]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[extractor/youtube] Add extractor-arg `include_duplicate_formats`
[yt-dlp.git] / yt_dlp / extractor / youtube.py
1 import base64
2 import calendar
3 import collections
4 import copy
5 import datetime
6 import enum
7 import hashlib
8 import itertools
9 import json
10 import math
11 import os.path
12 import random
13 import re
14 import sys
15 import threading
16 import time
17 import traceback
18 import urllib.error
19 import urllib.parse
20
21 from .common import InfoExtractor, SearchInfoExtractor
22 from .openload import PhantomJSwrapper
23 from ..compat import functools
24 from ..jsinterp import JSInterpreter
25 from ..utils import (
26 NO_DEFAULT,
27 ExtractorError,
28 LazyList,
29 UserNotLive,
30 bug_reports_message,
31 classproperty,
32 clean_html,
33 datetime_from_str,
34 dict_get,
35 filter_dict,
36 float_or_none,
37 format_field,
38 get_first,
39 int_or_none,
40 is_html,
41 join_nonempty,
42 js_to_json,
43 mimetype2ext,
44 network_exceptions,
45 orderedSet,
46 parse_codecs,
47 parse_count,
48 parse_duration,
49 parse_iso8601,
50 parse_qs,
51 qualities,
52 remove_start,
53 smuggle_url,
54 str_or_none,
55 str_to_int,
56 strftime_or_none,
57 traverse_obj,
58 try_get,
59 unescapeHTML,
60 unified_strdate,
61 unified_timestamp,
62 unsmuggle_url,
63 update_url_query,
64 url_or_none,
65 urljoin,
66 variadic,
67 )
68
69
70 STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
71 # any clients starting with _ cannot be explicitly requested by the user
72 INNERTUBE_CLIENTS = {
73 'web': {
74 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
75 'INNERTUBE_CONTEXT': {
76 'client': {
77 'clientName': 'WEB',
78 'clientVersion': '2.20220801.00.00',
79 }
80 },
81 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
82 },
83 'web_embedded': {
84 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
85 'INNERTUBE_CONTEXT': {
86 'client': {
87 'clientName': 'WEB_EMBEDDED_PLAYER',
88 'clientVersion': '1.20220731.00.00',
89 },
90 },
91 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
92 },
93 'web_music': {
94 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
95 'INNERTUBE_HOST': 'music.youtube.com',
96 'INNERTUBE_CONTEXT': {
97 'client': {
98 'clientName': 'WEB_REMIX',
99 'clientVersion': '1.20220727.01.00',
100 }
101 },
102 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
103 },
104 'web_creator': {
105 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
106 'INNERTUBE_CONTEXT': {
107 'client': {
108 'clientName': 'WEB_CREATOR',
109 'clientVersion': '1.20220726.00.00',
110 }
111 },
112 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
113 },
114 'android': {
115 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
116 'INNERTUBE_CONTEXT': {
117 'client': {
118 'clientName': 'ANDROID',
119 'clientVersion': '17.31.35',
120 'androidSdkVersion': 30,
121 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
122 }
123 },
124 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
125 'REQUIRE_JS_PLAYER': False
126 },
127 'android_embedded': {
128 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
129 'INNERTUBE_CONTEXT': {
130 'client': {
131 'clientName': 'ANDROID_EMBEDDED_PLAYER',
132 'clientVersion': '17.31.35',
133 'androidSdkVersion': 30,
134 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
135 },
136 },
137 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
138 'REQUIRE_JS_PLAYER': False
139 },
140 'android_music': {
141 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
142 'INNERTUBE_CONTEXT': {
143 'client': {
144 'clientName': 'ANDROID_MUSIC',
145 'clientVersion': '5.16.51',
146 'androidSdkVersion': 30,
147 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
148 }
149 },
150 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
151 'REQUIRE_JS_PLAYER': False
152 },
153 'android_creator': {
154 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
155 'INNERTUBE_CONTEXT': {
156 'client': {
157 'clientName': 'ANDROID_CREATOR',
158 'clientVersion': '22.30.100',
159 'androidSdkVersion': 30,
160 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
161 },
162 },
163 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
164 'REQUIRE_JS_PLAYER': False
165 },
166 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
167 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
168 'ios': {
169 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS',
173 'clientVersion': '17.33.2',
174 'deviceModel': 'iPhone14,3',
175 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
176 }
177 },
178 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
179 'REQUIRE_JS_PLAYER': False
180 },
181 'ios_embedded': {
182 'INNERTUBE_CONTEXT': {
183 'client': {
184 'clientName': 'IOS_MESSAGES_EXTENSION',
185 'clientVersion': '17.33.2',
186 'deviceModel': 'iPhone14,3',
187 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
188 },
189 },
190 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
191 'REQUIRE_JS_PLAYER': False
192 },
193 'ios_music': {
194 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
195 'INNERTUBE_CONTEXT': {
196 'client': {
197 'clientName': 'IOS_MUSIC',
198 'clientVersion': '5.21',
199 'deviceModel': 'iPhone14,3',
200 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
201 },
202 },
203 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
204 'REQUIRE_JS_PLAYER': False
205 },
206 'ios_creator': {
207 'INNERTUBE_CONTEXT': {
208 'client': {
209 'clientName': 'IOS_CREATOR',
210 'clientVersion': '22.33.101',
211 'deviceModel': 'iPhone14,3',
212 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
213 },
214 },
215 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
216 'REQUIRE_JS_PLAYER': False
217 },
218 # mweb has 'ultralow' formats
219 # See: https://github.com/yt-dlp/yt-dlp/pull/557
220 'mweb': {
221 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
222 'INNERTUBE_CONTEXT': {
223 'client': {
224 'clientName': 'MWEB',
225 'clientVersion': '2.20220801.00.00',
226 }
227 },
228 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
229 },
230 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
231 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
232 'tv_embedded': {
233 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
234 'INNERTUBE_CONTEXT': {
235 'client': {
236 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
237 'clientVersion': '2.0',
238 },
239 },
240 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
241 },
242 }
243
244
245 def _split_innertube_client(client_name):
246 variant, *base = client_name.rsplit('.', 1)
247 if base:
248 return variant, base[0], variant
249 base, *variant = client_name.split('_', 1)
250 return client_name, base, variant[0] if variant else None
251
252
253 def short_client_name(client_name):
254 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
255 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
256
257
258 def build_innertube_clients():
259 THIRD_PARTY = {
260 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
261 }
262 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
263 priority = qualities(BASE_CLIENTS[::-1])
264
265 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
266 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
267 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
268 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
269 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
270
271 _, base_client, variant = _split_innertube_client(client)
272 ytcfg['priority'] = 10 * priority(base_client)
273
274 if not variant:
275 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
276 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
277 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
278 embedscreen['priority'] -= 3
279 elif variant == 'embedded':
280 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
281 ytcfg['priority'] -= 2
282 else:
283 ytcfg['priority'] -= 3
284
285
286 build_innertube_clients()
287
288
289 class BadgeType(enum.Enum):
290 AVAILABILITY_UNLISTED = enum.auto()
291 AVAILABILITY_PRIVATE = enum.auto()
292 AVAILABILITY_PUBLIC = enum.auto()
293 AVAILABILITY_PREMIUM = enum.auto()
294 AVAILABILITY_SUBSCRIPTION = enum.auto()
295 LIVE_NOW = enum.auto()
296
297
298 class YoutubeBaseInfoExtractor(InfoExtractor):
299 """Provide base functions for Youtube extractors"""
300
301 _RESERVED_NAMES = (
302 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
303 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
304 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
305 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
306
307 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
308
309 # _NETRC_MACHINE = 'youtube'
310
311 # If True it will raise an error if no login info is provided
312 _LOGIN_REQUIRED = False
313
314 _INVIDIOUS_SITES = (
315 # invidious-redirect websites
316 r'(?:www\.)?redirect\.invidious\.io',
317 r'(?:(?:www|dev)\.)?invidio\.us',
318 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
319 r'(?:www\.)?invidious\.pussthecat\.org',
320 r'(?:www\.)?invidious\.zee\.li',
321 r'(?:www\.)?invidious\.ethibox\.fr',
322 r'(?:www\.)?iv\.ggtyler\.dev',
323 r'(?:www\.)?inv\.vern\.i2p',
324 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
325 r'(?:www\.)?inv\.riverside\.rocks',
326 r'(?:www\.)?invidious\.silur\.me',
327 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
328 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
329 r'(?:www\.)?invidious\.slipfox\.xyz',
330 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
331 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
332 r'(?:www\.)?invidious\.tiekoetter\.com',
333 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
334 r'(?:www\.)?invidious\.nerdvpn\.de',
335 r'(?:www\.)?invidious\.weblibre\.org',
336 r'(?:www\.)?inv\.odyssey346\.dev',
337 r'(?:www\.)?invidious\.dhusch\.de',
338 r'(?:www\.)?iv\.melmac\.space',
339 r'(?:www\.)?watch\.thekitty\.zone',
340 r'(?:www\.)?invidious\.privacydev\.net',
341 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
342 r'(?:www\.)?invidious\.drivet\.xyz',
343 r'(?:www\.)?vid\.priv\.au',
344 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
345 r'(?:www\.)?inv\.vern\.cc',
346 r'(?:www\.)?invidious\.esmailelbob\.xyz',
347 r'(?:www\.)?invidious\.sethforprivacy\.com',
348 r'(?:www\.)?yt\.oelrichsgarcia\.de',
349 r'(?:www\.)?yt\.artemislena\.eu',
350 r'(?:www\.)?invidious\.flokinet\.to',
351 r'(?:www\.)?invidious\.baczek\.me',
352 r'(?:www\.)?y\.com\.sb',
353 r'(?:www\.)?invidious\.epicsite\.xyz',
354 r'(?:www\.)?invidious\.lidarshield\.cloud',
355 r'(?:www\.)?yt\.funami\.tech',
356 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
357 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
358 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
359 # youtube-dl invidious instances list
360 r'(?:(?:www|no)\.)?invidiou\.sh',
361 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
362 r'(?:www\.)?invidious\.kabi\.tk',
363 r'(?:www\.)?invidious\.mastodon\.host',
364 r'(?:www\.)?invidious\.zapashcanon\.fr',
365 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
366 r'(?:www\.)?invidious\.tinfoil-hat\.net',
367 r'(?:www\.)?invidious\.himiko\.cloud',
368 r'(?:www\.)?invidious\.reallyancient\.tech',
369 r'(?:www\.)?invidious\.tube',
370 r'(?:www\.)?invidiou\.site',
371 r'(?:www\.)?invidious\.site',
372 r'(?:www\.)?invidious\.xyz',
373 r'(?:www\.)?invidious\.nixnet\.xyz',
374 r'(?:www\.)?invidious\.048596\.xyz',
375 r'(?:www\.)?invidious\.drycat\.fr',
376 r'(?:www\.)?inv\.skyn3t\.in',
377 r'(?:www\.)?tube\.poal\.co',
378 r'(?:www\.)?tube\.connect\.cafe',
379 r'(?:www\.)?vid\.wxzm\.sx',
380 r'(?:www\.)?vid\.mint\.lgbt',
381 r'(?:www\.)?vid\.puffyan\.us',
382 r'(?:www\.)?yewtu\.be',
383 r'(?:www\.)?yt\.elukerio\.org',
384 r'(?:www\.)?yt\.lelux\.fi',
385 r'(?:www\.)?invidious\.ggc-project\.de',
386 r'(?:www\.)?yt\.maisputain\.ovh',
387 r'(?:www\.)?ytprivate\.com',
388 r'(?:www\.)?invidious\.13ad\.de',
389 r'(?:www\.)?invidious\.toot\.koeln',
390 r'(?:www\.)?invidious\.fdn\.fr',
391 r'(?:www\.)?watch\.nettohikari\.com',
392 r'(?:www\.)?invidious\.namazso\.eu',
393 r'(?:www\.)?invidious\.silkky\.cloud',
394 r'(?:www\.)?invidious\.exonip\.de',
395 r'(?:www\.)?invidious\.riverside\.rocks',
396 r'(?:www\.)?invidious\.blamefran\.net',
397 r'(?:www\.)?invidious\.moomoo\.de',
398 r'(?:www\.)?ytb\.trom\.tf',
399 r'(?:www\.)?yt\.cyberhost\.uk',
400 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
401 r'(?:www\.)?qklhadlycap4cnod\.onion',
402 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
403 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
404 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
405 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
406 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
407 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
408 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
409 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
410 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
411 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
412 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
413 r'(?:www\.)?piped\.kavin\.rocks',
414 r'(?:www\.)?piped\.tokhmi\.xyz',
415 r'(?:www\.)?piped\.syncpundit\.io',
416 r'(?:www\.)?piped\.mha\.fi',
417 r'(?:www\.)?watch\.whatever\.social',
418 r'(?:www\.)?piped\.garudalinux\.org',
419 r'(?:www\.)?piped\.rivo\.lol',
420 r'(?:www\.)?piped-libre\.kavin\.rocks',
421 r'(?:www\.)?yt\.jae\.fi',
422 r'(?:www\.)?piped\.mint\.lgbt',
423 r'(?:www\.)?il\.ax',
424 r'(?:www\.)?piped\.esmailelbob\.xyz',
425 r'(?:www\.)?piped\.projectsegfau\.lt',
426 r'(?:www\.)?piped\.privacydev\.net',
427 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
428 r'(?:www\.)?piped\.smnz\.de',
429 r'(?:www\.)?piped\.adminforge\.de',
430 r'(?:www\.)?watch\.whatevertinfoil\.de',
431 r'(?:www\.)?piped\.qdi\.fi',
432 r'(?:www\.)?piped\.video',
433 r'(?:www\.)?piped\.aeong\.one',
434 r'(?:www\.)?piped\.moomoo\.me',
435 r'(?:www\.)?piped\.chauvet\.pro',
436 r'(?:www\.)?watch\.leptons\.xyz',
437 r'(?:www\.)?pd\.vern\.cc',
438 r'(?:www\.)?piped\.hostux\.net',
439 r'(?:www\.)?piped\.lunar\.icu',
440 # Hyperpipe instances from https://hyperpipe.codeberg.page/
441 r'(?:www\.)?hyperpipe\.surge\.sh',
442 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
443 r'(?:www\.)?listen\.whatever\.social',
444 r'(?:www\.)?music\.adminforge\.de',
445 )
446
447 # extracted from account/account_menu ep
448 # XXX: These are the supported YouTube UI and API languages,
449 # which is slightly different from languages supported for translation in YouTube studio
450 _SUPPORTED_LANG_CODES = [
451 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
452 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
453 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
454 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
455 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
456 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
457 ]
458
459 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
460
461 @functools.cached_property
462 def _preferred_lang(self):
463 """
464 Returns a language code supported by YouTube for the user preferred language.
465 Returns None if no preferred language set.
466 """
467 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
468 if not preferred_lang:
469 return
470 if preferred_lang not in self._SUPPORTED_LANG_CODES:
471 raise ExtractorError(
472 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
473 expected=True)
474 elif preferred_lang != 'en':
475 self.report_warning(
476 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
477 return preferred_lang
478
479 def _initialize_consent(self):
480 cookies = self._get_cookies('https://www.youtube.com/')
481 if cookies.get('__Secure-3PSID'):
482 return
483 consent_id = None
484 consent = cookies.get('CONSENT')
485 if consent:
486 if 'YES' in consent.value:
487 return
488 consent_id = self._search_regex(
489 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
490 if not consent_id:
491 consent_id = random.randint(100, 999)
492 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
493
494 def _initialize_pref(self):
495 cookies = self._get_cookies('https://www.youtube.com/')
496 pref_cookie = cookies.get('PREF')
497 pref = {}
498 if pref_cookie:
499 try:
500 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
501 except ValueError:
502 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
503 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
504 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
505
506 def _real_initialize(self):
507 self._initialize_pref()
508 self._initialize_consent()
509 self._check_login_required()
510
511 def _check_login_required(self):
512 if self._LOGIN_REQUIRED and not self._cookies_passed:
513 self.raise_login_required('Login details are needed to download this content', method='cookies')
514
515 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
516 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
517
518 def _get_default_ytcfg(self, client='web'):
519 return copy.deepcopy(INNERTUBE_CLIENTS[client])
520
521 def _get_innertube_host(self, client='web'):
522 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
523
524 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
525 # try_get but with fallback to default ytcfg client values when present
526 _func = lambda y: try_get(y, getter, expected_type)
527 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
528
529 def _extract_client_name(self, ytcfg, default_client='web'):
530 return self._ytcfg_get_safe(
531 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
532 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
533
534 def _extract_client_version(self, ytcfg, default_client='web'):
535 return self._ytcfg_get_safe(
536 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
537 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
538
539 def _select_api_hostname(self, req_api_hostname, default_client=None):
540 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
541 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
542
543 def _extract_api_key(self, ytcfg=None, default_client='web'):
544 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
545
546 def _extract_context(self, ytcfg=None, default_client='web'):
547 context = get_first(
548 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
549 # Enforce language and tz for extraction
550 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
551 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
552 return context
553
554 _SAPISID = None
555
556 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
557 time_now = round(time.time())
558 if self._SAPISID is None:
559 yt_cookies = self._get_cookies('https://www.youtube.com')
560 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
561 # See: https://github.com/yt-dlp/yt-dlp/issues/393
562 sapisid_cookie = dict_get(
563 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
564 if sapisid_cookie and sapisid_cookie.value:
565 self._SAPISID = sapisid_cookie.value
566 self.write_debug('Extracted SAPISID cookie')
567 # SAPISID cookie is required if not already present
568 if not yt_cookies.get('SAPISID'):
569 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
570 self._set_cookie(
571 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
572 else:
573 self._SAPISID = False
574 if not self._SAPISID:
575 return None
576 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
577 sapisidhash = hashlib.sha1(
578 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
579 return f'SAPISIDHASH {time_now}_{sapisidhash}'
580
581 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
582 note='Downloading API JSON', errnote='Unable to download API page',
583 context=None, api_key=None, api_hostname=None, default_client='web'):
584
585 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
586 data.update(query)
587 real_headers = self.generate_api_headers(default_client=default_client)
588 real_headers.update({'content-type': 'application/json'})
589 if headers:
590 real_headers.update(headers)
591 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
592 or api_key or self._extract_api_key(default_client=default_client))
593 return self._download_json(
594 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
595 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
596 data=json.dumps(data).encode('utf8'), headers=real_headers,
597 query={'key': api_key, 'prettyPrint': 'false'})
598
599 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
600 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
601
602 @staticmethod
603 def _extract_session_index(*data):
604 """
605 Index of current account in account list.
606 See: https://github.com/yt-dlp/yt-dlp/pull/519
607 """
608 for ytcfg in data:
609 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
610 if session_index is not None:
611 return session_index
612
613 # Deprecated?
614 def _extract_identity_token(self, ytcfg=None, webpage=None):
615 if ytcfg:
616 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
617 if token:
618 return token
619 if webpage:
620 return self._search_regex(
621 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
622 'identity token', default=None, fatal=False)
623
624 @staticmethod
625 def _extract_account_syncid(*args):
626 """
627 Extract syncId required to download private playlists of secondary channels
628 @params response and/or ytcfg
629 """
630 for data in args:
631 # ytcfg includes channel_syncid if on secondary channel
632 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
633 if delegated_sid:
634 return delegated_sid
635 sync_ids = (try_get(
636 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
637 lambda x: x['DATASYNC_ID']), str) or '').split('||')
638 if len(sync_ids) >= 2 and sync_ids[1]:
639 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
640 # and just "user_syncid||" for primary channel. We only want the channel_syncid
641 return sync_ids[0]
642
643 @staticmethod
644 def _extract_visitor_data(*args):
645 """
646 Extracts visitorData from an API response or ytcfg
647 Appears to be used to track session state
648 """
649 return get_first(
650 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
651 expected_type=str)
652
653 @functools.cached_property
654 def is_authenticated(self):
655 return bool(self._generate_sapisidhash_header())
656
657 def extract_ytcfg(self, video_id, webpage):
658 if not webpage:
659 return {}
660 return self._parse_json(
661 self._search_regex(
662 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
663 default='{}'), video_id, fatal=False) or {}
664
665 def generate_api_headers(
666 self, *, ytcfg=None, account_syncid=None, session_index=None,
667 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
668
669 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
670 headers = {
671 'X-YouTube-Client-Name': str(
672 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
673 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
674 'Origin': origin,
675 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
676 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
677 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
678 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
679 }
680 if session_index is None:
681 session_index = self._extract_session_index(ytcfg)
682 if account_syncid or session_index is not None:
683 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
684
685 auth = self._generate_sapisidhash_header(origin)
686 if auth is not None:
687 headers['Authorization'] = auth
688 headers['X-Origin'] = origin
689 return filter_dict(headers)
690
691 def _download_ytcfg(self, client, video_id):
692 url = {
693 'web': 'https://www.youtube.com',
694 'web_music': 'https://music.youtube.com',
695 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
696 }.get(client)
697 if not url:
698 return {}
699 webpage = self._download_webpage(
700 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
701 return self.extract_ytcfg(video_id, webpage) or {}
702
703 @staticmethod
704 def _build_api_continuation_query(continuation, ctp=None):
705 query = {
706 'continuation': continuation
707 }
708 # TODO: Inconsistency with clickTrackingParams.
709 # Currently we have a fixed ctp contained within context (from ytcfg)
710 # and a ctp in root query for continuation.
711 if ctp:
712 query['clickTracking'] = {'clickTrackingParams': ctp}
713 return query
714
715 @classmethod
716 def _extract_next_continuation_data(cls, renderer):
717 next_continuation = try_get(
718 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
719 lambda x: x['continuation']['reloadContinuationData']), dict)
720 if not next_continuation:
721 return
722 continuation = next_continuation.get('continuation')
723 if not continuation:
724 return
725 ctp = next_continuation.get('clickTrackingParams')
726 return cls._build_api_continuation_query(continuation, ctp)
727
728 @classmethod
729 def _extract_continuation_ep_data(cls, continuation_ep: dict):
730 if isinstance(continuation_ep, dict):
731 continuation = try_get(
732 continuation_ep, lambda x: x['continuationCommand']['token'], str)
733 if not continuation:
734 return
735 ctp = continuation_ep.get('clickTrackingParams')
736 return cls._build_api_continuation_query(continuation, ctp)
737
738 @classmethod
739 def _extract_continuation(cls, renderer):
740 next_continuation = cls._extract_next_continuation_data(renderer)
741 if next_continuation:
742 return next_continuation
743
744 return traverse_obj(renderer, (
745 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
746 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
747 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
748
749 @classmethod
750 def _extract_alerts(cls, data):
751 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
752 if not isinstance(alert_dict, dict):
753 continue
754 for alert in alert_dict.values():
755 alert_type = alert.get('type')
756 if not alert_type:
757 continue
758 message = cls._get_text(alert, 'text')
759 if message:
760 yield alert_type, message
761
762 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
763 errors, warnings = [], []
764 for alert_type, alert_message in alerts:
765 if alert_type.lower() == 'error' and fatal:
766 errors.append([alert_type, alert_message])
767 elif alert_message not in self._IGNORED_WARNINGS:
768 warnings.append([alert_type, alert_message])
769
770 for alert_type, alert_message in (warnings + errors[:-1]):
771 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
772 if errors:
773 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
774
775 def _extract_and_report_alerts(self, data, *args, **kwargs):
776 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
777
778 def _extract_badges(self, renderer: dict):
779 privacy_icon_map = {
780 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
781 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
782 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
783 }
784
785 badge_style_map = {
786 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
787 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
788 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
789 }
790
791 label_map = {
792 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
793 'private': BadgeType.AVAILABILITY_PRIVATE,
794 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
795 'live': BadgeType.LIVE_NOW,
796 'premium': BadgeType.AVAILABILITY_PREMIUM
797 }
798
799 badges = []
800 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')):
801 badge_type = (
802 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
803 or badge_style_map.get(traverse_obj(badge, 'style'))
804 )
805 if badge_type:
806 badges.append({'type': badge_type})
807 continue
808
809 # fallback, won't work in some languages
810 label = traverse_obj(badge, 'label', expected_type=str, default='')
811 for match, label_badge_type in label_map.items():
812 if match in label.lower():
813 badges.append({'type': badge_type})
814 continue
815
816 return badges
817
818 @staticmethod
819 def _has_badge(badges, badge_type):
820 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
821
822 @staticmethod
823 def _get_text(data, *path_list, max_runs=None):
824 for path in path_list or [None]:
825 if path is None:
826 obj = [data]
827 else:
828 obj = traverse_obj(data, path, default=[])
829 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
830 obj = [obj]
831 for item in obj:
832 text = try_get(item, lambda x: x['simpleText'], str)
833 if text:
834 return text
835 runs = try_get(item, lambda x: x['runs'], list) or []
836 if not runs and isinstance(item, list):
837 runs = item
838
839 runs = runs[:min(len(runs), max_runs or len(runs))]
840 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
841 if text:
842 return text
843
844 def _get_count(self, data, *path_list):
845 count_text = self._get_text(data, *path_list) or ''
846 count = parse_count(count_text)
847 if count is None:
848 count = str_to_int(
849 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
850 return count
851
852 @staticmethod
853 def _extract_thumbnails(data, *path_list):
854 """
855 Extract thumbnails from thumbnails dict
856 @param path_list: path list to level that contains 'thumbnails' key
857 """
858 thumbnails = []
859 for path in path_list or [()]:
860 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
861 thumbnail_url = url_or_none(thumbnail.get('url'))
862 if not thumbnail_url:
863 continue
864 # Sometimes youtube gives a wrong thumbnail URL. See:
865 # https://github.com/yt-dlp/yt-dlp/issues/233
866 # https://github.com/ytdl-org/youtube-dl/issues/28023
867 if 'maxresdefault' in thumbnail_url:
868 thumbnail_url = thumbnail_url.split('?')[0]
869 thumbnails.append({
870 'url': thumbnail_url,
871 'height': int_or_none(thumbnail.get('height')),
872 'width': int_or_none(thumbnail.get('width')),
873 })
874 return thumbnails
875
876 @staticmethod
877 def extract_relative_time(relative_time_text):
878 """
879 Extracts a relative time from string and converts to dt object
880 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
881 """
882 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
883 if mobj:
884 start = mobj.group('start')
885 if start:
886 return datetime_from_str(start)
887 try:
888 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
889 except ValueError:
890 return None
891
892 def _parse_time_text(self, text):
893 if not text:
894 return
895 dt = self.extract_relative_time(text)
896 timestamp = None
897 if isinstance(dt, datetime.datetime):
898 timestamp = calendar.timegm(dt.timetuple())
899
900 if timestamp is None:
901 timestamp = (
902 unified_timestamp(text) or unified_timestamp(
903 self._search_regex(
904 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
905 text.lower(), 'time text', default=None)))
906
907 if text and timestamp is None and self._preferred_lang in (None, 'en'):
908 self.report_warning(
909 f'Cannot parse localized time text "{text}"', only_once=True)
910 return timestamp
911
912 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
913 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
914 default_client='web'):
915 for retry in self.RetryManager():
916 try:
917 response = self._call_api(
918 ep=ep, fatal=True, headers=headers,
919 video_id=item_id, query=query, note=note,
920 context=self._extract_context(ytcfg, default_client),
921 api_key=self._extract_api_key(ytcfg, default_client),
922 api_hostname=api_hostname, default_client=default_client)
923 except ExtractorError as e:
924 if not isinstance(e.cause, network_exceptions):
925 return self._error_or_warning(e, fatal=fatal)
926 elif not isinstance(e.cause, urllib.error.HTTPError):
927 retry.error = e
928 continue
929
930 first_bytes = e.cause.read(512)
931 if not is_html(first_bytes):
932 yt_error = try_get(
933 self._parse_json(
934 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
935 lambda x: x['error']['message'], str)
936 if yt_error:
937 self._report_alerts([('ERROR', yt_error)], fatal=False)
938 # Downloading page may result in intermittent 5xx HTTP error
939 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
940 # We also want to catch all other network exceptions since errors in later pages can be troublesome
941 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
942 if e.cause.code not in (403, 429):
943 retry.error = e
944 continue
945 return self._error_or_warning(e, fatal=fatal)
946
947 try:
948 self._extract_and_report_alerts(response, only_once=True)
949 except ExtractorError as e:
950 # YouTube servers may return errors we want to retry on in a 200 OK response
951 # See: https://github.com/yt-dlp/yt-dlp/issues/839
952 if 'unknown error' in e.msg.lower():
953 retry.error = e
954 continue
955 return self._error_or_warning(e, fatal=fatal)
956 # Youtube sometimes sends incomplete data
957 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
958 if not traverse_obj(response, *variadic(check_get_keys)):
959 retry.error = ExtractorError('Incomplete data received', expected=True)
960 continue
961
962 return response
963
964 @staticmethod
965 def is_music_url(url):
966 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
967
968 def _extract_video(self, renderer):
969 video_id = renderer.get('videoId')
970
971 reel_header_renderer = traverse_obj(renderer, (
972 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
973 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
974
975 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
976 description = self._get_text(renderer, 'descriptionSnippet')
977
978 duration = int_or_none(renderer.get('lengthSeconds'))
979 if duration is None:
980 duration = parse_duration(self._get_text(
981 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
982 if duration is None:
983 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
984 duration = parse_duration(self._search_regex(
985 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
986 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
987 video_id, default=None, group='duration'))
988
989 channel_id = traverse_obj(
990 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
991 expected_type=str, get_all=False)
992 if not channel_id:
993 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
994
995 overlay_style = traverse_obj(
996 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
997 get_all=False, expected_type=str)
998 badges = self._extract_badges(renderer)
999
1000 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
1001 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1002 expected_type=str)) or ''
1003 url = f'https://www.youtube.com/watch?v={video_id}'
1004 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
1005 url = f'https://www.youtube.com/shorts/{video_id}'
1006
1007 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1008 or self._get_text(reel_header_renderer, 'timestampText') or '')
1009 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1010
1011 live_status = (
1012 'is_upcoming' if scheduled_timestamp is not None
1013 else 'was_live' if 'streamed' in time_text.lower()
1014 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1015 else None)
1016
1017 # videoInfo is a string like '50K views • 10 years ago'.
1018 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1019 view_count = (0 if 'no views' in view_count_text.lower()
1020 else self._get_count({'simpleText': view_count_text}))
1021 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1022
1023 return {
1024 '_type': 'url',
1025 'ie_key': YoutubeIE.ie_key(),
1026 'id': video_id,
1027 'url': url,
1028 'title': title,
1029 'description': description,
1030 'duration': duration,
1031 'channel_id': channel_id,
1032 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
1033 or self._get_text(reel_header_renderer, 'channelTitleText')),
1034 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
1035 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
1036 'timestamp': (self._parse_time_text(time_text)
1037 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1038 else None),
1039 'release_timestamp': scheduled_timestamp,
1040 'availability':
1041 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1042 else self._availability(
1043 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1044 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1045 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
1046 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
1047 view_count_field: view_count,
1048 'live_status': live_status
1049 }
1050
1051
1052 class YoutubeIE(YoutubeBaseInfoExtractor):
1053 IE_DESC = 'YouTube'
1054 _VALID_URL = r"""(?x)^
1055 (
1056 (?:https?://|//) # http(s):// or protocol-independent URL
1057 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1058 (?:www\.)?deturl\.com/www\.youtube\.com|
1059 (?:www\.)?pwnyoutube\.com|
1060 (?:www\.)?hooktube\.com|
1061 (?:www\.)?yourepeat\.com|
1062 tube\.majestyc\.net|
1063 %(invidious)s|
1064 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
1065 (?:.*?\#/)? # handle anchor (#/) redirect urls
1066 (?: # the various things that can precede the ID:
1067 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
1068 |(?: # or the v= param in all its forms
1069 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
1070 (?:\?|\#!?) # the params delimiter ? or # or #!
1071 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
1072 v=
1073 )
1074 ))
1075 |(?:
1076 youtu\.be| # just youtu.be/xxxx
1077 vid\.plus| # or vid.plus/xxxx
1078 zwearz\.com/watch| # or zwearz.com/watch/xxxx
1079 %(invidious)s
1080 )/
1081 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
1082 )
1083 )? # all until now is optional -> you can pass the naked ID
1084 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
1085 (?(1).+)? # if we found the ID, everything can follow
1086 (?:\#|$)""" % {
1087 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
1088 }
1089 _EMBED_REGEX = [
1090 r'''(?x)
1091 (?:
1092 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
1093 data-video-url=|
1094 <embed[^>]+?src=|
1095 embedSWF\(?:\s*|
1096 <object[^>]+data=|
1097 new\s+SWFObject\(
1098 )
1099 (["\'])
1100 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1101 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1102 \1''',
1103 # https://wordpress.org/plugins/lazy-load-for-videos/
1104 r'''(?xs)
1105 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1106 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1107 ]
1108 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
1109
1110 _PLAYER_INFO_RE = (
1111 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1112 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
1113 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
1114 )
1115 _formats = {
1116 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1117 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1118 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1119 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1120 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1121 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1122 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1123 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1124 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
1125 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1126 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1127 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1128 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1129 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1130 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1131 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1132 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1133 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1134
1135
1136 # 3D videos
1137 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1138 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1139 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1140 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1141 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1142 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1143 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1144
1145 # Apple HTTP Live Streaming
1146 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1147 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1148 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1149 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1150 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1151 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1152 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1153 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
1154
1155 # DASH mp4 video
1156 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1157 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1158 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1159 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1160 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
1161 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
1162 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1163 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1164 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1165 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1166 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1167 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1168
1169 # Dash mp4 audio
1170 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1171 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1172 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1173 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1174 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1175 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1176 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1177
1178 # Dash webm
1179 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1180 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1181 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1182 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1183 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1184 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1185 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1186 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1187 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1188 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1189 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1190 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1191 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1192 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1193 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1194 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1195 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1196 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1197 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1198 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1199 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1200 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1201
1202 # Dash webm audio
1203 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1204 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1205
1206 # Dash webm audio with opus inside
1207 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1208 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1209 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1210
1211 # RTMP (unnamed)
1212 '_rtmp': {'protocol': 'rtmp'},
1213
1214 # av01 video only formats sometimes served with "unknown" codecs
1215 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1216 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1217 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1218 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1219 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1220 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1221 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1222 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1223 }
1224 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1225
1226 _GEO_BYPASS = False
1227
1228 IE_NAME = 'youtube'
1229 _TESTS = [
1230 {
1231 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1232 'info_dict': {
1233 'id': 'BaW_jenozKc',
1234 'ext': 'mp4',
1235 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1236 'uploader': 'Philipp Hagemeister',
1237 'uploader_id': 'phihag',
1238 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1239 'channel': 'Philipp Hagemeister',
1240 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1241 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1242 'upload_date': '20121002',
1243 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1244 'categories': ['Science & Technology'],
1245 'tags': ['youtube-dl'],
1246 'duration': 10,
1247 'view_count': int,
1248 'like_count': int,
1249 'availability': 'public',
1250 'playable_in_embed': True,
1251 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1252 'live_status': 'not_live',
1253 'age_limit': 0,
1254 'start_time': 1,
1255 'end_time': 9,
1256 'comment_count': int,
1257 'channel_follower_count': int
1258 }
1259 },
1260 {
1261 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1262 'note': 'Embed-only video (#1746)',
1263 'info_dict': {
1264 'id': 'yZIXLfi8CZQ',
1265 'ext': 'mp4',
1266 'upload_date': '20120608',
1267 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1268 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1269 'uploader': 'SET India',
1270 'uploader_id': 'setindia',
1271 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1272 'age_limit': 18,
1273 },
1274 'skip': 'Private video',
1275 },
1276 {
1277 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1278 'note': 'Use the first video ID in the URL',
1279 'info_dict': {
1280 'id': 'BaW_jenozKc',
1281 'ext': 'mp4',
1282 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1283 'uploader': 'Philipp Hagemeister',
1284 'uploader_id': 'phihag',
1285 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1286 'channel': 'Philipp Hagemeister',
1287 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1288 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1289 'upload_date': '20121002',
1290 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1291 'categories': ['Science & Technology'],
1292 'tags': ['youtube-dl'],
1293 'duration': 10,
1294 'view_count': int,
1295 'like_count': int,
1296 'availability': 'public',
1297 'playable_in_embed': True,
1298 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1299 'live_status': 'not_live',
1300 'age_limit': 0,
1301 'comment_count': int,
1302 'channel_follower_count': int
1303 },
1304 'params': {
1305 'skip_download': True,
1306 },
1307 },
1308 {
1309 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1310 'note': '256k DASH audio (format 141) via DASH manifest',
1311 'info_dict': {
1312 'id': 'a9LDPn-MO4I',
1313 'ext': 'm4a',
1314 'upload_date': '20121002',
1315 'uploader_id': '8KVIDEO',
1316 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1317 'description': '',
1318 'uploader': '8KVIDEO',
1319 'title': 'UHDTV TEST 8K VIDEO.mp4'
1320 },
1321 'params': {
1322 'youtube_include_dash_manifest': True,
1323 'format': '141',
1324 },
1325 'skip': 'format 141 not served anymore',
1326 },
1327 # DASH manifest with encrypted signature
1328 {
1329 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1330 'info_dict': {
1331 'id': 'IB3lcPjvWLA',
1332 'ext': 'm4a',
1333 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1334 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1335 'duration': 244,
1336 'uploader': 'AfrojackVEVO',
1337 'uploader_id': 'AfrojackVEVO',
1338 'upload_date': '20131011',
1339 'abr': 129.495,
1340 'like_count': int,
1341 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1342 'playable_in_embed': True,
1343 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1344 'view_count': int,
1345 'track': 'The Spark',
1346 'live_status': 'not_live',
1347 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1348 'channel': 'Afrojack',
1349 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1350 'tags': 'count:19',
1351 'availability': 'public',
1352 'categories': ['Music'],
1353 'age_limit': 0,
1354 'alt_title': 'The Spark',
1355 'channel_follower_count': int
1356 },
1357 'params': {
1358 'youtube_include_dash_manifest': True,
1359 'format': '141/bestaudio[ext=m4a]',
1360 },
1361 },
1362 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1363 {
1364 'note': 'Embed allowed age-gate video',
1365 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1366 'info_dict': {
1367 'id': 'HtVdAasjOgU',
1368 'ext': 'mp4',
1369 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1370 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1371 'duration': 142,
1372 'uploader': 'The Witcher',
1373 'uploader_id': 'WitcherGame',
1374 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1375 'upload_date': '20140605',
1376 'age_limit': 18,
1377 'categories': ['Gaming'],
1378 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1379 'availability': 'needs_auth',
1380 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1381 'like_count': int,
1382 'channel': 'The Witcher',
1383 'live_status': 'not_live',
1384 'tags': 'count:17',
1385 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1386 'playable_in_embed': True,
1387 'view_count': int,
1388 'channel_follower_count': int
1389 },
1390 },
1391 {
1392 'note': 'Age-gate video with embed allowed in public site',
1393 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1394 'info_dict': {
1395 'id': 'HsUATh_Nc2U',
1396 'ext': 'mp4',
1397 'title': 'Godzilla 2 (Official Video)',
1398 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1399 'upload_date': '20200408',
1400 'uploader_id': 'FlyingKitty900',
1401 'uploader': 'FlyingKitty',
1402 'age_limit': 18,
1403 'availability': 'needs_auth',
1404 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1405 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1406 'channel': 'FlyingKitty',
1407 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1408 'view_count': int,
1409 'categories': ['Entertainment'],
1410 'live_status': 'not_live',
1411 'tags': ['Flyingkitty', 'godzilla 2'],
1412 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1413 'like_count': int,
1414 'duration': 177,
1415 'playable_in_embed': True,
1416 'channel_follower_count': int
1417 },
1418 },
1419 {
1420 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1421 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1422 'info_dict': {
1423 'id': 'Tq92D6wQ1mg',
1424 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1425 'ext': 'mp4',
1426 'upload_date': '20191228',
1427 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1428 'uploader': 'Projekt Melody',
1429 'description': 'md5:17eccca93a786d51bc67646756894066',
1430 'age_limit': 18,
1431 'like_count': int,
1432 'availability': 'needs_auth',
1433 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1434 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1435 'view_count': int,
1436 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1437 'channel': 'Projekt Melody',
1438 'live_status': 'not_live',
1439 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1440 'playable_in_embed': True,
1441 'categories': ['Entertainment'],
1442 'duration': 106,
1443 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1444 'comment_count': int,
1445 'channel_follower_count': int
1446 },
1447 },
1448 {
1449 'note': 'Non-Agegated non-embeddable video',
1450 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1451 'info_dict': {
1452 'id': 'MeJVWBSsPAY',
1453 'ext': 'mp4',
1454 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1455 'uploader': 'Herr Lurik',
1456 'uploader_id': 'st3in234',
1457 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1458 'upload_date': '20130730',
1459 'track': 'Such mich find mich',
1460 'age_limit': 0,
1461 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1462 'like_count': int,
1463 'playable_in_embed': False,
1464 'creator': 'OOMPH!',
1465 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1466 'view_count': int,
1467 'alt_title': 'Such mich find mich',
1468 'duration': 210,
1469 'channel': 'Herr Lurik',
1470 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1471 'categories': ['Music'],
1472 'availability': 'public',
1473 'uploader_url': 'http://www.youtube.com/user/st3in234',
1474 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1475 'live_status': 'not_live',
1476 'artist': 'OOMPH!',
1477 'channel_follower_count': int
1478 },
1479 },
1480 {
1481 'note': 'Non-bypassable age-gated video',
1482 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1483 'only_matching': True,
1484 },
1485 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1486 # YouTube Red ad is not captured for creator
1487 {
1488 'url': '__2ABJjxzNo',
1489 'info_dict': {
1490 'id': '__2ABJjxzNo',
1491 'ext': 'mp4',
1492 'duration': 266,
1493 'upload_date': '20100430',
1494 'uploader_id': 'deadmau5',
1495 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1496 'creator': 'deadmau5',
1497 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1498 'uploader': 'deadmau5',
1499 'title': 'Deadmau5 - Some Chords (HD)',
1500 'alt_title': 'Some Chords',
1501 'availability': 'public',
1502 'tags': 'count:14',
1503 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1504 'view_count': int,
1505 'live_status': 'not_live',
1506 'channel': 'deadmau5',
1507 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1508 'like_count': int,
1509 'track': 'Some Chords',
1510 'artist': 'deadmau5',
1511 'playable_in_embed': True,
1512 'age_limit': 0,
1513 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1514 'categories': ['Music'],
1515 'album': 'Some Chords',
1516 'channel_follower_count': int
1517 },
1518 'expected_warnings': [
1519 'DASH manifest missing',
1520 ]
1521 },
1522 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1523 {
1524 'url': 'lqQg6PlCWgI',
1525 'info_dict': {
1526 'id': 'lqQg6PlCWgI',
1527 'ext': 'mp4',
1528 'duration': 6085,
1529 'upload_date': '20150827',
1530 'uploader_id': 'olympic',
1531 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1532 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1533 'uploader': 'Olympics',
1534 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1535 'like_count': int,
1536 'release_timestamp': 1343767800,
1537 'playable_in_embed': True,
1538 'categories': ['Sports'],
1539 'release_date': '20120731',
1540 'channel': 'Olympics',
1541 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1542 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1543 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1544 'age_limit': 0,
1545 'availability': 'public',
1546 'live_status': 'was_live',
1547 'view_count': int,
1548 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1549 'channel_follower_count': int
1550 },
1551 'params': {
1552 'skip_download': 'requires avconv',
1553 }
1554 },
1555 # Non-square pixels
1556 {
1557 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1558 'info_dict': {
1559 'id': '_b-2C3KPAM0',
1560 'ext': 'mp4',
1561 'stretched_ratio': 16 / 9.,
1562 'duration': 85,
1563 'upload_date': '20110310',
1564 'uploader_id': 'AllenMeow',
1565 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1566 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
1567 'uploader': '孫ᄋᄅ',
1568 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1569 'playable_in_embed': True,
1570 'channel': '孫ᄋᄅ',
1571 'age_limit': 0,
1572 'tags': 'count:11',
1573 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1574 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1575 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1576 'view_count': int,
1577 'categories': ['People & Blogs'],
1578 'like_count': int,
1579 'live_status': 'not_live',
1580 'availability': 'unlisted',
1581 'comment_count': int,
1582 'channel_follower_count': int
1583 },
1584 },
1585 # url_encoded_fmt_stream_map is empty string
1586 {
1587 'url': 'qEJwOuvDf7I',
1588 'info_dict': {
1589 'id': 'qEJwOuvDf7I',
1590 'ext': 'webm',
1591 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1592 'description': '',
1593 'upload_date': '20150404',
1594 'uploader_id': 'spbelect',
1595 'uploader': 'Наблюдатели Петербурга',
1596 },
1597 'params': {
1598 'skip_download': 'requires avconv',
1599 },
1600 'skip': 'This live event has ended.',
1601 },
1602 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1603 {
1604 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1605 'info_dict': {
1606 'id': 'FIl7x6_3R5Y',
1607 'ext': 'webm',
1608 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1609 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1610 'duration': 220,
1611 'upload_date': '20150625',
1612 'uploader_id': 'dorappi2000',
1613 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1614 'uploader': 'dorappi2000',
1615 'formats': 'mincount:31',
1616 },
1617 'skip': 'not actual anymore',
1618 },
1619 # DASH manifest with segment_list
1620 {
1621 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1622 'md5': '8ce563a1d667b599d21064e982ab9e31',
1623 'info_dict': {
1624 'id': 'CsmdDsKjzN8',
1625 'ext': 'mp4',
1626 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1627 'uploader': 'Airtek',
1628 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1629 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1630 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1631 },
1632 'params': {
1633 'youtube_include_dash_manifest': True,
1634 'format': '135', # bestvideo
1635 },
1636 'skip': 'This live event has ended.',
1637 },
1638 {
1639 # Multifeed videos (multiple cameras), URL can be of any Camera
1640 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
1641 'info_dict': {
1642 'id': 'zaPI8MvL8pg',
1643 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1644 'description': 'md5:563ccbc698b39298481ca3c571169519',
1645 },
1646 'playlist': [{
1647 'info_dict': {
1648 'id': 'j5yGuxZ8lLU',
1649 'ext': 'mp4',
1650 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
1651 'uploader': 'WiiLikeToPlay',
1652 'description': 'md5:563ccbc698b39298481ca3c571169519',
1653 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1654 'duration': 10120,
1655 'channel_follower_count': int,
1656 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1657 'availability': 'public',
1658 'playable_in_embed': True,
1659 'upload_date': '20131105',
1660 'uploader_id': 'WiiRikeToPray',
1661 'categories': ['Gaming'],
1662 'live_status': 'was_live',
1663 'tags': 'count:24',
1664 'release_timestamp': 1383701910,
1665 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1666 'comment_count': int,
1667 'age_limit': 0,
1668 'like_count': int,
1669 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1670 'channel': 'WiiLikeToPlay',
1671 'view_count': int,
1672 'release_date': '20131106',
1673 },
1674 }, {
1675 'info_dict': {
1676 'id': 'zaPI8MvL8pg',
1677 'ext': 'mp4',
1678 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
1679 'uploader_id': 'WiiRikeToPray',
1680 'availability': 'public',
1681 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1682 'channel': 'WiiLikeToPlay',
1683 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1684 'channel_follower_count': int,
1685 'description': 'md5:563ccbc698b39298481ca3c571169519',
1686 'duration': 10108,
1687 'age_limit': 0,
1688 'like_count': int,
1689 'tags': 'count:24',
1690 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1691 'uploader': 'WiiLikeToPlay',
1692 'release_timestamp': 1383701915,
1693 'comment_count': int,
1694 'upload_date': '20131105',
1695 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1696 'release_date': '20131106',
1697 'playable_in_embed': True,
1698 'live_status': 'was_live',
1699 'categories': ['Gaming'],
1700 'view_count': int,
1701 },
1702 }, {
1703 'info_dict': {
1704 'id': 'R7r3vfO7Hao',
1705 'ext': 'mp4',
1706 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1707 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1708 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1709 'like_count': int,
1710 'availability': 'public',
1711 'playable_in_embed': True,
1712 'upload_date': '20131105',
1713 'description': 'md5:563ccbc698b39298481ca3c571169519',
1714 'uploader_id': 'WiiRikeToPray',
1715 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1716 'channel_follower_count': int,
1717 'tags': 'count:24',
1718 'release_date': '20131106',
1719 'uploader': 'WiiLikeToPlay',
1720 'comment_count': int,
1721 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1722 'channel': 'WiiLikeToPlay',
1723 'categories': ['Gaming'],
1724 'release_timestamp': 1383701914,
1725 'live_status': 'was_live',
1726 'age_limit': 0,
1727 'duration': 10128,
1728 'view_count': int,
1729 },
1730 }],
1731 'params': {'skip_download': True},
1732 },
1733 {
1734 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1735 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1736 'info_dict': {
1737 'id': 'gVfLd0zydlo',
1738 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1739 },
1740 'playlist_count': 2,
1741 'skip': 'Not multifeed anymore',
1742 },
1743 {
1744 'url': 'https://vid.plus/FlRa-iH7PGw',
1745 'only_matching': True,
1746 },
1747 {
1748 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1749 'only_matching': True,
1750 },
1751 {
1752 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1753 # Also tests cut-off URL expansion in video description (see
1754 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1755 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1756 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1757 'info_dict': {
1758 'id': 'lsguqyKfVQg',
1759 'ext': 'mp4',
1760 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1761 'alt_title': 'Dark Walk',
1762 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1763 'duration': 133,
1764 'upload_date': '20151119',
1765 'uploader_id': 'IronSoulElf',
1766 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1767 'uploader': 'IronSoulElf',
1768 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1769 'track': 'Dark Walk',
1770 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1771 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1772 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1773 'categories': ['Film & Animation'],
1774 'view_count': int,
1775 'live_status': 'not_live',
1776 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1777 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1778 'tags': 'count:13',
1779 'availability': 'public',
1780 'channel': 'IronSoulElf',
1781 'playable_in_embed': True,
1782 'like_count': int,
1783 'age_limit': 0,
1784 'channel_follower_count': int
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 },
1790 {
1791 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1792 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1793 'only_matching': True,
1794 },
1795 {
1796 # Video with yt:stretch=17:0
1797 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1798 'info_dict': {
1799 'id': 'Q39EVAstoRM',
1800 'ext': 'mp4',
1801 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1802 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1803 'upload_date': '20151107',
1804 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1805 'uploader': 'CH GAMER DROID',
1806 },
1807 'params': {
1808 'skip_download': True,
1809 },
1810 'skip': 'This video does not exist.',
1811 },
1812 {
1813 # Video with incomplete 'yt:stretch=16:'
1814 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1815 'only_matching': True,
1816 },
1817 {
1818 # Video licensed under Creative Commons
1819 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1820 'info_dict': {
1821 'id': 'M4gD1WSo5mA',
1822 'ext': 'mp4',
1823 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1824 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1825 'duration': 721,
1826 'upload_date': '20150128',
1827 'uploader_id': 'BerkmanCenter',
1828 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1829 'uploader': 'The Berkman Klein Center for Internet & Society',
1830 'license': 'Creative Commons Attribution license (reuse allowed)',
1831 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1832 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1833 'like_count': int,
1834 'age_limit': 0,
1835 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1836 'channel': 'The Berkman Klein Center for Internet & Society',
1837 'availability': 'public',
1838 'view_count': int,
1839 'categories': ['Education'],
1840 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1841 'live_status': 'not_live',
1842 'playable_in_embed': True,
1843 'comment_count': int,
1844 'channel_follower_count': int,
1845 'chapters': list,
1846 },
1847 'params': {
1848 'skip_download': True,
1849 },
1850 },
1851 {
1852 # Channel-like uploader_url
1853 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1854 'info_dict': {
1855 'id': 'eQcmzGIKrzg',
1856 'ext': 'mp4',
1857 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1858 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1859 'duration': 4060,
1860 'upload_date': '20151120',
1861 'uploader': 'Bernie Sanders',
1862 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1863 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1864 'license': 'Creative Commons Attribution license (reuse allowed)',
1865 'playable_in_embed': True,
1866 'tags': 'count:12',
1867 'like_count': int,
1868 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1869 'age_limit': 0,
1870 'availability': 'public',
1871 'categories': ['News & Politics'],
1872 'channel': 'Bernie Sanders',
1873 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1874 'view_count': int,
1875 'live_status': 'not_live',
1876 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1877 'comment_count': int,
1878 'channel_follower_count': int,
1879 'chapters': list,
1880 },
1881 'params': {
1882 'skip_download': True,
1883 },
1884 },
1885 {
1886 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1887 'only_matching': True,
1888 },
1889 {
1890 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1891 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1892 'only_matching': True,
1893 },
1894 {
1895 # Rental video preview
1896 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1897 'info_dict': {
1898 'id': 'uGpuVWrhIzE',
1899 'ext': 'mp4',
1900 'title': 'Piku - Trailer',
1901 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1902 'upload_date': '20150811',
1903 'uploader': 'FlixMatrix',
1904 'uploader_id': 'FlixMatrixKaravan',
1905 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1906 'license': 'Standard YouTube License',
1907 },
1908 'params': {
1909 'skip_download': True,
1910 },
1911 'skip': 'This video is not available.',
1912 },
1913 {
1914 # YouTube Red video with episode data
1915 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1916 'info_dict': {
1917 'id': 'iqKdEhx-dD4',
1918 'ext': 'mp4',
1919 'title': 'Isolation - Mind Field (Ep 1)',
1920 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1921 'duration': 2085,
1922 'upload_date': '20170118',
1923 'uploader': 'Vsauce',
1924 'uploader_id': 'Vsauce',
1925 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1926 'series': 'Mind Field',
1927 'season_number': 1,
1928 'episode_number': 1,
1929 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1930 'tags': 'count:12',
1931 'view_count': int,
1932 'availability': 'public',
1933 'age_limit': 0,
1934 'channel': 'Vsauce',
1935 'episode': 'Episode 1',
1936 'categories': ['Entertainment'],
1937 'season': 'Season 1',
1938 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1939 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1940 'like_count': int,
1941 'playable_in_embed': True,
1942 'live_status': 'not_live',
1943 'channel_follower_count': int
1944 },
1945 'params': {
1946 'skip_download': True,
1947 },
1948 'expected_warnings': [
1949 'Skipping DASH manifest',
1950 ],
1951 },
1952 {
1953 # The following content has been identified by the YouTube community
1954 # as inappropriate or offensive to some audiences.
1955 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1956 'info_dict': {
1957 'id': '6SJNVb0GnPI',
1958 'ext': 'mp4',
1959 'title': 'Race Differences in Intelligence',
1960 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1961 'duration': 965,
1962 'upload_date': '20140124',
1963 'uploader': 'New Century Foundation',
1964 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1965 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1966 },
1967 'params': {
1968 'skip_download': True,
1969 },
1970 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1971 },
1972 {
1973 # itag 212
1974 'url': '1t24XAntNCY',
1975 'only_matching': True,
1976 },
1977 {
1978 # geo restricted to JP
1979 'url': 'sJL6WA-aGkQ',
1980 'only_matching': True,
1981 },
1982 {
1983 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1984 'only_matching': True,
1985 },
1986 {
1987 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1988 'only_matching': True,
1989 },
1990 {
1991 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1992 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1993 'only_matching': True,
1994 },
1995 {
1996 # DRM protected
1997 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1998 'only_matching': True,
1999 },
2000 {
2001 # Video with unsupported adaptive stream type formats
2002 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2003 'info_dict': {
2004 'id': 'Z4Vy8R84T1U',
2005 'ext': 'mp4',
2006 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2007 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2008 'duration': 433,
2009 'upload_date': '20130923',
2010 'uploader': 'Amelia Putri Harwita',
2011 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
2012 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
2013 'formats': 'maxcount:10',
2014 },
2015 'params': {
2016 'skip_download': True,
2017 'youtube_include_dash_manifest': False,
2018 },
2019 'skip': 'not actual anymore',
2020 },
2021 {
2022 # Youtube Music Auto-generated description
2023 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2024 'info_dict': {
2025 'id': 'MgNrAu2pzNs',
2026 'ext': 'mp4',
2027 'title': 'Voyeur Girl',
2028 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2029 'upload_date': '20190312',
2030 'uploader': 'Stephen - Topic',
2031 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2032 'artist': 'Stephen',
2033 'track': 'Voyeur Girl',
2034 'album': 'it\'s too much love to know my dear',
2035 'release_date': '20190313',
2036 'release_year': 2019,
2037 'alt_title': 'Voyeur Girl',
2038 'view_count': int,
2039 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2040 'playable_in_embed': True,
2041 'like_count': int,
2042 'categories': ['Music'],
2043 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2044 'channel': 'Stephen',
2045 'availability': 'public',
2046 'creator': 'Stephen',
2047 'duration': 169,
2048 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2049 'age_limit': 0,
2050 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2051 'tags': 'count:11',
2052 'live_status': 'not_live',
2053 'channel_follower_count': int
2054 },
2055 'params': {
2056 'skip_download': True,
2057 },
2058 },
2059 {
2060 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2061 'only_matching': True,
2062 },
2063 {
2064 # invalid -> valid video id redirection
2065 'url': 'DJztXj2GPfl',
2066 'info_dict': {
2067 'id': 'DJztXj2GPfk',
2068 'ext': 'mp4',
2069 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2070 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2071 'upload_date': '20090125',
2072 'uploader': 'Prochorowka',
2073 'uploader_id': 'Prochorowka',
2074 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
2075 'artist': 'Panjabi MC',
2076 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2077 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2078 },
2079 'params': {
2080 'skip_download': True,
2081 },
2082 'skip': 'Video unavailable',
2083 },
2084 {
2085 # empty description results in an empty string
2086 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2087 'info_dict': {
2088 'id': 'x41yOUIvK2k',
2089 'ext': 'mp4',
2090 'title': 'IMG 3456',
2091 'description': '',
2092 'upload_date': '20170613',
2093 'uploader_id': 'ElevageOrVert',
2094 'uploader': 'ElevageOrVert',
2095 'view_count': int,
2096 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2097 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2098 'like_count': int,
2099 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2100 'tags': [],
2101 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2102 'availability': 'public',
2103 'age_limit': 0,
2104 'categories': ['Pets & Animals'],
2105 'duration': 7,
2106 'playable_in_embed': True,
2107 'live_status': 'not_live',
2108 'channel': 'ElevageOrVert',
2109 'channel_follower_count': int
2110 },
2111 'params': {
2112 'skip_download': True,
2113 },
2114 },
2115 {
2116 # with '};' inside yt initial data (see [1])
2117 # see [2] for an example with '};' inside ytInitialPlayerResponse
2118 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2119 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
2120 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2121 'info_dict': {
2122 'id': 'CHqg6qOn4no',
2123 'ext': 'mp4',
2124 'title': 'Part 77 Sort a list of simple types in c#',
2125 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2126 'upload_date': '20130831',
2127 'uploader_id': 'kudvenkat',
2128 'uploader': 'kudvenkat',
2129 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2130 'like_count': int,
2131 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2132 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2133 'live_status': 'not_live',
2134 'categories': ['Education'],
2135 'availability': 'public',
2136 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2137 'tags': 'count:12',
2138 'playable_in_embed': True,
2139 'age_limit': 0,
2140 'view_count': int,
2141 'duration': 522,
2142 'channel': 'kudvenkat',
2143 'comment_count': int,
2144 'channel_follower_count': int,
2145 'chapters': list,
2146 },
2147 'params': {
2148 'skip_download': True,
2149 },
2150 },
2151 {
2152 # another example of '};' in ytInitialData
2153 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2154 'only_matching': True,
2155 },
2156 {
2157 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2158 'only_matching': True,
2159 },
2160 {
2161 # https://github.com/ytdl-org/youtube-dl/pull/28094
2162 'url': 'OtqTfy26tG0',
2163 'info_dict': {
2164 'id': 'OtqTfy26tG0',
2165 'ext': 'mp4',
2166 'title': 'Burn Out',
2167 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2168 'upload_date': '20141120',
2169 'uploader': 'The Cinematic Orchestra - Topic',
2170 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2171 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2172 'artist': 'The Cinematic Orchestra',
2173 'track': 'Burn Out',
2174 'album': 'Every Day',
2175 'like_count': int,
2176 'live_status': 'not_live',
2177 'alt_title': 'Burn Out',
2178 'duration': 614,
2179 'age_limit': 0,
2180 'view_count': int,
2181 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2182 'creator': 'The Cinematic Orchestra',
2183 'channel': 'The Cinematic Orchestra',
2184 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2185 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2186 'availability': 'public',
2187 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2188 'categories': ['Music'],
2189 'playable_in_embed': True,
2190 'channel_follower_count': int
2191 },
2192 'params': {
2193 'skip_download': True,
2194 },
2195 },
2196 {
2197 # controversial video, only works with bpctr when authenticated with cookies
2198 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2199 'only_matching': True,
2200 },
2201 {
2202 # controversial video, requires bpctr/contentCheckOk
2203 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2204 'info_dict': {
2205 'id': 'SZJvDhaSDnc',
2206 'ext': 'mp4',
2207 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2208 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2209 'uploader': 'CBS Mornings',
2210 'uploader_id': 'CBSThisMorning',
2211 'upload_date': '20140716',
2212 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2213 'duration': 170,
2214 'categories': ['News & Politics'],
2215 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2216 'view_count': int,
2217 'channel': 'CBS Mornings',
2218 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2219 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2220 'age_limit': 18,
2221 'availability': 'needs_auth',
2222 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2223 'like_count': int,
2224 'live_status': 'not_live',
2225 'playable_in_embed': True,
2226 'channel_follower_count': int
2227 }
2228 },
2229 {
2230 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2231 'url': 'cBvYw8_A0vQ',
2232 'info_dict': {
2233 'id': 'cBvYw8_A0vQ',
2234 'ext': 'mp4',
2235 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2236 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2237 'upload_date': '20201120',
2238 'uploader': 'Walk around Japan',
2239 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2240 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2241 'duration': 1456,
2242 'categories': ['Travel & Events'],
2243 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2244 'view_count': int,
2245 'channel': 'Walk around Japan',
2246 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2247 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2248 'age_limit': 0,
2249 'availability': 'public',
2250 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2251 'live_status': 'not_live',
2252 'playable_in_embed': True,
2253 'channel_follower_count': int
2254 },
2255 'params': {
2256 'skip_download': True,
2257 },
2258 }, {
2259 # Has multiple audio streams
2260 'url': 'WaOKSUlf4TM',
2261 'only_matching': True
2262 }, {
2263 # Requires Premium: has format 141 when requested using YTM url
2264 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2265 'only_matching': True
2266 }, {
2267 # multiple subtitles with same lang_code
2268 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2269 'only_matching': True,
2270 }, {
2271 # Force use android client fallback
2272 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2273 'info_dict': {
2274 'id': 'YOelRv7fMxY',
2275 'title': 'DIGGING A SECRET TUNNEL Part 1',
2276 'ext': '3gp',
2277 'upload_date': '20210624',
2278 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2279 'uploader': 'colinfurze',
2280 'uploader_id': 'colinfurze',
2281 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2282 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2283 'duration': 596,
2284 'categories': ['Entertainment'],
2285 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2286 'view_count': int,
2287 'channel': 'colinfurze',
2288 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2289 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2290 'age_limit': 0,
2291 'availability': 'public',
2292 'like_count': int,
2293 'live_status': 'not_live',
2294 'playable_in_embed': True,
2295 'channel_follower_count': int,
2296 'chapters': list,
2297 },
2298 'params': {
2299 'format': '17', # 3gp format available on android
2300 'extractor_args': {'youtube': {'player_client': ['android']}},
2301 },
2302 },
2303 {
2304 # Skip download of additional client configs (remix client config in this case)
2305 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2306 'only_matching': True,
2307 'params': {
2308 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2309 },
2310 }, {
2311 # shorts
2312 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2313 'only_matching': True,
2314 }, {
2315 'note': 'Storyboards',
2316 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2317 'info_dict': {
2318 'id': '5KLPxDtMqe8',
2319 'ext': 'mhtml',
2320 'format_id': 'sb0',
2321 'title': 'Your Brain is Plastic',
2322 'uploader_id': 'scishow',
2323 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2324 'upload_date': '20140324',
2325 'uploader': 'SciShow',
2326 'like_count': int,
2327 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2328 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2329 'view_count': int,
2330 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2331 'playable_in_embed': True,
2332 'tags': 'count:12',
2333 'uploader_url': 'http://www.youtube.com/user/scishow',
2334 'availability': 'public',
2335 'channel': 'SciShow',
2336 'live_status': 'not_live',
2337 'duration': 248,
2338 'categories': ['Education'],
2339 'age_limit': 0,
2340 'channel_follower_count': int,
2341 'chapters': list,
2342 }, 'params': {'format': 'mhtml', 'skip_download': True}
2343 }, {
2344 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2345 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2346 'info_dict': {
2347 'id': '2NUZ8W2llS4',
2348 'ext': 'mp4',
2349 'title': 'The NP that test your phone performance 🙂',
2350 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2351 'uploader': 'Leon Nguyen',
2352 'uploader_id': 'VNSXIII',
2353 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2354 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2355 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2356 'duration': 21,
2357 'view_count': int,
2358 'age_limit': 0,
2359 'categories': ['Gaming'],
2360 'tags': 'count:23',
2361 'playable_in_embed': True,
2362 'live_status': 'not_live',
2363 'upload_date': '20220103',
2364 'like_count': int,
2365 'availability': 'public',
2366 'channel': 'Leon Nguyen',
2367 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2368 'comment_count': int,
2369 'channel_follower_count': int
2370 }
2371 }, {
2372 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2373 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2374 'info_dict': {
2375 'id': '2NUZ8W2llS4',
2376 'ext': 'mp4',
2377 'title': 'The NP that test your phone performance 🙂',
2378 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2379 'uploader': 'Leon Nguyen',
2380 'uploader_id': 'VNSXIII',
2381 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2382 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2383 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2384 'duration': 21,
2385 'view_count': int,
2386 'age_limit': 0,
2387 'categories': ['Gaming'],
2388 'tags': 'count:23',
2389 'playable_in_embed': True,
2390 'live_status': 'not_live',
2391 'upload_date': '20220102',
2392 'like_count': int,
2393 'availability': 'public',
2394 'channel': 'Leon Nguyen',
2395 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2396 'comment_count': int,
2397 'channel_follower_count': int
2398 },
2399 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2400 }, {
2401 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2402 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2403 'info_dict': {
2404 'id': 'mzZzzBU6lrM',
2405 'ext': 'mp4',
2406 'title': 'I Met GeorgeNotFound In Real Life...',
2407 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2408 'uploader': 'Quackity',
2409 'uploader_id': 'QuackityHQ',
2410 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2411 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2412 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2413 'duration': 955,
2414 'view_count': int,
2415 'age_limit': 0,
2416 'categories': ['Entertainment'],
2417 'tags': 'count:26',
2418 'playable_in_embed': True,
2419 'live_status': 'not_live',
2420 'release_timestamp': 1641172509,
2421 'release_date': '20220103',
2422 'upload_date': '20220103',
2423 'like_count': int,
2424 'availability': 'public',
2425 'channel': 'Quackity',
2426 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2427 'channel_follower_count': int
2428 }
2429 },
2430 { # continuous livestream. Microformat upload date should be preferred.
2431 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2432 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2433 'info_dict': {
2434 'id': 'kgx4WGK0oNU',
2435 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2436 'ext': 'mp4',
2437 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2438 'availability': 'public',
2439 'age_limit': 0,
2440 'release_timestamp': 1637975704,
2441 'upload_date': '20210619',
2442 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2443 'live_status': 'is_live',
2444 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2445 'uploader': '阿鲍Abao',
2446 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2447 'channel': 'Abao in Tokyo',
2448 'channel_follower_count': int,
2449 'release_date': '20211127',
2450 'tags': 'count:39',
2451 'categories': ['People & Blogs'],
2452 'like_count': int,
2453 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2454 'view_count': int,
2455 'playable_in_embed': True,
2456 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2457 'concurrent_view_count': int,
2458 },
2459 'params': {'skip_download': True}
2460 }, {
2461 # Story. Requires specific player params to work.
2462 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2463 'info_dict': {
2464 'id': 'vv8qTUWmulI',
2465 'ext': 'mp4',
2466 'availability': 'unlisted',
2467 'view_count': int,
2468 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2469 'upload_date': '20220526',
2470 'categories': ['Education'],
2471 'title': 'Story',
2472 'channel': 'IT\'S HISTORY',
2473 'description': '',
2474 'uploader_id': 'BlastfromthePast',
2475 'duration': 12,
2476 'uploader': 'IT\'S HISTORY',
2477 'playable_in_embed': True,
2478 'age_limit': 0,
2479 'live_status': 'not_live',
2480 'tags': [],
2481 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2482 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2483 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2484 },
2485 'skip': 'stories get removed after some period of time',
2486 }, {
2487 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2488 'info_dict': {
2489 'id': 'tjjjtzRLHvA',
2490 'ext': 'mp4',
2491 'title': 'ハッシュタグ無し };if window.ytcsi',
2492 'upload_date': '20220323',
2493 'like_count': int,
2494 'availability': 'unlisted',
2495 'channel': 'nao20010128nao',
2496 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2497 'age_limit': 0,
2498 'uploader': 'nao20010128nao',
2499 'uploader_id': 'nao20010128nao',
2500 'categories': ['Music'],
2501 'view_count': int,
2502 'description': '',
2503 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2504 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2505 'live_status': 'not_live',
2506 'playable_in_embed': True,
2507 'channel_follower_count': int,
2508 'duration': 6,
2509 'tags': [],
2510 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2511 }
2512 }, {
2513 # Prefer primary title+description language metadata by default
2514 # Do not prefer translated description if primary is empty
2515 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2516 'info_dict': {
2517 'id': 'el3E4MbxRqQ',
2518 'ext': 'mp4',
2519 'title': 'dlp test video 2 - primary sv no desc',
2520 'description': '',
2521 'channel': 'cole-dlp-test-acc',
2522 'tags': [],
2523 'view_count': int,
2524 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2525 'like_count': int,
2526 'playable_in_embed': True,
2527 'availability': 'unlisted',
2528 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2529 'age_limit': 0,
2530 'duration': 5,
2531 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2532 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2533 'live_status': 'not_live',
2534 'upload_date': '20220908',
2535 'categories': ['People & Blogs'],
2536 'uploader': 'cole-dlp-test-acc',
2537 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2538 },
2539 'params': {'skip_download': True}
2540 }, {
2541 # Extractor argument: prefer translated title+description
2542 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2543 'info_dict': {
2544 'id': 'gHKT4uU8Zng',
2545 'ext': 'mp4',
2546 'channel': 'cole-dlp-test-acc',
2547 'tags': [],
2548 'duration': 5,
2549 'live_status': 'not_live',
2550 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2551 'upload_date': '20220728',
2552 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2553 'view_count': int,
2554 'categories': ['People & Blogs'],
2555 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2556 'title': 'dlp test video title translated (fr)',
2557 'availability': 'public',
2558 'uploader': 'cole-dlp-test-acc',
2559 'age_limit': 0,
2560 'description': 'dlp test video description translated (fr)',
2561 'playable_in_embed': True,
2562 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2563 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2564 },
2565 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2566 'expected_warnings': [r'Preferring "fr" translated fields'],
2567 }, {
2568 'note': '6 channel audio',
2569 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2570 'only_matching': True,
2571 }, {
2572 'note': 'Multiple HLS formats with same itag',
2573 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2574 'info_dict': {
2575 'id': 'kX3nB4PpJko',
2576 'ext': 'mp4',
2577 'categories': ['Entertainment'],
2578 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
2579 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
2580 'live_status': 'not_live',
2581 'duration': 937,
2582 'channel_follower_count': int,
2583 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2584 'title': 'Last To Take Hand Off Jet, Keeps It!',
2585 'channel': 'MrBeast',
2586 'playable_in_embed': True,
2587 'view_count': int,
2588 'upload_date': '20221112',
2589 'uploader': 'MrBeast',
2590 'uploader_id': 'MrBeast6000',
2591 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2592 'age_limit': 0,
2593 'availability': 'public',
2594 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2595 'like_count': int,
2596 'tags': [],
2597 },
2598 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
2599 }, {
2600 'note': 'Audio formats with Dynamic Range Compression',
2601 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2602 'info_dict': {
2603 'id': 'Tq92D6wQ1mg',
2604 'ext': 'weba',
2605 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2606 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2607 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2608 'channel_follower_count': int,
2609 'description': 'md5:17eccca93a786d51bc67646756894066',
2610 'upload_date': '20191228',
2611 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2612 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2613 'playable_in_embed': True,
2614 'like_count': int,
2615 'categories': ['Entertainment'],
2616 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2617 'age_limit': 18,
2618 'channel': 'Projekt Melody',
2619 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2620 'view_count': int,
2621 'availability': 'needs_auth',
2622 'comment_count': int,
2623 'live_status': 'not_live',
2624 'uploader': 'Projekt Melody',
2625 'duration': 106,
2626 },
2627 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
2628 },
2629 {
2630 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2631 'info_dict': {
2632 'id': 'qVv6vCqciTM',
2633 'ext': 'mp4',
2634 'age_limit': 0,
2635 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2636 'comment_count': int,
2637 'chapters': 'count:13',
2638 'upload_date': '20221223',
2639 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2640 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2641 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2642 'like_count': int,
2643 'release_date': '20221223',
2644 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2645 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
2646 'view_count': int,
2647 'playable_in_embed': True,
2648 'duration': 4438,
2649 'availability': 'public',
2650 'channel_follower_count': int,
2651 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2652 'categories': ['Entertainment'],
2653 'live_status': 'was_live',
2654 'release_timestamp': 1671793345,
2655 'channel': 'さなちゃんねる',
2656 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2657 'uploader': 'さなちゃんねる',
2658 },
2659 },
2660 ]
2661
2662 _WEBPAGE_TESTS = [
2663 # YouTube <object> embed
2664 {
2665 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2666 'md5': '873c81d308b979f0e23ee7e620b312a3',
2667 'info_dict': {
2668 'id': 'msN87y-iEx0',
2669 'ext': 'mp4',
2670 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2671 'upload_date': '20080526',
2672 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2673 'uploader': 'Christopher Sykes',
2674 'uploader_id': 'ChristopherJSykes',
2675 'age_limit': 0,
2676 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2677 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2678 'playable_in_embed': True,
2679 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2680 'like_count': int,
2681 'comment_count': int,
2682 'channel': 'Christopher Sykes',
2683 'live_status': 'not_live',
2684 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2685 'availability': 'public',
2686 'duration': 195,
2687 'view_count': int,
2688 'categories': ['Science & Technology'],
2689 'channel_follower_count': int,
2690 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2691 },
2692 'params': {
2693 'skip_download': True,
2694 }
2695 },
2696 ]
2697
2698 @classmethod
2699 def suitable(cls, url):
2700 from ..utils import parse_qs
2701
2702 qs = parse_qs(url)
2703 if qs.get('list', [None])[0]:
2704 return False
2705 return super().suitable(url)
2706
2707 def __init__(self, *args, **kwargs):
2708 super().__init__(*args, **kwargs)
2709 self._code_cache = {}
2710 self._player_cache = {}
2711
2712 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
2713 lock = threading.Lock()
2714 start_time = time.time()
2715 formats = [f for f in formats if f.get('is_from_start')]
2716
2717 def refetch_manifest(format_id, delay):
2718 nonlocal formats, start_time, is_live
2719 if time.time() <= start_time + delay:
2720 return
2721
2722 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2723 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
2724 microformats = traverse_obj(
2725 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2726 expected_type=dict)
2727 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2728 is_live = live_status == 'is_live'
2729 start_time = time.time()
2730
2731 def mpd_feed(format_id, delay):
2732 """
2733 @returns (manifest_url, manifest_stream_number, is_live) or None
2734 """
2735 for retry in self.RetryManager(fatal=False):
2736 with lock:
2737 refetch_manifest(format_id, delay)
2738
2739 f = next((f for f in formats if f['format_id'] == format_id), None)
2740 if not f:
2741 if not is_live:
2742 retry.error = f'{video_id}: Video is no longer live'
2743 else:
2744 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2745 continue
2746 return f['manifest_url'], f['manifest_stream_number'], is_live
2747 return None
2748
2749 for f in formats:
2750 f['is_live'] = is_live
2751 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2752 live_start_time, mpd_feed, not is_live and f.copy())
2753 if is_live:
2754 f['fragments'] = gen
2755 f['protocol'] = 'http_dash_segments_generator'
2756 else:
2757 f['fragments'] = LazyList(gen({}))
2758 del f['is_from_start']
2759
2760 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
2761 FETCH_SPAN, MAX_DURATION = 5, 432000
2762
2763 mpd_url, stream_number, is_live = None, None, True
2764
2765 begin_index = 0
2766 download_start_time = ctx.get('start') or time.time()
2767
2768 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2769 if lack_early_segments:
2770 self.report_warning(bug_reports_message(
2771 'Starting download from the last 120 hours of the live stream since '
2772 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2773 lack_early_segments = True
2774
2775 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2776 fragments, fragment_base_url = None, None
2777
2778 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2779 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2780 # Obtain from MPD's maximum seq value
2781 old_mpd_url = mpd_url
2782 last_error = ctx.pop('last_error', None)
2783 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2784 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2785 or (mpd_url, stream_number, False))
2786 if not refresh_sequence:
2787 if expire_fast and not is_live:
2788 return False, last_seq
2789 elif old_mpd_url == mpd_url:
2790 return True, last_seq
2791 if manifestless_orig_fmt:
2792 fmt_info = manifestless_orig_fmt
2793 else:
2794 try:
2795 fmts, _ = self._extract_mpd_formats_and_subtitles(
2796 mpd_url, None, note=False, errnote=False, fatal=False)
2797 except ExtractorError:
2798 fmts = None
2799 if not fmts:
2800 no_fragment_score += 2
2801 return False, last_seq
2802 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2803 fragments = fmt_info['fragments']
2804 fragment_base_url = fmt_info['fragment_base_url']
2805 assert fragment_base_url
2806
2807 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2808 return True, _last_seq
2809
2810 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
2811 while is_live:
2812 fetch_time = time.time()
2813 if no_fragment_score > 30:
2814 return
2815 if last_segment_url:
2816 # Obtain from "X-Head-Seqnum" header value from each segment
2817 try:
2818 urlh = self._request_webpage(
2819 last_segment_url, None, note=False, errnote=False, fatal=False)
2820 except ExtractorError:
2821 urlh = None
2822 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2823 if last_seq is None:
2824 no_fragment_score += 2
2825 last_segment_url = None
2826 continue
2827 else:
2828 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2829 no_fragment_score += 2
2830 if not should_continue:
2831 continue
2832
2833 if known_idx > last_seq:
2834 last_segment_url = None
2835 continue
2836
2837 last_seq += 1
2838
2839 if begin_index < 0 and known_idx < 0:
2840 # skip from the start when it's negative value
2841 known_idx = last_seq + begin_index
2842 if lack_early_segments:
2843 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2844 try:
2845 for idx in range(known_idx, last_seq):
2846 # do not update sequence here or you'll get skipped some part of it
2847 should_continue, _ = _extract_sequence_from_mpd(False, False)
2848 if not should_continue:
2849 known_idx = idx - 1
2850 raise ExtractorError('breaking out of outer loop')
2851 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2852 yield {
2853 'url': last_segment_url,
2854 'fragment_count': last_seq,
2855 }
2856 if known_idx == last_seq:
2857 no_fragment_score += 5
2858 else:
2859 no_fragment_score = 0
2860 known_idx = last_seq
2861 except ExtractorError:
2862 continue
2863
2864 if manifestless_orig_fmt:
2865 # Stop at the first iteration if running for post-live manifestless;
2866 # fragment count no longer increase since it starts
2867 break
2868
2869 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2870
2871 def _extract_player_url(self, *ytcfgs, webpage=None):
2872 player_url = traverse_obj(
2873 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2874 get_all=False, expected_type=str)
2875 if not player_url:
2876 return
2877 return urljoin('https://www.youtube.com', player_url)
2878
2879 def _download_player_url(self, video_id, fatal=False):
2880 res = self._download_webpage(
2881 'https://www.youtube.com/iframe_api',
2882 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2883 if res:
2884 player_version = self._search_regex(
2885 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2886 if player_version:
2887 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2888
2889 def _signature_cache_id(self, example_sig):
2890 """ Return a string representation of a signature """
2891 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2892
2893 @classmethod
2894 def _extract_player_info(cls, player_url):
2895 for player_re in cls._PLAYER_INFO_RE:
2896 id_m = re.search(player_re, player_url)
2897 if id_m:
2898 break
2899 else:
2900 raise ExtractorError('Cannot identify player %r' % player_url)
2901 return id_m.group('id')
2902
2903 def _load_player(self, video_id, player_url, fatal=True):
2904 player_id = self._extract_player_info(player_url)
2905 if player_id not in self._code_cache:
2906 code = self._download_webpage(
2907 player_url, video_id, fatal=fatal,
2908 note='Downloading player ' + player_id,
2909 errnote='Download of %s failed' % player_url)
2910 if code:
2911 self._code_cache[player_id] = code
2912 return self._code_cache.get(player_id)
2913
2914 def _extract_signature_function(self, video_id, player_url, example_sig):
2915 player_id = self._extract_player_info(player_url)
2916
2917 # Read from filesystem cache
2918 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2919 assert os.path.basename(func_id) == func_id
2920
2921 self.write_debug(f'Extracting signature function {func_id}')
2922 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2923
2924 if not cache_spec:
2925 code = self._load_player(video_id, player_url)
2926 if code:
2927 res = self._parse_sig_js(code)
2928 test_string = ''.join(map(chr, range(len(example_sig))))
2929 cache_spec = [ord(c) for c in res(test_string)]
2930 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2931
2932 return lambda s: ''.join(s[i] for i in cache_spec)
2933
2934 def _print_sig_code(self, func, example_sig):
2935 if not self.get_param('youtube_print_sig_code'):
2936 return
2937
2938 def gen_sig_code(idxs):
2939 def _genslice(start, end, step):
2940 starts = '' if start == 0 else str(start)
2941 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2942 steps = '' if step == 1 else (':%d' % step)
2943 return f's[{starts}{ends}{steps}]'
2944
2945 step = None
2946 # Quelch pyflakes warnings - start will be set when step is set
2947 start = '(Never used)'
2948 for i, prev in zip(idxs[1:], idxs[:-1]):
2949 if step is not None:
2950 if i - prev == step:
2951 continue
2952 yield _genslice(start, prev, step)
2953 step = None
2954 continue
2955 if i - prev in [-1, 1]:
2956 step = i - prev
2957 start = prev
2958 continue
2959 else:
2960 yield 's[%d]' % prev
2961 if step is None:
2962 yield 's[%d]' % i
2963 else:
2964 yield _genslice(start, i, step)
2965
2966 test_string = ''.join(map(chr, range(len(example_sig))))
2967 cache_res = func(test_string)
2968 cache_spec = [ord(c) for c in cache_res]
2969 expr_code = ' + '.join(gen_sig_code(cache_spec))
2970 signature_id_tuple = '(%s)' % (
2971 ', '.join(str(len(p)) for p in example_sig.split('.')))
2972 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2973 ' return %s\n') % (signature_id_tuple, expr_code)
2974 self.to_screen('Extracted signature function:\n' + code)
2975
2976 def _parse_sig_js(self, jscode):
2977 funcname = self._search_regex(
2978 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2979 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2980 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2981 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2982 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
2983 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2984 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2985 # Obsolete patterns
2986 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2987 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2988 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2989 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2990 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2991 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2992 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2993 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2994 jscode, 'Initial JS player signature function name', group='sig')
2995
2996 jsi = JSInterpreter(jscode)
2997 initial_function = jsi.extract_function(funcname)
2998 return lambda s: initial_function([s])
2999
3000 def _cached(self, func, *cache_id):
3001 def inner(*args, **kwargs):
3002 if cache_id not in self._player_cache:
3003 try:
3004 self._player_cache[cache_id] = func(*args, **kwargs)
3005 except ExtractorError as e:
3006 self._player_cache[cache_id] = e
3007 except Exception as e:
3008 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3009
3010 ret = self._player_cache[cache_id]
3011 if isinstance(ret, Exception):
3012 raise ret
3013 return ret
3014 return inner
3015
3016 def _decrypt_signature(self, s, video_id, player_url):
3017 """Turn the encrypted s field into a working signature"""
3018 extract_sig = self._cached(
3019 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3020 func = extract_sig(video_id, player_url, s)
3021 self._print_sig_code(func, s)
3022 return func(s)
3023
3024 def _decrypt_nsig(self, s, video_id, player_url):
3025 """Turn the encrypted n field into a working signature"""
3026 if player_url is None:
3027 raise ExtractorError('Cannot decrypt nsig without player_url')
3028 player_url = urljoin('https://www.youtube.com', player_url)
3029
3030 try:
3031 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3032 except ExtractorError as e:
3033 raise ExtractorError('Unable to extract nsig function code', cause=e)
3034 if self.get_param('youtube_print_sig_code'):
3035 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
3036
3037 try:
3038 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3039 ret = extract_nsig(jsi, func_code)(s)
3040 except JSInterpreter.Exception as e:
3041 try:
3042 jsi = PhantomJSwrapper(self, timeout=5000)
3043 except ExtractorError:
3044 raise e
3045 self.report_warning(
3046 f'Native nsig extraction failed: Trying with PhantomJS\n'
3047 f' n = {s} ; player = {player_url}', video_id)
3048 self.write_debug(e, only_once=True)
3049
3050 args, func_body = func_code
3051 ret = jsi.execute(
3052 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3053 video_id=video_id, note='Executing signature code').strip()
3054
3055 self.write_debug(f'Decrypted nsig {s} => {ret}')
3056 return ret
3057
3058 def _extract_n_function_name(self, jscode):
3059 funcname, idx = self._search_regex(
3060 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3061 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3062 if not idx:
3063 return funcname
3064
3065 return json.loads(js_to_json(self._search_regex(
3066 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3067 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3068
3069 def _extract_n_function_code(self, video_id, player_url):
3070 player_id = self._extract_player_info(player_url)
3071 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
3072 jscode = func_code or self._load_player(video_id, player_url)
3073 jsi = JSInterpreter(jscode)
3074
3075 if func_code:
3076 return jsi, player_id, func_code
3077
3078 func_name = self._extract_n_function_name(jscode)
3079
3080 # For redundancy
3081 func_code = self._search_regex(
3082 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3083 # NB: The end of the regex is intentionally kept strict
3084 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3085 jscode, 'nsig function', group=('var', 'code'), default=None)
3086 if func_code:
3087 func_code = ([func_code[0]], func_code[1])
3088 else:
3089 self.write_debug('Extracting nsig function with jsinterp')
3090 func_code = jsi.extract_function_code(func_name)
3091
3092 self.cache.store('youtube-nsig', player_id, func_code)
3093 return jsi, player_id, func_code
3094
3095 def _extract_n_function_from_code(self, jsi, func_code):
3096 func = jsi.extract_function_from_code(*func_code)
3097
3098 def extract_nsig(s):
3099 try:
3100 ret = func([s])
3101 except JSInterpreter.Exception:
3102 raise
3103 except Exception as e:
3104 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3105
3106 if ret.startswith('enhanced_except_'):
3107 raise JSInterpreter.Exception('Signature function returned an exception')
3108 return ret
3109
3110 return extract_nsig
3111
3112 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3113 """
3114 Extract signatureTimestamp (sts)
3115 Required to tell API what sig/player version is in use.
3116 """
3117 sts = None
3118 if isinstance(ytcfg, dict):
3119 sts = int_or_none(ytcfg.get('STS'))
3120
3121 if not sts:
3122 # Attempt to extract from player
3123 if player_url is None:
3124 error_msg = 'Cannot extract signature timestamp without player_url.'
3125 if fatal:
3126 raise ExtractorError(error_msg)
3127 self.report_warning(error_msg)
3128 return
3129 code = self._load_player(video_id, player_url, fatal=fatal)
3130 if code:
3131 sts = int_or_none(self._search_regex(
3132 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3133 'JS player signature timestamp', group='sts', fatal=fatal))
3134 return sts
3135
3136 def _mark_watched(self, video_id, player_responses):
3137 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3138 label = 'fully ' if is_full else ''
3139 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3140 expected_type=url_or_none)
3141 if not url:
3142 self.report_warning(f'Unable to mark {label}watched')
3143 return
3144 parsed_url = urllib.parse.urlparse(url)
3145 qs = urllib.parse.parse_qs(parsed_url.query)
3146
3147 # cpn generation algorithm is reverse engineered from base.js.
3148 # In fact it works even with dummy cpn.
3149 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3150 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3151
3152 # # more consistent results setting it to right before the end
3153 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3154
3155 qs.update({
3156 'ver': ['2'],
3157 'cpn': [cpn],
3158 'cmt': video_length,
3159 'el': 'detailpage', # otherwise defaults to "shorts"
3160 })
3161
3162 if is_full:
3163 # these seem to mark watchtime "history" in the real world
3164 # they're required, so send in a single value
3165 qs.update({
3166 'st': 0,
3167 'et': video_length,
3168 })
3169
3170 url = urllib.parse.urlunparse(
3171 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
3172
3173 self._download_webpage(
3174 url, video_id, f'Marking {label}watched',
3175 'Unable to mark watched', fatal=False)
3176
3177 @classmethod
3178 def _extract_from_webpage(cls, url, webpage):
3179 # Invidious Instances
3180 # https://github.com/yt-dlp/yt-dlp/issues/195
3181 # https://github.com/iv-org/invidious/pull/1730
3182 mobj = re.search(
3183 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3184 webpage)
3185 if mobj:
3186 yield cls.url_result(mobj.group('url'), cls)
3187 raise cls.StopExtraction()
3188
3189 yield from super()._extract_from_webpage(url, webpage)
3190
3191 # lazyYT YouTube embed
3192 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3193 yield cls.url_result(unescapeHTML(id_), cls, id_)
3194
3195 # Wordpress "YouTube Video Importer" plugin
3196 for m in re.findall(r'''(?x)<div[^>]+
3197 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3198 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3199 yield cls.url_result(m[-1], cls, m[-1])
3200
3201 @classmethod
3202 def extract_id(cls, url):
3203 video_id = cls.get_temp_id(url)
3204 if not video_id:
3205 raise ExtractorError(f'Invalid URL: {url}')
3206 return video_id
3207
3208 def _extract_chapters_from_json(self, data, duration):
3209 chapter_list = traverse_obj(
3210 data, (
3211 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3212 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3213 ), expected_type=list)
3214
3215 return self._extract_chapters_helper(
3216 chapter_list,
3217 start_function=lambda chapter: float_or_none(
3218 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3219 title_function=lambda chapter: traverse_obj(
3220 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3221 duration=duration)
3222
3223 def _extract_chapters_from_engagement_panel(self, data, duration):
3224 content_list = traverse_obj(
3225 data,
3226 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
3227 expected_type=list)
3228 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3229 chapter_title = lambda chapter: self._get_text(chapter, 'title')
3230
3231 return next(filter(None, (
3232 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3233 chapter_time, chapter_title, duration)
3234 for contents in content_list)), [])
3235
3236 def _extract_comment(self, comment_renderer, parent=None):
3237 comment_id = comment_renderer.get('commentId')
3238 if not comment_id:
3239 return
3240
3241 text = self._get_text(comment_renderer, 'contentText')
3242
3243 # Timestamp is an estimate calculated from the current time and time_text
3244 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3245 timestamp = self._parse_time_text(time_text)
3246
3247 author = self._get_text(comment_renderer, 'authorText')
3248 author_id = try_get(comment_renderer,
3249 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3250
3251 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3252 lambda x: x['likeCount']), str)) or 0
3253 author_thumbnail = try_get(comment_renderer,
3254 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3255
3256 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3257 is_favorited = 'creatorHeart' in (try_get(
3258 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3259 return {
3260 'id': comment_id,
3261 'text': text,
3262 'timestamp': timestamp,
3263 'time_text': time_text,
3264 'like_count': votes,
3265 'is_favorited': is_favorited,
3266 'author': author,
3267 'author_id': author_id,
3268 'author_thumbnail': author_thumbnail,
3269 'author_is_uploader': author_is_uploader,
3270 'parent': parent or 'root'
3271 }
3272
3273 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3274
3275 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3276
3277 def extract_header(contents):
3278 _continuation = None
3279 for content in contents:
3280 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3281 expected_comment_count = self._get_count(
3282 comments_header_renderer, 'countText', 'commentsCount')
3283
3284 if expected_comment_count:
3285 tracker['est_total'] = expected_comment_count
3286 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3287 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3288
3289 sort_menu_item = try_get(
3290 comments_header_renderer,
3291 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3292 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3293
3294 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3295 if not _continuation:
3296 continue
3297
3298 sort_text = str_or_none(sort_menu_item.get('title'))
3299 if not sort_text:
3300 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3301 self.to_screen('Sorting comments by %s' % sort_text.lower())
3302 break
3303 return _continuation
3304
3305 def extract_thread(contents):
3306 if not parent:
3307 tracker['current_page_thread'] = 0
3308 for content in contents:
3309 if not parent and tracker['total_parent_comments'] >= max_parents:
3310 yield
3311 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3312 comment_renderer = get_first(
3313 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3314 expected_type=dict, default={})
3315
3316 comment = self._extract_comment(comment_renderer, parent)
3317 if not comment:
3318 continue
3319 # Sometimes YouTube may break and give us infinite looping comments.
3320 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
3321 if comment['id'] in tracker['seen_comment_ids']:
3322 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3323 yield
3324 else:
3325 tracker['seen_comment_ids'].add(comment['id'])
3326
3327 tracker['running_total'] += 1
3328 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3329 yield comment
3330
3331 # Attempt to get the replies
3332 comment_replies_renderer = try_get(
3333 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3334
3335 if comment_replies_renderer:
3336 tracker['current_page_thread'] += 1
3337 comment_entries_iter = self._comment_entries(
3338 comment_replies_renderer, ytcfg, video_id,
3339 parent=comment.get('id'), tracker=tracker)
3340 yield from itertools.islice(comment_entries_iter, min(
3341 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3342
3343 # Keeps track of counts across recursive calls
3344 if not tracker:
3345 tracker = dict(
3346 running_total=0,
3347 est_total=0,
3348 current_page_thread=0,
3349 total_parent_comments=0,
3350 total_reply_comments=0,
3351 seen_comment_ids=set())
3352
3353 # TODO: Deprecated
3354 # YouTube comments have a max depth of 2
3355 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3356 if max_depth:
3357 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3358 'Set max replies in the max-comments extractor argument instead')
3359 if max_depth == 1 and parent:
3360 return
3361
3362 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3363 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3364
3365 continuation = self._extract_continuation(root_continuation_data)
3366
3367 response = None
3368 is_forced_continuation = False
3369 is_first_continuation = parent is None
3370 if is_first_continuation and not continuation:
3371 # Sometimes you can get comments by generating the continuation yourself,
3372 # even if YouTube initially reports them being disabled - e.g. stories comments.
3373 # Note: if the comment section is actually disabled, YouTube may return a response with
3374 # required check_get_keys missing. So we will disable that check initially in this case.
3375 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3376 is_forced_continuation = True
3377
3378 for page_num in itertools.count(0):
3379 if not continuation:
3380 break
3381 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3382 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
3383 if page_num == 0:
3384 if is_first_continuation:
3385 note_prefix = 'Downloading comment section API JSON'
3386 else:
3387 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3388 tracker['current_page_thread'], comment_prog_str)
3389 else:
3390 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3391 ' ' if parent else '', ' replies' if parent else '',
3392 page_num, comment_prog_str)
3393 try:
3394 response = self._extract_response(
3395 item_id=None, query=continuation,
3396 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3397 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3398 except ExtractorError as e:
3399 # Ignore incomplete data error for replies if retries didn't work.
3400 # This is to allow any other parent comments and comment threads to be downloaded.
3401 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3402 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3403 self.report_warning(
3404 'Received incomplete data for a comment reply thread and retrying did not help. '
3405 'Ignoring to let other comments be downloaded.')
3406 else:
3407 raise
3408 is_forced_continuation = False
3409 continuation_contents = traverse_obj(
3410 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3411
3412 continuation = None
3413 for continuation_section in continuation_contents:
3414 continuation_items = traverse_obj(
3415 continuation_section,
3416 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3417 get_all=False, expected_type=list) or []
3418 if is_first_continuation:
3419 continuation = extract_header(continuation_items)
3420 is_first_continuation = False
3421 if continuation:
3422 break
3423 continue
3424
3425 for entry in extract_thread(continuation_items):
3426 if not entry:
3427 return
3428 yield entry
3429 continuation = self._extract_continuation({'contents': continuation_items})
3430 if continuation:
3431 break
3432
3433 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3434 if message and not parent and tracker['running_total'] == 0:
3435 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3436 raise self.CommentsDisabled
3437
3438 @staticmethod
3439 def _generate_comment_continuation(video_id):
3440 """
3441 Generates initial comment section continuation token from given video id
3442 """
3443 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3444 return base64.b64encode(token.encode()).decode()
3445
3446 def _get_comments(self, ytcfg, video_id, contents, webpage):
3447 """Entry for comment extraction"""
3448 def _real_comment_extract(contents):
3449 renderer = next((
3450 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3451 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3452 yield from self._comment_entries(renderer, ytcfg, video_id)
3453
3454 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3455 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3456
3457 @staticmethod
3458 def _get_checkok_params():
3459 return {'contentCheckOk': True, 'racyCheckOk': True}
3460
3461 @classmethod
3462 def _generate_player_context(cls, sts=None):
3463 context = {
3464 'html5Preference': 'HTML5_PREF_WANTS',
3465 }
3466 if sts is not None:
3467 context['signatureTimestamp'] = sts
3468 return {
3469 'playbackContext': {
3470 'contentPlaybackContext': context
3471 },
3472 **cls._get_checkok_params()
3473 }
3474
3475 @staticmethod
3476 def _is_agegated(player_response):
3477 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3478 return True
3479
3480 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
3481 AGE_GATE_REASONS = (
3482 'confirm your age', 'age-restricted', 'inappropriate', # reason
3483 'age_verification_required', 'age_check_required', # status
3484 )
3485 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3486
3487 @staticmethod
3488 def _is_unplayable(player_response):
3489 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3490
3491 _STORY_PLAYER_PARAMS = '8AEB'
3492
3493 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3494
3495 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3496 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3497 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3498 headers = self.generate_api_headers(
3499 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3500
3501 yt_query = {
3502 'videoId': video_id,
3503 }
3504 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3505 yt_query['params'] = self._STORY_PLAYER_PARAMS
3506
3507 yt_query.update(self._generate_player_context(sts))
3508 return self._extract_response(
3509 item_id=video_id, ep='player', query=yt_query,
3510 ytcfg=player_ytcfg, headers=headers, fatal=True,
3511 default_client=client,
3512 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3513 ) or None
3514
3515 def _get_requested_clients(self, url, smuggled_data):
3516 requested_clients = []
3517 default = ['android', 'web']
3518 allowed_clients = sorted(
3519 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3520 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3521 for client in self._configuration_arg('player_client'):
3522 if client in allowed_clients:
3523 requested_clients.append(client)
3524 elif client == 'default':
3525 requested_clients.extend(default)
3526 elif client == 'all':
3527 requested_clients.extend(allowed_clients)
3528 else:
3529 self.report_warning(f'Skipping unsupported client {client}')
3530 if not requested_clients:
3531 requested_clients = default
3532
3533 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3534 requested_clients.extend(
3535 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3536
3537 return orderedSet(requested_clients)
3538
3539 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3540 initial_pr = None
3541 if webpage:
3542 initial_pr = self._search_json(
3543 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3544
3545 all_clients = set(clients)
3546 clients = clients[::-1]
3547 prs = []
3548
3549 def append_client(*client_names):
3550 """ Append the first client name that exists but not already used """
3551 for client_name in client_names:
3552 actual_client = _split_innertube_client(client_name)[0]
3553 if actual_client in INNERTUBE_CLIENTS:
3554 if actual_client not in all_clients:
3555 clients.append(client_name)
3556 all_clients.add(actual_client)
3557 return
3558
3559 # Android player_response does not have microFormats which are needed for
3560 # extraction of some data. So we return the initial_pr with formats
3561 # stripped out even if not requested by the user
3562 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3563 if initial_pr:
3564 pr = dict(initial_pr)
3565 pr['streamingData'] = None
3566 prs.append(pr)
3567
3568 last_error = None
3569 tried_iframe_fallback = False
3570 player_url = None
3571 while clients:
3572 client, base_client, variant = _split_innertube_client(clients.pop())
3573 player_ytcfg = master_ytcfg if client == 'web' else {}
3574 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3575 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3576
3577 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3578 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3579 if 'js' in self._configuration_arg('player_skip'):
3580 require_js_player = False
3581 player_url = None
3582
3583 if not player_url and not tried_iframe_fallback and require_js_player:
3584 player_url = self._download_player_url(video_id)
3585 tried_iframe_fallback = True
3586
3587 try:
3588 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3589 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3590 except ExtractorError as e:
3591 if last_error:
3592 self.report_warning(last_error)
3593 last_error = e
3594 continue
3595
3596 if pr:
3597 # YouTube may return a different video player response than expected.
3598 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3599 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3600 if pr_video_id and pr_video_id != video_id:
3601 self.report_warning(
3602 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
3603 else:
3604 # Save client name for introspection later
3605 name = short_client_name(client)
3606 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3607 sd[STREAMING_DATA_CLIENT_NAME] = name
3608 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3609 f[STREAMING_DATA_CLIENT_NAME] = name
3610 prs.append(pr)
3611
3612 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3613 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3614 append_client(f'{base_client}_creator')
3615 elif self._is_agegated(pr):
3616 if variant == 'tv_embedded':
3617 append_client(f'{base_client}_embedded')
3618 elif not variant:
3619 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3620
3621 if last_error:
3622 if not len(prs):
3623 raise last_error
3624 self.report_warning(last_error)
3625 return prs, player_url
3626
3627 def _needs_live_processing(self, live_status, duration):
3628 if (live_status == 'is_live' and self.get_param('live_from_start')
3629 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3630 return live_status
3631
3632 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3633 itags, stream_ids = collections.defaultdict(set), []
3634 itag_qualities, res_qualities = {}, {0: None}
3635 q = qualities([
3636 # Normally tiny is the smallest video-only formats. But
3637 # audio-only formats with unknown quality may get tagged as tiny
3638 'tiny',
3639 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3640 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3641 ])
3642 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
3643 all_formats = self._configuration_arg('include_duplicate_formats')
3644
3645 for fmt in streaming_formats:
3646 if fmt.get('targetDurationSec'):
3647 continue
3648
3649 itag = str_or_none(fmt.get('itag'))
3650 audio_track = fmt.get('audioTrack') or {}
3651 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
3652 if not all_formats:
3653 if stream_id in stream_ids:
3654 continue
3655
3656 quality = fmt.get('quality')
3657 height = int_or_none(fmt.get('height'))
3658 if quality == 'tiny' or not quality:
3659 quality = fmt.get('audioQuality', '').lower() or quality
3660 # The 3gp format (17) in android client has a quality of "small",
3661 # but is actually worse than other formats
3662 if itag == '17':
3663 quality = 'tiny'
3664 if quality:
3665 if itag:
3666 itag_qualities[itag] = quality
3667 if height:
3668 res_qualities[height] = quality
3669 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3670 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3671 # number of fragment that would subsequently requested with (`&sq=N`)
3672 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3673 continue
3674
3675 fmt_url = fmt.get('url')
3676 if not fmt_url:
3677 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3678 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3679 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3680 if not all((sc, fmt_url, player_url, encrypted_sig)):
3681 continue
3682 try:
3683 fmt_url += '&%s=%s' % (
3684 traverse_obj(sc, ('sp', -1)) or 'signature',
3685 self._decrypt_signature(encrypted_sig, video_id, player_url)
3686 )
3687 except ExtractorError as e:
3688 self.report_warning('Signature extraction failed: Some formats may be missing',
3689 video_id=video_id, only_once=True)
3690 self.write_debug(e, only_once=True)
3691 continue
3692
3693 query = parse_qs(fmt_url)
3694 throttled = False
3695 if query.get('n'):
3696 try:
3697 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3698 fmt_url = update_url_query(fmt_url, {
3699 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3700 })
3701 except ExtractorError as e:
3702 phantomjs_hint = ''
3703 if isinstance(e, JSInterpreter.Exception):
3704 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3705 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3706 if player_url:
3707 self.report_warning(
3708 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3709 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3710 self.write_debug(e, only_once=True)
3711 else:
3712 self.report_warning(
3713 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3714 video_id=video_id, only_once=True)
3715 throttled = True
3716
3717 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3718 language_preference = (
3719 10 if audio_track.get('audioIsDefault') and 10
3720 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3721 else -1)
3722 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3723 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3724 # Make sure to avoid false positives with small duration differences.
3725 # E.g. __2ABJjxzNo, ySuUZEjARPY
3726 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3727 if is_damaged:
3728 self.report_warning(
3729 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3730
3731 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
3732 dct = {
3733 'asr': int_or_none(fmt.get('audioSampleRate')),
3734 'filesize': int_or_none(fmt.get('contentLength')),
3735 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
3736 'format_note': join_nonempty(
3737 join_nonempty(audio_track.get('displayName'),
3738 language_preference > 0 and ' (default)', delim=''),
3739 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3740 fmt.get('isDrc') and 'DRC',
3741 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3742 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3743 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
3744 (self.get_param('verbose') or all_formats) and client_name,
3745 delim=', '),
3746 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3747 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3748 'fps': int_or_none(fmt.get('fps')) or None,
3749 'audio_channels': fmt.get('audioChannels'),
3750 'height': height,
3751 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
3752 'has_drm': bool(fmt.get('drmFamilies')),
3753 'tbr': tbr,
3754 'url': fmt_url,
3755 'width': int_or_none(fmt.get('width')),
3756 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3757 'desc' if language_preference < -1 else '') or None,
3758 'language_preference': language_preference,
3759 # Strictly de-prioritize damaged and 3gp formats
3760 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3761 }
3762 mime_mobj = re.match(
3763 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3764 if mime_mobj:
3765 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3766 dct.update(parse_codecs(mime_mobj.group(2)))
3767 if itag:
3768 itags[itag].add(('https', dct.get('language')))
3769 stream_ids.append(stream_id)
3770 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3771 if single_stream and dct.get('ext'):
3772 dct['container'] = dct['ext'] + '_dash'
3773
3774 CHUNK_SIZE = 10 << 20
3775 if dct['filesize']:
3776 yield {
3777 **dct,
3778 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
3779 'protocol': 'http_dash_segments',
3780 'fragments': [{
3781 'url': update_url_query(dct['url'], {
3782 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, dct["filesize"])}'
3783 })
3784 } for range_start in range(0, dct['filesize'], CHUNK_SIZE)]
3785 }
3786 if not all_formats:
3787 continue
3788 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3789 yield dct
3790
3791 needs_live_processing = self._needs_live_processing(live_status, duration)
3792 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3793
3794 skip_manifests = set(self._configuration_arg('skip'))
3795 if (not self.get_param('youtube_include_hls_manifest', True)
3796 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3797 or needs_live_processing and skip_bad_formats):
3798 skip_manifests.add('hls')
3799
3800 if not self.get_param('youtube_include_dash_manifest', True):
3801 skip_manifests.add('dash')
3802 if self._configuration_arg('include_live_dash'):
3803 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3804 'Use include_incomplete_formats extractor argument instead')
3805 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3806 skip_manifests.add('dash')
3807
3808 def process_manifest_format(f, proto, client_name, itag):
3809 key = (proto, f.get('language'))
3810 if not all_formats and key in itags[itag]:
3811 return False
3812 itags[itag].add(key)
3813
3814 if itag and all_formats:
3815 f['format_id'] = f'{itag}-{proto}'
3816 elif any(p != proto for p, _ in itags[itag]):
3817 f['format_id'] = f'{itag}-{proto}'
3818 elif itag:
3819 f['format_id'] = itag
3820
3821 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3822 if f['quality'] == -1 and f.get('height'):
3823 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3824 if self.get_param('verbose'):
3825 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
3826 return True
3827
3828 subtitles = {}
3829 for sd in streaming_data:
3830 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3831
3832 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3833 if hls_manifest_url:
3834 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3835 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3836 subtitles = self._merge_subtitles(subs, subtitles)
3837 for f in fmts:
3838 if process_manifest_format(f, 'hls', client_name, self._search_regex(
3839 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3840 yield f
3841
3842 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3843 if dash_manifest_url:
3844 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3845 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3846 for f in formats:
3847 if process_manifest_format(f, 'dash', client_name, f['format_id']):
3848 f['filesize'] = int_or_none(self._search_regex(
3849 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3850 if needs_live_processing:
3851 f['is_from_start'] = True
3852
3853 yield f
3854 yield subtitles
3855
3856 def _extract_storyboard(self, player_responses, duration):
3857 spec = get_first(
3858 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3859 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3860 if not base_url:
3861 return
3862 L = len(spec) - 1
3863 for i, args in enumerate(spec):
3864 args = args.split('#')
3865 counts = list(map(int_or_none, args[:5]))
3866 if len(args) != 8 or not all(counts):
3867 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3868 continue
3869 width, height, frame_count, cols, rows = counts
3870 N, sigh = args[6:]
3871
3872 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3873 fragment_count = frame_count / (cols * rows)
3874 fragment_duration = duration / fragment_count
3875 yield {
3876 'format_id': f'sb{i}',
3877 'format_note': 'storyboard',
3878 'ext': 'mhtml',
3879 'protocol': 'mhtml',
3880 'acodec': 'none',
3881 'vcodec': 'none',
3882 'url': url,
3883 'width': width,
3884 'height': height,
3885 'fps': frame_count / duration,
3886 'rows': rows,
3887 'columns': cols,
3888 'fragments': [{
3889 'url': url.replace('$M', str(j)),
3890 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3891 } for j in range(math.ceil(fragment_count))],
3892 }
3893
3894 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3895 webpage = None
3896 if 'webpage' not in self._configuration_arg('player_skip'):
3897 query = {'bpctr': '9999999999', 'has_verified': '1'}
3898 if smuggled_data.get('is_story'):
3899 query['pp'] = self._STORY_PLAYER_PARAMS
3900 webpage = self._download_webpage(
3901 webpage_url, video_id, fatal=False, query=query)
3902
3903 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3904
3905 player_responses, player_url = self._extract_player_responses(
3906 self._get_requested_clients(url, smuggled_data),
3907 video_id, webpage, master_ytcfg, smuggled_data)
3908
3909 return webpage, master_ytcfg, player_responses, player_url
3910
3911 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3912 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3913 is_live = get_first(video_details, 'isLive')
3914 if is_live is None:
3915 is_live = get_first(live_broadcast_details, 'isLiveNow')
3916 live_content = get_first(video_details, 'isLiveContent')
3917 is_upcoming = get_first(video_details, 'isUpcoming')
3918 post_live = get_first(video_details, 'isPostLiveDvr')
3919 live_status = ('post_live' if post_live
3920 else 'is_live' if is_live
3921 else 'is_upcoming' if is_upcoming
3922 else 'was_live' if live_content
3923 else 'not_live' if False in (is_live, live_content)
3924 else None)
3925 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
3926 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3927
3928 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3929
3930 def _real_extract(self, url):
3931 url, smuggled_data = unsmuggle_url(url, {})
3932 video_id = self._match_id(url)
3933
3934 base_url = self.http_scheme() + '//www.youtube.com/'
3935 webpage_url = base_url + 'watch?v=' + video_id
3936
3937 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3938
3939 playability_statuses = traverse_obj(
3940 player_responses, (..., 'playabilityStatus'), expected_type=dict)
3941
3942 trailer_video_id = get_first(
3943 playability_statuses,
3944 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3945 expected_type=str)
3946 if trailer_video_id:
3947 return self.url_result(
3948 trailer_video_id, self.ie_key(), trailer_video_id)
3949
3950 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3951 if webpage else (lambda x: None))
3952
3953 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
3954 microformats = traverse_obj(
3955 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3956 expected_type=dict)
3957
3958 translated_title = self._get_text(microformats, (..., 'title'))
3959 video_title = (self._preferred_lang and translated_title
3960 or get_first(video_details, 'title') # primary
3961 or translated_title
3962 or search_meta(['og:title', 'twitter:title', 'title']))
3963 translated_description = self._get_text(microformats, (..., 'description'))
3964 original_description = get_first(video_details, 'shortDescription')
3965 video_description = (
3966 self._preferred_lang and translated_description
3967 # If original description is blank, it will be an empty string.
3968 # Do not prefer translated description in this case.
3969 or original_description if original_description is not None else translated_description)
3970
3971 multifeed_metadata_list = get_first(
3972 player_responses,
3973 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3974 expected_type=str)
3975 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3976 if self.get_param('noplaylist'):
3977 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3978 else:
3979 entries = []
3980 feed_ids = []
3981 for feed in multifeed_metadata_list.split(','):
3982 # Unquote should take place before split on comma (,) since textual
3983 # fields may contain comma as well (see
3984 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3985 feed_data = urllib.parse.parse_qs(
3986 urllib.parse.unquote_plus(feed))
3987
3988 def feed_entry(name):
3989 return try_get(
3990 feed_data, lambda x: x[name][0], str)
3991
3992 feed_id = feed_entry('id')
3993 if not feed_id:
3994 continue
3995 feed_title = feed_entry('title')
3996 title = video_title
3997 if feed_title:
3998 title += ' (%s)' % feed_title
3999 entries.append({
4000 '_type': 'url_transparent',
4001 'ie_key': 'Youtube',
4002 'url': smuggle_url(
4003 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4004 {'force_singlefeed': True}),
4005 'title': title,
4006 })
4007 feed_ids.append(feed_id)
4008 self.to_screen(
4009 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4010 % (', '.join(feed_ids), video_id))
4011 return self.playlist_result(
4012 entries, video_id, video_title, video_description)
4013
4014 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4015 or int_or_none(get_first(microformats, 'lengthSeconds'))
4016 or parse_duration(search_meta('duration')) or None)
4017
4018 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4019 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4020 if live_status == 'post_live':
4021 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
4022
4023 if not formats:
4024 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
4025 self.report_drm(video_id)
4026 pemr = get_first(
4027 playability_statuses,
4028 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4029 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4030 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
4031 if subreason:
4032 if subreason == 'The uploader has not made this video available in your country.':
4033 countries = get_first(microformats, 'availableCountries')
4034 if not countries:
4035 regions_allowed = search_meta('regionsAllowed')
4036 countries = regions_allowed.split(',') if regions_allowed else None
4037 self.raise_geo_restricted(subreason, countries, metadata_available=True)
4038 reason += f'. {subreason}'
4039 if reason:
4040 self.raise_no_formats(reason, expected=True)
4041
4042 keywords = get_first(video_details, 'keywords', expected_type=list) or []
4043 if not keywords and webpage:
4044 keywords = [
4045 unescapeHTML(m.group('content'))
4046 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4047 for keyword in keywords:
4048 if keyword.startswith('yt:stretch='):
4049 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4050 if mobj:
4051 # NB: float is intentional for forcing float division
4052 w, h = (float(v) for v in mobj.groups())
4053 if w > 0 and h > 0:
4054 ratio = w / h
4055 for f in formats:
4056 if f.get('vcodec') != 'none':
4057 f['stretched_ratio'] = ratio
4058 break
4059 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
4060 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4061 if thumbnail_url:
4062 thumbnails.append({
4063 'url': thumbnail_url,
4064 })
4065 original_thumbnails = thumbnails.copy()
4066
4067 # The best resolution thumbnails sometimes does not appear in the webpage
4068 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4069 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4070 thumbnail_names = [
4071 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4072 # in resolution, these are not the custom thumbnail. So de-prioritize them
4073 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4074 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4075 ]
4076 n_thumbnail_names = len(thumbnail_names)
4077 thumbnails.extend({
4078 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4079 video_id=video_id, name=name, ext=ext,
4080 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
4081 } for name in thumbnail_names for ext in ('webp', 'jpg'))
4082 for thumb in thumbnails:
4083 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
4084 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
4085 self._remove_duplicate_formats(thumbnails)
4086 self._downloader._sort_thumbnails(original_thumbnails)
4087
4088 category = get_first(microformats, 'category') or search_meta('genre')
4089 channel_id = str_or_none(
4090 get_first(video_details, 'channelId')
4091 or get_first(microformats, 'externalChannelId')
4092 or search_meta('channelId'))
4093 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4094
4095 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4096 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4097 if not duration and live_end_time and live_start_time:
4098 duration = live_end_time - live_start_time
4099
4100 needs_live_processing = self._needs_live_processing(live_status, duration)
4101
4102 def is_bad_format(fmt):
4103 if needs_live_processing and not fmt.get('is_from_start'):
4104 return True
4105 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4106 and fmt.get('protocol') == 'http_dash_segments'):
4107 return True
4108
4109 for fmt in filter(is_bad_format, formats):
4110 fmt['preference'] = (fmt.get('preference') or -1) - 10
4111 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4112
4113 if needs_live_processing:
4114 self._prepare_live_from_start_formats(
4115 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
4116
4117 formats.extend(self._extract_storyboard(player_responses, duration))
4118
4119 info = {
4120 'id': video_id,
4121 'title': video_title,
4122 'formats': formats,
4123 'thumbnails': thumbnails,
4124 # The best thumbnail that we are sure exists. Prevents unnecessary
4125 # URL checking if user don't care about getting the best possible thumbnail
4126 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
4127 'description': video_description,
4128 'uploader': get_first(video_details, 'author'),
4129 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
4130 'uploader_url': owner_profile_url,
4131 'channel_id': channel_id,
4132 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
4133 'duration': duration,
4134 'view_count': int_or_none(
4135 get_first((video_details, microformats), (..., 'viewCount'))
4136 or search_meta('interactionCount')),
4137 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
4138 'age_limit': 18 if (
4139 get_first(microformats, 'isFamilySafe') is False
4140 or search_meta('isFamilyFriendly') == 'false'
4141 or search_meta('og:restrictions:age') == '18+') else 0,
4142 'webpage_url': webpage_url,
4143 'categories': [category] if category else None,
4144 'tags': keywords,
4145 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4146 'live_status': live_status,
4147 'release_timestamp': live_start_time,
4148 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4149 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4150 }
4151
4152 subtitles = {}
4153 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
4154 if pctr:
4155 def get_lang_code(track):
4156 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4157 or track.get('languageCode'))
4158
4159 # Converted into dicts to remove duplicates
4160 captions = {
4161 get_lang_code(sub): sub
4162 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
4163 translation_languages = {
4164 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
4165 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
4166
4167 def process_language(container, base_url, lang_code, sub_name, query):
4168 lang_subs = container.setdefault(lang_code, [])
4169 for fmt in self._SUBTITLE_FORMATS:
4170 query.update({
4171 'fmt': fmt,
4172 })
4173 lang_subs.append({
4174 'ext': fmt,
4175 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
4176 'name': sub_name,
4177 })
4178
4179 # NB: Constructing the full subtitle dictionary is slow
4180 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4181 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
4182 for lang_code, caption_track in captions.items():
4183 base_url = caption_track.get('baseUrl')
4184 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
4185 if not base_url:
4186 continue
4187 lang_name = self._get_text(caption_track, 'name', max_runs=1)
4188 if caption_track.get('kind') != 'asr':
4189 if not lang_code:
4190 continue
4191 process_language(
4192 subtitles, base_url, lang_code, lang_name, {})
4193 if not caption_track.get('isTranslatable'):
4194 continue
4195 for trans_code, trans_name in translation_languages.items():
4196 if not trans_code:
4197 continue
4198 orig_trans_code = trans_code
4199 if caption_track.get('kind') != 'asr' and trans_code != 'und':
4200 if not get_translated_subs:
4201 continue
4202 trans_code += f'-{lang_code}'
4203 trans_name += format_field(lang_name, None, ' from %s')
4204 # Add an "-orig" label to the original language so that it can be distinguished.
4205 # The subs are returned without "-orig" as well for compatibility
4206 if lang_code == f'a-{orig_trans_code}':
4207 process_language(
4208 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4209 # Setting tlang=lang returns damaged subtitles.
4210 process_language(automatic_captions, base_url, trans_code, trans_name,
4211 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
4212
4213 info['automatic_captions'] = automatic_captions
4214 info['subtitles'] = subtitles
4215
4216 parsed_url = urllib.parse.urlparse(url)
4217 for component in [parsed_url.fragment, parsed_url.query]:
4218 query = urllib.parse.parse_qs(component)
4219 for k, v in query.items():
4220 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4221 d_k += '_time'
4222 if d_k not in info and k in s_ks:
4223 info[d_k] = parse_duration(query[k][0])
4224
4225 # Youtube Music Auto-generated description
4226 if video_description:
4227 mobj = re.search(
4228 r'''(?xs)
4229 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4230 (?P<album>[^\n]+)
4231 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4232 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4233 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4234 .+\nAuto-generated\ by\ YouTube\.\s*$
4235 ''', video_description)
4236 if mobj:
4237 release_year = mobj.group('release_year')
4238 release_date = mobj.group('release_date')
4239 if release_date:
4240 release_date = release_date.replace('-', '')
4241 if not release_year:
4242 release_year = release_date[:4]
4243 info.update({
4244 'album': mobj.group('album'.strip()),
4245 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4246 'track': mobj.group('track').strip(),
4247 'release_date': release_date,
4248 'release_year': int_or_none(release_year),
4249 })
4250
4251 initial_data = None
4252 if webpage:
4253 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4254 if not initial_data:
4255 query = {'videoId': video_id}
4256 query.update(self._get_checkok_params())
4257 initial_data = self._extract_response(
4258 item_id=video_id, ep='next', fatal=False,
4259 ytcfg=master_ytcfg, query=query,
4260 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4261 note='Downloading initial data API JSON')
4262
4263 info['comment_count'] = traverse_obj(initial_data, (
4264 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4265 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4266 ), (
4267 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4268 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4269 ), expected_type=int_or_none, get_all=False)
4270
4271 try: # This will error if there is no livechat
4272 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4273 except (KeyError, IndexError, TypeError):
4274 pass
4275 else:
4276 info.setdefault('subtitles', {})['live_chat'] = [{
4277 # url is needed to set cookies
4278 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4279 'video_id': video_id,
4280 'ext': 'json',
4281 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4282 else 'youtube_live_chat_replay'),
4283 }]
4284
4285 if initial_data:
4286 info['chapters'] = (
4287 self._extract_chapters_from_json(initial_data, duration)
4288 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4289 or self._extract_chapters_from_description(video_description, duration)
4290 or None)
4291
4292 contents = traverse_obj(
4293 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4294 expected_type=list, default=[])
4295
4296 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4297 if vpir:
4298 stl = vpir.get('superTitleLink')
4299 if stl:
4300 stl = self._get_text(stl)
4301 if try_get(
4302 vpir,
4303 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4304 info['location'] = stl
4305 else:
4306 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4307 if mobj:
4308 info.update({
4309 'series': mobj.group(1),
4310 'season_number': int(mobj.group(2)),
4311 'episode_number': int(mobj.group(3)),
4312 })
4313 for tlb in (try_get(
4314 vpir,
4315 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4316 list) or []):
4317 tbrs = variadic(
4318 traverse_obj(
4319 tlb, ('toggleButtonRenderer', ...),
4320 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4321 for tbr in tbrs:
4322 for getter, regex in [(
4323 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4324 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4325 lambda x: x['accessibility'],
4326 lambda x: x['accessibilityData']['accessibilityData'],
4327 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4328 label = (try_get(tbr, getter, dict) or {}).get('label')
4329 if label:
4330 mobj = re.match(regex, label)
4331 if mobj:
4332 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4333 break
4334 sbr_tooltip = try_get(
4335 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4336 if sbr_tooltip:
4337 like_count, dislike_count = sbr_tooltip.split(' / ')
4338 info.update({
4339 'like_count': str_to_int(like_count),
4340 'dislike_count': str_to_int(dislike_count),
4341 })
4342 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4343 if vcr:
4344 vc = self._get_count(vcr, 'viewCount')
4345 # Upcoming premieres with waiting count are treated as live here
4346 if vcr.get('isLive'):
4347 info['concurrent_view_count'] = vc
4348 elif info.get('view_count') is None:
4349 info['view_count'] = vc
4350
4351 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4352 if vsir:
4353 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4354 info.update({
4355 'channel': self._get_text(vor, 'title'),
4356 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4357
4358 rows = try_get(
4359 vsir,
4360 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4361 list) or []
4362 multiple_songs = False
4363 for row in rows:
4364 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4365 multiple_songs = True
4366 break
4367 for row in rows:
4368 mrr = row.get('metadataRowRenderer') or {}
4369 mrr_title = mrr.get('title')
4370 if not mrr_title:
4371 continue
4372 mrr_title = self._get_text(mrr, 'title')
4373 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4374 if mrr_title == 'License':
4375 info['license'] = mrr_contents_text
4376 elif not multiple_songs:
4377 if mrr_title == 'Album':
4378 info['album'] = mrr_contents_text
4379 elif mrr_title == 'Artist':
4380 info['artist'] = mrr_contents_text
4381 elif mrr_title == 'Song':
4382 info['track'] = mrr_contents_text
4383
4384 fallbacks = {
4385 'channel': 'uploader',
4386 'channel_id': 'uploader_id',
4387 'channel_url': 'uploader_url',
4388 }
4389
4390 # The upload date for scheduled, live and past live streams / premieres in microformats
4391 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4392 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4393 upload_date = (
4394 unified_strdate(get_first(microformats, 'uploadDate'))
4395 or unified_strdate(search_meta('uploadDate')))
4396 if not upload_date or (
4397 live_status in ('not_live', None)
4398 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4399 ):
4400 upload_date = strftime_or_none(
4401 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4402 info['upload_date'] = upload_date
4403
4404 for to, frm in fallbacks.items():
4405 if not info.get(to):
4406 info[to] = info.get(frm)
4407
4408 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4409 v = info.get(s_k)
4410 if v:
4411 info[d_k] = v
4412
4413 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4414
4415 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4416 or get_first(video_details, 'isPrivate', expected_type=bool))
4417
4418 info['availability'] = (
4419 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4420 else self._availability(
4421 is_private=is_private,
4422 needs_premium=(
4423 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4424 or False if initial_data and is_private is not None else None),
4425 needs_subscription=(
4426 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4427 or False if initial_data and is_private is not None else None),
4428 needs_auth=info['age_limit'] >= 18,
4429 is_unlisted=None if is_private is None else (
4430 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4431 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4432
4433 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4434
4435 self.mark_watched(video_id, player_responses)
4436
4437 return info
4438
4439
4440 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4441 @staticmethod
4442 def passthrough_smuggled_data(func):
4443 def _smuggle(info, smuggled_data):
4444 if info.get('_type') not in ('url', 'url_transparent'):
4445 return info
4446 if smuggled_data.get('is_music_url'):
4447 parsed_url = urllib.parse.urlparse(info['url'])
4448 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4449 smuggled_data.pop('is_music_url')
4450 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4451 if smuggled_data:
4452 info['url'] = smuggle_url(info['url'], smuggled_data)
4453 return info
4454
4455 @functools.wraps(func)
4456 def wrapper(self, url):
4457 url, smuggled_data = unsmuggle_url(url, {})
4458 if self.is_music_url(url):
4459 smuggled_data['is_music_url'] = True
4460 info_dict = func(self, url, smuggled_data)
4461 if smuggled_data:
4462 _smuggle(info_dict, smuggled_data)
4463 if info_dict.get('entries'):
4464 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
4465 return info_dict
4466 return wrapper
4467
4468 @staticmethod
4469 def _extract_basic_item_renderer(item):
4470 # Modified from _extract_grid_item_renderer
4471 known_basic_renderers = (
4472 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4473 )
4474 for key, renderer in item.items():
4475 if not isinstance(renderer, dict):
4476 continue
4477 elif key in known_basic_renderers:
4478 return renderer
4479 elif key.startswith('grid') and key.endswith('Renderer'):
4480 return renderer
4481
4482 def _extract_channel_renderer(self, renderer):
4483 channel_id = renderer['channelId']
4484 title = self._get_text(renderer, 'title')
4485 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4486 return {
4487 '_type': 'url',
4488 'url': channel_url,
4489 'id': channel_id,
4490 'ie_key': YoutubeTabIE.ie_key(),
4491 'channel': title,
4492 'channel_id': channel_id,
4493 'channel_url': channel_url,
4494 'title': title,
4495 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4496 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4497 'playlist_count': self._get_count(renderer, 'videoCountText'),
4498 'description': self._get_text(renderer, 'descriptionSnippet'),
4499 }
4500
4501 def _grid_entries(self, grid_renderer):
4502 for item in grid_renderer['items']:
4503 if not isinstance(item, dict):
4504 continue
4505 renderer = self._extract_basic_item_renderer(item)
4506 if not isinstance(renderer, dict):
4507 continue
4508 title = self._get_text(renderer, 'title')
4509
4510 # playlist
4511 playlist_id = renderer.get('playlistId')
4512 if playlist_id:
4513 yield self.url_result(
4514 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4515 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4516 video_title=title)
4517 continue
4518 # video
4519 video_id = renderer.get('videoId')
4520 if video_id:
4521 yield self._extract_video(renderer)
4522 continue
4523 # channel
4524 channel_id = renderer.get('channelId')
4525 if channel_id:
4526 yield self._extract_channel_renderer(renderer)
4527 continue
4528 # generic endpoint URL support
4529 ep_url = urljoin('https://www.youtube.com/', try_get(
4530 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4531 str))
4532 if ep_url:
4533 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4534 if ie.suitable(ep_url):
4535 yield self.url_result(
4536 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4537 break
4538
4539 def _music_reponsive_list_entry(self, renderer):
4540 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4541 if video_id:
4542 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4543 ie=YoutubeIE.ie_key(), video_id=video_id)
4544 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4545 if playlist_id:
4546 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4547 if video_id:
4548 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4549 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4550 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4551 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4552 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4553 if browse_id:
4554 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4555 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4556
4557 def _shelf_entries_from_content(self, shelf_renderer):
4558 content = shelf_renderer.get('content')
4559 if not isinstance(content, dict):
4560 return
4561 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4562 if renderer:
4563 # TODO: add support for nested playlists so each shelf is processed
4564 # as separate playlist
4565 # TODO: this includes only first N items
4566 yield from self._grid_entries(renderer)
4567 renderer = content.get('horizontalListRenderer')
4568 if renderer:
4569 # TODO
4570 pass
4571
4572 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4573 ep = try_get(
4574 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4575 str)
4576 shelf_url = urljoin('https://www.youtube.com', ep)
4577 if shelf_url:
4578 # Skipping links to another channels, note that checking for
4579 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4580 # will not work
4581 if skip_channels and '/channels?' in shelf_url:
4582 return
4583 title = self._get_text(shelf_renderer, 'title')
4584 yield self.url_result(shelf_url, video_title=title)
4585 # Shelf may not contain shelf URL, fallback to extraction from content
4586 yield from self._shelf_entries_from_content(shelf_renderer)
4587
4588 def _playlist_entries(self, video_list_renderer):
4589 for content in video_list_renderer['contents']:
4590 if not isinstance(content, dict):
4591 continue
4592 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4593 if not isinstance(renderer, dict):
4594 continue
4595 video_id = renderer.get('videoId')
4596 if not video_id:
4597 continue
4598 yield self._extract_video(renderer)
4599
4600 def _rich_entries(self, rich_grid_renderer):
4601 renderer = traverse_obj(
4602 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4603 video_id = renderer.get('videoId')
4604 if not video_id:
4605 return
4606 yield self._extract_video(renderer)
4607
4608 def _video_entry(self, video_renderer):
4609 video_id = video_renderer.get('videoId')
4610 if video_id:
4611 return self._extract_video(video_renderer)
4612
4613 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4614 url = urljoin('https://youtube.com', traverse_obj(
4615 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4616 if url:
4617 return self.url_result(
4618 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4619
4620 def _post_thread_entries(self, post_thread_renderer):
4621 post_renderer = try_get(
4622 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4623 if not post_renderer:
4624 return
4625 # video attachment
4626 video_renderer = try_get(
4627 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4628 video_id = video_renderer.get('videoId')
4629 if video_id:
4630 entry = self._extract_video(video_renderer)
4631 if entry:
4632 yield entry
4633 # playlist attachment
4634 playlist_id = try_get(
4635 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4636 if playlist_id:
4637 yield self.url_result(
4638 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4639 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4640 # inline video links
4641 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4642 for run in runs:
4643 if not isinstance(run, dict):
4644 continue
4645 ep_url = try_get(
4646 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4647 if not ep_url:
4648 continue
4649 if not YoutubeIE.suitable(ep_url):
4650 continue
4651 ep_video_id = YoutubeIE._match_id(ep_url)
4652 if video_id == ep_video_id:
4653 continue
4654 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4655
4656 def _post_thread_continuation_entries(self, post_thread_continuation):
4657 contents = post_thread_continuation.get('contents')
4658 if not isinstance(contents, list):
4659 return
4660 for content in contents:
4661 renderer = content.get('backstagePostThreadRenderer')
4662 if isinstance(renderer, dict):
4663 yield from self._post_thread_entries(renderer)
4664 continue
4665 renderer = content.get('videoRenderer')
4666 if isinstance(renderer, dict):
4667 yield self._video_entry(renderer)
4668
4669 r''' # unused
4670 def _rich_grid_entries(self, contents):
4671 for content in contents:
4672 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4673 if video_renderer:
4674 entry = self._video_entry(video_renderer)
4675 if entry:
4676 yield entry
4677 '''
4678
4679 def _report_history_entries(self, renderer):
4680 for url in traverse_obj(renderer, (
4681 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4682 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4683 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4684 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4685
4686 def _extract_entries(self, parent_renderer, continuation_list):
4687 # continuation_list is modified in-place with continuation_list = [continuation_token]
4688 continuation_list[:] = [None]
4689 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4690 for content in contents:
4691 if not isinstance(content, dict):
4692 continue
4693 is_renderer = traverse_obj(
4694 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4695 expected_type=dict)
4696 if not is_renderer:
4697 if content.get('richItemRenderer'):
4698 for entry in self._rich_entries(content['richItemRenderer']):
4699 yield entry
4700 continuation_list[0] = self._extract_continuation(parent_renderer)
4701 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4702 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4703 yield from self._report_history_entries(table)
4704 continuation_list[0] = self._extract_continuation(table)
4705 continue
4706
4707 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4708 for isr_content in isr_contents:
4709 if not isinstance(isr_content, dict):
4710 continue
4711
4712 known_renderers = {
4713 'playlistVideoListRenderer': self._playlist_entries,
4714 'gridRenderer': self._grid_entries,
4715 'reelShelfRenderer': self._grid_entries,
4716 'shelfRenderer': self._shelf_entries,
4717 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4718 'backstagePostThreadRenderer': self._post_thread_entries,
4719 'videoRenderer': lambda x: [self._video_entry(x)],
4720 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4721 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4722 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4723 }
4724 for key, renderer in isr_content.items():
4725 if key not in known_renderers:
4726 continue
4727 for entry in known_renderers[key](renderer):
4728 if entry:
4729 yield entry
4730 continuation_list[0] = self._extract_continuation(renderer)
4731 break
4732
4733 if not continuation_list[0]:
4734 continuation_list[0] = self._extract_continuation(is_renderer)
4735
4736 if not continuation_list[0]:
4737 continuation_list[0] = self._extract_continuation(parent_renderer)
4738
4739 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4740 continuation_list = [None]
4741 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4742 tab_content = try_get(tab, lambda x: x['content'], dict)
4743 if not tab_content:
4744 return
4745 parent_renderer = (
4746 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4747 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4748 yield from extract_entries(parent_renderer)
4749 continuation = continuation_list[0]
4750
4751 for page_num in itertools.count(1):
4752 if not continuation:
4753 break
4754 headers = self.generate_api_headers(
4755 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4756 response = self._extract_response(
4757 item_id=f'{item_id} page {page_num}',
4758 query=continuation, headers=headers, ytcfg=ytcfg,
4759 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4760
4761 if not response:
4762 break
4763 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4764 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4765 visitor_data = self._extract_visitor_data(response) or visitor_data
4766
4767 known_renderers = {
4768 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4769 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4770 'gridVideoRenderer': (self._grid_entries, 'items'),
4771 'gridChannelRenderer': (self._grid_entries, 'items'),
4772 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4773 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4774 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4775 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4776 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4777 'playlistVideoListContinuation': (self._playlist_entries, None),
4778 'gridContinuation': (self._grid_entries, None),
4779 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4780 'sectionListContinuation': (extract_entries, None), # for feeds
4781 }
4782
4783 continuation_items = traverse_obj(response, (
4784 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4785 'appendContinuationItemsAction', 'continuationItems'
4786 ), 'continuationContents', get_all=False)
4787 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4788
4789 video_items_renderer = None
4790 for key in continuation_item.keys():
4791 if key not in known_renderers:
4792 continue
4793 func, parent_key = known_renderers[key]
4794 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4795 continuation_list = [None]
4796 yield from func(video_items_renderer)
4797 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4798
4799 if not video_items_renderer:
4800 break
4801
4802 @staticmethod
4803 def _extract_selected_tab(tabs, fatal=True):
4804 for tab_renderer in tabs:
4805 if tab_renderer.get('selected'):
4806 return tab_renderer
4807 if fatal:
4808 raise ExtractorError('Unable to find selected tab')
4809
4810 @staticmethod
4811 def _extract_tab_renderers(response):
4812 return traverse_obj(
4813 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
4814
4815 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4816 metadata = self._extract_metadata_from_tabs(item_id, data)
4817
4818 selected_tab = self._extract_selected_tab(tabs)
4819 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4820 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4821
4822 return self.playlist_result(
4823 self._entries(
4824 selected_tab, metadata['id'], ytcfg,
4825 self._extract_account_syncid(ytcfg, data),
4826 self._extract_visitor_data(data, ytcfg)),
4827 **metadata)
4828
4829 def _extract_metadata_from_tabs(self, item_id, data):
4830 info = {'id': item_id}
4831
4832 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
4833 if metadata_renderer:
4834 info.update({
4835 'uploader': metadata_renderer.get('title'),
4836 'uploader_id': metadata_renderer.get('externalId'),
4837 'uploader_url': metadata_renderer.get('channelUrl'),
4838 })
4839 if info['uploader_id']:
4840 info['id'] = info['uploader_id']
4841 else:
4842 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
4843
4844 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4845 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4846 def _get_uncropped(url):
4847 return url_or_none((url or '').split('=')[0] + '=s0')
4848
4849 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
4850 if avatar_thumbnails:
4851 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4852 if uncropped_avatar:
4853 avatar_thumbnails.append({
4854 'url': uncropped_avatar,
4855 'id': 'avatar_uncropped',
4856 'preference': 1
4857 })
4858
4859 channel_banners = self._extract_thumbnails(
4860 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4861 for banner in channel_banners:
4862 banner['preference'] = -10
4863
4864 if channel_banners:
4865 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4866 if uncropped_banner:
4867 channel_banners.append({
4868 'url': uncropped_banner,
4869 'id': 'banner_uncropped',
4870 'preference': -5
4871 })
4872
4873 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4874 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4875 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4876
4877 primary_thumbnails = self._extract_thumbnails(
4878 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4879 playlist_thumbnails = self._extract_thumbnails(
4880 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4881
4882 info.update({
4883 'title': (traverse_obj(metadata_renderer, 'title')
4884 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4885 or info['id']),
4886 'availability': self._extract_availability(data),
4887 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4888 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4889 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4890 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4891 })
4892
4893 # Playlist stats is a text runs array containing [video count, view count, last updated].
4894 # last updated or (view count and last updated) may be missing.
4895 playlist_stats = get_first(
4896 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4897
4898 last_updated_unix = self._parse_time_text(
4899 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4900 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4901 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
4902
4903 info['view_count'] = self._get_count(playlist_stats, 1)
4904 if info['view_count'] is None: # 0 is allowed
4905 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4906 if info['view_count'] is None:
4907 info['view_count'] = self._get_count(data, (
4908 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4909 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4910
4911 info['playlist_count'] = self._get_count(playlist_stats, 0)
4912 if info['playlist_count'] is None: # 0 is allowed
4913 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4914
4915 if not info.get('uploader_id'):
4916 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4917 if not owner: # Deprecated
4918 owner = traverse_obj(
4919 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4920 ('videoOwner', 'videoOwnerRenderer', 'title'))
4921 owner_text = self._get_text(owner)
4922 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4923 info.update({
4924 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4925 'uploader_id': browse_ep.get('browseId'),
4926 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4927 })
4928
4929 info.update({
4930 'channel': info['uploader'],
4931 'channel_id': info['uploader_id'],
4932 'channel_url': info['uploader_url']
4933 })
4934 return info
4935
4936 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4937 first_id = last_id = response = None
4938 for page_num in itertools.count(1):
4939 videos = list(self._playlist_entries(playlist))
4940 if not videos:
4941 return
4942 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4943 if start >= len(videos):
4944 return
4945 yield from videos[start:]
4946 first_id = first_id or videos[0]['id']
4947 last_id = videos[-1]['id']
4948 watch_endpoint = try_get(
4949 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4950 headers = self.generate_api_headers(
4951 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4952 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4953 query = {
4954 'playlistId': playlist_id,
4955 'videoId': watch_endpoint.get('videoId') or last_id,
4956 'index': watch_endpoint.get('index') or len(videos),
4957 'params': watch_endpoint.get('params') or 'OAE%3D'
4958 }
4959 response = self._extract_response(
4960 item_id='%s page %d' % (playlist_id, page_num),
4961 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4962 check_get_keys='contents'
4963 )
4964 playlist = try_get(
4965 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4966
4967 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4968 title = playlist.get('title') or try_get(
4969 data, lambda x: x['titleText']['simpleText'], str)
4970 playlist_id = playlist.get('playlistId') or item_id
4971
4972 # Delegating everything except mix playlists to regular tab-based playlist URL
4973 playlist_url = urljoin(url, try_get(
4974 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4975 str))
4976
4977 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4978 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4979 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4980
4981 if playlist_url and playlist_url != url and not is_known_unviewable:
4982 return self.url_result(
4983 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4984 video_title=title)
4985
4986 return self.playlist_result(
4987 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4988 playlist_id=playlist_id, playlist_title=title)
4989
4990 def _extract_availability(self, data):
4991 """
4992 Gets the availability of a given playlist/tab.
4993 Note: Unless YouTube tells us explicitly, we do not assume it is public
4994 @param data: response
4995 """
4996 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4997 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4998 player_header_privacy = playlist_header_renderer.get('privacy')
4999
5000 badges = self._extract_badges(sidebar_renderer)
5001
5002 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
5003 privacy_setting_icon = get_first(
5004 (playlist_header_renderer, sidebar_renderer),
5005 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5006 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5007 expected_type=str)
5008
5009 microformats_is_unlisted = traverse_obj(
5010 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
5011
5012 return (
5013 'public' if (
5014 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5015 or player_header_privacy == 'PUBLIC'
5016 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5017 else self._availability(
5018 is_private=(
5019 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5020 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5021 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5022 is_unlisted=(
5023 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5024 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
5025 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5026 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
5027 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5028 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5029 needs_auth=False))
5030
5031 @staticmethod
5032 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5033 sidebar_renderer = try_get(
5034 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5035 for item in sidebar_renderer:
5036 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5037 if renderer:
5038 return renderer
5039
5040 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
5041 """
5042 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5043 """
5044 is_playlist = bool(traverse_obj(
5045 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5046 if not is_playlist:
5047 return
5048 headers = self.generate_api_headers(
5049 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5050 visitor_data=self._extract_visitor_data(data, ytcfg))
5051 query = {
5052 'params': 'wgYCCAA=',
5053 'browseId': f'VL{item_id}'
5054 }
5055 return self._extract_response(
5056 item_id=item_id, headers=headers, query=query,
5057 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
5058 note='Redownloading playlist API JSON with unavailable videos')
5059
5060 @functools.cached_property
5061 def skip_webpage(self):
5062 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5063
5064 def _extract_webpage(self, url, item_id, fatal=True):
5065 webpage, data = None, None
5066 for retry in self.RetryManager(fatal=fatal):
5067 try:
5068 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
5069 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5070 except ExtractorError as e:
5071 if isinstance(e.cause, network_exceptions):
5072 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
5073 retry.error = e
5074 continue
5075 self._error_or_warning(e, fatal=fatal)
5076 break
5077
5078 try:
5079 self._extract_and_report_alerts(data)
5080 except ExtractorError as e:
5081 self._error_or_warning(e, fatal=fatal)
5082 break
5083
5084 # Sometimes youtube returns a webpage with incomplete ytInitialData
5085 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5086 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5087 retry.error = ExtractorError('Incomplete yt initial data received')
5088 continue
5089
5090 return webpage, data
5091
5092 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5093 """Use if failed to extract ytcfg (and data) from initial webpage"""
5094 if not ytcfg and self.is_authenticated:
5095 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5096 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5097 raise ExtractorError(
5098 f'{msg}. If you are not downloading private content, or '
5099 'your cookies are only for the first account and channel,'
5100 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5101 expected=True)
5102 self.report_warning(msg, only_once=True)
5103
5104 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5105 data = None
5106 if not self.skip_webpage:
5107 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5108 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
5109 # Reject webpage data if redirected to home page without explicitly requesting
5110 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
5111 if (url != 'https://www.youtube.com/feed/recommended'
5112 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5113 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5114 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5115 if fatal:
5116 raise ExtractorError(msg, expected=True)
5117 self.report_warning(msg, only_once=True)
5118 if not data:
5119 self._report_playlist_authcheck(ytcfg, fatal=fatal)
5120 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5121 return data, ytcfg
5122
5123 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5124 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5125 resolve_response = self._extract_response(
5126 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5127 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5128 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5129 for ep_key, ep in endpoints.items():
5130 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5131 if params:
5132 return self._extract_response(
5133 item_id=item_id, query=params, ep=ep, headers=headers,
5134 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
5135 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5136 err_note = 'Failed to resolve url (does the playlist exist?)'
5137 if fatal:
5138 raise ExtractorError(err_note, expected=True)
5139 self.report_warning(err_note, item_id)
5140
5141 _SEARCH_PARAMS = None
5142
5143 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
5144 data = {'query': query}
5145 if params is NO_DEFAULT:
5146 params = self._SEARCH_PARAMS
5147 if params:
5148 data['params'] = params
5149
5150 content_keys = (
5151 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5152 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5153 # ytmusic search
5154 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5155 ('continuationContents', ),
5156 )
5157 display_id = f'query "{query}"'
5158 check_get_keys = tuple({keys[0] for keys in content_keys})
5159 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5160 self._report_playlist_authcheck(ytcfg, fatal=False)
5161
5162 continuation_list = [None]
5163 search = None
5164 for page_num in itertools.count(1):
5165 data.update(continuation_list[0] or {})
5166 headers = self.generate_api_headers(
5167 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
5168 search = self._extract_response(
5169 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5170 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
5171 slr_contents = traverse_obj(search, *content_keys)
5172 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
5173 if not continuation_list[0]:
5174 break
5175
5176
5177 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5178 IE_DESC = 'YouTube Tabs'
5179 _VALID_URL = r'''(?x:
5180 https?://
5181 (?!consent\.)(?:\w+\.)?
5182 (?:
5183 youtube(?:kids)?\.com|
5184 %(invidious)s
5185 )/
5186 (?:
5187 (?P<channel_type>channel|c|user|browse)/|
5188 (?P<not_channel>
5189 feed/|hashtag/|
5190 (?:playlist|watch)\?.*?\blist=
5191 )|
5192 (?!(?:%(reserved_names)s)\b) # Direct URLs
5193 )
5194 (?P<id>[^/?\#&]+)
5195 )''' % {
5196 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5197 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5198 }
5199 IE_NAME = 'youtube:tab'
5200
5201 _TESTS = [{
5202 'note': 'playlists, multipage',
5203 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5204 'playlist_mincount': 94,
5205 'info_dict': {
5206 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5207 'title': 'Igor Kleiner - Playlists',
5208 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5209 'uploader': 'Igor Kleiner',
5210 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5211 'channel': 'Igor Kleiner',
5212 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5213 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5214 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5215 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5216 'channel_follower_count': int
5217 },
5218 }, {
5219 'note': 'playlists, multipage, different order',
5220 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5221 'playlist_mincount': 94,
5222 'info_dict': {
5223 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5224 'title': 'Igor Kleiner - Playlists',
5225 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5226 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5227 'uploader': 'Igor Kleiner',
5228 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5229 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5230 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5231 'channel': 'Igor Kleiner',
5232 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5233 'channel_follower_count': int
5234 },
5235 }, {
5236 'note': 'playlists, series',
5237 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5238 'playlist_mincount': 5,
5239 'info_dict': {
5240 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5241 'title': '3Blue1Brown - Playlists',
5242 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5243 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5244 'uploader': '3Blue1Brown',
5245 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5246 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5247 'channel': '3Blue1Brown',
5248 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5249 'tags': ['Mathematics'],
5250 'channel_follower_count': int
5251 },
5252 }, {
5253 'note': 'playlists, singlepage',
5254 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5255 'playlist_mincount': 4,
5256 'info_dict': {
5257 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5258 'title': 'ThirstForScience - Playlists',
5259 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5260 'uploader': 'ThirstForScience',
5261 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5262 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5263 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5264 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5265 'tags': 'count:13',
5266 'channel': 'ThirstForScience',
5267 'channel_follower_count': int
5268 }
5269 }, {
5270 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5271 'only_matching': True,
5272 }, {
5273 'note': 'basic, single video playlist',
5274 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5275 'info_dict': {
5276 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5277 'uploader': 'Sergey M.',
5278 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5279 'title': 'youtube-dl public playlist',
5280 'description': '',
5281 'tags': [],
5282 'view_count': int,
5283 'modified_date': '20201130',
5284 'channel': 'Sergey M.',
5285 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5286 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5287 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5288 'availability': 'public',
5289 },
5290 'playlist_count': 1,
5291 }, {
5292 'note': 'empty playlist',
5293 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5294 'info_dict': {
5295 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5296 'uploader': 'Sergey M.',
5297 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5298 'title': 'youtube-dl empty playlist',
5299 'tags': [],
5300 'channel': 'Sergey M.',
5301 'description': '',
5302 'modified_date': '20160902',
5303 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5304 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5305 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5306 'availability': 'public',
5307 },
5308 'playlist_count': 0,
5309 }, {
5310 'note': 'Home tab',
5311 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5312 'info_dict': {
5313 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5314 'title': 'lex will - Home',
5315 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5316 'uploader': 'lex will',
5317 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5318 'channel': 'lex will',
5319 'tags': ['bible', 'history', 'prophesy'],
5320 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5321 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5322 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5323 'channel_follower_count': int
5324 },
5325 'playlist_mincount': 2,
5326 }, {
5327 'note': 'Videos tab',
5328 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5329 'info_dict': {
5330 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5331 'title': 'lex will - Videos',
5332 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5333 'uploader': 'lex will',
5334 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5335 'tags': ['bible', 'history', 'prophesy'],
5336 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5337 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5338 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5339 'channel': 'lex will',
5340 'channel_follower_count': int
5341 },
5342 'playlist_mincount': 975,
5343 }, {
5344 'note': 'Videos tab, sorted by popular',
5345 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5346 'info_dict': {
5347 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5348 'title': 'lex will - Videos',
5349 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5350 'uploader': 'lex will',
5351 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5352 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5353 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5354 'channel': 'lex will',
5355 'tags': ['bible', 'history', 'prophesy'],
5356 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5357 'channel_follower_count': int
5358 },
5359 'playlist_mincount': 199,
5360 }, {
5361 'note': 'Playlists tab',
5362 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5363 'info_dict': {
5364 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5365 'title': 'lex will - Playlists',
5366 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5367 'uploader': 'lex will',
5368 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5369 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5370 'channel': 'lex will',
5371 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5372 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5373 'tags': ['bible', 'history', 'prophesy'],
5374 'channel_follower_count': int
5375 },
5376 'playlist_mincount': 17,
5377 }, {
5378 'note': 'Community tab',
5379 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5380 'info_dict': {
5381 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5382 'title': 'lex will - Community',
5383 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5384 'uploader': 'lex will',
5385 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5386 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5387 'channel': 'lex will',
5388 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5389 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5390 'tags': ['bible', 'history', 'prophesy'],
5391 'channel_follower_count': int
5392 },
5393 'playlist_mincount': 18,
5394 }, {
5395 'note': 'Channels tab',
5396 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5397 'info_dict': {
5398 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5399 'title': 'lex will - Channels',
5400 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5401 'uploader': 'lex will',
5402 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5403 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5404 'channel': 'lex will',
5405 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5406 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5407 'tags': ['bible', 'history', 'prophesy'],
5408 'channel_follower_count': int
5409 },
5410 'playlist_mincount': 12,
5411 }, {
5412 'note': 'Search tab',
5413 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5414 'playlist_mincount': 40,
5415 'info_dict': {
5416 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5417 'title': '3Blue1Brown - Search - linear algebra',
5418 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5419 'uploader': '3Blue1Brown',
5420 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5421 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5422 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5423 'tags': ['Mathematics'],
5424 'channel': '3Blue1Brown',
5425 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5426 'channel_follower_count': int
5427 },
5428 }, {
5429 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5430 'only_matching': True,
5431 }, {
5432 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5433 'only_matching': True,
5434 }, {
5435 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5436 'only_matching': True,
5437 }, {
5438 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5439 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5440 'info_dict': {
5441 'title': '29C3: Not my department',
5442 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5443 'uploader': 'Christiaan008',
5444 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5445 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5446 'tags': [],
5447 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5448 'view_count': int,
5449 'modified_date': '20150605',
5450 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5451 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5452 'channel': 'Christiaan008',
5453 'availability': 'public',
5454 },
5455 'playlist_count': 96,
5456 }, {
5457 'note': 'Large playlist',
5458 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5459 'info_dict': {
5460 'title': 'Uploads from Cauchemar',
5461 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5462 'uploader': 'Cauchemar',
5463 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5464 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5465 'tags': [],
5466 'modified_date': r're:\d{8}',
5467 'channel': 'Cauchemar',
5468 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5469 'view_count': int,
5470 'description': '',
5471 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5472 'availability': 'public',
5473 },
5474 'playlist_mincount': 1123,
5475 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5476 }, {
5477 'note': 'even larger playlist, 8832 videos',
5478 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5479 'only_matching': True,
5480 }, {
5481 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5482 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5483 'info_dict': {
5484 'title': 'Uploads from Interstellar Movie',
5485 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5486 'uploader': 'Interstellar Movie',
5487 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5488 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5489 'tags': [],
5490 'view_count': int,
5491 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5492 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5493 'channel': 'Interstellar Movie',
5494 'description': '',
5495 'modified_date': r're:\d{8}',
5496 'availability': 'public',
5497 },
5498 'playlist_mincount': 21,
5499 }, {
5500 'note': 'Playlist with "show unavailable videos" button',
5501 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5502 'info_dict': {
5503 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5504 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5505 'uploader': 'Phim Siêu Nhân Nhật Bản',
5506 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5507 'view_count': int,
5508 'channel': 'Phim Siêu Nhân Nhật Bản',
5509 'tags': [],
5510 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5511 'description': '',
5512 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5513 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5514 'modified_date': r're:\d{8}',
5515 'availability': 'public',
5516 },
5517 'playlist_mincount': 200,
5518 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5519 }, {
5520 'note': 'Playlist with unavailable videos in page 7',
5521 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5522 'info_dict': {
5523 'title': 'Uploads from BlankTV',
5524 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5525 'uploader': 'BlankTV',
5526 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5527 'channel': 'BlankTV',
5528 'channel_url': 'https://www.youtube.com/c/blanktv',
5529 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5530 'view_count': int,
5531 'tags': [],
5532 'uploader_url': 'https://www.youtube.com/c/blanktv',
5533 'modified_date': r're:\d{8}',
5534 'description': '',
5535 'availability': 'public',
5536 },
5537 'playlist_mincount': 1000,
5538 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5539 }, {
5540 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5541 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5542 'info_dict': {
5543 'title': 'Data Analysis with Dr Mike Pound',
5544 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5545 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5546 'uploader': 'Computerphile',
5547 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5548 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5549 'tags': [],
5550 'view_count': int,
5551 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5552 'channel_url': 'https://www.youtube.com/user/Computerphile',
5553 'channel': 'Computerphile',
5554 'availability': 'public',
5555 'modified_date': '20190712',
5556 },
5557 'playlist_mincount': 11,
5558 }, {
5559 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5560 'only_matching': True,
5561 }, {
5562 'note': 'Playlist URL that does not actually serve a playlist',
5563 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5564 'info_dict': {
5565 'id': 'FqZTN594JQw',
5566 'ext': 'webm',
5567 'title': "Smiley's People 01 detective, Adventure Series, Action",
5568 'uploader': 'STREEM',
5569 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5570 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5571 'upload_date': '20150526',
5572 'license': 'Standard YouTube License',
5573 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5574 'categories': ['People & Blogs'],
5575 'tags': list,
5576 'view_count': int,
5577 'like_count': int,
5578 },
5579 'params': {
5580 'skip_download': True,
5581 },
5582 'skip': 'This video is not available.',
5583 'add_ie': [YoutubeIE.ie_key()],
5584 }, {
5585 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5586 'only_matching': True,
5587 }, {
5588 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5589 'only_matching': True,
5590 }, {
5591 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5592 'info_dict': {
5593 'id': 'Wq15eF5vCbI', # This will keep changing
5594 'ext': 'mp4',
5595 'title': str,
5596 'uploader': 'Sky News',
5597 'uploader_id': 'skynews',
5598 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5599 'upload_date': r're:\d{8}',
5600 'description': str,
5601 'categories': ['News & Politics'],
5602 'tags': list,
5603 'like_count': int,
5604 'release_timestamp': int,
5605 'channel': 'Sky News',
5606 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5607 'age_limit': 0,
5608 'view_count': int,
5609 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5610 'playable_in_embed': True,
5611 'release_date': r're:\d+',
5612 'availability': 'public',
5613 'live_status': 'is_live',
5614 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5615 'channel_follower_count': int,
5616 'concurrent_view_count': int,
5617 },
5618 'params': {
5619 'skip_download': True,
5620 },
5621 'expected_warnings': ['Ignoring subtitle tracks found in '],
5622 }, {
5623 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5624 'info_dict': {
5625 'id': 'a48o2S1cPoo',
5626 'ext': 'mp4',
5627 'title': 'The Young Turks - Live Main Show',
5628 'uploader': 'The Young Turks',
5629 'uploader_id': 'TheYoungTurks',
5630 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5631 'upload_date': '20150715',
5632 'license': 'Standard YouTube License',
5633 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5634 'categories': ['News & Politics'],
5635 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5636 'like_count': int,
5637 },
5638 'params': {
5639 'skip_download': True,
5640 },
5641 'only_matching': True,
5642 }, {
5643 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5644 'only_matching': True,
5645 }, {
5646 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5647 'only_matching': True,
5648 }, {
5649 'note': 'A channel that is not live. Should raise error',
5650 'url': 'https://www.youtube.com/user/numberphile/live',
5651 'only_matching': True,
5652 }, {
5653 'url': 'https://www.youtube.com/feed/trending',
5654 'only_matching': True,
5655 }, {
5656 'url': 'https://www.youtube.com/feed/library',
5657 'only_matching': True,
5658 }, {
5659 'url': 'https://www.youtube.com/feed/history',
5660 'only_matching': True,
5661 }, {
5662 'url': 'https://www.youtube.com/feed/subscriptions',
5663 'only_matching': True,
5664 }, {
5665 'url': 'https://www.youtube.com/feed/watch_later',
5666 'only_matching': True,
5667 }, {
5668 'note': 'Recommended - redirects to home page.',
5669 'url': 'https://www.youtube.com/feed/recommended',
5670 'only_matching': True,
5671 }, {
5672 'note': 'inline playlist with not always working continuations',
5673 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5674 'only_matching': True,
5675 }, {
5676 'url': 'https://www.youtube.com/course',
5677 'only_matching': True,
5678 }, {
5679 'url': 'https://www.youtube.com/zsecurity',
5680 'only_matching': True,
5681 }, {
5682 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5683 'only_matching': True,
5684 }, {
5685 'url': 'https://www.youtube.com/TheYoungTurks/live',
5686 'only_matching': True,
5687 }, {
5688 'url': 'https://www.youtube.com/hashtag/cctv9',
5689 'info_dict': {
5690 'id': 'cctv9',
5691 'title': '#cctv9',
5692 'tags': [],
5693 },
5694 'playlist_mincount': 300, # not consistent but should be over 300
5695 }, {
5696 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5697 'only_matching': True,
5698 }, {
5699 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5700 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5701 'only_matching': True
5702 }, {
5703 'note': '/browse/ should redirect to /channel/',
5704 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5705 'only_matching': True
5706 }, {
5707 'note': 'VLPL, should redirect to playlist?list=PL...',
5708 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5709 'info_dict': {
5710 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5711 'uploader': 'NoCopyrightSounds',
5712 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5713 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5714 'title': 'NCS : All Releases 💿',
5715 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5716 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5717 'modified_date': r're:\d{8}',
5718 'view_count': int,
5719 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5720 'tags': [],
5721 'channel': 'NoCopyrightSounds',
5722 'availability': 'public',
5723 },
5724 'playlist_mincount': 166,
5725 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5726 }, {
5727 'note': 'Topic, should redirect to playlist?list=UU...',
5728 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5729 'info_dict': {
5730 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5731 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5732 'title': 'Uploads from Royalty Free Music - Topic',
5733 'uploader': 'Royalty Free Music - Topic',
5734 'tags': [],
5735 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5736 'channel': 'Royalty Free Music - Topic',
5737 'view_count': int,
5738 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5739 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5740 'modified_date': r're:\d{8}',
5741 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5742 'description': '',
5743 'availability': 'public',
5744 },
5745 'playlist_mincount': 101,
5746 }, {
5747 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5748 # Treat as a general feed
5749 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5750 'info_dict': {
5751 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5752 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5753 'tags': [],
5754 },
5755 'playlist_mincount': 9,
5756 }, {
5757 'note': 'Youtube music Album',
5758 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5759 'info_dict': {
5760 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5761 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5762 'tags': [],
5763 'view_count': int,
5764 'description': '',
5765 'availability': 'unlisted',
5766 'modified_date': r're:\d{8}',
5767 },
5768 'playlist_count': 50,
5769 }, {
5770 'note': 'unlisted single video playlist',
5771 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5772 'info_dict': {
5773 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5774 'uploader': 'colethedj',
5775 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5776 'title': 'yt-dlp unlisted playlist test',
5777 'availability': 'unlisted',
5778 'tags': [],
5779 'modified_date': '20220418',
5780 'channel': 'colethedj',
5781 'view_count': int,
5782 'description': '',
5783 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5784 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5785 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5786 },
5787 'playlist_count': 1,
5788 }, {
5789 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5790 'url': 'https://www.youtube.com/feed/recommended',
5791 'info_dict': {
5792 'id': 'recommended',
5793 'title': 'recommended',
5794 'tags': [],
5795 },
5796 'playlist_mincount': 50,
5797 'params': {
5798 'skip_download': True,
5799 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5800 },
5801 }, {
5802 'note': 'API Fallback: /videos tab, sorted by oldest first',
5803 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5804 'info_dict': {
5805 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5806 'title': 'Cody\'sLab - Videos',
5807 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5808 'uploader': 'Cody\'sLab',
5809 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5810 'channel': 'Cody\'sLab',
5811 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5812 'tags': [],
5813 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5814 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5815 'channel_follower_count': int
5816 },
5817 'playlist_mincount': 650,
5818 'params': {
5819 'skip_download': True,
5820 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5821 },
5822 'skip': 'Query for sorting no longer works',
5823 }, {
5824 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5825 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5826 'info_dict': {
5827 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5828 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5829 'title': 'Uploads from Royalty Free Music - Topic',
5830 'uploader': 'Royalty Free Music - Topic',
5831 'modified_date': r're:\d{8}',
5832 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5833 'description': '',
5834 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5835 'tags': [],
5836 'channel': 'Royalty Free Music - Topic',
5837 'view_count': int,
5838 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5839 'availability': 'public',
5840 },
5841 'playlist_mincount': 101,
5842 'params': {
5843 'skip_download': True,
5844 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5845 },
5846 }, {
5847 'note': 'non-standard redirect to regional channel',
5848 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5849 'only_matching': True
5850 }, {
5851 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5852 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5853 'info_dict': {
5854 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5855 'modified_date': '20220407',
5856 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5857 'tags': [],
5858 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5859 'uploader': 'pukkandan',
5860 'availability': 'unlisted',
5861 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5862 'channel': 'pukkandan',
5863 'description': 'Test for collaborative playlist',
5864 'title': 'yt-dlp test - collaborative playlist',
5865 'view_count': int,
5866 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5867 },
5868 'playlist_mincount': 2
5869 }, {
5870 'note': 'translated tab name',
5871 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5872 'info_dict': {
5873 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5874 'tags': [],
5875 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5876 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5877 'description': 'test description',
5878 'title': 'cole-dlp-test-acc - 再生リスト',
5879 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5880 'uploader': 'cole-dlp-test-acc',
5881 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5882 'channel': 'cole-dlp-test-acc',
5883 },
5884 'playlist_mincount': 1,
5885 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5886 'expected_warnings': ['Preferring "ja"'],
5887 }, {
5888 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5889 'note': 'preferred lang set with playlist with translated video titles',
5890 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5891 'info_dict': {
5892 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5893 'tags': [],
5894 'view_count': int,
5895 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5896 'uploader': 'cole-dlp-test-acc',
5897 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5898 'channel': 'cole-dlp-test-acc',
5899 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5900 'description': 'test',
5901 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5902 'title': 'dlp test playlist',
5903 'availability': 'public',
5904 },
5905 'playlist_mincount': 1,
5906 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5907 'expected_warnings': ['Preferring "ja"'],
5908 }, {
5909 # shorts audio pivot for 2GtVksBMYFM.
5910 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5911 'info_dict': {
5912 'id': 'sfv_audio_pivot',
5913 'title': 'sfv_audio_pivot',
5914 'tags': [],
5915 },
5916 'playlist_mincount': 50,
5917
5918 }, {
5919 # Channel with a real live tab (not to be mistaken with streams tab)
5920 # Do not treat like it should redirect to live stream
5921 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5922 'info_dict': {
5923 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5924 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5925 'tags': [],
5926 },
5927 'playlist_mincount': 20,
5928 }, {
5929 # Tab name is not the same as tab id
5930 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5931 'info_dict': {
5932 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5933 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5934 'tags': [],
5935 },
5936 'playlist_mincount': 8,
5937 }, {
5938 # Home tab id is literally home. Not to get mistaken with featured
5939 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5940 'info_dict': {
5941 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5942 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5943 'tags': [],
5944 },
5945 'playlist_mincount': 8,
5946 }, {
5947 # Should get three playlists for videos, shorts and streams tabs
5948 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5949 'info_dict': {
5950 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5951 'title': 'Polka Ch. 尾丸ポルカ',
5952 'channel_follower_count': int,
5953 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5954 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5955 'uploader': 'Polka Ch. 尾丸ポルカ',
5956 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5957 'channel': 'Polka Ch. 尾丸ポルカ',
5958 'tags': 'count:35',
5959 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5960 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5961 },
5962 'playlist_count': 3,
5963 }, {
5964 # Shorts tab with channel with handle
5965 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5966 'info_dict': {
5967 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5968 'title': 'Not Just Bikes - Shorts',
5969 'tags': 'count:12',
5970 'uploader': 'Not Just Bikes',
5971 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5972 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5973 'channel_follower_count': int,
5974 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5975 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5976 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5977 'channel': 'Not Just Bikes',
5978 },
5979 'playlist_mincount': 10,
5980 }, {
5981 # Streams tab
5982 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5983 'info_dict': {
5984 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5985 'title': '中村悠一 - Live',
5986 'tags': 'count:7',
5987 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5988 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5989 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5990 'channel': '中村悠一',
5991 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5992 'channel_follower_count': int,
5993 'uploader': '中村悠一',
5994 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5995 },
5996 'playlist_mincount': 60,
5997 }, {
5998 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5999 # See test_youtube_lists
6000 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6001 'only_matching': True,
6002 }, {
6003 # No uploads and no UCID given. Should fail with no uploads error
6004 # See test_youtube_lists
6005 'url': 'https://www.youtube.com/news',
6006 'only_matching': True
6007 }, {
6008 # No videos tab but has a shorts tab
6009 'url': 'https://www.youtube.com/c/TKFShorts',
6010 'info_dict': {
6011 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6012 'title': 'Shorts Break - Shorts',
6013 'tags': 'count:32',
6014 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6015 'channel': 'Shorts Break',
6016 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
6017 'uploader': 'Shorts Break',
6018 'channel_follower_count': int,
6019 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6020 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6021 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6022 },
6023 'playlist_mincount': 30,
6024 }, {
6025 # Trending Now Tab. tab id is empty
6026 'url': 'https://www.youtube.com/feed/trending',
6027 'info_dict': {
6028 'id': 'trending',
6029 'title': 'trending - Now',
6030 'tags': [],
6031 },
6032 'playlist_mincount': 30,
6033 }, {
6034 # Trending Gaming Tab. tab id is empty
6035 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6036 'info_dict': {
6037 'id': 'trending',
6038 'title': 'trending - Gaming',
6039 'tags': [],
6040 },
6041 'playlist_mincount': 30,
6042 }, {
6043 # Shorts url result in shorts tab
6044 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6045 'info_dict': {
6046 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6047 'title': 'cole-dlp-test-acc - Shorts',
6048 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6049 'channel': 'cole-dlp-test-acc',
6050 'description': 'test description',
6051 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6052 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6053 'tags': [],
6054 'uploader': 'cole-dlp-test-acc',
6055 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6056
6057 },
6058 'playlist': [{
6059 'info_dict': {
6060 '_type': 'url',
6061 'ie_key': 'Youtube',
6062 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6063 'id': 'sSM9J5YH_60',
6064 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6065 'title': 'SHORT short',
6066 'channel': 'cole-dlp-test-acc',
6067 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6068 'view_count': int,
6069 'thumbnails': list,
6070 }
6071 }],
6072 'params': {'extract_flat': True},
6073 }, {
6074 # Live video status should be extracted
6075 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6076 'info_dict': {
6077 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6078 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6079 'tags': []
6080 },
6081 'playlist': [{
6082 'info_dict': {
6083 '_type': 'url',
6084 'ie_key': 'Youtube',
6085 'url': 'startswith:https://www.youtube.com/watch?v=',
6086 'id': str,
6087 'title': str,
6088 'live_status': 'is_live',
6089 'channel_id': str,
6090 'channel_url': str,
6091 'concurrent_view_count': int,
6092 'channel': str,
6093 }
6094 }],
6095 'params': {'extract_flat': True, 'playlist_items': '1'},
6096 'playlist_mincount': 1
6097 }, {
6098 # Channel renderer metadata. Contains number of videos on the channel
6099 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6100 'info_dict': {
6101 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6102 'title': 'cole-dlp-test-acc - Channels',
6103 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6104 'channel': 'cole-dlp-test-acc',
6105 'description': 'test description',
6106 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6107 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6108 'tags': [],
6109 'uploader': 'cole-dlp-test-acc',
6110 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6111
6112 },
6113 'playlist': [{
6114 'info_dict': {
6115 '_type': 'url',
6116 'ie_key': 'YoutubeTab',
6117 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6118 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6119 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6120 'title': 'PewDiePie',
6121 'channel': 'PewDiePie',
6122 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6123 'thumbnails': list,
6124 'channel_follower_count': int,
6125 'playlist_count': int
6126 }
6127 }],
6128 'params': {'extract_flat': True},
6129 }, {
6130 'url': 'https://www.youtube.com/@3blue1brown/about',
6131 'info_dict': {
6132 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6133 'tags': ['Mathematics'],
6134 'title': '3Blue1Brown - About',
6135 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6136 'channel_follower_count': int,
6137 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6138 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6139 'channel': '3Blue1Brown',
6140 'uploader': '3Blue1Brown',
6141 'view_count': int,
6142 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6143 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6144 },
6145 'playlist_count': 0,
6146 }]
6147
6148 @classmethod
6149 def suitable(cls, url):
6150 return False if YoutubeIE.suitable(url) else super().suitable(url)
6151
6152 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6153
6154 def _get_url_mobj(self, url):
6155 mobj = self._URL_RE.match(url).groupdict()
6156 mobj.update((k, '') for k, v in mobj.items() if v is None)
6157 return mobj
6158
6159 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6160 tab_name = (tab.get('title') or '').lower()
6161 tab_url = urljoin(base_url, traverse_obj(
6162 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6163
6164 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6165 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
6166 if tab_id:
6167 return {
6168 'TAB_ID_SPONSORSHIPS': 'membership',
6169 }.get(tab_id, tab_id), tab_name
6170
6171 # Fallback to tab name if we cannot get the tab id.
6172 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6173 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6174 if tab_name:
6175 self.write_debug(f'Falling back to selected tab name: {tab_name}')
6176 return {
6177 'home': 'featured',
6178 'live': 'streams',
6179 }.get(tab_name, tab_name), tab_name
6180
6181 def _has_tab(self, tabs, tab_id):
6182 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
6183
6184 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6185 def _real_extract(self, url, smuggled_data):
6186 item_id = self._match_id(url)
6187 url = urllib.parse.urlunparse(
6188 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
6189 compat_opts = self.get_param('compat_opts', [])
6190
6191 mobj = self._get_url_mobj(url)
6192 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
6193 if is_channel and smuggled_data.get('is_music_url'):
6194 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6195 return self.url_result(
6196 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6197 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6198 mdata = self._extract_tab_endpoint(
6199 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6200 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6201 get_all=False, expected_type=str)
6202 if not murl:
6203 raise ExtractorError('Failed to resolve album to playlist')
6204 return self.url_result(murl, YoutubeTabIE)
6205 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6206 return self.url_result(
6207 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6208
6209 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
6210 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
6211 url = f'{pre}/videos{post}'
6212 if smuggled_data.get('is_music_url'):
6213 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
6214
6215 # Handle both video/playlist URLs
6216 qs = parse_qs(url)
6217 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
6218 if not video_id and mobj['not_channel'].startswith('watch'):
6219 if not playlist_id:
6220 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6221 raise ExtractorError('A video URL was given without video ID', expected=True)
6222 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6223 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6224 return self.url_result(
6225 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
6226
6227 if not self._yes_playlist(playlist_id, video_id):
6228 return self.url_result(
6229 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6230
6231 data, ytcfg = self._extract_data(url, display_id)
6232
6233 # YouTube may provide a non-standard redirect to the regional channel
6234 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6235 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6236 redirect_url = traverse_obj(
6237 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6238 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
6239 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
6240 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6241 return self.url_result(redirect_url, YoutubeTabIE)
6242
6243 tabs, extra_tabs = self._extract_tab_renderers(data), []
6244 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
6245 selected_tab = self._extract_selected_tab(tabs)
6246 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6247 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6248
6249 if not original_tab_id and selected_tab_name:
6250 self.to_screen('Downloading all uploads of the channel. '
6251 'To download only the videos in a specific tab, pass the tab\'s URL')
6252 if self._has_tab(tabs, 'streams'):
6253 extra_tabs.append(''.join((pre, '/streams', post)))
6254 if self._has_tab(tabs, 'shorts'):
6255 extra_tabs.append(''.join((pre, '/shorts', post)))
6256 # XXX: Members-only tab should also be extracted
6257
6258 if not extra_tabs and selected_tab_id != 'videos':
6259 # Channel does not have streams, shorts or videos tabs
6260 if item_id[:2] != 'UC':
6261 raise ExtractorError('This channel has no uploads', expected=True)
6262
6263 # Topic channels don't have /videos. Use the equivalent playlist instead
6264 pl_id = f'UU{item_id[2:]}'
6265 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6266 try:
6267 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6268 except ExtractorError:
6269 raise ExtractorError('This channel has no uploads', expected=True)
6270 else:
6271 item_id, url = pl_id, pl_url
6272 self.to_screen(
6273 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6274
6275 elif extra_tabs and selected_tab_id != 'videos':
6276 # When there are shorts/live tabs but not videos tab
6277 url, data = f'{pre}{post}', None
6278
6279 elif (original_tab_id or 'videos') != selected_tab_id:
6280 if original_tab_id == 'live':
6281 # Live tab should have redirected to the video
6282 # Except in the case the channel has an actual live tab
6283 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6284 raise UserNotLive(video_id=item_id)
6285 elif selected_tab_name:
6286 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6287
6288 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6289 url = f'{pre}{post}'
6290
6291 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6292 if 'no-youtube-unavailable-videos' not in compat_opts:
6293 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
6294 self._extract_and_report_alerts(data, only_once=True)
6295
6296 tabs, entries = self._extract_tab_renderers(data), []
6297 if tabs:
6298 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6299 entries[0].update({
6300 'extractor_key': YoutubeTabIE.ie_key(),
6301 'extractor': YoutubeTabIE.IE_NAME,
6302 'webpage_url': url,
6303 })
6304 if self.get_param('playlist_items') == '0':
6305 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6306 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6307 entries.extend(map(self._real_extract, extra_tabs))
6308
6309 if len(entries) == 1:
6310 return entries[0]
6311 elif entries:
6312 metadata = self._extract_metadata_from_tabs(item_id, data)
6313 uploads_url = 'the Uploads (UU) playlist URL'
6314 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6315 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6316 self.to_screen(
6317 'Downloading as multiple playlists, separated by tabs. '
6318 f'To download as a single playlist instead, pass {uploads_url}')
6319 return self.playlist_result(entries, item_id, **metadata)
6320
6321 # Inline playlist
6322 playlist = traverse_obj(
6323 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
6324 if playlist:
6325 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
6326
6327 video_id = traverse_obj(
6328 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
6329 if video_id:
6330 if tab != '/live': # live tab is expected to redirect to video
6331 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
6332 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
6333
6334 raise ExtractorError('Unable to recognize tab page')
6335
6336
6337 class YoutubePlaylistIE(InfoExtractor):
6338 IE_DESC = 'YouTube playlists'
6339 _VALID_URL = r'''(?x)(?:
6340 (?:https?://)?
6341 (?:\w+\.)?
6342 (?:
6343 (?:
6344 youtube(?:kids)?\.com|
6345 %(invidious)s
6346 )
6347 /.*?\?.*?\blist=
6348 )?
6349 (?P<id>%(playlist_id)s)
6350 )''' % {
6351 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6352 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6353 }
6354 IE_NAME = 'youtube:playlist'
6355 _TESTS = [{
6356 'note': 'issue #673',
6357 'url': 'PLBB231211A4F62143',
6358 'info_dict': {
6359 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6360 'id': 'PLBB231211A4F62143',
6361 'uploader': 'Wickman',
6362 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6363 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6364 'view_count': int,
6365 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6366 'modified_date': r're:\d{8}',
6367 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6368 'channel': 'Wickman',
6369 'tags': [],
6370 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6371 'availability': 'public',
6372 },
6373 'playlist_mincount': 29,
6374 }, {
6375 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6376 'info_dict': {
6377 'title': 'YDL_safe_search',
6378 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6379 },
6380 'playlist_count': 2,
6381 'skip': 'This playlist is private',
6382 }, {
6383 'note': 'embedded',
6384 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6385 'playlist_count': 4,
6386 'info_dict': {
6387 'title': 'JODA15',
6388 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6389 'uploader': 'milan',
6390 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6391 'description': '',
6392 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6393 'tags': [],
6394 'modified_date': '20140919',
6395 'view_count': int,
6396 'channel': 'milan',
6397 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6398 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6399 'availability': 'public',
6400 },
6401 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
6402 }, {
6403 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6404 'playlist_mincount': 455,
6405 'info_dict': {
6406 'title': '2018 Chinese New Singles (11/6 updated)',
6407 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6408 'uploader': 'LBK',
6409 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6410 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6411 'channel': 'LBK',
6412 'view_count': int,
6413 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6414 'tags': [],
6415 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6416 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6417 'modified_date': r're:\d{8}',
6418 'availability': 'public',
6419 },
6420 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
6421 }, {
6422 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6423 'only_matching': True,
6424 }, {
6425 # music album playlist
6426 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6427 'only_matching': True,
6428 }]
6429
6430 @classmethod
6431 def suitable(cls, url):
6432 if YoutubeTabIE.suitable(url):
6433 return False
6434 from ..utils import parse_qs
6435 qs = parse_qs(url)
6436 if qs.get('v', [None])[0]:
6437 return False
6438 return super().suitable(url)
6439
6440 def _real_extract(self, url):
6441 playlist_id = self._match_id(url)
6442 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
6443 url = update_url_query(
6444 'https://www.youtube.com/playlist',
6445 parse_qs(url) or {'list': playlist_id})
6446 if is_music_url:
6447 url = smuggle_url(url, {'is_music_url': True})
6448 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6449
6450
6451 class YoutubeYtBeIE(InfoExtractor):
6452 IE_DESC = 'youtu.be'
6453 _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}
6454 _TESTS = [{
6455 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6456 'info_dict': {
6457 'id': 'yeWKywCrFtk',
6458 'ext': 'mp4',
6459 'title': 'Small Scale Baler and Braiding Rugs',
6460 'uploader': 'Backus-Page House Museum',
6461 'uploader_id': 'backuspagemuseum',
6462 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6463 'upload_date': '20161008',
6464 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6465 'categories': ['Nonprofits & Activism'],
6466 'tags': list,
6467 'like_count': int,
6468 'age_limit': 0,
6469 'playable_in_embed': True,
6470 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6471 'channel': 'Backus-Page House Museum',
6472 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6473 'live_status': 'not_live',
6474 'view_count': int,
6475 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6476 'availability': 'public',
6477 'duration': 59,
6478 'comment_count': int,
6479 'channel_follower_count': int
6480 },
6481 'params': {
6482 'noplaylist': True,
6483 'skip_download': True,
6484 },
6485 }, {
6486 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6487 'only_matching': True,
6488 }]
6489
6490 def _real_extract(self, url):
6491 mobj = self._match_valid_url(url)
6492 video_id = mobj.group('id')
6493 playlist_id = mobj.group('playlist_id')
6494 return self.url_result(
6495 update_url_query('https://www.youtube.com/watch', {
6496 'v': video_id,
6497 'list': playlist_id,
6498 'feature': 'youtu.be',
6499 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
6500
6501
6502 class YoutubeLivestreamEmbedIE(InfoExtractor):
6503 IE_DESC = 'YouTube livestream embeds'
6504 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6505 _TESTS = [{
6506 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6507 'only_matching': True,
6508 }]
6509
6510 def _real_extract(self, url):
6511 channel_id = self._match_id(url)
6512 return self.url_result(
6513 f'https://www.youtube.com/channel/{channel_id}/live',
6514 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6515
6516
6517 class YoutubeYtUserIE(InfoExtractor):
6518 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6519 IE_NAME = 'youtube:user'
6520 _VALID_URL = r'ytuser:(?P<id>.+)'
6521 _TESTS = [{
6522 'url': 'ytuser:phihag',
6523 'only_matching': True,
6524 }]
6525
6526 def _real_extract(self, url):
6527 user_id = self._match_id(url)
6528 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
6529
6530
6531 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6532 IE_NAME = 'youtube:favorites'
6533 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6534 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6535 _LOGIN_REQUIRED = True
6536 _TESTS = [{
6537 'url': ':ytfav',
6538 'only_matching': True,
6539 }, {
6540 'url': ':ytfavorites',
6541 'only_matching': True,
6542 }]
6543
6544 def _real_extract(self, url):
6545 return self.url_result(
6546 'https://www.youtube.com/playlist?list=LL',
6547 ie=YoutubeTabIE.ie_key())
6548
6549
6550 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6551 IE_NAME = 'youtube:notif'
6552 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6553 _VALID_URL = r':ytnotif(?:ication)?s?'
6554 _LOGIN_REQUIRED = True
6555 _TESTS = [{
6556 'url': ':ytnotif',
6557 'only_matching': True,
6558 }, {
6559 'url': ':ytnotifications',
6560 'only_matching': True,
6561 }]
6562
6563 def _extract_notification_menu(self, response, continuation_list):
6564 notification_list = traverse_obj(
6565 response,
6566 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6567 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6568 expected_type=list) or []
6569 continuation_list[0] = None
6570 for item in notification_list:
6571 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6572 if entry:
6573 yield entry
6574 continuation = item.get('continuationItemRenderer')
6575 if continuation:
6576 continuation_list[0] = continuation
6577
6578 def _extract_notification_renderer(self, notification):
6579 video_id = traverse_obj(
6580 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6581 url = f'https://www.youtube.com/watch?v={video_id}'
6582 channel_id = None
6583 if not video_id:
6584 browse_ep = traverse_obj(
6585 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6586 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6587 post_id = self._search_regex(
6588 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6589 'post id', default=None)
6590 if not channel_id or not post_id:
6591 return
6592 # The direct /post url redirects to this in the browser
6593 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6594
6595 channel = traverse_obj(
6596 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6597 expected_type=str)
6598 notification_title = self._get_text(notification, 'shortMessage')
6599 if notification_title:
6600 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6601 # TODO: handle recommended videos
6602 title = self._search_regex(
6603 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6604 'video title', default=None)
6605 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6606 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6607 else None)
6608 return {
6609 '_type': 'url',
6610 'url': url,
6611 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6612 'video_id': video_id,
6613 'title': title,
6614 'channel_id': channel_id,
6615 'channel': channel,
6616 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6617 'timestamp': timestamp,
6618 }
6619
6620 def _notification_menu_entries(self, ytcfg):
6621 continuation_list = [None]
6622 response = None
6623 for page in itertools.count(1):
6624 ctoken = traverse_obj(
6625 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6626 response = self._extract_response(
6627 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6628 ep='notification/get_notification_menu', check_get_keys='actions',
6629 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6630 yield from self._extract_notification_menu(response, continuation_list)
6631 if not continuation_list[0]:
6632 break
6633
6634 def _real_extract(self, url):
6635 display_id = 'notifications'
6636 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6637 self._report_playlist_authcheck(ytcfg)
6638 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6639
6640
6641 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6642 IE_DESC = 'YouTube search'
6643 IE_NAME = 'youtube:search'
6644 _SEARCH_KEY = 'ytsearch'
6645 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6646 _TESTS = [{
6647 'url': 'ytsearch5:youtube-dl test video',
6648 'playlist_count': 5,
6649 'info_dict': {
6650 'id': 'youtube-dl test video',
6651 'title': 'youtube-dl test video',
6652 }
6653 }]
6654
6655
6656 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6657 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6658 _SEARCH_KEY = 'ytsearchdate'
6659 IE_DESC = 'YouTube search, newest videos first'
6660 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6661 _TESTS = [{
6662 'url': 'ytsearchdate5:youtube-dl test video',
6663 'playlist_count': 5,
6664 'info_dict': {
6665 'id': 'youtube-dl test video',
6666 'title': 'youtube-dl test video',
6667 }
6668 }]
6669
6670
6671 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6672 IE_DESC = 'YouTube search URLs with sorting and filter support'
6673 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6674 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6675 _TESTS = [{
6676 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6677 'playlist_mincount': 5,
6678 'info_dict': {
6679 'id': 'youtube-dl test video',
6680 'title': 'youtube-dl test video',
6681 }
6682 }, {
6683 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6684 'playlist_mincount': 5,
6685 'info_dict': {
6686 'id': 'python',
6687 'title': 'python',
6688 }
6689 }, {
6690 'url': 'https://www.youtube.com/results?search_query=%23cats',
6691 'playlist_mincount': 1,
6692 'info_dict': {
6693 'id': '#cats',
6694 'title': '#cats',
6695 # The test suite does not have support for nested playlists
6696 # 'entries': [{
6697 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6698 # 'title': '#cats',
6699 # }],
6700 },
6701 }, {
6702 # Channel results
6703 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6704 'info_dict': {
6705 'id': 'kurzgesagt',
6706 'title': 'kurzgesagt',
6707 },
6708 'playlist': [{
6709 'info_dict': {
6710 '_type': 'url',
6711 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6712 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6713 'ie_key': 'YoutubeTab',
6714 'channel': 'Kurzgesagt – In a Nutshell',
6715 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6716 'title': 'Kurzgesagt – In a Nutshell',
6717 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6718 'playlist_count': int, # XXX: should have a way of saying > 1
6719 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6720 'thumbnails': list
6721 }
6722 }],
6723 'params': {'extract_flat': True, 'playlist_items': '1'},
6724 'playlist_mincount': 1,
6725 }, {
6726 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6727 'only_matching': True,
6728 }]
6729
6730 def _real_extract(self, url):
6731 qs = parse_qs(url)
6732 query = (qs.get('search_query') or qs.get('q'))[0]
6733 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6734
6735
6736 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6737 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6738 IE_NAME = 'youtube:music:search_url'
6739 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6740 _TESTS = [{
6741 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6742 'playlist_count': 16,
6743 'info_dict': {
6744 'id': 'royalty free music',
6745 'title': 'royalty free music',
6746 }
6747 }, {
6748 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6749 'playlist_mincount': 30,
6750 'info_dict': {
6751 'id': 'royalty free music - songs',
6752 'title': 'royalty free music - songs',
6753 },
6754 'params': {'extract_flat': 'in_playlist'}
6755 }, {
6756 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6757 'playlist_mincount': 30,
6758 'info_dict': {
6759 'id': 'royalty free music - community playlists',
6760 'title': 'royalty free music - community playlists',
6761 },
6762 'params': {'extract_flat': 'in_playlist'}
6763 }]
6764
6765 _SECTIONS = {
6766 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6767 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6768 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6769 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6770 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6771 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6772 }
6773
6774 def _real_extract(self, url):
6775 qs = parse_qs(url)
6776 query = (qs.get('search_query') or qs.get('q'))[0]
6777 params = qs.get('sp', (None,))[0]
6778 if params:
6779 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6780 else:
6781 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6782 params = self._SECTIONS.get(section)
6783 if not params:
6784 section = None
6785 title = join_nonempty(query, section, delim=' - ')
6786 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6787
6788
6789 class YoutubeFeedsInfoExtractor(InfoExtractor):
6790 """
6791 Base class for feed extractors
6792 Subclasses must re-define the _FEED_NAME property.
6793 """
6794 _LOGIN_REQUIRED = True
6795 _FEED_NAME = 'feeds'
6796
6797 def _real_initialize(self):
6798 YoutubeBaseInfoExtractor._check_login_required(self)
6799
6800 @classproperty
6801 def IE_NAME(self):
6802 return f'youtube:{self._FEED_NAME}'
6803
6804 def _real_extract(self, url):
6805 return self.url_result(
6806 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6807
6808
6809 class YoutubeWatchLaterIE(InfoExtractor):
6810 IE_NAME = 'youtube:watchlater'
6811 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6812 _VALID_URL = r':ytwatchlater'
6813 _TESTS = [{
6814 'url': ':ytwatchlater',
6815 'only_matching': True,
6816 }]
6817
6818 def _real_extract(self, url):
6819 return self.url_result(
6820 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6821
6822
6823 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6824 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6825 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6826 _FEED_NAME = 'recommended'
6827 _LOGIN_REQUIRED = False
6828 _TESTS = [{
6829 'url': ':ytrec',
6830 'only_matching': True,
6831 }, {
6832 'url': ':ytrecommended',
6833 'only_matching': True,
6834 }, {
6835 'url': 'https://youtube.com',
6836 'only_matching': True,
6837 }]
6838
6839
6840 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6841 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6842 _VALID_URL = r':ytsub(?:scription)?s?'
6843 _FEED_NAME = 'subscriptions'
6844 _TESTS = [{
6845 'url': ':ytsubs',
6846 'only_matching': True,
6847 }, {
6848 'url': ':ytsubscriptions',
6849 'only_matching': True,
6850 }]
6851
6852
6853 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6854 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6855 _VALID_URL = r':ythis(?:tory)?'
6856 _FEED_NAME = 'history'
6857 _TESTS = [{
6858 'url': ':ythistory',
6859 'only_matching': True,
6860 }]
6861
6862
6863 class YoutubeStoriesIE(InfoExtractor):
6864 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6865 IE_NAME = 'youtube:stories'
6866 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6867 _TESTS = [{
6868 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6869 'only_matching': True,
6870 }]
6871
6872 def _real_extract(self, url):
6873 playlist_id = f'RLTD{self._match_id(url)}'
6874 return self.url_result(
6875 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6876 ie=YoutubeTabIE, video_id=playlist_id)
6877
6878
6879 class YoutubeShortsAudioPivotIE(InfoExtractor):
6880 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6881 IE_NAME = 'youtube:shorts:pivot:audio'
6882 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6883 _TESTS = [{
6884 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6885 'only_matching': True,
6886 }]
6887
6888 @staticmethod
6889 def _generate_audio_pivot_params(video_id):
6890 """
6891 Generates sfv_audio_pivot browse params for this video id
6892 """
6893 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6894 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6895
6896 def _real_extract(self, url):
6897 video_id = self._match_id(url)
6898 return self.url_result(
6899 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6900 ie=YoutubeTabIE)
6901
6902
6903 class YoutubeTruncatedURLIE(InfoExtractor):
6904 IE_NAME = 'youtube:truncated_url'
6905 IE_DESC = False # Do not list
6906 _VALID_URL = r'''(?x)
6907 (?:https?://)?
6908 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6909 (?:watch\?(?:
6910 feature=[a-z_]+|
6911 annotation_id=annotation_[^&]+|
6912 x-yt-cl=[0-9]+|
6913 hl=[^&]*|
6914 t=[0-9]+
6915 )?
6916 |
6917 attribution_link\?a=[^&]+
6918 )
6919 $
6920 '''
6921
6922 _TESTS = [{
6923 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6924 'only_matching': True,
6925 }, {
6926 'url': 'https://www.youtube.com/watch?',
6927 'only_matching': True,
6928 }, {
6929 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6930 'only_matching': True,
6931 }, {
6932 'url': 'https://www.youtube.com/watch?feature=foo',
6933 'only_matching': True,
6934 }, {
6935 'url': 'https://www.youtube.com/watch?hl=en-GB',
6936 'only_matching': True,
6937 }, {
6938 'url': 'https://www.youtube.com/watch?t=2372',
6939 'only_matching': True,
6940 }]
6941
6942 def _real_extract(self, url):
6943 raise ExtractorError(
6944 'Did you forget to quote the URL? Remember that & is a meta '
6945 'character in most shells, so you want to put the URL in quotes, '
6946 'like youtube-dl '
6947 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6948 ' or simply youtube-dl BaW_jenozKc .',
6949 expected=True)
6950
6951
6952 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6953 IE_NAME = 'youtube:clip'
6954 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6955 _TESTS = [{
6956 # FIXME: Other metadata should be extracted from the clip, not from the base video
6957 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6958 'info_dict': {
6959 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6960 'ext': 'mp4',
6961 'section_start': 29.0,
6962 'section_end': 39.7,
6963 'duration': 10.7,
6964 'age_limit': 0,
6965 'availability': 'public',
6966 'categories': ['Gaming'],
6967 'channel': 'Scott The Woz',
6968 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6969 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6970 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6971 'like_count': int,
6972 'playable_in_embed': True,
6973 'tags': 'count:17',
6974 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6975 'title': 'Mobile Games on Console - Scott The Woz',
6976 'upload_date': '20210920',
6977 'uploader': 'Scott The Woz',
6978 'uploader_id': 'scottthewoz',
6979 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6980 'view_count': int,
6981 'live_status': 'not_live',
6982 'channel_follower_count': int
6983 }
6984 }]
6985
6986 def _real_extract(self, url):
6987 clip_id = self._match_id(url)
6988 _, data = self._extract_webpage(url, clip_id)
6989
6990 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6991 if not video_id:
6992 raise ExtractorError('Unable to find video ID')
6993
6994 clip_data = traverse_obj(data, (
6995 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6996 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6997 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6998 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6999
7000 return {
7001 '_type': 'url_transparent',
7002 'url': f'https://www.youtube.com/watch?v={video_id}',
7003 'ie_key': YoutubeIE.ie_key(),
7004 'id': clip_id,
7005 'section_start': int(clip_data['startTimeMs']) / 1000,
7006 'section_end': int(clip_data['endTimeMs']) / 1000,
7007 }
7008
7009
7010 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7011 IE_NAME = 'youtube:consent'
7012 IE_DESC = False # Do not list
7013 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7014 _TESTS = [{
7015 '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',
7016 'info_dict': {
7017 'id': 'qVv6vCqciTM',
7018 'ext': 'mp4',
7019 'age_limit': 0,
7020 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7021 'comment_count': int,
7022 'chapters': 'count:13',
7023 'upload_date': '20221223',
7024 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7025 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7026 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7027 'like_count': int,
7028 'release_date': '20221223',
7029 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7030 '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】',
7031 'view_count': int,
7032 'playable_in_embed': True,
7033 'duration': 4438,
7034 'availability': 'public',
7035 'channel_follower_count': int,
7036 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7037 'categories': ['Entertainment'],
7038 'live_status': 'was_live',
7039 'release_timestamp': 1671793345,
7040 'channel': 'さなちゃんねる',
7041 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7042 'uploader': 'さなちゃんねる',
7043 },
7044 'add_ie': ['Youtube'],
7045 'params': {'skip_download': 'Youtube'},
7046 }]
7047
7048 def _real_extract(self, url):
7049 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7050 if not redirect_url:
7051 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7052 return self.url_result(redirect_url)
7053
7054
7055 class YoutubeTruncatedIDIE(InfoExtractor):
7056 IE_NAME = 'youtube:truncated_id'
7057 IE_DESC = False # Do not list
7058 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7059
7060 _TESTS = [{
7061 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7062 'only_matching': True,
7063 }]
7064
7065 def _real_extract(self, url):
7066 video_id = self._match_id(url)
7067 raise ExtractorError(
7068 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
7069 expected=True)