]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[extractor/youtube] Add client name to `format_note` when `-v` (#6254)
[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
70 STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
71 # any clients starting with _ cannot be explicitly requested by the user
72 INNERTUBE_CLIENTS = {
73 'web': {
74 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
75 'INNERTUBE_CONTEXT': {
76 'client': {
77 'clientName': 'WEB',
78 'clientVersion': '2.20220801.00.00',
79 }
80 },
81 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
82 },
83 'web_embedded': {
84 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
85 'INNERTUBE_CONTEXT': {
86 'client': {
87 'clientName': 'WEB_EMBEDDED_PLAYER',
88 'clientVersion': '1.20220731.00.00',
89 },
90 },
91 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
92 },
93 'web_music': {
94 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
95 'INNERTUBE_HOST': 'music.youtube.com',
96 'INNERTUBE_CONTEXT': {
97 'client': {
98 'clientName': 'WEB_REMIX',
99 'clientVersion': '1.20220727.01.00',
100 }
101 },
102 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
103 },
104 'web_creator': {
105 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
106 'INNERTUBE_CONTEXT': {
107 'client': {
108 'clientName': 'WEB_CREATOR',
109 'clientVersion': '1.20220726.00.00',
110 }
111 },
112 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
113 },
114 'android': {
115 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
116 'INNERTUBE_CONTEXT': {
117 'client': {
118 'clientName': 'ANDROID',
119 'clientVersion': '17.31.35',
120 'androidSdkVersion': 30,
121 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
122 }
123 },
124 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
125 'REQUIRE_JS_PLAYER': False
126 },
127 'android_embedded': {
128 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
129 'INNERTUBE_CONTEXT': {
130 'client': {
131 'clientName': 'ANDROID_EMBEDDED_PLAYER',
132 'clientVersion': '17.31.35',
133 'androidSdkVersion': 30,
134 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
135 },
136 },
137 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
138 'REQUIRE_JS_PLAYER': False
139 },
140 'android_music': {
141 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
142 'INNERTUBE_CONTEXT': {
143 'client': {
144 'clientName': 'ANDROID_MUSIC',
145 'clientVersion': '5.16.51',
146 'androidSdkVersion': 30,
147 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
148 }
149 },
150 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
151 'REQUIRE_JS_PLAYER': False
152 },
153 'android_creator': {
154 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
155 'INNERTUBE_CONTEXT': {
156 'client': {
157 'clientName': 'ANDROID_CREATOR',
158 'clientVersion': '22.30.100',
159 'androidSdkVersion': 30,
160 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
161 },
162 },
163 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
164 'REQUIRE_JS_PLAYER': False
165 },
166 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
167 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
168 'ios': {
169 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS',
173 'clientVersion': '17.33.2',
174 'deviceModel': 'iPhone14,3',
175 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
176 }
177 },
178 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
179 'REQUIRE_JS_PLAYER': False
180 },
181 'ios_embedded': {
182 'INNERTUBE_CONTEXT': {
183 'client': {
184 'clientName': 'IOS_MESSAGES_EXTENSION',
185 'clientVersion': '17.33.2',
186 'deviceModel': 'iPhone14,3',
187 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
188 },
189 },
190 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
191 'REQUIRE_JS_PLAYER': False
192 },
193 'ios_music': {
194 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
195 'INNERTUBE_CONTEXT': {
196 'client': {
197 'clientName': 'IOS_MUSIC',
198 'clientVersion': '5.21',
199 'deviceModel': 'iPhone14,3',
200 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
201 },
202 },
203 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
204 'REQUIRE_JS_PLAYER': False
205 },
206 'ios_creator': {
207 'INNERTUBE_CONTEXT': {
208 'client': {
209 'clientName': 'IOS_CREATOR',
210 'clientVersion': '22.33.101',
211 'deviceModel': 'iPhone14,3',
212 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
213 },
214 },
215 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
216 'REQUIRE_JS_PLAYER': False
217 },
218 # mweb has 'ultralow' formats
219 # See: https://github.com/yt-dlp/yt-dlp/pull/557
220 'mweb': {
221 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
222 'INNERTUBE_CONTEXT': {
223 'client': {
224 'clientName': 'MWEB',
225 'clientVersion': '2.20220801.00.00',
226 }
227 },
228 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
229 },
230 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
231 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
232 'tv_embedded': {
233 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
234 'INNERTUBE_CONTEXT': {
235 'client': {
236 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
237 'clientVersion': '2.0',
238 },
239 },
240 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
241 },
242 }
243
244
245 def _split_innertube_client(client_name):
246 variant, *base = client_name.rsplit('.', 1)
247 if base:
248 return variant, base[0], variant
249 base, *variant = client_name.split('_', 1)
250 return client_name, base, variant[0] if variant else None
251
252
253 def short_client_name(client_name):
254 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
255 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
256
257
258 def build_innertube_clients():
259 THIRD_PARTY = {
260 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
261 }
262 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
263 priority = qualities(BASE_CLIENTS[::-1])
264
265 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
266 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
267 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
268 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
269 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
270
271 _, base_client, variant = _split_innertube_client(client)
272 ytcfg['priority'] = 10 * priority(base_client)
273
274 if not variant:
275 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
276 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
277 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
278 embedscreen['priority'] -= 3
279 elif variant == 'embedded':
280 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
281 ytcfg['priority'] -= 2
282 else:
283 ytcfg['priority'] -= 3
284
285
286 build_innertube_clients()
287
288
289 class BadgeType(enum.Enum):
290 AVAILABILITY_UNLISTED = enum.auto()
291 AVAILABILITY_PRIVATE = enum.auto()
292 AVAILABILITY_PUBLIC = enum.auto()
293 AVAILABILITY_PREMIUM = enum.auto()
294 AVAILABILITY_SUBSCRIPTION = enum.auto()
295 LIVE_NOW = enum.auto()
296
297
298 class YoutubeBaseInfoExtractor(InfoExtractor):
299 """Provide base functions for Youtube extractors"""
300
301 _RESERVED_NAMES = (
302 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
303 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
304 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
305 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
306
307 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
308
309 # _NETRC_MACHINE = 'youtube'
310
311 # If True it will raise an error if no login info is provided
312 _LOGIN_REQUIRED = False
313
314 _INVIDIOUS_SITES = (
315 # invidious-redirect websites
316 r'(?:www\.)?redirect\.invidious\.io',
317 r'(?:(?:www|dev)\.)?invidio\.us',
318 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
319 r'(?:www\.)?invidious\.pussthecat\.org',
320 r'(?:www\.)?invidious\.zee\.li',
321 r'(?:www\.)?invidious\.ethibox\.fr',
322 r'(?:www\.)?iv\.ggtyler\.dev',
323 r'(?:www\.)?inv\.vern\.i2p',
324 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
325 r'(?:www\.)?inv\.riverside\.rocks',
326 r'(?:www\.)?invidious\.silur\.me',
327 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
328 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
329 r'(?:www\.)?invidious\.slipfox\.xyz',
330 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
331 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
332 r'(?:www\.)?invidious\.tiekoetter\.com',
333 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
334 r'(?:www\.)?invidious\.nerdvpn\.de',
335 r'(?:www\.)?invidious\.weblibre\.org',
336 r'(?:www\.)?inv\.odyssey346\.dev',
337 r'(?:www\.)?invidious\.dhusch\.de',
338 r'(?:www\.)?iv\.melmac\.space',
339 r'(?:www\.)?watch\.thekitty\.zone',
340 r'(?:www\.)?invidious\.privacydev\.net',
341 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
342 r'(?:www\.)?invidious\.drivet\.xyz',
343 r'(?:www\.)?vid\.priv\.au',
344 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
345 r'(?:www\.)?inv\.vern\.cc',
346 r'(?:www\.)?invidious\.esmailelbob\.xyz',
347 r'(?:www\.)?invidious\.sethforprivacy\.com',
348 r'(?:www\.)?yt\.oelrichsgarcia\.de',
349 r'(?:www\.)?yt\.artemislena\.eu',
350 r'(?:www\.)?invidious\.flokinet\.to',
351 r'(?:www\.)?invidious\.baczek\.me',
352 r'(?:www\.)?y\.com\.sb',
353 r'(?:www\.)?invidious\.epicsite\.xyz',
354 r'(?:www\.)?invidious\.lidarshield\.cloud',
355 r'(?:www\.)?yt\.funami\.tech',
356 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
357 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
358 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
359 # youtube-dl invidious instances list
360 r'(?:(?:www|no)\.)?invidiou\.sh',
361 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
362 r'(?:www\.)?invidious\.kabi\.tk',
363 r'(?:www\.)?invidious\.mastodon\.host',
364 r'(?:www\.)?invidious\.zapashcanon\.fr',
365 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
366 r'(?:www\.)?invidious\.tinfoil-hat\.net',
367 r'(?:www\.)?invidious\.himiko\.cloud',
368 r'(?:www\.)?invidious\.reallyancient\.tech',
369 r'(?:www\.)?invidious\.tube',
370 r'(?:www\.)?invidiou\.site',
371 r'(?:www\.)?invidious\.site',
372 r'(?:www\.)?invidious\.xyz',
373 r'(?:www\.)?invidious\.nixnet\.xyz',
374 r'(?:www\.)?invidious\.048596\.xyz',
375 r'(?:www\.)?invidious\.drycat\.fr',
376 r'(?:www\.)?inv\.skyn3t\.in',
377 r'(?:www\.)?tube\.poal\.co',
378 r'(?:www\.)?tube\.connect\.cafe',
379 r'(?:www\.)?vid\.wxzm\.sx',
380 r'(?:www\.)?vid\.mint\.lgbt',
381 r'(?:www\.)?vid\.puffyan\.us',
382 r'(?:www\.)?yewtu\.be',
383 r'(?:www\.)?yt\.elukerio\.org',
384 r'(?:www\.)?yt\.lelux\.fi',
385 r'(?:www\.)?invidious\.ggc-project\.de',
386 r'(?:www\.)?yt\.maisputain\.ovh',
387 r'(?:www\.)?ytprivate\.com',
388 r'(?:www\.)?invidious\.13ad\.de',
389 r'(?:www\.)?invidious\.toot\.koeln',
390 r'(?:www\.)?invidious\.fdn\.fr',
391 r'(?:www\.)?watch\.nettohikari\.com',
392 r'(?:www\.)?invidious\.namazso\.eu',
393 r'(?:www\.)?invidious\.silkky\.cloud',
394 r'(?:www\.)?invidious\.exonip\.de',
395 r'(?:www\.)?invidious\.riverside\.rocks',
396 r'(?:www\.)?invidious\.blamefran\.net',
397 r'(?:www\.)?invidious\.moomoo\.de',
398 r'(?:www\.)?ytb\.trom\.tf',
399 r'(?:www\.)?yt\.cyberhost\.uk',
400 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
401 r'(?:www\.)?qklhadlycap4cnod\.onion',
402 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
403 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
404 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
405 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
406 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
407 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
408 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
409 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
410 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
411 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
412 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
413 r'(?:www\.)?piped\.kavin\.rocks',
414 r'(?:www\.)?piped\.tokhmi\.xyz',
415 r'(?:www\.)?piped\.syncpundit\.io',
416 r'(?:www\.)?piped\.mha\.fi',
417 r'(?:www\.)?watch\.whatever\.social',
418 r'(?:www\.)?piped\.garudalinux\.org',
419 r'(?:www\.)?piped\.rivo\.lol',
420 r'(?:www\.)?piped-libre\.kavin\.rocks',
421 r'(?:www\.)?yt\.jae\.fi',
422 r'(?:www\.)?piped\.mint\.lgbt',
423 r'(?:www\.)?il\.ax',
424 r'(?:www\.)?piped\.esmailelbob\.xyz',
425 r'(?:www\.)?piped\.projectsegfau\.lt',
426 r'(?:www\.)?piped\.privacydev\.net',
427 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
428 r'(?:www\.)?piped\.smnz\.de',
429 r'(?:www\.)?piped\.adminforge\.de',
430 r'(?:www\.)?watch\.whatevertinfoil\.de',
431 r'(?:www\.)?piped\.qdi\.fi',
432 r'(?:www\.)?piped\.video',
433 r'(?:www\.)?piped\.aeong\.one',
434 r'(?:www\.)?piped\.moomoo\.me',
435 r'(?:www\.)?piped\.chauvet\.pro',
436 r'(?:www\.)?watch\.leptons\.xyz',
437 r'(?:www\.)?pd\.vern\.cc',
438 r'(?:www\.)?piped\.hostux\.net',
439 r'(?:www\.)?piped\.lunar\.icu',
440 # Hyperpipe instances from https://hyperpipe.codeberg.page/
441 r'(?:www\.)?hyperpipe\.surge\.sh',
442 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
443 r'(?:www\.)?listen\.whatever\.social',
444 r'(?:www\.)?music\.adminforge\.de',
445 )
446
447 # extracted from account/account_menu ep
448 # XXX: These are the supported YouTube UI and API languages,
449 # which is slightly different from languages supported for translation in YouTube studio
450 _SUPPORTED_LANG_CODES = [
451 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
452 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
453 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
454 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
455 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
456 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
457 ]
458
459 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
460
461 @functools.cached_property
462 def _preferred_lang(self):
463 """
464 Returns a language code supported by YouTube for the user preferred language.
465 Returns None if no preferred language set.
466 """
467 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
468 if not preferred_lang:
469 return
470 if preferred_lang not in self._SUPPORTED_LANG_CODES:
471 raise ExtractorError(
472 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
473 expected=True)
474 elif preferred_lang != 'en':
475 self.report_warning(
476 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
477 return preferred_lang
478
479 def _initialize_consent(self):
480 cookies = self._get_cookies('https://www.youtube.com/')
481 if cookies.get('__Secure-3PSID'):
482 return
483 consent_id = None
484 consent = cookies.get('CONSENT')
485 if consent:
486 if 'YES' in consent.value:
487 return
488 consent_id = self._search_regex(
489 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
490 if not consent_id:
491 consent_id = random.randint(100, 999)
492 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
493
494 def _initialize_pref(self):
495 cookies = self._get_cookies('https://www.youtube.com/')
496 pref_cookie = cookies.get('PREF')
497 pref = {}
498 if pref_cookie:
499 try:
500 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
501 except ValueError:
502 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
503 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
504 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
505
506 def _real_initialize(self):
507 self._initialize_pref()
508 self._initialize_consent()
509 self._check_login_required()
510
511 def _check_login_required(self):
512 if self._LOGIN_REQUIRED and not self._cookies_passed:
513 self.raise_login_required('Login details are needed to download this content', method='cookies')
514
515 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
516 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
517
518 def _get_default_ytcfg(self, client='web'):
519 return copy.deepcopy(INNERTUBE_CLIENTS[client])
520
521 def _get_innertube_host(self, client='web'):
522 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
523
524 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
525 # try_get but with fallback to default ytcfg client values when present
526 _func = lambda y: try_get(y, getter, expected_type)
527 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
528
529 def _extract_client_name(self, ytcfg, default_client='web'):
530 return self._ytcfg_get_safe(
531 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
532 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
533
534 def _extract_client_version(self, ytcfg, default_client='web'):
535 return self._ytcfg_get_safe(
536 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
537 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
538
539 def _select_api_hostname(self, req_api_hostname, default_client=None):
540 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
541 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
542
543 def _extract_api_key(self, ytcfg=None, default_client='web'):
544 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
545
546 def _extract_context(self, ytcfg=None, default_client='web'):
547 context = get_first(
548 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
549 # Enforce language and tz for extraction
550 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
551 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
552 return context
553
554 _SAPISID = None
555
556 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
557 time_now = round(time.time())
558 if self._SAPISID is None:
559 yt_cookies = self._get_cookies('https://www.youtube.com')
560 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
561 # See: https://github.com/yt-dlp/yt-dlp/issues/393
562 sapisid_cookie = dict_get(
563 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
564 if sapisid_cookie and sapisid_cookie.value:
565 self._SAPISID = sapisid_cookie.value
566 self.write_debug('Extracted SAPISID cookie')
567 # SAPISID cookie is required if not already present
568 if not yt_cookies.get('SAPISID'):
569 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
570 self._set_cookie(
571 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
572 else:
573 self._SAPISID = False
574 if not self._SAPISID:
575 return None
576 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
577 sapisidhash = hashlib.sha1(
578 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
579 return f'SAPISIDHASH {time_now}_{sapisidhash}'
580
581 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
582 note='Downloading API JSON', errnote='Unable to download API page',
583 context=None, api_key=None, api_hostname=None, default_client='web'):
584
585 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
586 data.update(query)
587 real_headers = self.generate_api_headers(default_client=default_client)
588 real_headers.update({'content-type': 'application/json'})
589 if headers:
590 real_headers.update(headers)
591 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
592 or api_key or self._extract_api_key(default_client=default_client))
593 return self._download_json(
594 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
595 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
596 data=json.dumps(data).encode('utf8'), headers=real_headers,
597 query={'key': api_key, 'prettyPrint': 'false'})
598
599 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
600 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
601
602 @staticmethod
603 def _extract_session_index(*data):
604 """
605 Index of current account in account list.
606 See: https://github.com/yt-dlp/yt-dlp/pull/519
607 """
608 for ytcfg in data:
609 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
610 if session_index is not None:
611 return session_index
612
613 # Deprecated?
614 def _extract_identity_token(self, ytcfg=None, webpage=None):
615 if ytcfg:
616 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
617 if token:
618 return token
619 if webpage:
620 return self._search_regex(
621 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
622 'identity token', default=None, fatal=False)
623
624 @staticmethod
625 def _extract_account_syncid(*args):
626 """
627 Extract syncId required to download private playlists of secondary channels
628 @params response and/or ytcfg
629 """
630 for data in args:
631 # ytcfg includes channel_syncid if on secondary channel
632 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
633 if delegated_sid:
634 return delegated_sid
635 sync_ids = (try_get(
636 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
637 lambda x: x['DATASYNC_ID']), str) or '').split('||')
638 if len(sync_ids) >= 2 and sync_ids[1]:
639 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
640 # and just "user_syncid||" for primary channel. We only want the channel_syncid
641 return sync_ids[0]
642
643 @staticmethod
644 def _extract_visitor_data(*args):
645 """
646 Extracts visitorData from an API response or ytcfg
647 Appears to be used to track session state
648 """
649 return get_first(
650 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
651 expected_type=str)
652
653 @functools.cached_property
654 def is_authenticated(self):
655 return bool(self._generate_sapisidhash_header())
656
657 def extract_ytcfg(self, video_id, webpage):
658 if not webpage:
659 return {}
660 return self._parse_json(
661 self._search_regex(
662 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
663 default='{}'), video_id, fatal=False) or {}
664
665 def generate_api_headers(
666 self, *, ytcfg=None, account_syncid=None, session_index=None,
667 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
668
669 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
670 headers = {
671 'X-YouTube-Client-Name': str(
672 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
673 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
674 'Origin': origin,
675 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
676 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
677 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
678 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
679 }
680 if session_index is None:
681 session_index = self._extract_session_index(ytcfg)
682 if account_syncid or session_index is not None:
683 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
684
685 auth = self._generate_sapisidhash_header(origin)
686 if auth is not None:
687 headers['Authorization'] = auth
688 headers['X-Origin'] = origin
689 return filter_dict(headers)
690
691 def _download_ytcfg(self, client, video_id):
692 url = {
693 'web': 'https://www.youtube.com',
694 'web_music': 'https://music.youtube.com',
695 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
696 }.get(client)
697 if not url:
698 return {}
699 webpage = self._download_webpage(
700 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
701 return self.extract_ytcfg(video_id, webpage) or {}
702
703 @staticmethod
704 def _build_api_continuation_query(continuation, ctp=None):
705 query = {
706 'continuation': continuation
707 }
708 # TODO: Inconsistency with clickTrackingParams.
709 # Currently we have a fixed ctp contained within context (from ytcfg)
710 # and a ctp in root query for continuation.
711 if ctp:
712 query['clickTracking'] = {'clickTrackingParams': ctp}
713 return query
714
715 @classmethod
716 def _extract_next_continuation_data(cls, renderer):
717 next_continuation = try_get(
718 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
719 lambda x: x['continuation']['reloadContinuationData']), dict)
720 if not next_continuation:
721 return
722 continuation = next_continuation.get('continuation')
723 if not continuation:
724 return
725 ctp = next_continuation.get('clickTrackingParams')
726 return cls._build_api_continuation_query(continuation, ctp)
727
728 @classmethod
729 def _extract_continuation_ep_data(cls, continuation_ep: dict):
730 if isinstance(continuation_ep, dict):
731 continuation = try_get(
732 continuation_ep, lambda x: x['continuationCommand']['token'], str)
733 if not continuation:
734 return
735 ctp = continuation_ep.get('clickTrackingParams')
736 return cls._build_api_continuation_query(continuation, ctp)
737
738 @classmethod
739 def _extract_continuation(cls, renderer):
740 next_continuation = cls._extract_next_continuation_data(renderer)
741 if next_continuation:
742 return next_continuation
743
744 return traverse_obj(renderer, (
745 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
746 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
747 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
748
749 @classmethod
750 def _extract_alerts(cls, data):
751 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
752 if not isinstance(alert_dict, dict):
753 continue
754 for alert in alert_dict.values():
755 alert_type = alert.get('type')
756 if not alert_type:
757 continue
758 message = cls._get_text(alert, 'text')
759 if message:
760 yield alert_type, message
761
762 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
763 errors, warnings = [], []
764 for alert_type, alert_message in alerts:
765 if alert_type.lower() == 'error' and fatal:
766 errors.append([alert_type, alert_message])
767 elif alert_message not in self._IGNORED_WARNINGS:
768 warnings.append([alert_type, alert_message])
769
770 for alert_type, alert_message in (warnings + errors[:-1]):
771 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
772 if errors:
773 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
774
775 def _extract_and_report_alerts(self, data, *args, **kwargs):
776 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
777
778 def _extract_badges(self, renderer: dict):
779 privacy_icon_map = {
780 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
781 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
782 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
783 }
784
785 badge_style_map = {
786 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
787 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
788 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
789 }
790
791 label_map = {
792 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
793 'private': BadgeType.AVAILABILITY_PRIVATE,
794 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
795 'live': BadgeType.LIVE_NOW,
796 'premium': BadgeType.AVAILABILITY_PREMIUM
797 }
798
799 badges = []
800 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')):
801 badge_type = (
802 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
803 or badge_style_map.get(traverse_obj(badge, 'style'))
804 )
805 if badge_type:
806 badges.append({'type': badge_type})
807 continue
808
809 # fallback, won't work in some languages
810 label = traverse_obj(badge, 'label', expected_type=str, default='')
811 for match, label_badge_type in label_map.items():
812 if match in label.lower():
813 badges.append({'type': badge_type})
814 continue
815
816 return badges
817
818 @staticmethod
819 def _has_badge(badges, badge_type):
820 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
821
822 @staticmethod
823 def _get_text(data, *path_list, max_runs=None):
824 for path in path_list or [None]:
825 if path is None:
826 obj = [data]
827 else:
828 obj = traverse_obj(data, path, default=[])
829 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
830 obj = [obj]
831 for item in obj:
832 text = try_get(item, lambda x: x['simpleText'], str)
833 if text:
834 return text
835 runs = try_get(item, lambda x: x['runs'], list) or []
836 if not runs and isinstance(item, list):
837 runs = item
838
839 runs = runs[:min(len(runs), max_runs or len(runs))]
840 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
841 if text:
842 return text
843
844 def _get_count(self, data, *path_list):
845 count_text = self._get_text(data, *path_list) or ''
846 count = parse_count(count_text)
847 if count is None:
848 count = str_to_int(
849 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
850 return count
851
852 @staticmethod
853 def _extract_thumbnails(data, *path_list):
854 """
855 Extract thumbnails from thumbnails dict
856 @param path_list: path list to level that contains 'thumbnails' key
857 """
858 thumbnails = []
859 for path in path_list or [()]:
860 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
861 thumbnail_url = url_or_none(thumbnail.get('url'))
862 if not thumbnail_url:
863 continue
864 # Sometimes youtube gives a wrong thumbnail URL. See:
865 # https://github.com/yt-dlp/yt-dlp/issues/233
866 # https://github.com/ytdl-org/youtube-dl/issues/28023
867 if 'maxresdefault' in thumbnail_url:
868 thumbnail_url = thumbnail_url.split('?')[0]
869 thumbnails.append({
870 'url': thumbnail_url,
871 'height': int_or_none(thumbnail.get('height')),
872 'width': int_or_none(thumbnail.get('width')),
873 })
874 return thumbnails
875
876 @staticmethod
877 def extract_relative_time(relative_time_text):
878 """
879 Extracts a relative time from string and converts to dt object
880 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
881 """
882 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)
883 if mobj:
884 start = mobj.group('start')
885 if start:
886 return datetime_from_str(start)
887 try:
888 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
889 except ValueError:
890 return None
891
892 def _parse_time_text(self, text):
893 if not text:
894 return
895 dt = self.extract_relative_time(text)
896 timestamp = None
897 if isinstance(dt, datetime.datetime):
898 timestamp = calendar.timegm(dt.timetuple())
899
900 if timestamp is None:
901 timestamp = (
902 unified_timestamp(text) or unified_timestamp(
903 self._search_regex(
904 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
905 text.lower(), 'time text', default=None)))
906
907 if text and timestamp is None and self._preferred_lang in (None, 'en'):
908 self.report_warning(
909 f'Cannot parse localized time text "{text}"', only_once=True)
910 return timestamp
911
912 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
913 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
914 default_client='web'):
915 for retry in self.RetryManager():
916 try:
917 response = self._call_api(
918 ep=ep, fatal=True, headers=headers,
919 video_id=item_id, query=query, note=note,
920 context=self._extract_context(ytcfg, default_client),
921 api_key=self._extract_api_key(ytcfg, default_client),
922 api_hostname=api_hostname, default_client=default_client)
923 except ExtractorError as e:
924 if not isinstance(e.cause, network_exceptions):
925 return self._error_or_warning(e, fatal=fatal)
926 elif not isinstance(e.cause, urllib.error.HTTPError):
927 retry.error = e
928 continue
929
930 first_bytes = e.cause.read(512)
931 if not is_html(first_bytes):
932 yt_error = try_get(
933 self._parse_json(
934 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
935 lambda x: x['error']['message'], str)
936 if yt_error:
937 self._report_alerts([('ERROR', yt_error)], fatal=False)
938 # Downloading page may result in intermittent 5xx HTTP error
939 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
940 # We also want to catch all other network exceptions since errors in later pages can be troublesome
941 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
942 if e.cause.code not in (403, 429):
943 retry.error = e
944 continue
945 return self._error_or_warning(e, fatal=fatal)
946
947 try:
948 self._extract_and_report_alerts(response, only_once=True)
949 except ExtractorError as e:
950 # YouTube servers may return errors we want to retry on in a 200 OK response
951 # See: https://github.com/yt-dlp/yt-dlp/issues/839
952 if 'unknown error' in e.msg.lower():
953 retry.error = e
954 continue
955 return self._error_or_warning(e, fatal=fatal)
956 # Youtube sometimes sends incomplete data
957 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
958 if not traverse_obj(response, *variadic(check_get_keys)):
959 retry.error = ExtractorError('Incomplete data received', expected=True)
960 continue
961
962 return response
963
964 @staticmethod
965 def is_music_url(url):
966 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
967
968 def _extract_video(self, renderer):
969 video_id = renderer.get('videoId')
970
971 reel_header_renderer = traverse_obj(renderer, (
972 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
973 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
974
975 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
976 description = self._get_text(renderer, 'descriptionSnippet')
977
978 duration = int_or_none(renderer.get('lengthSeconds'))
979 if duration is None:
980 duration = parse_duration(self._get_text(
981 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
982 if duration is None:
983 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
984 duration = parse_duration(self._search_regex(
985 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
986 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
987 video_id, default=None, group='duration'))
988
989 channel_id = traverse_obj(
990 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
991 expected_type=str, get_all=False)
992 if not channel_id:
993 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
994
995 overlay_style = traverse_obj(
996 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
997 get_all=False, expected_type=str)
998 badges = self._extract_badges(renderer)
999
1000 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
1001 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1002 expected_type=str)) or ''
1003 url = f'https://www.youtube.com/watch?v={video_id}'
1004 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
1005 url = f'https://www.youtube.com/shorts/{video_id}'
1006
1007 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1008 or self._get_text(reel_header_renderer, 'timestampText') or '')
1009 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1010
1011 live_status = (
1012 'is_upcoming' if scheduled_timestamp is not None
1013 else 'was_live' if 'streamed' in time_text.lower()
1014 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1015 else None)
1016
1017 # videoInfo is a string like '50K views • 10 years ago'.
1018 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1019 view_count = (0 if 'no views' in view_count_text.lower()
1020 else self._get_count({'simpleText': view_count_text}))
1021 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1022
1023 return {
1024 '_type': 'url',
1025 'ie_key': YoutubeIE.ie_key(),
1026 'id': video_id,
1027 'url': url,
1028 'title': title,
1029 'description': description,
1030 'duration': duration,
1031 'channel_id': channel_id,
1032 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
1033 or self._get_text(reel_header_renderer, 'channelTitleText')),
1034 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
1035 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
1036 'timestamp': (self._parse_time_text(time_text)
1037 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1038 else None),
1039 'release_timestamp': scheduled_timestamp,
1040 'availability':
1041 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1042 else self._availability(
1043 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1044 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1045 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
1046 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
1047 view_count_field: view_count,
1048 'live_status': live_status
1049 }
1050
1051
1052 class YoutubeIE(YoutubeBaseInfoExtractor):
1053 IE_DESC = 'YouTube'
1054 _VALID_URL = r"""(?x)^
1055 (
1056 (?:https?://|//) # http(s):// or protocol-independent URL
1057 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1058 (?:www\.)?deturl\.com/www\.youtube\.com|
1059 (?:www\.)?pwnyoutube\.com|
1060 (?:www\.)?hooktube\.com|
1061 (?:www\.)?yourepeat\.com|
1062 tube\.majestyc\.net|
1063 %(invidious)s|
1064 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
1065 (?:.*?\#/)? # handle anchor (#/) redirect urls
1066 (?: # the various things that can precede the ID:
1067 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
1068 |(?: # or the v= param in all its forms
1069 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
1070 (?:\?|\#!?) # the params delimiter ? or # or #!
1071 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
1072 v=
1073 )
1074 ))
1075 |(?:
1076 youtu\.be| # just youtu.be/xxxx
1077 vid\.plus| # or vid.plus/xxxx
1078 zwearz\.com/watch| # or zwearz.com/watch/xxxx
1079 %(invidious)s
1080 )/
1081 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
1082 )
1083 )? # all until now is optional -> you can pass the naked ID
1084 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
1085 (?(1).+)? # if we found the ID, everything can follow
1086 (?:\#|$)""" % {
1087 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
1088 }
1089 _EMBED_REGEX = [
1090 r'''(?x)
1091 (?:
1092 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
1093 data-video-url=|
1094 <embed[^>]+?src=|
1095 embedSWF\(?:\s*|
1096 <object[^>]+data=|
1097 new\s+SWFObject\(
1098 )
1099 (["\'])
1100 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1101 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1102 \1''',
1103 # https://wordpress.org/plugins/lazy-load-for-videos/
1104 r'''(?xs)
1105 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1106 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1107 ]
1108 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
1109
1110 _PLAYER_INFO_RE = (
1111 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1112 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$',
1113 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
1114 )
1115 _formats = {
1116 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1117 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1118 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1119 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1120 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1121 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1122 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1123 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1124 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
1125 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1126 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1127 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1128 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1129 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1130 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1131 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1132 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1133 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1134
1135
1136 # 3D videos
1137 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1138 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1139 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1140 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1141 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1142 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1143 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1144
1145 # Apple HTTP Live Streaming
1146 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1147 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1148 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1149 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1150 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1151 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1152 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1153 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
1154
1155 # DASH mp4 video
1156 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1157 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1158 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1159 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1160 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
1161 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
1162 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1163 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1164 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1165 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1166 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1167 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1168
1169 # Dash mp4 audio
1170 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1171 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1172 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1173 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1174 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1175 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1176 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1177
1178 # Dash webm
1179 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1180 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1181 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1182 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1183 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1184 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1185 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1186 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1187 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1188 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1189 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1190 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1191 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1192 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1193 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1194 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1195 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1196 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1197 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1198 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1199 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1200 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1201
1202 # Dash webm audio
1203 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1204 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1205
1206 # Dash webm audio with opus inside
1207 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1208 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1209 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1210
1211 # RTMP (unnamed)
1212 '_rtmp': {'protocol': 'rtmp'},
1213
1214 # av01 video only formats sometimes served with "unknown" codecs
1215 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1216 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1217 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1218 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1219 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1220 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1221 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1222 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1223 }
1224 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1225
1226 _GEO_BYPASS = False
1227
1228 IE_NAME = 'youtube'
1229 _TESTS = [
1230 {
1231 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1232 'info_dict': {
1233 'id': 'BaW_jenozKc',
1234 'ext': 'mp4',
1235 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1236 'uploader': 'Philipp Hagemeister',
1237 'uploader_id': 'phihag',
1238 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1239 'channel': 'Philipp Hagemeister',
1240 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1241 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1242 'upload_date': '20121002',
1243 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1244 'categories': ['Science & Technology'],
1245 'tags': ['youtube-dl'],
1246 'duration': 10,
1247 'view_count': int,
1248 'like_count': int,
1249 'availability': 'public',
1250 'playable_in_embed': True,
1251 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1252 'live_status': 'not_live',
1253 'age_limit': 0,
1254 'start_time': 1,
1255 'end_time': 9,
1256 'comment_count': int,
1257 'channel_follower_count': int
1258 }
1259 },
1260 {
1261 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1262 'note': 'Embed-only video (#1746)',
1263 'info_dict': {
1264 'id': 'yZIXLfi8CZQ',
1265 'ext': 'mp4',
1266 'upload_date': '20120608',
1267 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1268 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1269 'uploader': 'SET India',
1270 'uploader_id': 'setindia',
1271 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1272 'age_limit': 18,
1273 },
1274 'skip': 'Private video',
1275 },
1276 {
1277 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1278 'note': 'Use the first video ID in the URL',
1279 'info_dict': {
1280 'id': 'BaW_jenozKc',
1281 'ext': 'mp4',
1282 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1283 'uploader': 'Philipp Hagemeister',
1284 'uploader_id': 'phihag',
1285 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1286 'channel': 'Philipp Hagemeister',
1287 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1288 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1289 'upload_date': '20121002',
1290 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1291 'categories': ['Science & Technology'],
1292 'tags': ['youtube-dl'],
1293 'duration': 10,
1294 'view_count': int,
1295 'like_count': int,
1296 'availability': 'public',
1297 'playable_in_embed': True,
1298 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1299 'live_status': 'not_live',
1300 'age_limit': 0,
1301 'comment_count': int,
1302 'channel_follower_count': int
1303 },
1304 'params': {
1305 'skip_download': True,
1306 },
1307 },
1308 {
1309 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1310 'note': '256k DASH audio (format 141) via DASH manifest',
1311 'info_dict': {
1312 'id': 'a9LDPn-MO4I',
1313 'ext': 'm4a',
1314 'upload_date': '20121002',
1315 'uploader_id': '8KVIDEO',
1316 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1317 'description': '',
1318 'uploader': '8KVIDEO',
1319 'title': 'UHDTV TEST 8K VIDEO.mp4'
1320 },
1321 'params': {
1322 'youtube_include_dash_manifest': True,
1323 'format': '141',
1324 },
1325 'skip': 'format 141 not served anymore',
1326 },
1327 # DASH manifest with encrypted signature
1328 {
1329 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1330 'info_dict': {
1331 'id': 'IB3lcPjvWLA',
1332 'ext': 'm4a',
1333 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1334 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1335 'duration': 244,
1336 'uploader': 'AfrojackVEVO',
1337 'uploader_id': 'AfrojackVEVO',
1338 'upload_date': '20131011',
1339 'abr': 129.495,
1340 'like_count': int,
1341 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1342 'playable_in_embed': True,
1343 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1344 'view_count': int,
1345 'track': 'The Spark',
1346 'live_status': 'not_live',
1347 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1348 'channel': 'Afrojack',
1349 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1350 'tags': 'count:19',
1351 'availability': 'public',
1352 'categories': ['Music'],
1353 'age_limit': 0,
1354 'alt_title': 'The Spark',
1355 'channel_follower_count': int
1356 },
1357 'params': {
1358 'youtube_include_dash_manifest': True,
1359 'format': '141/bestaudio[ext=m4a]',
1360 },
1361 },
1362 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1363 {
1364 'note': 'Embed allowed age-gate video',
1365 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1366 'info_dict': {
1367 'id': 'HtVdAasjOgU',
1368 'ext': 'mp4',
1369 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1370 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1371 'duration': 142,
1372 'uploader': 'The Witcher',
1373 'uploader_id': 'WitcherGame',
1374 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1375 'upload_date': '20140605',
1376 'age_limit': 18,
1377 'categories': ['Gaming'],
1378 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1379 'availability': 'needs_auth',
1380 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1381 'like_count': int,
1382 'channel': 'The Witcher',
1383 'live_status': 'not_live',
1384 'tags': 'count:17',
1385 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1386 'playable_in_embed': True,
1387 'view_count': int,
1388 'channel_follower_count': int
1389 },
1390 },
1391 {
1392 'note': 'Age-gate video with embed allowed in public site',
1393 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1394 'info_dict': {
1395 'id': 'HsUATh_Nc2U',
1396 'ext': 'mp4',
1397 'title': 'Godzilla 2 (Official Video)',
1398 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1399 'upload_date': '20200408',
1400 'uploader_id': 'FlyingKitty900',
1401 'uploader': 'FlyingKitty',
1402 'age_limit': 18,
1403 'availability': 'needs_auth',
1404 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1405 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1406 'channel': 'FlyingKitty',
1407 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1408 'view_count': int,
1409 'categories': ['Entertainment'],
1410 'live_status': 'not_live',
1411 'tags': ['Flyingkitty', 'godzilla 2'],
1412 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1413 'like_count': int,
1414 'duration': 177,
1415 'playable_in_embed': True,
1416 'channel_follower_count': int
1417 },
1418 },
1419 {
1420 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1421 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1422 'info_dict': {
1423 'id': 'Tq92D6wQ1mg',
1424 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1425 'ext': 'mp4',
1426 'upload_date': '20191228',
1427 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1428 'uploader': 'Projekt Melody',
1429 'description': 'md5:17eccca93a786d51bc67646756894066',
1430 'age_limit': 18,
1431 'like_count': int,
1432 'availability': 'needs_auth',
1433 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1434 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1435 'view_count': int,
1436 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1437 'channel': 'Projekt Melody',
1438 'live_status': 'not_live',
1439 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1440 'playable_in_embed': True,
1441 'categories': ['Entertainment'],
1442 'duration': 106,
1443 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1444 'comment_count': int,
1445 'channel_follower_count': int
1446 },
1447 },
1448 {
1449 'note': 'Non-Agegated non-embeddable video',
1450 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1451 'info_dict': {
1452 'id': 'MeJVWBSsPAY',
1453 'ext': 'mp4',
1454 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1455 'uploader': 'Herr Lurik',
1456 'uploader_id': 'st3in234',
1457 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1458 'upload_date': '20130730',
1459 'track': 'Such mich find mich',
1460 'age_limit': 0,
1461 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1462 'like_count': int,
1463 'playable_in_embed': False,
1464 'creator': 'OOMPH!',
1465 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1466 'view_count': int,
1467 'alt_title': 'Such mich find mich',
1468 'duration': 210,
1469 'channel': 'Herr Lurik',
1470 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1471 'categories': ['Music'],
1472 'availability': 'public',
1473 'uploader_url': 'http://www.youtube.com/user/st3in234',
1474 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1475 'live_status': 'not_live',
1476 'artist': 'OOMPH!',
1477 'channel_follower_count': int
1478 },
1479 },
1480 {
1481 'note': 'Non-bypassable age-gated video',
1482 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1483 'only_matching': True,
1484 },
1485 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1486 # YouTube Red ad is not captured for creator
1487 {
1488 'url': '__2ABJjxzNo',
1489 'info_dict': {
1490 'id': '__2ABJjxzNo',
1491 'ext': 'mp4',
1492 'duration': 266,
1493 'upload_date': '20100430',
1494 'uploader_id': 'deadmau5',
1495 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1496 'creator': 'deadmau5',
1497 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1498 'uploader': 'deadmau5',
1499 'title': 'Deadmau5 - Some Chords (HD)',
1500 'alt_title': 'Some Chords',
1501 'availability': 'public',
1502 'tags': 'count:14',
1503 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1504 'view_count': int,
1505 'live_status': 'not_live',
1506 'channel': 'deadmau5',
1507 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1508 'like_count': int,
1509 'track': 'Some Chords',
1510 'artist': 'deadmau5',
1511 'playable_in_embed': True,
1512 'age_limit': 0,
1513 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1514 'categories': ['Music'],
1515 'album': 'Some Chords',
1516 'channel_follower_count': int
1517 },
1518 'expected_warnings': [
1519 'DASH manifest missing',
1520 ]
1521 },
1522 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1523 {
1524 'url': 'lqQg6PlCWgI',
1525 'info_dict': {
1526 'id': 'lqQg6PlCWgI',
1527 'ext': 'mp4',
1528 'duration': 6085,
1529 'upload_date': '20150827',
1530 'uploader_id': 'olympic',
1531 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1532 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1533 'uploader': 'Olympics',
1534 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1535 'like_count': int,
1536 'release_timestamp': 1343767800,
1537 'playable_in_embed': True,
1538 'categories': ['Sports'],
1539 'release_date': '20120731',
1540 'channel': 'Olympics',
1541 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1542 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1543 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1544 'age_limit': 0,
1545 'availability': 'public',
1546 'live_status': 'was_live',
1547 'view_count': int,
1548 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1549 'channel_follower_count': int
1550 },
1551 'params': {
1552 'skip_download': 'requires avconv',
1553 }
1554 },
1555 # Non-square pixels
1556 {
1557 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1558 'info_dict': {
1559 'id': '_b-2C3KPAM0',
1560 'ext': 'mp4',
1561 'stretched_ratio': 16 / 9.,
1562 'duration': 85,
1563 'upload_date': '20110310',
1564 'uploader_id': 'AllenMeow',
1565 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1566 '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',
1567 'uploader': '孫ᄋᄅ',
1568 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1569 'playable_in_embed': True,
1570 'channel': '孫ᄋᄅ',
1571 'age_limit': 0,
1572 'tags': 'count:11',
1573 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1574 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1575 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1576 'view_count': int,
1577 'categories': ['People & Blogs'],
1578 'like_count': int,
1579 'live_status': 'not_live',
1580 'availability': 'unlisted',
1581 'comment_count': int,
1582 'channel_follower_count': int
1583 },
1584 },
1585 # url_encoded_fmt_stream_map is empty string
1586 {
1587 'url': 'qEJwOuvDf7I',
1588 'info_dict': {
1589 'id': 'qEJwOuvDf7I',
1590 'ext': 'webm',
1591 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1592 'description': '',
1593 'upload_date': '20150404',
1594 'uploader_id': 'spbelect',
1595 'uploader': 'Наблюдатели Петербурга',
1596 },
1597 'params': {
1598 'skip_download': 'requires avconv',
1599 },
1600 'skip': 'This live event has ended.',
1601 },
1602 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1603 {
1604 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1605 'info_dict': {
1606 'id': 'FIl7x6_3R5Y',
1607 'ext': 'webm',
1608 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1609 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1610 'duration': 220,
1611 'upload_date': '20150625',
1612 'uploader_id': 'dorappi2000',
1613 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1614 'uploader': 'dorappi2000',
1615 'formats': 'mincount:31',
1616 },
1617 'skip': 'not actual anymore',
1618 },
1619 # DASH manifest with segment_list
1620 {
1621 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1622 'md5': '8ce563a1d667b599d21064e982ab9e31',
1623 'info_dict': {
1624 'id': 'CsmdDsKjzN8',
1625 'ext': 'mp4',
1626 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1627 'uploader': 'Airtek',
1628 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1629 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1630 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1631 },
1632 'params': {
1633 'youtube_include_dash_manifest': True,
1634 'format': '135', # bestvideo
1635 },
1636 'skip': 'This live event has ended.',
1637 },
1638 {
1639 # Multifeed videos (multiple cameras), URL can be of any Camera
1640 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
1641 'info_dict': {
1642 'id': 'zaPI8MvL8pg',
1643 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1644 'description': 'md5:563ccbc698b39298481ca3c571169519',
1645 },
1646 'playlist': [{
1647 'info_dict': {
1648 'id': 'j5yGuxZ8lLU',
1649 'ext': 'mp4',
1650 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
1651 'uploader': 'WiiLikeToPlay',
1652 'description': 'md5:563ccbc698b39298481ca3c571169519',
1653 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1654 'duration': 10120,
1655 'channel_follower_count': int,
1656 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1657 'availability': 'public',
1658 'playable_in_embed': True,
1659 'upload_date': '20131105',
1660 'uploader_id': 'WiiRikeToPray',
1661 'categories': ['Gaming'],
1662 'live_status': 'was_live',
1663 'tags': 'count:24',
1664 'release_timestamp': 1383701910,
1665 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1666 'comment_count': int,
1667 'age_limit': 0,
1668 'like_count': int,
1669 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1670 'channel': 'WiiLikeToPlay',
1671 'view_count': int,
1672 'release_date': '20131106',
1673 },
1674 }, {
1675 'info_dict': {
1676 'id': 'zaPI8MvL8pg',
1677 'ext': 'mp4',
1678 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
1679 'uploader_id': 'WiiRikeToPray',
1680 'availability': 'public',
1681 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1682 'channel': 'WiiLikeToPlay',
1683 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1684 'channel_follower_count': int,
1685 'description': 'md5:563ccbc698b39298481ca3c571169519',
1686 'duration': 10108,
1687 'age_limit': 0,
1688 'like_count': int,
1689 'tags': 'count:24',
1690 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1691 'uploader': 'WiiLikeToPlay',
1692 'release_timestamp': 1383701915,
1693 'comment_count': int,
1694 'upload_date': '20131105',
1695 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1696 'release_date': '20131106',
1697 'playable_in_embed': True,
1698 'live_status': 'was_live',
1699 'categories': ['Gaming'],
1700 'view_count': int,
1701 },
1702 }, {
1703 'info_dict': {
1704 'id': 'R7r3vfO7Hao',
1705 'ext': 'mp4',
1706 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1707 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1708 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1709 'like_count': int,
1710 'availability': 'public',
1711 'playable_in_embed': True,
1712 'upload_date': '20131105',
1713 'description': 'md5:563ccbc698b39298481ca3c571169519',
1714 'uploader_id': 'WiiRikeToPray',
1715 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1716 'channel_follower_count': int,
1717 'tags': 'count:24',
1718 'release_date': '20131106',
1719 'uploader': 'WiiLikeToPlay',
1720 'comment_count': int,
1721 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1722 'channel': 'WiiLikeToPlay',
1723 'categories': ['Gaming'],
1724 'release_timestamp': 1383701914,
1725 'live_status': 'was_live',
1726 'age_limit': 0,
1727 'duration': 10128,
1728 'view_count': int,
1729 },
1730 }],
1731 'params': {'skip_download': True},
1732 },
1733 {
1734 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1735 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1736 'info_dict': {
1737 'id': 'gVfLd0zydlo',
1738 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1739 },
1740 'playlist_count': 2,
1741 'skip': 'Not multifeed anymore',
1742 },
1743 {
1744 'url': 'https://vid.plus/FlRa-iH7PGw',
1745 'only_matching': True,
1746 },
1747 {
1748 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1749 'only_matching': True,
1750 },
1751 {
1752 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1753 # Also tests cut-off URL expansion in video description (see
1754 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1755 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1756 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1757 'info_dict': {
1758 'id': 'lsguqyKfVQg',
1759 'ext': 'mp4',
1760 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1761 'alt_title': 'Dark Walk',
1762 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1763 'duration': 133,
1764 'upload_date': '20151119',
1765 'uploader_id': 'IronSoulElf',
1766 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1767 'uploader': 'IronSoulElf',
1768 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1769 'track': 'Dark Walk',
1770 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1771 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1772 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1773 'categories': ['Film & Animation'],
1774 'view_count': int,
1775 'live_status': 'not_live',
1776 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1777 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1778 'tags': 'count:13',
1779 'availability': 'public',
1780 'channel': 'IronSoulElf',
1781 'playable_in_embed': True,
1782 'like_count': int,
1783 'age_limit': 0,
1784 'channel_follower_count': int
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 },
1790 {
1791 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1792 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1793 'only_matching': True,
1794 },
1795 {
1796 # Video with yt:stretch=17:0
1797 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1798 'info_dict': {
1799 'id': 'Q39EVAstoRM',
1800 'ext': 'mp4',
1801 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1802 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1803 'upload_date': '20151107',
1804 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1805 'uploader': 'CH GAMER DROID',
1806 },
1807 'params': {
1808 'skip_download': True,
1809 },
1810 'skip': 'This video does not exist.',
1811 },
1812 {
1813 # Video with incomplete 'yt:stretch=16:'
1814 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1815 'only_matching': True,
1816 },
1817 {
1818 # Video licensed under Creative Commons
1819 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1820 'info_dict': {
1821 'id': 'M4gD1WSo5mA',
1822 'ext': 'mp4',
1823 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1824 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1825 'duration': 721,
1826 'upload_date': '20150128',
1827 'uploader_id': 'BerkmanCenter',
1828 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1829 'uploader': 'The Berkman Klein Center for Internet & Society',
1830 'license': 'Creative Commons Attribution license (reuse allowed)',
1831 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1832 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1833 'like_count': int,
1834 'age_limit': 0,
1835 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1836 'channel': 'The Berkman Klein Center for Internet & Society',
1837 'availability': 'public',
1838 'view_count': int,
1839 'categories': ['Education'],
1840 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1841 'live_status': 'not_live',
1842 'playable_in_embed': True,
1843 'comment_count': int,
1844 'channel_follower_count': int,
1845 'chapters': list,
1846 },
1847 'params': {
1848 'skip_download': True,
1849 },
1850 },
1851 {
1852 # Channel-like uploader_url
1853 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1854 'info_dict': {
1855 'id': 'eQcmzGIKrzg',
1856 'ext': 'mp4',
1857 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1858 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1859 'duration': 4060,
1860 'upload_date': '20151120',
1861 'uploader': 'Bernie Sanders',
1862 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1863 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1864 'license': 'Creative Commons Attribution license (reuse allowed)',
1865 'playable_in_embed': True,
1866 'tags': 'count:12',
1867 'like_count': int,
1868 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1869 'age_limit': 0,
1870 'availability': 'public',
1871 'categories': ['News & Politics'],
1872 'channel': 'Bernie Sanders',
1873 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1874 'view_count': int,
1875 'live_status': 'not_live',
1876 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1877 'comment_count': int,
1878 'channel_follower_count': int,
1879 'chapters': list,
1880 },
1881 'params': {
1882 'skip_download': True,
1883 },
1884 },
1885 {
1886 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1887 'only_matching': True,
1888 },
1889 {
1890 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1891 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1892 'only_matching': True,
1893 },
1894 {
1895 # Rental video preview
1896 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1897 'info_dict': {
1898 'id': 'uGpuVWrhIzE',
1899 'ext': 'mp4',
1900 'title': 'Piku - Trailer',
1901 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1902 'upload_date': '20150811',
1903 'uploader': 'FlixMatrix',
1904 'uploader_id': 'FlixMatrixKaravan',
1905 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1906 'license': 'Standard YouTube License',
1907 },
1908 'params': {
1909 'skip_download': True,
1910 },
1911 'skip': 'This video is not available.',
1912 },
1913 {
1914 # YouTube Red video with episode data
1915 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1916 'info_dict': {
1917 'id': 'iqKdEhx-dD4',
1918 'ext': 'mp4',
1919 'title': 'Isolation - Mind Field (Ep 1)',
1920 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1921 'duration': 2085,
1922 'upload_date': '20170118',
1923 'uploader': 'Vsauce',
1924 'uploader_id': 'Vsauce',
1925 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1926 'series': 'Mind Field',
1927 'season_number': 1,
1928 'episode_number': 1,
1929 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1930 'tags': 'count:12',
1931 'view_count': int,
1932 'availability': 'public',
1933 'age_limit': 0,
1934 'channel': 'Vsauce',
1935 'episode': 'Episode 1',
1936 'categories': ['Entertainment'],
1937 'season': 'Season 1',
1938 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1939 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1940 'like_count': int,
1941 'playable_in_embed': True,
1942 'live_status': 'not_live',
1943 'channel_follower_count': int
1944 },
1945 'params': {
1946 'skip_download': True,
1947 },
1948 'expected_warnings': [
1949 'Skipping DASH manifest',
1950 ],
1951 },
1952 {
1953 # The following content has been identified by the YouTube community
1954 # as inappropriate or offensive to some audiences.
1955 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1956 'info_dict': {
1957 'id': '6SJNVb0GnPI',
1958 'ext': 'mp4',
1959 'title': 'Race Differences in Intelligence',
1960 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1961 'duration': 965,
1962 'upload_date': '20140124',
1963 'uploader': 'New Century Foundation',
1964 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1965 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1966 },
1967 'params': {
1968 'skip_download': True,
1969 },
1970 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1971 },
1972 {
1973 # itag 212
1974 'url': '1t24XAntNCY',
1975 'only_matching': True,
1976 },
1977 {
1978 # geo restricted to JP
1979 'url': 'sJL6WA-aGkQ',
1980 'only_matching': True,
1981 },
1982 {
1983 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1984 'only_matching': True,
1985 },
1986 {
1987 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1988 'only_matching': True,
1989 },
1990 {
1991 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1992 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1993 'only_matching': True,
1994 },
1995 {
1996 # DRM protected
1997 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1998 'only_matching': True,
1999 },
2000 {
2001 # Video with unsupported adaptive stream type formats
2002 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2003 'info_dict': {
2004 'id': 'Z4Vy8R84T1U',
2005 'ext': 'mp4',
2006 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2007 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2008 'duration': 433,
2009 'upload_date': '20130923',
2010 'uploader': 'Amelia Putri Harwita',
2011 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
2012 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
2013 'formats': 'maxcount:10',
2014 },
2015 'params': {
2016 'skip_download': True,
2017 'youtube_include_dash_manifest': False,
2018 },
2019 'skip': 'not actual anymore',
2020 },
2021 {
2022 # Youtube Music Auto-generated description
2023 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2024 'info_dict': {
2025 'id': 'MgNrAu2pzNs',
2026 'ext': 'mp4',
2027 'title': 'Voyeur Girl',
2028 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2029 'upload_date': '20190312',
2030 'uploader': 'Stephen - Topic',
2031 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2032 'artist': 'Stephen',
2033 'track': 'Voyeur Girl',
2034 'album': 'it\'s too much love to know my dear',
2035 'release_date': '20190313',
2036 'release_year': 2019,
2037 'alt_title': 'Voyeur Girl',
2038 'view_count': int,
2039 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2040 'playable_in_embed': True,
2041 'like_count': int,
2042 'categories': ['Music'],
2043 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2044 'channel': 'Stephen',
2045 'availability': 'public',
2046 'creator': 'Stephen',
2047 'duration': 169,
2048 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2049 'age_limit': 0,
2050 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2051 'tags': 'count:11',
2052 'live_status': 'not_live',
2053 'channel_follower_count': int
2054 },
2055 'params': {
2056 'skip_download': True,
2057 },
2058 },
2059 {
2060 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2061 'only_matching': True,
2062 },
2063 {
2064 # invalid -> valid video id redirection
2065 'url': 'DJztXj2GPfl',
2066 'info_dict': {
2067 'id': 'DJztXj2GPfk',
2068 'ext': 'mp4',
2069 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2070 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2071 'upload_date': '20090125',
2072 'uploader': 'Prochorowka',
2073 'uploader_id': 'Prochorowka',
2074 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
2075 'artist': 'Panjabi MC',
2076 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2077 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2078 },
2079 'params': {
2080 'skip_download': True,
2081 },
2082 'skip': 'Video unavailable',
2083 },
2084 {
2085 # empty description results in an empty string
2086 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2087 'info_dict': {
2088 'id': 'x41yOUIvK2k',
2089 'ext': 'mp4',
2090 'title': 'IMG 3456',
2091 'description': '',
2092 'upload_date': '20170613',
2093 'uploader_id': 'ElevageOrVert',
2094 'uploader': 'ElevageOrVert',
2095 'view_count': int,
2096 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2097 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2098 'like_count': int,
2099 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2100 'tags': [],
2101 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2102 'availability': 'public',
2103 'age_limit': 0,
2104 'categories': ['Pets & Animals'],
2105 'duration': 7,
2106 'playable_in_embed': True,
2107 'live_status': 'not_live',
2108 'channel': 'ElevageOrVert',
2109 'channel_follower_count': int
2110 },
2111 'params': {
2112 'skip_download': True,
2113 },
2114 },
2115 {
2116 # with '};' inside yt initial data (see [1])
2117 # see [2] for an example with '};' inside ytInitialPlayerResponse
2118 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2119 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
2120 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2121 'info_dict': {
2122 'id': 'CHqg6qOn4no',
2123 'ext': 'mp4',
2124 'title': 'Part 77 Sort a list of simple types in c#',
2125 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2126 'upload_date': '20130831',
2127 'uploader_id': 'kudvenkat',
2128 'uploader': 'kudvenkat',
2129 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2130 'like_count': int,
2131 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2132 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2133 'live_status': 'not_live',
2134 'categories': ['Education'],
2135 'availability': 'public',
2136 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2137 'tags': 'count:12',
2138 'playable_in_embed': True,
2139 'age_limit': 0,
2140 'view_count': int,
2141 'duration': 522,
2142 'channel': 'kudvenkat',
2143 'comment_count': int,
2144 'channel_follower_count': int,
2145 'chapters': list,
2146 },
2147 'params': {
2148 'skip_download': True,
2149 },
2150 },
2151 {
2152 # another example of '};' in ytInitialData
2153 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2154 'only_matching': True,
2155 },
2156 {
2157 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2158 'only_matching': True,
2159 },
2160 {
2161 # https://github.com/ytdl-org/youtube-dl/pull/28094
2162 'url': 'OtqTfy26tG0',
2163 'info_dict': {
2164 'id': 'OtqTfy26tG0',
2165 'ext': 'mp4',
2166 'title': 'Burn Out',
2167 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2168 'upload_date': '20141120',
2169 'uploader': 'The Cinematic Orchestra - Topic',
2170 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2171 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2172 'artist': 'The Cinematic Orchestra',
2173 'track': 'Burn Out',
2174 'album': 'Every Day',
2175 'like_count': int,
2176 'live_status': 'not_live',
2177 'alt_title': 'Burn Out',
2178 'duration': 614,
2179 'age_limit': 0,
2180 'view_count': int,
2181 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2182 'creator': 'The Cinematic Orchestra',
2183 'channel': 'The Cinematic Orchestra',
2184 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2185 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2186 'availability': 'public',
2187 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2188 'categories': ['Music'],
2189 'playable_in_embed': True,
2190 'channel_follower_count': int
2191 },
2192 'params': {
2193 'skip_download': True,
2194 },
2195 },
2196 {
2197 # controversial video, only works with bpctr when authenticated with cookies
2198 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2199 'only_matching': True,
2200 },
2201 {
2202 # controversial video, requires bpctr/contentCheckOk
2203 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2204 'info_dict': {
2205 'id': 'SZJvDhaSDnc',
2206 'ext': 'mp4',
2207 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2208 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2209 'uploader': 'CBS Mornings',
2210 'uploader_id': 'CBSThisMorning',
2211 'upload_date': '20140716',
2212 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2213 'duration': 170,
2214 'categories': ['News & Politics'],
2215 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2216 'view_count': int,
2217 'channel': 'CBS Mornings',
2218 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2219 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2220 'age_limit': 18,
2221 'availability': 'needs_auth',
2222 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2223 'like_count': int,
2224 'live_status': 'not_live',
2225 'playable_in_embed': True,
2226 'channel_follower_count': int
2227 }
2228 },
2229 {
2230 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2231 'url': 'cBvYw8_A0vQ',
2232 'info_dict': {
2233 'id': 'cBvYw8_A0vQ',
2234 'ext': 'mp4',
2235 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2236 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2237 'upload_date': '20201120',
2238 'uploader': 'Walk around Japan',
2239 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2240 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2241 'duration': 1456,
2242 'categories': ['Travel & Events'],
2243 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2244 'view_count': int,
2245 'channel': 'Walk around Japan',
2246 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2247 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2248 'age_limit': 0,
2249 'availability': 'public',
2250 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2251 'live_status': 'not_live',
2252 'playable_in_embed': True,
2253 'channel_follower_count': int
2254 },
2255 'params': {
2256 'skip_download': True,
2257 },
2258 }, {
2259 # Has multiple audio streams
2260 'url': 'WaOKSUlf4TM',
2261 'only_matching': True
2262 }, {
2263 # Requires Premium: has format 141 when requested using YTM url
2264 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2265 'only_matching': True
2266 }, {
2267 # multiple subtitles with same lang_code
2268 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2269 'only_matching': True,
2270 }, {
2271 # Force use android client fallback
2272 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2273 'info_dict': {
2274 'id': 'YOelRv7fMxY',
2275 'title': 'DIGGING A SECRET TUNNEL Part 1',
2276 'ext': '3gp',
2277 'upload_date': '20210624',
2278 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2279 'uploader': 'colinfurze',
2280 'uploader_id': 'colinfurze',
2281 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2282 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2283 'duration': 596,
2284 'categories': ['Entertainment'],
2285 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2286 'view_count': int,
2287 'channel': 'colinfurze',
2288 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2289 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2290 'age_limit': 0,
2291 'availability': 'public',
2292 'like_count': int,
2293 'live_status': 'not_live',
2294 'playable_in_embed': True,
2295 'channel_follower_count': int,
2296 'chapters': list,
2297 },
2298 'params': {
2299 'format': '17', # 3gp format available on android
2300 'extractor_args': {'youtube': {'player_client': ['android']}},
2301 },
2302 },
2303 {
2304 # Skip download of additional client configs (remix client config in this case)
2305 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2306 'only_matching': True,
2307 'params': {
2308 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2309 },
2310 }, {
2311 # shorts
2312 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2313 'only_matching': True,
2314 }, {
2315 'note': 'Storyboards',
2316 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2317 'info_dict': {
2318 'id': '5KLPxDtMqe8',
2319 'ext': 'mhtml',
2320 'format_id': 'sb0',
2321 'title': 'Your Brain is Plastic',
2322 'uploader_id': 'scishow',
2323 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2324 'upload_date': '20140324',
2325 'uploader': 'SciShow',
2326 'like_count': int,
2327 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2328 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2329 'view_count': int,
2330 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2331 'playable_in_embed': True,
2332 'tags': 'count:12',
2333 'uploader_url': 'http://www.youtube.com/user/scishow',
2334 'availability': 'public',
2335 'channel': 'SciShow',
2336 'live_status': 'not_live',
2337 'duration': 248,
2338 'categories': ['Education'],
2339 'age_limit': 0,
2340 'channel_follower_count': int,
2341 'chapters': list,
2342 }, 'params': {'format': 'mhtml', 'skip_download': True}
2343 }, {
2344 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2345 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2346 'info_dict': {
2347 'id': '2NUZ8W2llS4',
2348 'ext': 'mp4',
2349 'title': 'The NP that test your phone performance 🙂',
2350 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2351 'uploader': 'Leon Nguyen',
2352 'uploader_id': 'VNSXIII',
2353 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2354 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2355 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2356 'duration': 21,
2357 'view_count': int,
2358 'age_limit': 0,
2359 'categories': ['Gaming'],
2360 'tags': 'count:23',
2361 'playable_in_embed': True,
2362 'live_status': 'not_live',
2363 'upload_date': '20220103',
2364 'like_count': int,
2365 'availability': 'public',
2366 'channel': 'Leon Nguyen',
2367 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2368 'comment_count': int,
2369 'channel_follower_count': int
2370 }
2371 }, {
2372 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2373 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2374 'info_dict': {
2375 'id': '2NUZ8W2llS4',
2376 'ext': 'mp4',
2377 'title': 'The NP that test your phone performance 🙂',
2378 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2379 'uploader': 'Leon Nguyen',
2380 'uploader_id': 'VNSXIII',
2381 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2382 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2383 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2384 'duration': 21,
2385 'view_count': int,
2386 'age_limit': 0,
2387 'categories': ['Gaming'],
2388 'tags': 'count:23',
2389 'playable_in_embed': True,
2390 'live_status': 'not_live',
2391 'upload_date': '20220102',
2392 'like_count': int,
2393 'availability': 'public',
2394 'channel': 'Leon Nguyen',
2395 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2396 'comment_count': int,
2397 'channel_follower_count': int
2398 },
2399 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2400 }, {
2401 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2402 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2403 'info_dict': {
2404 'id': 'mzZzzBU6lrM',
2405 'ext': 'mp4',
2406 'title': 'I Met GeorgeNotFound In Real Life...',
2407 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2408 'uploader': 'Quackity',
2409 'uploader_id': 'QuackityHQ',
2410 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2411 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2412 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2413 'duration': 955,
2414 'view_count': int,
2415 'age_limit': 0,
2416 'categories': ['Entertainment'],
2417 'tags': 'count:26',
2418 'playable_in_embed': True,
2419 'live_status': 'not_live',
2420 'release_timestamp': 1641172509,
2421 'release_date': '20220103',
2422 'upload_date': '20220103',
2423 'like_count': int,
2424 'availability': 'public',
2425 'channel': 'Quackity',
2426 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2427 'channel_follower_count': int
2428 }
2429 },
2430 { # continuous livestream. Microformat upload date should be preferred.
2431 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2432 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2433 'info_dict': {
2434 'id': 'kgx4WGK0oNU',
2435 '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}',
2436 'ext': 'mp4',
2437 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2438 'availability': 'public',
2439 'age_limit': 0,
2440 'release_timestamp': 1637975704,
2441 'upload_date': '20210619',
2442 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2443 'live_status': 'is_live',
2444 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2445 'uploader': '阿鲍Abao',
2446 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2447 'channel': 'Abao in Tokyo',
2448 'channel_follower_count': int,
2449 'release_date': '20211127',
2450 'tags': 'count:39',
2451 'categories': ['People & Blogs'],
2452 'like_count': int,
2453 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2454 'view_count': int,
2455 'playable_in_embed': True,
2456 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2457 'concurrent_view_count': int,
2458 },
2459 'params': {'skip_download': True}
2460 }, {
2461 # Story. Requires specific player params to work.
2462 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2463 'info_dict': {
2464 'id': 'vv8qTUWmulI',
2465 'ext': 'mp4',
2466 'availability': 'unlisted',
2467 'view_count': int,
2468 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2469 'upload_date': '20220526',
2470 'categories': ['Education'],
2471 'title': 'Story',
2472 'channel': 'IT\'S HISTORY',
2473 'description': '',
2474 'uploader_id': 'BlastfromthePast',
2475 'duration': 12,
2476 'uploader': 'IT\'S HISTORY',
2477 'playable_in_embed': True,
2478 'age_limit': 0,
2479 'live_status': 'not_live',
2480 'tags': [],
2481 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2482 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2483 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2484 },
2485 'skip': 'stories get removed after some period of time',
2486 }, {
2487 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2488 'info_dict': {
2489 'id': 'tjjjtzRLHvA',
2490 'ext': 'mp4',
2491 'title': 'ハッシュタグ無し };if window.ytcsi',
2492 'upload_date': '20220323',
2493 'like_count': int,
2494 'availability': 'unlisted',
2495 'channel': 'nao20010128nao',
2496 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2497 'age_limit': 0,
2498 'uploader': 'nao20010128nao',
2499 'uploader_id': 'nao20010128nao',
2500 'categories': ['Music'],
2501 'view_count': int,
2502 'description': '',
2503 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2504 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2505 'live_status': 'not_live',
2506 'playable_in_embed': True,
2507 'channel_follower_count': int,
2508 'duration': 6,
2509 'tags': [],
2510 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2511 }
2512 }, {
2513 # Prefer primary title+description language metadata by default
2514 # Do not prefer translated description if primary is empty
2515 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2516 'info_dict': {
2517 'id': 'el3E4MbxRqQ',
2518 'ext': 'mp4',
2519 'title': 'dlp test video 2 - primary sv no desc',
2520 'description': '',
2521 'channel': 'cole-dlp-test-acc',
2522 'tags': [],
2523 'view_count': int,
2524 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2525 'like_count': int,
2526 'playable_in_embed': True,
2527 'availability': 'unlisted',
2528 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2529 'age_limit': 0,
2530 'duration': 5,
2531 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2532 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2533 'live_status': 'not_live',
2534 'upload_date': '20220908',
2535 'categories': ['People & Blogs'],
2536 'uploader': 'cole-dlp-test-acc',
2537 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2538 },
2539 'params': {'skip_download': True}
2540 }, {
2541 # Extractor argument: prefer translated title+description
2542 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2543 'info_dict': {
2544 'id': 'gHKT4uU8Zng',
2545 'ext': 'mp4',
2546 'channel': 'cole-dlp-test-acc',
2547 'tags': [],
2548 'duration': 5,
2549 'live_status': 'not_live',
2550 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2551 'upload_date': '20220728',
2552 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2553 'view_count': int,
2554 'categories': ['People & Blogs'],
2555 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2556 'title': 'dlp test video title translated (fr)',
2557 'availability': 'public',
2558 'uploader': 'cole-dlp-test-acc',
2559 'age_limit': 0,
2560 'description': 'dlp test video description translated (fr)',
2561 'playable_in_embed': True,
2562 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2563 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2564 },
2565 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2566 'expected_warnings': [r'Preferring "fr" translated fields'],
2567 }, {
2568 'note': '6 channel audio',
2569 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2570 'only_matching': True,
2571 }, {
2572 'note': 'Multiple HLS formats with same itag',
2573 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2574 'info_dict': {
2575 'id': 'kX3nB4PpJko',
2576 'ext': 'mp4',
2577 'categories': ['Entertainment'],
2578 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
2579 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
2580 'live_status': 'not_live',
2581 'duration': 937,
2582 'channel_follower_count': int,
2583 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2584 'title': 'Last To Take Hand Off Jet, Keeps It!',
2585 'channel': 'MrBeast',
2586 'playable_in_embed': True,
2587 'view_count': int,
2588 'upload_date': '20221112',
2589 'uploader': 'MrBeast',
2590 'uploader_id': 'MrBeast6000',
2591 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2592 'age_limit': 0,
2593 'availability': 'public',
2594 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2595 'like_count': int,
2596 'tags': [],
2597 },
2598 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
2599 }, {
2600 'note': 'Audio formats with Dynamic Range Compression',
2601 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2602 'info_dict': {
2603 'id': 'Tq92D6wQ1mg',
2604 'ext': 'weba',
2605 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2606 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2607 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2608 'channel_follower_count': int,
2609 'description': 'md5:17eccca93a786d51bc67646756894066',
2610 'upload_date': '20191228',
2611 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2612 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2613 'playable_in_embed': True,
2614 'like_count': int,
2615 'categories': ['Entertainment'],
2616 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2617 'age_limit': 18,
2618 'channel': 'Projekt Melody',
2619 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2620 'view_count': int,
2621 'availability': 'needs_auth',
2622 'comment_count': int,
2623 'live_status': 'not_live',
2624 'uploader': 'Projekt Melody',
2625 'duration': 106,
2626 },
2627 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
2628 },
2629 {
2630 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2631 'info_dict': {
2632 'id': 'qVv6vCqciTM',
2633 'ext': 'mp4',
2634 'age_limit': 0,
2635 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2636 'comment_count': int,
2637 'chapters': 'count:13',
2638 'upload_date': '20221223',
2639 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2640 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2641 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2642 'like_count': int,
2643 'release_date': '20221223',
2644 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2645 '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】',
2646 'view_count': int,
2647 'playable_in_embed': True,
2648 'duration': 4438,
2649 'availability': 'public',
2650 'channel_follower_count': int,
2651 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2652 'categories': ['Entertainment'],
2653 'live_status': 'was_live',
2654 'release_timestamp': 1671793345,
2655 'channel': 'さなちゃんねる',
2656 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2657 'uploader': 'さなちゃんねる',
2658 },
2659 },
2660 ]
2661
2662 _WEBPAGE_TESTS = [
2663 # YouTube <object> embed
2664 {
2665 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2666 'md5': '873c81d308b979f0e23ee7e620b312a3',
2667 'info_dict': {
2668 'id': 'msN87y-iEx0',
2669 'ext': 'mp4',
2670 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2671 'upload_date': '20080526',
2672 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2673 'uploader': 'Christopher Sykes',
2674 'uploader_id': 'ChristopherJSykes',
2675 'age_limit': 0,
2676 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2677 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2678 'playable_in_embed': True,
2679 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2680 'like_count': int,
2681 'comment_count': int,
2682 'channel': 'Christopher Sykes',
2683 'live_status': 'not_live',
2684 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2685 'availability': 'public',
2686 'duration': 195,
2687 'view_count': int,
2688 'categories': ['Science & Technology'],
2689 'channel_follower_count': int,
2690 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2691 },
2692 'params': {
2693 'skip_download': True,
2694 }
2695 },
2696 ]
2697
2698 @classmethod
2699 def suitable(cls, url):
2700 from ..utils import parse_qs
2701
2702 qs = parse_qs(url)
2703 if qs.get('list', [None])[0]:
2704 return False
2705 return super().suitable(url)
2706
2707 def __init__(self, *args, **kwargs):
2708 super().__init__(*args, **kwargs)
2709 self._code_cache = {}
2710 self._player_cache = {}
2711
2712 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
2713 lock = threading.Lock()
2714 start_time = time.time()
2715 formats = [f for f in formats if f.get('is_from_start')]
2716
2717 def refetch_manifest(format_id, delay):
2718 nonlocal formats, start_time, is_live
2719 if time.time() <= start_time + delay:
2720 return
2721
2722 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2723 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
2724 microformats = traverse_obj(
2725 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2726 expected_type=dict)
2727 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2728 is_live = live_status == 'is_live'
2729 start_time = time.time()
2730
2731 def mpd_feed(format_id, delay):
2732 """
2733 @returns (manifest_url, manifest_stream_number, is_live) or None
2734 """
2735 for retry in self.RetryManager(fatal=False):
2736 with lock:
2737 refetch_manifest(format_id, delay)
2738
2739 f = next((f for f in formats if f['format_id'] == format_id), None)
2740 if not f:
2741 if not is_live:
2742 retry.error = f'{video_id}: Video is no longer live'
2743 else:
2744 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2745 continue
2746 return f['manifest_url'], f['manifest_stream_number'], is_live
2747 return None
2748
2749 for f in formats:
2750 f['is_live'] = is_live
2751 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2752 live_start_time, mpd_feed, not is_live and f.copy())
2753 if is_live:
2754 f['fragments'] = gen
2755 f['protocol'] = 'http_dash_segments_generator'
2756 else:
2757 f['fragments'] = LazyList(gen({}))
2758 del f['is_from_start']
2759
2760 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
2761 FETCH_SPAN, MAX_DURATION = 5, 432000
2762
2763 mpd_url, stream_number, is_live = None, None, True
2764
2765 begin_index = 0
2766 download_start_time = ctx.get('start') or time.time()
2767
2768 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2769 if lack_early_segments:
2770 self.report_warning(bug_reports_message(
2771 'Starting download from the last 120 hours of the live stream since '
2772 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2773 lack_early_segments = True
2774
2775 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2776 fragments, fragment_base_url = None, None
2777
2778 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2779 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2780 # Obtain from MPD's maximum seq value
2781 old_mpd_url = mpd_url
2782 last_error = ctx.pop('last_error', None)
2783 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2784 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2785 or (mpd_url, stream_number, False))
2786 if not refresh_sequence:
2787 if expire_fast and not is_live:
2788 return False, last_seq
2789 elif old_mpd_url == mpd_url:
2790 return True, last_seq
2791 if manifestless_orig_fmt:
2792 fmt_info = manifestless_orig_fmt
2793 else:
2794 try:
2795 fmts, _ = self._extract_mpd_formats_and_subtitles(
2796 mpd_url, None, note=False, errnote=False, fatal=False)
2797 except ExtractorError:
2798 fmts = None
2799 if not fmts:
2800 no_fragment_score += 2
2801 return False, last_seq
2802 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2803 fragments = fmt_info['fragments']
2804 fragment_base_url = fmt_info['fragment_base_url']
2805 assert fragment_base_url
2806
2807 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2808 return True, _last_seq
2809
2810 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
2811 while is_live:
2812 fetch_time = time.time()
2813 if no_fragment_score > 30:
2814 return
2815 if last_segment_url:
2816 # Obtain from "X-Head-Seqnum" header value from each segment
2817 try:
2818 urlh = self._request_webpage(
2819 last_segment_url, None, note=False, errnote=False, fatal=False)
2820 except ExtractorError:
2821 urlh = None
2822 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2823 if last_seq is None:
2824 no_fragment_score += 2
2825 last_segment_url = None
2826 continue
2827 else:
2828 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2829 no_fragment_score += 2
2830 if not should_continue:
2831 continue
2832
2833 if known_idx > last_seq:
2834 last_segment_url = None
2835 continue
2836
2837 last_seq += 1
2838
2839 if begin_index < 0 and known_idx < 0:
2840 # skip from the start when it's negative value
2841 known_idx = last_seq + begin_index
2842 if lack_early_segments:
2843 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2844 try:
2845 for idx in range(known_idx, last_seq):
2846 # do not update sequence here or you'll get skipped some part of it
2847 should_continue, _ = _extract_sequence_from_mpd(False, False)
2848 if not should_continue:
2849 known_idx = idx - 1
2850 raise ExtractorError('breaking out of outer loop')
2851 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2852 yield {
2853 'url': last_segment_url,
2854 'fragment_count': last_seq,
2855 }
2856 if known_idx == last_seq:
2857 no_fragment_score += 5
2858 else:
2859 no_fragment_score = 0
2860 known_idx = last_seq
2861 except ExtractorError:
2862 continue
2863
2864 if manifestless_orig_fmt:
2865 # Stop at the first iteration if running for post-live manifestless;
2866 # fragment count no longer increase since it starts
2867 break
2868
2869 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2870
2871 def _extract_player_url(self, *ytcfgs, webpage=None):
2872 player_url = traverse_obj(
2873 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2874 get_all=False, expected_type=str)
2875 if not player_url:
2876 return
2877 return urljoin('https://www.youtube.com', player_url)
2878
2879 def _download_player_url(self, video_id, fatal=False):
2880 res = self._download_webpage(
2881 'https://www.youtube.com/iframe_api',
2882 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2883 if res:
2884 player_version = self._search_regex(
2885 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2886 if player_version:
2887 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2888
2889 def _signature_cache_id(self, example_sig):
2890 """ Return a string representation of a signature """
2891 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2892
2893 @classmethod
2894 def _extract_player_info(cls, player_url):
2895 for player_re in cls._PLAYER_INFO_RE:
2896 id_m = re.search(player_re, player_url)
2897 if id_m:
2898 break
2899 else:
2900 raise ExtractorError('Cannot identify player %r' % player_url)
2901 return id_m.group('id')
2902
2903 def _load_player(self, video_id, player_url, fatal=True):
2904 player_id = self._extract_player_info(player_url)
2905 if player_id not in self._code_cache:
2906 code = self._download_webpage(
2907 player_url, video_id, fatal=fatal,
2908 note='Downloading player ' + player_id,
2909 errnote='Download of %s failed' % player_url)
2910 if code:
2911 self._code_cache[player_id] = code
2912 return self._code_cache.get(player_id)
2913
2914 def _extract_signature_function(self, video_id, player_url, example_sig):
2915 player_id = self._extract_player_info(player_url)
2916
2917 # Read from filesystem cache
2918 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2919 assert os.path.basename(func_id) == func_id
2920
2921 self.write_debug(f'Extracting signature function {func_id}')
2922 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2923
2924 if not cache_spec:
2925 code = self._load_player(video_id, player_url)
2926 if code:
2927 res = self._parse_sig_js(code)
2928 test_string = ''.join(map(chr, range(len(example_sig))))
2929 cache_spec = [ord(c) for c in res(test_string)]
2930 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2931
2932 return lambda s: ''.join(s[i] for i in cache_spec)
2933
2934 def _print_sig_code(self, func, example_sig):
2935 if not self.get_param('youtube_print_sig_code'):
2936 return
2937
2938 def gen_sig_code(idxs):
2939 def _genslice(start, end, step):
2940 starts = '' if start == 0 else str(start)
2941 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2942 steps = '' if step == 1 else (':%d' % step)
2943 return f's[{starts}{ends}{steps}]'
2944
2945 step = None
2946 # Quelch pyflakes warnings - start will be set when step is set
2947 start = '(Never used)'
2948 for i, prev in zip(idxs[1:], idxs[:-1]):
2949 if step is not None:
2950 if i - prev == step:
2951 continue
2952 yield _genslice(start, prev, step)
2953 step = None
2954 continue
2955 if i - prev in [-1, 1]:
2956 step = i - prev
2957 start = prev
2958 continue
2959 else:
2960 yield 's[%d]' % prev
2961 if step is None:
2962 yield 's[%d]' % i
2963 else:
2964 yield _genslice(start, i, step)
2965
2966 test_string = ''.join(map(chr, range(len(example_sig))))
2967 cache_res = func(test_string)
2968 cache_spec = [ord(c) for c in cache_res]
2969 expr_code = ' + '.join(gen_sig_code(cache_spec))
2970 signature_id_tuple = '(%s)' % (
2971 ', '.join(str(len(p)) for p in example_sig.split('.')))
2972 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2973 ' return %s\n') % (signature_id_tuple, expr_code)
2974 self.to_screen('Extracted signature function:\n' + code)
2975
2976 def _parse_sig_js(self, jscode):
2977 funcname = self._search_regex(
2978 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2979 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2980 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2981 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2982 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}\(a,\d+\)',
2983 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\(\s*""\s*\)',
2984 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2985 # Obsolete patterns
2986 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2987 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2988 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2989 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2990 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2991 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2992 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2993 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2994 jscode, 'Initial JS player signature function name', group='sig')
2995
2996 jsi = JSInterpreter(jscode)
2997 initial_function = jsi.extract_function(funcname)
2998 return lambda s: initial_function([s])
2999
3000 def _cached(self, func, *cache_id):
3001 def inner(*args, **kwargs):
3002 if cache_id not in self._player_cache:
3003 try:
3004 self._player_cache[cache_id] = func(*args, **kwargs)
3005 except ExtractorError as e:
3006 self._player_cache[cache_id] = e
3007 except Exception as e:
3008 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3009
3010 ret = self._player_cache[cache_id]
3011 if isinstance(ret, Exception):
3012 raise ret
3013 return ret
3014 return inner
3015
3016 def _decrypt_signature(self, s, video_id, player_url):
3017 """Turn the encrypted s field into a working signature"""
3018 extract_sig = self._cached(
3019 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3020 func = extract_sig(video_id, player_url, s)
3021 self._print_sig_code(func, s)
3022 return func(s)
3023
3024 def _decrypt_nsig(self, s, video_id, player_url):
3025 """Turn the encrypted n field into a working signature"""
3026 if player_url is None:
3027 raise ExtractorError('Cannot decrypt nsig without player_url')
3028 player_url = urljoin('https://www.youtube.com', player_url)
3029
3030 try:
3031 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3032 except ExtractorError as e:
3033 raise ExtractorError('Unable to extract nsig function code', cause=e)
3034 if self.get_param('youtube_print_sig_code'):
3035 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
3036
3037 try:
3038 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3039 ret = extract_nsig(jsi, func_code)(s)
3040 except JSInterpreter.Exception as e:
3041 try:
3042 jsi = PhantomJSwrapper(self, timeout=5000)
3043 except ExtractorError:
3044 raise e
3045 self.report_warning(
3046 f'Native nsig extraction failed: Trying with PhantomJS\n'
3047 f' n = {s} ; player = {player_url}', video_id)
3048 self.write_debug(e, only_once=True)
3049
3050 args, func_body = func_code
3051 ret = jsi.execute(
3052 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3053 video_id=video_id, note='Executing signature code').strip()
3054
3055 self.write_debug(f'Decrypted nsig {s} => {ret}')
3056 return ret
3057
3058 def _extract_n_function_name(self, jscode):
3059 funcname, idx = self._search_regex(
3060 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3061 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3062 if not idx:
3063 return funcname
3064
3065 return json.loads(js_to_json(self._search_regex(
3066 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3067 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3068
3069 def _extract_n_function_code(self, video_id, player_url):
3070 player_id = self._extract_player_info(player_url)
3071 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
3072 jscode = func_code or self._load_player(video_id, player_url)
3073 jsi = JSInterpreter(jscode)
3074
3075 if func_code:
3076 return jsi, player_id, func_code
3077
3078 func_name = self._extract_n_function_name(jscode)
3079
3080 # For redundancy
3081 func_code = self._search_regex(
3082 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3083 # NB: The end of the regex is intentionally kept strict
3084 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3085 jscode, 'nsig function', group=('var', 'code'), default=None)
3086 if func_code:
3087 func_code = ([func_code[0]], func_code[1])
3088 else:
3089 self.write_debug('Extracting nsig function with jsinterp')
3090 func_code = jsi.extract_function_code(func_name)
3091
3092 self.cache.store('youtube-nsig', player_id, func_code)
3093 return jsi, player_id, func_code
3094
3095 def _extract_n_function_from_code(self, jsi, func_code):
3096 func = jsi.extract_function_from_code(*func_code)
3097
3098 def extract_nsig(s):
3099 try:
3100 ret = func([s])
3101 except JSInterpreter.Exception:
3102 raise
3103 except Exception as e:
3104 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3105
3106 if ret.startswith('enhanced_except_'):
3107 raise JSInterpreter.Exception('Signature function returned an exception')
3108 return ret
3109
3110 return extract_nsig
3111
3112 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3113 """
3114 Extract signatureTimestamp (sts)
3115 Required to tell API what sig/player version is in use.
3116 """
3117 sts = None
3118 if isinstance(ytcfg, dict):
3119 sts = int_or_none(ytcfg.get('STS'))
3120
3121 if not sts:
3122 # Attempt to extract from player
3123 if player_url is None:
3124 error_msg = 'Cannot extract signature timestamp without player_url.'
3125 if fatal:
3126 raise ExtractorError(error_msg)
3127 self.report_warning(error_msg)
3128 return
3129 code = self._load_player(video_id, player_url, fatal=fatal)
3130 if code:
3131 sts = int_or_none(self._search_regex(
3132 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3133 'JS player signature timestamp', group='sts', fatal=fatal))
3134 return sts
3135
3136 def _mark_watched(self, video_id, player_responses):
3137 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3138 label = 'fully ' if is_full else ''
3139 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3140 expected_type=url_or_none)
3141 if not url:
3142 self.report_warning(f'Unable to mark {label}watched')
3143 return
3144 parsed_url = urllib.parse.urlparse(url)
3145 qs = urllib.parse.parse_qs(parsed_url.query)
3146
3147 # cpn generation algorithm is reverse engineered from base.js.
3148 # In fact it works even with dummy cpn.
3149 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3150 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3151
3152 # # more consistent results setting it to right before the end
3153 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3154
3155 qs.update({
3156 'ver': ['2'],
3157 'cpn': [cpn],
3158 'cmt': video_length,
3159 'el': 'detailpage', # otherwise defaults to "shorts"
3160 })
3161
3162 if is_full:
3163 # these seem to mark watchtime "history" in the real world
3164 # they're required, so send in a single value
3165 qs.update({
3166 'st': 0,
3167 'et': video_length,
3168 })
3169
3170 url = urllib.parse.urlunparse(
3171 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
3172
3173 self._download_webpage(
3174 url, video_id, f'Marking {label}watched',
3175 'Unable to mark watched', fatal=False)
3176
3177 @classmethod
3178 def _extract_from_webpage(cls, url, webpage):
3179 # Invidious Instances
3180 # https://github.com/yt-dlp/yt-dlp/issues/195
3181 # https://github.com/iv-org/invidious/pull/1730
3182 mobj = re.search(
3183 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3184 webpage)
3185 if mobj:
3186 yield cls.url_result(mobj.group('url'), cls)
3187 raise cls.StopExtraction()
3188
3189 yield from super()._extract_from_webpage(url, webpage)
3190
3191 # lazyYT YouTube embed
3192 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3193 yield cls.url_result(unescapeHTML(id_), cls, id_)
3194
3195 # Wordpress "YouTube Video Importer" plugin
3196 for m in re.findall(r'''(?x)<div[^>]+
3197 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3198 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3199 yield cls.url_result(m[-1], cls, m[-1])
3200
3201 @classmethod
3202 def extract_id(cls, url):
3203 video_id = cls.get_temp_id(url)
3204 if not video_id:
3205 raise ExtractorError(f'Invalid URL: {url}')
3206 return video_id
3207
3208 def _extract_chapters_from_json(self, data, duration):
3209 chapter_list = traverse_obj(
3210 data, (
3211 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3212 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3213 ), expected_type=list)
3214
3215 return self._extract_chapters_helper(
3216 chapter_list,
3217 start_function=lambda chapter: float_or_none(
3218 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3219 title_function=lambda chapter: traverse_obj(
3220 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3221 duration=duration)
3222
3223 def _extract_chapters_from_engagement_panel(self, data, duration):
3224 content_list = traverse_obj(
3225 data,
3226 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
3227 expected_type=list)
3228 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3229 chapter_title = lambda chapter: self._get_text(chapter, 'title')
3230
3231 return next(filter(None, (
3232 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3233 chapter_time, chapter_title, duration)
3234 for contents in content_list)), [])
3235
3236 def _extract_comment(self, comment_renderer, parent=None):
3237 comment_id = comment_renderer.get('commentId')
3238 if not comment_id:
3239 return
3240
3241 text = self._get_text(comment_renderer, 'contentText')
3242
3243 # Timestamp is an estimate calculated from the current time and time_text
3244 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3245 timestamp = self._parse_time_text(time_text)
3246
3247 author = self._get_text(comment_renderer, 'authorText')
3248 author_id = try_get(comment_renderer,
3249 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3250
3251 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3252 lambda x: x['likeCount']), str)) or 0
3253 author_thumbnail = try_get(comment_renderer,
3254 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3255
3256 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3257 is_favorited = 'creatorHeart' in (try_get(
3258 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3259 return {
3260 'id': comment_id,
3261 'text': text,
3262 'timestamp': timestamp,
3263 'time_text': time_text,
3264 'like_count': votes,
3265 'is_favorited': is_favorited,
3266 'author': author,
3267 'author_id': author_id,
3268 'author_thumbnail': author_thumbnail,
3269 'author_is_uploader': author_is_uploader,
3270 'parent': parent or 'root'
3271 }
3272
3273 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3274
3275 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3276
3277 def extract_header(contents):
3278 _continuation = None
3279 for content in contents:
3280 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3281 expected_comment_count = self._get_count(
3282 comments_header_renderer, 'countText', 'commentsCount')
3283
3284 if expected_comment_count:
3285 tracker['est_total'] = expected_comment_count
3286 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3287 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3288
3289 sort_menu_item = try_get(
3290 comments_header_renderer,
3291 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3292 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3293
3294 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3295 if not _continuation:
3296 continue
3297
3298 sort_text = str_or_none(sort_menu_item.get('title'))
3299 if not sort_text:
3300 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3301 self.to_screen('Sorting comments by %s' % sort_text.lower())
3302 break
3303 return _continuation
3304
3305 def extract_thread(contents):
3306 if not parent:
3307 tracker['current_page_thread'] = 0
3308 for content in contents:
3309 if not parent and tracker['total_parent_comments'] >= max_parents:
3310 yield
3311 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3312 comment_renderer = get_first(
3313 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3314 expected_type=dict, default={})
3315
3316 comment = self._extract_comment(comment_renderer, parent)
3317 if not comment:
3318 continue
3319 # Sometimes YouTube may break and give us infinite looping comments.
3320 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
3321 if comment['id'] in tracker['seen_comment_ids']:
3322 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3323 yield
3324 else:
3325 tracker['seen_comment_ids'].add(comment['id'])
3326
3327 tracker['running_total'] += 1
3328 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3329 yield comment
3330
3331 # Attempt to get the replies
3332 comment_replies_renderer = try_get(
3333 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3334
3335 if comment_replies_renderer:
3336 tracker['current_page_thread'] += 1
3337 comment_entries_iter = self._comment_entries(
3338 comment_replies_renderer, ytcfg, video_id,
3339 parent=comment.get('id'), tracker=tracker)
3340 yield from itertools.islice(comment_entries_iter, min(
3341 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3342
3343 # Keeps track of counts across recursive calls
3344 if not tracker:
3345 tracker = dict(
3346 running_total=0,
3347 est_total=0,
3348 current_page_thread=0,
3349 total_parent_comments=0,
3350 total_reply_comments=0,
3351 seen_comment_ids=set())
3352
3353 # TODO: Deprecated
3354 # YouTube comments have a max depth of 2
3355 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3356 if max_depth:
3357 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3358 'Set max replies in the max-comments extractor argument instead')
3359 if max_depth == 1 and parent:
3360 return
3361
3362 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3363 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3364
3365 continuation = self._extract_continuation(root_continuation_data)
3366
3367 response = None
3368 is_forced_continuation = False
3369 is_first_continuation = parent is None
3370 if is_first_continuation and not continuation:
3371 # Sometimes you can get comments by generating the continuation yourself,
3372 # even if YouTube initially reports them being disabled - e.g. stories comments.
3373 # Note: if the comment section is actually disabled, YouTube may return a response with
3374 # required check_get_keys missing. So we will disable that check initially in this case.
3375 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3376 is_forced_continuation = True
3377
3378 for page_num in itertools.count(0):
3379 if not continuation:
3380 break
3381 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3382 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
3383 if page_num == 0:
3384 if is_first_continuation:
3385 note_prefix = 'Downloading comment section API JSON'
3386 else:
3387 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3388 tracker['current_page_thread'], comment_prog_str)
3389 else:
3390 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3391 ' ' if parent else '', ' replies' if parent else '',
3392 page_num, comment_prog_str)
3393 try:
3394 response = self._extract_response(
3395 item_id=None, query=continuation,
3396 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3397 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3398 except ExtractorError as e:
3399 # Ignore incomplete data error for replies if retries didn't work.
3400 # This is to allow any other parent comments and comment threads to be downloaded.
3401 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3402 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3403 self.report_warning(
3404 'Received incomplete data for a comment reply thread and retrying did not help. '
3405 'Ignoring to let other comments be downloaded.')
3406 else:
3407 raise
3408 is_forced_continuation = False
3409 continuation_contents = traverse_obj(
3410 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3411
3412 continuation = None
3413 for continuation_section in continuation_contents:
3414 continuation_items = traverse_obj(
3415 continuation_section,
3416 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3417 get_all=False, expected_type=list) or []
3418 if is_first_continuation:
3419 continuation = extract_header(continuation_items)
3420 is_first_continuation = False
3421 if continuation:
3422 break
3423 continue
3424
3425 for entry in extract_thread(continuation_items):
3426 if not entry:
3427 return
3428 yield entry
3429 continuation = self._extract_continuation({'contents': continuation_items})
3430 if continuation:
3431 break
3432
3433 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3434 if message and not parent and tracker['running_total'] == 0:
3435 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3436 raise self.CommentsDisabled
3437
3438 @staticmethod
3439 def _generate_comment_continuation(video_id):
3440 """
3441 Generates initial comment section continuation token from given video id
3442 """
3443 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3444 return base64.b64encode(token.encode()).decode()
3445
3446 def _get_comments(self, ytcfg, video_id, contents, webpage):
3447 """Entry for comment extraction"""
3448 def _real_comment_extract(contents):
3449 renderer = next((
3450 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3451 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3452 yield from self._comment_entries(renderer, ytcfg, video_id)
3453
3454 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3455 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3456
3457 @staticmethod
3458 def _get_checkok_params():
3459 return {'contentCheckOk': True, 'racyCheckOk': True}
3460
3461 @classmethod
3462 def _generate_player_context(cls, sts=None):
3463 context = {
3464 'html5Preference': 'HTML5_PREF_WANTS',
3465 }
3466 if sts is not None:
3467 context['signatureTimestamp'] = sts
3468 return {
3469 'playbackContext': {
3470 'contentPlaybackContext': context
3471 },
3472 **cls._get_checkok_params()
3473 }
3474
3475 @staticmethod
3476 def _is_agegated(player_response):
3477 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3478 return True
3479
3480 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
3481 AGE_GATE_REASONS = (
3482 'confirm your age', 'age-restricted', 'inappropriate', # reason
3483 'age_verification_required', 'age_check_required', # status
3484 )
3485 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3486
3487 @staticmethod
3488 def _is_unplayable(player_response):
3489 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3490
3491 _STORY_PLAYER_PARAMS = '8AEB'
3492
3493 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3494
3495 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3496 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3497 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3498 headers = self.generate_api_headers(
3499 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3500
3501 yt_query = {
3502 'videoId': video_id,
3503 }
3504 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3505 yt_query['params'] = self._STORY_PLAYER_PARAMS
3506
3507 yt_query.update(self._generate_player_context(sts))
3508 return self._extract_response(
3509 item_id=video_id, ep='player', query=yt_query,
3510 ytcfg=player_ytcfg, headers=headers, fatal=True,
3511 default_client=client,
3512 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3513 ) or None
3514
3515 def _get_requested_clients(self, url, smuggled_data):
3516 requested_clients = []
3517 default = ['android', 'web']
3518 allowed_clients = sorted(
3519 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3520 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3521 for client in self._configuration_arg('player_client'):
3522 if client in allowed_clients:
3523 requested_clients.append(client)
3524 elif client == 'default':
3525 requested_clients.extend(default)
3526 elif client == 'all':
3527 requested_clients.extend(allowed_clients)
3528 else:
3529 self.report_warning(f'Skipping unsupported client {client}')
3530 if not requested_clients:
3531 requested_clients = default
3532
3533 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3534 requested_clients.extend(
3535 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3536
3537 return orderedSet(requested_clients)
3538
3539 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3540 initial_pr = None
3541 if webpage:
3542 initial_pr = self._search_json(
3543 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3544
3545 all_clients = set(clients)
3546 clients = clients[::-1]
3547 prs = []
3548
3549 def append_client(*client_names):
3550 """ Append the first client name that exists but not already used """
3551 for client_name in client_names:
3552 actual_client = _split_innertube_client(client_name)[0]
3553 if actual_client in INNERTUBE_CLIENTS:
3554 if actual_client not in all_clients:
3555 clients.append(client_name)
3556 all_clients.add(actual_client)
3557 return
3558
3559 # Android player_response does not have microFormats which are needed for
3560 # extraction of some data. So we return the initial_pr with formats
3561 # stripped out even if not requested by the user
3562 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3563 if initial_pr:
3564 pr = dict(initial_pr)
3565 pr['streamingData'] = None
3566 prs.append(pr)
3567
3568 last_error = None
3569 tried_iframe_fallback = False
3570 player_url = None
3571 while clients:
3572 client, base_client, variant = _split_innertube_client(clients.pop())
3573 player_ytcfg = master_ytcfg if client == 'web' else {}
3574 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3575 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3576
3577 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3578 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3579 if 'js' in self._configuration_arg('player_skip'):
3580 require_js_player = False
3581 player_url = None
3582
3583 if not player_url and not tried_iframe_fallback and require_js_player:
3584 player_url = self._download_player_url(video_id)
3585 tried_iframe_fallback = True
3586
3587 try:
3588 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3589 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3590 except ExtractorError as e:
3591 if last_error:
3592 self.report_warning(last_error)
3593 last_error = e
3594 continue
3595
3596 if pr:
3597 # YouTube may return a different video player response than expected.
3598 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3599 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3600 if pr_video_id and pr_video_id != video_id:
3601 self.report_warning(
3602 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
3603 else:
3604 # Save client name for introspection later
3605 name = short_client_name(client)
3606 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3607 sd[STREAMING_DATA_CLIENT_NAME] = name
3608 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3609 f[STREAMING_DATA_CLIENT_NAME] = name
3610 prs.append(pr)
3611
3612 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3613 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3614 append_client(f'{base_client}_creator')
3615 elif self._is_agegated(pr):
3616 if variant == 'tv_embedded':
3617 append_client(f'{base_client}_embedded')
3618 elif not variant:
3619 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3620
3621 if last_error:
3622 if not len(prs):
3623 raise last_error
3624 self.report_warning(last_error)
3625 return prs, player_url
3626
3627 def _needs_live_processing(self, live_status, duration):
3628 if (live_status == 'is_live' and self.get_param('live_from_start')
3629 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3630 return live_status
3631
3632 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3633 itags, stream_ids = collections.defaultdict(set), []
3634 itag_qualities, res_qualities = {}, {0: None}
3635 q = qualities([
3636 # Normally tiny is the smallest video-only formats. But
3637 # audio-only formats with unknown quality may get tagged as tiny
3638 'tiny',
3639 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3640 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3641 ])
3642 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
3643
3644 for fmt in streaming_formats:
3645 if fmt.get('targetDurationSec'):
3646 continue
3647
3648 itag = str_or_none(fmt.get('itag'))
3649 audio_track = fmt.get('audioTrack') or {}
3650 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
3651 if stream_id in stream_ids:
3652 continue
3653
3654 quality = fmt.get('quality')
3655 height = int_or_none(fmt.get('height'))
3656 if quality == 'tiny' or not quality:
3657 quality = fmt.get('audioQuality', '').lower() or quality
3658 # The 3gp format (17) in android client has a quality of "small",
3659 # but is actually worse than other formats
3660 if itag == '17':
3661 quality = 'tiny'
3662 if quality:
3663 if itag:
3664 itag_qualities[itag] = quality
3665 if height:
3666 res_qualities[height] = quality
3667 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3668 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3669 # number of fragment that would subsequently requested with (`&sq=N`)
3670 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3671 continue
3672
3673 fmt_url = fmt.get('url')
3674 if not fmt_url:
3675 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3676 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3677 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3678 if not all((sc, fmt_url, player_url, encrypted_sig)):
3679 continue
3680 try:
3681 fmt_url += '&%s=%s' % (
3682 traverse_obj(sc, ('sp', -1)) or 'signature',
3683 self._decrypt_signature(encrypted_sig, video_id, player_url)
3684 )
3685 except ExtractorError as e:
3686 self.report_warning('Signature extraction failed: Some formats may be missing',
3687 video_id=video_id, only_once=True)
3688 self.write_debug(e, only_once=True)
3689 continue
3690
3691 query = parse_qs(fmt_url)
3692 throttled = False
3693 if query.get('n'):
3694 try:
3695 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3696 fmt_url = update_url_query(fmt_url, {
3697 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3698 })
3699 except ExtractorError as e:
3700 phantomjs_hint = ''
3701 if isinstance(e, JSInterpreter.Exception):
3702 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3703 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3704 if player_url:
3705 self.report_warning(
3706 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3707 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3708 self.write_debug(e, only_once=True)
3709 else:
3710 self.report_warning(
3711 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3712 video_id=video_id, only_once=True)
3713 throttled = True
3714
3715 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3716 language_preference = (
3717 10 if audio_track.get('audioIsDefault') and 10
3718 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3719 else -1)
3720 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3721 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3722 # Make sure to avoid false positives with small duration differences.
3723 # E.g. __2ABJjxzNo, ySuUZEjARPY
3724 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3725 if is_damaged:
3726 self.report_warning(
3727 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3728
3729 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
3730 dct = {
3731 'asr': int_or_none(fmt.get('audioSampleRate')),
3732 'filesize': int_or_none(fmt.get('contentLength')),
3733 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
3734 'format_note': join_nonempty(
3735 join_nonempty(audio_track.get('displayName'),
3736 language_preference > 0 and ' (default)', delim=''),
3737 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3738 fmt.get('isDrc') and 'DRC',
3739 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3740 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3741 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
3742 self.get_param('verbose') and client_name,
3743 delim=', '),
3744 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3745 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3746 'fps': int_or_none(fmt.get('fps')) or None,
3747 'audio_channels': fmt.get('audioChannels'),
3748 'height': height,
3749 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
3750 'has_drm': bool(fmt.get('drmFamilies')),
3751 'tbr': tbr,
3752 'url': fmt_url,
3753 'width': int_or_none(fmt.get('width')),
3754 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3755 'desc' if language_preference < -1 else '') or None,
3756 'language_preference': language_preference,
3757 # Strictly de-prioritize damaged and 3gp formats
3758 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3759 }
3760 mime_mobj = re.match(
3761 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3762 if mime_mobj:
3763 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3764 dct.update(parse_codecs(mime_mobj.group(2)))
3765
3766 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3767 if single_stream and dct.get('ext'):
3768 dct['container'] = dct['ext'] + '_dash'
3769 if single_stream or itag == '17':
3770 CHUNK_SIZE = 10 << 20
3771 dct.update({
3772 'protocol': 'http_dash_segments',
3773 'fragments': [{
3774 'url': update_url_query(dct['url'], {
3775 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, dct["filesize"])}'
3776 })
3777 } for range_start in range(0, dct['filesize'], CHUNK_SIZE)]
3778 } if itag != '17' and dct['filesize'] else {
3779 'downloader_options': {'http_chunk_size': CHUNK_SIZE}
3780 })
3781
3782 if itag:
3783 itags[itag].add(('https', dct.get('language')))
3784 stream_ids.append(stream_id)
3785 yield dct
3786
3787 needs_live_processing = self._needs_live_processing(live_status, duration)
3788 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3789
3790 skip_manifests = set(self._configuration_arg('skip'))
3791 if (not self.get_param('youtube_include_hls_manifest', True)
3792 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3793 or needs_live_processing and skip_bad_formats):
3794 skip_manifests.add('hls')
3795
3796 if not self.get_param('youtube_include_dash_manifest', True):
3797 skip_manifests.add('dash')
3798 if self._configuration_arg('include_live_dash'):
3799 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3800 'Use include_incomplete_formats extractor argument instead')
3801 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3802 skip_manifests.add('dash')
3803
3804 def process_manifest_format(f, proto, client_name, itag):
3805 key = (proto, f.get('language'))
3806 if key in itags[itag]:
3807 return False
3808 itags[itag].add(key)
3809
3810 if any(p != proto for p, _ in itags[itag]):
3811 f['format_id'] = f'{itag}-{proto}'
3812 elif itag:
3813 f['format_id'] = itag
3814
3815 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3816 if f['quality'] == -1 and f.get('height'):
3817 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3818 if self.get_param('verbose'):
3819 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
3820 return True
3821
3822 subtitles = {}
3823 for sd in streaming_data:
3824 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3825
3826 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3827 if hls_manifest_url:
3828 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3829 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3830 subtitles = self._merge_subtitles(subs, subtitles)
3831 for f in fmts:
3832 if process_manifest_format(f, 'hls', client_name, self._search_regex(
3833 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3834 yield f
3835
3836 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3837 if dash_manifest_url:
3838 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3839 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3840 for f in formats:
3841 if process_manifest_format(f, 'dash', client_name, f['format_id']):
3842 f['filesize'] = int_or_none(self._search_regex(
3843 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3844 if needs_live_processing:
3845 f['is_from_start'] = True
3846
3847 yield f
3848 yield subtitles
3849
3850 def _extract_storyboard(self, player_responses, duration):
3851 spec = get_first(
3852 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3853 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3854 if not base_url:
3855 return
3856 L = len(spec) - 1
3857 for i, args in enumerate(spec):
3858 args = args.split('#')
3859 counts = list(map(int_or_none, args[:5]))
3860 if len(args) != 8 or not all(counts):
3861 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3862 continue
3863 width, height, frame_count, cols, rows = counts
3864 N, sigh = args[6:]
3865
3866 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3867 fragment_count = frame_count / (cols * rows)
3868 fragment_duration = duration / fragment_count
3869 yield {
3870 'format_id': f'sb{i}',
3871 'format_note': 'storyboard',
3872 'ext': 'mhtml',
3873 'protocol': 'mhtml',
3874 'acodec': 'none',
3875 'vcodec': 'none',
3876 'url': url,
3877 'width': width,
3878 'height': height,
3879 'fps': frame_count / duration,
3880 'rows': rows,
3881 'columns': cols,
3882 'fragments': [{
3883 'url': url.replace('$M', str(j)),
3884 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3885 } for j in range(math.ceil(fragment_count))],
3886 }
3887
3888 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3889 webpage = None
3890 if 'webpage' not in self._configuration_arg('player_skip'):
3891 query = {'bpctr': '9999999999', 'has_verified': '1'}
3892 if smuggled_data.get('is_story'):
3893 query['pp'] = self._STORY_PLAYER_PARAMS
3894 webpage = self._download_webpage(
3895 webpage_url, video_id, fatal=False, query=query)
3896
3897 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3898
3899 player_responses, player_url = self._extract_player_responses(
3900 self._get_requested_clients(url, smuggled_data),
3901 video_id, webpage, master_ytcfg, smuggled_data)
3902
3903 return webpage, master_ytcfg, player_responses, player_url
3904
3905 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3906 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3907 is_live = get_first(video_details, 'isLive')
3908 if is_live is None:
3909 is_live = get_first(live_broadcast_details, 'isLiveNow')
3910 live_content = get_first(video_details, 'isLiveContent')
3911 is_upcoming = get_first(video_details, 'isUpcoming')
3912 post_live = get_first(video_details, 'isPostLiveDvr')
3913 live_status = ('post_live' if post_live
3914 else 'is_live' if is_live
3915 else 'is_upcoming' if is_upcoming
3916 else 'was_live' if live_content
3917 else 'not_live' if False in (is_live, live_content)
3918 else None)
3919 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
3920 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3921
3922 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3923
3924 def _real_extract(self, url):
3925 url, smuggled_data = unsmuggle_url(url, {})
3926 video_id = self._match_id(url)
3927
3928 base_url = self.http_scheme() + '//www.youtube.com/'
3929 webpage_url = base_url + 'watch?v=' + video_id
3930
3931 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3932
3933 playability_statuses = traverse_obj(
3934 player_responses, (..., 'playabilityStatus'), expected_type=dict)
3935
3936 trailer_video_id = get_first(
3937 playability_statuses,
3938 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3939 expected_type=str)
3940 if trailer_video_id:
3941 return self.url_result(
3942 trailer_video_id, self.ie_key(), trailer_video_id)
3943
3944 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3945 if webpage else (lambda x: None))
3946
3947 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
3948 microformats = traverse_obj(
3949 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3950 expected_type=dict)
3951
3952 translated_title = self._get_text(microformats, (..., 'title'))
3953 video_title = (self._preferred_lang and translated_title
3954 or get_first(video_details, 'title') # primary
3955 or translated_title
3956 or search_meta(['og:title', 'twitter:title', 'title']))
3957 translated_description = self._get_text(microformats, (..., 'description'))
3958 original_description = get_first(video_details, 'shortDescription')
3959 video_description = (
3960 self._preferred_lang and translated_description
3961 # If original description is blank, it will be an empty string.
3962 # Do not prefer translated description in this case.
3963 or original_description if original_description is not None else translated_description)
3964
3965 multifeed_metadata_list = get_first(
3966 player_responses,
3967 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3968 expected_type=str)
3969 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3970 if self.get_param('noplaylist'):
3971 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3972 else:
3973 entries = []
3974 feed_ids = []
3975 for feed in multifeed_metadata_list.split(','):
3976 # Unquote should take place before split on comma (,) since textual
3977 # fields may contain comma as well (see
3978 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3979 feed_data = urllib.parse.parse_qs(
3980 urllib.parse.unquote_plus(feed))
3981
3982 def feed_entry(name):
3983 return try_get(
3984 feed_data, lambda x: x[name][0], str)
3985
3986 feed_id = feed_entry('id')
3987 if not feed_id:
3988 continue
3989 feed_title = feed_entry('title')
3990 title = video_title
3991 if feed_title:
3992 title += ' (%s)' % feed_title
3993 entries.append({
3994 '_type': 'url_transparent',
3995 'ie_key': 'Youtube',
3996 'url': smuggle_url(
3997 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3998 {'force_singlefeed': True}),
3999 'title': title,
4000 })
4001 feed_ids.append(feed_id)
4002 self.to_screen(
4003 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4004 % (', '.join(feed_ids), video_id))
4005 return self.playlist_result(
4006 entries, video_id, video_title, video_description)
4007
4008 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4009 or int_or_none(get_first(microformats, 'lengthSeconds'))
4010 or parse_duration(search_meta('duration')) or None)
4011
4012 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4013 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4014 if live_status == 'post_live':
4015 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
4016
4017 if not formats:
4018 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
4019 self.report_drm(video_id)
4020 pemr = get_first(
4021 playability_statuses,
4022 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4023 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4024 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
4025 if subreason:
4026 if subreason == 'The uploader has not made this video available in your country.':
4027 countries = get_first(microformats, 'availableCountries')
4028 if not countries:
4029 regions_allowed = search_meta('regionsAllowed')
4030 countries = regions_allowed.split(',') if regions_allowed else None
4031 self.raise_geo_restricted(subreason, countries, metadata_available=True)
4032 reason += f'. {subreason}'
4033 if reason:
4034 self.raise_no_formats(reason, expected=True)
4035
4036 keywords = get_first(video_details, 'keywords', expected_type=list) or []
4037 if not keywords and webpage:
4038 keywords = [
4039 unescapeHTML(m.group('content'))
4040 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4041 for keyword in keywords:
4042 if keyword.startswith('yt:stretch='):
4043 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4044 if mobj:
4045 # NB: float is intentional for forcing float division
4046 w, h = (float(v) for v in mobj.groups())
4047 if w > 0 and h > 0:
4048 ratio = w / h
4049 for f in formats:
4050 if f.get('vcodec') != 'none':
4051 f['stretched_ratio'] = ratio
4052 break
4053 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
4054 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4055 if thumbnail_url:
4056 thumbnails.append({
4057 'url': thumbnail_url,
4058 })
4059 original_thumbnails = thumbnails.copy()
4060
4061 # The best resolution thumbnails sometimes does not appear in the webpage
4062 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4063 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4064 thumbnail_names = [
4065 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4066 # in resolution, these are not the custom thumbnail. So de-prioritize them
4067 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4068 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4069 ]
4070 n_thumbnail_names = len(thumbnail_names)
4071 thumbnails.extend({
4072 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4073 video_id=video_id, name=name, ext=ext,
4074 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
4075 } for name in thumbnail_names for ext in ('webp', 'jpg'))
4076 for thumb in thumbnails:
4077 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
4078 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
4079 self._remove_duplicate_formats(thumbnails)
4080 self._downloader._sort_thumbnails(original_thumbnails)
4081
4082 category = get_first(microformats, 'category') or search_meta('genre')
4083 channel_id = str_or_none(
4084 get_first(video_details, 'channelId')
4085 or get_first(microformats, 'externalChannelId')
4086 or search_meta('channelId'))
4087 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4088
4089 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4090 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4091 if not duration and live_end_time and live_start_time:
4092 duration = live_end_time - live_start_time
4093
4094 needs_live_processing = self._needs_live_processing(live_status, duration)
4095
4096 def is_bad_format(fmt):
4097 if needs_live_processing and not fmt.get('is_from_start'):
4098 return True
4099 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4100 and fmt.get('protocol') == 'http_dash_segments'):
4101 return True
4102
4103 for fmt in filter(is_bad_format, formats):
4104 fmt['preference'] = (fmt.get('preference') or -1) - 10
4105 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4106
4107 if needs_live_processing:
4108 self._prepare_live_from_start_formats(
4109 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
4110
4111 formats.extend(self._extract_storyboard(player_responses, duration))
4112
4113 info = {
4114 'id': video_id,
4115 'title': video_title,
4116 'formats': formats,
4117 'thumbnails': thumbnails,
4118 # The best thumbnail that we are sure exists. Prevents unnecessary
4119 # URL checking if user don't care about getting the best possible thumbnail
4120 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
4121 'description': video_description,
4122 'uploader': get_first(video_details, 'author'),
4123 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
4124 'uploader_url': owner_profile_url,
4125 'channel_id': channel_id,
4126 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
4127 'duration': duration,
4128 'view_count': int_or_none(
4129 get_first((video_details, microformats), (..., 'viewCount'))
4130 or search_meta('interactionCount')),
4131 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
4132 'age_limit': 18 if (
4133 get_first(microformats, 'isFamilySafe') is False
4134 or search_meta('isFamilyFriendly') == 'false'
4135 or search_meta('og:restrictions:age') == '18+') else 0,
4136 'webpage_url': webpage_url,
4137 'categories': [category] if category else None,
4138 'tags': keywords,
4139 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4140 'live_status': live_status,
4141 'release_timestamp': live_start_time,
4142 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4143 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4144 }
4145
4146 subtitles = {}
4147 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
4148 if pctr:
4149 def get_lang_code(track):
4150 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4151 or track.get('languageCode'))
4152
4153 # Converted into dicts to remove duplicates
4154 captions = {
4155 get_lang_code(sub): sub
4156 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
4157 translation_languages = {
4158 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4159 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
4160
4161 def process_language(container, base_url, lang_code, sub_name, query):
4162 lang_subs = container.setdefault(lang_code, [])
4163 for fmt in self._SUBTITLE_FORMATS:
4164 query.update({
4165 'fmt': fmt,
4166 })
4167 lang_subs.append({
4168 'ext': fmt,
4169 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
4170 'name': sub_name,
4171 })
4172
4173 # NB: Constructing the full subtitle dictionary is slow
4174 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4175 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
4176 for lang_code, caption_track in captions.items():
4177 base_url = caption_track.get('baseUrl')
4178 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
4179 if not base_url:
4180 continue
4181 lang_name = self._get_text(caption_track, 'name', max_runs=1)
4182 if caption_track.get('kind') != 'asr':
4183 if not lang_code:
4184 continue
4185 process_language(
4186 subtitles, base_url, lang_code, lang_name, {})
4187 if not caption_track.get('isTranslatable'):
4188 continue
4189 for trans_code, trans_name in translation_languages.items():
4190 if not trans_code:
4191 continue
4192 orig_trans_code = trans_code
4193 if caption_track.get('kind') != 'asr' and trans_code != 'und':
4194 if not get_translated_subs:
4195 continue
4196 trans_code += f'-{lang_code}'
4197 trans_name += format_field(lang_name, None, ' from %s')
4198 # Add an "-orig" label to the original language so that it can be distinguished.
4199 # The subs are returned without "-orig" as well for compatibility
4200 if lang_code == f'a-{orig_trans_code}':
4201 process_language(
4202 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4203 # Setting tlang=lang returns damaged subtitles.
4204 process_language(automatic_captions, base_url, trans_code, trans_name,
4205 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
4206
4207 info['automatic_captions'] = automatic_captions
4208 info['subtitles'] = subtitles
4209
4210 parsed_url = urllib.parse.urlparse(url)
4211 for component in [parsed_url.fragment, parsed_url.query]:
4212 query = urllib.parse.parse_qs(component)
4213 for k, v in query.items():
4214 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4215 d_k += '_time'
4216 if d_k not in info and k in s_ks:
4217 info[d_k] = parse_duration(query[k][0])
4218
4219 # Youtube Music Auto-generated description
4220 if video_description:
4221 mobj = re.search(
4222 r'''(?xs)
4223 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4224 (?P<album>[^\n]+)
4225 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4226 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4227 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4228 .+\nAuto-generated\ by\ YouTube\.\s*$
4229 ''', video_description)
4230 if mobj:
4231 release_year = mobj.group('release_year')
4232 release_date = mobj.group('release_date')
4233 if release_date:
4234 release_date = release_date.replace('-', '')
4235 if not release_year:
4236 release_year = release_date[:4]
4237 info.update({
4238 'album': mobj.group('album'.strip()),
4239 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4240 'track': mobj.group('track').strip(),
4241 'release_date': release_date,
4242 'release_year': int_or_none(release_year),
4243 })
4244
4245 initial_data = None
4246 if webpage:
4247 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4248 if not initial_data:
4249 query = {'videoId': video_id}
4250 query.update(self._get_checkok_params())
4251 initial_data = self._extract_response(
4252 item_id=video_id, ep='next', fatal=False,
4253 ytcfg=master_ytcfg, query=query,
4254 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4255 note='Downloading initial data API JSON')
4256
4257 info['comment_count'] = traverse_obj(initial_data, (
4258 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4259 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4260 ), (
4261 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4262 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4263 ), expected_type=int_or_none, get_all=False)
4264
4265 try: # This will error if there is no livechat
4266 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4267 except (KeyError, IndexError, TypeError):
4268 pass
4269 else:
4270 info.setdefault('subtitles', {})['live_chat'] = [{
4271 # url is needed to set cookies
4272 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4273 'video_id': video_id,
4274 'ext': 'json',
4275 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4276 else 'youtube_live_chat_replay'),
4277 }]
4278
4279 if initial_data:
4280 info['chapters'] = (
4281 self._extract_chapters_from_json(initial_data, duration)
4282 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4283 or self._extract_chapters_from_description(video_description, duration)
4284 or None)
4285
4286 contents = traverse_obj(
4287 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4288 expected_type=list, default=[])
4289
4290 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4291 if vpir:
4292 stl = vpir.get('superTitleLink')
4293 if stl:
4294 stl = self._get_text(stl)
4295 if try_get(
4296 vpir,
4297 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4298 info['location'] = stl
4299 else:
4300 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4301 if mobj:
4302 info.update({
4303 'series': mobj.group(1),
4304 'season_number': int(mobj.group(2)),
4305 'episode_number': int(mobj.group(3)),
4306 })
4307 for tlb in (try_get(
4308 vpir,
4309 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4310 list) or []):
4311 tbrs = variadic(
4312 traverse_obj(
4313 tlb, ('toggleButtonRenderer', ...),
4314 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4315 for tbr in tbrs:
4316 for getter, regex in [(
4317 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4318 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4319 lambda x: x['accessibility'],
4320 lambda x: x['accessibilityData']['accessibilityData'],
4321 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4322 label = (try_get(tbr, getter, dict) or {}).get('label')
4323 if label:
4324 mobj = re.match(regex, label)
4325 if mobj:
4326 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4327 break
4328 sbr_tooltip = try_get(
4329 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4330 if sbr_tooltip:
4331 like_count, dislike_count = sbr_tooltip.split(' / ')
4332 info.update({
4333 'like_count': str_to_int(like_count),
4334 'dislike_count': str_to_int(dislike_count),
4335 })
4336 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4337 if vcr:
4338 vc = self._get_count(vcr, 'viewCount')
4339 # Upcoming premieres with waiting count are treated as live here
4340 if vcr.get('isLive'):
4341 info['concurrent_view_count'] = vc
4342 elif info.get('view_count') is None:
4343 info['view_count'] = vc
4344
4345 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4346 if vsir:
4347 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4348 info.update({
4349 'channel': self._get_text(vor, 'title'),
4350 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4351
4352 rows = try_get(
4353 vsir,
4354 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4355 list) or []
4356 multiple_songs = False
4357 for row in rows:
4358 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4359 multiple_songs = True
4360 break
4361 for row in rows:
4362 mrr = row.get('metadataRowRenderer') or {}
4363 mrr_title = mrr.get('title')
4364 if not mrr_title:
4365 continue
4366 mrr_title = self._get_text(mrr, 'title')
4367 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4368 if mrr_title == 'License':
4369 info['license'] = mrr_contents_text
4370 elif not multiple_songs:
4371 if mrr_title == 'Album':
4372 info['album'] = mrr_contents_text
4373 elif mrr_title == 'Artist':
4374 info['artist'] = mrr_contents_text
4375 elif mrr_title == 'Song':
4376 info['track'] = mrr_contents_text
4377
4378 fallbacks = {
4379 'channel': 'uploader',
4380 'channel_id': 'uploader_id',
4381 'channel_url': 'uploader_url',
4382 }
4383
4384 # The upload date for scheduled, live and past live streams / premieres in microformats
4385 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4386 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4387 upload_date = (
4388 unified_strdate(get_first(microformats, 'uploadDate'))
4389 or unified_strdate(search_meta('uploadDate')))
4390 if not upload_date or (
4391 live_status in ('not_live', None)
4392 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4393 ):
4394 upload_date = strftime_or_none(
4395 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4396 info['upload_date'] = upload_date
4397
4398 for to, frm in fallbacks.items():
4399 if not info.get(to):
4400 info[to] = info.get(frm)
4401
4402 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4403 v = info.get(s_k)
4404 if v:
4405 info[d_k] = v
4406
4407 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4408
4409 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4410 or get_first(video_details, 'isPrivate', expected_type=bool))
4411
4412 info['availability'] = (
4413 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4414 else self._availability(
4415 is_private=is_private,
4416 needs_premium=(
4417 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4418 or False if initial_data and is_private is not None else None),
4419 needs_subscription=(
4420 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4421 or False if initial_data and is_private is not None else None),
4422 needs_auth=info['age_limit'] >= 18,
4423 is_unlisted=None if is_private is None else (
4424 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4425 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4426
4427 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4428
4429 self.mark_watched(video_id, player_responses)
4430
4431 return info
4432
4433
4434 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4435 @staticmethod
4436 def passthrough_smuggled_data(func):
4437 def _smuggle(info, smuggled_data):
4438 if info.get('_type') not in ('url', 'url_transparent'):
4439 return info
4440 if smuggled_data.get('is_music_url'):
4441 parsed_url = urllib.parse.urlparse(info['url'])
4442 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4443 smuggled_data.pop('is_music_url')
4444 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4445 if smuggled_data:
4446 info['url'] = smuggle_url(info['url'], smuggled_data)
4447 return info
4448
4449 @functools.wraps(func)
4450 def wrapper(self, url):
4451 url, smuggled_data = unsmuggle_url(url, {})
4452 if self.is_music_url(url):
4453 smuggled_data['is_music_url'] = True
4454 info_dict = func(self, url, smuggled_data)
4455 if smuggled_data:
4456 _smuggle(info_dict, smuggled_data)
4457 if info_dict.get('entries'):
4458 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
4459 return info_dict
4460 return wrapper
4461
4462 @staticmethod
4463 def _extract_basic_item_renderer(item):
4464 # Modified from _extract_grid_item_renderer
4465 known_basic_renderers = (
4466 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4467 )
4468 for key, renderer in item.items():
4469 if not isinstance(renderer, dict):
4470 continue
4471 elif key in known_basic_renderers:
4472 return renderer
4473 elif key.startswith('grid') and key.endswith('Renderer'):
4474 return renderer
4475
4476 def _extract_channel_renderer(self, renderer):
4477 channel_id = renderer['channelId']
4478 title = self._get_text(renderer, 'title')
4479 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4480 return {
4481 '_type': 'url',
4482 'url': channel_url,
4483 'id': channel_id,
4484 'ie_key': YoutubeTabIE.ie_key(),
4485 'channel': title,
4486 'channel_id': channel_id,
4487 'channel_url': channel_url,
4488 'title': title,
4489 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4490 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4491 'playlist_count': self._get_count(renderer, 'videoCountText'),
4492 'description': self._get_text(renderer, 'descriptionSnippet'),
4493 }
4494
4495 def _grid_entries(self, grid_renderer):
4496 for item in grid_renderer['items']:
4497 if not isinstance(item, dict):
4498 continue
4499 renderer = self._extract_basic_item_renderer(item)
4500 if not isinstance(renderer, dict):
4501 continue
4502 title = self._get_text(renderer, 'title')
4503
4504 # playlist
4505 playlist_id = renderer.get('playlistId')
4506 if playlist_id:
4507 yield self.url_result(
4508 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4509 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4510 video_title=title)
4511 continue
4512 # video
4513 video_id = renderer.get('videoId')
4514 if video_id:
4515 yield self._extract_video(renderer)
4516 continue
4517 # channel
4518 channel_id = renderer.get('channelId')
4519 if channel_id:
4520 yield self._extract_channel_renderer(renderer)
4521 continue
4522 # generic endpoint URL support
4523 ep_url = urljoin('https://www.youtube.com/', try_get(
4524 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4525 str))
4526 if ep_url:
4527 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4528 if ie.suitable(ep_url):
4529 yield self.url_result(
4530 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4531 break
4532
4533 def _music_reponsive_list_entry(self, renderer):
4534 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4535 if video_id:
4536 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4537 ie=YoutubeIE.ie_key(), video_id=video_id)
4538 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4539 if playlist_id:
4540 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4541 if video_id:
4542 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4543 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4544 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4545 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4546 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4547 if browse_id:
4548 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4549 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4550
4551 def _shelf_entries_from_content(self, shelf_renderer):
4552 content = shelf_renderer.get('content')
4553 if not isinstance(content, dict):
4554 return
4555 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4556 if renderer:
4557 # TODO: add support for nested playlists so each shelf is processed
4558 # as separate playlist
4559 # TODO: this includes only first N items
4560 yield from self._grid_entries(renderer)
4561 renderer = content.get('horizontalListRenderer')
4562 if renderer:
4563 # TODO
4564 pass
4565
4566 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4567 ep = try_get(
4568 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4569 str)
4570 shelf_url = urljoin('https://www.youtube.com', ep)
4571 if shelf_url:
4572 # Skipping links to another channels, note that checking for
4573 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4574 # will not work
4575 if skip_channels and '/channels?' in shelf_url:
4576 return
4577 title = self._get_text(shelf_renderer, 'title')
4578 yield self.url_result(shelf_url, video_title=title)
4579 # Shelf may not contain shelf URL, fallback to extraction from content
4580 yield from self._shelf_entries_from_content(shelf_renderer)
4581
4582 def _playlist_entries(self, video_list_renderer):
4583 for content in video_list_renderer['contents']:
4584 if not isinstance(content, dict):
4585 continue
4586 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4587 if not isinstance(renderer, dict):
4588 continue
4589 video_id = renderer.get('videoId')
4590 if not video_id:
4591 continue
4592 yield self._extract_video(renderer)
4593
4594 def _rich_entries(self, rich_grid_renderer):
4595 renderer = traverse_obj(
4596 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4597 video_id = renderer.get('videoId')
4598 if not video_id:
4599 return
4600 yield self._extract_video(renderer)
4601
4602 def _video_entry(self, video_renderer):
4603 video_id = video_renderer.get('videoId')
4604 if video_id:
4605 return self._extract_video(video_renderer)
4606
4607 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4608 url = urljoin('https://youtube.com', traverse_obj(
4609 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4610 if url:
4611 return self.url_result(
4612 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4613
4614 def _post_thread_entries(self, post_thread_renderer):
4615 post_renderer = try_get(
4616 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4617 if not post_renderer:
4618 return
4619 # video attachment
4620 video_renderer = try_get(
4621 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4622 video_id = video_renderer.get('videoId')
4623 if video_id:
4624 entry = self._extract_video(video_renderer)
4625 if entry:
4626 yield entry
4627 # playlist attachment
4628 playlist_id = try_get(
4629 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4630 if playlist_id:
4631 yield self.url_result(
4632 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4633 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4634 # inline video links
4635 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4636 for run in runs:
4637 if not isinstance(run, dict):
4638 continue
4639 ep_url = try_get(
4640 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4641 if not ep_url:
4642 continue
4643 if not YoutubeIE.suitable(ep_url):
4644 continue
4645 ep_video_id = YoutubeIE._match_id(ep_url)
4646 if video_id == ep_video_id:
4647 continue
4648 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4649
4650 def _post_thread_continuation_entries(self, post_thread_continuation):
4651 contents = post_thread_continuation.get('contents')
4652 if not isinstance(contents, list):
4653 return
4654 for content in contents:
4655 renderer = content.get('backstagePostThreadRenderer')
4656 if isinstance(renderer, dict):
4657 yield from self._post_thread_entries(renderer)
4658 continue
4659 renderer = content.get('videoRenderer')
4660 if isinstance(renderer, dict):
4661 yield self._video_entry(renderer)
4662
4663 r''' # unused
4664 def _rich_grid_entries(self, contents):
4665 for content in contents:
4666 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4667 if video_renderer:
4668 entry = self._video_entry(video_renderer)
4669 if entry:
4670 yield entry
4671 '''
4672
4673 def _report_history_entries(self, renderer):
4674 for url in traverse_obj(renderer, (
4675 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4676 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4677 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4678 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4679
4680 def _extract_entries(self, parent_renderer, continuation_list):
4681 # continuation_list is modified in-place with continuation_list = [continuation_token]
4682 continuation_list[:] = [None]
4683 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4684 for content in contents:
4685 if not isinstance(content, dict):
4686 continue
4687 is_renderer = traverse_obj(
4688 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4689 expected_type=dict)
4690 if not is_renderer:
4691 if content.get('richItemRenderer'):
4692 for entry in self._rich_entries(content['richItemRenderer']):
4693 yield entry
4694 continuation_list[0] = self._extract_continuation(parent_renderer)
4695 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4696 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4697 yield from self._report_history_entries(table)
4698 continuation_list[0] = self._extract_continuation(table)
4699 continue
4700
4701 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4702 for isr_content in isr_contents:
4703 if not isinstance(isr_content, dict):
4704 continue
4705
4706 known_renderers = {
4707 'playlistVideoListRenderer': self._playlist_entries,
4708 'gridRenderer': self._grid_entries,
4709 'reelShelfRenderer': self._grid_entries,
4710 'shelfRenderer': self._shelf_entries,
4711 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4712 'backstagePostThreadRenderer': self._post_thread_entries,
4713 'videoRenderer': lambda x: [self._video_entry(x)],
4714 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4715 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4716 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4717 }
4718 for key, renderer in isr_content.items():
4719 if key not in known_renderers:
4720 continue
4721 for entry in known_renderers[key](renderer):
4722 if entry:
4723 yield entry
4724 continuation_list[0] = self._extract_continuation(renderer)
4725 break
4726
4727 if not continuation_list[0]:
4728 continuation_list[0] = self._extract_continuation(is_renderer)
4729
4730 if not continuation_list[0]:
4731 continuation_list[0] = self._extract_continuation(parent_renderer)
4732
4733 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4734 continuation_list = [None]
4735 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4736 tab_content = try_get(tab, lambda x: x['content'], dict)
4737 if not tab_content:
4738 return
4739 parent_renderer = (
4740 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4741 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4742 yield from extract_entries(parent_renderer)
4743 continuation = continuation_list[0]
4744
4745 for page_num in itertools.count(1):
4746 if not continuation:
4747 break
4748 headers = self.generate_api_headers(
4749 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4750 response = self._extract_response(
4751 item_id=f'{item_id} page {page_num}',
4752 query=continuation, headers=headers, ytcfg=ytcfg,
4753 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4754
4755 if not response:
4756 break
4757 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4758 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4759 visitor_data = self._extract_visitor_data(response) or visitor_data
4760
4761 known_renderers = {
4762 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4763 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4764 'gridVideoRenderer': (self._grid_entries, 'items'),
4765 'gridChannelRenderer': (self._grid_entries, 'items'),
4766 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4767 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4768 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4769 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4770 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4771 'playlistVideoListContinuation': (self._playlist_entries, None),
4772 'gridContinuation': (self._grid_entries, None),
4773 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4774 'sectionListContinuation': (extract_entries, None), # for feeds
4775 }
4776
4777 continuation_items = traverse_obj(response, (
4778 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4779 'appendContinuationItemsAction', 'continuationItems'
4780 ), 'continuationContents', get_all=False)
4781 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4782
4783 video_items_renderer = None
4784 for key in continuation_item.keys():
4785 if key not in known_renderers:
4786 continue
4787 func, parent_key = known_renderers[key]
4788 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4789 continuation_list = [None]
4790 yield from func(video_items_renderer)
4791 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4792
4793 if not video_items_renderer:
4794 break
4795
4796 @staticmethod
4797 def _extract_selected_tab(tabs, fatal=True):
4798 for tab_renderer in tabs:
4799 if tab_renderer.get('selected'):
4800 return tab_renderer
4801 if fatal:
4802 raise ExtractorError('Unable to find selected tab')
4803
4804 @staticmethod
4805 def _extract_tab_renderers(response):
4806 return traverse_obj(
4807 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
4808
4809 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4810 metadata = self._extract_metadata_from_tabs(item_id, data)
4811
4812 selected_tab = self._extract_selected_tab(tabs)
4813 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4814 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4815
4816 return self.playlist_result(
4817 self._entries(
4818 selected_tab, metadata['id'], ytcfg,
4819 self._extract_account_syncid(ytcfg, data),
4820 self._extract_visitor_data(data, ytcfg)),
4821 **metadata)
4822
4823 def _extract_metadata_from_tabs(self, item_id, data):
4824 info = {'id': item_id}
4825
4826 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
4827 if metadata_renderer:
4828 info.update({
4829 'uploader': metadata_renderer.get('title'),
4830 'uploader_id': metadata_renderer.get('externalId'),
4831 'uploader_url': metadata_renderer.get('channelUrl'),
4832 })
4833 if info['uploader_id']:
4834 info['id'] = info['uploader_id']
4835 else:
4836 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
4837
4838 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4839 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4840 def _get_uncropped(url):
4841 return url_or_none((url or '').split('=')[0] + '=s0')
4842
4843 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
4844 if avatar_thumbnails:
4845 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4846 if uncropped_avatar:
4847 avatar_thumbnails.append({
4848 'url': uncropped_avatar,
4849 'id': 'avatar_uncropped',
4850 'preference': 1
4851 })
4852
4853 channel_banners = self._extract_thumbnails(
4854 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4855 for banner in channel_banners:
4856 banner['preference'] = -10
4857
4858 if channel_banners:
4859 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4860 if uncropped_banner:
4861 channel_banners.append({
4862 'url': uncropped_banner,
4863 'id': 'banner_uncropped',
4864 'preference': -5
4865 })
4866
4867 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4868 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4869 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4870
4871 primary_thumbnails = self._extract_thumbnails(
4872 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4873 playlist_thumbnails = self._extract_thumbnails(
4874 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4875
4876 info.update({
4877 'title': (traverse_obj(metadata_renderer, 'title')
4878 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4879 or info['id']),
4880 'availability': self._extract_availability(data),
4881 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4882 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4883 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4884 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4885 })
4886
4887 # Playlist stats is a text runs array containing [video count, view count, last updated].
4888 # last updated or (view count and last updated) may be missing.
4889 playlist_stats = get_first(
4890 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4891
4892 last_updated_unix = self._parse_time_text(
4893 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4894 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4895 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
4896
4897 info['view_count'] = self._get_count(playlist_stats, 1)
4898 if info['view_count'] is None: # 0 is allowed
4899 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4900 if info['view_count'] is None:
4901 info['view_count'] = self._get_count(data, (
4902 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4903 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4904
4905 info['playlist_count'] = self._get_count(playlist_stats, 0)
4906 if info['playlist_count'] is None: # 0 is allowed
4907 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4908
4909 if not info.get('uploader_id'):
4910 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4911 if not owner: # Deprecated
4912 owner = traverse_obj(
4913 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4914 ('videoOwner', 'videoOwnerRenderer', 'title'))
4915 owner_text = self._get_text(owner)
4916 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4917 info.update({
4918 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4919 'uploader_id': browse_ep.get('browseId'),
4920 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4921 })
4922
4923 info.update({
4924 'channel': info['uploader'],
4925 'channel_id': info['uploader_id'],
4926 'channel_url': info['uploader_url']
4927 })
4928 return info
4929
4930 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4931 first_id = last_id = response = None
4932 for page_num in itertools.count(1):
4933 videos = list(self._playlist_entries(playlist))
4934 if not videos:
4935 return
4936 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4937 if start >= len(videos):
4938 return
4939 yield from videos[start:]
4940 first_id = first_id or videos[0]['id']
4941 last_id = videos[-1]['id']
4942 watch_endpoint = try_get(
4943 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4944 headers = self.generate_api_headers(
4945 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4946 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4947 query = {
4948 'playlistId': playlist_id,
4949 'videoId': watch_endpoint.get('videoId') or last_id,
4950 'index': watch_endpoint.get('index') or len(videos),
4951 'params': watch_endpoint.get('params') or 'OAE%3D'
4952 }
4953 response = self._extract_response(
4954 item_id='%s page %d' % (playlist_id, page_num),
4955 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4956 check_get_keys='contents'
4957 )
4958 playlist = try_get(
4959 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4960
4961 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4962 title = playlist.get('title') or try_get(
4963 data, lambda x: x['titleText']['simpleText'], str)
4964 playlist_id = playlist.get('playlistId') or item_id
4965
4966 # Delegating everything except mix playlists to regular tab-based playlist URL
4967 playlist_url = urljoin(url, try_get(
4968 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4969 str))
4970
4971 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4972 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4973 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4974
4975 if playlist_url and playlist_url != url and not is_known_unviewable:
4976 return self.url_result(
4977 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4978 video_title=title)
4979
4980 return self.playlist_result(
4981 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4982 playlist_id=playlist_id, playlist_title=title)
4983
4984 def _extract_availability(self, data):
4985 """
4986 Gets the availability of a given playlist/tab.
4987 Note: Unless YouTube tells us explicitly, we do not assume it is public
4988 @param data: response
4989 """
4990 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4991 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4992 player_header_privacy = playlist_header_renderer.get('privacy')
4993
4994 badges = self._extract_badges(sidebar_renderer)
4995
4996 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4997 privacy_setting_icon = get_first(
4998 (playlist_header_renderer, sidebar_renderer),
4999 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5000 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5001 expected_type=str)
5002
5003 microformats_is_unlisted = traverse_obj(
5004 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
5005
5006 return (
5007 'public' if (
5008 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5009 or player_header_privacy == 'PUBLIC'
5010 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5011 else self._availability(
5012 is_private=(
5013 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5014 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5015 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5016 is_unlisted=(
5017 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5018 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
5019 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5020 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
5021 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5022 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5023 needs_auth=False))
5024
5025 @staticmethod
5026 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5027 sidebar_renderer = try_get(
5028 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5029 for item in sidebar_renderer:
5030 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5031 if renderer:
5032 return renderer
5033
5034 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
5035 """
5036 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5037 """
5038 is_playlist = bool(traverse_obj(
5039 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5040 if not is_playlist:
5041 return
5042 headers = self.generate_api_headers(
5043 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5044 visitor_data=self._extract_visitor_data(data, ytcfg))
5045 query = {
5046 'params': 'wgYCCAA=',
5047 'browseId': f'VL{item_id}'
5048 }
5049 return self._extract_response(
5050 item_id=item_id, headers=headers, query=query,
5051 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
5052 note='Redownloading playlist API JSON with unavailable videos')
5053
5054 @functools.cached_property
5055 def skip_webpage(self):
5056 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5057
5058 def _extract_webpage(self, url, item_id, fatal=True):
5059 webpage, data = None, None
5060 for retry in self.RetryManager(fatal=fatal):
5061 try:
5062 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
5063 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5064 except ExtractorError as e:
5065 if isinstance(e.cause, network_exceptions):
5066 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
5067 retry.error = e
5068 continue
5069 self._error_or_warning(e, fatal=fatal)
5070 break
5071
5072 try:
5073 self._extract_and_report_alerts(data)
5074 except ExtractorError as e:
5075 self._error_or_warning(e, fatal=fatal)
5076 break
5077
5078 # Sometimes youtube returns a webpage with incomplete ytInitialData
5079 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5080 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5081 retry.error = ExtractorError('Incomplete yt initial data received')
5082 continue
5083
5084 return webpage, data
5085
5086 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5087 """Use if failed to extract ytcfg (and data) from initial webpage"""
5088 if not ytcfg and self.is_authenticated:
5089 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5090 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5091 raise ExtractorError(
5092 f'{msg}. If you are not downloading private content, or '
5093 'your cookies are only for the first account and channel,'
5094 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5095 expected=True)
5096 self.report_warning(msg, only_once=True)
5097
5098 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5099 data = None
5100 if not self.skip_webpage:
5101 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5102 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
5103 # Reject webpage data if redirected to home page without explicitly requesting
5104 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
5105 if (url != 'https://www.youtube.com/feed/recommended'
5106 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5107 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5108 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5109 if fatal:
5110 raise ExtractorError(msg, expected=True)
5111 self.report_warning(msg, only_once=True)
5112 if not data:
5113 self._report_playlist_authcheck(ytcfg, fatal=fatal)
5114 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5115 return data, ytcfg
5116
5117 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5118 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5119 resolve_response = self._extract_response(
5120 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5121 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5122 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5123 for ep_key, ep in endpoints.items():
5124 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5125 if params:
5126 return self._extract_response(
5127 item_id=item_id, query=params, ep=ep, headers=headers,
5128 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
5129 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5130 err_note = 'Failed to resolve url (does the playlist exist?)'
5131 if fatal:
5132 raise ExtractorError(err_note, expected=True)
5133 self.report_warning(err_note, item_id)
5134
5135 _SEARCH_PARAMS = None
5136
5137 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
5138 data = {'query': query}
5139 if params is NO_DEFAULT:
5140 params = self._SEARCH_PARAMS
5141 if params:
5142 data['params'] = params
5143
5144 content_keys = (
5145 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5146 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5147 # ytmusic search
5148 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5149 ('continuationContents', ),
5150 )
5151 display_id = f'query "{query}"'
5152 check_get_keys = tuple({keys[0] for keys in content_keys})
5153 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5154 self._report_playlist_authcheck(ytcfg, fatal=False)
5155
5156 continuation_list = [None]
5157 search = None
5158 for page_num in itertools.count(1):
5159 data.update(continuation_list[0] or {})
5160 headers = self.generate_api_headers(
5161 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
5162 search = self._extract_response(
5163 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5164 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
5165 slr_contents = traverse_obj(search, *content_keys)
5166 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
5167 if not continuation_list[0]:
5168 break
5169
5170
5171 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5172 IE_DESC = 'YouTube Tabs'
5173 _VALID_URL = r'''(?x:
5174 https?://
5175 (?!consent\.)(?:\w+\.)?
5176 (?:
5177 youtube(?:kids)?\.com|
5178 %(invidious)s
5179 )/
5180 (?:
5181 (?P<channel_type>channel|c|user|browse)/|
5182 (?P<not_channel>
5183 feed/|hashtag/|
5184 (?:playlist|watch)\?.*?\blist=
5185 )|
5186 (?!(?:%(reserved_names)s)\b) # Direct URLs
5187 )
5188 (?P<id>[^/?\#&]+)
5189 )''' % {
5190 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5191 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5192 }
5193 IE_NAME = 'youtube:tab'
5194
5195 _TESTS = [{
5196 'note': 'playlists, multipage',
5197 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5198 'playlist_mincount': 94,
5199 'info_dict': {
5200 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5201 'title': 'Igor Kleiner - Playlists',
5202 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5203 'uploader': 'Igor Kleiner',
5204 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5205 'channel': 'Igor Kleiner',
5206 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5207 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5208 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5209 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5210 'channel_follower_count': int
5211 },
5212 }, {
5213 'note': 'playlists, multipage, different order',
5214 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5215 'playlist_mincount': 94,
5216 'info_dict': {
5217 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5218 'title': 'Igor Kleiner - Playlists',
5219 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5220 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5221 'uploader': 'Igor Kleiner',
5222 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5223 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5224 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5225 'channel': 'Igor Kleiner',
5226 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5227 'channel_follower_count': int
5228 },
5229 }, {
5230 'note': 'playlists, series',
5231 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5232 'playlist_mincount': 5,
5233 'info_dict': {
5234 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5235 'title': '3Blue1Brown - Playlists',
5236 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5237 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5238 'uploader': '3Blue1Brown',
5239 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5240 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5241 'channel': '3Blue1Brown',
5242 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5243 'tags': ['Mathematics'],
5244 'channel_follower_count': int
5245 },
5246 }, {
5247 'note': 'playlists, singlepage',
5248 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5249 'playlist_mincount': 4,
5250 'info_dict': {
5251 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5252 'title': 'ThirstForScience - Playlists',
5253 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5254 'uploader': 'ThirstForScience',
5255 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5256 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5257 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5258 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5259 'tags': 'count:13',
5260 'channel': 'ThirstForScience',
5261 'channel_follower_count': int
5262 }
5263 }, {
5264 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5265 'only_matching': True,
5266 }, {
5267 'note': 'basic, single video playlist',
5268 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5269 'info_dict': {
5270 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5271 'uploader': 'Sergey M.',
5272 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5273 'title': 'youtube-dl public playlist',
5274 'description': '',
5275 'tags': [],
5276 'view_count': int,
5277 'modified_date': '20201130',
5278 'channel': 'Sergey M.',
5279 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5280 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5281 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5282 'availability': 'public',
5283 },
5284 'playlist_count': 1,
5285 }, {
5286 'note': 'empty playlist',
5287 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5288 'info_dict': {
5289 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5290 'uploader': 'Sergey M.',
5291 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5292 'title': 'youtube-dl empty playlist',
5293 'tags': [],
5294 'channel': 'Sergey M.',
5295 'description': '',
5296 'modified_date': '20160902',
5297 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5298 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5299 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5300 'availability': 'public',
5301 },
5302 'playlist_count': 0,
5303 }, {
5304 'note': 'Home tab',
5305 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5306 'info_dict': {
5307 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5308 'title': 'lex will - Home',
5309 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5310 'uploader': 'lex will',
5311 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5312 'channel': 'lex will',
5313 'tags': ['bible', 'history', 'prophesy'],
5314 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5315 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5316 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5317 'channel_follower_count': int
5318 },
5319 'playlist_mincount': 2,
5320 }, {
5321 'note': 'Videos tab',
5322 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5323 'info_dict': {
5324 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5325 'title': 'lex will - Videos',
5326 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5327 'uploader': 'lex will',
5328 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5329 'tags': ['bible', 'history', 'prophesy'],
5330 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5331 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5332 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5333 'channel': 'lex will',
5334 'channel_follower_count': int
5335 },
5336 'playlist_mincount': 975,
5337 }, {
5338 'note': 'Videos tab, sorted by popular',
5339 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5340 'info_dict': {
5341 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5342 'title': 'lex will - Videos',
5343 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5344 'uploader': 'lex will',
5345 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5346 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5347 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5348 'channel': 'lex will',
5349 'tags': ['bible', 'history', 'prophesy'],
5350 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5351 'channel_follower_count': int
5352 },
5353 'playlist_mincount': 199,
5354 }, {
5355 'note': 'Playlists tab',
5356 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5357 'info_dict': {
5358 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5359 'title': 'lex will - Playlists',
5360 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5361 'uploader': 'lex will',
5362 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5363 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5364 'channel': 'lex will',
5365 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5366 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5367 'tags': ['bible', 'history', 'prophesy'],
5368 'channel_follower_count': int
5369 },
5370 'playlist_mincount': 17,
5371 }, {
5372 'note': 'Community tab',
5373 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5374 'info_dict': {
5375 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5376 'title': 'lex will - Community',
5377 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5378 'uploader': 'lex will',
5379 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5380 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5381 'channel': 'lex will',
5382 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5383 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5384 'tags': ['bible', 'history', 'prophesy'],
5385 'channel_follower_count': int
5386 },
5387 'playlist_mincount': 18,
5388 }, {
5389 'note': 'Channels tab',
5390 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5391 'info_dict': {
5392 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5393 'title': 'lex will - Channels',
5394 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5395 'uploader': 'lex will',
5396 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5397 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5398 'channel': 'lex will',
5399 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5400 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5401 'tags': ['bible', 'history', 'prophesy'],
5402 'channel_follower_count': int
5403 },
5404 'playlist_mincount': 12,
5405 }, {
5406 'note': 'Search tab',
5407 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5408 'playlist_mincount': 40,
5409 'info_dict': {
5410 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5411 'title': '3Blue1Brown - Search - linear algebra',
5412 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5413 'uploader': '3Blue1Brown',
5414 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5415 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5416 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5417 'tags': ['Mathematics'],
5418 'channel': '3Blue1Brown',
5419 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5420 'channel_follower_count': int
5421 },
5422 }, {
5423 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5424 'only_matching': True,
5425 }, {
5426 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5427 'only_matching': True,
5428 }, {
5429 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5430 'only_matching': True,
5431 }, {
5432 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5433 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5434 'info_dict': {
5435 'title': '29C3: Not my department',
5436 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5437 'uploader': 'Christiaan008',
5438 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5439 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5440 'tags': [],
5441 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5442 'view_count': int,
5443 'modified_date': '20150605',
5444 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5445 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5446 'channel': 'Christiaan008',
5447 'availability': 'public',
5448 },
5449 'playlist_count': 96,
5450 }, {
5451 'note': 'Large playlist',
5452 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5453 'info_dict': {
5454 'title': 'Uploads from Cauchemar',
5455 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5456 'uploader': 'Cauchemar',
5457 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5458 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5459 'tags': [],
5460 'modified_date': r're:\d{8}',
5461 'channel': 'Cauchemar',
5462 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5463 'view_count': int,
5464 'description': '',
5465 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5466 'availability': 'public',
5467 },
5468 'playlist_mincount': 1123,
5469 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5470 }, {
5471 'note': 'even larger playlist, 8832 videos',
5472 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5473 'only_matching': True,
5474 }, {
5475 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5476 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5477 'info_dict': {
5478 'title': 'Uploads from Interstellar Movie',
5479 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5480 'uploader': 'Interstellar Movie',
5481 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5482 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5483 'tags': [],
5484 'view_count': int,
5485 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5486 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5487 'channel': 'Interstellar Movie',
5488 'description': '',
5489 'modified_date': r're:\d{8}',
5490 'availability': 'public',
5491 },
5492 'playlist_mincount': 21,
5493 }, {
5494 'note': 'Playlist with "show unavailable videos" button',
5495 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5496 'info_dict': {
5497 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5498 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5499 'uploader': 'Phim Siêu Nhân Nhật Bản',
5500 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5501 'view_count': int,
5502 'channel': 'Phim Siêu Nhân Nhật Bản',
5503 'tags': [],
5504 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5505 'description': '',
5506 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5507 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5508 'modified_date': r're:\d{8}',
5509 'availability': 'public',
5510 },
5511 'playlist_mincount': 200,
5512 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5513 }, {
5514 'note': 'Playlist with unavailable videos in page 7',
5515 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5516 'info_dict': {
5517 'title': 'Uploads from BlankTV',
5518 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5519 'uploader': 'BlankTV',
5520 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5521 'channel': 'BlankTV',
5522 'channel_url': 'https://www.youtube.com/c/blanktv',
5523 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5524 'view_count': int,
5525 'tags': [],
5526 'uploader_url': 'https://www.youtube.com/c/blanktv',
5527 'modified_date': r're:\d{8}',
5528 'description': '',
5529 'availability': 'public',
5530 },
5531 'playlist_mincount': 1000,
5532 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5533 }, {
5534 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5535 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5536 'info_dict': {
5537 'title': 'Data Analysis with Dr Mike Pound',
5538 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5539 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5540 'uploader': 'Computerphile',
5541 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5542 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5543 'tags': [],
5544 'view_count': int,
5545 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5546 'channel_url': 'https://www.youtube.com/user/Computerphile',
5547 'channel': 'Computerphile',
5548 'availability': 'public',
5549 'modified_date': '20190712',
5550 },
5551 'playlist_mincount': 11,
5552 }, {
5553 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5554 'only_matching': True,
5555 }, {
5556 'note': 'Playlist URL that does not actually serve a playlist',
5557 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5558 'info_dict': {
5559 'id': 'FqZTN594JQw',
5560 'ext': 'webm',
5561 'title': "Smiley's People 01 detective, Adventure Series, Action",
5562 'uploader': 'STREEM',
5563 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5564 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5565 'upload_date': '20150526',
5566 'license': 'Standard YouTube License',
5567 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5568 'categories': ['People & Blogs'],
5569 'tags': list,
5570 'view_count': int,
5571 'like_count': int,
5572 },
5573 'params': {
5574 'skip_download': True,
5575 },
5576 'skip': 'This video is not available.',
5577 'add_ie': [YoutubeIE.ie_key()],
5578 }, {
5579 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5580 'only_matching': True,
5581 }, {
5582 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5583 'only_matching': True,
5584 }, {
5585 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5586 'info_dict': {
5587 'id': 'Wq15eF5vCbI', # This will keep changing
5588 'ext': 'mp4',
5589 'title': str,
5590 'uploader': 'Sky News',
5591 'uploader_id': 'skynews',
5592 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5593 'upload_date': r're:\d{8}',
5594 'description': str,
5595 'categories': ['News & Politics'],
5596 'tags': list,
5597 'like_count': int,
5598 'release_timestamp': int,
5599 'channel': 'Sky News',
5600 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5601 'age_limit': 0,
5602 'view_count': int,
5603 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5604 'playable_in_embed': True,
5605 'release_date': r're:\d+',
5606 'availability': 'public',
5607 'live_status': 'is_live',
5608 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5609 'channel_follower_count': int,
5610 'concurrent_view_count': int,
5611 },
5612 'params': {
5613 'skip_download': True,
5614 },
5615 'expected_warnings': ['Ignoring subtitle tracks found in '],
5616 }, {
5617 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5618 'info_dict': {
5619 'id': 'a48o2S1cPoo',
5620 'ext': 'mp4',
5621 'title': 'The Young Turks - Live Main Show',
5622 'uploader': 'The Young Turks',
5623 'uploader_id': 'TheYoungTurks',
5624 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5625 'upload_date': '20150715',
5626 'license': 'Standard YouTube License',
5627 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5628 'categories': ['News & Politics'],
5629 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5630 'like_count': int,
5631 },
5632 'params': {
5633 'skip_download': True,
5634 },
5635 'only_matching': True,
5636 }, {
5637 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5638 'only_matching': True,
5639 }, {
5640 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5641 'only_matching': True,
5642 }, {
5643 'note': 'A channel that is not live. Should raise error',
5644 'url': 'https://www.youtube.com/user/numberphile/live',
5645 'only_matching': True,
5646 }, {
5647 'url': 'https://www.youtube.com/feed/trending',
5648 'only_matching': True,
5649 }, {
5650 'url': 'https://www.youtube.com/feed/library',
5651 'only_matching': True,
5652 }, {
5653 'url': 'https://www.youtube.com/feed/history',
5654 'only_matching': True,
5655 }, {
5656 'url': 'https://www.youtube.com/feed/subscriptions',
5657 'only_matching': True,
5658 }, {
5659 'url': 'https://www.youtube.com/feed/watch_later',
5660 'only_matching': True,
5661 }, {
5662 'note': 'Recommended - redirects to home page.',
5663 'url': 'https://www.youtube.com/feed/recommended',
5664 'only_matching': True,
5665 }, {
5666 'note': 'inline playlist with not always working continuations',
5667 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5668 'only_matching': True,
5669 }, {
5670 'url': 'https://www.youtube.com/course',
5671 'only_matching': True,
5672 }, {
5673 'url': 'https://www.youtube.com/zsecurity',
5674 'only_matching': True,
5675 }, {
5676 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5677 'only_matching': True,
5678 }, {
5679 'url': 'https://www.youtube.com/TheYoungTurks/live',
5680 'only_matching': True,
5681 }, {
5682 'url': 'https://www.youtube.com/hashtag/cctv9',
5683 'info_dict': {
5684 'id': 'cctv9',
5685 'title': '#cctv9',
5686 'tags': [],
5687 },
5688 'playlist_mincount': 300, # not consistent but should be over 300
5689 }, {
5690 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5691 'only_matching': True,
5692 }, {
5693 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5694 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5695 'only_matching': True
5696 }, {
5697 'note': '/browse/ should redirect to /channel/',
5698 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5699 'only_matching': True
5700 }, {
5701 'note': 'VLPL, should redirect to playlist?list=PL...',
5702 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5703 'info_dict': {
5704 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5705 'uploader': 'NoCopyrightSounds',
5706 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5707 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5708 'title': 'NCS : All Releases 💿',
5709 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5710 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5711 'modified_date': r're:\d{8}',
5712 'view_count': int,
5713 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5714 'tags': [],
5715 'channel': 'NoCopyrightSounds',
5716 'availability': 'public',
5717 },
5718 'playlist_mincount': 166,
5719 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5720 }, {
5721 'note': 'Topic, should redirect to playlist?list=UU...',
5722 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5723 'info_dict': {
5724 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5725 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5726 'title': 'Uploads from Royalty Free Music - Topic',
5727 'uploader': 'Royalty Free Music - Topic',
5728 'tags': [],
5729 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5730 'channel': 'Royalty Free Music - Topic',
5731 'view_count': int,
5732 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5733 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5734 'modified_date': r're:\d{8}',
5735 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5736 'description': '',
5737 'availability': 'public',
5738 },
5739 'playlist_mincount': 101,
5740 }, {
5741 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5742 # Treat as a general feed
5743 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5744 'info_dict': {
5745 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5746 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5747 'tags': [],
5748 },
5749 'playlist_mincount': 9,
5750 }, {
5751 'note': 'Youtube music Album',
5752 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5753 'info_dict': {
5754 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5755 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5756 'tags': [],
5757 'view_count': int,
5758 'description': '',
5759 'availability': 'unlisted',
5760 'modified_date': r're:\d{8}',
5761 },
5762 'playlist_count': 50,
5763 }, {
5764 'note': 'unlisted single video playlist',
5765 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5766 'info_dict': {
5767 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5768 'uploader': 'colethedj',
5769 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5770 'title': 'yt-dlp unlisted playlist test',
5771 'availability': 'unlisted',
5772 'tags': [],
5773 'modified_date': '20220418',
5774 'channel': 'colethedj',
5775 'view_count': int,
5776 'description': '',
5777 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5778 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5779 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5780 },
5781 'playlist_count': 1,
5782 }, {
5783 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5784 'url': 'https://www.youtube.com/feed/recommended',
5785 'info_dict': {
5786 'id': 'recommended',
5787 'title': 'recommended',
5788 'tags': [],
5789 },
5790 'playlist_mincount': 50,
5791 'params': {
5792 'skip_download': True,
5793 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5794 },
5795 }, {
5796 'note': 'API Fallback: /videos tab, sorted by oldest first',
5797 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5798 'info_dict': {
5799 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5800 'title': 'Cody\'sLab - Videos',
5801 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5802 'uploader': 'Cody\'sLab',
5803 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5804 'channel': 'Cody\'sLab',
5805 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5806 'tags': [],
5807 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5808 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5809 'channel_follower_count': int
5810 },
5811 'playlist_mincount': 650,
5812 'params': {
5813 'skip_download': True,
5814 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5815 },
5816 'skip': 'Query for sorting no longer works',
5817 }, {
5818 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5819 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5820 'info_dict': {
5821 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5822 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5823 'title': 'Uploads from Royalty Free Music - Topic',
5824 'uploader': 'Royalty Free Music - Topic',
5825 'modified_date': r're:\d{8}',
5826 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5827 'description': '',
5828 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5829 'tags': [],
5830 'channel': 'Royalty Free Music - Topic',
5831 'view_count': int,
5832 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5833 'availability': 'public',
5834 },
5835 'playlist_mincount': 101,
5836 'params': {
5837 'skip_download': True,
5838 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5839 },
5840 }, {
5841 'note': 'non-standard redirect to regional channel',
5842 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5843 'only_matching': True
5844 }, {
5845 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5846 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5847 'info_dict': {
5848 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5849 'modified_date': '20220407',
5850 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5851 'tags': [],
5852 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5853 'uploader': 'pukkandan',
5854 'availability': 'unlisted',
5855 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5856 'channel': 'pukkandan',
5857 'description': 'Test for collaborative playlist',
5858 'title': 'yt-dlp test - collaborative playlist',
5859 'view_count': int,
5860 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5861 },
5862 'playlist_mincount': 2
5863 }, {
5864 'note': 'translated tab name',
5865 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5866 'info_dict': {
5867 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5868 'tags': [],
5869 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5870 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5871 'description': 'test description',
5872 'title': 'cole-dlp-test-acc - 再生リスト',
5873 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5874 'uploader': 'cole-dlp-test-acc',
5875 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5876 'channel': 'cole-dlp-test-acc',
5877 },
5878 'playlist_mincount': 1,
5879 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5880 'expected_warnings': ['Preferring "ja"'],
5881 }, {
5882 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5883 'note': 'preferred lang set with playlist with translated video titles',
5884 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5885 'info_dict': {
5886 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5887 'tags': [],
5888 'view_count': int,
5889 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5890 'uploader': 'cole-dlp-test-acc',
5891 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5892 'channel': 'cole-dlp-test-acc',
5893 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5894 'description': 'test',
5895 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5896 'title': 'dlp test playlist',
5897 'availability': 'public',
5898 },
5899 'playlist_mincount': 1,
5900 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5901 'expected_warnings': ['Preferring "ja"'],
5902 }, {
5903 # shorts audio pivot for 2GtVksBMYFM.
5904 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5905 'info_dict': {
5906 'id': 'sfv_audio_pivot',
5907 'title': 'sfv_audio_pivot',
5908 'tags': [],
5909 },
5910 'playlist_mincount': 50,
5911
5912 }, {
5913 # Channel with a real live tab (not to be mistaken with streams tab)
5914 # Do not treat like it should redirect to live stream
5915 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5916 'info_dict': {
5917 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5918 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5919 'tags': [],
5920 },
5921 'playlist_mincount': 20,
5922 }, {
5923 # Tab name is not the same as tab id
5924 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5925 'info_dict': {
5926 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5927 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5928 'tags': [],
5929 },
5930 'playlist_mincount': 8,
5931 }, {
5932 # Home tab id is literally home. Not to get mistaken with featured
5933 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5934 'info_dict': {
5935 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5936 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5937 'tags': [],
5938 },
5939 'playlist_mincount': 8,
5940 }, {
5941 # Should get three playlists for videos, shorts and streams tabs
5942 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5943 'info_dict': {
5944 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5945 'title': 'Polka Ch. 尾丸ポルカ',
5946 'channel_follower_count': int,
5947 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5948 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5949 'uploader': 'Polka Ch. 尾丸ポルカ',
5950 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5951 'channel': 'Polka Ch. 尾丸ポルカ',
5952 'tags': 'count:35',
5953 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5954 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5955 },
5956 'playlist_count': 3,
5957 }, {
5958 # Shorts tab with channel with handle
5959 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5960 'info_dict': {
5961 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5962 'title': 'Not Just Bikes - Shorts',
5963 'tags': 'count:12',
5964 'uploader': 'Not Just Bikes',
5965 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5966 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5967 'channel_follower_count': int,
5968 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5969 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5970 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5971 'channel': 'Not Just Bikes',
5972 },
5973 'playlist_mincount': 10,
5974 }, {
5975 # Streams tab
5976 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5977 'info_dict': {
5978 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5979 'title': '中村悠一 - Live',
5980 'tags': 'count:7',
5981 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5982 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5983 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5984 'channel': '中村悠一',
5985 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5986 'channel_follower_count': int,
5987 'uploader': '中村悠一',
5988 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5989 },
5990 'playlist_mincount': 60,
5991 }, {
5992 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5993 # See test_youtube_lists
5994 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5995 'only_matching': True,
5996 }, {
5997 # No uploads and no UCID given. Should fail with no uploads error
5998 # See test_youtube_lists
5999 'url': 'https://www.youtube.com/news',
6000 'only_matching': True
6001 }, {
6002 # No videos tab but has a shorts tab
6003 'url': 'https://www.youtube.com/c/TKFShorts',
6004 'info_dict': {
6005 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6006 'title': 'Shorts Break - Shorts',
6007 'tags': 'count:32',
6008 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6009 'channel': 'Shorts Break',
6010 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
6011 'uploader': 'Shorts Break',
6012 'channel_follower_count': int,
6013 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6014 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6015 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6016 },
6017 'playlist_mincount': 30,
6018 }, {
6019 # Trending Now Tab. tab id is empty
6020 'url': 'https://www.youtube.com/feed/trending',
6021 'info_dict': {
6022 'id': 'trending',
6023 'title': 'trending - Now',
6024 'tags': [],
6025 },
6026 'playlist_mincount': 30,
6027 }, {
6028 # Trending Gaming Tab. tab id is empty
6029 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6030 'info_dict': {
6031 'id': 'trending',
6032 'title': 'trending - Gaming',
6033 'tags': [],
6034 },
6035 'playlist_mincount': 30,
6036 }, {
6037 # Shorts url result in shorts tab
6038 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6039 'info_dict': {
6040 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6041 'title': 'cole-dlp-test-acc - Shorts',
6042 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6043 'channel': 'cole-dlp-test-acc',
6044 'description': 'test description',
6045 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6046 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6047 'tags': [],
6048 'uploader': 'cole-dlp-test-acc',
6049 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6050
6051 },
6052 'playlist': [{
6053 'info_dict': {
6054 '_type': 'url',
6055 'ie_key': 'Youtube',
6056 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6057 'id': 'sSM9J5YH_60',
6058 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6059 'title': 'SHORT short',
6060 'channel': 'cole-dlp-test-acc',
6061 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6062 'view_count': int,
6063 'thumbnails': list,
6064 }
6065 }],
6066 'params': {'extract_flat': True},
6067 }, {
6068 # Live video status should be extracted
6069 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6070 'info_dict': {
6071 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6072 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6073 'tags': []
6074 },
6075 'playlist': [{
6076 'info_dict': {
6077 '_type': 'url',
6078 'ie_key': 'Youtube',
6079 'url': 'startswith:https://www.youtube.com/watch?v=',
6080 'id': str,
6081 'title': str,
6082 'live_status': 'is_live',
6083 'channel_id': str,
6084 'channel_url': str,
6085 'concurrent_view_count': int,
6086 'channel': str,
6087 }
6088 }],
6089 'params': {'extract_flat': True, 'playlist_items': '1'},
6090 'playlist_mincount': 1
6091 }, {
6092 # Channel renderer metadata. Contains number of videos on the channel
6093 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6094 'info_dict': {
6095 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6096 'title': 'cole-dlp-test-acc - Channels',
6097 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6098 'channel': 'cole-dlp-test-acc',
6099 'description': 'test description',
6100 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6101 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6102 'tags': [],
6103 'uploader': 'cole-dlp-test-acc',
6104 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6105
6106 },
6107 'playlist': [{
6108 'info_dict': {
6109 '_type': 'url',
6110 'ie_key': 'YoutubeTab',
6111 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6112 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6113 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6114 'title': 'PewDiePie',
6115 'channel': 'PewDiePie',
6116 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6117 'thumbnails': list,
6118 'channel_follower_count': int,
6119 'playlist_count': int
6120 }
6121 }],
6122 'params': {'extract_flat': True},
6123 }, {
6124 'url': 'https://www.youtube.com/@3blue1brown/about',
6125 'info_dict': {
6126 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6127 'tags': ['Mathematics'],
6128 'title': '3Blue1Brown - About',
6129 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6130 'channel_follower_count': int,
6131 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6132 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6133 'channel': '3Blue1Brown',
6134 'uploader': '3Blue1Brown',
6135 'view_count': int,
6136 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6137 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6138 },
6139 'playlist_count': 0,
6140 }]
6141
6142 @classmethod
6143 def suitable(cls, url):
6144 return False if YoutubeIE.suitable(url) else super().suitable(url)
6145
6146 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6147
6148 def _get_url_mobj(self, url):
6149 mobj = self._URL_RE.match(url).groupdict()
6150 mobj.update((k, '') for k, v in mobj.items() if v is None)
6151 return mobj
6152
6153 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6154 tab_name = (tab.get('title') or '').lower()
6155 tab_url = urljoin(base_url, traverse_obj(
6156 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6157
6158 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6159 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
6160 if tab_id:
6161 return {
6162 'TAB_ID_SPONSORSHIPS': 'membership',
6163 }.get(tab_id, tab_id), tab_name
6164
6165 # Fallback to tab name if we cannot get the tab id.
6166 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6167 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6168 if tab_name:
6169 self.write_debug(f'Falling back to selected tab name: {tab_name}')
6170 return {
6171 'home': 'featured',
6172 'live': 'streams',
6173 }.get(tab_name, tab_name), tab_name
6174
6175 def _has_tab(self, tabs, tab_id):
6176 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
6177
6178 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6179 def _real_extract(self, url, smuggled_data):
6180 item_id = self._match_id(url)
6181 url = urllib.parse.urlunparse(
6182 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
6183 compat_opts = self.get_param('compat_opts', [])
6184
6185 mobj = self._get_url_mobj(url)
6186 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
6187 if is_channel and smuggled_data.get('is_music_url'):
6188 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6189 return self.url_result(
6190 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6191 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6192 mdata = self._extract_tab_endpoint(
6193 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6194 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6195 get_all=False, expected_type=str)
6196 if not murl:
6197 raise ExtractorError('Failed to resolve album to playlist')
6198 return self.url_result(murl, YoutubeTabIE)
6199 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6200 return self.url_result(
6201 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6202
6203 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
6204 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
6205 url = f'{pre}/videos{post}'
6206 if smuggled_data.get('is_music_url'):
6207 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
6208
6209 # Handle both video/playlist URLs
6210 qs = parse_qs(url)
6211 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
6212 if not video_id and mobj['not_channel'].startswith('watch'):
6213 if not playlist_id:
6214 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6215 raise ExtractorError('A video URL was given without video ID', expected=True)
6216 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6217 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6218 return self.url_result(
6219 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
6220
6221 if not self._yes_playlist(playlist_id, video_id):
6222 return self.url_result(
6223 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6224
6225 data, ytcfg = self._extract_data(url, display_id)
6226
6227 # YouTube may provide a non-standard redirect to the regional channel
6228 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6229 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6230 redirect_url = traverse_obj(
6231 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6232 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
6233 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
6234 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6235 return self.url_result(redirect_url, YoutubeTabIE)
6236
6237 tabs, extra_tabs = self._extract_tab_renderers(data), []
6238 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
6239 selected_tab = self._extract_selected_tab(tabs)
6240 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6241 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6242
6243 if not original_tab_id and selected_tab_name:
6244 self.to_screen('Downloading all uploads of the channel. '
6245 'To download only the videos in a specific tab, pass the tab\'s URL')
6246 if self._has_tab(tabs, 'streams'):
6247 extra_tabs.append(''.join((pre, '/streams', post)))
6248 if self._has_tab(tabs, 'shorts'):
6249 extra_tabs.append(''.join((pre, '/shorts', post)))
6250 # XXX: Members-only tab should also be extracted
6251
6252 if not extra_tabs and selected_tab_id != 'videos':
6253 # Channel does not have streams, shorts or videos tabs
6254 if item_id[:2] != 'UC':
6255 raise ExtractorError('This channel has no uploads', expected=True)
6256
6257 # Topic channels don't have /videos. Use the equivalent playlist instead
6258 pl_id = f'UU{item_id[2:]}'
6259 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6260 try:
6261 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6262 except ExtractorError:
6263 raise ExtractorError('This channel has no uploads', expected=True)
6264 else:
6265 item_id, url = pl_id, pl_url
6266 self.to_screen(
6267 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6268
6269 elif extra_tabs and selected_tab_id != 'videos':
6270 # When there are shorts/live tabs but not videos tab
6271 url, data = f'{pre}{post}', None
6272
6273 elif (original_tab_id or 'videos') != selected_tab_id:
6274 if original_tab_id == 'live':
6275 # Live tab should have redirected to the video
6276 # Except in the case the channel has an actual live tab
6277 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6278 raise UserNotLive(video_id=item_id)
6279 elif selected_tab_name:
6280 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6281
6282 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6283 url = f'{pre}{post}'
6284
6285 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6286 if 'no-youtube-unavailable-videos' not in compat_opts:
6287 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
6288 self._extract_and_report_alerts(data, only_once=True)
6289
6290 tabs, entries = self._extract_tab_renderers(data), []
6291 if tabs:
6292 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6293 entries[0].update({
6294 'extractor_key': YoutubeTabIE.ie_key(),
6295 'extractor': YoutubeTabIE.IE_NAME,
6296 'webpage_url': url,
6297 })
6298 if self.get_param('playlist_items') == '0':
6299 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6300 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6301 entries.extend(map(self._real_extract, extra_tabs))
6302
6303 if len(entries) == 1:
6304 return entries[0]
6305 elif entries:
6306 metadata = self._extract_metadata_from_tabs(item_id, data)
6307 uploads_url = 'the Uploads (UU) playlist URL'
6308 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6309 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6310 self.to_screen(
6311 'Downloading as multiple playlists, separated by tabs. '
6312 f'To download as a single playlist instead, pass {uploads_url}')
6313 return self.playlist_result(entries, item_id, **metadata)
6314
6315 # Inline playlist
6316 playlist = traverse_obj(
6317 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
6318 if playlist:
6319 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
6320
6321 video_id = traverse_obj(
6322 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
6323 if video_id:
6324 if tab != '/live': # live tab is expected to redirect to video
6325 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
6326 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6327
6328 raise ExtractorError('Unable to recognize tab page')
6329
6330
6331 class YoutubePlaylistIE(InfoExtractor):
6332 IE_DESC = 'YouTube playlists'
6333 _VALID_URL = r'''(?x)(?:
6334 (?:https?://)?
6335 (?:\w+\.)?
6336 (?:
6337 (?:
6338 youtube(?:kids)?\.com|
6339 %(invidious)s
6340 )
6341 /.*?\?.*?\blist=
6342 )?
6343 (?P<id>%(playlist_id)s)
6344 )''' % {
6345 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6346 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6347 }
6348 IE_NAME = 'youtube:playlist'
6349 _TESTS = [{
6350 'note': 'issue #673',
6351 'url': 'PLBB231211A4F62143',
6352 'info_dict': {
6353 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6354 'id': 'PLBB231211A4F62143',
6355 'uploader': 'Wickman',
6356 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6357 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6358 'view_count': int,
6359 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6360 'modified_date': r're:\d{8}',
6361 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6362 'channel': 'Wickman',
6363 'tags': [],
6364 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6365 'availability': 'public',
6366 },
6367 'playlist_mincount': 29,
6368 }, {
6369 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6370 'info_dict': {
6371 'title': 'YDL_safe_search',
6372 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6373 },
6374 'playlist_count': 2,
6375 'skip': 'This playlist is private',
6376 }, {
6377 'note': 'embedded',
6378 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6379 'playlist_count': 4,
6380 'info_dict': {
6381 'title': 'JODA15',
6382 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6383 'uploader': 'milan',
6384 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6385 'description': '',
6386 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6387 'tags': [],
6388 'modified_date': '20140919',
6389 'view_count': int,
6390 'channel': 'milan',
6391 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6392 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6393 'availability': 'public',
6394 },
6395 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
6396 }, {
6397 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6398 'playlist_mincount': 455,
6399 'info_dict': {
6400 'title': '2018 Chinese New Singles (11/6 updated)',
6401 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6402 'uploader': 'LBK',
6403 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6404 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6405 'channel': 'LBK',
6406 'view_count': int,
6407 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6408 'tags': [],
6409 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6410 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6411 'modified_date': r're:\d{8}',
6412 'availability': 'public',
6413 },
6414 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
6415 }, {
6416 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6417 'only_matching': True,
6418 }, {
6419 # music album playlist
6420 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6421 'only_matching': True,
6422 }]
6423
6424 @classmethod
6425 def suitable(cls, url):
6426 if YoutubeTabIE.suitable(url):
6427 return False
6428 from ..utils import parse_qs
6429 qs = parse_qs(url)
6430 if qs.get('v', [None])[0]:
6431 return False
6432 return super().suitable(url)
6433
6434 def _real_extract(self, url):
6435 playlist_id = self._match_id(url)
6436 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
6437 url = update_url_query(
6438 'https://www.youtube.com/playlist',
6439 parse_qs(url) or {'list': playlist_id})
6440 if is_music_url:
6441 url = smuggle_url(url, {'is_music_url': True})
6442 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6443
6444
6445 class YoutubeYtBeIE(InfoExtractor):
6446 IE_DESC = 'youtu.be'
6447 _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}
6448 _TESTS = [{
6449 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6450 'info_dict': {
6451 'id': 'yeWKywCrFtk',
6452 'ext': 'mp4',
6453 'title': 'Small Scale Baler and Braiding Rugs',
6454 'uploader': 'Backus-Page House Museum',
6455 'uploader_id': 'backuspagemuseum',
6456 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6457 'upload_date': '20161008',
6458 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6459 'categories': ['Nonprofits & Activism'],
6460 'tags': list,
6461 'like_count': int,
6462 'age_limit': 0,
6463 'playable_in_embed': True,
6464 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6465 'channel': 'Backus-Page House Museum',
6466 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6467 'live_status': 'not_live',
6468 'view_count': int,
6469 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6470 'availability': 'public',
6471 'duration': 59,
6472 'comment_count': int,
6473 'channel_follower_count': int
6474 },
6475 'params': {
6476 'noplaylist': True,
6477 'skip_download': True,
6478 },
6479 }, {
6480 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6481 'only_matching': True,
6482 }]
6483
6484 def _real_extract(self, url):
6485 mobj = self._match_valid_url(url)
6486 video_id = mobj.group('id')
6487 playlist_id = mobj.group('playlist_id')
6488 return self.url_result(
6489 update_url_query('https://www.youtube.com/watch', {
6490 'v': video_id,
6491 'list': playlist_id,
6492 'feature': 'youtu.be',
6493 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6494
6495
6496 class YoutubeLivestreamEmbedIE(InfoExtractor):
6497 IE_DESC = 'YouTube livestream embeds'
6498 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6499 _TESTS = [{
6500 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6501 'only_matching': True,
6502 }]
6503
6504 def _real_extract(self, url):
6505 channel_id = self._match_id(url)
6506 return self.url_result(
6507 f'https://www.youtube.com/channel/{channel_id}/live',
6508 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6509
6510
6511 class YoutubeYtUserIE(InfoExtractor):
6512 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6513 IE_NAME = 'youtube:user'
6514 _VALID_URL = r'ytuser:(?P<id>.+)'
6515 _TESTS = [{
6516 'url': 'ytuser:phihag',
6517 'only_matching': True,
6518 }]
6519
6520 def _real_extract(self, url):
6521 user_id = self._match_id(url)
6522 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
6523
6524
6525 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6526 IE_NAME = 'youtube:favorites'
6527 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6528 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6529 _LOGIN_REQUIRED = True
6530 _TESTS = [{
6531 'url': ':ytfav',
6532 'only_matching': True,
6533 }, {
6534 'url': ':ytfavorites',
6535 'only_matching': True,
6536 }]
6537
6538 def _real_extract(self, url):
6539 return self.url_result(
6540 'https://www.youtube.com/playlist?list=LL',
6541 ie=YoutubeTabIE.ie_key())
6542
6543
6544 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6545 IE_NAME = 'youtube:notif'
6546 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6547 _VALID_URL = r':ytnotif(?:ication)?s?'
6548 _LOGIN_REQUIRED = True
6549 _TESTS = [{
6550 'url': ':ytnotif',
6551 'only_matching': True,
6552 }, {
6553 'url': ':ytnotifications',
6554 'only_matching': True,
6555 }]
6556
6557 def _extract_notification_menu(self, response, continuation_list):
6558 notification_list = traverse_obj(
6559 response,
6560 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6561 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6562 expected_type=list) or []
6563 continuation_list[0] = None
6564 for item in notification_list:
6565 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6566 if entry:
6567 yield entry
6568 continuation = item.get('continuationItemRenderer')
6569 if continuation:
6570 continuation_list[0] = continuation
6571
6572 def _extract_notification_renderer(self, notification):
6573 video_id = traverse_obj(
6574 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6575 url = f'https://www.youtube.com/watch?v={video_id}'
6576 channel_id = None
6577 if not video_id:
6578 browse_ep = traverse_obj(
6579 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6580 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6581 post_id = self._search_regex(
6582 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6583 'post id', default=None)
6584 if not channel_id or not post_id:
6585 return
6586 # The direct /post url redirects to this in the browser
6587 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6588
6589 channel = traverse_obj(
6590 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6591 expected_type=str)
6592 notification_title = self._get_text(notification, 'shortMessage')
6593 if notification_title:
6594 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6595 # TODO: handle recommended videos
6596 title = self._search_regex(
6597 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6598 'video title', default=None)
6599 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6600 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6601 else None)
6602 return {
6603 '_type': 'url',
6604 'url': url,
6605 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6606 'video_id': video_id,
6607 'title': title,
6608 'channel_id': channel_id,
6609 'channel': channel,
6610 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6611 'timestamp': timestamp,
6612 }
6613
6614 def _notification_menu_entries(self, ytcfg):
6615 continuation_list = [None]
6616 response = None
6617 for page in itertools.count(1):
6618 ctoken = traverse_obj(
6619 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6620 response = self._extract_response(
6621 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6622 ep='notification/get_notification_menu', check_get_keys='actions',
6623 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6624 yield from self._extract_notification_menu(response, continuation_list)
6625 if not continuation_list[0]:
6626 break
6627
6628 def _real_extract(self, url):
6629 display_id = 'notifications'
6630 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6631 self._report_playlist_authcheck(ytcfg)
6632 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6633
6634
6635 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6636 IE_DESC = 'YouTube search'
6637 IE_NAME = 'youtube:search'
6638 _SEARCH_KEY = 'ytsearch'
6639 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6640 _TESTS = [{
6641 'url': 'ytsearch5:youtube-dl test video',
6642 'playlist_count': 5,
6643 'info_dict': {
6644 'id': 'youtube-dl test video',
6645 'title': 'youtube-dl test video',
6646 }
6647 }]
6648
6649
6650 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6651 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6652 _SEARCH_KEY = 'ytsearchdate'
6653 IE_DESC = 'YouTube search, newest videos first'
6654 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6655 _TESTS = [{
6656 'url': 'ytsearchdate5:youtube-dl test video',
6657 'playlist_count': 5,
6658 'info_dict': {
6659 'id': 'youtube-dl test video',
6660 'title': 'youtube-dl test video',
6661 }
6662 }]
6663
6664
6665 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6666 IE_DESC = 'YouTube search URLs with sorting and filter support'
6667 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6668 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6669 _TESTS = [{
6670 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6671 'playlist_mincount': 5,
6672 'info_dict': {
6673 'id': 'youtube-dl test video',
6674 'title': 'youtube-dl test video',
6675 }
6676 }, {
6677 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6678 'playlist_mincount': 5,
6679 'info_dict': {
6680 'id': 'python',
6681 'title': 'python',
6682 }
6683 }, {
6684 'url': 'https://www.youtube.com/results?search_query=%23cats',
6685 'playlist_mincount': 1,
6686 'info_dict': {
6687 'id': '#cats',
6688 'title': '#cats',
6689 # The test suite does not have support for nested playlists
6690 # 'entries': [{
6691 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6692 # 'title': '#cats',
6693 # }],
6694 },
6695 }, {
6696 # Channel results
6697 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6698 'info_dict': {
6699 'id': 'kurzgesagt',
6700 'title': 'kurzgesagt',
6701 },
6702 'playlist': [{
6703 'info_dict': {
6704 '_type': 'url',
6705 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6706 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6707 'ie_key': 'YoutubeTab',
6708 'channel': 'Kurzgesagt – In a Nutshell',
6709 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6710 'title': 'Kurzgesagt – In a Nutshell',
6711 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6712 'playlist_count': int, # XXX: should have a way of saying > 1
6713 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6714 'thumbnails': list
6715 }
6716 }],
6717 'params': {'extract_flat': True, 'playlist_items': '1'},
6718 'playlist_mincount': 1,
6719 }, {
6720 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6721 'only_matching': True,
6722 }]
6723
6724 def _real_extract(self, url):
6725 qs = parse_qs(url)
6726 query = (qs.get('search_query') or qs.get('q'))[0]
6727 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6728
6729
6730 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6731 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6732 IE_NAME = 'youtube:music:search_url'
6733 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6734 _TESTS = [{
6735 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6736 'playlist_count': 16,
6737 'info_dict': {
6738 'id': 'royalty free music',
6739 'title': 'royalty free music',
6740 }
6741 }, {
6742 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6743 'playlist_mincount': 30,
6744 'info_dict': {
6745 'id': 'royalty free music - songs',
6746 'title': 'royalty free music - songs',
6747 },
6748 'params': {'extract_flat': 'in_playlist'}
6749 }, {
6750 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6751 'playlist_mincount': 30,
6752 'info_dict': {
6753 'id': 'royalty free music - community playlists',
6754 'title': 'royalty free music - community playlists',
6755 },
6756 'params': {'extract_flat': 'in_playlist'}
6757 }]
6758
6759 _SECTIONS = {
6760 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6761 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6762 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6763 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6764 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6765 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6766 }
6767
6768 def _real_extract(self, url):
6769 qs = parse_qs(url)
6770 query = (qs.get('search_query') or qs.get('q'))[0]
6771 params = qs.get('sp', (None,))[0]
6772 if params:
6773 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6774 else:
6775 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6776 params = self._SECTIONS.get(section)
6777 if not params:
6778 section = None
6779 title = join_nonempty(query, section, delim=' - ')
6780 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6781
6782
6783 class YoutubeFeedsInfoExtractor(InfoExtractor):
6784 """
6785 Base class for feed extractors
6786 Subclasses must re-define the _FEED_NAME property.
6787 """
6788 _LOGIN_REQUIRED = True
6789 _FEED_NAME = 'feeds'
6790
6791 def _real_initialize(self):
6792 YoutubeBaseInfoExtractor._check_login_required(self)
6793
6794 @classproperty
6795 def IE_NAME(self):
6796 return f'youtube:{self._FEED_NAME}'
6797
6798 def _real_extract(self, url):
6799 return self.url_result(
6800 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6801
6802
6803 class YoutubeWatchLaterIE(InfoExtractor):
6804 IE_NAME = 'youtube:watchlater'
6805 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6806 _VALID_URL = r':ytwatchlater'
6807 _TESTS = [{
6808 'url': ':ytwatchlater',
6809 'only_matching': True,
6810 }]
6811
6812 def _real_extract(self, url):
6813 return self.url_result(
6814 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6815
6816
6817 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6818 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6819 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6820 _FEED_NAME = 'recommended'
6821 _LOGIN_REQUIRED = False
6822 _TESTS = [{
6823 'url': ':ytrec',
6824 'only_matching': True,
6825 }, {
6826 'url': ':ytrecommended',
6827 'only_matching': True,
6828 }, {
6829 'url': 'https://youtube.com',
6830 'only_matching': True,
6831 }]
6832
6833
6834 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6835 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6836 _VALID_URL = r':ytsub(?:scription)?s?'
6837 _FEED_NAME = 'subscriptions'
6838 _TESTS = [{
6839 'url': ':ytsubs',
6840 'only_matching': True,
6841 }, {
6842 'url': ':ytsubscriptions',
6843 'only_matching': True,
6844 }]
6845
6846
6847 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6848 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6849 _VALID_URL = r':ythis(?:tory)?'
6850 _FEED_NAME = 'history'
6851 _TESTS = [{
6852 'url': ':ythistory',
6853 'only_matching': True,
6854 }]
6855
6856
6857 class YoutubeStoriesIE(InfoExtractor):
6858 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6859 IE_NAME = 'youtube:stories'
6860 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6861 _TESTS = [{
6862 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6863 'only_matching': True,
6864 }]
6865
6866 def _real_extract(self, url):
6867 playlist_id = f'RLTD{self._match_id(url)}'
6868 return self.url_result(
6869 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6870 ie=YoutubeTabIE, video_id=playlist_id)
6871
6872
6873 class YoutubeShortsAudioPivotIE(InfoExtractor):
6874 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6875 IE_NAME = 'youtube:shorts:pivot:audio'
6876 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6877 _TESTS = [{
6878 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6879 'only_matching': True,
6880 }]
6881
6882 @staticmethod
6883 def _generate_audio_pivot_params(video_id):
6884 """
6885 Generates sfv_audio_pivot browse params for this video id
6886 """
6887 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6888 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6889
6890 def _real_extract(self, url):
6891 video_id = self._match_id(url)
6892 return self.url_result(
6893 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6894 ie=YoutubeTabIE)
6895
6896
6897 class YoutubeTruncatedURLIE(InfoExtractor):
6898 IE_NAME = 'youtube:truncated_url'
6899 IE_DESC = False # Do not list
6900 _VALID_URL = r'''(?x)
6901 (?:https?://)?
6902 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6903 (?:watch\?(?:
6904 feature=[a-z_]+|
6905 annotation_id=annotation_[^&]+|
6906 x-yt-cl=[0-9]+|
6907 hl=[^&]*|
6908 t=[0-9]+
6909 )?
6910 |
6911 attribution_link\?a=[^&]+
6912 )
6913 $
6914 '''
6915
6916 _TESTS = [{
6917 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6918 'only_matching': True,
6919 }, {
6920 'url': 'https://www.youtube.com/watch?',
6921 'only_matching': True,
6922 }, {
6923 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6924 'only_matching': True,
6925 }, {
6926 'url': 'https://www.youtube.com/watch?feature=foo',
6927 'only_matching': True,
6928 }, {
6929 'url': 'https://www.youtube.com/watch?hl=en-GB',
6930 'only_matching': True,
6931 }, {
6932 'url': 'https://www.youtube.com/watch?t=2372',
6933 'only_matching': True,
6934 }]
6935
6936 def _real_extract(self, url):
6937 raise ExtractorError(
6938 'Did you forget to quote the URL? Remember that & is a meta '
6939 'character in most shells, so you want to put the URL in quotes, '
6940 'like youtube-dl '
6941 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6942 ' or simply youtube-dl BaW_jenozKc .',
6943 expected=True)
6944
6945
6946 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6947 IE_NAME = 'youtube:clip'
6948 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6949 _TESTS = [{
6950 # FIXME: Other metadata should be extracted from the clip, not from the base video
6951 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6952 'info_dict': {
6953 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6954 'ext': 'mp4',
6955 'section_start': 29.0,
6956 'section_end': 39.7,
6957 'duration': 10.7,
6958 'age_limit': 0,
6959 'availability': 'public',
6960 'categories': ['Gaming'],
6961 'channel': 'Scott The Woz',
6962 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6963 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6964 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6965 'like_count': int,
6966 'playable_in_embed': True,
6967 'tags': 'count:17',
6968 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6969 'title': 'Mobile Games on Console - Scott The Woz',
6970 'upload_date': '20210920',
6971 'uploader': 'Scott The Woz',
6972 'uploader_id': 'scottthewoz',
6973 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6974 'view_count': int,
6975 'live_status': 'not_live',
6976 'channel_follower_count': int
6977 }
6978 }]
6979
6980 def _real_extract(self, url):
6981 clip_id = self._match_id(url)
6982 _, data = self._extract_webpage(url, clip_id)
6983
6984 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6985 if not video_id:
6986 raise ExtractorError('Unable to find video ID')
6987
6988 clip_data = traverse_obj(data, (
6989 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6990 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6991 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6992 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6993
6994 return {
6995 '_type': 'url_transparent',
6996 'url': f'https://www.youtube.com/watch?v={video_id}',
6997 'ie_key': YoutubeIE.ie_key(),
6998 'id': clip_id,
6999 'section_start': int(clip_data['startTimeMs']) / 1000,
7000 'section_end': int(clip_data['endTimeMs']) / 1000,
7001 }
7002
7003
7004 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7005 IE_NAME = 'youtube:consent'
7006 IE_DESC = False # Do not list
7007 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7008 _TESTS = [{
7009 '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',
7010 'info_dict': {
7011 'id': 'qVv6vCqciTM',
7012 'ext': 'mp4',
7013 'age_limit': 0,
7014 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7015 'comment_count': int,
7016 'chapters': 'count:13',
7017 'upload_date': '20221223',
7018 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7019 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7020 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7021 'like_count': int,
7022 'release_date': '20221223',
7023 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7024 '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】',
7025 'view_count': int,
7026 'playable_in_embed': True,
7027 'duration': 4438,
7028 'availability': 'public',
7029 'channel_follower_count': int,
7030 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7031 'categories': ['Entertainment'],
7032 'live_status': 'was_live',
7033 'release_timestamp': 1671793345,
7034 'channel': 'さなちゃんねる',
7035 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7036 'uploader': 'さなちゃんねる',
7037 },
7038 'add_ie': ['Youtube'],
7039 'params': {'skip_download': 'Youtube'},
7040 }]
7041
7042 def _real_extract(self, url):
7043 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7044 if not redirect_url:
7045 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7046 return self.url_result(redirect_url)
7047
7048
7049 class YoutubeTruncatedIDIE(InfoExtractor):
7050 IE_NAME = 'youtube:truncated_id'
7051 IE_DESC = False # Do not list
7052 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7053
7054 _TESTS = [{
7055 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7056 'only_matching': True,
7057 }]
7058
7059 def _real_extract(self, url):
7060 video_id = self._match_id(url)
7061 raise ExtractorError(
7062 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
7063 expected=True)