter_title=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(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3226 chapter_time, chapter_title, duration)
3227 for contents in content_list)), [])
3228
3229 def _extract_chapters_from_description(self, description, duration):
3230 duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
3231 sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
3232 return self._extract_chapters(
3233 re.findall(sep_re % (duration_re, r'.+?'), description or ''),
3234 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
3235 duration=duration, strict=False) or self._extract_chapters(
3236 re.findall(sep_re % (r'.+?', duration_re), description or ''),
3237 chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
3238 duration=duration, strict=False)
3239
3240 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3241 if not duration:
3242 return
3243 chapter_list = [{
3244 'start_time': chapter_time(chapter),
3245 'title': chapter_title(chapter),
3246 } for chapter in chapter_list or []]
3247 if not strict:
3248 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3249
3250 chapters = [{'start_time': 0}]
3251 for idx, chapter in enumerate(chapter_list):
3252 if chapter['start_time'] is None:
3253 self.report_warning(f'Incomplete chapter {idx}')
3254 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
3255 chapters.append(chapter)
3256 elif chapter not in chapters:
3257 self.report_warning(
3258 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
3259 return chapters[1:]
3260
3261 def _extract_comment(self, comment_renderer, parent=None):
3262 comment_id = comment_renderer.get('commentId')
3263 if not comment_id:
3264 return
3265
3266 text = self._get_text(comment_renderer, 'contentText')
3267
3268 # Timestamp is an estimate calculated from the current time and time_text
3269 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3270 timestamp = self._parse_time_text(time_text)
3271
3272 author = self._get_text(comment_renderer, 'authorText')
3273 author_id = try_get(comment_renderer,
3274 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3275
3276 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3277 lambda x: x['likeCount']), str)) or 0
3278 author_thumbnail = try_get(comment_renderer,
3279 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3280
3281 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3282 is_favorited = 'creatorHeart' in (try_get(
3283 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3284 return {
3285 'id': comment_id,
3286 'text': text,
3287 'timestamp': timestamp,
3288 'time_text': time_text,
3289 'like_count': votes,
3290 'is_favorited': is_favorited,
3291 'author': author,
3292 'author_id': author_id,
3293 'author_thumbnail': author_thumbnail,
3294 'author_is_uploader': author_is_uploader,
3295 'parent': parent or 'root'
3296 }
3297
3298 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3299
3300 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3301
3302 def extract_header(contents):
3303 _continuation = None
3304 for content in contents:
3305 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3306 expected_comment_count = self._get_count(
3307 comments_header_renderer, 'countText', 'commentsCount')
3308
3309 if expected_comment_count:
3310 tracker['est_total'] = expected_comment_count
3311 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3312 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3313
3314 sort_menu_item = try_get(
3315 comments_header_renderer,
3316 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3317 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3318
3319 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3320 if not _continuation:
3321 continue
3322
3323 sort_text = str_or_none(sort_menu_item.get('title'))
3324 if not sort_text:
3325 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3326 self.to_screen('Sorting comments by %s' % sort_text.lower())
3327 break
3328 return _continuation
3329
3330 def extract_thread(contents):
3331 if not parent:
3332 tracker['current_page_thread'] = 0
3333 for content in contents:
3334 if not parent and tracker['total_parent_comments'] >= max_parents:
3335 yield
3336 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3337 comment_renderer = get_first(
3338 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3339 expected_type=dict, default={})
3340
3341 comment = self._extract_comment(comment_renderer, parent)
3342 if not comment:
3343 continue
3344 # Sometimes YouTube may break and give us infinite looping comments.
3345 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
3346 if comment['id'] in tracker['seen_comment_ids']:
3347 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3348 yield
3349 else:
3350 tracker['seen_comment_ids'].add(comment['id'])
3351
3352 tracker['running_total'] += 1
3353 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3354 yield comment
3355
3356 # Attempt to get the replies
3357 comment_replies_renderer = try_get(
3358 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3359
3360 if comment_replies_renderer:
3361 tracker['current_page_thread'] += 1
3362 comment_entries_iter = self._comment_entries(
3363 comment_replies_renderer, ytcfg, video_id,
3364 parent=comment.get('id'), tracker=tracker)
3365 yield from itertools.islice(comment_entries_iter, min(
3366 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3367
3368 # Keeps track of counts across recursive calls
3369 if not tracker:
3370 tracker = dict(
3371 running_total=0,
3372 est_total=0,
3373 current_page_thread=0,
3374 total_parent_comments=0,
3375 total_reply_comments=0,
3376 seen_comment_ids=set())
3377
3378 # TODO: Deprecated
3379 # YouTube comments have a max depth of 2
3380 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3381 if max_depth:
3382 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3383 'Set max replies in the max-comments extractor argument instead')
3384 if max_depth == 1 and parent:
3385 return
3386
3387 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3388 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3389
3390 continuation = self._extract_continuation(root_continuation_data)
3391
3392 response = None
3393 is_forced_continuation = False
3394 is_first_continuation = parent is None
3395 if is_first_continuation and not continuation:
3396 # Sometimes you can get comments by generating the continuation yourself,
3397 # even if YouTube initially reports them being disabled - e.g. stories comments.
3398 # Note: if the comment section is actually disabled, YouTube may return a response with
3399 # required check_get_keys missing. So we will disable that check initially in this case.
3400 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3401 is_forced_continuation = True
3402
3403 for page_num in itertools.count(0):
3404 if not continuation:
3405 break
3406 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3407 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
3408 if page_num == 0:
3409 if is_first_continuation:
3410 note_prefix = 'Downloading comment section API JSON'
3411 else:
3412 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3413 tracker['current_page_thread'], comment_prog_str)
3414 else:
3415 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3416 ' ' if parent else '', ' replies' if parent else '',
3417 page_num, comment_prog_str)
3418 try:
3419 response = self._extract_response(
3420 item_id=None, query=continuation,
3421 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3422 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3423 except ExtractorError as e:
3424 # Ignore incomplete data error for replies if retries didn't work.
3425 # This is to allow any other parent comments and comment threads to be downloaded.
3426 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3427 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3428 self.report_warning(
3429 'Received incomplete data for a comment reply thread and retrying did not help. '
3430 'Ignoring to let other comments be downloaded.')
3431 else:
3432 raise
3433 is_forced_continuation = False
3434 continuation_contents = traverse_obj(
3435 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3436
3437 continuation = None
3438 for continuation_section in continuation_contents:
3439 continuation_items = traverse_obj(
3440 continuation_section,
3441 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3442 get_all=False, expected_type=list) or []
3443 if is_first_continuation:
3444 continuation = extract_header(continuation_items)
3445 is_first_continuation = False
3446 if continuation:
3447 break
3448 continue
3449
3450 for entry in extract_thread(continuation_items):
3451 if not entry:
3452 return
3453 yield entry
3454 continuation = self._extract_continuation({'contents': continuation_items})
3455 if continuation:
3456 break
3457
3458 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3459 if message and not parent and tracker['running_total'] == 0:
3460 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3461 raise self.CommentsDisabled
3462
3463 @staticmethod
3464 def _generate_comment_continuation(video_id):
3465 """
3466 Generates initial comment section continuation token from given video id
3467 """
3468 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3469 return base64.b64encode(token.encode()).decode()
3470
3471 def _get_comments(self, ytcfg, video_id, contents, webpage):
3472 """Entry for comment extraction"""
3473 def _real_comment_extract(contents):
3474 renderer = next((
3475 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3476 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3477 yield from self._comment_entries(renderer, ytcfg, video_id)
3478
3479 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3480 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3481
3482 @staticmethod
3483 def _get_checkok_params():
3484 return {'contentCheckOk': True, 'racyCheckOk': True}
3485
3486 @classmethod
3487 def _generate_player_context(cls, sts=None):
3488 context = {
3489 'html5Preference': 'HTML5_PREF_WANTS',
3490 }
3491 if sts is not None:
3492 context['signatureTimestamp'] = sts
3493 return {
3494 'playbackContext': {
3495 'contentPlaybackContext': context
3496 },
3497 **cls._get_checkok_params()
3498 }
3499
3500 @staticmethod
3501 def _is_agegated(player_response):
3502 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3503 return True
3504
3505 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
3506 AGE_GATE_REASONS = (
3507 'confirm your age', 'age-restricted', 'inappropriate', # reason
3508 'age_verification_required', 'age_check_required', # status
3509 )
3510 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3511
3512 @staticmethod
3513 def _is_unplayable(player_response):
3514 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3515
3516 _STORY_PLAYER_PARAMS = '8AEB'
3517
3518 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3519
3520 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3521 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3522 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3523 headers = self.generate_api_headers(
3524 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3525
3526 yt_query = {
3527 'videoId': video_id,
3528 }
3529 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3530 yt_query['params'] = self._STORY_PLAYER_PARAMS
3531
3532 yt_query.update(self._generate_player_context(sts))
3533 return self._extract_response(
3534 item_id=video_id, ep='player', query=yt_query,
3535 ytcfg=player_ytcfg, headers=headers, fatal=True,
3536 default_client=client,
3537 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3538 ) or None
3539
3540 def _get_requested_clients(self, url, smuggled_data):
3541 requested_clients = []
3542 default = ['android', 'web']
3543 allowed_clients = sorted(
3544 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3545 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3546 for client in self._configuration_arg('player_client'):
3547 if client in allowed_clients:
3548 requested_clients.append(client)
3549 elif client == 'default':
3550 requested_clients.extend(default)
3551 elif client == 'all':
3552 requested_clients.extend(allowed_clients)
3553 else:
3554 self.report_warning(f'Skipping unsupported client {client}')
3555 if not requested_clients:
3556 requested_clients = default
3557
3558 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3559 requested_clients.extend(
3560 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3561
3562 return orderedSet(requested_clients)
3563
3564 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3565 initial_pr = None
3566 if webpage:
3567 initial_pr = self._search_json(
3568 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3569
3570 all_clients = set(clients)
3571 clients = clients[::-1]
3572 prs = []
3573
3574 def append_client(*client_names):
3575 """ Append the first client name that exists but not already used """
3576 for client_name in client_names:
3577 actual_client = _split_innertube_client(client_name)[0]
3578 if actual_client in INNERTUBE_CLIENTS:
3579 if actual_client not in all_clients:
3580 clients.append(client_name)
3581 all_clients.add(actual_client)
3582 return
3583
3584 # Android player_response does not have microFormats which are needed for
3585 # extraction of some data. So we return the initial_pr with formats
3586 # stripped out even if not requested by the user
3587 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3588 if initial_pr:
3589 pr = dict(initial_pr)
3590 pr['streamingData'] = None
3591 prs.append(pr)
3592
3593 last_error = None
3594 tried_iframe_fallback = False
3595 player_url = None
3596 while clients:
3597 client, base_client, variant = _split_innertube_client(clients.pop())
3598 player_ytcfg = master_ytcfg if client == 'web' else {}
3599 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3600 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3601
3602 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3603 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3604 if 'js' in self._configuration_arg('player_skip'):
3605 require_js_player = False
3606 player_url = None
3607
3608 if not player_url and not tried_iframe_fallback and require_js_player:
3609 player_url = self._download_player_url(video_id)
3610 tried_iframe_fallback = True
3611
3612 try:
3613 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3614 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3615 except ExtractorError as e:
3616 if last_error:
3617 self.report_warning(last_error)
3618 last_error = e
3619 continue
3620
3621 if pr:
3622 # YouTube may return a different video player response than expected.
3623 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3624 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3625 if pr_video_id and pr_video_id != video_id:
3626 self.report_warning(
3627 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
3628 else:
3629 prs.append(pr)
3630
3631 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3632 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3633 append_client(f'{base_client}_creator')
3634 elif self._is_agegated(pr):
3635 if variant == 'tv_embedded':
3636 append_client(f'{base_client}_embedded')
3637 elif not variant:
3638 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3639
3640 if last_error:
3641 if not len(prs):
3642 raise last_error
3643 self.report_warning(last_error)
3644 return prs, player_url
3645
3646 def _needs_live_processing(self, live_status, duration):
3647 if (live_status == 'is_live' and self.get_param('live_from_start')
3648 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3649 return live_status
3650
3651 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3652 itags, stream_ids = collections.defaultdict(set), []
3653 itag_qualities, res_qualities = {}, {0: None}
3654 q = qualities([
3655 # Normally tiny is the smallest video-only formats. But
3656 # audio-only formats with unknown quality may get tagged as tiny
3657 'tiny',
3658 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3659 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3660 ])
3661 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
3662
3663 for fmt in streaming_formats:
3664 if fmt.get('targetDurationSec'):
3665 continue
3666
3667 itag = str_or_none(fmt.get('itag'))
3668 audio_track = fmt.get('audioTrack') or {}
3669 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
3670 if stream_id in stream_ids:
3671 continue
3672
3673 quality = fmt.get('quality')
3674 height = int_or_none(fmt.get('height'))
3675 if quality == 'tiny' or not quality:
3676 quality = fmt.get('audioQuality', '').lower() or quality
3677 # The 3gp format (17) in android client has a quality of "small",
3678 # but is actually worse than other formats
3679 if itag == '17':
3680 quality = 'tiny'
3681 if quality:
3682 if itag:
3683 itag_qualities[itag] = quality
3684 if height:
3685 res_qualities[height] = quality
3686 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3687 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3688 # number of fragment that would subsequently requested with (`&sq=N`)
3689 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3690 continue
3691
3692 fmt_url = fmt.get('url')
3693 if not fmt_url:
3694 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3695 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3696 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3697 if not all((sc, fmt_url, player_url, encrypted_sig)):
3698 continue
3699 try:
3700 fmt_url += '&%s=%s' % (
3701 traverse_obj(sc, ('sp', -1)) or 'signature',
3702 self._decrypt_signature(encrypted_sig, video_id, player_url)
3703 )
3704 except ExtractorError as e:
3705 self.report_warning('Signature extraction failed: Some formats may be missing',
3706 video_id=video_id, only_once=True)
3707 self.write_debug(e, only_once=True)
3708 continue
3709
3710 query = parse_qs(fmt_url)
3711 throttled = False
3712 if query.get('n'):
3713 try:
3714 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3715 fmt_url = update_url_query(fmt_url, {
3716 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3717 })
3718 except ExtractorError as e:
3719 phantomjs_hint = ''
3720 if isinstance(e, JSInterpreter.Exception):
3721 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3722 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3723 if player_url:
3724 self.report_warning(
3725 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3726 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3727 self.write_debug(e, only_once=True)
3728 else:
3729 self.report_warning(
3730 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3731 video_id=video_id, only_once=True)
3732 throttled = True
3733
3734 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3735 language_preference = (
3736 10 if audio_track.get('audioIsDefault') and 10
3737 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3738 else -1)
3739 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3740 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3741 # Make sure to avoid false positives with small duration differences.
3742 # E.g. __2ABJjxzNo, ySuUZEjARPY
3743 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3744 if is_damaged:
3745 self.report_warning(
3746 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3747 dct = {
3748 'asr': int_or_none(fmt.get('audioSampleRate')),
3749 'filesize': int_or_none(fmt.get('contentLength')),
3750 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
3751 'format_note': join_nonempty(
3752 '%s%s' % (audio_track.get('displayName') or '',
3753 ' (default)' if language_preference > 0 else ''),
3754 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3755 'DRC' if fmt.get('isDrc') else None,
3756 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3757 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3758 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3759 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3760 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3761 'fps': int_or_none(fmt.get('fps')) or None,
3762 'audio_channels': fmt.get('audioChannels'),
3763 'height': height,
3764 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
3765 'has_drm': bool(fmt.get('drmFamilies')),
3766 'tbr': tbr,
3767 'url': fmt_url,
3768 'width': int_or_none(fmt.get('width')),
3769 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3770 'desc' if language_preference < -1 else '') or None,
3771 'language_preference': language_preference,
3772 # Strictly de-prioritize damaged and 3gp formats
3773 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3774 }
3775 mime_mobj = re.match(
3776 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3777 if mime_mobj:
3778 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3779 dct.update(parse_codecs(mime_mobj.group(2)))
3780 no_audio = dct.get('acodec') == 'none'
3781 no_video = dct.get('vcodec') == 'none'
3782 if no_audio:
3783 dct['vbr'] = tbr
3784 if no_video:
3785 dct['abr'] = tbr
3786 if no_audio or no_video:
3787 CHUNK_SIZE = 10 << 20
3788 dct.update({
3789 'protocol': 'http_dash_segments',
3790 'fragments': [{
3791 'url': update_url_query(dct['url'], {
3792 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, dct["filesize"])}'
3793 })
3794 } for range_start in range(0, dct['filesize'], CHUNK_SIZE)]
3795 } if dct['filesize'] else {
3796 'downloader_options': {'http_chunk_size': CHUNK_SIZE} # No longer useful?
3797 })
3798
3799 if dct.get('ext'):
3800 dct['container'] = dct['ext'] + '_dash'
3801
3802 if itag:
3803 itags[itag].add(('https', dct.get('language')))
3804 stream_ids.append(stream_id)
3805 yield dct
3806
3807 needs_live_processing = self._needs_live_processing(live_status, duration)
3808 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3809
3810 skip_manifests = set(self._configuration_arg('skip'))
3811 if (not self.get_param('youtube_include_hls_manifest', True)
3812 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3813 or needs_live_processing and skip_bad_formats):
3814 skip_manifests.add('hls')
3815
3816 if not self.get_param('youtube_include_dash_manifest', True):
3817 skip_manifests.add('dash')
3818 if self._configuration_arg('include_live_dash'):
3819 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3820 'Use include_incomplete_formats extractor argument instead')
3821 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3822 skip_manifests.add('dash')
3823
3824 def process_manifest_format(f, proto, itag):
3825 key = (proto, f.get('language'))
3826 if key in itags[itag]:
3827 return False
3828 itags[itag].add(key)
3829
3830 if any(p != proto for p, _ in itags[itag]):
3831 f['format_id'] = f'{itag}-{proto}'
3832 elif itag:
3833 f['format_id'] = itag
3834
3835 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3836 if f['quality'] == -1 and f.get('height'):
3837 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3838 return True
3839
3840 subtitles = {}
3841 for sd in streaming_data:
3842 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3843 if hls_manifest_url:
3844 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3845 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3846 subtitles = self._merge_subtitles(subs, subtitles)
3847 for f in fmts:
3848 if process_manifest_format(f, 'hls', self._search_regex(
3849 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3850 yield f
3851
3852 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3853 if dash_manifest_url:
3854 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3855 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3856 for f in formats:
3857 if process_manifest_format(f, 'dash', f['format_id']):
3858 f['filesize'] = int_or_none(self._search_regex(
3859 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3860 if needs_live_processing:
3861 f['is_from_start'] = True
3862
3863 yield f
3864 yield subtitles
3865
3866 def _extract_storyboard(self, player_responses, duration):
3867 spec = get_first(
3868 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3869 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3870 if not base_url:
3871 return
3872 L = len(spec) - 1
3873 for i, args in enumerate(spec):
3874 args = args.split('#')
3875 counts = list(map(int_or_none, args[:5]))
3876 if len(args) != 8 or not all(counts):
3877 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3878 continue
3879 width, height, frame_count, cols, rows = counts
3880 N, sigh = args[6:]
3881
3882 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3883 fragment_count = frame_count / (cols * rows)
3884 fragment_duration = duration / fragment_count
3885 yield {
3886 'format_id': f'sb{i}',
3887 'format_note': 'storyboard',
3888 'ext': 'mhtml',
3889 'protocol': 'mhtml',
3890 'acodec': 'none',
3891 'vcodec': 'none',
3892 'url': url,
3893 'width': width,
3894 'height': height,
3895 'fps': frame_count / duration,
3896 'rows': rows,
3897 'columns': cols,
3898 'fragments': [{
3899 'url': url.replace('$M', str(j)),
3900 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3901 } for j in range(math.ceil(fragment_count))],
3902 }
3903
3904 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3905 webpage = None
3906 if 'webpage' not in self._configuration_arg('player_skip'):
3907 query = {'bpctr': '9999999999', 'has_verified': '1'}
3908 if smuggled_data.get('is_story'):
3909 query['pp'] = self._STORY_PLAYER_PARAMS
3910 webpage = self._download_webpage(
3911 webpage_url, video_id, fatal=False, query=query)
3912
3913 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3914
3915 player_responses, player_url = self._extract_player_responses(
3916 self._get_requested_clients(url, smuggled_data),
3917 video_id, webpage, master_ytcfg, smuggled_data)
3918
3919 return webpage, master_ytcfg, player_responses, player_url
3920
3921 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3922 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3923 is_live = get_first(video_details, 'isLive')
3924 if is_live is None:
3925 is_live = get_first(live_broadcast_details, 'isLiveNow')
3926 live_content = get_first(video_details, 'isLiveContent')
3927 is_upcoming = get_first(video_details, 'isUpcoming')
3928 post_live = get_first(video_details, 'isPostLiveDvr')
3929 live_status = ('post_live' if post_live
3930 else 'is_live' if is_live
3931 else 'is_upcoming' if is_upcoming
3932 else 'was_live' if live_content
3933 else 'not_live' if False in (is_live, live_content)
3934 else None)
3935 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
3936 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3937
3938 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3939
3940 def _real_extract(self, url):
3941 url, smuggled_data = unsmuggle_url(url, {})
3942 video_id = self._match_id(url)
3943
3944 base_url = self.http_scheme() + '//www.youtube.com/'
3945 webpage_url = base_url + 'watch?v=' + video_id
3946
3947 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3948
3949 playability_statuses = traverse_obj(
3950 player_responses, (..., 'playabilityStatus'), expected_type=dict)
3951
3952 trailer_video_id = get_first(
3953 playability_statuses,
3954 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3955 expected_type=str)
3956 if trailer_video_id:
3957 return self.url_result(
3958 trailer_video_id, self.ie_key(), trailer_video_id)
3959
3960 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3961 if webpage else (lambda x: None))
3962
3963 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
3964 microformats = traverse_obj(
3965 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3966 expected_type=dict)
3967
3968 translated_title = self._get_text(microformats, (..., 'title'))
3969 video_title = (self._preferred_lang and translated_title
3970 or get_first(video_details, 'title') # primary
3971 or translated_title
3972 or search_meta(['og:title', 'twitter:title', 'title']))
3973 translated_description = self._get_text(microformats, (..., 'description'))
3974 original_description = get_first(video_details, 'shortDescription')
3975 video_description = (
3976 self._preferred_lang and translated_description
3977 # If original description is blank, it will be an empty string.
3978 # Do not prefer translated description in this case.
3979 or original_description if original_description is not None else translated_description)
3980
3981 multifeed_metadata_list = get_first(
3982 player_responses,
3983 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3984 expected_type=str)
3985 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3986 if self.get_param('noplaylist'):
3987 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3988 else:
3989 entries = []
3990 feed_ids = []
3991 for feed in multifeed_metadata_list.split(','):
3992 # Unquote should take place before split on comma (,) since textual
3993 # fields may contain comma as well (see
3994 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3995 feed_data = urllib.parse.parse_qs(
3996 urllib.parse.unquote_plus(feed))
3997
3998 def feed_entry(name):
3999 return try_get(
4000 feed_data, lambda x: x[name][0], str)
4001
4002 feed_id = feed_entry('id')
4003 if not feed_id:
4004 continue
4005 feed_title = feed_entry('title')
4006 title = video_title
4007 if feed_title:
4008 title += ' (%s)' % feed_title
4009 entries.append({
4010 '_type': 'url_transparent',
4011 'ie_key': 'Youtube',
4012 'url': smuggle_url(
4013 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4014 {'force_singlefeed': True}),
4015 'title': title,
4016 })
4017 feed_ids.append(feed_id)
4018 self.to_screen(
4019 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4020 % (', '.join(feed_ids), video_id))
4021 return self.playlist_result(
4022 entries, video_id, video_title, video_description)
4023
4024 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4025 or int_or_none(get_first(microformats, 'lengthSeconds'))
4026 or parse_duration(search_meta('duration')) or None)
4027
4028 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4029 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4030 if live_status == 'post_live':
4031 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
4032
4033 if not formats:
4034 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
4035 self.report_drm(video_id)
4036 pemr = get_first(
4037 playability_statuses,
4038 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4039 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4040 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
4041 if subreason:
4042 if subreason == 'The uploader has not made this video available in your country.':
4043 countries = get_first(microformats, 'availableCountries')
4044 if not countries:
4045 regions_allowed = search_meta('regionsAllowed')
4046 countries = regions_allowed.split(',') if regions_allowed else None
4047 self.raise_geo_restricted(subreason, countries, metadata_available=True)
4048 reason += f'. {subreason}'
4049 if reason:
4050 self.raise_no_formats(reason, expected=True)
4051
4052 keywords = get_first(video_details, 'keywords', expected_type=list) or []
4053 if not keywords and webpage:
4054 keywords = [
4055 unescapeHTML(m.group('content'))
4056 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4057 for keyword in keywords:
4058 if keyword.startswith('yt:stretch='):
4059 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4060 if mobj:
4061 # NB: float is intentional for forcing float division
4062 w, h = (float(v) for v in mobj.groups())
4063 if w > 0 and h > 0:
4064 ratio = w / h
4065 for f in formats:
4066 if f.get('vcodec') != 'none':
4067 f['stretched_ratio'] = ratio
4068 break
4069 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
4070 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4071 if thumbnail_url:
4072 thumbnails.append({
4073 'url': thumbnail_url,
4074 })
4075 original_thumbnails = thumbnails.copy()
4076
4077 # The best resolution thumbnails sometimes does not appear in the webpage
4078 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4079 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4080 thumbnail_names = [
4081 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4082 # in resolution, these are not the custom thumbnail. So de-prioritize them
4083 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4084 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4085 ]
4086 n_thumbnail_names = len(thumbnail_names)
4087 thumbnails.extend({
4088 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4089 video_id=video_id, name=name, ext=ext,
4090 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
4091 } for name in thumbnail_names for ext in ('webp', 'jpg'))
4092 for thumb in thumbnails:
4093 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
4094 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
4095 self._remove_duplicate_formats(thumbnails)
4096 self._downloader._sort_thumbnails(original_thumbnails)
4097
4098 category = get_first(microformats, 'category') or search_meta('genre')
4099 channel_id = str_or_none(
4100 get_first(video_details, 'channelId')
4101 or get_first(microformats, 'externalChannelId')
4102 or search_meta('channelId'))
4103 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4104
4105 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4106 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4107 if not duration and live_end_time and live_start_time:
4108 duration = live_end_time - live_start_time
4109
4110 needs_live_processing = self._needs_live_processing(live_status, duration)
4111
4112 def is_bad_format(fmt):
4113 if needs_live_processing and not fmt.get('is_from_start'):
4114 return True
4115 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4116 and fmt.get('protocol') == 'http_dash_segments'):
4117 return True
4118
4119 for fmt in filter(is_bad_format, formats):
4120 fmt['preference'] = (fmt.get('preference') or -1) - 10
4121 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4122
4123 if needs_live_processing:
4124 self._prepare_live_from_start_formats(
4125 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
4126
4127 formats.extend(self._extract_storyboard(player_responses, duration))
4128
4129 info = {
4130 'id': video_id,
4131 'title': video_title,
4132 'formats': formats,
4133 'thumbnails': thumbnails,
4134 # The best thumbnail that we are sure exists. Prevents unnecessary
4135 # URL checking if user don't care about getting the best possible thumbnail
4136 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
4137 'description': video_description,
4138 'uploader': get_first(video_details, 'author'),
4139 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
4140 'uploader_url': owner_profile_url,
4141 'channel_id': channel_id,
4142 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
4143 'duration': duration,
4144 'view_count': int_or_none(
4145 get_first((video_details, microformats), (..., 'viewCount'))
4146 or search_meta('interactionCount')),
4147 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
4148 'age_limit': 18 if (
4149 get_first(microformats, 'isFamilySafe') is False
4150 or search_meta('isFamilyFriendly') == 'false'
4151 or search_meta('og:restrictions:age') == '18+') else 0,
4152 'webpage_url': webpage_url,
4153 'categories': [category] if category else None,
4154 'tags': keywords,
4155 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4156 'live_status': live_status,
4157 'release_timestamp': live_start_time,
4158 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4159 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4160 }
4161
4162 subtitles = {}
4163 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
4164 if pctr:
4165 def get_lang_code(track):
4166 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4167 or track.get('languageCode'))
4168
4169 # Converted into dicts to remove duplicates
4170 captions = {
4171 get_lang_code(sub): sub
4172 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
4173 translation_languages = {
4174 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4175 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
4176
4177 def process_language(container, base_url, lang_code, sub_name, query):
4178 lang_subs = container.setdefault(lang_code, [])
4179 for fmt in self._SUBTITLE_FORMATS:
4180 query.update({
4181 'fmt': fmt,
4182 })
4183 lang_subs.append({
4184 'ext': fmt,
4185 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
4186 'name': sub_name,
4187 })
4188
4189 # NB: Constructing the full subtitle dictionary is slow
4190 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4191 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
4192 for lang_code, caption_track in captions.items():
4193 base_url = caption_track.get('baseUrl')
4194 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
4195 if not base_url:
4196 continue
4197 lang_name = self._get_text(caption_track, 'name', max_runs=1)
4198 if caption_track.get('kind') != 'asr':
4199 if not lang_code:
4200 continue
4201 process_language(
4202 subtitles, base_url, lang_code, lang_name, {})
4203 if not caption_track.get('isTranslatable'):
4204 continue
4205 for trans_code, trans_name in translation_languages.items():
4206 if not trans_code:
4207 continue
4208 orig_trans_code = trans_code
4209 if caption_track.get('kind') != 'asr' and trans_code != 'und':
4210 if not get_translated_subs:
4211 continue
4212 trans_code += f'-{lang_code}'
4213 trans_name += format_field(lang_name, None, ' from %s')
4214 # Add an "-orig" label to the original language so that it can be distinguished.
4215 # The subs are returned without "-orig" as well for compatibility
4216 if lang_code == f'a-{orig_trans_code}':
4217 process_language(
4218 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4219 # Setting tlang=lang returns damaged subtitles.
4220 process_language(automatic_captions, base_url, trans_code, trans_name,
4221 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
4222
4223 info['automatic_captions'] = automatic_captions
4224 info['subtitles'] = subtitles
4225
4226 parsed_url = urllib.parse.urlparse(url)
4227 for component in [parsed_url.fragment, parsed_url.query]:
4228 query = urllib.parse.parse_qs(component)
4229 for k, v in query.items():
4230 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4231 d_k += '_time'
4232 if d_k not in info and k in s_ks:
4233 info[d_k] = parse_duration(query[k][0])
4234
4235 # Youtube Music Auto-generated description
4236 if video_description:
4237 mobj = re.search(
4238 r'''(?xs)
4239 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4240 (?P<album>[^\n]+)
4241 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4242 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4243 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4244 .+\nAuto-generated\ by\ YouTube\.\s*$
4245 ''', video_description)
4246 if mobj:
4247 release_year = mobj.group('release_year')
4248 release_date = mobj.group('release_date')
4249 if release_date:
4250 release_date = release_date.replace('-', '')
4251 if not release_year:
4252 release_year = release_date[:4]
4253 info.update({
4254 'album': mobj.group('album'.strip()),
4255 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4256 'track': mobj.group('track').strip(),
4257 'release_date': release_date,
4258 'release_year': int_or_none(release_year),
4259 })
4260
4261 initial_data = None
4262 if webpage:
4263 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4264 if not initial_data:
4265 query = {'videoId': video_id}
4266 query.update(self._get_checkok_params())
4267 initial_data = self._extract_response(
4268 item_id=video_id, ep='next', fatal=False,
4269 ytcfg=master_ytcfg, query=query,
4270 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4271 note='Downloading initial data API JSON')
4272
4273 info['comment_count'] = traverse_obj(initial_data, (
4274 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4275 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4276 ), (
4277 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4278 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4279 ), expected_type=int_or_none, get_all=False)
4280
4281 try: # This will error if there is no livechat
4282 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4283 except (KeyError, IndexError, TypeError):
4284 pass
4285 else:
4286 info.setdefault('subtitles', {})['live_chat'] = [{
4287 # url is needed to set cookies
4288 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4289 'video_id': video_id,
4290 'ext': 'json',
4291 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4292 else 'youtube_live_chat_replay'),
4293 }]
4294
4295 if initial_data:
4296 info['chapters'] = (
4297 self._extract_chapters_from_json(initial_data, duration)
4298 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4299 or self._extract_chapters_from_description(video_description, duration)
4300 or None)
4301
4302 contents = traverse_obj(
4303 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4304 expected_type=list, default=[])
4305
4306 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4307 if vpir:
4308 stl = vpir.get('superTitleLink')
4309 if stl:
4310 stl = self._get_text(stl)
4311 if try_get(
4312 vpir,
4313 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4314 info['location'] = stl
4315 else:
4316 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4317 if mobj:
4318 info.update({
4319 'series': mobj.group(1),
4320 'season_number': int(mobj.group(2)),
4321 'episode_number': int(mobj.group(3)),
4322 })
4323 for tlb in (try_get(
4324 vpir,
4325 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4326 list) or []):
4327 tbrs = variadic(
4328 traverse_obj(
4329 tlb, ('toggleButtonRenderer', ...),
4330 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4331 for tbr in tbrs:
4332 for getter, regex in [(
4333 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4334 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4335 lambda x: x['accessibility'],
4336 lambda x: x['accessibilityData']['accessibilityData'],
4337 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4338 label = (try_get(tbr, getter, dict) or {}).get('label')
4339 if label:
4340 mobj = re.match(regex, label)
4341 if mobj:
4342 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4343 break
4344 sbr_tooltip = try_get(
4345 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4346 if sbr_tooltip:
4347 like_count, dislike_count = sbr_tooltip.split(' / ')
4348 info.update({
4349 'like_count': str_to_int(like_count),
4350 'dislike_count': str_to_int(dislike_count),
4351 })
4352 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4353 if vcr:
4354 vc = self._get_count(vcr, 'viewCount')
4355 # Upcoming premieres with waiting count are treated as live here
4356 if vcr.get('isLive'):
4357 info['concurrent_view_count'] = vc
4358 elif info.get('view_count') is None:
4359 info['view_count'] = vc
4360
4361 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4362 if vsir:
4363 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4364 info.update({
4365 'channel': self._get_text(vor, 'title'),
4366 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4367
4368 rows = try_get(
4369 vsir,
4370 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4371 list) or []
4372 multiple_songs = False
4373 for row in rows:
4374 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4375 multiple_songs = True
4376 break
4377 for row in rows:
4378 mrr = row.get('metadataRowRenderer') or {}
4379 mrr_title = mrr.get('title')
4380 if not mrr_title:
4381 continue
4382 mrr_title = self._get_text(mrr, 'title')
4383 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4384 if mrr_title == 'License':
4385 info['license'] = mrr_contents_text
4386 elif not multiple_songs:
4387 if mrr_title == 'Album':
4388 info['album'] = mrr_contents_text
4389 elif mrr_title == 'Artist':
4390 info['artist'] = mrr_contents_text
4391 elif mrr_title == 'Song':
4392 info['track'] = mrr_contents_text
4393
4394 fallbacks = {
4395 'channel': 'uploader',
4396 'channel_id': 'uploader_id',
4397 'channel_url': 'uploader_url',
4398 }
4399
4400 # The upload date for scheduled, live and past live streams / premieres in microformats
4401 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4402 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4403 upload_date = (
4404 unified_strdate(get_first(microformats, 'uploadDate'))
4405 or unified_strdate(search_meta('uploadDate')))
4406 if not upload_date or (
4407 live_status in ('not_live', None)
4408 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4409 ):
4410 upload_date = strftime_or_none(
4411 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4412 info['upload_date'] = upload_date
4413
4414 for to, frm in fallbacks.items():
4415 if not info.get(to):
4416 info[to] = info.get(frm)
4417
4418 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4419 v = info.get(s_k)
4420 if v:
4421 info[d_k] = v
4422
4423 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4424
4425 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4426 or get_first(video_details, 'isPrivate', expected_type=bool))
4427
4428 info['availability'] = (
4429 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4430 else self._availability(
4431 is_private=is_private,
4432 needs_premium=(
4433 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4434 or False if initial_data and is_private is not None else None),
4435 needs_subscription=(
4436 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4437 or False if initial_data and is_private is not None else None),
4438 needs_auth=info['age_limit'] >= 18,
4439 is_unlisted=None if is_private is None else (
4440 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4441 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4442
4443 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4444
4445 self.mark_watched(video_id, player_responses)
4446
4447 return info
4448
4449
4450 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4451 @staticmethod
4452 def passthrough_smuggled_data(func):
4453 def _smuggle(info, smuggled_data):
4454 if info.get('_type') not in ('url', 'url_transparent'):
4455 return info
4456 if smuggled_data.get('is_music_url'):
4457 parsed_url = urllib.parse.urlparse(info['url'])
4458 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4459 smuggled_data.pop('is_music_url')
4460 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4461 if smuggled_data:
4462 info['url'] = smuggle_url(info['url'], smuggled_data)
4463 return info
4464
4465 @functools.wraps(func)
4466 def wrapper(self, url):
4467 url, smuggled_data = unsmuggle_url(url, {})
4468 if self.is_music_url(url):
4469 smuggled_data['is_music_url'] = True
4470 info_dict = func(self, url, smuggled_data)
4471 if smuggled_data:
4472 _smuggle(info_dict, smuggled_data)
4473 if info_dict.get('entries'):
4474 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
4475 return info_dict
4476 return wrapper
4477
4478 @staticmethod
4479 def _extract_basic_item_renderer(item):
4480 # Modified from _extract_grid_item_renderer
4481 known_basic_renderers = (
4482 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4483 )
4484 for key, renderer in item.items():
4485 if not isinstance(renderer, dict):
4486 continue
4487 elif key in known_basic_renderers:
4488 return renderer
4489 elif key.startswith('grid') and key.endswith('Renderer'):
4490 return renderer
4491
4492 def _extract_channel_renderer(self, renderer):
4493 channel_id = renderer['channelId']
4494 title = self._get_text(renderer, 'title')
4495 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4496 return {
4497 '_type': 'url',
4498 'url': channel_url,
4499 'id': channel_id,
4500 'ie_key': YoutubeTabIE.ie_key(),
4501 'channel': title,
4502 'channel_id': channel_id,
4503 'channel_url': channel_url,
4504 'title': title,
4505 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4506 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4507 'playlist_count': self._get_count(renderer, 'videoCountText'),
4508 'description': self._get_text(renderer, 'descriptionSnippet'),
4509 }
4510
4511 def _grid_entries(self, grid_renderer):
4512 for item in grid_renderer['items']:
4513 if not isinstance(item, dict):
4514 continue
4515 renderer = self._extract_basic_item_renderer(item)
4516 if not isinstance(renderer, dict):
4517 continue
4518 title = self._get_text(renderer, 'title')
4519
4520 # playlist
4521 playlist_id = renderer.get('playlistId')
4522 if playlist_id:
4523 yield self.url_result(
4524 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4525 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4526 video_title=title)
4527 continue
4528 # video
4529 video_id = renderer.get('videoId')
4530 if video_id:
4531 yield self._extract_video(renderer)
4532 continue
4533 # channel
4534 channel_id = renderer.get('channelId')
4535 if channel_id:
4536 yield self._extract_channel_renderer(renderer)
4537 continue
4538 # generic endpoint URL support
4539 ep_url = urljoin('https://www.youtube.com/', try_get(
4540 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4541 str))
4542 if ep_url:
4543 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4544 if ie.suitable(ep_url):
4545 yield self.url_result(
4546 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4547 break
4548
4549 def _music_reponsive_list_entry(self, renderer):
4550 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4551 if video_id:
4552 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4553 ie=YoutubeIE.ie_key(), video_id=video_id)
4554 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4555 if playlist_id:
4556 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4557 if video_id:
4558 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4559 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4560 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4561 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4562 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4563 if browse_id:
4564 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4565 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4566
4567 def _shelf_entries_from_content(self, shelf_renderer):
4568 content = shelf_renderer.get('content')
4569 if not isinstance(content, dict):
4570 return
4571 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4572 if renderer:
4573 # TODO: add support for nested playlists so each shelf is processed
4574 # as separate playlist
4575 # TODO: this includes only first N items
4576 yield from self._grid_entries(renderer)
4577 renderer = content.get('horizontalListRenderer')
4578 if renderer:
4579 # TODO
4580 pass
4581
4582 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4583 ep = try_get(
4584 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4585 str)
4586 shelf_url = urljoin('https://www.youtube.com', ep)
4587 if shelf_url:
4588 # Skipping links to another channels, note that checking for
4589 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4590 # will not work
4591 if skip_channels and '/channels?' in shelf_url:
4592 return
4593 title = self._get_text(shelf_renderer, 'title')
4594 yield self.url_result(shelf_url, video_title=title)
4595 # Shelf may not contain shelf URL, fallback to extraction from content
4596 yield from self._shelf_entries_from_content(shelf_renderer)
4597
4598 def _playlist_entries(self, video_list_renderer):
4599 for content in video_list_renderer['contents']:
4600 if not isinstance(content, dict):
4601 continue
4602 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4603 if not isinstance(renderer, dict):
4604 continue
4605 video_id = renderer.get('videoId')
4606 if not video_id:
4607 continue
4608 yield self._extract_video(renderer)
4609
4610 def _rich_entries(self, rich_grid_renderer):
4611 renderer = traverse_obj(
4612 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4613 video_id = renderer.get('videoId')
4614 if not video_id:
4615 return
4616 yield self._extract_video(renderer)
4617
4618 def _video_entry(self, video_renderer):
4619 video_id = video_renderer.get('videoId')
4620 if video_id:
4621 return self._extract_video(video_renderer)
4622
4623 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4624 url = urljoin('https://youtube.com', traverse_obj(
4625 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4626 if url:
4627 return self.url_result(
4628 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4629
4630 def _post_thread_entries(self, post_thread_renderer):
4631 post_renderer = try_get(
4632 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4633 if not post_renderer:
4634 return
4635 # video attachment
4636 video_renderer = try_get(
4637 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4638 video_id = video_renderer.get('videoId')
4639 if video_id:
4640 entry = self._extract_video(video_renderer)
4641 if entry:
4642 yield entry
4643 # playlist attachment
4644 playlist_id = try_get(
4645 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4646 if playlist_id:
4647 yield self.url_result(
4648 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4649 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4650 # inline video links
4651 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4652 for run in runs:
4653 if not isinstance(run, dict):
4654 continue
4655 ep_url = try_get(
4656 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4657 if not ep_url:
4658 continue
4659 if not YoutubeIE.suitable(ep_url):
4660 continue
4661 ep_video_id = YoutubeIE._match_id(ep_url)
4662 if video_id == ep_video_id:
4663 continue
4664 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4665
4666 def _post_thread_continuation_entries(self, post_thread_continuation):
4667 contents = post_thread_continuation.get('contents')
4668 if not isinstance(contents, list):
4669 return
4670 for content in contents:
4671 renderer = content.get('backstagePostThreadRenderer')
4672 if isinstance(renderer, dict):
4673 yield from self._post_thread_entries(renderer)
4674 continue
4675 renderer = content.get('videoRenderer')
4676 if isinstance(renderer, dict):
4677 yield self._video_entry(renderer)
4678
4679 r''' # unused
4680 def _rich_grid_entries(self, contents):
4681 for content in contents:
4682 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4683 if video_renderer:
4684 entry = self._video_entry(video_renderer)
4685 if entry:
4686 yield entry
4687 '''
4688
4689 def _report_history_entries(self, renderer):
4690 for url in traverse_obj(renderer, (
4691 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4692 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4693 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4694 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4695
4696 def _extract_entries(self, parent_renderer, continuation_list):
4697 # continuation_list is modified in-place with continuation_list = [continuation_token]
4698 continuation_list[:] = [None]
4699 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4700 for content in contents:
4701 if not isinstance(content, dict):
4702 continue
4703 is_renderer = traverse_obj(
4704 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4705 expected_type=dict)
4706 if not is_renderer:
4707 if content.get('richItemRenderer'):
4708 for entry in self._rich_entries(content['richItemRenderer']):
4709 yield entry
4710 continuation_list[0] = self._extract_continuation(parent_renderer)
4711 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4712 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4713 yield from self._report_history_entries(table)
4714 continuation_list[0] = self._extract_continuation(table)
4715 continue
4716
4717 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4718 for isr_content in isr_contents:
4719 if not isinstance(isr_content, dict):
4720 continue
4721
4722 known_renderers = {
4723 'playlistVideoListRenderer': self._playlist_entries,
4724 'gridRenderer': self._grid_entries,
4725 'reelShelfRenderer': self._grid_entries,
4726 'shelfRenderer': self._shelf_entries,
4727 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4728 'backstagePostThreadRenderer': self._post_thread_entries,
4729 'videoRenderer': lambda x: [self._video_entry(x)],
4730 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4731 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4732 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4733 }
4734 for key, renderer in isr_content.items():
4735 if key not in known_renderers:
4736 continue
4737 for entry in known_renderers[key](renderer):
4738 if entry:
4739 yield entry
4740 continuation_list[0] = self._extract_continuation(renderer)
4741 break
4742
4743 if not continuation_list[0]:
4744 continuation_list[0] = self._extract_continuation(is_renderer)
4745
4746 if not continuation_list[0]:
4747 continuation_list[0] = self._extract_continuation(parent_renderer)
4748
4749 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4750 continuation_list = [None]
4751 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4752 tab_content = try_get(tab, lambda x: x['content'], dict)
4753 if not tab_content:
4754 return
4755 parent_renderer = (
4756 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4757 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4758 yield from extract_entries(parent_renderer)
4759 continuation = continuation_list[0]
4760
4761 for page_num in itertools.count(1):
4762 if not continuation:
4763 break
4764 headers = self.generate_api_headers(
4765 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4766 response = self._extract_response(
4767 item_id=f'{item_id} page {page_num}',
4768 query=continuation, headers=headers, ytcfg=ytcfg,
4769 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4770
4771 if not response:
4772 break
4773 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4774 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4775 visitor_data = self._extract_visitor_data(response) or visitor_data
4776
4777 known_renderers = {
4778 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4779 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4780 'gridVideoRenderer': (self._grid_entries, 'items'),
4781 'gridChannelRenderer': (self._grid_entries, 'items'),
4782 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4783 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4784 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4785 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4786 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4787 'playlistVideoListContinuation': (self._playlist_entries, None),
4788 'gridContinuation': (self._grid_entries, None),
4789 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4790 'sectionListContinuation': (extract_entries, None), # for feeds
4791 }
4792
4793 continuation_items = traverse_obj(response, (
4794 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4795 'appendContinuationItemsAction', 'continuationItems'
4796 ), 'continuationContents', get_all=False)
4797 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4798
4799 video_items_renderer = None
4800 for key in continuation_item.keys():
4801 if key not in known_renderers:
4802 continue
4803 func, parent_key = known_renderers[key]
4804 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4805 continuation_list = [None]
4806 yield from func(video_items_renderer)
4807 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4808
4809 if not video_items_renderer:
4810 break
4811
4812 @staticmethod
4813 def _extract_selected_tab(tabs, fatal=True):
4814 for tab_renderer in tabs:
4815 if tab_renderer.get('selected'):
4816 return tab_renderer
4817 if fatal:
4818 raise ExtractorError('Unable to find selected tab')
4819
4820 @staticmethod
4821 def _extract_tab_renderers(response):
4822 return traverse_obj(
4823 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
4824
4825 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4826 metadata = self._extract_metadata_from_tabs(item_id, data)
4827
4828 selected_tab = self._extract_selected_tab(tabs)
4829 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4830 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4831
4832 return self.playlist_result(
4833 self._entries(
4834 selected_tab, metadata['id'], ytcfg,
4835 self._extract_account_syncid(ytcfg, data),
4836 self._extract_visitor_data(data, ytcfg)),
4837 **metadata)
4838
4839 def _extract_metadata_from_tabs(self, item_id, data):
4840 info = {'id': item_id}
4841
4842 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
4843 if metadata_renderer:
4844 info.update({
4845 'uploader': metadata_renderer.get('title'),
4846 'uploader_id': metadata_renderer.get('externalId'),
4847 'uploader_url': metadata_renderer.get('channelUrl'),
4848 })
4849 if info['uploader_id']:
4850 info['id'] = info['uploader_id']
4851 else:
4852 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
4853
4854 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4855 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4856 def _get_uncropped(url):
4857 return url_or_none((url or '').split('=')[0] + '=s0')
4858
4859 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
4860 if avatar_thumbnails:
4861 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4862 if uncropped_avatar:
4863 avatar_thumbnails.append({
4864 'url': uncropped_avatar,
4865 'id': 'avatar_uncropped',
4866 'preference': 1
4867 })
4868
4869 channel_banners = self._extract_thumbnails(
4870 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4871 for banner in channel_banners:
4872 banner['preference'] = -10
4873
4874 if channel_banners:
4875 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4876 if uncropped_banner:
4877 channel_banners.append({
4878 'url': uncropped_banner,
4879 'id': 'banner_uncropped',
4880 'preference': -5
4881 })
4882
4883 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4884 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4885 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4886
4887 primary_thumbnails = self._extract_thumbnails(
4888 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4889 playlist_thumbnails = self._extract_thumbnails(
4890 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4891
4892 info.update({
4893 'title': (traverse_obj(metadata_renderer, 'title')
4894 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4895 or info['id']),
4896 'availability': self._extract_availability(data),
4897 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4898 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4899 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4900 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4901 })
4902
4903 # Playlist stats is a text runs array containing [video count, view count, last updated].
4904 # last updated or (view count and last updated) may be missing.
4905 playlist_stats = get_first(
4906 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4907
4908 last_updated_unix = self._parse_time_text(
4909 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4910 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4911 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
4912
4913 info['view_count'] = self._get_count(playlist_stats, 1)
4914 if info['view_count'] is None: # 0 is allowed
4915 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4916 if info['view_count'] is None:
4917 info['view_count'] = self._get_count(data, (
4918 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4919 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4920
4921 info['playlist_count'] = self._get_count(playlist_stats, 0)
4922 if info['playlist_count'] is None: # 0 is allowed
4923 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4924
4925 if not info.get('uploader_id'):
4926 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4927 if not owner: # Deprecated
4928 owner = traverse_obj(
4929 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4930 ('videoOwner', 'videoOwnerRenderer', 'title'))
4931 owner_text = self._get_text(owner)
4932 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4933 info.update({
4934 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4935 'uploader_id': browse_ep.get('browseId'),
4936 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4937 })
4938
4939 info.update({
4940 'channel': info['uploader'],
4941 'channel_id': info['uploader_id'],
4942 'channel_url': info['uploader_url']
4943 })
4944 return info
4945
4946 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4947 first_id = last_id = response = None
4948 for page_num in itertools.count(1):
4949 videos = list(self._playlist_entries(playlist))
4950 if not videos:
4951 return
4952 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4953 if start >= len(videos):
4954 return
4955 yield from videos[start:]
4956 first_id = first_id or videos[0]['id']
4957 last_id = videos[-1]['id']
4958 watch_endpoint = try_get(
4959 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4960 headers = self.generate_api_headers(
4961 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4962 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4963 query = {
4964 'playlistId': playlist_id,
4965 'videoId': watch_endpoint.get('videoId') or last_id,
4966 'index': watch_endpoint.get('index') or len(videos),
4967 'params': watch_endpoint.get('params') or 'OAE%3D'
4968 }
4969 response = self._extract_response(
4970 item_id='%s page %d' % (playlist_id, page_num),
4971 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4972 check_get_keys='contents'
4973 )
4974 playlist = try_get(
4975 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4976
4977 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4978 title = playlist.get('title') or try_get(
4979 data, lambda x: x['titleText']['simpleText'], str)
4980 playlist_id = playlist.get('playlistId') or item_id
4981
4982 # Delegating everything except mix playlists to regular tab-based playlist URL
4983 playlist_url = urljoin(url, try_get(
4984 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4985 str))
4986
4987 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4988 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4989 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4990
4991 if playlist_url and playlist_url != url and not is_known_unviewable:
4992 return self.url_result(
4993 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4994 video_title=title)
4995
4996 return self.playlist_result(
4997 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4998 playlist_id=playlist_id, playlist_title=title)
4999
5000 def _extract_availability(self, data):
5001 """
5002 Gets the availability of a given playlist/tab.
5003 Note: Unless YouTube tells us explicitly, we do not assume it is public
5004 @param data: response
5005 """
5006 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5007 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5008 player_header_privacy = playlist_header_renderer.get('privacy')
5009
5010 badges = self._extract_badges(sidebar_renderer)
5011
5012 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
5013 privacy_setting_icon = get_first(
5014 (playlist_header_renderer, sidebar_renderer),
5015 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5016 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5017 expected_type=str)
5018
5019 microformats_is_unlisted = traverse_obj(
5020 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
5021
5022 return (
5023 'public' if (
5024 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5025 or player_header_privacy == 'PUBLIC'
5026 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5027 else self._availability(
5028 is_private=(
5029 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5030 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5031 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5032 is_unlisted=(
5033 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5034 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
5035 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5036 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
5037 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5038 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5039 needs_auth=False))
5040
5041 @staticmethod
5042 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5043 sidebar_renderer = try_get(
5044 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5045 for item in sidebar_renderer:
5046 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5047 if renderer:
5048 return renderer
5049
5050 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
5051 """
5052 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5053 """
5054 is_playlist = bool(traverse_obj(
5055 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5056 if not is_playlist:
5057 return
5058 headers = self.generate_api_headers(
5059 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5060 visitor_data=self._extract_visitor_data(data, ytcfg))
5061 query = {
5062 'params': 'wgYCCAA=',
5063 'browseId': f'VL{item_id}'
5064 }
5065 return self._extract_response(
5066 item_id=item_id, headers=headers, query=query,
5067 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
5068 note='Redownloading playlist API JSON with unavailable videos')
5069
5070 @functools.cached_property
5071 def skip_webpage(self):
5072 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5073
5074 def _extract_webpage(self, url, item_id, fatal=True):
5075 webpage, data = None, None
5076 for retry in self.RetryManager(fatal=fatal):
5077 try:
5078 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
5079 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5080 except ExtractorError as e:
5081 if isinstance(e.cause, network_exceptions):
5082 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
5083 retry.error = e
5084 continue
5085 self._error_or_warning(e, fatal=fatal)
5086 break
5087
5088 try:
5089 self._extract_and_report_alerts(data)
5090 except ExtractorError as e:
5091 self._error_or_warning(e, fatal=fatal)
5092 break
5093
5094 # Sometimes youtube returns a webpage with incomplete ytInitialData
5095 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5096 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5097 retry.error = ExtractorError('Incomplete yt initial data received')
5098 continue
5099
5100 return webpage, data
5101
5102 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5103 """Use if failed to extract ytcfg (and data) from initial webpage"""
5104 if not ytcfg and self.is_authenticated:
5105 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5106 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5107 raise ExtractorError(
5108 f'{msg}. If you are not downloading private content, or '
5109 'your cookies are only for the first account and channel,'
5110 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5111 expected=True)
5112 self.report_warning(msg, only_once=True)
5113
5114 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5115 data = None
5116 if not self.skip_webpage:
5117 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5118 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
5119 # Reject webpage data if redirected to home page without explicitly requesting
5120 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
5121 if (url != 'https://www.youtube.com/feed/recommended'
5122 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5123 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5124 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5125 if fatal:
5126 raise ExtractorError(msg, expected=True)
5127 self.report_warning(msg, only_once=True)
5128 if not data:
5129 self._report_playlist_authcheck(ytcfg, fatal=fatal)
5130 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5131 return data, ytcfg
5132
5133 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5134 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5135 resolve_response = self._extract_response(
5136 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5137 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5138 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5139 for ep_key, ep in endpoints.items():
5140 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5141 if params:
5142 return self._extract_response(
5143 item_id=item_id, query=params, ep=ep, headers=headers,
5144 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
5145 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5146 err_note = 'Failed to resolve url (does the playlist exist?)'
5147 if fatal:
5148 raise ExtractorError(err_note, expected=True)
5149 self.report_warning(err_note, item_id)
5150
5151 _SEARCH_PARAMS = None
5152
5153 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
5154 data = {'query': query}
5155 if params is NO_DEFAULT:
5156 params = self._SEARCH_PARAMS
5157 if params:
5158 data['params'] = params
5159
5160 content_keys = (
5161 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5162 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5163 # ytmusic search
5164 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5165 ('continuationContents', ),
5166 )
5167 display_id = f'query "{query}"'
5168 check_get_keys = tuple({keys[0] for keys in content_keys})
5169 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5170 self._report_playlist_authcheck(ytcfg, fatal=False)
5171
5172 continuation_list = [None]
5173 search = None
5174 for page_num in itertools.count(1):
5175 data.update(continuation_list[0] or {})
5176 headers = self.generate_api_headers(
5177 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
5178 search = self._extract_response(
5179 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5180 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
5181 slr_contents = traverse_obj(search, *content_keys)
5182 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
5183 if not continuation_list[0]:
5184 break
5185
5186
5187 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5188 IE_DESC = 'YouTube Tabs'
5189 _VALID_URL = r'''(?x:
5190 https?://
5191 (?!consent\.)(?:\w+\.)?
5192 (?:
5193 youtube(?:kids)?\.com|
5194 %(invidious)s
5195 )/
5196 (?:
5197 (?P<channel_type>channel|c|user|browse)/|
5198 (?P<not_channel>
5199 feed/|hashtag/|
5200 (?:playlist|watch)\?.*?\blist=
5201 )|
5202 (?!(?:%(reserved_names)s)\b) # Direct URLs
5203 )
5204 (?P<id>[^/?\#&]+)
5205 )''' % {
5206 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5207 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5208 }
5209 IE_NAME = 'youtube:tab'
5210
5211 _TESTS = [{
5212 'note': 'playlists, multipage',
5213 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5214 'playlist_mincount': 94,
5215 'info_dict': {
5216 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5217 'title': 'Igor Kleiner - Playlists',
5218 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5219 'uploader': 'Igor Kleiner',
5220 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5221 'channel': 'Igor Kleiner',
5222 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5223 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5224 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5225 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5226 'channel_follower_count': int
5227 },
5228 }, {
5229 'note': 'playlists, multipage, different order',
5230 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5231 'playlist_mincount': 94,
5232 'info_dict': {
5233 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5234 'title': 'Igor Kleiner - Playlists',
5235 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5236 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5237 'uploader': 'Igor Kleiner',
5238 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5239 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5240 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5241 'channel': 'Igor Kleiner',
5242 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5243 'channel_follower_count': int
5244 },
5245 }, {
5246 'note': 'playlists, series',
5247 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5248 'playlist_mincount': 5,
5249 'info_dict': {
5250 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5251 'title': '3Blue1Brown - Playlists',
5252 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5253 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5254 'uploader': '3Blue1Brown',
5255 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5256 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5257 'channel': '3Blue1Brown',
5258 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5259 'tags': ['Mathematics'],
5260 'channel_follower_count': int
5261 },
5262 }, {
5263 'note': 'playlists, singlepage',
5264 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5265 'playlist_mincount': 4,
5266 'info_dict': {
5267 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5268 'title': 'ThirstForScience - Playlists',
5269 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5270 'uploader': 'ThirstForScience',
5271 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5272 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5273 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5274 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5275 'tags': 'count:13',
5276 'channel': 'ThirstForScience',
5277 'channel_follower_count': int
5278 }
5279 }, {
5280 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5281 'only_matching': True,
5282 }, {
5283 'note': 'basic, single video playlist',
5284 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5285 'info_dict': {
5286 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5287 'uploader': 'Sergey M.',
5288 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5289 'title': 'youtube-dl public playlist',
5290 'description': '',
5291 'tags': [],
5292 'view_count': int,
5293 'modified_date': '20201130',
5294 'channel': 'Sergey M.',
5295 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5296 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5297 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5298 'availability': 'public',
5299 },
5300 'playlist_count': 1,
5301 }, {
5302 'note': 'empty playlist',
5303 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5304 'info_dict': {
5305 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5306 'uploader': 'Sergey M.',
5307 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5308 'title': 'youtube-dl empty playlist',
5309 'tags': [],
5310 'channel': 'Sergey M.',
5311 'description': '',
5312 'modified_date': '20160902',
5313 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5314 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5315 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5316 'availability': 'public',
5317 },
5318 'playlist_count': 0,
5319 }, {
5320 'note': 'Home tab',
5321 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5322 'info_dict': {
5323 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5324 'title': 'lex will - Home',
5325 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5326 'uploader': 'lex will',
5327 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5328 'channel': 'lex will',
5329 'tags': ['bible', 'history', 'prophesy'],
5330 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5331 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5332 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5333 'channel_follower_count': int
5334 },
5335 'playlist_mincount': 2,
5336 }, {
5337 'note': 'Videos tab',
5338 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5339 'info_dict': {
5340 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5341 'title': 'lex will - Videos',
5342 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5343 'uploader': 'lex will',
5344 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5345 'tags': ['bible', 'history', 'prophesy'],
5346 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5347 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5348 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5349 'channel': 'lex will',
5350 'channel_follower_count': int
5351 },
5352 'playlist_mincount': 975,
5353 }, {
5354 'note': 'Videos tab, sorted by popular',
5355 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5356 'info_dict': {
5357 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5358 'title': 'lex will - Videos',
5359 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5360 'uploader': 'lex will',
5361 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5362 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5363 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5364 'channel': 'lex will',
5365 'tags': ['bible', 'history', 'prophesy'],
5366 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5367 'channel_follower_count': int
5368 },
5369 'playlist_mincount': 199,
5370 }, {
5371 'note': 'Playlists tab',
5372 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5373 'info_dict': {
5374 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5375 'title': 'lex will - Playlists',
5376 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5377 'uploader': 'lex will',
5378 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5379 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5380 'channel': 'lex will',
5381 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5382 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5383 'tags': ['bible', 'history', 'prophesy'],
5384 'channel_follower_count': int
5385 },
5386 'playlist_mincount': 17,
5387 }, {
5388 'note': 'Community tab',
5389 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5390 'info_dict': {
5391 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5392 'title': 'lex will - Community',
5393 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5394 'uploader': 'lex will',
5395 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5396 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5397 'channel': 'lex will',
5398 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5399 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5400 'tags': ['bible', 'history', 'prophesy'],
5401 'channel_follower_count': int
5402 },
5403 'playlist_mincount': 18,
5404 }, {
5405 'note': 'Channels tab',
5406 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5407 'info_dict': {
5408 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5409 'title': 'lex will - Channels',
5410 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5411 'uploader': 'lex will',
5412 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5413 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5414 'channel': 'lex will',
5415 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5416 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5417 'tags': ['bible', 'history', 'prophesy'],
5418 'channel_follower_count': int
5419 },
5420 'playlist_mincount': 12,
5421 }, {
5422 'note': 'Search tab',
5423 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5424 'playlist_mincount': 40,
5425 'info_dict': {
5426 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5427 'title': '3Blue1Brown - Search - linear algebra',
5428 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5429 'uploader': '3Blue1Brown',
5430 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5431 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5432 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5433 'tags': ['Mathematics'],
5434 'channel': '3Blue1Brown',
5435 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5436 'channel_follower_count': int
5437 },
5438 }, {
5439 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5440 'only_matching': True,
5441 }, {
5442 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5443 'only_matching': True,
5444 }, {
5445 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5446 'only_matching': True,
5447 }, {
5448 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5449 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5450 'info_dict': {
5451 'title': '29C3: Not my department',
5452 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5453 'uploader': 'Christiaan008',
5454 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5455 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5456 'tags': [],
5457 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5458 'view_count': int,
5459 'modified_date': '20150605',
5460 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5461 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5462 'channel': 'Christiaan008',
5463 'availability': 'public',
5464 },
5465 'playlist_count': 96,
5466 }, {
5467 'note': 'Large playlist',
5468 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5469 'info_dict': {
5470 'title': 'Uploads from Cauchemar',
5471 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5472 'uploader': 'Cauchemar',
5473 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5474 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5475 'tags': [],
5476 'modified_date': r're:\d{8}',
5477 'channel': 'Cauchemar',
5478 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5479 'view_count': int,
5480 'description': '',
5481 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5482 'availability': 'public',
5483 },
5484 'playlist_mincount': 1123,
5485 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5486 }, {
5487 'note': 'even larger playlist, 8832 videos',
5488 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5489 'only_matching': True,
5490 }, {
5491 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5492 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5493 'info_dict': {
5494 'title': 'Uploads from Interstellar Movie',
5495 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5496 'uploader': 'Interstellar Movie',
5497 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5498 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5499 'tags': [],
5500 'view_count': int,
5501 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5502 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5503 'channel': 'Interstellar Movie',
5504 'description': '',
5505 'modified_date': r're:\d{8}',
5506 'availability': 'public',
5507 },
5508 'playlist_mincount': 21,
5509 }, {
5510 'note': 'Playlist with "show unavailable videos" button',
5511 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5512 'info_dict': {
5513 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5514 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5515 'uploader': 'Phim Siêu Nhân Nhật Bản',
5516 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5517 'view_count': int,
5518 'channel': 'Phim Siêu Nhân Nhật Bản',
5519 'tags': [],
5520 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5521 'description': '',
5522 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5523 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5524 'modified_date': r're:\d{8}',
5525 'availability': 'public',
5526 },
5527 'playlist_mincount': 200,
5528 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5529 }, {
5530 'note': 'Playlist with unavailable videos in page 7',
5531 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5532 'info_dict': {
5533 'title': 'Uploads from BlankTV',
5534 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5535 'uploader': 'BlankTV',
5536 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5537 'channel': 'BlankTV',
5538 'channel_url': 'https://www.youtube.com/c/blanktv',
5539 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5540 'view_count': int,
5541 'tags': [],
5542 'uploader_url': 'https://www.youtube.com/c/blanktv',
5543 'modified_date': r're:\d{8}',
5544 'description': '',
5545 'availability': 'public',
5546 },
5547 'playlist_mincount': 1000,
5548 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5549 }, {
5550 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5551 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5552 'info_dict': {
5553 'title': 'Data Analysis with Dr Mike Pound',
5554 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5555 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5556 'uploader': 'Computerphile',
5557 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5558 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5559 'tags': [],
5560 'view_count': int,
5561 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5562 'channel_url': 'https://www.youtube.com/user/Computerphile',
5563 'channel': 'Computerphile',
5564 'availability': 'public',
5565 'modified_date': '20190712',
5566 },
5567 'playlist_mincount': 11,
5568 }, {
5569 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5570 'only_matching': True,
5571 }, {
5572 'note': 'Playlist URL that does not actually serve a playlist',
5573 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5574 'info_dict': {
5575 'id': 'FqZTN594JQw',
5576 'ext': 'webm',
5577 'title': "Smiley's People 01 detective, Adventure Series, Action",
5578 'uploader': 'STREEM',
5579 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5580 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5581 'upload_date': '20150526',
5582 'license': 'Standard YouTube License',
5583 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5584 'categories': ['People & Blogs'],
5585 'tags': list,
5586 'view_count': int,
5587 'like_count': int,
5588 },
5589 'params': {
5590 'skip_download': True,
5591 },
5592 'skip': 'This video is not available.',
5593 'add_ie': [YoutubeIE.ie_key()],
5594 }, {
5595 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5596 'only_matching': True,
5597 }, {
5598 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5599 'only_matching': True,
5600 }, {
5601 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5602 'info_dict': {
5603 'id': 'Wq15eF5vCbI', # This will keep changing
5604 'ext': 'mp4',
5605 'title': str,
5606 'uploader': 'Sky News',
5607 'uploader_id': 'skynews',
5608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5609 'upload_date': r're:\d{8}',
5610 'description': str,
5611 'categories': ['News & Politics'],
5612 'tags': list,
5613 'like_count': int,
5614 'release_timestamp': int,
5615 'channel': 'Sky News',
5616 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5617 'age_limit': 0,
5618 'view_count': int,
5619 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5620 'playable_in_embed': True,
5621 'release_date': r're:\d+',
5622 'availability': 'public',
5623 'live_status': 'is_live',
5624 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5625 'channel_follower_count': int,
5626 'concurrent_view_count': int,
5627 },
5628 'params': {
5629 'skip_download': True,
5630 },
5631 'expected_warnings': ['Ignoring subtitle tracks found in '],
5632 }, {
5633 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5634 'info_dict': {
5635 'id': 'a48o2S1cPoo',
5636 'ext': 'mp4',
5637 'title': 'The Young Turks - Live Main Show',
5638 'uploader': 'The Young Turks',
5639 'uploader_id': 'TheYoungTurks',
5640 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5641 'upload_date': '20150715',
5642 'license': 'Standard YouTube License',
5643 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5644 'categories': ['News & Politics'],
5645 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5646 'like_count': int,
5647 },
5648 'params': {
5649 'skip_download': True,
5650 },
5651 'only_matching': True,
5652 }, {
5653 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5654 'only_matching': True,
5655 }, {
5656 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5657 'only_matching': True,
5658 }, {
5659 'note': 'A channel that is not live. Should raise error',
5660 'url': 'https://www.youtube.com/user/numberphile/live',
5661 'only_matching': True,
5662 }, {
5663 'url': 'https://www.youtube.com/feed/trending',
5664 'only_matching': True,
5665 }, {
5666 'url': 'https://www.youtube.com/feed/library',
5667 'only_matching': True,
5668 }, {
5669 'url': 'https://www.youtube.com/feed/history',
5670 'only_matching': True,
5671 }, {
5672 'url': 'https://www.youtube.com/feed/subscriptions',
5673 'only_matching': True,
5674 }, {
5675 'url': 'https://www.youtube.com/feed/watch_later',
5676 'only_matching': True,
5677 }, {
5678 'note': 'Recommended - redirects to home page.',
5679 'url': 'https://www.youtube.com/feed/recommended',
5680 'only_matching': True,
5681 }, {
5682 'note': 'inline playlist with not always working continuations',
5683 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5684 'only_matching': True,
5685 }, {
5686 'url': 'https://www.youtube.com/course',
5687 'only_matching': True,
5688 }, {
5689 'url': 'https://www.youtube.com/zsecurity',
5690 'only_matching': True,
5691 }, {
5692 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5693 'only_matching': True,
5694 }, {
5695 'url': 'https://www.youtube.com/TheYoungTurks/live',
5696 'only_matching': True,
5697 }, {
5698 'url': 'https://www.youtube.com/hashtag/cctv9',
5699 'info_dict': {
5700 'id': 'cctv9',
5701 'title': '#cctv9',
5702 'tags': [],
5703 },
5704 'playlist_mincount': 300, # not consistent but should be over 300
5705 }, {
5706 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5707 'only_matching': True,
5708 }, {
5709 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5710 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5711 'only_matching': True
5712 }, {
5713 'note': '/browse/ should redirect to /channel/',
5714 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5715 'only_matching': True
5716 }, {
5717 'note': 'VLPL, should redirect to playlist?list=PL...',
5718 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5719 'info_dict': {
5720 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5721 'uploader': 'NoCopyrightSounds',
5722 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5723 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5724 'title': 'NCS : All Releases 💿',
5725 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5726 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5727 'modified_date': r're:\d{8}',
5728 'view_count': int,
5729 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5730 'tags': [],
5731 'channel': 'NoCopyrightSounds',
5732 'availability': 'public',
5733 },
5734 'playlist_mincount': 166,
5735 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5736 }, {
5737 'note': 'Topic, should redirect to playlist?list=UU...',
5738 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5739 'info_dict': {
5740 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5741 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5742 'title': 'Uploads from Royalty Free Music - Topic',
5743 'uploader': 'Royalty Free Music - Topic',
5744 'tags': [],
5745 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5746 'channel': 'Royalty Free Music - Topic',
5747 'view_count': int,
5748 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5749 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5750 'modified_date': r're:\d{8}',
5751 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5752 'description': '',
5753 'availability': 'public',
5754 },
5755 'playlist_mincount': 101,
5756 }, {
5757 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5758 # Treat as a general feed
5759 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5760 'info_dict': {
5761 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5762 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5763 'tags': [],
5764 },
5765 'playlist_mincount': 9,
5766 }, {
5767 'note': 'Youtube music Album',
5768 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5769 'info_dict': {
5770 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5771 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5772 'tags': [],
5773 'view_count': int,
5774 'description': '',
5775 'availability': 'unlisted',
5776 'modified_date': r're:\d{8}',
5777 },
5778 'playlist_count': 50,
5779 }, {
5780 'note': 'unlisted single video playlist',
5781 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5782 'info_dict': {
5783 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5784 'uploader': 'colethedj',
5785 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5786 'title': 'yt-dlp unlisted playlist test',
5787 'availability': 'unlisted',
5788 'tags': [],
5789 'modified_date': '20220418',
5790 'channel': 'colethedj',
5791 'view_count': int,
5792 'description': '',
5793 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5794 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5795 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5796 },
5797 'playlist_count': 1,
5798 }, {
5799 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5800 'url': 'https://www.youtube.com/feed/recommended',
5801 'info_dict': {
5802 'id': 'recommended',
5803 'title': 'recommended',
5804 'tags': [],
5805 },
5806 'playlist_mincount': 50,
5807 'params': {
5808 'skip_download': True,
5809 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5810 },
5811 }, {
5812 'note': 'API Fallback: /videos tab, sorted by oldest first',
5813 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5814 'info_dict': {
5815 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5816 'title': 'Cody\'sLab - Videos',
5817 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5818 'uploader': 'Cody\'sLab',
5819 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5820 'channel': 'Cody\'sLab',
5821 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5822 'tags': [],
5823 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5824 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5825 'channel_follower_count': int
5826 },
5827 'playlist_mincount': 650,
5828 'params': {
5829 'skip_download': True,
5830 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5831 },
5832 'skip': 'Query for sorting no longer works',
5833 }, {
5834 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5835 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5836 'info_dict': {
5837 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5838 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5839 'title': 'Uploads from Royalty Free Music - Topic',
5840 'uploader': 'Royalty Free Music - Topic',
5841 'modified_date': r're:\d{8}',
5842 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5843 'description': '',
5844 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5845 'tags': [],
5846 'channel': 'Royalty Free Music - Topic',
5847 'view_count': int,
5848 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5849 'availability': 'public',
5850 },
5851 'playlist_mincount': 101,
5852 'params': {
5853 'skip_download': True,
5854 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5855 },
5856 }, {
5857 'note': 'non-standard redirect to regional channel',
5858 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5859 'only_matching': True
5860 }, {
5861 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5862 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5863 'info_dict': {
5864 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5865 'modified_date': '20220407',
5866 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5867 'tags': [],
5868 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5869 'uploader': 'pukkandan',
5870 'availability': 'unlisted',
5871 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5872 'channel': 'pukkandan',
5873 'description': 'Test for collaborative playlist',
5874 'title': 'yt-dlp test - collaborative playlist',
5875 'view_count': int,
5876 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5877 },
5878 'playlist_mincount': 2
5879 }, {
5880 'note': 'translated tab name',
5881 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5882 'info_dict': {
5883 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5884 'tags': [],
5885 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5886 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5887 'description': 'test description',
5888 'title': 'cole-dlp-test-acc - 再生リスト',
5889 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5890 'uploader': 'cole-dlp-test-acc',
5891 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5892 'channel': 'cole-dlp-test-acc',
5893 },
5894 'playlist_mincount': 1,
5895 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5896 'expected_warnings': ['Preferring "ja"'],
5897 }, {
5898 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5899 'note': 'preferred lang set with playlist with translated video titles',
5900 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5901 'info_dict': {
5902 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5903 'tags': [],
5904 'view_count': int,
5905 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5906 'uploader': 'cole-dlp-test-acc',
5907 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5908 'channel': 'cole-dlp-test-acc',
5909 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5910 'description': 'test',
5911 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5912 'title': 'dlp test playlist',
5913 'availability': 'public',
5914 },
5915 'playlist_mincount': 1,
5916 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5917 'expected_warnings': ['Preferring "ja"'],
5918 }, {
5919 # shorts audio pivot for 2GtVksBMYFM.
5920 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5921 'info_dict': {
5922 'id': 'sfv_audio_pivot',
5923 'title': 'sfv_audio_pivot',
5924 'tags': [],
5925 },
5926 'playlist_mincount': 50,
5927
5928 }, {
5929 # Channel with a real live tab (not to be mistaken with streams tab)
5930 # Do not treat like it should redirect to live stream
5931 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5932 'info_dict': {
5933 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5934 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5935 'tags': [],
5936 },
5937 'playlist_mincount': 20,
5938 }, {
5939 # Tab name is not the same as tab id
5940 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5941 'info_dict': {
5942 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5943 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5944 'tags': [],
5945 },
5946 'playlist_mincount': 8,
5947 }, {
5948 # Home tab id is literally home. Not to get mistaken with featured
5949 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5950 'info_dict': {
5951 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5952 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5953 'tags': [],
5954 },
5955 'playlist_mincount': 8,
5956 }, {
5957 # Should get three playlists for videos, shorts and streams tabs
5958 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5959 'info_dict': {
5960 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5961 'title': 'Polka Ch. 尾丸ポルカ',
5962 'channel_follower_count': int,
5963 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5964 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5965 'uploader': 'Polka Ch. 尾丸ポルカ',
5966 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5967 'channel': 'Polka Ch. 尾丸ポルカ',
5968 'tags': 'count:35',
5969 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5970 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5971 },
5972 'playlist_count': 3,
5973 }, {
5974 # Shorts tab with channel with handle
5975 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5976 'info_dict': {
5977 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5978 'title': 'Not Just Bikes - Shorts',
5979 'tags': 'count:12',
5980 'uploader': 'Not Just Bikes',
5981 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5982 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5983 'channel_follower_count': int,
5984 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5985 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5986 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5987 'channel': 'Not Just Bikes',
5988 },
5989 'playlist_mincount': 10,
5990 }, {
5991 # Streams tab
5992 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5993 'info_dict': {
5994 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5995 'title': '中村悠一 - Live',
5996 'tags': 'count:7',
5997 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5998 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5999 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6000 'channel': '中村悠一',
6001 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
6002 'channel_follower_count': int,
6003 'uploader': '中村悠一',
6004 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
6005 },
6006 'playlist_mincount': 60,
6007 }, {
6008 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6009 # See test_youtube_lists
6010 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6011 'only_matching': True,
6012 }, {
6013 # No uploads and no UCID given. Should fail with no uploads error
6014 # See test_youtube_lists
6015 'url': 'https://www.youtube.com/news',
6016 'only_matching': True
6017 }, {
6018 # No videos tab but has a shorts tab
6019 'url': 'https://www.youtube.com/c/TKFShorts',
6020 'info_dict': {
6021 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6022 'title': 'Shorts Break - Shorts',
6023 'tags': 'count:32',
6024 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6025 'channel': 'Shorts Break',
6026 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
6027 'uploader': 'Shorts Break',
6028 'channel_follower_count': int,
6029 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6030 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6031 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6032 },
6033 'playlist_mincount': 30,
6034 }, {
6035 # Trending Now Tab. tab id is empty
6036 'url': 'https://www.youtube.com/feed/trending',
6037 'info_dict': {
6038 'id': 'trending',
6039 'title': 'trending - Now',
6040 'tags': [],
6041 },
6042 'playlist_mincount': 30,
6043 }, {
6044 # Trending Gaming Tab. tab id is empty
6045 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6046 'info_dict': {
6047 'id': 'trending',
6048 'title': 'trending - Gaming',
6049 'tags': [],
6050 },
6051 'playlist_mincount': 30,
6052 }, {
6053 # Shorts url result in shorts tab
6054 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6055 'info_dict': {
6056 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6057 'title': 'cole-dlp-test-acc - Shorts',
6058 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6059 'channel': 'cole-dlp-test-acc',
6060 'description': 'test description',
6061 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6062 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6063 'tags': [],
6064 'uploader': 'cole-dlp-test-acc',
6065 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6066
6067 },
6068 'playlist': [{
6069 'info_dict': {
6070 '_type': 'url',
6071 'ie_key': 'Youtube',
6072 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6073 'id': 'sSM9J5YH_60',
6074 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6075 'title': 'SHORT short',
6076 'channel': 'cole-dlp-test-acc',
6077 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6078 'view_count': int,
6079 'thumbnails': list,
6080 }
6081 }],
6082 'params': {'extract_flat': True},
6083 }, {
6084 # Live video status should be extracted
6085 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6086 'info_dict': {
6087 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6088 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6089 'tags': []
6090 },
6091 'playlist': [{
6092 'info_dict': {
6093 '_type': 'url',
6094 'ie_key': 'Youtube',
6095 'url': 'startswith:https://www.youtube.com/watch?v=',
6096 'id': str,
6097 'title': str,
6098 'live_status': 'is_live',
6099 'channel_id': str,
6100 'channel_url': str,
6101 'concurrent_view_count': int,
6102 'channel': str,
6103 }
6104 }],
6105 'params': {'extract_flat': True, 'playlist_items': '1'},
6106 'playlist_mincount': 1
6107 }, {
6108 # Channel renderer metadata. Contains number of videos on the channel
6109 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6110 'info_dict': {
6111 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6112 'title': 'cole-dlp-test-acc - Channels',
6113 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6114 'channel': 'cole-dlp-test-acc',
6115 'description': 'test description',
6116 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6117 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6118 'tags': [],
6119 'uploader': 'cole-dlp-test-acc',
6120 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6121
6122 },
6123 'playlist': [{
6124 'info_dict': {
6125 '_type': 'url',
6126 'ie_key': 'YoutubeTab',
6127 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6128 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6129 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6130 'title': 'PewDiePie',
6131 'channel': 'PewDiePie',
6132 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6133 'thumbnails': list,
6134 'channel_follower_count': int,
6135 'playlist_count': int
6136 }
6137 }],
6138 'params': {'extract_flat': True},
6139 }, {
6140 'url': 'https://www.youtube.com/@3blue1brown/about',
6141 'info_dict': {
6142 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6143 'tags': ['Mathematics'],
6144 'title': '3Blue1Brown - About',
6145 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6146 'channel_follower_count': int,
6147 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6148 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6149 'channel': '3Blue1Brown',
6150 'uploader': '3Blue1Brown',
6151 'view_count': int,
6152 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6153 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6154 },
6155 'playlist_count': 0,
6156 }]
6157
6158 @classmethod
6159 def suitable(cls, url):
6160 return False if YoutubeIE.suitable(url) else super().suitable(url)
6161
6162 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6163
6164 def _get_url_mobj(self, url):
6165 mobj = self._URL_RE.match(url).groupdict()
6166 mobj.update((k, '') for k, v in mobj.items() if v is None)
6167 return mobj
6168
6169 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6170 tab_name = (tab.get('title') or '').lower()
6171 tab_url = urljoin(base_url, traverse_obj(
6172 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6173
6174 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6175 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
6176 if tab_id:
6177 return {
6178 'TAB_ID_SPONSORSHIPS': 'membership',
6179 }.get(tab_id, tab_id), tab_name
6180
6181 # Fallback to tab name if we cannot get the tab id.
6182 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6183 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6184 if tab_name:
6185 self.write_debug(f'Falling back to selected tab name: {tab_name}')
6186 return {
6187 'home': 'featured',
6188 'live': 'streams',
6189 }.get(tab_name, tab_name), tab_name
6190
6191 def _has_tab(self, tabs, tab_id):
6192 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
6193
6194 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6195 def _real_extract(self, url, smuggled_data):
6196 item_id = self._match_id(url)
6197 url = urllib.parse.urlunparse(
6198 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
6199 compat_opts = self.get_param('compat_opts', [])
6200
6201 mobj = self._get_url_mobj(url)
6202 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
6203 if is_channel and smuggled_data.get('is_music_url'):
6204 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6205 return self.url_result(
6206 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6207 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6208 mdata = self._extract_tab_endpoint(
6209 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6210 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6211 get_all=False, expected_type=str)
6212 if not murl:
6213 raise ExtractorError('Failed to resolve album to playlist')
6214 return self.url_result(murl, YoutubeTabIE)
6215 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6216 return self.url_result(
6217 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6218
6219 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
6220 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
6221 url = f'{pre}/videos{post}'
6222 if smuggled_data.get('is_music_url'):
6223 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
6224
6225 # Handle both video/playlist URLs
6226 qs = parse_qs(url)
6227 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
6228 if not video_id and mobj['not_channel'].startswith('watch'):
6229 if not playlist_id:
6230 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6231 raise ExtractorError('A video URL was given without video ID', expected=True)
6232 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6233 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6234 return self.url_result(
6235 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
6236
6237 if not self._yes_playlist(playlist_id, video_id):
6238 return self.url_result(
6239 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6240
6241 data, ytcfg = self._extract_data(url, display_id)
6242
6243 # YouTube may provide a non-standard redirect to the regional channel
6244 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6245 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6246 redirect_url = traverse_obj(
6247 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6248 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
6249 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
6250 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6251 return self.url_result(redirect_url, YoutubeTabIE)
6252
6253 tabs, extra_tabs = self._extract_tab_renderers(data), []
6254 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
6255 selected_tab = self._extract_selected_tab(tabs)
6256 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6257 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6258
6259 if not original_tab_id and selected_tab_name:
6260 self.to_screen('Downloading all uploads of the channel. '
6261 'To download only the videos in a specific tab, pass the tab\'s URL')
6262 if self._has_tab(tabs, 'streams'):
6263 extra_tabs.append(''.join((pre, '/streams', post)))
6264 if self._has_tab(tabs, 'shorts'):
6265 extra_tabs.append(''.join((pre, '/shorts', post)))
6266 # XXX: Members-only tab should also be extracted
6267
6268 if not extra_tabs and selected_tab_id != 'videos':
6269 # Channel does not have streams, shorts or videos tabs
6270 if item_id[:2] != 'UC':
6271 raise ExtractorError('This channel has no uploads', expected=True)
6272
6273 # Topic channels don't have /videos. Use the equivalent playlist instead
6274 pl_id = f'UU{item_id[2:]}'
6275 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6276 try:
6277 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6278 except ExtractorError:
6279 raise ExtractorError('This channel has no uploads', expected=True)
6280 else:
6281 item_id, url = pl_id, pl_url
6282 self.to_screen(
6283 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6284
6285 elif extra_tabs and selected_tab_id != 'videos':
6286 # When there are shorts/live tabs but not videos tab
6287 url, data = f'{pre}{post}', None
6288
6289 elif (original_tab_id or 'videos') != selected_tab_id:
6290 if original_tab_id == 'live':
6291 # Live tab should have redirected to the video
6292 # Except in the case the channel has an actual live tab
6293 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6294 raise UserNotLive(video_id=item_id)
6295 elif selected_tab_name:
6296 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6297
6298 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6299 url = f'{pre}{post}'
6300
6301 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6302 if 'no-youtube-unavailable-videos' not in compat_opts:
6303 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
6304 self._extract_and_report_alerts(data, only_once=True)
6305
6306 tabs, entries = self._extract_tab_renderers(data), []
6307 if tabs:
6308 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6309 entries[0].update({
6310 'extractor_key': YoutubeTabIE.ie_key(),
6311 'extractor': YoutubeTabIE.IE_NAME,
6312 'webpage_url': url,
6313 })
6314 if self.get_param('playlist_items') == '0':
6315 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6316 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6317 entries.extend(map(self._real_extract, extra_tabs))
6318
6319 if len(entries) == 1:
6320 return entries[0]
6321 elif entries:
6322 metadata = self._extract_metadata_from_tabs(item_id, data)
6323 uploads_url = 'the Uploads (UU) playlist URL'
6324 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6325 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6326 self.to_screen(
6327 'Downloading as multiple playlists, separated by tabs. '
6328 f'To download as a single playlist instead, pass {uploads_url}')
6329 return self.playlist_result(entries, item_id, **metadata)
6330
6331 # Inline playlist
6332 playlist = traverse_obj(
6333 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
6334 if playlist:
6335 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
6336
6337 video_id = traverse_obj(
6338 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
6339 if video_id:
6340 if tab != '/live': # live tab is expected to redirect to video
6341 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
6342 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6343
6344 raise ExtractorError('Unable to recognize tab page')
6345
6346
6347 class YoutubePlaylistIE(InfoExtractor):
6348 IE_DESC = 'YouTube playlists'
6349 _VALID_URL = r'''(?x)(?:
6350 (?:https?://)?
6351 (?:\w+\.)?
6352 (?:
6353 (?:
6354 youtube(?:kids)?\.com|
6355 %(invidious)s
6356 )
6357 /.*?\?.*?\blist=
6358 )?
6359 (?P<id>%(playlist_id)s)
6360 )''' % {
6361 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6362 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6363 }
6364 IE_NAME = 'youtube:playlist'
6365 _TESTS = [{
6366 'note': 'issue #673',
6367 'url': 'PLBB231211A4F62143',
6368 'info_dict': {
6369 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6370 'id': 'PLBB231211A4F62143',
6371 'uploader': 'Wickman',
6372 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6373 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6374 'view_count': int,
6375 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6376 'modified_date': r're:\d{8}',
6377 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6378 'channel': 'Wickman',
6379 'tags': [],
6380 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6381 'availability': 'public',
6382 },
6383 'playlist_mincount': 29,
6384 }, {
6385 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6386 'info_dict': {
6387 'title': 'YDL_safe_search',
6388 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6389 },
6390 'playlist_count': 2,
6391 'skip': 'This playlist is private',
6392 }, {
6393 'note': 'embedded',
6394 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6395 'playlist_count': 4,
6396 'info_dict': {
6397 'title': 'JODA15',
6398 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6399 'uploader': 'milan',
6400 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6401 'description': '',
6402 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6403 'tags': [],
6404 'modified_date': '20140919',
6405 'view_count': int,
6406 'channel': 'milan',
6407 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6408 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6409 'availability': 'public',
6410 },
6411 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
6412 }, {
6413 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6414 'playlist_mincount': 455,
6415 'info_dict': {
6416 'title': '2018 Chinese New Singles (11/6 updated)',
6417 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6418 'uploader': 'LBK',
6419 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6420 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6421 'channel': 'LBK',
6422 'view_count': int,
6423 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6424 'tags': [],
6425 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6426 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6427 'modified_date': r're:\d{8}',
6428 'availability': 'public',
6429 },
6430 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
6431 }, {
6432 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6433 'only_matching': True,
6434 }, {
6435 # music album playlist
6436 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6437 'only_matching': True,
6438 }]
6439
6440 @classmethod
6441 def suitable(cls, url):
6442 if YoutubeTabIE.suitable(url):
6443 return False
6444 from ..utils import parse_qs
6445 qs = parse_qs(url)
6446 if qs.get('v', [None])[0]:
6447 return False
6448 return super().suitable(url)
6449
6450 def _real_extract(self, url):
6451 playlist_id = self._match_id(url)
6452 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
6453 url = update_url_query(
6454 'https://www.youtube.com/playlist',
6455 parse_qs(url) or {'list': playlist_id})
6456 if is_music_url:
6457 url = smuggle_url(url, {'is_music_url': True})
6458 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6459
6460
6461 class YoutubeYtBeIE(InfoExtractor):
6462 IE_DESC = 'youtu.be'
6463 _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}
6464 _TESTS = [{
6465 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6466 'info_dict': {
6467 'id': 'yeWKywCrFtk',
6468 'ext': 'mp4',
6469 'title': 'Small Scale Baler and Braiding Rugs',
6470 'uploader': 'Backus-Page House Museum',
6471 'uploader_id': 'backuspagemuseum',
6472 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6473 'upload_date': '20161008',
6474 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6475 'categories': ['Nonprofits & Activism'],
6476 'tags': list,
6477 'like_count': int,
6478 'age_limit': 0,
6479 'playable_in_embed': True,
6480 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6481 'channel': 'Backus-Page House Museum',
6482 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6483 'live_status': 'not_live',
6484 'view_count': int,
6485 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6486 'availability': 'public',
6487 'duration': 59,
6488 'comment_count': int,
6489 'channel_follower_count': int
6490 },
6491 'params': {
6492 'noplaylist': True,
6493 'skip_download': True,
6494 },
6495 }, {
6496 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6497 'only_matching': True,
6498 }]
6499
6500 def _real_extract(self, url):
6501 mobj = self._match_valid_url(url)
6502 video_id = mobj.group('id')
6503 playlist_id = mobj.group('playlist_id')
6504 return self.url_result(
6505 update_url_query('https://www.youtube.com/watch', {
6506 'v': video_id,
6507 'list': playlist_id,
6508 'feature': 'youtu.be',
6509 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6510
6511
6512 class YoutubeLivestreamEmbedIE(InfoExtractor):
6513 IE_DESC = 'YouTube livestream embeds'
6514 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6515 _TESTS = [{
6516 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6517 'only_matching': True,
6518 }]
6519
6520 def _real_extract(self, url):
6521 channel_id = self._match_id(url)
6522 return self.url_result(
6523 f'https://www.youtube.com/channel/{channel_id}/live',
6524 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6525
6526
6527 class YoutubeYtUserIE(InfoExtractor):
6528 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6529 IE_NAME = 'youtube:user'
6530 _VALID_URL = r'ytuser:(?P<id>.+)'
6531 _TESTS = [{
6532 'url': 'ytuser:phihag',
6533 'only_matching': True,
6534 }]
6535
6536 def _real_extract(self, url):
6537 user_id = self._match_id(url)
6538 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
6539
6540
6541 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6542 IE_NAME = 'youtube:favorites'
6543 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6544 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6545 _LOGIN_REQUIRED = True
6546 _TESTS = [{
6547 'url': ':ytfav',
6548 'only_matching': True,
6549 }, {
6550 'url': ':ytfavorites',
6551 'only_matching': True,
6552 }]
6553
6554 def _real_extract(self, url):
6555 return self.url_result(
6556 'https://www.youtube.com/playlist?list=LL',
6557 ie=YoutubeTabIE.ie_key())
6558
6559
6560 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6561 IE_NAME = 'youtube:notif'
6562 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6563 _VALID_URL = r':ytnotif(?:ication)?s?'
6564 _LOGIN_REQUIRED = True
6565 _TESTS = [{
6566 'url': ':ytnotif',
6567 'only_matching': True,
6568 }, {
6569 'url': ':ytnotifications',
6570 'only_matching': True,
6571 }]
6572
6573 def _extract_notification_menu(self, response, continuation_list):
6574 notification_list = traverse_obj(
6575 response,
6576 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6577 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6578 expected_type=list) or []
6579 continuation_list[0] = None
6580 for item in notification_list:
6581 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6582 if entry:
6583 yield entry
6584 continuation = item.get('continuationItemRenderer')
6585 if continuation:
6586 continuation_list[0] = continuation
6587
6588 def _extract_notification_renderer(self, notification):
6589 video_id = traverse_obj(
6590 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6591 url = f'https://www.youtube.com/watch?v={video_id}'
6592 channel_id = None
6593 if not video_id:
6594 browse_ep = traverse_obj(
6595 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6596 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6597 post_id = self._search_regex(
6598 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6599 'post id', default=None)
6600 if not channel_id or not post_id:
6601 return
6602 # The direct /post url redirects to this in the browser
6603 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6604
6605 channel = traverse_obj(
6606 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6607 expected_type=str)
6608 notification_title = self._get_text(notification, 'shortMessage')
6609 if notification_title:
6610 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6611 # TODO: handle recommended videos
6612 title = self._search_regex(
6613 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6614 'video title', default=None)
6615 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6616 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6617 else None)
6618 return {
6619 '_type': 'url',
6620 'url': url,
6621 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6622 'video_id': video_id,
6623 'title': title,
6624 'channel_id': channel_id,
6625 'channel': channel,
6626 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6627 'timestamp': timestamp,
6628 }
6629
6630 def _notification_menu_entries(self, ytcfg):
6631 continuation_list = [None]
6632 response = None
6633 for page in itertools.count(1):
6634 ctoken = traverse_obj(
6635 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6636 response = self._extract_response(
6637 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6638 ep='notification/get_notification_menu', check_get_keys='actions',
6639 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6640 yield from self._extract_notification_menu(response, continuation_list)
6641 if not continuation_list[0]:
6642 break
6643
6644 def _real_extract(self, url):
6645 display_id = 'notifications'
6646 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6647 self._report_playlist_authcheck(ytcfg)
6648 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6649
6650
6651 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6652 IE_DESC = 'YouTube search'
6653 IE_NAME = 'youtube:search'
6654 _SEARCH_KEY = 'ytsearch'
6655 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6656 _TESTS = [{
6657 'url': 'ytsearch5:youtube-dl test video',
6658 'playlist_count': 5,
6659 'info_dict': {
6660 'id': 'youtube-dl test video',
6661 'title': 'youtube-dl test video',
6662 }
6663 }]
6664
6665
6666 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6667 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6668 _SEARCH_KEY = 'ytsearchdate'
6669 IE_DESC = 'YouTube search, newest videos first'
6670 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6671 _TESTS = [{
6672 'url': 'ytsearchdate5:youtube-dl test video',
6673 'playlist_count': 5,
6674 'info_dict': {
6675 'id': 'youtube-dl test video',
6676 'title': 'youtube-dl test video',
6677 }
6678 }]
6679
6680
6681 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6682 IE_DESC = 'YouTube search URLs with sorting and filter support'
6683 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6684 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6685 _TESTS = [{
6686 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6687 'playlist_mincount': 5,
6688 'info_dict': {
6689 'id': 'youtube-dl test video',
6690 'title': 'youtube-dl test video',
6691 }
6692 }, {
6693 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6694 'playlist_mincount': 5,
6695 'info_dict': {
6696 'id': 'python',
6697 'title': 'python',
6698 }
6699 }, {
6700 'url': 'https://www.youtube.com/results?search_query=%23cats',
6701 'playlist_mincount': 1,
6702 'info_dict': {
6703 'id': '#cats',
6704 'title': '#cats',
6705 # The test suite does not have support for nested playlists
6706 # 'entries': [{
6707 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6708 # 'title': '#cats',
6709 # }],
6710 },
6711 }, {
6712 # Channel results
6713 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6714 'info_dict': {
6715 'id': 'kurzgesagt',
6716 'title': 'kurzgesagt',
6717 },
6718 'playlist': [{
6719 'info_dict': {
6720 '_type': 'url',
6721 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6722 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6723 'ie_key': 'YoutubeTab',
6724 'channel': 'Kurzgesagt – In a Nutshell',
6725 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6726 'title': 'Kurzgesagt – In a Nutshell',
6727 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6728 'playlist_count': int, # XXX: should have a way of saying > 1
6729 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6730 'thumbnails': list
6731 }
6732 }],
6733 'params': {'extract_flat': True, 'playlist_items': '1'},
6734 'playlist_mincount': 1,
6735 }, {
6736 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6737 'only_matching': True,
6738 }]
6739
6740 def _real_extract(self, url):
6741 qs = parse_qs(url)
6742 query = (qs.get('search_query') or qs.get('q'))[0]
6743 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6744
6745
6746 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6747 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6748 IE_NAME = 'youtube:music:search_url'
6749 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6750 _TESTS = [{
6751 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6752 'playlist_count': 16,
6753 'info_dict': {
6754 'id': 'royalty free music',
6755 'title': 'royalty free music',
6756 }
6757 }, {
6758 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6759 'playlist_mincount': 30,
6760 'info_dict': {
6761 'id': 'royalty free music - songs',
6762 'title': 'royalty free music - songs',
6763 },
6764 'params': {'extract_flat': 'in_playlist'}
6765 }, {
6766 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6767 'playlist_mincount': 30,
6768 'info_dict': {
6769 'id': 'royalty free music - community playlists',
6770 'title': 'royalty free music - community playlists',
6771 },
6772 'params': {'extract_flat': 'in_playlist'}
6773 }]
6774
6775 _SECTIONS = {
6776 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6777 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6778 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6779 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6780 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6781 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6782 }
6783
6784 def _real_extract(self, url):
6785 qs = parse_qs(url)
6786 query = (qs.get('search_query') or qs.get('q'))[0]
6787 params = qs.get('sp', (None,))[0]
6788 if params:
6789 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6790 else:
6791 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6792 params = self._SECTIONS.get(section)
6793 if not params:
6794 section = None
6795 title = join_nonempty(query, section, delim=' - ')
6796 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6797
6798
6799 class YoutubeFeedsInfoExtractor(InfoExtractor):
6800 """
6801 Base class for feed extractors
6802 Subclasses must re-define the _FEED_NAME property.
6803 """
6804 _LOGIN_REQUIRED = True
6805 _FEED_NAME = 'feeds'
6806
6807 def _real_initialize(self):
6808 YoutubeBaseInfoExtractor._check_login_required(self)
6809
6810 @classproperty
6811 def IE_NAME(self):
6812 return f'youtube:{self._FEED_NAME}'
6813
6814 def _real_extract(self, url):
6815 return self.url_result(
6816 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6817
6818
6819 class YoutubeWatchLaterIE(InfoExtractor):
6820 IE_NAME = 'youtube:watchlater'
6821 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6822 _VALID_URL = r':ytwatchlater'
6823 _TESTS = [{
6824 'url': ':ytwatchlater',
6825 'only_matching': True,
6826 }]
6827
6828 def _real_extract(self, url):
6829 return self.url_result(
6830 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6831
6832
6833 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6834 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6835 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6836 _FEED_NAME = 'recommended'
6837 _LOGIN_REQUIRED = False
6838 _TESTS = [{
6839 'url': ':ytrec',
6840 'only_matching': True,
6841 }, {
6842 'url': ':ytrecommended',
6843 'only_matching': True,
6844 }, {
6845 'url': 'https://youtube.com',
6846 'only_matching': True,
6847 }]
6848
6849
6850 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6851 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6852 _VALID_URL = r':ytsub(?:scription)?s?'
6853 _FEED_NAME = 'subscriptions'
6854 _TESTS = [{
6855 'url': ':ytsubs',
6856 'only_matching': True,
6857 }, {
6858 'url': ':ytsubscriptions',
6859 'only_matching': True,
6860 }]
6861
6862
6863 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6864 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6865 _VALID_URL = r':ythis(?:tory)?'
6866 _FEED_NAME = 'history'
6867 _TESTS = [{
6868 'url': ':ythistory',
6869 'only_matching': True,
6870 }]
6871
6872
6873 class YoutubeStoriesIE(InfoExtractor):
6874 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6875 IE_NAME = 'youtube:stories'
6876 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6877 _TESTS = [{
6878 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6879 'only_matching': True,
6880 }]
6881
6882 def _real_extract(self, url):
6883 playlist_id = f'RLTD{self._match_id(url)}'
6884 return self.url_result(
6885 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6886 ie=YoutubeTabIE, video_id=playlist_id)
6887
6888
6889 class YoutubeShortsAudioPivotIE(InfoExtractor):
6890 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6891 IE_NAME = 'youtube:shorts:pivot:audio'
6892 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6893 _TESTS = [{
6894 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6895 'only_matching': True,
6896 }]
6897
6898 @staticmethod
6899 def _generate_audio_pivot_params(video_id):
6900 """
6901 Generates sfv_audio_pivot browse params for this video id
6902 """
6903 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6904 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6905
6906 def _real_extract(self, url):
6907 video_id = self._match_id(url)
6908 return self.url_result(
6909 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6910 ie=YoutubeTabIE)
6911
6912
6913 class YoutubeTruncatedURLIE(InfoExtractor):
6914 IE_NAME = 'youtube:truncated_url'
6915 IE_DESC = False # Do not list
6916 _VALID_URL = r'''(?x)
6917 (?:https?://)?
6918 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6919 (?:watch\?(?:
6920 feature=[a-z_]+|
6921 annotation_id=annotation_[^&]+|
6922 x-yt-cl=[0-9]+|
6923 hl=[^&]*|
6924 t=[0-9]+
6925 )?
6926 |
6927 attribution_link\?a=[^&]+
6928 )
6929 $
6930 '''
6931
6932 _TESTS = [{
6933 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6934 'only_matching': True,
6935 }, {
6936 'url': 'https://www.youtube.com/watch?',
6937 'only_matching': True,
6938 }, {
6939 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6940 'only_matching': True,
6941 }, {
6942 'url': 'https://www.youtube.com/watch?feature=foo',
6943 'only_matching': True,
6944 }, {
6945 'url': 'https://www.youtube.com/watch?hl=en-GB',
6946 'only_matching': True,
6947 }, {
6948 'url': 'https://www.youtube.com/watch?t=2372',
6949 'only_matching': True,
6950 }]
6951
6952 def _real_extract(self, url):
6953 raise ExtractorError(
6954 'Did you forget to quote the URL? Remember that & is a meta '
6955 'character in most shells, so you want to put the URL in quotes, '
6956 'like youtube-dl '
6957 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6958 ' or simply youtube-dl BaW_jenozKc .',
6959 expected=True)
6960
6961
6962 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6963 IE_NAME = 'youtube:clip'
6964 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6965 _TESTS = [{
6966 # FIXME: Other metadata should be extracted from the clip, not from the base video
6967 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6968 'info_dict': {
6969 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6970 'ext': 'mp4',
6971 'section_start': 29.0,
6972 'section_end': 39.7,
6973 'duration': 10.7,
6974 'age_limit': 0,
6975 'availability': 'public',
6976 'categories': ['Gaming'],
6977 'channel': 'Scott The Woz',
6978 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6979 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6980 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6981 'like_count': int,
6982 'playable_in_embed': True,
6983 'tags': 'count:17',
6984 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6985 'title': 'Mobile Games on Console - Scott The Woz',
6986 'upload_date': '20210920',
6987 'uploader': 'Scott The Woz',
6988 'uploader_id': 'scottthewoz',
6989 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6990 'view_count': int,
6991 'live_status': 'not_live',
6992 'channel_follower_count': int
6993 }
6994 }]
6995
6996 def _real_extract(self, url):
6997 clip_id = self._match_id(url)
6998 _, data = self._extract_webpage(url, clip_id)
6999
7000 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7001 if not video_id:
7002 raise ExtractorError('Unable to find video ID')
7003
7004 clip_data = traverse_obj(data, (
7005 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7006 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7007 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7008 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7009
7010 return {
7011 '_type': 'url_transparent',
7012 'url': f'https://www.youtube.com/watch?v={video_id}',
7013 'ie_key': YoutubeIE.ie_key(),
7014 'id': clip_id,
7015 'section_start': int(clip_data['startTimeMs']) / 1000,
7016 'section_end': int(clip_data['endTimeMs']) / 1000,
7017 }
7018
7019
7020 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7021 IE_NAME = 'youtube:consent'
7022 IE_DESC = False # Do not list
7023 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7024 _TESTS = [{
7025 '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',
7026 'info_dict': {
7027 'id': 'qVv6vCqciTM',
7028 'ext': 'mp4',
7029 'age_limit': 0,
7030 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7031 'comment_count': int,
7032 'chapters': 'count:13',
7033 'upload_date': '20221223',
7034 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7035 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7036 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7037 'like_count': int,
7038 'release_date': '20221223',
7039 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7040 '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】',
7041 'view_count': int,
7042 'playable_in_embed': True,
7043 'duration': 4438,
7044 'availability': 'public',
7045 'channel_follower_count': int,
7046 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7047 'categories': ['Entertainment'],
7048 'live_status': 'was_live',
7049 'release_timestamp': 1671793345,
7050 'channel': 'さなちゃんねる',
7051 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7052 'uploader': 'さなちゃんねる',
7053 },
7054 'add_ie': ['Youtube'],
7055 'params': {'skip_download': 'Youtube'},
7056 }]
7057
7058 def _real_extract(self, url):
7059 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7060 if not redirect_url:
7061 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7062 return self.url_result(redirect_url)
7063
7064
7065 class YoutubeTruncatedIDIE(InfoExtractor):
7066 IE_NAME = 'youtube:truncated_id'
7067 IE_DESC = False # Do not list
7068 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7069
7070 _TESTS = [{
7071 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7072 'only_matching': True,
7073 }]
7074
7075 def _real_extract(self, url):
7076 video_id = self._match_id(url)
7077 raise ExtractorError(
7078 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
7079 expected=True)