]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
6dc36f9b998db35131d1e8daf5f1ed84d23a3134
[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 is_pinned = bool(traverse_obj(comment_renderer, 'pinnedCommentBadge'))
3320 comment_id = comment['id']
3321 if is_pinned:
3322 tracker['pinned_comment_ids'].add(comment_id)
3323 # Sometimes YouTube may break and give us infinite looping comments.
3324 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
3325 if comment_id in tracker['seen_comment_ids']:
3326 if comment_id in tracker['pinned_comment_ids'] and not is_pinned:
3327 # Pinned comments may appear a second time in newest first sort
3328 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3329 continue
3330 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3331 yield
3332 else:
3333 tracker['seen_comment_ids'].add(comment['id'])
3334
3335 tracker['running_total'] += 1
3336 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3337 yield comment
3338
3339 # Attempt to get the replies
3340 comment_replies_renderer = try_get(
3341 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3342
3343 if comment_replies_renderer:
3344 tracker['current_page_thread'] += 1
3345 comment_entries_iter = self._comment_entries(
3346 comment_replies_renderer, ytcfg, video_id,
3347 parent=comment.get('id'), tracker=tracker)
3348 yield from itertools.islice(comment_entries_iter, min(
3349 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3350
3351 # Keeps track of counts across recursive calls
3352 if not tracker:
3353 tracker = dict(
3354 running_total=0,
3355 est_total=0,
3356 current_page_thread=0,
3357 total_parent_comments=0,
3358 total_reply_comments=0,
3359 seen_comment_ids=set(),
3360 pinned_comment_ids=set()
3361 )
3362
3363 # TODO: Deprecated
3364 # YouTube comments have a max depth of 2
3365 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3366 if max_depth:
3367 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3368 'Set max replies in the max-comments extractor argument instead')
3369 if max_depth == 1 and parent:
3370 return
3371
3372 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3373 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3374
3375 continuation = self._extract_continuation(root_continuation_data)
3376
3377 response = None
3378 is_forced_continuation = False
3379 is_first_continuation = parent is None
3380 if is_first_continuation and not continuation:
3381 # Sometimes you can get comments by generating the continuation yourself,
3382 # even if YouTube initially reports them being disabled - e.g. stories comments.
3383 # Note: if the comment section is actually disabled, YouTube may return a response with
3384 # required check_get_keys missing. So we will disable that check initially in this case.
3385 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3386 is_forced_continuation = True
3387
3388 for page_num in itertools.count(0):
3389 if not continuation:
3390 break
3391 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3392 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
3393 if page_num == 0:
3394 if is_first_continuation:
3395 note_prefix = 'Downloading comment section API JSON'
3396 else:
3397 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3398 tracker['current_page_thread'], comment_prog_str)
3399 else:
3400 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3401 ' ' if parent else '', ' replies' if parent else '',
3402 page_num, comment_prog_str)
3403 try:
3404 response = self._extract_response(
3405 item_id=None, query=continuation,
3406 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3407 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3408 except ExtractorError as e:
3409 # Ignore incomplete data error for replies if retries didn't work.
3410 # This is to allow any other parent comments and comment threads to be downloaded.
3411 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3412 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3413 self.report_warning(
3414 'Received incomplete data for a comment reply thread and retrying did not help. '
3415 'Ignoring to let other comments be downloaded.')
3416 else:
3417 raise
3418 is_forced_continuation = False
3419 continuation_contents = traverse_obj(
3420 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3421
3422 continuation = None
3423 for continuation_section in continuation_contents:
3424 continuation_items = traverse_obj(
3425 continuation_section,
3426 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3427 get_all=False, expected_type=list) or []
3428 if is_first_continuation:
3429 continuation = extract_header(continuation_items)
3430 is_first_continuation = False
3431 if continuation:
3432 break
3433 continue
3434
3435 for entry in extract_thread(continuation_items):
3436 if not entry:
3437 return
3438 yield entry
3439 continuation = self._extract_continuation({'contents': continuation_items})
3440 if continuation:
3441 break
3442
3443 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3444 if message and not parent and tracker['running_total'] == 0:
3445 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3446 raise self.CommentsDisabled
3447
3448 @staticmethod
3449 def _generate_comment_continuation(video_id):
3450 """
3451 Generates initial comment section continuation token from given video id
3452 """
3453 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3454 return base64.b64encode(token.encode()).decode()
3455
3456 def _get_comments(self, ytcfg, video_id, contents, webpage):
3457 """Entry for comment extraction"""
3458 def _real_comment_extract(contents):
3459 renderer = next((
3460 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3461 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3462 yield from self._comment_entries(renderer, ytcfg, video_id)
3463
3464 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3465 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3466
3467 @staticmethod
3468 def _get_checkok_params():
3469 return {'contentCheckOk': True, 'racyCheckOk': True}
3470
3471 @classmethod
3472 def _generate_player_context(cls, sts=None):
3473 context = {
3474 'html5Preference': 'HTML5_PREF_WANTS',
3475 }
3476 if sts is not None:
3477 context['signatureTimestamp'] = sts
3478 return {
3479 'playbackContext': {
3480 'contentPlaybackContext': context
3481 },
3482 **cls._get_checkok_params()
3483 }
3484
3485 @staticmethod
3486 def _is_agegated(player_response):
3487 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3488 return True
3489
3490 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
3491 AGE_GATE_REASONS = (
3492 'confirm your age', 'age-restricted', 'inappropriate', # reason
3493 'age_verification_required', 'age_check_required', # status
3494 )
3495 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3496
3497 @staticmethod
3498 def _is_unplayable(player_response):
3499 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3500
3501 _STORY_PLAYER_PARAMS = '8AEB'
3502
3503 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3504
3505 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3506 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3507 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3508 headers = self.generate_api_headers(
3509 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3510
3511 yt_query = {
3512 'videoId': video_id,
3513 }
3514 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3515 yt_query['params'] = self._STORY_PLAYER_PARAMS
3516
3517 yt_query.update(self._generate_player_context(sts))
3518 return self._extract_response(
3519 item_id=video_id, ep='player', query=yt_query,
3520 ytcfg=player_ytcfg, headers=headers, fatal=True,
3521 default_client=client,
3522 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3523 ) or None
3524
3525 def _get_requested_clients(self, url, smuggled_data):
3526 requested_clients = []
3527 default = ['android', 'web']
3528 allowed_clients = sorted(
3529 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3530 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3531 for client in self._configuration_arg('player_client'):
3532 if client in allowed_clients:
3533 requested_clients.append(client)
3534 elif client == 'default':
3535 requested_clients.extend(default)
3536 elif client == 'all':
3537 requested_clients.extend(allowed_clients)
3538 else:
3539 self.report_warning(f'Skipping unsupported client {client}')
3540 if not requested_clients:
3541 requested_clients = default
3542
3543 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3544 requested_clients.extend(
3545 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3546
3547 return orderedSet(requested_clients)
3548
3549 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3550 initial_pr = None
3551 if webpage:
3552 initial_pr = self._search_json(
3553 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3554
3555 all_clients = set(clients)
3556 clients = clients[::-1]
3557 prs = []
3558
3559 def append_client(*client_names):
3560 """ Append the first client name that exists but not already used """
3561 for client_name in client_names:
3562 actual_client = _split_innertube_client(client_name)[0]
3563 if actual_client in INNERTUBE_CLIENTS:
3564 if actual_client not in all_clients:
3565 clients.append(client_name)
3566 all_clients.add(actual_client)
3567 return
3568
3569 # Android player_response does not have microFormats which are needed for
3570 # extraction of some data. So we return the initial_pr with formats
3571 # stripped out even if not requested by the user
3572 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3573 if initial_pr:
3574 pr = dict(initial_pr)
3575 pr['streamingData'] = None
3576 prs.append(pr)
3577
3578 last_error = None
3579 tried_iframe_fallback = False
3580 player_url = None
3581 while clients:
3582 client, base_client, variant = _split_innertube_client(clients.pop())
3583 player_ytcfg = master_ytcfg if client == 'web' else {}
3584 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3585 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3586
3587 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3588 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3589 if 'js' in self._configuration_arg('player_skip'):
3590 require_js_player = False
3591 player_url = None
3592
3593 if not player_url and not tried_iframe_fallback and require_js_player:
3594 player_url = self._download_player_url(video_id)
3595 tried_iframe_fallback = True
3596
3597 try:
3598 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3599 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3600 except ExtractorError as e:
3601 if last_error:
3602 self.report_warning(last_error)
3603 last_error = e
3604 continue
3605
3606 if pr:
3607 # YouTube may return a different video player response than expected.
3608 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3609 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3610 if pr_video_id and pr_video_id != video_id:
3611 self.report_warning(
3612 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
3613 else:
3614 # Save client name for introspection later
3615 name = short_client_name(client)
3616 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3617 sd[STREAMING_DATA_CLIENT_NAME] = name
3618 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3619 f[STREAMING_DATA_CLIENT_NAME] = name
3620 prs.append(pr)
3621
3622 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3623 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3624 append_client(f'{base_client}_creator')
3625 elif self._is_agegated(pr):
3626 if variant == 'tv_embedded':
3627 append_client(f'{base_client}_embedded')
3628 elif not variant:
3629 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3630
3631 if last_error:
3632 if not len(prs):
3633 raise last_error
3634 self.report_warning(last_error)
3635 return prs, player_url
3636
3637 def _needs_live_processing(self, live_status, duration):
3638 if (live_status == 'is_live' and self.get_param('live_from_start')
3639 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3640 return live_status
3641
3642 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3643 CHUNK_SIZE = 10 << 20
3644 itags, stream_ids = collections.defaultdict(set), []
3645 itag_qualities, res_qualities = {}, {0: None}
3646 q = qualities([
3647 # Normally tiny is the smallest video-only formats. But
3648 # audio-only formats with unknown quality may get tagged as tiny
3649 'tiny',
3650 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3651 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3652 ])
3653 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
3654 all_formats = self._configuration_arg('include_duplicate_formats')
3655
3656 def build_fragments(f):
3657 return LazyList({
3658 'url': update_url_query(f['url'], {
3659 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3660 })
3661 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3662
3663 for fmt in streaming_formats:
3664 if fmt.get('targetDurationSec'):
3665 continue
3666
3667 itag = str_or_none(fmt.get('itag'))
3668 audio_track = fmt.get('audioTrack') or {}
3669 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
3670 if not all_formats:
3671 if stream_id in stream_ids:
3672 continue
3673
3674 quality = fmt.get('quality')
3675 height = int_or_none(fmt.get('height'))
3676 if quality == 'tiny' or not quality:
3677 quality = fmt.get('audioQuality', '').lower() or quality
3678 # The 3gp format (17) in android client has a quality of "small",
3679 # but is actually worse than other formats
3680 if itag == '17':
3681 quality = 'tiny'
3682 if quality:
3683 if itag:
3684 itag_qualities[itag] = quality
3685 if height:
3686 res_qualities[height] = quality
3687 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3688 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3689 # number of fragment that would subsequently requested with (`&sq=N`)
3690 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3691 continue
3692
3693 fmt_url = fmt.get('url')
3694 if not fmt_url:
3695 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3696 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3697 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3698 if not all((sc, fmt_url, player_url, encrypted_sig)):
3699 continue
3700 try:
3701 fmt_url += '&%s=%s' % (
3702 traverse_obj(sc, ('sp', -1)) or 'signature',
3703 self._decrypt_signature(encrypted_sig, video_id, player_url)
3704 )
3705 except ExtractorError as e:
3706 self.report_warning('Signature extraction failed: Some formats may be missing',
3707 video_id=video_id, only_once=True)
3708 self.write_debug(e, only_once=True)
3709 continue
3710
3711 query = parse_qs(fmt_url)
3712 throttled = False
3713 if query.get('n'):
3714 try:
3715 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3716 fmt_url = update_url_query(fmt_url, {
3717 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3718 })
3719 except ExtractorError as e:
3720 phantomjs_hint = ''
3721 if isinstance(e, JSInterpreter.Exception):
3722 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3723 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3724 if player_url:
3725 self.report_warning(
3726 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3727 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3728 self.write_debug(e, only_once=True)
3729 else:
3730 self.report_warning(
3731 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3732 video_id=video_id, only_once=True)
3733 throttled = True
3734
3735 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3736 language_preference = (
3737 10 if audio_track.get('audioIsDefault') and 10
3738 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3739 else -1)
3740 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3741 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3742 # Make sure to avoid false positives with small duration differences.
3743 # E.g. __2ABJjxzNo, ySuUZEjARPY
3744 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3745 if is_damaged:
3746 self.report_warning(
3747 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3748
3749 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
3750 dct = {
3751 'asr': int_or_none(fmt.get('audioSampleRate')),
3752 'filesize': int_or_none(fmt.get('contentLength')),
3753 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
3754 'format_note': join_nonempty(
3755 join_nonempty(audio_track.get('displayName'),
3756 language_preference > 0 and ' (default)', delim=''),
3757 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3758 fmt.get('isDrc') and 'DRC',
3759 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3760 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3761 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
3762 (self.get_param('verbose') or all_formats) and client_name,
3763 delim=', '),
3764 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3765 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3766 'fps': int_or_none(fmt.get('fps')) or None,
3767 'audio_channels': fmt.get('audioChannels'),
3768 'height': height,
3769 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
3770 'has_drm': bool(fmt.get('drmFamilies')),
3771 'tbr': tbr,
3772 'url': fmt_url,
3773 'width': int_or_none(fmt.get('width')),
3774 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3775 'desc' if language_preference < -1 else '') or None,
3776 'language_preference': language_preference,
3777 # Strictly de-prioritize damaged and 3gp formats
3778 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3779 }
3780 mime_mobj = re.match(
3781 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3782 if mime_mobj:
3783 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3784 dct.update(parse_codecs(mime_mobj.group(2)))
3785 if itag:
3786 itags[itag].add(('https', dct.get('language')))
3787 stream_ids.append(stream_id)
3788 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3789 if single_stream and dct.get('ext'):
3790 dct['container'] = dct['ext'] + '_dash'
3791
3792 if dct['filesize']:
3793 yield {
3794 **dct,
3795 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
3796 'protocol': 'http_dash_segments',
3797 'fragments': build_fragments(dct),
3798 }
3799 if not all_formats:
3800 continue
3801 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3802 yield dct
3803
3804 needs_live_processing = self._needs_live_processing(live_status, duration)
3805 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3806
3807 skip_manifests = set(self._configuration_arg('skip'))
3808 if (not self.get_param('youtube_include_hls_manifest', True)
3809 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3810 or needs_live_processing and skip_bad_formats):
3811 skip_manifests.add('hls')
3812
3813 if not self.get_param('youtube_include_dash_manifest', True):
3814 skip_manifests.add('dash')
3815 if self._configuration_arg('include_live_dash'):
3816 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3817 'Use include_incomplete_formats extractor argument instead')
3818 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3819 skip_manifests.add('dash')
3820
3821 def process_manifest_format(f, proto, client_name, itag):
3822 key = (proto, f.get('language'))
3823 if not all_formats and key in itags[itag]:
3824 return False
3825 itags[itag].add(key)
3826
3827 if itag and all_formats:
3828 f['format_id'] = f'{itag}-{proto}'
3829 elif any(p != proto for p, _ in itags[itag]):
3830 f['format_id'] = f'{itag}-{proto}'
3831 elif itag:
3832 f['format_id'] = itag
3833
3834 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3835 if f['quality'] == -1 and f.get('height'):
3836 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3837 if self.get_param('verbose'):
3838 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
3839 return True
3840
3841 subtitles = {}
3842 for sd in streaming_data:
3843 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3844
3845 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3846 if hls_manifest_url:
3847 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3848 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3849 subtitles = self._merge_subtitles(subs, subtitles)
3850 for f in fmts:
3851 if process_manifest_format(f, 'hls', client_name, self._search_regex(
3852 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3853 yield f
3854
3855 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3856 if dash_manifest_url:
3857 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3858 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3859 for f in formats:
3860 if process_manifest_format(f, 'dash', client_name, f['format_id']):
3861 f['filesize'] = int_or_none(self._search_regex(
3862 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3863 if needs_live_processing:
3864 f['is_from_start'] = True
3865
3866 yield f
3867 yield subtitles
3868
3869 def _extract_storyboard(self, player_responses, duration):
3870 spec = get_first(
3871 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3872 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3873 if not base_url:
3874 return
3875 L = len(spec) - 1
3876 for i, args in enumerate(spec):
3877 args = args.split('#')
3878 counts = list(map(int_or_none, args[:5]))
3879 if len(args) != 8 or not all(counts):
3880 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3881 continue
3882 width, height, frame_count, cols, rows = counts
3883 N, sigh = args[6:]
3884
3885 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3886 fragment_count = frame_count / (cols * rows)
3887 fragment_duration = duration / fragment_count
3888 yield {
3889 'format_id': f'sb{i}',
3890 'format_note': 'storyboard',
3891 'ext': 'mhtml',
3892 'protocol': 'mhtml',
3893 'acodec': 'none',
3894 'vcodec': 'none',
3895 'url': url,
3896 'width': width,
3897 'height': height,
3898 'fps': frame_count / duration,
3899 'rows': rows,
3900 'columns': cols,
3901 'fragments': [{
3902 'url': url.replace('$M', str(j)),
3903 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3904 } for j in range(math.ceil(fragment_count))],
3905 }
3906
3907 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3908 webpage = None
3909 if 'webpage' not in self._configuration_arg('player_skip'):
3910 query = {'bpctr': '9999999999', 'has_verified': '1'}
3911 if smuggled_data.get('is_story'):
3912 query['pp'] = self._STORY_PLAYER_PARAMS
3913 webpage = self._download_webpage(
3914 webpage_url, video_id, fatal=False, query=query)
3915
3916 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3917
3918 player_responses, player_url = self._extract_player_responses(
3919 self._get_requested_clients(url, smuggled_data),
3920 video_id, webpage, master_ytcfg, smuggled_data)
3921
3922 return webpage, master_ytcfg, player_responses, player_url
3923
3924 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3925 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3926 is_live = get_first(video_details, 'isLive')
3927 if is_live is None:
3928 is_live = get_first(live_broadcast_details, 'isLiveNow')
3929 live_content = get_first(video_details, 'isLiveContent')
3930 is_upcoming = get_first(video_details, 'isUpcoming')
3931 post_live = get_first(video_details, 'isPostLiveDvr')
3932 live_status = ('post_live' if post_live
3933 else 'is_live' if is_live
3934 else 'is_upcoming' if is_upcoming
3935 else 'was_live' if live_content
3936 else 'not_live' if False in (is_live, live_content)
3937 else None)
3938 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
3939 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3940
3941 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3942
3943 def _real_extract(self, url):
3944 url, smuggled_data = unsmuggle_url(url, {})
3945 video_id = self._match_id(url)
3946
3947 base_url = self.http_scheme() + '//www.youtube.com/'
3948 webpage_url = base_url + 'watch?v=' + video_id
3949
3950 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3951
3952 playability_statuses = traverse_obj(
3953 player_responses, (..., 'playabilityStatus'), expected_type=dict)
3954
3955 trailer_video_id = get_first(
3956 playability_statuses,
3957 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3958 expected_type=str)
3959 if trailer_video_id:
3960 return self.url_result(
3961 trailer_video_id, self.ie_key(), trailer_video_id)
3962
3963 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3964 if webpage else (lambda x: None))
3965
3966 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
3967 microformats = traverse_obj(
3968 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3969 expected_type=dict)
3970
3971 translated_title = self._get_text(microformats, (..., 'title'))
3972 video_title = (self._preferred_lang and translated_title
3973 or get_first(video_details, 'title') # primary
3974 or translated_title
3975 or search_meta(['og:title', 'twitter:title', 'title']))
3976 translated_description = self._get_text(microformats, (..., 'description'))
3977 original_description = get_first(video_details, 'shortDescription')
3978 video_description = (
3979 self._preferred_lang and translated_description
3980 # If original description is blank, it will be an empty string.
3981 # Do not prefer translated description in this case.
3982 or original_description if original_description is not None else translated_description)
3983
3984 multifeed_metadata_list = get_first(
3985 player_responses,
3986 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3987 expected_type=str)
3988 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3989 if self.get_param('noplaylist'):
3990 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3991 else:
3992 entries = []
3993 feed_ids = []
3994 for feed in multifeed_metadata_list.split(','):
3995 # Unquote should take place before split on comma (,) since textual
3996 # fields may contain comma as well (see
3997 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3998 feed_data = urllib.parse.parse_qs(
3999 urllib.parse.unquote_plus(feed))
4000
4001 def feed_entry(name):
4002 return try_get(
4003 feed_data, lambda x: x[name][0], str)
4004
4005 feed_id = feed_entry('id')
4006 if not feed_id:
4007 continue
4008 feed_title = feed_entry('title')
4009 title = video_title
4010 if feed_title:
4011 title += ' (%s)' % feed_title
4012 entries.append({
4013 '_type': 'url_transparent',
4014 'ie_key': 'Youtube',
4015 'url': smuggle_url(
4016 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4017 {'force_singlefeed': True}),
4018 'title': title,
4019 })
4020 feed_ids.append(feed_id)
4021 self.to_screen(
4022 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4023 % (', '.join(feed_ids), video_id))
4024 return self.playlist_result(
4025 entries, video_id, video_title, video_description)
4026
4027 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4028 or int_or_none(get_first(microformats, 'lengthSeconds'))
4029 or parse_duration(search_meta('duration')) or None)
4030
4031 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4032 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4033 if live_status == 'post_live':
4034 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
4035
4036 if not formats:
4037 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
4038 self.report_drm(video_id)
4039 pemr = get_first(
4040 playability_statuses,
4041 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4042 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4043 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
4044 if subreason:
4045 if subreason == 'The uploader has not made this video available in your country.':
4046 countries = get_first(microformats, 'availableCountries')
4047 if not countries:
4048 regions_allowed = search_meta('regionsAllowed')
4049 countries = regions_allowed.split(',') if regions_allowed else None
4050 self.raise_geo_restricted(subreason, countries, metadata_available=True)
4051 reason += f'. {subreason}'
4052 if reason:
4053 self.raise_no_formats(reason, expected=True)
4054
4055 keywords = get_first(video_details, 'keywords', expected_type=list) or []
4056 if not keywords and webpage:
4057 keywords = [
4058 unescapeHTML(m.group('content'))
4059 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4060 for keyword in keywords:
4061 if keyword.startswith('yt:stretch='):
4062 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4063 if mobj:
4064 # NB: float is intentional for forcing float division
4065 w, h = (float(v) for v in mobj.groups())
4066 if w > 0 and h > 0:
4067 ratio = w / h
4068 for f in formats:
4069 if f.get('vcodec') != 'none':
4070 f['stretched_ratio'] = ratio
4071 break
4072 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
4073 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4074 if thumbnail_url:
4075 thumbnails.append({
4076 'url': thumbnail_url,
4077 })
4078 original_thumbnails = thumbnails.copy()
4079
4080 # The best resolution thumbnails sometimes does not appear in the webpage
4081 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4082 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4083 thumbnail_names = [
4084 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4085 # in resolution, these are not the custom thumbnail. So de-prioritize them
4086 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4087 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4088 ]
4089 n_thumbnail_names = len(thumbnail_names)
4090 thumbnails.extend({
4091 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4092 video_id=video_id, name=name, ext=ext,
4093 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
4094 } for name in thumbnail_names for ext in ('webp', 'jpg'))
4095 for thumb in thumbnails:
4096 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
4097 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
4098 self._remove_duplicate_formats(thumbnails)
4099 self._downloader._sort_thumbnails(original_thumbnails)
4100
4101 category = get_first(microformats, 'category') or search_meta('genre')
4102 channel_id = str_or_none(
4103 get_first(video_details, 'channelId')
4104 or get_first(microformats, 'externalChannelId')
4105 or search_meta('channelId'))
4106 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4107
4108 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4109 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4110 if not duration and live_end_time and live_start_time:
4111 duration = live_end_time - live_start_time
4112
4113 needs_live_processing = self._needs_live_processing(live_status, duration)
4114
4115 def is_bad_format(fmt):
4116 if needs_live_processing and not fmt.get('is_from_start'):
4117 return True
4118 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4119 and fmt.get('protocol') == 'http_dash_segments'):
4120 return True
4121
4122 for fmt in filter(is_bad_format, formats):
4123 fmt['preference'] = (fmt.get('preference') or -1) - 10
4124 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4125
4126 if needs_live_processing:
4127 self._prepare_live_from_start_formats(
4128 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
4129
4130 formats.extend(self._extract_storyboard(player_responses, duration))
4131
4132 info = {
4133 'id': video_id,
4134 'title': video_title,
4135 'formats': formats,
4136 'thumbnails': thumbnails,
4137 # The best thumbnail that we are sure exists. Prevents unnecessary
4138 # URL checking if user don't care about getting the best possible thumbnail
4139 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
4140 'description': video_description,
4141 'uploader': get_first(video_details, 'author'),
4142 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
4143 'uploader_url': owner_profile_url,
4144 'channel_id': channel_id,
4145 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
4146 'duration': duration,
4147 'view_count': int_or_none(
4148 get_first((video_details, microformats), (..., 'viewCount'))
4149 or search_meta('interactionCount')),
4150 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
4151 'age_limit': 18 if (
4152 get_first(microformats, 'isFamilySafe') is False
4153 or search_meta('isFamilyFriendly') == 'false'
4154 or search_meta('og:restrictions:age') == '18+') else 0,
4155 'webpage_url': webpage_url,
4156 'categories': [category] if category else None,
4157 'tags': keywords,
4158 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4159 'live_status': live_status,
4160 'release_timestamp': live_start_time,
4161 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4162 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4163 }
4164
4165 subtitles = {}
4166 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
4167 if pctr:
4168 def get_lang_code(track):
4169 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4170 or track.get('languageCode'))
4171
4172 # Converted into dicts to remove duplicates
4173 captions = {
4174 get_lang_code(sub): sub
4175 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
4176 translation_languages = {
4177 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4178 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
4179
4180 def process_language(container, base_url, lang_code, sub_name, query):
4181 lang_subs = container.setdefault(lang_code, [])
4182 for fmt in self._SUBTITLE_FORMATS:
4183 query.update({
4184 'fmt': fmt,
4185 })
4186 lang_subs.append({
4187 'ext': fmt,
4188 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
4189 'name': sub_name,
4190 })
4191
4192 # NB: Constructing the full subtitle dictionary is slow
4193 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4194 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
4195 for lang_code, caption_track in captions.items():
4196 base_url = caption_track.get('baseUrl')
4197 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
4198 if not base_url:
4199 continue
4200 lang_name = self._get_text(caption_track, 'name', max_runs=1)
4201 if caption_track.get('kind') != 'asr':
4202 if not lang_code:
4203 continue
4204 process_language(
4205 subtitles, base_url, lang_code, lang_name, {})
4206 if not caption_track.get('isTranslatable'):
4207 continue
4208 for trans_code, trans_name in translation_languages.items():
4209 if not trans_code:
4210 continue
4211 orig_trans_code = trans_code
4212 if caption_track.get('kind') != 'asr' and trans_code != 'und':
4213 if not get_translated_subs:
4214 continue
4215 trans_code += f'-{lang_code}'
4216 trans_name += format_field(lang_name, None, ' from %s')
4217 # Add an "-orig" label to the original language so that it can be distinguished.
4218 # The subs are returned without "-orig" as well for compatibility
4219 if lang_code == f'a-{orig_trans_code}':
4220 process_language(
4221 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4222 # Setting tlang=lang returns damaged subtitles.
4223 process_language(automatic_captions, base_url, trans_code, trans_name,
4224 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
4225
4226 info['automatic_captions'] = automatic_captions
4227 info['subtitles'] = subtitles
4228
4229 parsed_url = urllib.parse.urlparse(url)
4230 for component in [parsed_url.fragment, parsed_url.query]:
4231 query = urllib.parse.parse_qs(component)
4232 for k, v in query.items():
4233 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4234 d_k += '_time'
4235 if d_k not in info and k in s_ks:
4236 info[d_k] = parse_duration(query[k][0])
4237
4238 # Youtube Music Auto-generated description
4239 if video_description:
4240 mobj = re.search(
4241 r'''(?xs)
4242 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4243 (?P<album>[^\n]+)
4244 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4245 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4246 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4247 .+\nAuto-generated\ by\ YouTube\.\s*$
4248 ''', video_description)
4249 if mobj:
4250 release_year = mobj.group('release_year')
4251 release_date = mobj.group('release_date')
4252 if release_date:
4253 release_date = release_date.replace('-', '')
4254 if not release_year:
4255 release_year = release_date[:4]
4256 info.update({
4257 'album': mobj.group('album'.strip()),
4258 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4259 'track': mobj.group('track').strip(),
4260 'release_date': release_date,
4261 'release_year': int_or_none(release_year),
4262 })
4263
4264 initial_data = None
4265 if webpage:
4266 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4267 if not traverse_obj(initial_data, 'contents'):
4268 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4269 initial_data = None
4270 if not initial_data:
4271 query = {'videoId': video_id}
4272 query.update(self._get_checkok_params())
4273 initial_data = self._extract_response(
4274 item_id=video_id, ep='next', fatal=False,
4275 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
4276 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4277 note='Downloading initial data API JSON')
4278
4279 info['comment_count'] = traverse_obj(initial_data, (
4280 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4281 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
4282 ), (
4283 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4284 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4285 ), expected_type=self._get_count, get_all=False)
4286
4287 try: # This will error if there is no livechat
4288 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4289 except (KeyError, IndexError, TypeError):
4290 pass
4291 else:
4292 info.setdefault('subtitles', {})['live_chat'] = [{
4293 # url is needed to set cookies
4294 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4295 'video_id': video_id,
4296 'ext': 'json',
4297 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4298 else 'youtube_live_chat_replay'),
4299 }]
4300
4301 if initial_data:
4302 info['chapters'] = (
4303 self._extract_chapters_from_json(initial_data, duration)
4304 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4305 or self._extract_chapters_from_description(video_description, duration)
4306 or None)
4307
4308 contents = traverse_obj(
4309 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4310 expected_type=list, default=[])
4311
4312 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4313 if vpir:
4314 stl = vpir.get('superTitleLink')
4315 if stl:
4316 stl = self._get_text(stl)
4317 if try_get(
4318 vpir,
4319 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4320 info['location'] = stl
4321 else:
4322 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4323 if mobj:
4324 info.update({
4325 'series': mobj.group(1),
4326 'season_number': int(mobj.group(2)),
4327 'episode_number': int(mobj.group(3)),
4328 })
4329 for tlb in (try_get(
4330 vpir,
4331 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4332 list) or []):
4333 tbrs = variadic(
4334 traverse_obj(
4335 tlb, ('toggleButtonRenderer', ...),
4336 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4337 for tbr in tbrs:
4338 for getter, regex in [(
4339 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4340 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4341 lambda x: x['accessibility'],
4342 lambda x: x['accessibilityData']['accessibilityData'],
4343 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4344 label = (try_get(tbr, getter, dict) or {}).get('label')
4345 if label:
4346 mobj = re.match(regex, label)
4347 if mobj:
4348 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4349 break
4350 sbr_tooltip = try_get(
4351 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4352 if sbr_tooltip:
4353 like_count, dislike_count = sbr_tooltip.split(' / ')
4354 info.update({
4355 'like_count': str_to_int(like_count),
4356 'dislike_count': str_to_int(dislike_count),
4357 })
4358 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4359 if vcr:
4360 vc = self._get_count(vcr, 'viewCount')
4361 # Upcoming premieres with waiting count are treated as live here
4362 if vcr.get('isLive'):
4363 info['concurrent_view_count'] = vc
4364 elif info.get('view_count') is None:
4365 info['view_count'] = vc
4366
4367 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4368 if vsir:
4369 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4370 info.update({
4371 'channel': self._get_text(vor, 'title'),
4372 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4373
4374 rows = try_get(
4375 vsir,
4376 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4377 list) or []
4378 multiple_songs = False
4379 for row in rows:
4380 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4381 multiple_songs = True
4382 break
4383 for row in rows:
4384 mrr = row.get('metadataRowRenderer') or {}
4385 mrr_title = mrr.get('title')
4386 if not mrr_title:
4387 continue
4388 mrr_title = self._get_text(mrr, 'title')
4389 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4390 if mrr_title == 'License':
4391 info['license'] = mrr_contents_text
4392 elif not multiple_songs:
4393 if mrr_title == 'Album':
4394 info['album'] = mrr_contents_text
4395 elif mrr_title == 'Artist':
4396 info['artist'] = mrr_contents_text
4397 elif mrr_title == 'Song':
4398 info['track'] = mrr_contents_text
4399
4400 fallbacks = {
4401 'channel': 'uploader',
4402 'channel_id': 'uploader_id',
4403 'channel_url': 'uploader_url',
4404 }
4405
4406 # The upload date for scheduled, live and past live streams / premieres in microformats
4407 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4408 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4409 upload_date = (
4410 unified_strdate(get_first(microformats, 'uploadDate'))
4411 or unified_strdate(search_meta('uploadDate')))
4412 if not upload_date or (
4413 live_status in ('not_live', None)
4414 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4415 ):
4416 upload_date = strftime_or_none(
4417 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4418 info['upload_date'] = upload_date
4419
4420 for to, frm in fallbacks.items():
4421 if not info.get(to):
4422 info[to] = info.get(frm)
4423
4424 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4425 v = info.get(s_k)
4426 if v:
4427 info[d_k] = v
4428
4429 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4430
4431 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4432 or get_first(video_details, 'isPrivate', expected_type=bool))
4433
4434 info['availability'] = (
4435 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4436 else self._availability(
4437 is_private=is_private,
4438 needs_premium=(
4439 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4440 or False if initial_data and is_private is not None else None),
4441 needs_subscription=(
4442 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4443 or False if initial_data and is_private is not None else None),
4444 needs_auth=info['age_limit'] >= 18,
4445 is_unlisted=None if is_private is None else (
4446 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4447 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4448
4449 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4450
4451 self.mark_watched(video_id, player_responses)
4452
4453 return info
4454
4455
4456 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4457 @staticmethod
4458 def passthrough_smuggled_data(func):
4459 def _smuggle(info, smuggled_data):
4460 if info.get('_type') not in ('url', 'url_transparent'):
4461 return info
4462 if smuggled_data.get('is_music_url'):
4463 parsed_url = urllib.parse.urlparse(info['url'])
4464 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4465 smuggled_data.pop('is_music_url')
4466 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4467 if smuggled_data:
4468 info['url'] = smuggle_url(info['url'], smuggled_data)
4469 return info
4470
4471 @functools.wraps(func)
4472 def wrapper(self, url):
4473 url, smuggled_data = unsmuggle_url(url, {})
4474 if self.is_music_url(url):
4475 smuggled_data['is_music_url'] = True
4476 info_dict = func(self, url, smuggled_data)
4477 if smuggled_data:
4478 _smuggle(info_dict, smuggled_data)
4479 if info_dict.get('entries'):
4480 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
4481 return info_dict
4482 return wrapper
4483
4484 @staticmethod
4485 def _extract_basic_item_renderer(item):
4486 # Modified from _extract_grid_item_renderer
4487 known_basic_renderers = (
4488 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4489 )
4490 for key, renderer in item.items():
4491 if not isinstance(renderer, dict):
4492 continue
4493 elif key in known_basic_renderers:
4494 return renderer
4495 elif key.startswith('grid') and key.endswith('Renderer'):
4496 return renderer
4497
4498 def _extract_channel_renderer(self, renderer):
4499 channel_id = renderer['channelId']
4500 title = self._get_text(renderer, 'title')
4501 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4502 return {
4503 '_type': 'url',
4504 'url': channel_url,
4505 'id': channel_id,
4506 'ie_key': YoutubeTabIE.ie_key(),
4507 'channel': title,
4508 'channel_id': channel_id,
4509 'channel_url': channel_url,
4510 'title': title,
4511 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4512 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4513 'playlist_count': self._get_count(renderer, 'videoCountText'),
4514 'description': self._get_text(renderer, 'descriptionSnippet'),
4515 }
4516
4517 def _grid_entries(self, grid_renderer):
4518 for item in grid_renderer['items']:
4519 if not isinstance(item, dict):
4520 continue
4521 renderer = self._extract_basic_item_renderer(item)
4522 if not isinstance(renderer, dict):
4523 continue
4524 title = self._get_text(renderer, 'title')
4525
4526 # playlist
4527 playlist_id = renderer.get('playlistId')
4528 if playlist_id:
4529 yield self.url_result(
4530 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4531 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4532 video_title=title)
4533 continue
4534 # video
4535 video_id = renderer.get('videoId')
4536 if video_id:
4537 yield self._extract_video(renderer)
4538 continue
4539 # channel
4540 channel_id = renderer.get('channelId')
4541 if channel_id:
4542 yield self._extract_channel_renderer(renderer)
4543 continue
4544 # generic endpoint URL support
4545 ep_url = urljoin('https://www.youtube.com/', try_get(
4546 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4547 str))
4548 if ep_url:
4549 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4550 if ie.suitable(ep_url):
4551 yield self.url_result(
4552 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4553 break
4554
4555 def _music_reponsive_list_entry(self, renderer):
4556 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4557 if video_id:
4558 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4559 ie=YoutubeIE.ie_key(), video_id=video_id)
4560 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4561 if playlist_id:
4562 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4563 if video_id:
4564 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4565 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4566 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4567 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4568 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4569 if browse_id:
4570 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4571 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4572
4573 def _shelf_entries_from_content(self, shelf_renderer):
4574 content = shelf_renderer.get('content')
4575 if not isinstance(content, dict):
4576 return
4577 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4578 if renderer:
4579 # TODO: add support for nested playlists so each shelf is processed
4580 # as separate playlist
4581 # TODO: this includes only first N items
4582 yield from self._grid_entries(renderer)
4583 renderer = content.get('horizontalListRenderer')
4584 if renderer:
4585 # TODO
4586 pass
4587
4588 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4589 ep = try_get(
4590 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4591 str)
4592 shelf_url = urljoin('https://www.youtube.com', ep)
4593 if shelf_url:
4594 # Skipping links to another channels, note that checking for
4595 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4596 # will not work
4597 if skip_channels and '/channels?' in shelf_url:
4598 return
4599 title = self._get_text(shelf_renderer, 'title')
4600 yield self.url_result(shelf_url, video_title=title)
4601 # Shelf may not contain shelf URL, fallback to extraction from content
4602 yield from self._shelf_entries_from_content(shelf_renderer)
4603
4604 def _playlist_entries(self, video_list_renderer):
4605 for content in video_list_renderer['contents']:
4606 if not isinstance(content, dict):
4607 continue
4608 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4609 if not isinstance(renderer, dict):
4610 continue
4611 video_id = renderer.get('videoId')
4612 if not video_id:
4613 continue
4614 yield self._extract_video(renderer)
4615
4616 def _rich_entries(self, rich_grid_renderer):
4617 renderer = traverse_obj(
4618 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4619 video_id = renderer.get('videoId')
4620 if not video_id:
4621 return
4622 yield self._extract_video(renderer)
4623
4624 def _video_entry(self, video_renderer):
4625 video_id = video_renderer.get('videoId')
4626 if video_id:
4627 return self._extract_video(video_renderer)
4628
4629 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4630 url = urljoin('https://youtube.com', traverse_obj(
4631 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4632 if url:
4633 return self.url_result(
4634 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4635
4636 def _post_thread_entries(self, post_thread_renderer):
4637 post_renderer = try_get(
4638 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4639 if not post_renderer:
4640 return
4641 # video attachment
4642 video_renderer = try_get(
4643 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4644 video_id = video_renderer.get('videoId')
4645 if video_id:
4646 entry = self._extract_video(video_renderer)
4647 if entry:
4648 yield entry
4649 # playlist attachment
4650 playlist_id = try_get(
4651 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4652 if playlist_id:
4653 yield self.url_result(
4654 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4655 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4656 # inline video links
4657 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4658 for run in runs:
4659 if not isinstance(run, dict):
4660 continue
4661 ep_url = try_get(
4662 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4663 if not ep_url:
4664 continue
4665 if not YoutubeIE.suitable(ep_url):
4666 continue
4667 ep_video_id = YoutubeIE._match_id(ep_url)
4668 if video_id == ep_video_id:
4669 continue
4670 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4671
4672 def _post_thread_continuation_entries(self, post_thread_continuation):
4673 contents = post_thread_continuation.get('contents')
4674 if not isinstance(contents, list):
4675 return
4676 for content in contents:
4677 renderer = content.get('backstagePostThreadRenderer')
4678 if isinstance(renderer, dict):
4679 yield from self._post_thread_entries(renderer)
4680 continue
4681 renderer = content.get('videoRenderer')
4682 if isinstance(renderer, dict):
4683 yield self._video_entry(renderer)
4684
4685 r''' # unused
4686 def _rich_grid_entries(self, contents):
4687 for content in contents:
4688 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4689 if video_renderer:
4690 entry = self._video_entry(video_renderer)
4691 if entry:
4692 yield entry
4693 '''
4694
4695 def _report_history_entries(self, renderer):
4696 for url in traverse_obj(renderer, (
4697 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4698 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4699 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4700 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4701
4702 def _extract_entries(self, parent_renderer, continuation_list):
4703 # continuation_list is modified in-place with continuation_list = [continuation_token]
4704 continuation_list[:] = [None]
4705 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4706 for content in contents:
4707 if not isinstance(content, dict):
4708 continue
4709 is_renderer = traverse_obj(
4710 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4711 expected_type=dict)
4712 if not is_renderer:
4713 if content.get('richItemRenderer'):
4714 for entry in self._rich_entries(content['richItemRenderer']):
4715 yield entry
4716 continuation_list[0] = self._extract_continuation(parent_renderer)
4717 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4718 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4719 yield from self._report_history_entries(table)
4720 continuation_list[0] = self._extract_continuation(table)
4721 continue
4722
4723 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4724 for isr_content in isr_contents:
4725 if not isinstance(isr_content, dict):
4726 continue
4727
4728 known_renderers = {
4729 'playlistVideoListRenderer': self._playlist_entries,
4730 'gridRenderer': self._grid_entries,
4731 'reelShelfRenderer': self._grid_entries,
4732 'shelfRenderer': self._shelf_entries,
4733 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4734 'backstagePostThreadRenderer': self._post_thread_entries,
4735 'videoRenderer': lambda x: [self._video_entry(x)],
4736 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4737 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4738 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4739 }
4740 for key, renderer in isr_content.items():
4741 if key not in known_renderers:
4742 continue
4743 for entry in known_renderers[key](renderer):
4744 if entry:
4745 yield entry
4746 continuation_list[0] = self._extract_continuation(renderer)
4747 break
4748
4749 if not continuation_list[0]:
4750 continuation_list[0] = self._extract_continuation(is_renderer)
4751
4752 if not continuation_list[0]:
4753 continuation_list[0] = self._extract_continuation(parent_renderer)
4754
4755 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4756 continuation_list = [None]
4757 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4758 tab_content = try_get(tab, lambda x: x['content'], dict)
4759 if not tab_content:
4760 return
4761 parent_renderer = (
4762 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4763 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4764 yield from extract_entries(parent_renderer)
4765 continuation = continuation_list[0]
4766
4767 for page_num in itertools.count(1):
4768 if not continuation:
4769 break
4770 headers = self.generate_api_headers(
4771 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4772 response = self._extract_response(
4773 item_id=f'{item_id} page {page_num}',
4774 query=continuation, headers=headers, ytcfg=ytcfg,
4775 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4776
4777 if not response:
4778 break
4779 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4780 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4781 visitor_data = self._extract_visitor_data(response) or visitor_data
4782
4783 known_renderers = {
4784 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4785 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4786 'gridVideoRenderer': (self._grid_entries, 'items'),
4787 'gridChannelRenderer': (self._grid_entries, 'items'),
4788 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4789 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4790 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4791 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4792 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4793 'playlistVideoListContinuation': (self._playlist_entries, None),
4794 'gridContinuation': (self._grid_entries, None),
4795 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4796 'sectionListContinuation': (extract_entries, None), # for feeds
4797 }
4798
4799 continuation_items = traverse_obj(response, (
4800 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4801 'appendContinuationItemsAction', 'continuationItems'
4802 ), 'continuationContents', get_all=False)
4803 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4804
4805 video_items_renderer = None
4806 for key in continuation_item.keys():
4807 if key not in known_renderers:
4808 continue
4809 func, parent_key = known_renderers[key]
4810 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4811 continuation_list = [None]
4812 yield from func(video_items_renderer)
4813 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4814
4815 if not video_items_renderer:
4816 break
4817
4818 @staticmethod
4819 def _extract_selected_tab(tabs, fatal=True):
4820 for tab_renderer in tabs:
4821 if tab_renderer.get('selected'):
4822 return tab_renderer
4823 if fatal:
4824 raise ExtractorError('Unable to find selected tab')
4825
4826 @staticmethod
4827 def _extract_tab_renderers(response):
4828 return traverse_obj(
4829 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
4830
4831 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4832 metadata = self._extract_metadata_from_tabs(item_id, data)
4833
4834 selected_tab = self._extract_selected_tab(tabs)
4835 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4836 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4837
4838 return self.playlist_result(
4839 self._entries(
4840 selected_tab, metadata['id'], ytcfg,
4841 self._extract_account_syncid(ytcfg, data),
4842 self._extract_visitor_data(data, ytcfg)),
4843 **metadata)
4844
4845 def _extract_metadata_from_tabs(self, item_id, data):
4846 info = {'id': item_id}
4847
4848 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
4849 if metadata_renderer:
4850 info.update({
4851 'uploader': metadata_renderer.get('title'),
4852 'uploader_id': metadata_renderer.get('externalId'),
4853 'uploader_url': metadata_renderer.get('channelUrl'),
4854 })
4855 if info['uploader_id']:
4856 info['id'] = info['uploader_id']
4857 else:
4858 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
4859
4860 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4861 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4862 def _get_uncropped(url):
4863 return url_or_none((url or '').split('=')[0] + '=s0')
4864
4865 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
4866 if avatar_thumbnails:
4867 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4868 if uncropped_avatar:
4869 avatar_thumbnails.append({
4870 'url': uncropped_avatar,
4871 'id': 'avatar_uncropped',
4872 'preference': 1
4873 })
4874
4875 channel_banners = self._extract_thumbnails(
4876 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4877 for banner in channel_banners:
4878 banner['preference'] = -10
4879
4880 if channel_banners:
4881 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4882 if uncropped_banner:
4883 channel_banners.append({
4884 'url': uncropped_banner,
4885 'id': 'banner_uncropped',
4886 'preference': -5
4887 })
4888
4889 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4890 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4891 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4892
4893 primary_thumbnails = self._extract_thumbnails(
4894 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4895 playlist_thumbnails = self._extract_thumbnails(
4896 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4897
4898 info.update({
4899 'title': (traverse_obj(metadata_renderer, 'title')
4900 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4901 or info['id']),
4902 'availability': self._extract_availability(data),
4903 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4904 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4905 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4906 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4907 })
4908
4909 # Playlist stats is a text runs array containing [video count, view count, last updated].
4910 # last updated or (view count and last updated) may be missing.
4911 playlist_stats = get_first(
4912 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4913
4914 last_updated_unix = self._parse_time_text(
4915 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4916 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4917 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
4918
4919 info['view_count'] = self._get_count(playlist_stats, 1)
4920 if info['view_count'] is None: # 0 is allowed
4921 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4922 if info['view_count'] is None:
4923 info['view_count'] = self._get_count(data, (
4924 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4925 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4926
4927 info['playlist_count'] = self._get_count(playlist_stats, 0)
4928 if info['playlist_count'] is None: # 0 is allowed
4929 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4930
4931 if not info.get('uploader_id'):
4932 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4933 if not owner: # Deprecated
4934 owner = traverse_obj(
4935 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4936 ('videoOwner', 'videoOwnerRenderer', 'title'))
4937 owner_text = self._get_text(owner)
4938 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4939 info.update({
4940 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4941 'uploader_id': browse_ep.get('browseId'),
4942 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4943 })
4944
4945 info.update({
4946 'channel': info['uploader'],
4947 'channel_id': info['uploader_id'],
4948 'channel_url': info['uploader_url']
4949 })
4950 return info
4951
4952 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4953 first_id = last_id = response = None
4954 for page_num in itertools.count(1):
4955 videos = list(self._playlist_entries(playlist))
4956 if not videos:
4957 return
4958 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4959 if start >= len(videos):
4960 return
4961 yield from videos[start:]
4962 first_id = first_id or videos[0]['id']
4963 last_id = videos[-1]['id']
4964 watch_endpoint = try_get(
4965 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4966 headers = self.generate_api_headers(
4967 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4968 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4969 query = {
4970 'playlistId': playlist_id,
4971 'videoId': watch_endpoint.get('videoId') or last_id,
4972 'index': watch_endpoint.get('index') or len(videos),
4973 'params': watch_endpoint.get('params') or 'OAE%3D'
4974 }
4975 response = self._extract_response(
4976 item_id='%s page %d' % (playlist_id, page_num),
4977 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4978 check_get_keys='contents'
4979 )
4980 playlist = try_get(
4981 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4982
4983 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4984 title = playlist.get('title') or try_get(
4985 data, lambda x: x['titleText']['simpleText'], str)
4986 playlist_id = playlist.get('playlistId') or item_id
4987
4988 # Delegating everything except mix playlists to regular tab-based playlist URL
4989 playlist_url = urljoin(url, try_get(
4990 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4991 str))
4992
4993 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4994 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4995 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4996
4997 if playlist_url and playlist_url != url and not is_known_unviewable:
4998 return self.url_result(
4999 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5000 video_title=title)
5001
5002 return self.playlist_result(
5003 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
5004 playlist_id=playlist_id, playlist_title=title)
5005
5006 def _extract_availability(self, data):
5007 """
5008 Gets the availability of a given playlist/tab.
5009 Note: Unless YouTube tells us explicitly, we do not assume it is public
5010 @param data: response
5011 """
5012 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5013 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5014 player_header_privacy = playlist_header_renderer.get('privacy')
5015
5016 badges = self._extract_badges(sidebar_renderer)
5017
5018 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
5019 privacy_setting_icon = get_first(
5020 (playlist_header_renderer, sidebar_renderer),
5021 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5022 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5023 expected_type=str)
5024
5025 microformats_is_unlisted = traverse_obj(
5026 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
5027
5028 return (
5029 'public' if (
5030 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5031 or player_header_privacy == 'PUBLIC'
5032 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5033 else self._availability(
5034 is_private=(
5035 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5036 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5037 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5038 is_unlisted=(
5039 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5040 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
5041 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5042 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
5043 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5044 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5045 needs_auth=False))
5046
5047 @staticmethod
5048 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5049 sidebar_renderer = try_get(
5050 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5051 for item in sidebar_renderer:
5052 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5053 if renderer:
5054 return renderer
5055
5056 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
5057 """
5058 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5059 """
5060 is_playlist = bool(traverse_obj(
5061 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5062 if not is_playlist:
5063 return
5064 headers = self.generate_api_headers(
5065 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5066 visitor_data=self._extract_visitor_data(data, ytcfg))
5067 query = {
5068 'params': 'wgYCCAA=',
5069 'browseId': f'VL{item_id}'
5070 }
5071 return self._extract_response(
5072 item_id=item_id, headers=headers, query=query,
5073 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
5074 note='Redownloading playlist API JSON with unavailable videos')
5075
5076 @functools.cached_property
5077 def skip_webpage(self):
5078 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5079
5080 def _extract_webpage(self, url, item_id, fatal=True):
5081 webpage, data = None, None
5082 for retry in self.RetryManager(fatal=fatal):
5083 try:
5084 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
5085 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5086 except ExtractorError as e:
5087 if isinstance(e.cause, network_exceptions):
5088 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
5089 retry.error = e
5090 continue
5091 self._error_or_warning(e, fatal=fatal)
5092 break
5093
5094 try:
5095 self._extract_and_report_alerts(data)
5096 except ExtractorError as e:
5097 self._error_or_warning(e, fatal=fatal)
5098 break
5099
5100 # Sometimes youtube returns a webpage with incomplete ytInitialData
5101 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5102 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5103 retry.error = ExtractorError('Incomplete yt initial data received')
5104 continue
5105
5106 return webpage, data
5107
5108 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5109 """Use if failed to extract ytcfg (and data) from initial webpage"""
5110 if not ytcfg and self.is_authenticated:
5111 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5112 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5113 raise ExtractorError(
5114 f'{msg}. If you are not downloading private content, or '
5115 'your cookies are only for the first account and channel,'
5116 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5117 expected=True)
5118 self.report_warning(msg, only_once=True)
5119
5120 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5121 data = None
5122 if not self.skip_webpage:
5123 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5124 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
5125 # Reject webpage data if redirected to home page without explicitly requesting
5126 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
5127 if (url != 'https://www.youtube.com/feed/recommended'
5128 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5129 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5130 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5131 if fatal:
5132 raise ExtractorError(msg, expected=True)
5133 self.report_warning(msg, only_once=True)
5134 if not data:
5135 self._report_playlist_authcheck(ytcfg, fatal=fatal)
5136 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5137 return data, ytcfg
5138
5139 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5140 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5141 resolve_response = self._extract_response(
5142 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5143 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5144 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5145 for ep_key, ep in endpoints.items():
5146 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5147 if params:
5148 return self._extract_response(
5149 item_id=item_id, query=params, ep=ep, headers=headers,
5150 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
5151 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5152 err_note = 'Failed to resolve url (does the playlist exist?)'
5153 if fatal:
5154 raise ExtractorError(err_note, expected=True)
5155 self.report_warning(err_note, item_id)
5156
5157 _SEARCH_PARAMS = None
5158
5159 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
5160 data = {'query': query}
5161 if params is NO_DEFAULT:
5162 params = self._SEARCH_PARAMS
5163 if params:
5164 data['params'] = params
5165
5166 content_keys = (
5167 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5168 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5169 # ytmusic search
5170 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5171 ('continuationContents', ),
5172 )
5173 display_id = f'query "{query}"'
5174 check_get_keys = tuple({keys[0] for keys in content_keys})
5175 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5176 self._report_playlist_authcheck(ytcfg, fatal=False)
5177
5178 continuation_list = [None]
5179 search = None
5180 for page_num in itertools.count(1):
5181 data.update(continuation_list[0] or {})
5182 headers = self.generate_api_headers(
5183 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
5184 search = self._extract_response(
5185 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5186 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
5187 slr_contents = traverse_obj(search, *content_keys)
5188 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
5189 if not continuation_list[0]:
5190 break
5191
5192
5193 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5194 IE_DESC = 'YouTube Tabs'
5195 _VALID_URL = r'''(?x:
5196 https?://
5197 (?!consent\.)(?:\w+\.)?
5198 (?:
5199 youtube(?:kids)?\.com|
5200 %(invidious)s
5201 )/
5202 (?:
5203 (?P<channel_type>channel|c|user|browse)/|
5204 (?P<not_channel>
5205 feed/|hashtag/|
5206 (?:playlist|watch)\?.*?\blist=
5207 )|
5208 (?!(?:%(reserved_names)s)\b) # Direct URLs
5209 )
5210 (?P<id>[^/?\#&]+)
5211 )''' % {
5212 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5213 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5214 }
5215 IE_NAME = 'youtube:tab'
5216
5217 _TESTS = [{
5218 'note': 'playlists, multipage',
5219 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5220 'playlist_mincount': 94,
5221 'info_dict': {
5222 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5223 'title': 'Igor Kleiner - Playlists',
5224 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5225 'uploader': 'Igor Kleiner',
5226 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5227 'channel': 'Igor Kleiner',
5228 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5229 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5230 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5231 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5232 'channel_follower_count': int
5233 },
5234 }, {
5235 'note': 'playlists, multipage, different order',
5236 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5237 'playlist_mincount': 94,
5238 'info_dict': {
5239 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5240 'title': 'Igor Kleiner - Playlists',
5241 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5242 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5243 'uploader': 'Igor Kleiner',
5244 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5245 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5246 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5247 'channel': 'Igor Kleiner',
5248 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5249 'channel_follower_count': int
5250 },
5251 }, {
5252 'note': 'playlists, series',
5253 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5254 'playlist_mincount': 5,
5255 'info_dict': {
5256 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5257 'title': '3Blue1Brown - Playlists',
5258 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5259 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5260 'uploader': '3Blue1Brown',
5261 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5262 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5263 'channel': '3Blue1Brown',
5264 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5265 'tags': ['Mathematics'],
5266 'channel_follower_count': int
5267 },
5268 }, {
5269 'note': 'playlists, singlepage',
5270 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5271 'playlist_mincount': 4,
5272 'info_dict': {
5273 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5274 'title': 'ThirstForScience - Playlists',
5275 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5276 'uploader': 'ThirstForScience',
5277 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5278 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5279 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5280 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5281 'tags': 'count:13',
5282 'channel': 'ThirstForScience',
5283 'channel_follower_count': int
5284 }
5285 }, {
5286 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5287 'only_matching': True,
5288 }, {
5289 'note': 'basic, single video playlist',
5290 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5291 'info_dict': {
5292 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5293 'uploader': 'Sergey M.',
5294 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5295 'title': 'youtube-dl public playlist',
5296 'description': '',
5297 'tags': [],
5298 'view_count': int,
5299 'modified_date': '20201130',
5300 'channel': 'Sergey M.',
5301 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5302 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5303 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5304 'availability': 'public',
5305 },
5306 'playlist_count': 1,
5307 }, {
5308 'note': 'empty playlist',
5309 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5310 'info_dict': {
5311 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5312 'uploader': 'Sergey M.',
5313 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5314 'title': 'youtube-dl empty playlist',
5315 'tags': [],
5316 'channel': 'Sergey M.',
5317 'description': '',
5318 'modified_date': '20160902',
5319 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5320 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5321 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5322 'availability': 'public',
5323 },
5324 'playlist_count': 0,
5325 }, {
5326 'note': 'Home tab',
5327 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5328 'info_dict': {
5329 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5330 'title': 'lex will - Home',
5331 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5332 'uploader': 'lex will',
5333 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5334 'channel': 'lex will',
5335 'tags': ['bible', 'history', 'prophesy'],
5336 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5337 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5338 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5339 'channel_follower_count': int
5340 },
5341 'playlist_mincount': 2,
5342 }, {
5343 'note': 'Videos tab',
5344 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5345 'info_dict': {
5346 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5347 'title': 'lex will - Videos',
5348 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5349 'uploader': 'lex will',
5350 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5351 'tags': ['bible', 'history', 'prophesy'],
5352 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5353 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5354 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5355 'channel': 'lex will',
5356 'channel_follower_count': int
5357 },
5358 'playlist_mincount': 975,
5359 }, {
5360 'note': 'Videos tab, sorted by popular',
5361 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5362 'info_dict': {
5363 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5364 'title': 'lex will - Videos',
5365 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5366 'uploader': 'lex will',
5367 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5368 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5369 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5370 'channel': 'lex will',
5371 'tags': ['bible', 'history', 'prophesy'],
5372 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5373 'channel_follower_count': int
5374 },
5375 'playlist_mincount': 199,
5376 }, {
5377 'note': 'Playlists tab',
5378 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5379 'info_dict': {
5380 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5381 'title': 'lex will - Playlists',
5382 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5383 'uploader': 'lex will',
5384 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5385 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5386 'channel': 'lex will',
5387 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5388 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5389 'tags': ['bible', 'history', 'prophesy'],
5390 'channel_follower_count': int
5391 },
5392 'playlist_mincount': 17,
5393 }, {
5394 'note': 'Community tab',
5395 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5396 'info_dict': {
5397 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5398 'title': 'lex will - Community',
5399 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5400 'uploader': 'lex will',
5401 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5402 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5403 'channel': 'lex will',
5404 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5405 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5406 'tags': ['bible', 'history', 'prophesy'],
5407 'channel_follower_count': int
5408 },
5409 'playlist_mincount': 18,
5410 }, {
5411 'note': 'Channels tab',
5412 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5413 'info_dict': {
5414 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5415 'title': 'lex will - Channels',
5416 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5417 'uploader': 'lex will',
5418 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5419 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5420 'channel': 'lex will',
5421 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5422 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5423 'tags': ['bible', 'history', 'prophesy'],
5424 'channel_follower_count': int
5425 },
5426 'playlist_mincount': 12,
5427 }, {
5428 'note': 'Search tab',
5429 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5430 'playlist_mincount': 40,
5431 'info_dict': {
5432 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5433 'title': '3Blue1Brown - Search - linear algebra',
5434 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5435 'uploader': '3Blue1Brown',
5436 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5437 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5438 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5439 'tags': ['Mathematics'],
5440 'channel': '3Blue1Brown',
5441 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5442 'channel_follower_count': int
5443 },
5444 }, {
5445 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5446 'only_matching': True,
5447 }, {
5448 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5449 'only_matching': True,
5450 }, {
5451 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5452 'only_matching': True,
5453 }, {
5454 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5455 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5456 'info_dict': {
5457 'title': '29C3: Not my department',
5458 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5459 'uploader': 'Christiaan008',
5460 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5461 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5462 'tags': [],
5463 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5464 'view_count': int,
5465 'modified_date': '20150605',
5466 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5467 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5468 'channel': 'Christiaan008',
5469 'availability': 'public',
5470 },
5471 'playlist_count': 96,
5472 }, {
5473 'note': 'Large playlist',
5474 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5475 'info_dict': {
5476 'title': 'Uploads from Cauchemar',
5477 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5478 'uploader': 'Cauchemar',
5479 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5480 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5481 'tags': [],
5482 'modified_date': r're:\d{8}',
5483 'channel': 'Cauchemar',
5484 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5485 'view_count': int,
5486 'description': '',
5487 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5488 'availability': 'public',
5489 },
5490 'playlist_mincount': 1123,
5491 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5492 }, {
5493 'note': 'even larger playlist, 8832 videos',
5494 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5495 'only_matching': True,
5496 }, {
5497 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5498 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5499 'info_dict': {
5500 'title': 'Uploads from Interstellar Movie',
5501 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5502 'uploader': 'Interstellar Movie',
5503 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5504 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5505 'tags': [],
5506 'view_count': int,
5507 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5508 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5509 'channel': 'Interstellar Movie',
5510 'description': '',
5511 'modified_date': r're:\d{8}',
5512 'availability': 'public',
5513 },
5514 'playlist_mincount': 21,
5515 }, {
5516 'note': 'Playlist with "show unavailable videos" button',
5517 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5518 'info_dict': {
5519 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5520 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5521 'uploader': 'Phim Siêu Nhân Nhật Bản',
5522 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5523 'view_count': int,
5524 'channel': 'Phim Siêu Nhân Nhật Bản',
5525 'tags': [],
5526 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5527 'description': '',
5528 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5529 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5530 'modified_date': r're:\d{8}',
5531 'availability': 'public',
5532 },
5533 'playlist_mincount': 200,
5534 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5535 }, {
5536 'note': 'Playlist with unavailable videos in page 7',
5537 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5538 'info_dict': {
5539 'title': 'Uploads from BlankTV',
5540 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5541 'uploader': 'BlankTV',
5542 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5543 'channel': 'BlankTV',
5544 'channel_url': 'https://www.youtube.com/c/blanktv',
5545 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5546 'view_count': int,
5547 'tags': [],
5548 'uploader_url': 'https://www.youtube.com/c/blanktv',
5549 'modified_date': r're:\d{8}',
5550 'description': '',
5551 'availability': 'public',
5552 },
5553 'playlist_mincount': 1000,
5554 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5555 }, {
5556 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5557 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5558 'info_dict': {
5559 'title': 'Data Analysis with Dr Mike Pound',
5560 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5561 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5562 'uploader': 'Computerphile',
5563 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5564 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5565 'tags': [],
5566 'view_count': int,
5567 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5568 'channel_url': 'https://www.youtube.com/user/Computerphile',
5569 'channel': 'Computerphile',
5570 'availability': 'public',
5571 'modified_date': '20190712',
5572 },
5573 'playlist_mincount': 11,
5574 }, {
5575 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5576 'only_matching': True,
5577 }, {
5578 'note': 'Playlist URL that does not actually serve a playlist',
5579 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5580 'info_dict': {
5581 'id': 'FqZTN594JQw',
5582 'ext': 'webm',
5583 'title': "Smiley's People 01 detective, Adventure Series, Action",
5584 'uploader': 'STREEM',
5585 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5586 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5587 'upload_date': '20150526',
5588 'license': 'Standard YouTube License',
5589 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5590 'categories': ['People & Blogs'],
5591 'tags': list,
5592 'view_count': int,
5593 'like_count': int,
5594 },
5595 'params': {
5596 'skip_download': True,
5597 },
5598 'skip': 'This video is not available.',
5599 'add_ie': [YoutubeIE.ie_key()],
5600 }, {
5601 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5602 'only_matching': True,
5603 }, {
5604 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5605 'only_matching': True,
5606 }, {
5607 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5608 'info_dict': {
5609 'id': 'Wq15eF5vCbI', # This will keep changing
5610 'ext': 'mp4',
5611 'title': str,
5612 'uploader': 'Sky News',
5613 'uploader_id': 'skynews',
5614 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5615 'upload_date': r're:\d{8}',
5616 'description': str,
5617 'categories': ['News & Politics'],
5618 'tags': list,
5619 'like_count': int,
5620 'release_timestamp': int,
5621 'channel': 'Sky News',
5622 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5623 'age_limit': 0,
5624 'view_count': int,
5625 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5626 'playable_in_embed': True,
5627 'release_date': r're:\d+',
5628 'availability': 'public',
5629 'live_status': 'is_live',
5630 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5631 'channel_follower_count': int,
5632 'concurrent_view_count': int,
5633 },
5634 'params': {
5635 'skip_download': True,
5636 },
5637 'expected_warnings': ['Ignoring subtitle tracks found in '],
5638 }, {
5639 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5640 'info_dict': {
5641 'id': 'a48o2S1cPoo',
5642 'ext': 'mp4',
5643 'title': 'The Young Turks - Live Main Show',
5644 'uploader': 'The Young Turks',
5645 'uploader_id': 'TheYoungTurks',
5646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5647 'upload_date': '20150715',
5648 'license': 'Standard YouTube License',
5649 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5650 'categories': ['News & Politics'],
5651 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5652 'like_count': int,
5653 },
5654 'params': {
5655 'skip_download': True,
5656 },
5657 'only_matching': True,
5658 }, {
5659 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5660 'only_matching': True,
5661 }, {
5662 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5663 'only_matching': True,
5664 }, {
5665 'note': 'A channel that is not live. Should raise error',
5666 'url': 'https://www.youtube.com/user/numberphile/live',
5667 'only_matching': True,
5668 }, {
5669 'url': 'https://www.youtube.com/feed/trending',
5670 'only_matching': True,
5671 }, {
5672 'url': 'https://www.youtube.com/feed/library',
5673 'only_matching': True,
5674 }, {
5675 'url': 'https://www.youtube.com/feed/history',
5676 'only_matching': True,
5677 }, {
5678 'url': 'https://www.youtube.com/feed/subscriptions',
5679 'only_matching': True,
5680 }, {
5681 'url': 'https://www.youtube.com/feed/watch_later',
5682 'only_matching': True,
5683 }, {
5684 'note': 'Recommended - redirects to home page.',
5685 'url': 'https://www.youtube.com/feed/recommended',
5686 'only_matching': True,
5687 }, {
5688 'note': 'inline playlist with not always working continuations',
5689 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5690 'only_matching': True,
5691 }, {
5692 'url': 'https://www.youtube.com/course',
5693 'only_matching': True,
5694 }, {
5695 'url': 'https://www.youtube.com/zsecurity',
5696 'only_matching': True,
5697 }, {
5698 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5699 'only_matching': True,
5700 }, {
5701 'url': 'https://www.youtube.com/TheYoungTurks/live',
5702 'only_matching': True,
5703 }, {
5704 'url': 'https://www.youtube.com/hashtag/cctv9',
5705 'info_dict': {
5706 'id': 'cctv9',
5707 'title': '#cctv9',
5708 'tags': [],
5709 },
5710 'playlist_mincount': 300, # not consistent but should be over 300
5711 }, {
5712 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5713 'only_matching': True,
5714 }, {
5715 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5716 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5717 'only_matching': True
5718 }, {
5719 'note': '/browse/ should redirect to /channel/',
5720 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5721 'only_matching': True
5722 }, {
5723 'note': 'VLPL, should redirect to playlist?list=PL...',
5724 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5725 'info_dict': {
5726 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5727 'uploader': 'NoCopyrightSounds',
5728 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5729 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5730 'title': 'NCS : All Releases 💿',
5731 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5732 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5733 'modified_date': r're:\d{8}',
5734 'view_count': int,
5735 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5736 'tags': [],
5737 'channel': 'NoCopyrightSounds',
5738 'availability': 'public',
5739 },
5740 'playlist_mincount': 166,
5741 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5742 }, {
5743 'note': 'Topic, should redirect to playlist?list=UU...',
5744 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5745 'info_dict': {
5746 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5747 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5748 'title': 'Uploads from Royalty Free Music - Topic',
5749 'uploader': 'Royalty Free Music - Topic',
5750 'tags': [],
5751 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5752 'channel': 'Royalty Free Music - Topic',
5753 'view_count': int,
5754 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5755 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5756 'modified_date': r're:\d{8}',
5757 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5758 'description': '',
5759 'availability': 'public',
5760 },
5761 'playlist_mincount': 101,
5762 }, {
5763 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5764 # Treat as a general feed
5765 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5766 'info_dict': {
5767 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5768 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5769 'tags': [],
5770 },
5771 'playlist_mincount': 9,
5772 }, {
5773 'note': 'Youtube music Album',
5774 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5775 'info_dict': {
5776 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5777 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5778 'tags': [],
5779 'view_count': int,
5780 'description': '',
5781 'availability': 'unlisted',
5782 'modified_date': r're:\d{8}',
5783 },
5784 'playlist_count': 50,
5785 }, {
5786 'note': 'unlisted single video playlist',
5787 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5788 'info_dict': {
5789 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5790 'uploader': 'colethedj',
5791 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5792 'title': 'yt-dlp unlisted playlist test',
5793 'availability': 'unlisted',
5794 'tags': [],
5795 'modified_date': '20220418',
5796 'channel': 'colethedj',
5797 'view_count': int,
5798 'description': '',
5799 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5800 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5801 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5802 },
5803 'playlist_count': 1,
5804 }, {
5805 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5806 'url': 'https://www.youtube.com/feed/recommended',
5807 'info_dict': {
5808 'id': 'recommended',
5809 'title': 'recommended',
5810 'tags': [],
5811 },
5812 'playlist_mincount': 50,
5813 'params': {
5814 'skip_download': True,
5815 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5816 },
5817 }, {
5818 'note': 'API Fallback: /videos tab, sorted by oldest first',
5819 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5820 'info_dict': {
5821 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5822 'title': 'Cody\'sLab - Videos',
5823 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5824 'uploader': 'Cody\'sLab',
5825 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5826 'channel': 'Cody\'sLab',
5827 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5828 'tags': [],
5829 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5830 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5831 'channel_follower_count': int
5832 },
5833 'playlist_mincount': 650,
5834 'params': {
5835 'skip_download': True,
5836 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5837 },
5838 'skip': 'Query for sorting no longer works',
5839 }, {
5840 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5841 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5842 'info_dict': {
5843 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5844 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5845 'title': 'Uploads from Royalty Free Music - Topic',
5846 'uploader': 'Royalty Free Music - Topic',
5847 'modified_date': r're:\d{8}',
5848 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5849 'description': '',
5850 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5851 'tags': [],
5852 'channel': 'Royalty Free Music - Topic',
5853 'view_count': int,
5854 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5855 'availability': 'public',
5856 },
5857 'playlist_mincount': 101,
5858 'params': {
5859 'skip_download': True,
5860 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5861 },
5862 }, {
5863 'note': 'non-standard redirect to regional channel',
5864 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5865 'only_matching': True
5866 }, {
5867 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5868 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5869 'info_dict': {
5870 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5871 'modified_date': '20220407',
5872 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5873 'tags': [],
5874 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5875 'uploader': 'pukkandan',
5876 'availability': 'unlisted',
5877 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5878 'channel': 'pukkandan',
5879 'description': 'Test for collaborative playlist',
5880 'title': 'yt-dlp test - collaborative playlist',
5881 'view_count': int,
5882 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5883 },
5884 'playlist_mincount': 2
5885 }, {
5886 'note': 'translated tab name',
5887 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5888 'info_dict': {
5889 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5890 'tags': [],
5891 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5892 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5893 'description': 'test description',
5894 'title': 'cole-dlp-test-acc - 再生リスト',
5895 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5896 'uploader': 'cole-dlp-test-acc',
5897 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5898 'channel': 'cole-dlp-test-acc',
5899 },
5900 'playlist_mincount': 1,
5901 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5902 'expected_warnings': ['Preferring "ja"'],
5903 }, {
5904 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5905 'note': 'preferred lang set with playlist with translated video titles',
5906 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5907 'info_dict': {
5908 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5909 'tags': [],
5910 'view_count': int,
5911 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5912 'uploader': 'cole-dlp-test-acc',
5913 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5914 'channel': 'cole-dlp-test-acc',
5915 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5916 'description': 'test',
5917 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5918 'title': 'dlp test playlist',
5919 'availability': 'public',
5920 },
5921 'playlist_mincount': 1,
5922 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5923 'expected_warnings': ['Preferring "ja"'],
5924 }, {
5925 # shorts audio pivot for 2GtVksBMYFM.
5926 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5927 'info_dict': {
5928 'id': 'sfv_audio_pivot',
5929 'title': 'sfv_audio_pivot',
5930 'tags': [],
5931 },
5932 'playlist_mincount': 50,
5933
5934 }, {
5935 # Channel with a real live tab (not to be mistaken with streams tab)
5936 # Do not treat like it should redirect to live stream
5937 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5938 'info_dict': {
5939 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5940 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5941 'tags': [],
5942 },
5943 'playlist_mincount': 20,
5944 }, {
5945 # Tab name is not the same as tab id
5946 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5947 'info_dict': {
5948 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5949 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5950 'tags': [],
5951 },
5952 'playlist_mincount': 8,
5953 }, {
5954 # Home tab id is literally home. Not to get mistaken with featured
5955 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5956 'info_dict': {
5957 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5958 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5959 'tags': [],
5960 },
5961 'playlist_mincount': 8,
5962 }, {
5963 # Should get three playlists for videos, shorts and streams tabs
5964 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5965 'info_dict': {
5966 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5967 'title': 'Polka Ch. 尾丸ポルカ',
5968 'channel_follower_count': int,
5969 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5970 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5971 'uploader': 'Polka Ch. 尾丸ポルカ',
5972 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5973 'channel': 'Polka Ch. 尾丸ポルカ',
5974 'tags': 'count:35',
5975 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5976 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5977 },
5978 'playlist_count': 3,
5979 }, {
5980 # Shorts tab with channel with handle
5981 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5982 'info_dict': {
5983 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5984 'title': 'Not Just Bikes - Shorts',
5985 'tags': 'count:12',
5986 'uploader': 'Not Just Bikes',
5987 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5988 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5989 'channel_follower_count': int,
5990 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5991 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5992 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5993 'channel': 'Not Just Bikes',
5994 },
5995 'playlist_mincount': 10,
5996 }, {
5997 # Streams tab
5998 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5999 'info_dict': {
6000 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6001 'title': '中村悠一 - Live',
6002 'tags': 'count:7',
6003 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6004 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
6005 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6006 'channel': '中村悠一',
6007 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
6008 'channel_follower_count': int,
6009 'uploader': '中村悠一',
6010 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
6011 },
6012 'playlist_mincount': 60,
6013 }, {
6014 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6015 # See test_youtube_lists
6016 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6017 'only_matching': True,
6018 }, {
6019 # No uploads and no UCID given. Should fail with no uploads error
6020 # See test_youtube_lists
6021 'url': 'https://www.youtube.com/news',
6022 'only_matching': True
6023 }, {
6024 # No videos tab but has a shorts tab
6025 'url': 'https://www.youtube.com/c/TKFShorts',
6026 'info_dict': {
6027 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6028 'title': 'Shorts Break - Shorts',
6029 'tags': 'count:32',
6030 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6031 'channel': 'Shorts Break',
6032 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
6033 'uploader': 'Shorts Break',
6034 'channel_follower_count': int,
6035 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6036 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6037 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6038 },
6039 'playlist_mincount': 30,
6040 }, {
6041 # Trending Now Tab. tab id is empty
6042 'url': 'https://www.youtube.com/feed/trending',
6043 'info_dict': {
6044 'id': 'trending',
6045 'title': 'trending - Now',
6046 'tags': [],
6047 },
6048 'playlist_mincount': 30,
6049 }, {
6050 # Trending Gaming Tab. tab id is empty
6051 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6052 'info_dict': {
6053 'id': 'trending',
6054 'title': 'trending - Gaming',
6055 'tags': [],
6056 },
6057 'playlist_mincount': 30,
6058 }, {
6059 # Shorts url result in shorts tab
6060 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6061 'info_dict': {
6062 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6063 'title': 'cole-dlp-test-acc - Shorts',
6064 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6065 'channel': 'cole-dlp-test-acc',
6066 'description': 'test description',
6067 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6068 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6069 'tags': [],
6070 'uploader': 'cole-dlp-test-acc',
6071 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6072
6073 },
6074 'playlist': [{
6075 'info_dict': {
6076 '_type': 'url',
6077 'ie_key': 'Youtube',
6078 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6079 'id': 'sSM9J5YH_60',
6080 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6081 'title': 'SHORT short',
6082 'channel': 'cole-dlp-test-acc',
6083 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6084 'view_count': int,
6085 'thumbnails': list,
6086 }
6087 }],
6088 'params': {'extract_flat': True},
6089 }, {
6090 # Live video status should be extracted
6091 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6092 'info_dict': {
6093 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6094 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6095 'tags': []
6096 },
6097 'playlist': [{
6098 'info_dict': {
6099 '_type': 'url',
6100 'ie_key': 'Youtube',
6101 'url': 'startswith:https://www.youtube.com/watch?v=',
6102 'id': str,
6103 'title': str,
6104 'live_status': 'is_live',
6105 'channel_id': str,
6106 'channel_url': str,
6107 'concurrent_view_count': int,
6108 'channel': str,
6109 }
6110 }],
6111 'params': {'extract_flat': True, 'playlist_items': '1'},
6112 'playlist_mincount': 1
6113 }, {
6114 # Channel renderer metadata. Contains number of videos on the channel
6115 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6116 'info_dict': {
6117 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6118 'title': 'cole-dlp-test-acc - Channels',
6119 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6120 'channel': 'cole-dlp-test-acc',
6121 'description': 'test description',
6122 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6123 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6124 'tags': [],
6125 'uploader': 'cole-dlp-test-acc',
6126 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6127
6128 },
6129 'playlist': [{
6130 'info_dict': {
6131 '_type': 'url',
6132 'ie_key': 'YoutubeTab',
6133 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6134 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6135 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6136 'title': 'PewDiePie',
6137 'channel': 'PewDiePie',
6138 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6139 'thumbnails': list,
6140 'channel_follower_count': int,
6141 'playlist_count': int
6142 }
6143 }],
6144 'params': {'extract_flat': True},
6145 }, {
6146 'url': 'https://www.youtube.com/@3blue1brown/about',
6147 'info_dict': {
6148 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6149 'tags': ['Mathematics'],
6150 'title': '3Blue1Brown - About',
6151 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6152 'channel_follower_count': int,
6153 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6154 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6155 'channel': '3Blue1Brown',
6156 'uploader': '3Blue1Brown',
6157 'view_count': int,
6158 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6159 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6160 },
6161 'playlist_count': 0,
6162 }]
6163
6164 @classmethod
6165 def suitable(cls, url):
6166 return False if YoutubeIE.suitable(url) else super().suitable(url)
6167
6168 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6169
6170 def _get_url_mobj(self, url):
6171 mobj = self._URL_RE.match(url).groupdict()
6172 mobj.update((k, '') for k, v in mobj.items() if v is None)
6173 return mobj
6174
6175 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6176 tab_name = (tab.get('title') or '').lower()
6177 tab_url = urljoin(base_url, traverse_obj(
6178 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6179
6180 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6181 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
6182 if tab_id:
6183 return {
6184 'TAB_ID_SPONSORSHIPS': 'membership',
6185 }.get(tab_id, tab_id), tab_name
6186
6187 # Fallback to tab name if we cannot get the tab id.
6188 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6189 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6190 if tab_name:
6191 self.write_debug(f'Falling back to selected tab name: {tab_name}')
6192 return {
6193 'home': 'featured',
6194 'live': 'streams',
6195 }.get(tab_name, tab_name), tab_name
6196
6197 def _has_tab(self, tabs, tab_id):
6198 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
6199
6200 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6201 def _real_extract(self, url, smuggled_data):
6202 item_id = self._match_id(url)
6203 url = urllib.parse.urlunparse(
6204 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
6205 compat_opts = self.get_param('compat_opts', [])
6206
6207 mobj = self._get_url_mobj(url)
6208 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
6209 if is_channel and smuggled_data.get('is_music_url'):
6210 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6211 return self.url_result(
6212 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6213 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6214 mdata = self._extract_tab_endpoint(
6215 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6216 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6217 get_all=False, expected_type=str)
6218 if not murl:
6219 raise ExtractorError('Failed to resolve album to playlist')
6220 return self.url_result(murl, YoutubeTabIE)
6221 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6222 return self.url_result(
6223 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6224
6225 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
6226 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
6227 url = f'{pre}/videos{post}'
6228 if smuggled_data.get('is_music_url'):
6229 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
6230
6231 # Handle both video/playlist URLs
6232 qs = parse_qs(url)
6233 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
6234 if not video_id and mobj['not_channel'].startswith('watch'):
6235 if not playlist_id:
6236 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6237 raise ExtractorError('A video URL was given without video ID', expected=True)
6238 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6239 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6240 return self.url_result(
6241 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
6242
6243 if not self._yes_playlist(playlist_id, video_id):
6244 return self.url_result(
6245 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6246
6247 data, ytcfg = self._extract_data(url, display_id)
6248
6249 # YouTube may provide a non-standard redirect to the regional channel
6250 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6251 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6252 redirect_url = traverse_obj(
6253 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6254 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
6255 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
6256 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6257 return self.url_result(redirect_url, YoutubeTabIE)
6258
6259 tabs, extra_tabs = self._extract_tab_renderers(data), []
6260 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
6261 selected_tab = self._extract_selected_tab(tabs)
6262 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6263 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6264
6265 if not original_tab_id and selected_tab_name:
6266 self.to_screen('Downloading all uploads of the channel. '
6267 'To download only the videos in a specific tab, pass the tab\'s URL')
6268 if self._has_tab(tabs, 'streams'):
6269 extra_tabs.append(''.join((pre, '/streams', post)))
6270 if self._has_tab(tabs, 'shorts'):
6271 extra_tabs.append(''.join((pre, '/shorts', post)))
6272 # XXX: Members-only tab should also be extracted
6273
6274 if not extra_tabs and selected_tab_id != 'videos':
6275 # Channel does not have streams, shorts or videos tabs
6276 if item_id[:2] != 'UC':
6277 raise ExtractorError('This channel has no uploads', expected=True)
6278
6279 # Topic channels don't have /videos. Use the equivalent playlist instead
6280 pl_id = f'UU{item_id[2:]}'
6281 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6282 try:
6283 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6284 except ExtractorError:
6285 raise ExtractorError('This channel has no uploads', expected=True)
6286 else:
6287 item_id, url = pl_id, pl_url
6288 self.to_screen(
6289 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6290
6291 elif extra_tabs and selected_tab_id != 'videos':
6292 # When there are shorts/live tabs but not videos tab
6293 url, data = f'{pre}{post}', None
6294
6295 elif (original_tab_id or 'videos') != selected_tab_id:
6296 if original_tab_id == 'live':
6297 # Live tab should have redirected to the video
6298 # Except in the case the channel has an actual live tab
6299 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6300 raise UserNotLive(video_id=item_id)
6301 elif selected_tab_name:
6302 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6303
6304 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6305 url = f'{pre}{post}'
6306
6307 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6308 if 'no-youtube-unavailable-videos' not in compat_opts:
6309 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
6310 self._extract_and_report_alerts(data, only_once=True)
6311
6312 tabs, entries = self._extract_tab_renderers(data), []
6313 if tabs:
6314 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6315 entries[0].update({
6316 'extractor_key': YoutubeTabIE.ie_key(),
6317 'extractor': YoutubeTabIE.IE_NAME,
6318 'webpage_url': url,
6319 })
6320 if self.get_param('playlist_items') == '0':
6321 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6322 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6323 entries.extend(map(self._real_extract, extra_tabs))
6324
6325 if len(entries) == 1:
6326 return entries[0]
6327 elif entries:
6328 metadata = self._extract_metadata_from_tabs(item_id, data)
6329 uploads_url = 'the Uploads (UU) playlist URL'
6330 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6331 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6332 self.to_screen(
6333 'Downloading as multiple playlists, separated by tabs. '
6334 f'To download as a single playlist instead, pass {uploads_url}')
6335 return self.playlist_result(entries, item_id, **metadata)
6336
6337 # Inline playlist
6338 playlist = traverse_obj(
6339 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
6340 if playlist:
6341 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
6342
6343 video_id = traverse_obj(
6344 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
6345 if video_id:
6346 if tab != '/live': # live tab is expected to redirect to video
6347 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
6348 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6349
6350 raise ExtractorError('Unable to recognize tab page')
6351
6352
6353 class YoutubePlaylistIE(InfoExtractor):
6354 IE_DESC = 'YouTube playlists'
6355 _VALID_URL = r'''(?x)(?:
6356 (?:https?://)?
6357 (?:\w+\.)?
6358 (?:
6359 (?:
6360 youtube(?:kids)?\.com|
6361 %(invidious)s
6362 )
6363 /.*?\?.*?\blist=
6364 )?
6365 (?P<id>%(playlist_id)s)
6366 )''' % {
6367 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6368 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6369 }
6370 IE_NAME = 'youtube:playlist'
6371 _TESTS = [{
6372 'note': 'issue #673',
6373 'url': 'PLBB231211A4F62143',
6374 'info_dict': {
6375 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6376 'id': 'PLBB231211A4F62143',
6377 'uploader': 'Wickman',
6378 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6379 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6380 'view_count': int,
6381 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6382 'modified_date': r're:\d{8}',
6383 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6384 'channel': 'Wickman',
6385 'tags': [],
6386 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6387 'availability': 'public',
6388 },
6389 'playlist_mincount': 29,
6390 }, {
6391 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6392 'info_dict': {
6393 'title': 'YDL_safe_search',
6394 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6395 },
6396 'playlist_count': 2,
6397 'skip': 'This playlist is private',
6398 }, {
6399 'note': 'embedded',
6400 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6401 'playlist_count': 4,
6402 'info_dict': {
6403 'title': 'JODA15',
6404 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6405 'uploader': 'milan',
6406 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6407 'description': '',
6408 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6409 'tags': [],
6410 'modified_date': '20140919',
6411 'view_count': int,
6412 'channel': 'milan',
6413 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6414 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6415 'availability': 'public',
6416 },
6417 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
6418 }, {
6419 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6420 'playlist_mincount': 455,
6421 'info_dict': {
6422 'title': '2018 Chinese New Singles (11/6 updated)',
6423 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6424 'uploader': 'LBK',
6425 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6426 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6427 'channel': 'LBK',
6428 'view_count': int,
6429 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6430 'tags': [],
6431 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6432 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6433 'modified_date': r're:\d{8}',
6434 'availability': 'public',
6435 },
6436 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
6437 }, {
6438 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6439 'only_matching': True,
6440 }, {
6441 # music album playlist
6442 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6443 'only_matching': True,
6444 }]
6445
6446 @classmethod
6447 def suitable(cls, url):
6448 if YoutubeTabIE.suitable(url):
6449 return False
6450 from ..utils import parse_qs
6451 qs = parse_qs(url)
6452 if qs.get('v', [None])[0]:
6453 return False
6454 return super().suitable(url)
6455
6456 def _real_extract(self, url):
6457 playlist_id = self._match_id(url)
6458 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
6459 url = update_url_query(
6460 'https://www.youtube.com/playlist',
6461 parse_qs(url) or {'list': playlist_id})
6462 if is_music_url:
6463 url = smuggle_url(url, {'is_music_url': True})
6464 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6465
6466
6467 class YoutubeYtBeIE(InfoExtractor):
6468 IE_DESC = 'youtu.be'
6469 _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}
6470 _TESTS = [{
6471 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6472 'info_dict': {
6473 'id': 'yeWKywCrFtk',
6474 'ext': 'mp4',
6475 'title': 'Small Scale Baler and Braiding Rugs',
6476 'uploader': 'Backus-Page House Museum',
6477 'uploader_id': 'backuspagemuseum',
6478 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6479 'upload_date': '20161008',
6480 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6481 'categories': ['Nonprofits & Activism'],
6482 'tags': list,
6483 'like_count': int,
6484 'age_limit': 0,
6485 'playable_in_embed': True,
6486 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6487 'channel': 'Backus-Page House Museum',
6488 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6489 'live_status': 'not_live',
6490 'view_count': int,
6491 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6492 'availability': 'public',
6493 'duration': 59,
6494 'comment_count': int,
6495 'channel_follower_count': int
6496 },
6497 'params': {
6498 'noplaylist': True,
6499 'skip_download': True,
6500 },
6501 }, {
6502 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6503 'only_matching': True,
6504 }]
6505
6506 def _real_extract(self, url):
6507 mobj = self._match_valid_url(url)
6508 video_id = mobj.group('id')
6509 playlist_id = mobj.group('playlist_id')
6510 return self.url_result(
6511 update_url_query('https://www.youtube.com/watch', {
6512 'v': video_id,
6513 'list': playlist_id,
6514 'feature': 'youtu.be',
6515 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6516
6517
6518 class YoutubeLivestreamEmbedIE(InfoExtractor):
6519 IE_DESC = 'YouTube livestream embeds'
6520 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6521 _TESTS = [{
6522 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6523 'only_matching': True,
6524 }]
6525
6526 def _real_extract(self, url):
6527 channel_id = self._match_id(url)
6528 return self.url_result(
6529 f'https://www.youtube.com/channel/{channel_id}/live',
6530 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6531
6532
6533 class YoutubeYtUserIE(InfoExtractor):
6534 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6535 IE_NAME = 'youtube:user'
6536 _VALID_URL = r'ytuser:(?P<id>.+)'
6537 _TESTS = [{
6538 'url': 'ytuser:phihag',
6539 'only_matching': True,
6540 }]
6541
6542 def _real_extract(self, url):
6543 user_id = self._match_id(url)
6544 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
6545
6546
6547 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6548 IE_NAME = 'youtube:favorites'
6549 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6550 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6551 _LOGIN_REQUIRED = True
6552 _TESTS = [{
6553 'url': ':ytfav',
6554 'only_matching': True,
6555 }, {
6556 'url': ':ytfavorites',
6557 'only_matching': True,
6558 }]
6559
6560 def _real_extract(self, url):
6561 return self.url_result(
6562 'https://www.youtube.com/playlist?list=LL',
6563 ie=YoutubeTabIE.ie_key())
6564
6565
6566 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6567 IE_NAME = 'youtube:notif'
6568 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6569 _VALID_URL = r':ytnotif(?:ication)?s?'
6570 _LOGIN_REQUIRED = True
6571 _TESTS = [{
6572 'url': ':ytnotif',
6573 'only_matching': True,
6574 }, {
6575 'url': ':ytnotifications',
6576 'only_matching': True,
6577 }]
6578
6579 def _extract_notification_menu(self, response, continuation_list):
6580 notification_list = traverse_obj(
6581 response,
6582 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6583 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6584 expected_type=list) or []
6585 continuation_list[0] = None
6586 for item in notification_list:
6587 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6588 if entry:
6589 yield entry
6590 continuation = item.get('continuationItemRenderer')
6591 if continuation:
6592 continuation_list[0] = continuation
6593
6594 def _extract_notification_renderer(self, notification):
6595 video_id = traverse_obj(
6596 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6597 url = f'https://www.youtube.com/watch?v={video_id}'
6598 channel_id = None
6599 if not video_id:
6600 browse_ep = traverse_obj(
6601 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6602 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6603 post_id = self._search_regex(
6604 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6605 'post id', default=None)
6606 if not channel_id or not post_id:
6607 return
6608 # The direct /post url redirects to this in the browser
6609 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6610
6611 channel = traverse_obj(
6612 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6613 expected_type=str)
6614 notification_title = self._get_text(notification, 'shortMessage')
6615 if notification_title:
6616 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6617 # TODO: handle recommended videos
6618 title = self._search_regex(
6619 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6620 'video title', default=None)
6621 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6622 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6623 else None)
6624 return {
6625 '_type': 'url',
6626 'url': url,
6627 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6628 'video_id': video_id,
6629 'title': title,
6630 'channel_id': channel_id,
6631 'channel': channel,
6632 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6633 'timestamp': timestamp,
6634 }
6635
6636 def _notification_menu_entries(self, ytcfg):
6637 continuation_list = [None]
6638 response = None
6639 for page in itertools.count(1):
6640 ctoken = traverse_obj(
6641 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6642 response = self._extract_response(
6643 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6644 ep='notification/get_notification_menu', check_get_keys='actions',
6645 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6646 yield from self._extract_notification_menu(response, continuation_list)
6647 if not continuation_list[0]:
6648 break
6649
6650 def _real_extract(self, url):
6651 display_id = 'notifications'
6652 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6653 self._report_playlist_authcheck(ytcfg)
6654 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6655
6656
6657 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6658 IE_DESC = 'YouTube search'
6659 IE_NAME = 'youtube:search'
6660 _SEARCH_KEY = 'ytsearch'
6661 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6662 _TESTS = [{
6663 'url': 'ytsearch5:youtube-dl test video',
6664 'playlist_count': 5,
6665 'info_dict': {
6666 'id': 'youtube-dl test video',
6667 'title': 'youtube-dl test video',
6668 }
6669 }]
6670
6671
6672 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6673 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6674 _SEARCH_KEY = 'ytsearchdate'
6675 IE_DESC = 'YouTube search, newest videos first'
6676 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6677 _TESTS = [{
6678 'url': 'ytsearchdate5:youtube-dl test video',
6679 'playlist_count': 5,
6680 'info_dict': {
6681 'id': 'youtube-dl test video',
6682 'title': 'youtube-dl test video',
6683 }
6684 }]
6685
6686
6687 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6688 IE_DESC = 'YouTube search URLs with sorting and filter support'
6689 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6690 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6691 _TESTS = [{
6692 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6693 'playlist_mincount': 5,
6694 'info_dict': {
6695 'id': 'youtube-dl test video',
6696 'title': 'youtube-dl test video',
6697 }
6698 }, {
6699 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6700 'playlist_mincount': 5,
6701 'info_dict': {
6702 'id': 'python',
6703 'title': 'python',
6704 }
6705 }, {
6706 'url': 'https://www.youtube.com/results?search_query=%23cats',
6707 'playlist_mincount': 1,
6708 'info_dict': {
6709 'id': '#cats',
6710 'title': '#cats',
6711 # The test suite does not have support for nested playlists
6712 # 'entries': [{
6713 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6714 # 'title': '#cats',
6715 # }],
6716 },
6717 }, {
6718 # Channel results
6719 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6720 'info_dict': {
6721 'id': 'kurzgesagt',
6722 'title': 'kurzgesagt',
6723 },
6724 'playlist': [{
6725 'info_dict': {
6726 '_type': 'url',
6727 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6728 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6729 'ie_key': 'YoutubeTab',
6730 'channel': 'Kurzgesagt – In a Nutshell',
6731 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6732 'title': 'Kurzgesagt – In a Nutshell',
6733 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6734 'playlist_count': int, # XXX: should have a way of saying > 1
6735 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6736 'thumbnails': list
6737 }
6738 }],
6739 'params': {'extract_flat': True, 'playlist_items': '1'},
6740 'playlist_mincount': 1,
6741 }, {
6742 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6743 'only_matching': True,
6744 }]
6745
6746 def _real_extract(self, url):
6747 qs = parse_qs(url)
6748 query = (qs.get('search_query') or qs.get('q'))[0]
6749 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6750
6751
6752 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6753 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6754 IE_NAME = 'youtube:music:search_url'
6755 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6756 _TESTS = [{
6757 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6758 'playlist_count': 16,
6759 'info_dict': {
6760 'id': 'royalty free music',
6761 'title': 'royalty free music',
6762 }
6763 }, {
6764 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6765 'playlist_mincount': 30,
6766 'info_dict': {
6767 'id': 'royalty free music - songs',
6768 'title': 'royalty free music - songs',
6769 },
6770 'params': {'extract_flat': 'in_playlist'}
6771 }, {
6772 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6773 'playlist_mincount': 30,
6774 'info_dict': {
6775 'id': 'royalty free music - community playlists',
6776 'title': 'royalty free music - community playlists',
6777 },
6778 'params': {'extract_flat': 'in_playlist'}
6779 }]
6780
6781 _SECTIONS = {
6782 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6783 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6784 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6785 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6786 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6787 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6788 }
6789
6790 def _real_extract(self, url):
6791 qs = parse_qs(url)
6792 query = (qs.get('search_query') or qs.get('q'))[0]
6793 params = qs.get('sp', (None,))[0]
6794 if params:
6795 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6796 else:
6797 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6798 params = self._SECTIONS.get(section)
6799 if not params:
6800 section = None
6801 title = join_nonempty(query, section, delim=' - ')
6802 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6803
6804
6805 class YoutubeFeedsInfoExtractor(InfoExtractor):
6806 """
6807 Base class for feed extractors
6808 Subclasses must re-define the _FEED_NAME property.
6809 """
6810 _LOGIN_REQUIRED = True
6811 _FEED_NAME = 'feeds'
6812
6813 def _real_initialize(self):
6814 YoutubeBaseInfoExtractor._check_login_required(self)
6815
6816 @classproperty
6817 def IE_NAME(self):
6818 return f'youtube:{self._FEED_NAME}'
6819
6820 def _real_extract(self, url):
6821 return self.url_result(
6822 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6823
6824
6825 class YoutubeWatchLaterIE(InfoExtractor):
6826 IE_NAME = 'youtube:watchlater'
6827 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6828 _VALID_URL = r':ytwatchlater'
6829 _TESTS = [{
6830 'url': ':ytwatchlater',
6831 'only_matching': True,
6832 }]
6833
6834 def _real_extract(self, url):
6835 return self.url_result(
6836 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6837
6838
6839 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6840 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6841 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6842 _FEED_NAME = 'recommended'
6843 _LOGIN_REQUIRED = False
6844 _TESTS = [{
6845 'url': ':ytrec',
6846 'only_matching': True,
6847 }, {
6848 'url': ':ytrecommended',
6849 'only_matching': True,
6850 }, {
6851 'url': 'https://youtube.com',
6852 'only_matching': True,
6853 }]
6854
6855
6856 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6857 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6858 _VALID_URL = r':ytsub(?:scription)?s?'
6859 _FEED_NAME = 'subscriptions'
6860 _TESTS = [{
6861 'url': ':ytsubs',
6862 'only_matching': True,
6863 }, {
6864 'url': ':ytsubscriptions',
6865 'only_matching': True,
6866 }]
6867
6868
6869 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6870 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6871 _VALID_URL = r':ythis(?:tory)?'
6872 _FEED_NAME = 'history'
6873 _TESTS = [{
6874 'url': ':ythistory',
6875 'only_matching': True,
6876 }]
6877
6878
6879 class YoutubeStoriesIE(InfoExtractor):
6880 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6881 IE_NAME = 'youtube:stories'
6882 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6883 _TESTS = [{
6884 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6885 'only_matching': True,
6886 }]
6887
6888 def _real_extract(self, url):
6889 playlist_id = f'RLTD{self._match_id(url)}'
6890 return self.url_result(
6891 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6892 ie=YoutubeTabIE, video_id=playlist_id)
6893
6894
6895 class YoutubeShortsAudioPivotIE(InfoExtractor):
6896 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6897 IE_NAME = 'youtube:shorts:pivot:audio'
6898 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6899 _TESTS = [{
6900 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6901 'only_matching': True,
6902 }]
6903
6904 @staticmethod
6905 def _generate_audio_pivot_params(video_id):
6906 """
6907 Generates sfv_audio_pivot browse params for this video id
6908 """
6909 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6910 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6911
6912 def _real_extract(self, url):
6913 video_id = self._match_id(url)
6914 return self.url_result(
6915 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6916 ie=YoutubeTabIE)
6917
6918
6919 class YoutubeTruncatedURLIE(InfoExtractor):
6920 IE_NAME = 'youtube:truncated_url'
6921 IE_DESC = False # Do not list
6922 _VALID_URL = r'''(?x)
6923 (?:https?://)?
6924 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6925 (?:watch\?(?:
6926 feature=[a-z_]+|
6927 annotation_id=annotation_[^&]+|
6928 x-yt-cl=[0-9]+|
6929 hl=[^&]*|
6930 t=[0-9]+
6931 )?
6932 |
6933 attribution_link\?a=[^&]+
6934 )
6935 $
6936 '''
6937
6938 _TESTS = [{
6939 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6940 'only_matching': True,
6941 }, {
6942 'url': 'https://www.youtube.com/watch?',
6943 'only_matching': True,
6944 }, {
6945 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6946 'only_matching': True,
6947 }, {
6948 'url': 'https://www.youtube.com/watch?feature=foo',
6949 'only_matching': True,
6950 }, {
6951 'url': 'https://www.youtube.com/watch?hl=en-GB',
6952 'only_matching': True,
6953 }, {
6954 'url': 'https://www.youtube.com/watch?t=2372',
6955 'only_matching': True,
6956 }]
6957
6958 def _real_extract(self, url):
6959 raise ExtractorError(
6960 'Did you forget to quote the URL? Remember that & is a meta '
6961 'character in most shells, so you want to put the URL in quotes, '
6962 'like youtube-dl '
6963 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6964 ' or simply youtube-dl BaW_jenozKc .',
6965 expected=True)
6966
6967
6968 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6969 IE_NAME = 'youtube:clip'
6970 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6971 _TESTS = [{
6972 # FIXME: Other metadata should be extracted from the clip, not from the base video
6973 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6974 'info_dict': {
6975 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6976 'ext': 'mp4',
6977 'section_start': 29.0,
6978 'section_end': 39.7,
6979 'duration': 10.7,
6980 'age_limit': 0,
6981 'availability': 'public',
6982 'categories': ['Gaming'],
6983 'channel': 'Scott The Woz',
6984 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6985 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6986 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6987 'like_count': int,
6988 'playable_in_embed': True,
6989 'tags': 'count:17',
6990 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6991 'title': 'Mobile Games on Console - Scott The Woz',
6992 'upload_date': '20210920',
6993 'uploader': 'Scott The Woz',
6994 'uploader_id': 'scottthewoz',
6995 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6996 'view_count': int,
6997 'live_status': 'not_live',
6998 'channel_follower_count': int
6999 }
7000 }]
7001
7002 def _real_extract(self, url):
7003 clip_id = self._match_id(url)
7004 _, data = self._extract_webpage(url, clip_id)
7005
7006 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7007 if not video_id:
7008 raise ExtractorError('Unable to find video ID')
7009
7010 clip_data = traverse_obj(data, (
7011 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7012 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7013 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7014 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7015
7016 return {
7017 '_type': 'url_transparent',
7018 'url': f'https://www.youtube.com/watch?v={video_id}',
7019 'ie_key': YoutubeIE.ie_key(),
7020 'id': clip_id,
7021 'section_start': int(clip_data['startTimeMs']) / 1000,
7022 'section_end': int(clip_data['endTimeMs']) / 1000,
7023 }
7024
7025
7026 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7027 IE_NAME = 'youtube:consent'
7028 IE_DESC = False # Do not list
7029 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7030 _TESTS = [{
7031 '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',
7032 'info_dict': {
7033 'id': 'qVv6vCqciTM',
7034 'ext': 'mp4',
7035 'age_limit': 0,
7036 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7037 'comment_count': int,
7038 'chapters': 'count:13',
7039 'upload_date': '20221223',
7040 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7041 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7042 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7043 'like_count': int,
7044 'release_date': '20221223',
7045 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7046 '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】',
7047 'view_count': int,
7048 'playable_in_embed': True,
7049 'duration': 4438,
7050 'availability': 'public',
7051 'channel_follower_count': int,
7052 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7053 'categories': ['Entertainment'],
7054 'live_status': 'was_live',
7055 'release_timestamp': 1671793345,
7056 'channel': 'さなちゃんねる',
7057 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7058 'uploader': 'さなちゃんねる',
7059 },
7060 'add_ie': ['Youtube'],
7061 'params': {'skip_download': 'Youtube'},
7062 }]
7063
7064 def _real_extract(self, url):
7065 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7066 if not redirect_url:
7067 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7068 return self.url_result(redirect_url)
7069
7070
7071 class YoutubeTruncatedIDIE(InfoExtractor):
7072 IE_NAME = 'youtube:truncated_id'
7073 IE_DESC = False # Do not list
7074 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7075
7076 _TESTS = [{
7077 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7078 'only_matching': True,
7079 }]
7080
7081 def _real_extract(self, url):
7082 video_id = self._match_id(url)
7083 raise ExtractorError(
7084 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
7085 expected=True)