]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[extractor/youtube] Fix live_status
[yt-dlp.git] / yt_dlp / extractor / youtube.py
1 import base64
2 import calendar
3 import copy
4 import datetime
5 import enum
6 import hashlib
7 import itertools
8 import json
9 import math
10 import os.path
11 import random
12 import re
13 import sys
14 import threading
15 import time
16 import traceback
17 import urllib.error
18 import urllib.parse
19
20 from .common import InfoExtractor, SearchInfoExtractor
21 from .openload import PhantomJSwrapper
22 from ..compat import functools
23 from ..jsinterp import JSInterpreter
24 from ..utils import (
25 NO_DEFAULT,
26 ExtractorError,
27 LazyList,
28 UserNotLive,
29 bug_reports_message,
30 classproperty,
31 clean_html,
32 datetime_from_str,
33 dict_get,
34 filter_dict,
35 float_or_none,
36 format_field,
37 get_first,
38 int_or_none,
39 is_html,
40 join_nonempty,
41 js_to_json,
42 mimetype2ext,
43 network_exceptions,
44 orderedSet,
45 parse_codecs,
46 parse_count,
47 parse_duration,
48 parse_iso8601,
49 parse_qs,
50 qualities,
51 remove_start,
52 smuggle_url,
53 str_or_none,
54 str_to_int,
55 strftime_or_none,
56 traverse_obj,
57 try_get,
58 unescapeHTML,
59 unified_strdate,
60 unified_timestamp,
61 unsmuggle_url,
62 update_url_query,
63 url_or_none,
64 urljoin,
65 variadic,
66 )
67
68 # any clients starting with _ cannot be explicitly requested by the user
69 INNERTUBE_CLIENTS = {
70 'web': {
71 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
72 'INNERTUBE_CONTEXT': {
73 'client': {
74 'clientName': 'WEB',
75 'clientVersion': '2.20220801.00.00',
76 }
77 },
78 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
79 },
80 'web_embedded': {
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
83 'client': {
84 'clientName': 'WEB_EMBEDDED_PLAYER',
85 'clientVersion': '1.20220731.00.00',
86 },
87 },
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
89 },
90 'web_music': {
91 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
92 'INNERTUBE_HOST': 'music.youtube.com',
93 'INNERTUBE_CONTEXT': {
94 'client': {
95 'clientName': 'WEB_REMIX',
96 'clientVersion': '1.20220727.01.00',
97 }
98 },
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
100 },
101 'web_creator': {
102 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
103 'INNERTUBE_CONTEXT': {
104 'client': {
105 'clientName': 'WEB_CREATOR',
106 'clientVersion': '1.20220726.00.00',
107 }
108 },
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
110 },
111 'android': {
112 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
113 'INNERTUBE_CONTEXT': {
114 'client': {
115 'clientName': 'ANDROID',
116 'clientVersion': '17.31.35',
117 'androidSdkVersion': 30,
118 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
119 }
120 },
121 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
122 'REQUIRE_JS_PLAYER': False
123 },
124 'android_embedded': {
125 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
126 'INNERTUBE_CONTEXT': {
127 'client': {
128 'clientName': 'ANDROID_EMBEDDED_PLAYER',
129 'clientVersion': '17.31.35',
130 'androidSdkVersion': 30,
131 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
132 },
133 },
134 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
135 'REQUIRE_JS_PLAYER': False
136 },
137 'android_music': {
138 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
139 'INNERTUBE_CONTEXT': {
140 'client': {
141 'clientName': 'ANDROID_MUSIC',
142 'clientVersion': '5.16.51',
143 'androidSdkVersion': 30,
144 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
145 }
146 },
147 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
148 'REQUIRE_JS_PLAYER': False
149 },
150 'android_creator': {
151 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
152 'INNERTUBE_CONTEXT': {
153 'client': {
154 'clientName': 'ANDROID_CREATOR',
155 'clientVersion': '22.30.100',
156 'androidSdkVersion': 30,
157 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
158 },
159 },
160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
162 },
163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
165 'ios': {
166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS',
170 'clientVersion': '17.33.2',
171 'deviceModel': 'iPhone14,3',
172 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
173 }
174 },
175 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
176 'REQUIRE_JS_PLAYER': False
177 },
178 'ios_embedded': {
179 'INNERTUBE_CONTEXT': {
180 'client': {
181 'clientName': 'IOS_MESSAGES_EXTENSION',
182 'clientVersion': '17.33.2',
183 'deviceModel': 'iPhone14,3',
184 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
185 },
186 },
187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
189 },
190 'ios_music': {
191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_MUSIC',
195 'clientVersion': '5.21',
196 'deviceModel': 'iPhone14,3',
197 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
198 },
199 },
200 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
201 'REQUIRE_JS_PLAYER': False
202 },
203 'ios_creator': {
204 'INNERTUBE_CONTEXT': {
205 'client': {
206 'clientName': 'IOS_CREATOR',
207 'clientVersion': '22.33.101',
208 'deviceModel': 'iPhone14,3',
209 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
210 },
211 },
212 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
213 'REQUIRE_JS_PLAYER': False
214 },
215 # mweb has 'ultralow' formats
216 # See: https://github.com/yt-dlp/yt-dlp/pull/557
217 'mweb': {
218 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
219 'INNERTUBE_CONTEXT': {
220 'client': {
221 'clientName': 'MWEB',
222 'clientVersion': '2.20220801.00.00',
223 }
224 },
225 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
226 },
227 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
228 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
229 'tv_embedded': {
230 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
231 'INNERTUBE_CONTEXT': {
232 'client': {
233 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
234 'clientVersion': '2.0',
235 },
236 },
237 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
238 },
239 }
240
241
242 def _split_innertube_client(client_name):
243 variant, *base = client_name.rsplit('.', 1)
244 if base:
245 return variant, base[0], variant
246 base, *variant = client_name.split('_', 1)
247 return client_name, base, variant[0] if variant else None
248
249
250 def build_innertube_clients():
251 THIRD_PARTY = {
252 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
253 }
254 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
255 priority = qualities(BASE_CLIENTS[::-1])
256
257 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
258 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
259 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
260 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
261 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
262
263 _, base_client, variant = _split_innertube_client(client)
264 ytcfg['priority'] = 10 * priority(base_client)
265
266 if not variant:
267 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
268 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
269 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
270 embedscreen['priority'] -= 3
271 elif variant == 'embedded':
272 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
273 ytcfg['priority'] -= 2
274 else:
275 ytcfg['priority'] -= 3
276
277
278 build_innertube_clients()
279
280
281 class BadgeType(enum.Enum):
282 AVAILABILITY_UNLISTED = enum.auto()
283 AVAILABILITY_PRIVATE = enum.auto()
284 AVAILABILITY_PUBLIC = enum.auto()
285 AVAILABILITY_PREMIUM = enum.auto()
286 AVAILABILITY_SUBSCRIPTION = enum.auto()
287 LIVE_NOW = enum.auto()
288
289
290 class YoutubeBaseInfoExtractor(InfoExtractor):
291 """Provide base functions for Youtube extractors"""
292
293 _RESERVED_NAMES = (
294 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
295 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
296 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
297 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
298
299 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
300
301 # _NETRC_MACHINE = 'youtube'
302
303 # If True it will raise an error if no login info is provided
304 _LOGIN_REQUIRED = False
305
306 _INVIDIOUS_SITES = (
307 # invidious-redirect websites
308 r'(?:www\.)?redirect\.invidious\.io',
309 r'(?:(?:www|dev)\.)?invidio\.us',
310 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
311 r'(?:www\.)?invidious\.pussthecat\.org',
312 r'(?:www\.)?invidious\.zee\.li',
313 r'(?:www\.)?invidious\.ethibox\.fr',
314 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
315 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
316 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
317 # youtube-dl invidious instances list
318 r'(?:(?:www|no)\.)?invidiou\.sh',
319 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
320 r'(?:www\.)?invidious\.kabi\.tk',
321 r'(?:www\.)?invidious\.mastodon\.host',
322 r'(?:www\.)?invidious\.zapashcanon\.fr',
323 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
324 r'(?:www\.)?invidious\.tinfoil-hat\.net',
325 r'(?:www\.)?invidious\.himiko\.cloud',
326 r'(?:www\.)?invidious\.reallyancient\.tech',
327 r'(?:www\.)?invidious\.tube',
328 r'(?:www\.)?invidiou\.site',
329 r'(?:www\.)?invidious\.site',
330 r'(?:www\.)?invidious\.xyz',
331 r'(?:www\.)?invidious\.nixnet\.xyz',
332 r'(?:www\.)?invidious\.048596\.xyz',
333 r'(?:www\.)?invidious\.drycat\.fr',
334 r'(?:www\.)?inv\.skyn3t\.in',
335 r'(?:www\.)?tube\.poal\.co',
336 r'(?:www\.)?tube\.connect\.cafe',
337 r'(?:www\.)?vid\.wxzm\.sx',
338 r'(?:www\.)?vid\.mint\.lgbt',
339 r'(?:www\.)?vid\.puffyan\.us',
340 r'(?:www\.)?yewtu\.be',
341 r'(?:www\.)?yt\.elukerio\.org',
342 r'(?:www\.)?yt\.lelux\.fi',
343 r'(?:www\.)?invidious\.ggc-project\.de',
344 r'(?:www\.)?yt\.maisputain\.ovh',
345 r'(?:www\.)?ytprivate\.com',
346 r'(?:www\.)?invidious\.13ad\.de',
347 r'(?:www\.)?invidious\.toot\.koeln',
348 r'(?:www\.)?invidious\.fdn\.fr',
349 r'(?:www\.)?watch\.nettohikari\.com',
350 r'(?:www\.)?invidious\.namazso\.eu',
351 r'(?:www\.)?invidious\.silkky\.cloud',
352 r'(?:www\.)?invidious\.exonip\.de',
353 r'(?:www\.)?invidious\.riverside\.rocks',
354 r'(?:www\.)?invidious\.blamefran\.net',
355 r'(?:www\.)?invidious\.moomoo\.de',
356 r'(?:www\.)?ytb\.trom\.tf',
357 r'(?:www\.)?yt\.cyberhost\.uk',
358 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
359 r'(?:www\.)?qklhadlycap4cnod\.onion',
360 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
361 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
362 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
363 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
364 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
365 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
366 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
367 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
368 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
369 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
370 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
371 r'(?:www\.)?piped\.kavin\.rocks',
372 r'(?:www\.)?piped\.silkky\.cloud',
373 r'(?:www\.)?piped\.tokhmi\.xyz',
374 r'(?:www\.)?piped\.moomoo\.me',
375 r'(?:www\.)?il\.ax',
376 r'(?:www\.)?piped\.syncpundit\.com',
377 r'(?:www\.)?piped\.mha\.fi',
378 r'(?:www\.)?piped\.mint\.lgbt',
379 r'(?:www\.)?piped\.privacy\.com\.de',
380 )
381
382 # extracted from account/account_menu ep
383 # XXX: These are the supported YouTube UI and API languages,
384 # which is slightly different from languages supported for translation in YouTube studio
385 _SUPPORTED_LANG_CODES = [
386 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
387 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
388 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
389 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
390 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
391 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
392 ]
393
394 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
395
396 @functools.cached_property
397 def _preferred_lang(self):
398 """
399 Returns a language code supported by YouTube for the user preferred language.
400 Returns None if no preferred language set.
401 """
402 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
403 if not preferred_lang:
404 return
405 if preferred_lang not in self._SUPPORTED_LANG_CODES:
406 raise ExtractorError(
407 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
408 expected=True)
409 elif preferred_lang != 'en':
410 self.report_warning(
411 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
412 return preferred_lang
413
414 def _initialize_consent(self):
415 cookies = self._get_cookies('https://www.youtube.com/')
416 if cookies.get('__Secure-3PSID'):
417 return
418 consent_id = None
419 consent = cookies.get('CONSENT')
420 if consent:
421 if 'YES' in consent.value:
422 return
423 consent_id = self._search_regex(
424 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
425 if not consent_id:
426 consent_id = random.randint(100, 999)
427 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
428
429 def _initialize_pref(self):
430 cookies = self._get_cookies('https://www.youtube.com/')
431 pref_cookie = cookies.get('PREF')
432 pref = {}
433 if pref_cookie:
434 try:
435 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
436 except ValueError:
437 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
438 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
439 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
440
441 def _real_initialize(self):
442 self._initialize_pref()
443 self._initialize_consent()
444 self._check_login_required()
445
446 def _check_login_required(self):
447 if self._LOGIN_REQUIRED and not self._cookies_passed:
448 self.raise_login_required('Login details are needed to download this content', method='cookies')
449
450 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
451 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
452
453 def _get_default_ytcfg(self, client='web'):
454 return copy.deepcopy(INNERTUBE_CLIENTS[client])
455
456 def _get_innertube_host(self, client='web'):
457 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
458
459 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
460 # try_get but with fallback to default ytcfg client values when present
461 _func = lambda y: try_get(y, getter, expected_type)
462 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
463
464 def _extract_client_name(self, ytcfg, default_client='web'):
465 return self._ytcfg_get_safe(
466 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
467 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
468
469 def _extract_client_version(self, ytcfg, default_client='web'):
470 return self._ytcfg_get_safe(
471 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
472 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
473
474 def _select_api_hostname(self, req_api_hostname, default_client=None):
475 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
476 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
477
478 def _extract_api_key(self, ytcfg=None, default_client='web'):
479 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
480
481 def _extract_context(self, ytcfg=None, default_client='web'):
482 context = get_first(
483 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
484 # Enforce language and tz for extraction
485 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
486 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
487 return context
488
489 _SAPISID = None
490
491 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
492 time_now = round(time.time())
493 if self._SAPISID is None:
494 yt_cookies = self._get_cookies('https://www.youtube.com')
495 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
496 # See: https://github.com/yt-dlp/yt-dlp/issues/393
497 sapisid_cookie = dict_get(
498 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
499 if sapisid_cookie and sapisid_cookie.value:
500 self._SAPISID = sapisid_cookie.value
501 self.write_debug('Extracted SAPISID cookie')
502 # SAPISID cookie is required if not already present
503 if not yt_cookies.get('SAPISID'):
504 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
505 self._set_cookie(
506 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
507 else:
508 self._SAPISID = False
509 if not self._SAPISID:
510 return None
511 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
512 sapisidhash = hashlib.sha1(
513 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
514 return f'SAPISIDHASH {time_now}_{sapisidhash}'
515
516 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
517 note='Downloading API JSON', errnote='Unable to download API page',
518 context=None, api_key=None, api_hostname=None, default_client='web'):
519
520 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
521 data.update(query)
522 real_headers = self.generate_api_headers(default_client=default_client)
523 real_headers.update({'content-type': 'application/json'})
524 if headers:
525 real_headers.update(headers)
526 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
527 or api_key or self._extract_api_key(default_client=default_client))
528 return self._download_json(
529 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
530 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
531 data=json.dumps(data).encode('utf8'), headers=real_headers,
532 query={'key': api_key, 'prettyPrint': 'false'})
533
534 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
535 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
536
537 @staticmethod
538 def _extract_session_index(*data):
539 """
540 Index of current account in account list.
541 See: https://github.com/yt-dlp/yt-dlp/pull/519
542 """
543 for ytcfg in data:
544 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
545 if session_index is not None:
546 return session_index
547
548 # Deprecated?
549 def _extract_identity_token(self, ytcfg=None, webpage=None):
550 if ytcfg:
551 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
552 if token:
553 return token
554 if webpage:
555 return self._search_regex(
556 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
557 'identity token', default=None, fatal=False)
558
559 @staticmethod
560 def _extract_account_syncid(*args):
561 """
562 Extract syncId required to download private playlists of secondary channels
563 @params response and/or ytcfg
564 """
565 for data in args:
566 # ytcfg includes channel_syncid if on secondary channel
567 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
568 if delegated_sid:
569 return delegated_sid
570 sync_ids = (try_get(
571 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
572 lambda x: x['DATASYNC_ID']), str) or '').split('||')
573 if len(sync_ids) >= 2 and sync_ids[1]:
574 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
575 # and just "user_syncid||" for primary channel. We only want the channel_syncid
576 return sync_ids[0]
577
578 @staticmethod
579 def _extract_visitor_data(*args):
580 """
581 Extracts visitorData from an API response or ytcfg
582 Appears to be used to track session state
583 """
584 return get_first(
585 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
586 expected_type=str)
587
588 @functools.cached_property
589 def is_authenticated(self):
590 return bool(self._generate_sapisidhash_header())
591
592 def extract_ytcfg(self, video_id, webpage):
593 if not webpage:
594 return {}
595 return self._parse_json(
596 self._search_regex(
597 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
598 default='{}'), video_id, fatal=False) or {}
599
600 def generate_api_headers(
601 self, *, ytcfg=None, account_syncid=None, session_index=None,
602 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
603
604 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
605 headers = {
606 'X-YouTube-Client-Name': str(
607 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
608 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
609 'Origin': origin,
610 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
611 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
612 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
613 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
614 }
615 if session_index is None:
616 session_index = self._extract_session_index(ytcfg)
617 if account_syncid or session_index is not None:
618 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
619
620 auth = self._generate_sapisidhash_header(origin)
621 if auth is not None:
622 headers['Authorization'] = auth
623 headers['X-Origin'] = origin
624 return filter_dict(headers)
625
626 def _download_ytcfg(self, client, video_id):
627 url = {
628 'web': 'https://www.youtube.com',
629 'web_music': 'https://music.youtube.com',
630 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
631 }.get(client)
632 if not url:
633 return {}
634 webpage = self._download_webpage(
635 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
636 return self.extract_ytcfg(video_id, webpage) or {}
637
638 @staticmethod
639 def _build_api_continuation_query(continuation, ctp=None):
640 query = {
641 'continuation': continuation
642 }
643 # TODO: Inconsistency with clickTrackingParams.
644 # Currently we have a fixed ctp contained within context (from ytcfg)
645 # and a ctp in root query for continuation.
646 if ctp:
647 query['clickTracking'] = {'clickTrackingParams': ctp}
648 return query
649
650 @classmethod
651 def _extract_next_continuation_data(cls, renderer):
652 next_continuation = try_get(
653 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
654 lambda x: x['continuation']['reloadContinuationData']), dict)
655 if not next_continuation:
656 return
657 continuation = next_continuation.get('continuation')
658 if not continuation:
659 return
660 ctp = next_continuation.get('clickTrackingParams')
661 return cls._build_api_continuation_query(continuation, ctp)
662
663 @classmethod
664 def _extract_continuation_ep_data(cls, continuation_ep: dict):
665 if isinstance(continuation_ep, dict):
666 continuation = try_get(
667 continuation_ep, lambda x: x['continuationCommand']['token'], str)
668 if not continuation:
669 return
670 ctp = continuation_ep.get('clickTrackingParams')
671 return cls._build_api_continuation_query(continuation, ctp)
672
673 @classmethod
674 def _extract_continuation(cls, renderer):
675 next_continuation = cls._extract_next_continuation_data(renderer)
676 if next_continuation:
677 return next_continuation
678
679 return traverse_obj(renderer, (
680 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
681 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
682 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
683
684 @classmethod
685 def _extract_alerts(cls, data):
686 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
687 if not isinstance(alert_dict, dict):
688 continue
689 for alert in alert_dict.values():
690 alert_type = alert.get('type')
691 if not alert_type:
692 continue
693 message = cls._get_text(alert, 'text')
694 if message:
695 yield alert_type, message
696
697 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
698 errors, warnings = [], []
699 for alert_type, alert_message in alerts:
700 if alert_type.lower() == 'error' and fatal:
701 errors.append([alert_type, alert_message])
702 elif alert_message not in self._IGNORED_WARNINGS:
703 warnings.append([alert_type, alert_message])
704
705 for alert_type, alert_message in (warnings + errors[:-1]):
706 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
707 if errors:
708 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
709
710 def _extract_and_report_alerts(self, data, *args, **kwargs):
711 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
712
713 def _extract_badges(self, renderer: dict):
714 privacy_icon_map = {
715 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
716 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
717 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
718 }
719
720 badge_style_map = {
721 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
722 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
723 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
724 }
725
726 label_map = {
727 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
728 'private': BadgeType.AVAILABILITY_PRIVATE,
729 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
730 'live': BadgeType.LIVE_NOW,
731 'premium': BadgeType.AVAILABILITY_PREMIUM
732 }
733
734 badges = []
735 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer'), default=[]):
736 badge_type = (
737 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
738 or badge_style_map.get(traverse_obj(badge, 'style'))
739 )
740 if badge_type:
741 badges.append({'type': badge_type})
742 continue
743
744 # fallback, won't work in some languages
745 label = traverse_obj(badge, 'label', expected_type=str, default='')
746 for match, label_badge_type in label_map.items():
747 if match in label.lower():
748 badges.append({'type': badge_type})
749 continue
750
751 return badges
752
753 @staticmethod
754 def _has_badge(badges, badge_type):
755 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
756
757 @staticmethod
758 def _get_text(data, *path_list, max_runs=None):
759 for path in path_list or [None]:
760 if path is None:
761 obj = [data]
762 else:
763 obj = traverse_obj(data, path, default=[])
764 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
765 obj = [obj]
766 for item in obj:
767 text = try_get(item, lambda x: x['simpleText'], str)
768 if text:
769 return text
770 runs = try_get(item, lambda x: x['runs'], list) or []
771 if not runs and isinstance(item, list):
772 runs = item
773
774 runs = runs[:min(len(runs), max_runs or len(runs))]
775 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
776 if text:
777 return text
778
779 def _get_count(self, data, *path_list):
780 count_text = self._get_text(data, *path_list) or ''
781 count = parse_count(count_text)
782 if count is None:
783 count = str_to_int(
784 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
785 return count
786
787 @staticmethod
788 def _extract_thumbnails(data, *path_list):
789 """
790 Extract thumbnails from thumbnails dict
791 @param path_list: path list to level that contains 'thumbnails' key
792 """
793 thumbnails = []
794 for path in path_list or [()]:
795 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
796 thumbnail_url = url_or_none(thumbnail.get('url'))
797 if not thumbnail_url:
798 continue
799 # Sometimes youtube gives a wrong thumbnail URL. See:
800 # https://github.com/yt-dlp/yt-dlp/issues/233
801 # https://github.com/ytdl-org/youtube-dl/issues/28023
802 if 'maxresdefault' in thumbnail_url:
803 thumbnail_url = thumbnail_url.split('?')[0]
804 thumbnails.append({
805 'url': thumbnail_url,
806 'height': int_or_none(thumbnail.get('height')),
807 'width': int_or_none(thumbnail.get('width')),
808 })
809 return thumbnails
810
811 @staticmethod
812 def extract_relative_time(relative_time_text):
813 """
814 Extracts a relative time from string and converts to dt object
815 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
816 """
817 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)
818 if mobj:
819 start = mobj.group('start')
820 if start:
821 return datetime_from_str(start)
822 try:
823 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
824 except ValueError:
825 return None
826
827 def _parse_time_text(self, text):
828 if not text:
829 return
830 dt = self.extract_relative_time(text)
831 timestamp = None
832 if isinstance(dt, datetime.datetime):
833 timestamp = calendar.timegm(dt.timetuple())
834
835 if timestamp is None:
836 timestamp = (
837 unified_timestamp(text) or unified_timestamp(
838 self._search_regex(
839 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
840 text.lower(), 'time text', default=None)))
841
842 if text and timestamp is None and self._preferred_lang in (None, 'en'):
843 self.report_warning(
844 f'Cannot parse localized time text "{text}"', only_once=True)
845 return timestamp
846
847 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
848 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
849 default_client='web'):
850 for retry in self.RetryManager():
851 try:
852 response = self._call_api(
853 ep=ep, fatal=True, headers=headers,
854 video_id=item_id, query=query, note=note,
855 context=self._extract_context(ytcfg, default_client),
856 api_key=self._extract_api_key(ytcfg, default_client),
857 api_hostname=api_hostname, default_client=default_client)
858 except ExtractorError as e:
859 if not isinstance(e.cause, network_exceptions):
860 return self._error_or_warning(e, fatal=fatal)
861 elif not isinstance(e.cause, urllib.error.HTTPError):
862 retry.error = e
863 continue
864
865 first_bytes = e.cause.read(512)
866 if not is_html(first_bytes):
867 yt_error = try_get(
868 self._parse_json(
869 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
870 lambda x: x['error']['message'], str)
871 if yt_error:
872 self._report_alerts([('ERROR', yt_error)], fatal=False)
873 # Downloading page may result in intermittent 5xx HTTP error
874 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
875 # We also want to catch all other network exceptions since errors in later pages can be troublesome
876 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
877 if e.cause.code not in (403, 429):
878 retry.error = e
879 continue
880 return self._error_or_warning(e, fatal=fatal)
881
882 try:
883 self._extract_and_report_alerts(response, only_once=True)
884 except ExtractorError as e:
885 # YouTube servers may return errors we want to retry on in a 200 OK response
886 # See: https://github.com/yt-dlp/yt-dlp/issues/839
887 if 'unknown error' in e.msg.lower():
888 retry.error = e
889 continue
890 return self._error_or_warning(e, fatal=fatal)
891 # Youtube sometimes sends incomplete data
892 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
893 if not traverse_obj(response, *variadic(check_get_keys)):
894 retry.error = ExtractorError('Incomplete data received', expected=True)
895 continue
896
897 return response
898
899 @staticmethod
900 def is_music_url(url):
901 return re.match(r'https?://music\.youtube\.com/', url) is not None
902
903 def _extract_video(self, renderer):
904 video_id = renderer.get('videoId')
905 title = self._get_text(renderer, 'title')
906 description = self._get_text(renderer, 'descriptionSnippet')
907 duration = parse_duration(self._get_text(
908 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
909 if duration is None:
910 duration = parse_duration(self._search_regex(
911 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
912 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
913 video_id, default=None, group='duration'))
914
915 view_count = self._get_count(renderer, 'viewCountText', 'shortViewCountText')
916 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
917 channel_id = traverse_obj(
918 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
919 expected_type=str, get_all=False)
920 time_text = self._get_text(renderer, 'publishedTimeText') or ''
921 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
922 overlay_style = traverse_obj(
923 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
924 get_all=False, expected_type=str)
925 badges = self._extract_badges(renderer)
926 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
927 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
928 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
929 expected_type=str)) or ''
930 url = f'https://www.youtube.com/watch?v={video_id}'
931 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
932 url = f'https://www.youtube.com/shorts/{video_id}'
933
934 live_status = (
935 'is_upcoming' if scheduled_timestamp is not None
936 else 'was_live' if 'streamed' in time_text.lower()
937 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
938 else None)
939
940 return {
941 '_type': 'url',
942 'ie_key': YoutubeIE.ie_key(),
943 'id': video_id,
944 'url': url,
945 'title': title,
946 'description': description,
947 'duration': duration,
948 'uploader': uploader,
949 'channel_id': channel_id,
950 'thumbnails': thumbnails,
951 'timestamp': (self._parse_time_text(time_text)
952 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
953 else None),
954 'release_timestamp': scheduled_timestamp,
955 'availability':
956 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
957 else self._availability(
958 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
959 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
960 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
961 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
962 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count': view_count,
963 }
964
965
966 class YoutubeIE(YoutubeBaseInfoExtractor):
967 IE_DESC = 'YouTube'
968 _VALID_URL = r"""(?x)^
969 (
970 (?:https?://|//) # http(s):// or protocol-independent URL
971 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
972 (?:www\.)?deturl\.com/www\.youtube\.com|
973 (?:www\.)?pwnyoutube\.com|
974 (?:www\.)?hooktube\.com|
975 (?:www\.)?yourepeat\.com|
976 tube\.majestyc\.net|
977 %(invidious)s|
978 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
979 (?:.*?\#/)? # handle anchor (#/) redirect urls
980 (?: # the various things that can precede the ID:
981 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
982 |(?: # or the v= param in all its forms
983 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
984 (?:\?|\#!?) # the params delimiter ? or # or #!
985 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
986 v=
987 )
988 ))
989 |(?:
990 youtu\.be| # just youtu.be/xxxx
991 vid\.plus| # or vid.plus/xxxx
992 zwearz\.com/watch| # or zwearz.com/watch/xxxx
993 %(invidious)s
994 )/
995 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
996 )
997 )? # all until now is optional -> you can pass the naked ID
998 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
999 (?(1).+)? # if we found the ID, everything can follow
1000 (?:\#|$)""" % {
1001 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
1002 }
1003 _EMBED_REGEX = [
1004 r'''(?x)
1005 (?:
1006 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
1007 data-video-url=|
1008 <embed[^>]+?src=|
1009 embedSWF\(?:\s*|
1010 <object[^>]+data=|
1011 new\s+SWFObject\(
1012 )
1013 (["\'])
1014 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1015 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1016 \1''',
1017 # https://wordpress.org/plugins/lazy-load-for-videos/
1018 r'''(?xs)
1019 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1020 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1021 ]
1022
1023 _PLAYER_INFO_RE = (
1024 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1025 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$',
1026 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
1027 )
1028 _formats = {
1029 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1030 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1031 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1032 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1033 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1034 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1035 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1036 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1037 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
1038 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1039 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1040 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1041 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1042 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1043 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1044 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1045 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1046 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1047
1048
1049 # 3D videos
1050 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1051 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1052 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1053 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1054 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1055 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1056 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1057
1058 # Apple HTTP Live Streaming
1059 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1060 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1061 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1062 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1063 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1064 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1065 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1066 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
1067
1068 # DASH mp4 video
1069 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1070 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1071 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1072 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1073 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
1074 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
1075 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1076 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1077 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1078 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1079 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1080 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1081
1082 # Dash mp4 audio
1083 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1084 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1085 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1086 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1087 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1088 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1089 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1090
1091 # Dash webm
1092 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1093 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1094 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1095 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1096 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1097 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1098 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1099 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1100 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1101 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1102 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1103 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1104 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1105 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1106 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1107 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1108 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1109 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1110 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1111 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1112 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1113 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1114
1115 # Dash webm audio
1116 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1117 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1118
1119 # Dash webm audio with opus inside
1120 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1121 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1122 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1123
1124 # RTMP (unnamed)
1125 '_rtmp': {'protocol': 'rtmp'},
1126
1127 # av01 video only formats sometimes served with "unknown" codecs
1128 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1129 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1130 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1131 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1132 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1133 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1134 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1135 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1136 }
1137 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1138
1139 _GEO_BYPASS = False
1140
1141 IE_NAME = 'youtube'
1142 _TESTS = [
1143 {
1144 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1145 'info_dict': {
1146 'id': 'BaW_jenozKc',
1147 'ext': 'mp4',
1148 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1149 'uploader': 'Philipp Hagemeister',
1150 'uploader_id': 'phihag',
1151 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1152 'channel': 'Philipp Hagemeister',
1153 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1154 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1155 'upload_date': '20121002',
1156 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1157 'categories': ['Science & Technology'],
1158 'tags': ['youtube-dl'],
1159 'duration': 10,
1160 'view_count': int,
1161 'like_count': int,
1162 'availability': 'public',
1163 'playable_in_embed': True,
1164 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1165 'live_status': 'not_live',
1166 'age_limit': 0,
1167 'start_time': 1,
1168 'end_time': 9,
1169 'comment_count': int,
1170 'channel_follower_count': int
1171 }
1172 },
1173 {
1174 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1175 'note': 'Embed-only video (#1746)',
1176 'info_dict': {
1177 'id': 'yZIXLfi8CZQ',
1178 'ext': 'mp4',
1179 'upload_date': '20120608',
1180 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1181 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1182 'uploader': 'SET India',
1183 'uploader_id': 'setindia',
1184 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1185 'age_limit': 18,
1186 },
1187 'skip': 'Private video',
1188 },
1189 {
1190 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1191 'note': 'Use the first video ID in the URL',
1192 'info_dict': {
1193 'id': 'BaW_jenozKc',
1194 'ext': 'mp4',
1195 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1196 'uploader': 'Philipp Hagemeister',
1197 'uploader_id': 'phihag',
1198 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1199 'channel': 'Philipp Hagemeister',
1200 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1201 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1202 'upload_date': '20121002',
1203 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1204 'categories': ['Science & Technology'],
1205 'tags': ['youtube-dl'],
1206 'duration': 10,
1207 'view_count': int,
1208 'like_count': int,
1209 'availability': 'public',
1210 'playable_in_embed': True,
1211 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1212 'live_status': 'not_live',
1213 'age_limit': 0,
1214 'comment_count': int,
1215 'channel_follower_count': int
1216 },
1217 'params': {
1218 'skip_download': True,
1219 },
1220 },
1221 {
1222 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1223 'note': '256k DASH audio (format 141) via DASH manifest',
1224 'info_dict': {
1225 'id': 'a9LDPn-MO4I',
1226 'ext': 'm4a',
1227 'upload_date': '20121002',
1228 'uploader_id': '8KVIDEO',
1229 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1230 'description': '',
1231 'uploader': '8KVIDEO',
1232 'title': 'UHDTV TEST 8K VIDEO.mp4'
1233 },
1234 'params': {
1235 'youtube_include_dash_manifest': True,
1236 'format': '141',
1237 },
1238 'skip': 'format 141 not served anymore',
1239 },
1240 # DASH manifest with encrypted signature
1241 {
1242 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1243 'info_dict': {
1244 'id': 'IB3lcPjvWLA',
1245 'ext': 'm4a',
1246 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1247 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1248 'duration': 244,
1249 'uploader': 'AfrojackVEVO',
1250 'uploader_id': 'AfrojackVEVO',
1251 'upload_date': '20131011',
1252 'abr': 129.495,
1253 'like_count': int,
1254 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1255 'playable_in_embed': True,
1256 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1257 'view_count': int,
1258 'track': 'The Spark',
1259 'live_status': 'not_live',
1260 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1261 'channel': 'Afrojack',
1262 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1263 'tags': 'count:19',
1264 'availability': 'public',
1265 'categories': ['Music'],
1266 'age_limit': 0,
1267 'alt_title': 'The Spark',
1268 'channel_follower_count': int
1269 },
1270 'params': {
1271 'youtube_include_dash_manifest': True,
1272 'format': '141/bestaudio[ext=m4a]',
1273 },
1274 },
1275 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1276 {
1277 'note': 'Embed allowed age-gate video',
1278 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1279 'info_dict': {
1280 'id': 'HtVdAasjOgU',
1281 'ext': 'mp4',
1282 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1283 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1284 'duration': 142,
1285 'uploader': 'The Witcher',
1286 'uploader_id': 'WitcherGame',
1287 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1288 'upload_date': '20140605',
1289 'age_limit': 18,
1290 'categories': ['Gaming'],
1291 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1292 'availability': 'needs_auth',
1293 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1294 'like_count': int,
1295 'channel': 'The Witcher',
1296 'live_status': 'not_live',
1297 'tags': 'count:17',
1298 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1299 'playable_in_embed': True,
1300 'view_count': int,
1301 'channel_follower_count': int
1302 },
1303 },
1304 {
1305 'note': 'Age-gate video with embed allowed in public site',
1306 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1307 'info_dict': {
1308 'id': 'HsUATh_Nc2U',
1309 'ext': 'mp4',
1310 'title': 'Godzilla 2 (Official Video)',
1311 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1312 'upload_date': '20200408',
1313 'uploader_id': 'FlyingKitty900',
1314 'uploader': 'FlyingKitty',
1315 'age_limit': 18,
1316 'availability': 'needs_auth',
1317 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1318 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1319 'channel': 'FlyingKitty',
1320 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1321 'view_count': int,
1322 'categories': ['Entertainment'],
1323 'live_status': 'not_live',
1324 'tags': ['Flyingkitty', 'godzilla 2'],
1325 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1326 'like_count': int,
1327 'duration': 177,
1328 'playable_in_embed': True,
1329 'channel_follower_count': int
1330 },
1331 },
1332 {
1333 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1334 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1335 'info_dict': {
1336 'id': 'Tq92D6wQ1mg',
1337 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1338 'ext': 'mp4',
1339 'upload_date': '20191228',
1340 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1341 'uploader': 'Projekt Melody',
1342 'description': 'md5:17eccca93a786d51bc67646756894066',
1343 'age_limit': 18,
1344 'like_count': int,
1345 'availability': 'needs_auth',
1346 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1347 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1348 'view_count': int,
1349 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1350 'channel': 'Projekt Melody',
1351 'live_status': 'not_live',
1352 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1353 'playable_in_embed': True,
1354 'categories': ['Entertainment'],
1355 'duration': 106,
1356 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1357 'comment_count': int,
1358 'channel_follower_count': int
1359 },
1360 },
1361 {
1362 'note': 'Non-Agegated non-embeddable video',
1363 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1364 'info_dict': {
1365 'id': 'MeJVWBSsPAY',
1366 'ext': 'mp4',
1367 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1368 'uploader': 'Herr Lurik',
1369 'uploader_id': 'st3in234',
1370 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1371 'upload_date': '20130730',
1372 'track': 'Such mich find mich',
1373 'age_limit': 0,
1374 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1375 'like_count': int,
1376 'playable_in_embed': False,
1377 'creator': 'OOMPH!',
1378 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1379 'view_count': int,
1380 'alt_title': 'Such mich find mich',
1381 'duration': 210,
1382 'channel': 'Herr Lurik',
1383 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1384 'categories': ['Music'],
1385 'availability': 'public',
1386 'uploader_url': 'http://www.youtube.com/user/st3in234',
1387 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1388 'live_status': 'not_live',
1389 'artist': 'OOMPH!',
1390 'channel_follower_count': int
1391 },
1392 },
1393 {
1394 'note': 'Non-bypassable age-gated video',
1395 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1396 'only_matching': True,
1397 },
1398 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1399 # YouTube Red ad is not captured for creator
1400 {
1401 'url': '__2ABJjxzNo',
1402 'info_dict': {
1403 'id': '__2ABJjxzNo',
1404 'ext': 'mp4',
1405 'duration': 266,
1406 'upload_date': '20100430',
1407 'uploader_id': 'deadmau5',
1408 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1409 'creator': 'deadmau5',
1410 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1411 'uploader': 'deadmau5',
1412 'title': 'Deadmau5 - Some Chords (HD)',
1413 'alt_title': 'Some Chords',
1414 'availability': 'public',
1415 'tags': 'count:14',
1416 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1417 'view_count': int,
1418 'live_status': 'not_live',
1419 'channel': 'deadmau5',
1420 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1421 'like_count': int,
1422 'track': 'Some Chords',
1423 'artist': 'deadmau5',
1424 'playable_in_embed': True,
1425 'age_limit': 0,
1426 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1427 'categories': ['Music'],
1428 'album': 'Some Chords',
1429 'channel_follower_count': int
1430 },
1431 'expected_warnings': [
1432 'DASH manifest missing',
1433 ]
1434 },
1435 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1436 {
1437 'url': 'lqQg6PlCWgI',
1438 'info_dict': {
1439 'id': 'lqQg6PlCWgI',
1440 'ext': 'mp4',
1441 'duration': 6085,
1442 'upload_date': '20150827',
1443 'uploader_id': 'olympic',
1444 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1445 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1446 'uploader': 'Olympics',
1447 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1448 'like_count': int,
1449 'release_timestamp': 1343767800,
1450 'playable_in_embed': True,
1451 'categories': ['Sports'],
1452 'release_date': '20120731',
1453 'channel': 'Olympics',
1454 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1455 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1456 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1457 'age_limit': 0,
1458 'availability': 'public',
1459 'live_status': 'was_live',
1460 'view_count': int,
1461 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1462 'channel_follower_count': int
1463 },
1464 'params': {
1465 'skip_download': 'requires avconv',
1466 }
1467 },
1468 # Non-square pixels
1469 {
1470 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1471 'info_dict': {
1472 'id': '_b-2C3KPAM0',
1473 'ext': 'mp4',
1474 'stretched_ratio': 16 / 9.,
1475 'duration': 85,
1476 'upload_date': '20110310',
1477 'uploader_id': 'AllenMeow',
1478 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1479 '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',
1480 'uploader': '孫ᄋᄅ',
1481 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1482 'playable_in_embed': True,
1483 'channel': '孫ᄋᄅ',
1484 'age_limit': 0,
1485 'tags': 'count:11',
1486 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1487 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1488 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1489 'view_count': int,
1490 'categories': ['People & Blogs'],
1491 'like_count': int,
1492 'live_status': 'not_live',
1493 'availability': 'unlisted',
1494 'comment_count': int,
1495 'channel_follower_count': int
1496 },
1497 },
1498 # url_encoded_fmt_stream_map is empty string
1499 {
1500 'url': 'qEJwOuvDf7I',
1501 'info_dict': {
1502 'id': 'qEJwOuvDf7I',
1503 'ext': 'webm',
1504 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1505 'description': '',
1506 'upload_date': '20150404',
1507 'uploader_id': 'spbelect',
1508 'uploader': 'Наблюдатели Петербурга',
1509 },
1510 'params': {
1511 'skip_download': 'requires avconv',
1512 },
1513 'skip': 'This live event has ended.',
1514 },
1515 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1516 {
1517 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1518 'info_dict': {
1519 'id': 'FIl7x6_3R5Y',
1520 'ext': 'webm',
1521 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1522 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1523 'duration': 220,
1524 'upload_date': '20150625',
1525 'uploader_id': 'dorappi2000',
1526 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1527 'uploader': 'dorappi2000',
1528 'formats': 'mincount:31',
1529 },
1530 'skip': 'not actual anymore',
1531 },
1532 # DASH manifest with segment_list
1533 {
1534 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1535 'md5': '8ce563a1d667b599d21064e982ab9e31',
1536 'info_dict': {
1537 'id': 'CsmdDsKjzN8',
1538 'ext': 'mp4',
1539 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1540 'uploader': 'Airtek',
1541 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1542 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1543 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1544 },
1545 'params': {
1546 'youtube_include_dash_manifest': True,
1547 'format': '135', # bestvideo
1548 },
1549 'skip': 'This live event has ended.',
1550 },
1551 {
1552 # Multifeed videos (multiple cameras), URL is for Main Camera
1553 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1554 'info_dict': {
1555 'id': 'jvGDaLqkpTg',
1556 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1557 'description': 'md5:e03b909557865076822aa169218d6a5d',
1558 },
1559 'playlist': [{
1560 'info_dict': {
1561 'id': 'jvGDaLqkpTg',
1562 'ext': 'mp4',
1563 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1564 'description': 'md5:e03b909557865076822aa169218d6a5d',
1565 'duration': 10643,
1566 'upload_date': '20161111',
1567 'uploader': 'Team PGP',
1568 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1569 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1570 },
1571 }, {
1572 'info_dict': {
1573 'id': '3AKt1R1aDnw',
1574 'ext': 'mp4',
1575 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1576 'description': 'md5:e03b909557865076822aa169218d6a5d',
1577 'duration': 10991,
1578 'upload_date': '20161111',
1579 'uploader': 'Team PGP',
1580 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1581 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1582 },
1583 }, {
1584 'info_dict': {
1585 'id': 'RtAMM00gpVc',
1586 'ext': 'mp4',
1587 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1588 'description': 'md5:e03b909557865076822aa169218d6a5d',
1589 'duration': 10995,
1590 'upload_date': '20161111',
1591 'uploader': 'Team PGP',
1592 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1593 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1594 },
1595 }, {
1596 'info_dict': {
1597 'id': '6N2fdlP3C5U',
1598 'ext': 'mp4',
1599 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1600 'description': 'md5:e03b909557865076822aa169218d6a5d',
1601 'duration': 10990,
1602 'upload_date': '20161111',
1603 'uploader': 'Team PGP',
1604 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1605 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1606 },
1607 }],
1608 'params': {
1609 'skip_download': True,
1610 },
1611 'skip': 'Not multifeed anymore',
1612 },
1613 {
1614 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1615 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1616 'info_dict': {
1617 'id': 'gVfLd0zydlo',
1618 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1619 },
1620 'playlist_count': 2,
1621 'skip': 'Not multifeed anymore',
1622 },
1623 {
1624 'url': 'https://vid.plus/FlRa-iH7PGw',
1625 'only_matching': True,
1626 },
1627 {
1628 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1629 'only_matching': True,
1630 },
1631 {
1632 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1633 # Also tests cut-off URL expansion in video description (see
1634 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1635 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1636 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1637 'info_dict': {
1638 'id': 'lsguqyKfVQg',
1639 'ext': 'mp4',
1640 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1641 'alt_title': 'Dark Walk',
1642 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1643 'duration': 133,
1644 'upload_date': '20151119',
1645 'uploader_id': 'IronSoulElf',
1646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1647 'uploader': 'IronSoulElf',
1648 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1649 'track': 'Dark Walk',
1650 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1651 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1652 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1653 'categories': ['Film & Animation'],
1654 'view_count': int,
1655 'live_status': 'not_live',
1656 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1657 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1658 'tags': 'count:13',
1659 'availability': 'public',
1660 'channel': 'IronSoulElf',
1661 'playable_in_embed': True,
1662 'like_count': int,
1663 'age_limit': 0,
1664 'channel_follower_count': int
1665 },
1666 'params': {
1667 'skip_download': True,
1668 },
1669 },
1670 {
1671 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1672 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1673 'only_matching': True,
1674 },
1675 {
1676 # Video with yt:stretch=17:0
1677 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1678 'info_dict': {
1679 'id': 'Q39EVAstoRM',
1680 'ext': 'mp4',
1681 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1682 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1683 'upload_date': '20151107',
1684 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1685 'uploader': 'CH GAMER DROID',
1686 },
1687 'params': {
1688 'skip_download': True,
1689 },
1690 'skip': 'This video does not exist.',
1691 },
1692 {
1693 # Video with incomplete 'yt:stretch=16:'
1694 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1695 'only_matching': True,
1696 },
1697 {
1698 # Video licensed under Creative Commons
1699 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1700 'info_dict': {
1701 'id': 'M4gD1WSo5mA',
1702 'ext': 'mp4',
1703 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1704 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1705 'duration': 721,
1706 'upload_date': '20150128',
1707 'uploader_id': 'BerkmanCenter',
1708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1709 'uploader': 'The Berkman Klein Center for Internet & Society',
1710 'license': 'Creative Commons Attribution license (reuse allowed)',
1711 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1712 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1713 'like_count': int,
1714 'age_limit': 0,
1715 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1716 'channel': 'The Berkman Klein Center for Internet & Society',
1717 'availability': 'public',
1718 'view_count': int,
1719 'categories': ['Education'],
1720 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1721 'live_status': 'not_live',
1722 'playable_in_embed': True,
1723 'comment_count': int,
1724 'channel_follower_count': int
1725 },
1726 'params': {
1727 'skip_download': True,
1728 },
1729 },
1730 {
1731 # Channel-like uploader_url
1732 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1733 'info_dict': {
1734 'id': 'eQcmzGIKrzg',
1735 'ext': 'mp4',
1736 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1737 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1738 'duration': 4060,
1739 'upload_date': '20151120',
1740 'uploader': 'Bernie Sanders',
1741 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1742 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1743 'license': 'Creative Commons Attribution license (reuse allowed)',
1744 'playable_in_embed': True,
1745 'tags': 'count:12',
1746 'like_count': int,
1747 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1748 'age_limit': 0,
1749 'availability': 'public',
1750 'categories': ['News & Politics'],
1751 'channel': 'Bernie Sanders',
1752 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1753 'view_count': int,
1754 'live_status': 'not_live',
1755 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1756 'comment_count': int,
1757 'channel_follower_count': int
1758 },
1759 'params': {
1760 'skip_download': True,
1761 },
1762 },
1763 {
1764 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1765 'only_matching': True,
1766 },
1767 {
1768 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1769 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1770 'only_matching': True,
1771 },
1772 {
1773 # Rental video preview
1774 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1775 'info_dict': {
1776 'id': 'uGpuVWrhIzE',
1777 'ext': 'mp4',
1778 'title': 'Piku - Trailer',
1779 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1780 'upload_date': '20150811',
1781 'uploader': 'FlixMatrix',
1782 'uploader_id': 'FlixMatrixKaravan',
1783 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1784 'license': 'Standard YouTube License',
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 'skip': 'This video is not available.',
1790 },
1791 {
1792 # YouTube Red video with episode data
1793 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1794 'info_dict': {
1795 'id': 'iqKdEhx-dD4',
1796 'ext': 'mp4',
1797 'title': 'Isolation - Mind Field (Ep 1)',
1798 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1799 'duration': 2085,
1800 'upload_date': '20170118',
1801 'uploader': 'Vsauce',
1802 'uploader_id': 'Vsauce',
1803 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1804 'series': 'Mind Field',
1805 'season_number': 1,
1806 'episode_number': 1,
1807 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1808 'tags': 'count:12',
1809 'view_count': int,
1810 'availability': 'public',
1811 'age_limit': 0,
1812 'channel': 'Vsauce',
1813 'episode': 'Episode 1',
1814 'categories': ['Entertainment'],
1815 'season': 'Season 1',
1816 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1817 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1818 'like_count': int,
1819 'playable_in_embed': True,
1820 'live_status': 'not_live',
1821 'channel_follower_count': int
1822 },
1823 'params': {
1824 'skip_download': True,
1825 },
1826 'expected_warnings': [
1827 'Skipping DASH manifest',
1828 ],
1829 },
1830 {
1831 # The following content has been identified by the YouTube community
1832 # as inappropriate or offensive to some audiences.
1833 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1834 'info_dict': {
1835 'id': '6SJNVb0GnPI',
1836 'ext': 'mp4',
1837 'title': 'Race Differences in Intelligence',
1838 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1839 'duration': 965,
1840 'upload_date': '20140124',
1841 'uploader': 'New Century Foundation',
1842 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1843 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1844 },
1845 'params': {
1846 'skip_download': True,
1847 },
1848 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1849 },
1850 {
1851 # itag 212
1852 'url': '1t24XAntNCY',
1853 'only_matching': True,
1854 },
1855 {
1856 # geo restricted to JP
1857 'url': 'sJL6WA-aGkQ',
1858 'only_matching': True,
1859 },
1860 {
1861 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1862 'only_matching': True,
1863 },
1864 {
1865 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1866 'only_matching': True,
1867 },
1868 {
1869 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1870 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1871 'only_matching': True,
1872 },
1873 {
1874 # DRM protected
1875 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1876 'only_matching': True,
1877 },
1878 {
1879 # Video with unsupported adaptive stream type formats
1880 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1881 'info_dict': {
1882 'id': 'Z4Vy8R84T1U',
1883 'ext': 'mp4',
1884 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1885 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1886 'duration': 433,
1887 'upload_date': '20130923',
1888 'uploader': 'Amelia Putri Harwita',
1889 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1890 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1891 'formats': 'maxcount:10',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 'youtube_include_dash_manifest': False,
1896 },
1897 'skip': 'not actual anymore',
1898 },
1899 {
1900 # Youtube Music Auto-generated description
1901 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1902 'info_dict': {
1903 'id': 'MgNrAu2pzNs',
1904 'ext': 'mp4',
1905 'title': 'Voyeur Girl',
1906 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1907 'upload_date': '20190312',
1908 'uploader': 'Stephen - Topic',
1909 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1910 'artist': 'Stephen',
1911 'track': 'Voyeur Girl',
1912 'album': 'it\'s too much love to know my dear',
1913 'release_date': '20190313',
1914 'release_year': 2019,
1915 'alt_title': 'Voyeur Girl',
1916 'view_count': int,
1917 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1918 'playable_in_embed': True,
1919 'like_count': int,
1920 'categories': ['Music'],
1921 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1922 'channel': 'Stephen',
1923 'availability': 'public',
1924 'creator': 'Stephen',
1925 'duration': 169,
1926 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1927 'age_limit': 0,
1928 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1929 'tags': 'count:11',
1930 'live_status': 'not_live',
1931 'channel_follower_count': int
1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
1936 },
1937 {
1938 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1939 'only_matching': True,
1940 },
1941 {
1942 # invalid -> valid video id redirection
1943 'url': 'DJztXj2GPfl',
1944 'info_dict': {
1945 'id': 'DJztXj2GPfk',
1946 'ext': 'mp4',
1947 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1948 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1949 'upload_date': '20090125',
1950 'uploader': 'Prochorowka',
1951 'uploader_id': 'Prochorowka',
1952 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1953 'artist': 'Panjabi MC',
1954 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1955 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1956 },
1957 'params': {
1958 'skip_download': True,
1959 },
1960 'skip': 'Video unavailable',
1961 },
1962 {
1963 # empty description results in an empty string
1964 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1965 'info_dict': {
1966 'id': 'x41yOUIvK2k',
1967 'ext': 'mp4',
1968 'title': 'IMG 3456',
1969 'description': '',
1970 'upload_date': '20170613',
1971 'uploader_id': 'ElevageOrVert',
1972 'uploader': 'ElevageOrVert',
1973 'view_count': int,
1974 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1975 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1976 'like_count': int,
1977 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1978 'tags': [],
1979 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1980 'availability': 'public',
1981 'age_limit': 0,
1982 'categories': ['Pets & Animals'],
1983 'duration': 7,
1984 'playable_in_embed': True,
1985 'live_status': 'not_live',
1986 'channel': 'ElevageOrVert',
1987 'channel_follower_count': int
1988 },
1989 'params': {
1990 'skip_download': True,
1991 },
1992 },
1993 {
1994 # with '};' inside yt initial data (see [1])
1995 # see [2] for an example with '};' inside ytInitialPlayerResponse
1996 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1997 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1998 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1999 'info_dict': {
2000 'id': 'CHqg6qOn4no',
2001 'ext': 'mp4',
2002 'title': 'Part 77 Sort a list of simple types in c#',
2003 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2004 'upload_date': '20130831',
2005 'uploader_id': 'kudvenkat',
2006 'uploader': 'kudvenkat',
2007 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2008 'like_count': int,
2009 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2010 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2011 'live_status': 'not_live',
2012 'categories': ['Education'],
2013 'availability': 'public',
2014 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2015 'tags': 'count:12',
2016 'playable_in_embed': True,
2017 'age_limit': 0,
2018 'view_count': int,
2019 'duration': 522,
2020 'channel': 'kudvenkat',
2021 'comment_count': int,
2022 'channel_follower_count': int
2023 },
2024 'params': {
2025 'skip_download': True,
2026 },
2027 },
2028 {
2029 # another example of '};' in ytInitialData
2030 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2031 'only_matching': True,
2032 },
2033 {
2034 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2035 'only_matching': True,
2036 },
2037 {
2038 # https://github.com/ytdl-org/youtube-dl/pull/28094
2039 'url': 'OtqTfy26tG0',
2040 'info_dict': {
2041 'id': 'OtqTfy26tG0',
2042 'ext': 'mp4',
2043 'title': 'Burn Out',
2044 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2045 'upload_date': '20141120',
2046 'uploader': 'The Cinematic Orchestra - Topic',
2047 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2048 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2049 'artist': 'The Cinematic Orchestra',
2050 'track': 'Burn Out',
2051 'album': 'Every Day',
2052 'like_count': int,
2053 'live_status': 'not_live',
2054 'alt_title': 'Burn Out',
2055 'duration': 614,
2056 'age_limit': 0,
2057 'view_count': int,
2058 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2059 'creator': 'The Cinematic Orchestra',
2060 'channel': 'The Cinematic Orchestra',
2061 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2062 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2063 'availability': 'public',
2064 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2065 'categories': ['Music'],
2066 'playable_in_embed': True,
2067 'channel_follower_count': int
2068 },
2069 'params': {
2070 'skip_download': True,
2071 },
2072 },
2073 {
2074 # controversial video, only works with bpctr when authenticated with cookies
2075 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2076 'only_matching': True,
2077 },
2078 {
2079 # controversial video, requires bpctr/contentCheckOk
2080 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2081 'info_dict': {
2082 'id': 'SZJvDhaSDnc',
2083 'ext': 'mp4',
2084 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2085 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2086 'uploader': 'CBS Mornings',
2087 'uploader_id': 'CBSThisMorning',
2088 'upload_date': '20140716',
2089 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2090 'duration': 170,
2091 'categories': ['News & Politics'],
2092 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2093 'view_count': int,
2094 'channel': 'CBS Mornings',
2095 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2096 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2097 'age_limit': 18,
2098 'availability': 'needs_auth',
2099 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2100 'like_count': int,
2101 'live_status': 'not_live',
2102 'playable_in_embed': True,
2103 'channel_follower_count': int
2104 }
2105 },
2106 {
2107 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2108 'url': 'cBvYw8_A0vQ',
2109 'info_dict': {
2110 'id': 'cBvYw8_A0vQ',
2111 'ext': 'mp4',
2112 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2113 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2114 'upload_date': '20201120',
2115 'uploader': 'Walk around Japan',
2116 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2117 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2118 'duration': 1456,
2119 'categories': ['Travel & Events'],
2120 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2121 'view_count': int,
2122 'channel': 'Walk around Japan',
2123 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2124 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2125 'age_limit': 0,
2126 'availability': 'public',
2127 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2128 'live_status': 'not_live',
2129 'playable_in_embed': True,
2130 'channel_follower_count': int
2131 },
2132 'params': {
2133 'skip_download': True,
2134 },
2135 }, {
2136 # Has multiple audio streams
2137 'url': 'WaOKSUlf4TM',
2138 'only_matching': True
2139 }, {
2140 # Requires Premium: has format 141 when requested using YTM url
2141 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2142 'only_matching': True
2143 }, {
2144 # multiple subtitles with same lang_code
2145 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2146 'only_matching': True,
2147 }, {
2148 # Force use android client fallback
2149 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2150 'info_dict': {
2151 'id': 'YOelRv7fMxY',
2152 'title': 'DIGGING A SECRET TUNNEL Part 1',
2153 'ext': '3gp',
2154 'upload_date': '20210624',
2155 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2156 'uploader': 'colinfurze',
2157 'uploader_id': 'colinfurze',
2158 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2159 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2160 'duration': 596,
2161 'categories': ['Entertainment'],
2162 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2163 'view_count': int,
2164 'channel': 'colinfurze',
2165 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2166 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2167 'age_limit': 0,
2168 'availability': 'public',
2169 'like_count': int,
2170 'live_status': 'not_live',
2171 'playable_in_embed': True,
2172 'channel_follower_count': int
2173 },
2174 'params': {
2175 'format': '17', # 3gp format available on android
2176 'extractor_args': {'youtube': {'player_client': ['android']}},
2177 },
2178 },
2179 {
2180 # Skip download of additional client configs (remix client config in this case)
2181 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2182 'only_matching': True,
2183 'params': {
2184 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2185 },
2186 }, {
2187 # shorts
2188 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2189 'only_matching': True,
2190 }, {
2191 'note': 'Storyboards',
2192 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2193 'info_dict': {
2194 'id': '5KLPxDtMqe8',
2195 'ext': 'mhtml',
2196 'format_id': 'sb0',
2197 'title': 'Your Brain is Plastic',
2198 'uploader_id': 'scishow',
2199 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2200 'upload_date': '20140324',
2201 'uploader': 'SciShow',
2202 'like_count': int,
2203 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2204 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2205 'view_count': int,
2206 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2207 'playable_in_embed': True,
2208 'tags': 'count:12',
2209 'uploader_url': 'http://www.youtube.com/user/scishow',
2210 'availability': 'public',
2211 'channel': 'SciShow',
2212 'live_status': 'not_live',
2213 'duration': 248,
2214 'categories': ['Education'],
2215 'age_limit': 0,
2216 'channel_follower_count': int
2217 }, 'params': {'format': 'mhtml', 'skip_download': True}
2218 }, {
2219 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2220 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2221 'info_dict': {
2222 'id': '2NUZ8W2llS4',
2223 'ext': 'mp4',
2224 'title': 'The NP that test your phone performance 🙂',
2225 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2226 'uploader': 'Leon Nguyen',
2227 'uploader_id': 'VNSXIII',
2228 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2229 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2230 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2231 'duration': 21,
2232 'view_count': int,
2233 'age_limit': 0,
2234 'categories': ['Gaming'],
2235 'tags': 'count:23',
2236 'playable_in_embed': True,
2237 'live_status': 'not_live',
2238 'upload_date': '20220103',
2239 'like_count': int,
2240 'availability': 'public',
2241 'channel': 'Leon Nguyen',
2242 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2243 'comment_count': int,
2244 'channel_follower_count': int
2245 }
2246 }, {
2247 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2248 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2249 'info_dict': {
2250 'id': '2NUZ8W2llS4',
2251 'ext': 'mp4',
2252 'title': 'The NP that test your phone performance 🙂',
2253 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2254 'uploader': 'Leon Nguyen',
2255 'uploader_id': 'VNSXIII',
2256 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2257 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2258 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2259 'duration': 21,
2260 'view_count': int,
2261 'age_limit': 0,
2262 'categories': ['Gaming'],
2263 'tags': 'count:23',
2264 'playable_in_embed': True,
2265 'live_status': 'not_live',
2266 'upload_date': '20220102',
2267 'like_count': int,
2268 'availability': 'public',
2269 'channel': 'Leon Nguyen',
2270 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2271 'comment_count': int,
2272 'channel_follower_count': int
2273 },
2274 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2275 }, {
2276 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2277 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2278 'info_dict': {
2279 'id': 'mzZzzBU6lrM',
2280 'ext': 'mp4',
2281 'title': 'I Met GeorgeNotFound In Real Life...',
2282 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2283 'uploader': 'Quackity',
2284 'uploader_id': 'QuackityHQ',
2285 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2286 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2287 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2288 'duration': 955,
2289 'view_count': int,
2290 'age_limit': 0,
2291 'categories': ['Entertainment'],
2292 'tags': 'count:26',
2293 'playable_in_embed': True,
2294 'live_status': 'not_live',
2295 'release_timestamp': 1641172509,
2296 'release_date': '20220103',
2297 'upload_date': '20220103',
2298 'like_count': int,
2299 'availability': 'public',
2300 'channel': 'Quackity',
2301 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2302 'channel_follower_count': int
2303 }
2304 },
2305 { # continuous livestream. Microformat upload date should be preferred.
2306 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2307 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2308 'info_dict': {
2309 'id': 'kgx4WGK0oNU',
2310 '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}',
2311 'ext': 'mp4',
2312 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2313 'availability': 'public',
2314 'age_limit': 0,
2315 'release_timestamp': 1637975704,
2316 'upload_date': '20210619',
2317 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2318 'live_status': 'is_live',
2319 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2320 'uploader': '阿鲍Abao',
2321 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2322 'channel': 'Abao in Tokyo',
2323 'channel_follower_count': int,
2324 'release_date': '20211127',
2325 'tags': 'count:39',
2326 'categories': ['People & Blogs'],
2327 'like_count': int,
2328 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2329 'view_count': int,
2330 'playable_in_embed': True,
2331 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2332 'concurrent_view_count': int,
2333 },
2334 'params': {'skip_download': True}
2335 }, {
2336 # Story. Requires specific player params to work.
2337 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2338 'info_dict': {
2339 'id': 'vv8qTUWmulI',
2340 'ext': 'mp4',
2341 'availability': 'unlisted',
2342 'view_count': int,
2343 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2344 'upload_date': '20220526',
2345 'categories': ['Education'],
2346 'title': 'Story',
2347 'channel': 'IT\'S HISTORY',
2348 'description': '',
2349 'uploader_id': 'BlastfromthePast',
2350 'duration': 12,
2351 'uploader': 'IT\'S HISTORY',
2352 'playable_in_embed': True,
2353 'age_limit': 0,
2354 'live_status': 'not_live',
2355 'tags': [],
2356 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2357 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2358 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2359 },
2360 'skip': 'stories get removed after some period of time',
2361 }, {
2362 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2363 'info_dict': {
2364 'id': 'tjjjtzRLHvA',
2365 'ext': 'mp4',
2366 'title': 'ハッシュタグ無し };if window.ytcsi',
2367 'upload_date': '20220323',
2368 'like_count': int,
2369 'availability': 'unlisted',
2370 'channel': 'nao20010128nao',
2371 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2372 'age_limit': 0,
2373 'uploader': 'nao20010128nao',
2374 'uploader_id': 'nao20010128nao',
2375 'categories': ['Music'],
2376 'view_count': int,
2377 'description': '',
2378 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2379 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2380 'live_status': 'not_live',
2381 'playable_in_embed': True,
2382 'channel_follower_count': int,
2383 'duration': 6,
2384 'tags': [],
2385 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2386 }
2387 }, {
2388 # Prefer primary title+description language metadata by default
2389 # Do not prefer translated description if primary is empty
2390 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2391 'info_dict': {
2392 'id': 'el3E4MbxRqQ',
2393 'ext': 'mp4',
2394 'title': 'dlp test video 2 - primary sv no desc',
2395 'description': '',
2396 'channel': 'cole-dlp-test-acc',
2397 'tags': [],
2398 'view_count': int,
2399 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2400 'like_count': int,
2401 'playable_in_embed': True,
2402 'availability': 'unlisted',
2403 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2404 'age_limit': 0,
2405 'duration': 5,
2406 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2407 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2408 'live_status': 'not_live',
2409 'upload_date': '20220908',
2410 'categories': ['People & Blogs'],
2411 'uploader': 'cole-dlp-test-acc',
2412 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2413 },
2414 'params': {'skip_download': True}
2415 }, {
2416 # Extractor argument: prefer translated title+description
2417 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2418 'info_dict': {
2419 'id': 'gHKT4uU8Zng',
2420 'ext': 'mp4',
2421 'channel': 'cole-dlp-test-acc',
2422 'tags': [],
2423 'duration': 5,
2424 'live_status': 'not_live',
2425 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2426 'upload_date': '20220728',
2427 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2428 'view_count': int,
2429 'categories': ['People & Blogs'],
2430 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2431 'title': 'dlp test video title translated (fr)',
2432 'availability': 'public',
2433 'uploader': 'cole-dlp-test-acc',
2434 'age_limit': 0,
2435 'description': 'dlp test video description translated (fr)',
2436 'playable_in_embed': True,
2437 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2438 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2439 },
2440 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2441 'expected_warnings': [r'Preferring "fr" translated fields'],
2442 }, {
2443 'note': '6 channel audio',
2444 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2445 'only_matching': True,
2446 }
2447 ]
2448
2449 _WEBPAGE_TESTS = [
2450 # YouTube <object> embed
2451 {
2452 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2453 'md5': '873c81d308b979f0e23ee7e620b312a3',
2454 'info_dict': {
2455 'id': 'msN87y-iEx0',
2456 'ext': 'mp4',
2457 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2458 'upload_date': '20080526',
2459 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2460 'uploader': 'Christopher Sykes',
2461 'uploader_id': 'ChristopherJSykes',
2462 'age_limit': 0,
2463 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2464 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2465 'playable_in_embed': True,
2466 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2467 'like_count': int,
2468 'comment_count': int,
2469 'channel': 'Christopher Sykes',
2470 'live_status': 'not_live',
2471 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2472 'availability': 'public',
2473 'duration': 195,
2474 'view_count': int,
2475 'categories': ['Science & Technology'],
2476 'channel_follower_count': int,
2477 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2478 },
2479 'params': {
2480 'skip_download': True,
2481 }
2482 },
2483 ]
2484
2485 @classmethod
2486 def suitable(cls, url):
2487 from ..utils import parse_qs
2488
2489 qs = parse_qs(url)
2490 if qs.get('list', [None])[0]:
2491 return False
2492 return super().suitable(url)
2493
2494 def __init__(self, *args, **kwargs):
2495 super().__init__(*args, **kwargs)
2496 self._code_cache = {}
2497 self._player_cache = {}
2498
2499 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
2500 lock = threading.Lock()
2501 start_time = time.time()
2502 formats = [f for f in formats if f.get('is_from_start')]
2503
2504 def refetch_manifest(format_id, delay):
2505 nonlocal formats, start_time, is_live
2506 if time.time() <= start_time + delay:
2507 return
2508
2509 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2510 video_details = traverse_obj(
2511 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2512 microformats = traverse_obj(
2513 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2514 expected_type=dict, default=[])
2515 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2516 is_live = live_status == 'is_live'
2517 start_time = time.time()
2518
2519 def mpd_feed(format_id, delay):
2520 """
2521 @returns (manifest_url, manifest_stream_number, is_live) or None
2522 """
2523 with lock:
2524 refetch_manifest(format_id, delay)
2525
2526 f = next((f for f in formats if f['format_id'] == format_id), None)
2527 if not f:
2528 if not is_live:
2529 self.to_screen(f'{video_id}: Video is no longer live')
2530 else:
2531 self.report_warning(
2532 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2533 return None
2534 return f['manifest_url'], f['manifest_stream_number'], is_live
2535
2536 for f in formats:
2537 f['is_live'] = is_live
2538 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2539 live_start_time, mpd_feed, not is_live and f.copy())
2540 if is_live:
2541 f['fragments'] = gen
2542 f['protocol'] = 'http_dash_segments_generator'
2543 else:
2544 f['fragments'] = LazyList(gen({}))
2545 del f['is_from_start']
2546
2547 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
2548 FETCH_SPAN, MAX_DURATION = 5, 432000
2549
2550 mpd_url, stream_number, is_live = None, None, True
2551
2552 begin_index = 0
2553 download_start_time = ctx.get('start') or time.time()
2554
2555 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2556 if lack_early_segments:
2557 self.report_warning(bug_reports_message(
2558 'Starting download from the last 120 hours of the live stream since '
2559 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2560 lack_early_segments = True
2561
2562 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2563 fragments, fragment_base_url = None, None
2564
2565 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2566 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2567 # Obtain from MPD's maximum seq value
2568 old_mpd_url = mpd_url
2569 last_error = ctx.pop('last_error', None)
2570 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2571 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2572 or (mpd_url, stream_number, False))
2573 if not refresh_sequence:
2574 if expire_fast and not is_live:
2575 return False, last_seq
2576 elif old_mpd_url == mpd_url:
2577 return True, last_seq
2578 if manifestless_orig_fmt:
2579 fmt_info = manifestless_orig_fmt
2580 else:
2581 try:
2582 fmts, _ = self._extract_mpd_formats_and_subtitles(
2583 mpd_url, None, note=False, errnote=False, fatal=False)
2584 except ExtractorError:
2585 fmts = None
2586 if not fmts:
2587 no_fragment_score += 2
2588 return False, last_seq
2589 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2590 fragments = fmt_info['fragments']
2591 fragment_base_url = fmt_info['fragment_base_url']
2592 assert fragment_base_url
2593
2594 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2595 return True, _last_seq
2596
2597 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
2598 while is_live:
2599 fetch_time = time.time()
2600 if no_fragment_score > 30:
2601 return
2602 if last_segment_url:
2603 # Obtain from "X-Head-Seqnum" header value from each segment
2604 try:
2605 urlh = self._request_webpage(
2606 last_segment_url, None, note=False, errnote=False, fatal=False)
2607 except ExtractorError:
2608 urlh = None
2609 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2610 if last_seq is None:
2611 no_fragment_score += 2
2612 last_segment_url = None
2613 continue
2614 else:
2615 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2616 no_fragment_score += 2
2617 if not should_continue:
2618 continue
2619
2620 if known_idx > last_seq:
2621 last_segment_url = None
2622 continue
2623
2624 last_seq += 1
2625
2626 if begin_index < 0 and known_idx < 0:
2627 # skip from the start when it's negative value
2628 known_idx = last_seq + begin_index
2629 if lack_early_segments:
2630 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2631 try:
2632 for idx in range(known_idx, last_seq):
2633 # do not update sequence here or you'll get skipped some part of it
2634 should_continue, _ = _extract_sequence_from_mpd(False, False)
2635 if not should_continue:
2636 known_idx = idx - 1
2637 raise ExtractorError('breaking out of outer loop')
2638 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2639 yield {
2640 'url': last_segment_url,
2641 'fragment_count': last_seq,
2642 }
2643 if known_idx == last_seq:
2644 no_fragment_score += 5
2645 else:
2646 no_fragment_score = 0
2647 known_idx = last_seq
2648 except ExtractorError:
2649 continue
2650
2651 if manifestless_orig_fmt:
2652 # Stop at the first iteration if running for post-live manifestless;
2653 # fragment count no longer increase since it starts
2654 break
2655
2656 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2657
2658 def _extract_player_url(self, *ytcfgs, webpage=None):
2659 player_url = traverse_obj(
2660 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2661 get_all=False, expected_type=str)
2662 if not player_url:
2663 return
2664 return urljoin('https://www.youtube.com', player_url)
2665
2666 def _download_player_url(self, video_id, fatal=False):
2667 res = self._download_webpage(
2668 'https://www.youtube.com/iframe_api',
2669 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2670 if res:
2671 player_version = self._search_regex(
2672 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2673 if player_version:
2674 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2675
2676 def _signature_cache_id(self, example_sig):
2677 """ Return a string representation of a signature """
2678 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2679
2680 @classmethod
2681 def _extract_player_info(cls, player_url):
2682 for player_re in cls._PLAYER_INFO_RE:
2683 id_m = re.search(player_re, player_url)
2684 if id_m:
2685 break
2686 else:
2687 raise ExtractorError('Cannot identify player %r' % player_url)
2688 return id_m.group('id')
2689
2690 def _load_player(self, video_id, player_url, fatal=True):
2691 player_id = self._extract_player_info(player_url)
2692 if player_id not in self._code_cache:
2693 code = self._download_webpage(
2694 player_url, video_id, fatal=fatal,
2695 note='Downloading player ' + player_id,
2696 errnote='Download of %s failed' % player_url)
2697 if code:
2698 self._code_cache[player_id] = code
2699 return self._code_cache.get(player_id)
2700
2701 def _extract_signature_function(self, video_id, player_url, example_sig):
2702 player_id = self._extract_player_info(player_url)
2703
2704 # Read from filesystem cache
2705 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2706 assert os.path.basename(func_id) == func_id
2707
2708 self.write_debug(f'Extracting signature function {func_id}')
2709 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2710
2711 if not cache_spec:
2712 code = self._load_player(video_id, player_url)
2713 if code:
2714 res = self._parse_sig_js(code)
2715 test_string = ''.join(map(chr, range(len(example_sig))))
2716 cache_spec = [ord(c) for c in res(test_string)]
2717 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2718
2719 return lambda s: ''.join(s[i] for i in cache_spec)
2720
2721 def _print_sig_code(self, func, example_sig):
2722 if not self.get_param('youtube_print_sig_code'):
2723 return
2724
2725 def gen_sig_code(idxs):
2726 def _genslice(start, end, step):
2727 starts = '' if start == 0 else str(start)
2728 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2729 steps = '' if step == 1 else (':%d' % step)
2730 return f's[{starts}{ends}{steps}]'
2731
2732 step = None
2733 # Quelch pyflakes warnings - start will be set when step is set
2734 start = '(Never used)'
2735 for i, prev in zip(idxs[1:], idxs[:-1]):
2736 if step is not None:
2737 if i - prev == step:
2738 continue
2739 yield _genslice(start, prev, step)
2740 step = None
2741 continue
2742 if i - prev in [-1, 1]:
2743 step = i - prev
2744 start = prev
2745 continue
2746 else:
2747 yield 's[%d]' % prev
2748 if step is None:
2749 yield 's[%d]' % i
2750 else:
2751 yield _genslice(start, i, step)
2752
2753 test_string = ''.join(map(chr, range(len(example_sig))))
2754 cache_res = func(test_string)
2755 cache_spec = [ord(c) for c in cache_res]
2756 expr_code = ' + '.join(gen_sig_code(cache_spec))
2757 signature_id_tuple = '(%s)' % (
2758 ', '.join(str(len(p)) for p in example_sig.split('.')))
2759 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2760 ' return %s\n') % (signature_id_tuple, expr_code)
2761 self.to_screen('Extracted signature function:\n' + code)
2762
2763 def _parse_sig_js(self, jscode):
2764 funcname = self._search_regex(
2765 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2766 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2767 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2768 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2769 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}\(a,\d+\)',
2770 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\(\s*""\s*\)',
2771 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2772 # Obsolete patterns
2773 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2774 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2775 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2776 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2777 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2778 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2779 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2780 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2781 jscode, 'Initial JS player signature function name', group='sig')
2782
2783 jsi = JSInterpreter(jscode)
2784 initial_function = jsi.extract_function(funcname)
2785 return lambda s: initial_function([s])
2786
2787 def _cached(self, func, *cache_id):
2788 def inner(*args, **kwargs):
2789 if cache_id not in self._player_cache:
2790 try:
2791 self._player_cache[cache_id] = func(*args, **kwargs)
2792 except ExtractorError as e:
2793 self._player_cache[cache_id] = e
2794 except Exception as e:
2795 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2796
2797 ret = self._player_cache[cache_id]
2798 if isinstance(ret, Exception):
2799 raise ret
2800 return ret
2801 return inner
2802
2803 def _decrypt_signature(self, s, video_id, player_url):
2804 """Turn the encrypted s field into a working signature"""
2805 extract_sig = self._cached(
2806 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2807 func = extract_sig(video_id, player_url, s)
2808 self._print_sig_code(func, s)
2809 return func(s)
2810
2811 def _decrypt_nsig(self, s, video_id, player_url):
2812 """Turn the encrypted n field into a working signature"""
2813 if player_url is None:
2814 raise ExtractorError('Cannot decrypt nsig without player_url')
2815 player_url = urljoin('https://www.youtube.com', player_url)
2816
2817 try:
2818 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2819 except ExtractorError as e:
2820 raise ExtractorError('Unable to extract nsig function code', cause=e)
2821 if self.get_param('youtube_print_sig_code'):
2822 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2823
2824 try:
2825 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2826 ret = extract_nsig(jsi, func_code)(s)
2827 except JSInterpreter.Exception as e:
2828 try:
2829 jsi = PhantomJSwrapper(self, timeout=5000)
2830 except ExtractorError:
2831 raise e
2832 self.report_warning(
2833 f'Native nsig extraction failed: Trying with PhantomJS\n'
2834 f' n = {s} ; player = {player_url}', video_id)
2835 self.write_debug(e, only_once=True)
2836
2837 args, func_body = func_code
2838 ret = jsi.execute(
2839 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2840 video_id=video_id, note='Executing signature code').strip()
2841
2842 self.write_debug(f'Decrypted nsig {s} => {ret}')
2843 return ret
2844
2845 def _extract_n_function_name(self, jscode):
2846 funcname, idx = self._search_regex(
2847 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2848 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2849 if not idx:
2850 return funcname
2851
2852 return json.loads(js_to_json(self._search_regex(
2853 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2854 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2855
2856 def _extract_n_function_code(self, video_id, player_url):
2857 player_id = self._extract_player_info(player_url)
2858 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
2859 jscode = func_code or self._load_player(video_id, player_url)
2860 jsi = JSInterpreter(jscode)
2861
2862 if func_code:
2863 return jsi, player_id, func_code
2864
2865 func_name = self._extract_n_function_name(jscode)
2866
2867 # For redundancy
2868 func_code = self._search_regex(
2869 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
2870 # NB: The end of the regex is intentionally kept strict
2871 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
2872 jscode, 'nsig function', group=('var', 'code'), default=None)
2873 if func_code:
2874 func_code = ([func_code[0]], func_code[1])
2875 else:
2876 self.write_debug('Extracting nsig function with jsinterp')
2877 func_code = jsi.extract_function_code(func_name)
2878
2879 self.cache.store('youtube-nsig', player_id, func_code)
2880 return jsi, player_id, func_code
2881
2882 def _extract_n_function_from_code(self, jsi, func_code):
2883 func = jsi.extract_function_from_code(*func_code)
2884
2885 def extract_nsig(s):
2886 try:
2887 ret = func([s])
2888 except JSInterpreter.Exception:
2889 raise
2890 except Exception as e:
2891 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2892
2893 if ret.startswith('enhanced_except_'):
2894 raise JSInterpreter.Exception('Signature function returned an exception')
2895 return ret
2896
2897 return extract_nsig
2898
2899 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2900 """
2901 Extract signatureTimestamp (sts)
2902 Required to tell API what sig/player version is in use.
2903 """
2904 sts = None
2905 if isinstance(ytcfg, dict):
2906 sts = int_or_none(ytcfg.get('STS'))
2907
2908 if not sts:
2909 # Attempt to extract from player
2910 if player_url is None:
2911 error_msg = 'Cannot extract signature timestamp without player_url.'
2912 if fatal:
2913 raise ExtractorError(error_msg)
2914 self.report_warning(error_msg)
2915 return
2916 code = self._load_player(video_id, player_url, fatal=fatal)
2917 if code:
2918 sts = int_or_none(self._search_regex(
2919 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2920 'JS player signature timestamp', group='sts', fatal=fatal))
2921 return sts
2922
2923 def _mark_watched(self, video_id, player_responses):
2924 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2925 label = 'fully ' if is_full else ''
2926 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2927 expected_type=url_or_none)
2928 if not url:
2929 self.report_warning(f'Unable to mark {label}watched')
2930 return
2931 parsed_url = urllib.parse.urlparse(url)
2932 qs = urllib.parse.parse_qs(parsed_url.query)
2933
2934 # cpn generation algorithm is reverse engineered from base.js.
2935 # In fact it works even with dummy cpn.
2936 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2937 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2938
2939 # # more consistent results setting it to right before the end
2940 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2941
2942 qs.update({
2943 'ver': ['2'],
2944 'cpn': [cpn],
2945 'cmt': video_length,
2946 'el': 'detailpage', # otherwise defaults to "shorts"
2947 })
2948
2949 if is_full:
2950 # these seem to mark watchtime "history" in the real world
2951 # they're required, so send in a single value
2952 qs.update({
2953 'st': video_length,
2954 'et': video_length,
2955 })
2956
2957 url = urllib.parse.urlunparse(
2958 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2959
2960 self._download_webpage(
2961 url, video_id, f'Marking {label}watched',
2962 'Unable to mark watched', fatal=False)
2963
2964 @classmethod
2965 def _extract_from_webpage(cls, url, webpage):
2966 # Invidious Instances
2967 # https://github.com/yt-dlp/yt-dlp/issues/195
2968 # https://github.com/iv-org/invidious/pull/1730
2969 mobj = re.search(
2970 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2971 webpage)
2972 if mobj:
2973 yield cls.url_result(mobj.group('url'), cls)
2974 raise cls.StopExtraction()
2975
2976 yield from super()._extract_from_webpage(url, webpage)
2977
2978 # lazyYT YouTube embed
2979 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2980 yield cls.url_result(unescapeHTML(id_), cls, id_)
2981
2982 # Wordpress "YouTube Video Importer" plugin
2983 for m in re.findall(r'''(?x)<div[^>]+
2984 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2985 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2986 yield cls.url_result(m[-1], cls, m[-1])
2987
2988 @classmethod
2989 def extract_id(cls, url):
2990 video_id = cls.get_temp_id(url)
2991 if not video_id:
2992 raise ExtractorError(f'Invalid URL: {url}')
2993 return video_id
2994
2995 def _extract_chapters_from_json(self, data, duration):
2996 chapter_list = traverse_obj(
2997 data, (
2998 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2999 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3000 ), expected_type=list)
3001
3002 return self._extract_chapters(
3003 chapter_list,
3004 chapter_time=lambda chapter: float_or_none(
3005 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3006 chapter_title=lambda chapter: traverse_obj(
3007 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3008 duration=duration)
3009
3010 def _extract_chapters_from_engagement_panel(self, data, duration):
3011 content_list = traverse_obj(
3012 data,
3013 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
3014 expected_type=list, default=[])
3015 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3016 chapter_title = lambda chapter: self._get_text(chapter, 'title')
3017
3018 return next(filter(None, (
3019 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3020 chapter_time, chapter_title, duration)
3021 for contents in content_list)), [])
3022
3023 def _extract_chapters_from_description(self, description, duration):
3024 return self._extract_chapters(
3025 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
3026 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
3027 duration=duration, strict=False)
3028
3029 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3030 if not duration:
3031 return
3032 chapter_list = [{
3033 'start_time': chapter_time(chapter),
3034 'title': chapter_title(chapter),
3035 } for chapter in chapter_list or []]
3036 if not strict:
3037 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3038
3039 chapters = [{'start_time': 0}]
3040 for idx, chapter in enumerate(chapter_list):
3041 if chapter['start_time'] is None:
3042 self.report_warning(f'Incomplete chapter {idx}')
3043 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
3044 chapters.append(chapter)
3045 elif chapter not in chapters:
3046 self.report_warning(
3047 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
3048 return chapters[1:]
3049
3050 def _extract_comment(self, comment_renderer, parent=None):
3051 comment_id = comment_renderer.get('commentId')
3052 if not comment_id:
3053 return
3054
3055 text = self._get_text(comment_renderer, 'contentText')
3056
3057 # Timestamp is an estimate calculated from the current time and time_text
3058 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3059 timestamp = self._parse_time_text(time_text)
3060
3061 author = self._get_text(comment_renderer, 'authorText')
3062 author_id = try_get(comment_renderer,
3063 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3064
3065 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3066 lambda x: x['likeCount']), str)) or 0
3067 author_thumbnail = try_get(comment_renderer,
3068 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3069
3070 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3071 is_favorited = 'creatorHeart' in (try_get(
3072 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3073 return {
3074 'id': comment_id,
3075 'text': text,
3076 'timestamp': timestamp,
3077 'time_text': time_text,
3078 'like_count': votes,
3079 'is_favorited': is_favorited,
3080 'author': author,
3081 'author_id': author_id,
3082 'author_thumbnail': author_thumbnail,
3083 'author_is_uploader': author_is_uploader,
3084 'parent': parent or 'root'
3085 }
3086
3087 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3088
3089 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3090
3091 def extract_header(contents):
3092 _continuation = None
3093 for content in contents:
3094 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3095 expected_comment_count = self._get_count(
3096 comments_header_renderer, 'countText', 'commentsCount')
3097
3098 if expected_comment_count:
3099 tracker['est_total'] = expected_comment_count
3100 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3101 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3102
3103 sort_menu_item = try_get(
3104 comments_header_renderer,
3105 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3106 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3107
3108 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3109 if not _continuation:
3110 continue
3111
3112 sort_text = str_or_none(sort_menu_item.get('title'))
3113 if not sort_text:
3114 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3115 self.to_screen('Sorting comments by %s' % sort_text.lower())
3116 break
3117 return _continuation
3118
3119 def extract_thread(contents):
3120 if not parent:
3121 tracker['current_page_thread'] = 0
3122 for content in contents:
3123 if not parent and tracker['total_parent_comments'] >= max_parents:
3124 yield
3125 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3126 comment_renderer = get_first(
3127 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3128 expected_type=dict, default={})
3129
3130 comment = self._extract_comment(comment_renderer, parent)
3131 if not comment:
3132 continue
3133
3134 tracker['running_total'] += 1
3135 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3136 yield comment
3137
3138 # Attempt to get the replies
3139 comment_replies_renderer = try_get(
3140 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3141
3142 if comment_replies_renderer:
3143 tracker['current_page_thread'] += 1
3144 comment_entries_iter = self._comment_entries(
3145 comment_replies_renderer, ytcfg, video_id,
3146 parent=comment.get('id'), tracker=tracker)
3147 yield from itertools.islice(comment_entries_iter, min(
3148 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3149
3150 # Keeps track of counts across recursive calls
3151 if not tracker:
3152 tracker = dict(
3153 running_total=0,
3154 est_total=0,
3155 current_page_thread=0,
3156 total_parent_comments=0,
3157 total_reply_comments=0)
3158
3159 # TODO: Deprecated
3160 # YouTube comments have a max depth of 2
3161 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3162 if max_depth:
3163 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3164 'Set max replies in the max-comments extractor argument instead')
3165 if max_depth == 1 and parent:
3166 return
3167
3168 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3169 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3170
3171 continuation = self._extract_continuation(root_continuation_data)
3172
3173 response = None
3174 is_forced_continuation = False
3175 is_first_continuation = parent is None
3176 if is_first_continuation and not continuation:
3177 # Sometimes you can get comments by generating the continuation yourself,
3178 # even if YouTube initially reports them being disabled - e.g. stories comments.
3179 # Note: if the comment section is actually disabled, YouTube may return a response with
3180 # required check_get_keys missing. So we will disable that check initially in this case.
3181 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3182 is_forced_continuation = True
3183
3184 for page_num in itertools.count(0):
3185 if not continuation:
3186 break
3187 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3188 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
3189 if page_num == 0:
3190 if is_first_continuation:
3191 note_prefix = 'Downloading comment section API JSON'
3192 else:
3193 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3194 tracker['current_page_thread'], comment_prog_str)
3195 else:
3196 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3197 ' ' if parent else '', ' replies' if parent else '',
3198 page_num, comment_prog_str)
3199
3200 response = self._extract_response(
3201 item_id=None, query=continuation,
3202 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3203 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3204 is_forced_continuation = False
3205 continuation_contents = traverse_obj(
3206 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3207
3208 continuation = None
3209 for continuation_section in continuation_contents:
3210 continuation_items = traverse_obj(
3211 continuation_section,
3212 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3213 get_all=False, expected_type=list) or []
3214 if is_first_continuation:
3215 continuation = extract_header(continuation_items)
3216 is_first_continuation = False
3217 if continuation:
3218 break
3219 continue
3220
3221 for entry in extract_thread(continuation_items):
3222 if not entry:
3223 return
3224 yield entry
3225 continuation = self._extract_continuation({'contents': continuation_items})
3226 if continuation:
3227 break
3228
3229 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3230 if message and not parent and tracker['running_total'] == 0:
3231 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3232
3233 @staticmethod
3234 def _generate_comment_continuation(video_id):
3235 """
3236 Generates initial comment section continuation token from given video id
3237 """
3238 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3239 return base64.b64encode(token.encode()).decode()
3240
3241 def _get_comments(self, ytcfg, video_id, contents, webpage):
3242 """Entry for comment extraction"""
3243 def _real_comment_extract(contents):
3244 renderer = next((
3245 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3246 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3247 yield from self._comment_entries(renderer, ytcfg, video_id)
3248
3249 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3250 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3251
3252 @staticmethod
3253 def _get_checkok_params():
3254 return {'contentCheckOk': True, 'racyCheckOk': True}
3255
3256 @classmethod
3257 def _generate_player_context(cls, sts=None):
3258 context = {
3259 'html5Preference': 'HTML5_PREF_WANTS',
3260 }
3261 if sts is not None:
3262 context['signatureTimestamp'] = sts
3263 return {
3264 'playbackContext': {
3265 'contentPlaybackContext': context
3266 },
3267 **cls._get_checkok_params()
3268 }
3269
3270 @staticmethod
3271 def _is_agegated(player_response):
3272 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3273 return True
3274
3275 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3276 AGE_GATE_REASONS = (
3277 'confirm your age', 'age-restricted', 'inappropriate', # reason
3278 'age_verification_required', 'age_check_required', # status
3279 )
3280 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3281
3282 @staticmethod
3283 def _is_unplayable(player_response):
3284 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3285
3286 _STORY_PLAYER_PARAMS = '8AEB'
3287
3288 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3289
3290 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3291 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3292 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3293 headers = self.generate_api_headers(
3294 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3295
3296 yt_query = {
3297 'videoId': video_id,
3298 }
3299 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3300 yt_query['params'] = self._STORY_PLAYER_PARAMS
3301
3302 yt_query.update(self._generate_player_context(sts))
3303 return self._extract_response(
3304 item_id=video_id, ep='player', query=yt_query,
3305 ytcfg=player_ytcfg, headers=headers, fatal=True,
3306 default_client=client,
3307 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3308 ) or None
3309
3310 def _get_requested_clients(self, url, smuggled_data):
3311 requested_clients = []
3312 default = ['android', 'web']
3313 allowed_clients = sorted(
3314 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3315 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3316 for client in self._configuration_arg('player_client'):
3317 if client in allowed_clients:
3318 requested_clients.append(client)
3319 elif client == 'default':
3320 requested_clients.extend(default)
3321 elif client == 'all':
3322 requested_clients.extend(allowed_clients)
3323 else:
3324 self.report_warning(f'Skipping unsupported client {client}')
3325 if not requested_clients:
3326 requested_clients = default
3327
3328 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3329 requested_clients.extend(
3330 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3331
3332 return orderedSet(requested_clients)
3333
3334 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3335 initial_pr = None
3336 if webpage:
3337 initial_pr = self._search_json(
3338 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3339
3340 all_clients = set(clients)
3341 clients = clients[::-1]
3342 prs = []
3343
3344 def append_client(*client_names):
3345 """ Append the first client name that exists but not already used """
3346 for client_name in client_names:
3347 actual_client = _split_innertube_client(client_name)[0]
3348 if actual_client in INNERTUBE_CLIENTS:
3349 if actual_client not in all_clients:
3350 clients.append(client_name)
3351 all_clients.add(actual_client)
3352 return
3353
3354 # Android player_response does not have microFormats which are needed for
3355 # extraction of some data. So we return the initial_pr with formats
3356 # stripped out even if not requested by the user
3357 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3358 if initial_pr:
3359 pr = dict(initial_pr)
3360 pr['streamingData'] = None
3361 prs.append(pr)
3362
3363 last_error = None
3364 tried_iframe_fallback = False
3365 player_url = None
3366 while clients:
3367 client, base_client, variant = _split_innertube_client(clients.pop())
3368 player_ytcfg = master_ytcfg if client == 'web' else {}
3369 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3370 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3371
3372 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3373 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3374 if 'js' in self._configuration_arg('player_skip'):
3375 require_js_player = False
3376 player_url = None
3377
3378 if not player_url and not tried_iframe_fallback and require_js_player:
3379 player_url = self._download_player_url(video_id)
3380 tried_iframe_fallback = True
3381
3382 try:
3383 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3384 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3385 except ExtractorError as e:
3386 if last_error:
3387 self.report_warning(last_error)
3388 last_error = e
3389 continue
3390
3391 if pr:
3392 # YouTube may return a different video player response than expected.
3393 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3394 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3395 if pr_video_id and pr_video_id != video_id:
3396 self.report_warning(
3397 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
3398 else:
3399 prs.append(pr)
3400
3401 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3402 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3403 append_client(f'{base_client}_creator')
3404 elif self._is_agegated(pr):
3405 if variant == 'tv_embedded':
3406 append_client(f'{base_client}_embedded')
3407 elif not variant:
3408 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3409
3410 if last_error:
3411 if not len(prs):
3412 raise last_error
3413 self.report_warning(last_error)
3414 return prs, player_url
3415
3416 def _needs_live_processing(self, live_status, duration):
3417 if (live_status == 'is_live' and self.get_param('live_from_start')
3418 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3419 return live_status
3420
3421 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3422 itags, stream_ids = {}, []
3423 itag_qualities, res_qualities = {}, {0: None}
3424 q = qualities([
3425 # Normally tiny is the smallest video-only formats. But
3426 # audio-only formats with unknown quality may get tagged as tiny
3427 'tiny',
3428 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3429 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3430 ])
3431 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3432
3433 for fmt in streaming_formats:
3434 if fmt.get('targetDurationSec'):
3435 continue
3436
3437 itag = str_or_none(fmt.get('itag'))
3438 audio_track = fmt.get('audioTrack') or {}
3439 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3440 if stream_id in stream_ids:
3441 continue
3442
3443 quality = fmt.get('quality')
3444 height = int_or_none(fmt.get('height'))
3445 if quality == 'tiny' or not quality:
3446 quality = fmt.get('audioQuality', '').lower() or quality
3447 # The 3gp format (17) in android client has a quality of "small",
3448 # but is actually worse than other formats
3449 if itag == '17':
3450 quality = 'tiny'
3451 if quality:
3452 if itag:
3453 itag_qualities[itag] = quality
3454 if height:
3455 res_qualities[height] = quality
3456 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3457 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3458 # number of fragment that would subsequently requested with (`&sq=N`)
3459 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3460 continue
3461
3462 fmt_url = fmt.get('url')
3463 if not fmt_url:
3464 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3465 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3466 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3467 if not all((sc, fmt_url, player_url, encrypted_sig)):
3468 continue
3469 try:
3470 fmt_url += '&%s=%s' % (
3471 traverse_obj(sc, ('sp', -1)) or 'signature',
3472 self._decrypt_signature(encrypted_sig, video_id, player_url)
3473 )
3474 except ExtractorError as e:
3475 self.report_warning('Signature extraction failed: Some formats may be missing',
3476 video_id=video_id, only_once=True)
3477 self.write_debug(e, only_once=True)
3478 continue
3479
3480 query = parse_qs(fmt_url)
3481 throttled = False
3482 if query.get('n'):
3483 try:
3484 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3485 fmt_url = update_url_query(fmt_url, {
3486 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3487 })
3488 except ExtractorError as e:
3489 phantomjs_hint = ''
3490 if isinstance(e, JSInterpreter.Exception):
3491 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3492 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3493 if player_url:
3494 self.report_warning(
3495 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3496 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3497 self.write_debug(e, only_once=True)
3498 else:
3499 self.report_warning(
3500 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3501 video_id=video_id, only_once=True)
3502 throttled = True
3503
3504 if itag:
3505 itags[itag] = 'https'
3506 stream_ids.append(stream_id)
3507
3508 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3509 language_preference = (
3510 10 if audio_track.get('audioIsDefault') and 10
3511 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3512 else -1)
3513 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3514 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3515 # Make sure to avoid false positives with small duration differences.
3516 # E.g. __2ABJjxzNo, ySuUZEjARPY
3517 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3518 if is_damaged:
3519 self.report_warning(
3520 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3521 dct = {
3522 'asr': int_or_none(fmt.get('audioSampleRate')),
3523 'filesize': int_or_none(fmt.get('contentLength')),
3524 'format_id': itag,
3525 'format_note': join_nonempty(
3526 '%s%s' % (audio_track.get('displayName') or '',
3527 ' (default)' if language_preference > 0 else ''),
3528 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3529 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3530 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3531 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3532 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3533 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3534 'fps': int_or_none(fmt.get('fps')) or None,
3535 'audio_channels': fmt.get('audioChannels'),
3536 'height': height,
3537 'quality': q(quality),
3538 'has_drm': bool(fmt.get('drmFamilies')),
3539 'tbr': tbr,
3540 'url': fmt_url,
3541 'width': int_or_none(fmt.get('width')),
3542 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3543 'desc' if language_preference < -1 else ''),
3544 'language_preference': language_preference,
3545 # Strictly de-prioritize damaged and 3gp formats
3546 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3547 }
3548 mime_mobj = re.match(
3549 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3550 if mime_mobj:
3551 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3552 dct.update(parse_codecs(mime_mobj.group(2)))
3553 no_audio = dct.get('acodec') == 'none'
3554 no_video = dct.get('vcodec') == 'none'
3555 if no_audio:
3556 dct['vbr'] = tbr
3557 if no_video:
3558 dct['abr'] = tbr
3559 if no_audio or no_video:
3560 dct['downloader_options'] = {
3561 # Youtube throttles chunks >~10M
3562 'http_chunk_size': 10485760,
3563 }
3564 if dct.get('ext'):
3565 dct['container'] = dct['ext'] + '_dash'
3566 yield dct
3567
3568 needs_live_processing = self._needs_live_processing(live_status, duration)
3569 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3570
3571 skip_manifests = set(self._configuration_arg('skip'))
3572 if (not self.get_param('youtube_include_hls_manifest', True)
3573 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3574 or needs_live_processing and skip_bad_formats):
3575 skip_manifests.add('hls')
3576
3577 if not self.get_param('youtube_include_dash_manifest', True):
3578 skip_manifests.add('dash')
3579 if self._configuration_arg('include_live_dash'):
3580 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3581 'Use include_incomplete_formats extractor argument instead')
3582 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3583 skip_manifests.add('dash')
3584
3585 def process_manifest_format(f, proto, itag):
3586 if itag in itags:
3587 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3588 return False
3589 itag = f'{itag}-{proto}'
3590 if itag:
3591 f['format_id'] = itag
3592 itags[itag] = proto
3593
3594 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
3595 if f['quality'] == -1 and f.get('height'):
3596 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
3597 return True
3598
3599 subtitles = {}
3600 for sd in streaming_data:
3601 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
3602 if hls_manifest_url:
3603 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3604 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
3605 subtitles = self._merge_subtitles(subs, subtitles)
3606 for f in fmts:
3607 if process_manifest_format(f, 'hls', self._search_regex(
3608 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3609 yield f
3610
3611 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
3612 if dash_manifest_url:
3613 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3614 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3615 for f in formats:
3616 if process_manifest_format(f, 'dash', f['format_id']):
3617 f['filesize'] = int_or_none(self._search_regex(
3618 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3619 if needs_live_processing:
3620 f['is_from_start'] = True
3621
3622 yield f
3623 yield subtitles
3624
3625 def _extract_storyboard(self, player_responses, duration):
3626 spec = get_first(
3627 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3628 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3629 if not base_url:
3630 return
3631 L = len(spec) - 1
3632 for i, args in enumerate(spec):
3633 args = args.split('#')
3634 counts = list(map(int_or_none, args[:5]))
3635 if len(args) != 8 or not all(counts):
3636 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3637 continue
3638 width, height, frame_count, cols, rows = counts
3639 N, sigh = args[6:]
3640
3641 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3642 fragment_count = frame_count / (cols * rows)
3643 fragment_duration = duration / fragment_count
3644 yield {
3645 'format_id': f'sb{i}',
3646 'format_note': 'storyboard',
3647 'ext': 'mhtml',
3648 'protocol': 'mhtml',
3649 'acodec': 'none',
3650 'vcodec': 'none',
3651 'url': url,
3652 'width': width,
3653 'height': height,
3654 'fps': frame_count / duration,
3655 'rows': rows,
3656 'columns': cols,
3657 'fragments': [{
3658 'url': url.replace('$M', str(j)),
3659 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3660 } for j in range(math.ceil(fragment_count))],
3661 }
3662
3663 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3664 webpage = None
3665 if 'webpage' not in self._configuration_arg('player_skip'):
3666 query = {'bpctr': '9999999999', 'has_verified': '1'}
3667 if smuggled_data.get('is_story'):
3668 query['pp'] = self._STORY_PLAYER_PARAMS
3669 webpage = self._download_webpage(
3670 webpage_url, video_id, fatal=False, query=query)
3671
3672 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3673
3674 player_responses, player_url = self._extract_player_responses(
3675 self._get_requested_clients(url, smuggled_data),
3676 video_id, webpage, master_ytcfg, smuggled_data)
3677
3678 return webpage, master_ytcfg, player_responses, player_url
3679
3680 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3681 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3682 is_live = get_first(video_details, 'isLive')
3683 if is_live is None:
3684 is_live = get_first(live_broadcast_details, 'isLiveNow')
3685 live_content = get_first(video_details, 'isLiveContent')
3686 is_upcoming = get_first(video_details, 'isUpcoming')
3687 post_live = get_first(video_details, 'isPostLiveDvr')
3688 live_status = ('post_live' if post_live
3689 else 'is_live' if is_live
3690 else 'is_upcoming' if is_upcoming
3691 else 'was_live' if live_content
3692 else 'not_live' if False in (is_live, live_content)
3693 else None)
3694 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3695 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
3696
3697 return live_broadcast_details, live_status, streaming_data, formats, subtitles
3698
3699 def _real_extract(self, url):
3700 url, smuggled_data = unsmuggle_url(url, {})
3701 video_id = self._match_id(url)
3702
3703 base_url = self.http_scheme() + '//www.youtube.com/'
3704 webpage_url = base_url + 'watch?v=' + video_id
3705
3706 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3707
3708 playability_statuses = traverse_obj(
3709 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3710
3711 trailer_video_id = get_first(
3712 playability_statuses,
3713 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3714 expected_type=str)
3715 if trailer_video_id:
3716 return self.url_result(
3717 trailer_video_id, self.ie_key(), trailer_video_id)
3718
3719 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3720 if webpage else (lambda x: None))
3721
3722 video_details = traverse_obj(
3723 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3724 microformats = traverse_obj(
3725 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3726 expected_type=dict, default=[])
3727
3728 translated_title = self._get_text(microformats, (..., 'title'))
3729 video_title = (self._preferred_lang and translated_title
3730 or get_first(video_details, 'title') # primary
3731 or translated_title
3732 or search_meta(['og:title', 'twitter:title', 'title']))
3733 translated_description = self._get_text(microformats, (..., 'description'))
3734 original_description = get_first(video_details, 'shortDescription')
3735 video_description = (
3736 self._preferred_lang and translated_description
3737 # If original description is blank, it will be an empty string.
3738 # Do not prefer translated description in this case.
3739 or original_description if original_description is not None else translated_description)
3740
3741 multifeed_metadata_list = get_first(
3742 player_responses,
3743 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3744 expected_type=str)
3745 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3746 if self.get_param('noplaylist'):
3747 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3748 else:
3749 entries = []
3750 feed_ids = []
3751 for feed in multifeed_metadata_list.split(','):
3752 # Unquote should take place before split on comma (,) since textual
3753 # fields may contain comma as well (see
3754 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3755 feed_data = urllib.parse.parse_qs(
3756 urllib.parse.unquote_plus(feed))
3757
3758 def feed_entry(name):
3759 return try_get(
3760 feed_data, lambda x: x[name][0], str)
3761
3762 feed_id = feed_entry('id')
3763 if not feed_id:
3764 continue
3765 feed_title = feed_entry('title')
3766 title = video_title
3767 if feed_title:
3768 title += ' (%s)' % feed_title
3769 entries.append({
3770 '_type': 'url_transparent',
3771 'ie_key': 'Youtube',
3772 'url': smuggle_url(
3773 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3774 {'force_singlefeed': True}),
3775 'title': title,
3776 })
3777 feed_ids.append(feed_id)
3778 self.to_screen(
3779 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3780 % (', '.join(feed_ids), video_id))
3781 return self.playlist_result(
3782 entries, video_id, video_title, video_description)
3783
3784 duration = int_or_none(
3785 get_first(video_details, 'lengthSeconds')
3786 or get_first(microformats, 'lengthSeconds')
3787 or parse_duration(search_meta('duration'))) or None
3788
3789 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3790 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3791 if live_status == 'post_live':
3792 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
3793
3794 if not formats:
3795 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3796 self.report_drm(video_id)
3797 pemr = get_first(
3798 playability_statuses,
3799 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3800 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3801 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3802 if subreason:
3803 if subreason == 'The uploader has not made this video available in your country.':
3804 countries = get_first(microformats, 'availableCountries')
3805 if not countries:
3806 regions_allowed = search_meta('regionsAllowed')
3807 countries = regions_allowed.split(',') if regions_allowed else None
3808 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3809 reason += f'. {subreason}'
3810 if reason:
3811 self.raise_no_formats(reason, expected=True)
3812
3813 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3814 if not keywords and webpage:
3815 keywords = [
3816 unescapeHTML(m.group('content'))
3817 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3818 for keyword in keywords:
3819 if keyword.startswith('yt:stretch='):
3820 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3821 if mobj:
3822 # NB: float is intentional for forcing float division
3823 w, h = (float(v) for v in mobj.groups())
3824 if w > 0 and h > 0:
3825 ratio = w / h
3826 for f in formats:
3827 if f.get('vcodec') != 'none':
3828 f['stretched_ratio'] = ratio
3829 break
3830 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3831 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3832 if thumbnail_url:
3833 thumbnails.append({
3834 'url': thumbnail_url,
3835 })
3836 original_thumbnails = thumbnails.copy()
3837
3838 # The best resolution thumbnails sometimes does not appear in the webpage
3839 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3840 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3841 thumbnail_names = [
3842 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3843 # in resolution, these are not the custom thumbnail. So de-prioritize them
3844 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3845 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3846 ]
3847 n_thumbnail_names = len(thumbnail_names)
3848 thumbnails.extend({
3849 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3850 video_id=video_id, name=name, ext=ext,
3851 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
3852 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3853 for thumb in thumbnails:
3854 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3855 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3856 self._remove_duplicate_formats(thumbnails)
3857 self._downloader._sort_thumbnails(original_thumbnails)
3858
3859 category = get_first(microformats, 'category') or search_meta('genre')
3860 channel_id = str_or_none(
3861 get_first(video_details, 'channelId')
3862 or get_first(microformats, 'externalChannelId')
3863 or search_meta('channelId'))
3864 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3865
3866 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3867 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3868 if not duration and live_end_time and live_start_time:
3869 duration = live_end_time - live_start_time
3870
3871 needs_live_processing = self._needs_live_processing(live_status, duration)
3872
3873 def is_bad_format(fmt):
3874 if needs_live_processing and not fmt.get('is_from_start'):
3875 return True
3876 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
3877 and fmt.get('protocol') == 'http_dash_segments'):
3878 return True
3879
3880 for fmt in filter(is_bad_format, formats):
3881 fmt['preference'] = (fmt.get('preference') or -1) - 10
3882 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
3883
3884 if needs_live_processing:
3885 self._prepare_live_from_start_formats(
3886 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
3887
3888 formats.extend(self._extract_storyboard(player_responses, duration))
3889
3890 # source_preference is lower for throttled/potentially damaged formats
3891 self._sort_formats(formats, (
3892 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
3893
3894 info = {
3895 'id': video_id,
3896 'title': video_title,
3897 'formats': formats,
3898 'thumbnails': thumbnails,
3899 # The best thumbnail that we are sure exists. Prevents unnecessary
3900 # URL checking if user don't care about getting the best possible thumbnail
3901 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3902 'description': video_description,
3903 'uploader': get_first(video_details, 'author'),
3904 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3905 'uploader_url': owner_profile_url,
3906 'channel_id': channel_id,
3907 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
3908 'duration': duration,
3909 'view_count': int_or_none(
3910 get_first((video_details, microformats), (..., 'viewCount'))
3911 or search_meta('interactionCount')),
3912 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3913 'age_limit': 18 if (
3914 get_first(microformats, 'isFamilySafe') is False
3915 or search_meta('isFamilyFriendly') == 'false'
3916 or search_meta('og:restrictions:age') == '18+') else 0,
3917 'webpage_url': webpage_url,
3918 'categories': [category] if category else None,
3919 'tags': keywords,
3920 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3921 'live_status': live_status,
3922 'release_timestamp': live_start_time,
3923 }
3924
3925 subtitles = {}
3926 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3927 if pctr:
3928 def get_lang_code(track):
3929 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3930 or track.get('languageCode'))
3931
3932 # Converted into dicts to remove duplicates
3933 captions = {
3934 get_lang_code(sub): sub
3935 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3936 translation_languages = {
3937 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3938 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3939
3940 def process_language(container, base_url, lang_code, sub_name, query):
3941 lang_subs = container.setdefault(lang_code, [])
3942 for fmt in self._SUBTITLE_FORMATS:
3943 query.update({
3944 'fmt': fmt,
3945 })
3946 lang_subs.append({
3947 'ext': fmt,
3948 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3949 'name': sub_name,
3950 })
3951
3952 # NB: Constructing the full subtitle dictionary is slow
3953 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3954 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
3955 for lang_code, caption_track in captions.items():
3956 base_url = caption_track.get('baseUrl')
3957 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3958 if not base_url:
3959 continue
3960 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3961 if caption_track.get('kind') != 'asr':
3962 if not lang_code:
3963 continue
3964 process_language(
3965 subtitles, base_url, lang_code, lang_name, {})
3966 if not caption_track.get('isTranslatable'):
3967 continue
3968 for trans_code, trans_name in translation_languages.items():
3969 if not trans_code:
3970 continue
3971 orig_trans_code = trans_code
3972 if caption_track.get('kind') != 'asr':
3973 if not get_translated_subs:
3974 continue
3975 trans_code += f'-{lang_code}'
3976 trans_name += format_field(lang_name, None, ' from %s')
3977 # Add an "-orig" label to the original language so that it can be distinguished.
3978 # The subs are returned without "-orig" as well for compatibility
3979 if lang_code == f'a-{orig_trans_code}':
3980 process_language(
3981 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3982 # Setting tlang=lang returns damaged subtitles.
3983 process_language(automatic_captions, base_url, trans_code, trans_name,
3984 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
3985
3986 info['automatic_captions'] = automatic_captions
3987 info['subtitles'] = subtitles
3988
3989 parsed_url = urllib.parse.urlparse(url)
3990 for component in [parsed_url.fragment, parsed_url.query]:
3991 query = urllib.parse.parse_qs(component)
3992 for k, v in query.items():
3993 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3994 d_k += '_time'
3995 if d_k not in info and k in s_ks:
3996 info[d_k] = parse_duration(query[k][0])
3997
3998 # Youtube Music Auto-generated description
3999 if video_description:
4000 mobj = re.search(
4001 r'''(?xs)
4002 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4003 (?P<album>[^\n]+)
4004 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4005 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4006 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4007 .+\nAuto-generated\ by\ YouTube\.\s*$
4008 ''', video_description)
4009 if mobj:
4010 release_year = mobj.group('release_year')
4011 release_date = mobj.group('release_date')
4012 if release_date:
4013 release_date = release_date.replace('-', '')
4014 if not release_year:
4015 release_year = release_date[:4]
4016 info.update({
4017 'album': mobj.group('album'.strip()),
4018 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4019 'track': mobj.group('track').strip(),
4020 'release_date': release_date,
4021 'release_year': int_or_none(release_year),
4022 })
4023
4024 initial_data = None
4025 if webpage:
4026 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
4027 if not initial_data:
4028 query = {'videoId': video_id}
4029 query.update(self._get_checkok_params())
4030 initial_data = self._extract_response(
4031 item_id=video_id, ep='next', fatal=False,
4032 ytcfg=master_ytcfg, query=query,
4033 headers=self.generate_api_headers(ytcfg=master_ytcfg),
4034 note='Downloading initial data API JSON')
4035
4036 info['comment_count'] = traverse_obj(initial_data, (
4037 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4038 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4039 ), (
4040 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4041 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4042 ), expected_type=int_or_none, get_all=False)
4043
4044 try: # This will error if there is no livechat
4045 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4046 except (KeyError, IndexError, TypeError):
4047 pass
4048 else:
4049 info.setdefault('subtitles', {})['live_chat'] = [{
4050 # url is needed to set cookies
4051 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4052 'video_id': video_id,
4053 'ext': 'json',
4054 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4055 else 'youtube_live_chat_replay'),
4056 }]
4057
4058 if initial_data:
4059 info['chapters'] = (
4060 self._extract_chapters_from_json(initial_data, duration)
4061 or self._extract_chapters_from_engagement_panel(initial_data, duration)
4062 or self._extract_chapters_from_description(video_description, duration)
4063 or None)
4064
4065 contents = traverse_obj(
4066 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4067 expected_type=list, default=[])
4068
4069 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4070 if vpir:
4071 stl = vpir.get('superTitleLink')
4072 if stl:
4073 stl = self._get_text(stl)
4074 if try_get(
4075 vpir,
4076 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4077 info['location'] = stl
4078 else:
4079 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
4080 if mobj:
4081 info.update({
4082 'series': mobj.group(1),
4083 'season_number': int(mobj.group(2)),
4084 'episode_number': int(mobj.group(3)),
4085 })
4086 for tlb in (try_get(
4087 vpir,
4088 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4089 list) or []):
4090 tbrs = variadic(
4091 traverse_obj(
4092 tlb, 'toggleButtonRenderer',
4093 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4094 default=[]))
4095 for tbr in tbrs:
4096 for getter, regex in [(
4097 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4098 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4099 lambda x: x['accessibility'],
4100 lambda x: x['accessibilityData']['accessibilityData'],
4101 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4102 label = (try_get(tbr, getter, dict) or {}).get('label')
4103 if label:
4104 mobj = re.match(regex, label)
4105 if mobj:
4106 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4107 break
4108 sbr_tooltip = try_get(
4109 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4110 if sbr_tooltip:
4111 like_count, dislike_count = sbr_tooltip.split(' / ')
4112 info.update({
4113 'like_count': str_to_int(like_count),
4114 'dislike_count': str_to_int(dislike_count),
4115 })
4116 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4117 if vcr:
4118 vc = self._get_count(vcr, 'viewCount')
4119 # Upcoming premieres with waiting count are treated as live here
4120 if vcr.get('isLive'):
4121 info['concurrent_view_count'] = vc
4122 elif info.get('view_count') is None:
4123 info['view_count'] = vc
4124
4125 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4126 if vsir:
4127 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4128 info.update({
4129 'channel': self._get_text(vor, 'title'),
4130 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4131
4132 rows = try_get(
4133 vsir,
4134 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4135 list) or []
4136 multiple_songs = False
4137 for row in rows:
4138 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4139 multiple_songs = True
4140 break
4141 for row in rows:
4142 mrr = row.get('metadataRowRenderer') or {}
4143 mrr_title = mrr.get('title')
4144 if not mrr_title:
4145 continue
4146 mrr_title = self._get_text(mrr, 'title')
4147 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4148 if mrr_title == 'License':
4149 info['license'] = mrr_contents_text
4150 elif not multiple_songs:
4151 if mrr_title == 'Album':
4152 info['album'] = mrr_contents_text
4153 elif mrr_title == 'Artist':
4154 info['artist'] = mrr_contents_text
4155 elif mrr_title == 'Song':
4156 info['track'] = mrr_contents_text
4157
4158 fallbacks = {
4159 'channel': 'uploader',
4160 'channel_id': 'uploader_id',
4161 'channel_url': 'uploader_url',
4162 }
4163
4164 # The upload date for scheduled, live and past live streams / premieres in microformats
4165 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4166 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4167 upload_date = (
4168 unified_strdate(get_first(microformats, 'uploadDate'))
4169 or unified_strdate(search_meta('uploadDate')))
4170 if not upload_date or (
4171 live_status in ('not_live', None)
4172 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4173 ):
4174 upload_date = strftime_or_none(
4175 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
4176 info['upload_date'] = upload_date
4177
4178 for to, frm in fallbacks.items():
4179 if not info.get(to):
4180 info[to] = info.get(frm)
4181
4182 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4183 v = info.get(s_k)
4184 if v:
4185 info[d_k] = v
4186
4187 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4188
4189 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4190 or get_first(video_details, 'isPrivate', expected_type=bool))
4191
4192 info['availability'] = (
4193 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4194 else self._availability(
4195 is_private=is_private,
4196 needs_premium=(
4197 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4198 or False if initial_data and is_private is not None else None),
4199 needs_subscription=(
4200 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4201 or False if initial_data and is_private is not None else None),
4202 needs_auth=info['age_limit'] >= 18,
4203 is_unlisted=None if is_private is None else (
4204 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4205 or get_first(microformats, 'isUnlisted', expected_type=bool))))
4206
4207 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4208
4209 self.mark_watched(video_id, player_responses)
4210
4211 return info
4212
4213
4214 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
4215
4216 @staticmethod
4217 def passthrough_smuggled_data(func):
4218 def _smuggle(entries, smuggled_data):
4219 for entry in entries:
4220 # TODO: Convert URL to music.youtube instead.
4221 # Do we need to passthrough any other smuggled_data?
4222 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4223 yield entry
4224
4225 @functools.wraps(func)
4226 def wrapper(self, url):
4227 url, smuggled_data = unsmuggle_url(url, {})
4228 if self.is_music_url(url):
4229 smuggled_data['is_music_url'] = True
4230 info_dict = func(self, url, smuggled_data)
4231 if smuggled_data and info_dict.get('entries'):
4232 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4233 return info_dict
4234 return wrapper
4235
4236 def _extract_channel_id(self, webpage):
4237 channel_id = self._html_search_meta(
4238 'channelId', webpage, 'channel id', default=None)
4239 if channel_id:
4240 return channel_id
4241 channel_url = self._html_search_meta(
4242 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4243 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4244 'twitter:app:url:googleplay'), webpage, 'channel url')
4245 return self._search_regex(
4246 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4247 channel_url, 'channel id')
4248
4249 @staticmethod
4250 def _extract_basic_item_renderer(item):
4251 # Modified from _extract_grid_item_renderer
4252 known_basic_renderers = (
4253 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4254 )
4255 for key, renderer in item.items():
4256 if not isinstance(renderer, dict):
4257 continue
4258 elif key in known_basic_renderers:
4259 return renderer
4260 elif key.startswith('grid') and key.endswith('Renderer'):
4261 return renderer
4262
4263 def _grid_entries(self, grid_renderer):
4264 for item in grid_renderer['items']:
4265 if not isinstance(item, dict):
4266 continue
4267 renderer = self._extract_basic_item_renderer(item)
4268 if not isinstance(renderer, dict):
4269 continue
4270 title = self._get_text(renderer, 'title')
4271
4272 # playlist
4273 playlist_id = renderer.get('playlistId')
4274 if playlist_id:
4275 yield self.url_result(
4276 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4277 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4278 video_title=title)
4279 continue
4280 # video
4281 video_id = renderer.get('videoId')
4282 if video_id:
4283 yield self._extract_video(renderer)
4284 continue
4285 # channel
4286 channel_id = renderer.get('channelId')
4287 if channel_id:
4288 yield self.url_result(
4289 'https://www.youtube.com/channel/%s' % channel_id,
4290 ie=YoutubeTabIE.ie_key(), video_title=title)
4291 continue
4292 # generic endpoint URL support
4293 ep_url = urljoin('https://www.youtube.com/', try_get(
4294 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4295 str))
4296 if ep_url:
4297 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4298 if ie.suitable(ep_url):
4299 yield self.url_result(
4300 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4301 break
4302
4303 def _music_reponsive_list_entry(self, renderer):
4304 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4305 if video_id:
4306 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4307 ie=YoutubeIE.ie_key(), video_id=video_id)
4308 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4309 if playlist_id:
4310 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4311 if video_id:
4312 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4313 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4314 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4315 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4316 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4317 if browse_id:
4318 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4319 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4320
4321 def _shelf_entries_from_content(self, shelf_renderer):
4322 content = shelf_renderer.get('content')
4323 if not isinstance(content, dict):
4324 return
4325 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
4326 if renderer:
4327 # TODO: add support for nested playlists so each shelf is processed
4328 # as separate playlist
4329 # TODO: this includes only first N items
4330 yield from self._grid_entries(renderer)
4331 renderer = content.get('horizontalListRenderer')
4332 if renderer:
4333 # TODO
4334 pass
4335
4336 def _shelf_entries(self, shelf_renderer, skip_channels=False):
4337 ep = try_get(
4338 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4339 str)
4340 shelf_url = urljoin('https://www.youtube.com', ep)
4341 if shelf_url:
4342 # Skipping links to another channels, note that checking for
4343 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4344 # will not work
4345 if skip_channels and '/channels?' in shelf_url:
4346 return
4347 title = self._get_text(shelf_renderer, 'title')
4348 yield self.url_result(shelf_url, video_title=title)
4349 # Shelf may not contain shelf URL, fallback to extraction from content
4350 yield from self._shelf_entries_from_content(shelf_renderer)
4351
4352 def _playlist_entries(self, video_list_renderer):
4353 for content in video_list_renderer['contents']:
4354 if not isinstance(content, dict):
4355 continue
4356 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4357 if not isinstance(renderer, dict):
4358 continue
4359 video_id = renderer.get('videoId')
4360 if not video_id:
4361 continue
4362 yield self._extract_video(renderer)
4363
4364 def _rich_entries(self, rich_grid_renderer):
4365 renderer = traverse_obj(
4366 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
4367 video_id = renderer.get('videoId')
4368 if not video_id:
4369 return
4370 yield self._extract_video(renderer)
4371
4372 def _video_entry(self, video_renderer):
4373 video_id = video_renderer.get('videoId')
4374 if video_id:
4375 return self._extract_video(video_renderer)
4376
4377 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4378 url = urljoin('https://youtube.com', traverse_obj(
4379 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4380 if url:
4381 return self.url_result(
4382 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4383
4384 def _post_thread_entries(self, post_thread_renderer):
4385 post_renderer = try_get(
4386 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4387 if not post_renderer:
4388 return
4389 # video attachment
4390 video_renderer = try_get(
4391 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4392 video_id = video_renderer.get('videoId')
4393 if video_id:
4394 entry = self._extract_video(video_renderer)
4395 if entry:
4396 yield entry
4397 # playlist attachment
4398 playlist_id = try_get(
4399 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4400 if playlist_id:
4401 yield self.url_result(
4402 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4403 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4404 # inline video links
4405 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4406 for run in runs:
4407 if not isinstance(run, dict):
4408 continue
4409 ep_url = try_get(
4410 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4411 if not ep_url:
4412 continue
4413 if not YoutubeIE.suitable(ep_url):
4414 continue
4415 ep_video_id = YoutubeIE._match_id(ep_url)
4416 if video_id == ep_video_id:
4417 continue
4418 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4419
4420 def _post_thread_continuation_entries(self, post_thread_continuation):
4421 contents = post_thread_continuation.get('contents')
4422 if not isinstance(contents, list):
4423 return
4424 for content in contents:
4425 renderer = content.get('backstagePostThreadRenderer')
4426 if isinstance(renderer, dict):
4427 yield from self._post_thread_entries(renderer)
4428 continue
4429 renderer = content.get('videoRenderer')
4430 if isinstance(renderer, dict):
4431 yield self._video_entry(renderer)
4432
4433 r''' # unused
4434 def _rich_grid_entries(self, contents):
4435 for content in contents:
4436 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4437 if video_renderer:
4438 entry = self._video_entry(video_renderer)
4439 if entry:
4440 yield entry
4441 '''
4442
4443 def _report_history_entries(self, renderer):
4444 for url in traverse_obj(renderer, (
4445 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4446 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4447 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4448 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4449
4450 def _extract_entries(self, parent_renderer, continuation_list):
4451 # continuation_list is modified in-place with continuation_list = [continuation_token]
4452 continuation_list[:] = [None]
4453 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4454 for content in contents:
4455 if not isinstance(content, dict):
4456 continue
4457 is_renderer = traverse_obj(
4458 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4459 expected_type=dict)
4460 if not is_renderer:
4461 if content.get('richItemRenderer'):
4462 for entry in self._rich_entries(content['richItemRenderer']):
4463 yield entry
4464 continuation_list[0] = self._extract_continuation(parent_renderer)
4465 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4466 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4467 yield from self._report_history_entries(table)
4468 continuation_list[0] = self._extract_continuation(table)
4469 continue
4470
4471 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4472 for isr_content in isr_contents:
4473 if not isinstance(isr_content, dict):
4474 continue
4475
4476 known_renderers = {
4477 'playlistVideoListRenderer': self._playlist_entries,
4478 'gridRenderer': self._grid_entries,
4479 'reelShelfRenderer': self._grid_entries,
4480 'shelfRenderer': self._shelf_entries,
4481 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4482 'backstagePostThreadRenderer': self._post_thread_entries,
4483 'videoRenderer': lambda x: [self._video_entry(x)],
4484 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4485 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4486 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4487 }
4488 for key, renderer in isr_content.items():
4489 if key not in known_renderers:
4490 continue
4491 for entry in known_renderers[key](renderer):
4492 if entry:
4493 yield entry
4494 continuation_list[0] = self._extract_continuation(renderer)
4495 break
4496
4497 if not continuation_list[0]:
4498 continuation_list[0] = self._extract_continuation(is_renderer)
4499
4500 if not continuation_list[0]:
4501 continuation_list[0] = self._extract_continuation(parent_renderer)
4502
4503 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4504 continuation_list = [None]
4505 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4506 tab_content = try_get(tab, lambda x: x['content'], dict)
4507 if not tab_content:
4508 return
4509 parent_renderer = (
4510 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4511 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4512 yield from extract_entries(parent_renderer)
4513 continuation = continuation_list[0]
4514
4515 for page_num in itertools.count(1):
4516 if not continuation:
4517 break
4518 headers = self.generate_api_headers(
4519 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4520 response = self._extract_response(
4521 item_id=f'{item_id} page {page_num}',
4522 query=continuation, headers=headers, ytcfg=ytcfg,
4523 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4524
4525 if not response:
4526 break
4527 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4528 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4529 visitor_data = self._extract_visitor_data(response) or visitor_data
4530
4531 known_renderers = {
4532 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4533 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4534 'gridVideoRenderer': (self._grid_entries, 'items'),
4535 'gridChannelRenderer': (self._grid_entries, 'items'),
4536 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4537 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4538 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4539 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4540 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
4541 'playlistVideoListContinuation': (self._playlist_entries, None),
4542 'gridContinuation': (self._grid_entries, None),
4543 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4544 'sectionListContinuation': (extract_entries, None), # for feeds
4545 }
4546
4547 continuation_items = traverse_obj(response, (
4548 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4549 'appendContinuationItemsAction', 'continuationItems'
4550 ), 'continuationContents', get_all=False)
4551 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4552
4553 video_items_renderer = None
4554 for key in continuation_item.keys():
4555 if key not in known_renderers:
4556 continue
4557 func, parent_key = known_renderers[key]
4558 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
4559 continuation_list = [None]
4560 yield from func(video_items_renderer)
4561 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4562
4563 if not video_items_renderer:
4564 break
4565
4566 @staticmethod
4567 def _extract_selected_tab(tabs, fatal=True):
4568 for tab in tabs:
4569 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4570 if renderer.get('selected') is True:
4571 return renderer
4572 else:
4573 if fatal:
4574 raise ExtractorError('Unable to find selected tab')
4575
4576 def _extract_uploader(self, data):
4577 uploader = {}
4578 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4579 owner = try_get(
4580 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4581 if owner:
4582 owner_text = owner.get('text')
4583 uploader['uploader'] = self._search_regex(
4584 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
4585 uploader['uploader_id'] = try_get(
4586 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
4587 uploader['uploader_url'] = urljoin(
4588 'https://www.youtube.com/',
4589 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4590 return filter_dict(uploader)
4591
4592 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4593 playlist_id = title = description = channel_url = channel_name = channel_id = None
4594 tags = []
4595
4596 selected_tab = self._extract_selected_tab(tabs)
4597 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4598 renderer = try_get(
4599 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4600 if renderer:
4601 channel_name = renderer.get('title')
4602 channel_url = renderer.get('channelUrl')
4603 channel_id = renderer.get('externalId')
4604 else:
4605 renderer = try_get(
4606 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
4607
4608 if renderer:
4609 title = renderer.get('title')
4610 description = renderer.get('description', '')
4611 playlist_id = channel_id
4612 tags = renderer.get('keywords', '').split()
4613
4614 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4615 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4616 def _get_uncropped(url):
4617 return url_or_none((url or '').split('=')[0] + '=s0')
4618
4619 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4620 if avatar_thumbnails:
4621 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4622 if uncropped_avatar:
4623 avatar_thumbnails.append({
4624 'url': uncropped_avatar,
4625 'id': 'avatar_uncropped',
4626 'preference': 1
4627 })
4628
4629 channel_banners = self._extract_thumbnails(
4630 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4631 for banner in channel_banners:
4632 banner['preference'] = -10
4633
4634 if channel_banners:
4635 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4636 if uncropped_banner:
4637 channel_banners.append({
4638 'url': uncropped_banner,
4639 'id': 'banner_uncropped',
4640 'preference': -5
4641 })
4642
4643 primary_thumbnails = self._extract_thumbnails(
4644 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4645
4646 if playlist_id is None:
4647 playlist_id = item_id
4648
4649 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4650 last_updated_unix = self._parse_time_text(self._get_text(playlist_stats, 2))
4651 if title is None:
4652 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4653 title += format_field(selected_tab, 'title', ' - %s')
4654 title += format_field(selected_tab, 'expandedText', ' - %s')
4655
4656 metadata = {
4657 'playlist_id': playlist_id,
4658 'playlist_title': title,
4659 'playlist_description': description,
4660 'uploader': channel_name,
4661 'uploader_id': channel_id,
4662 'uploader_url': channel_url,
4663 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4664 'tags': tags,
4665 'view_count': self._get_count(playlist_stats, 1),
4666 'availability': self._extract_availability(data),
4667 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4668 'playlist_count': self._get_count(playlist_stats, 0),
4669 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4670 }
4671 if not channel_id:
4672 metadata.update(self._extract_uploader(data))
4673 metadata.update({
4674 'channel': metadata['uploader'],
4675 'channel_id': metadata['uploader_id'],
4676 'channel_url': metadata['uploader_url']})
4677 return self.playlist_result(
4678 self._entries(
4679 selected_tab, playlist_id, ytcfg,
4680 self._extract_account_syncid(ytcfg, data),
4681 self._extract_visitor_data(data, ytcfg)),
4682 **metadata)
4683
4684 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4685 first_id = last_id = response = None
4686 for page_num in itertools.count(1):
4687 videos = list(self._playlist_entries(playlist))
4688 if not videos:
4689 return
4690 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4691 if start >= len(videos):
4692 return
4693 yield from videos[start:]
4694 first_id = first_id or videos[0]['id']
4695 last_id = videos[-1]['id']
4696 watch_endpoint = try_get(
4697 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4698 headers = self.generate_api_headers(
4699 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4700 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4701 query = {
4702 'playlistId': playlist_id,
4703 'videoId': watch_endpoint.get('videoId') or last_id,
4704 'index': watch_endpoint.get('index') or len(videos),
4705 'params': watch_endpoint.get('params') or 'OAE%3D'
4706 }
4707 response = self._extract_response(
4708 item_id='%s page %d' % (playlist_id, page_num),
4709 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4710 check_get_keys='contents'
4711 )
4712 playlist = try_get(
4713 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4714
4715 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4716 title = playlist.get('title') or try_get(
4717 data, lambda x: x['titleText']['simpleText'], str)
4718 playlist_id = playlist.get('playlistId') or item_id
4719
4720 # Delegating everything except mix playlists to regular tab-based playlist URL
4721 playlist_url = urljoin(url, try_get(
4722 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4723 str))
4724
4725 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4726 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4727 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4728
4729 if playlist_url and playlist_url != url and not is_known_unviewable:
4730 return self.url_result(
4731 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4732 video_title=title)
4733
4734 return self.playlist_result(
4735 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4736 playlist_id=playlist_id, playlist_title=title)
4737
4738 def _extract_availability(self, data):
4739 """
4740 Gets the availability of a given playlist/tab.
4741 Note: Unless YouTube tells us explicitly, we do not assume it is public
4742 @param data: response
4743 """
4744 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4745
4746 player_header_privacy = traverse_obj(
4747 data, ('header', 'playlistHeaderRenderer', 'privacy'), expected_type=str)
4748
4749 badges = self._extract_badges(renderer)
4750
4751 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4752 privacy_setting_icon = traverse_obj(
4753 renderer, (
4754 'privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4755 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4756 get_all=False, expected_type=str)
4757
4758 return (
4759 'public' if (
4760 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4761 or player_header_privacy == 'PUBLIC'
4762 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4763 else self._availability(
4764 is_private=(
4765 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4766 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4767 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4768 is_unlisted=(
4769 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4770 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
4771 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None else None),
4772 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4773 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4774 needs_auth=False))
4775
4776 @staticmethod
4777 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4778 sidebar_renderer = try_get(
4779 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4780 for item in sidebar_renderer:
4781 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4782 if renderer:
4783 return renderer
4784
4785 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4786 """
4787 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4788 """
4789 browse_id = params = None
4790 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4791 if not renderer:
4792 return
4793 menu_renderer = try_get(
4794 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4795 for menu_item in menu_renderer:
4796 if not isinstance(menu_item, dict):
4797 continue
4798 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4799 text = try_get(
4800 nav_item_renderer, lambda x: x['text']['simpleText'], str)
4801 if not text or text.lower() != 'show unavailable videos':
4802 continue
4803 browse_endpoint = try_get(
4804 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4805 browse_id = browse_endpoint.get('browseId')
4806 params = browse_endpoint.get('params')
4807 break
4808
4809 headers = self.generate_api_headers(
4810 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4811 visitor_data=self._extract_visitor_data(data, ytcfg))
4812 query = {
4813 'params': params or 'wgYCCAA=',
4814 'browseId': browse_id or 'VL%s' % item_id
4815 }
4816 return self._extract_response(
4817 item_id=item_id, headers=headers, query=query,
4818 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4819 note='Downloading API JSON with unavailable videos')
4820
4821 @functools.cached_property
4822 def skip_webpage(self):
4823 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4824
4825 def _extract_webpage(self, url, item_id, fatal=True):
4826 webpage, data = None, None
4827 for retry in self.RetryManager(fatal=fatal):
4828 try:
4829 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
4830 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4831 except ExtractorError as e:
4832 if isinstance(e.cause, network_exceptions):
4833 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
4834 retry.error = e
4835 continue
4836 self._error_or_warning(e, fatal=fatal)
4837 break
4838
4839 try:
4840 self._extract_and_report_alerts(data)
4841 except ExtractorError as e:
4842 self._error_or_warning(e, fatal=fatal)
4843 break
4844
4845 # Sometimes youtube returns a webpage with incomplete ytInitialData
4846 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4847 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4848 retry.error = ExtractorError('Incomplete yt initial data received')
4849 continue
4850
4851 return webpage, data
4852
4853 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4854 """Use if failed to extract ytcfg (and data) from initial webpage"""
4855 if not ytcfg and self.is_authenticated:
4856 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4857 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4858 raise ExtractorError(
4859 f'{msg}. If you are not downloading private content, or '
4860 'your cookies are only for the first account and channel,'
4861 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4862 expected=True)
4863 self.report_warning(msg, only_once=True)
4864
4865 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4866 data = None
4867 if not self.skip_webpage:
4868 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4869 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4870 # Reject webpage data if redirected to home page without explicitly requesting
4871 selected_tab = self._extract_selected_tab(traverse_obj(
4872 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4873 if (url != 'https://www.youtube.com/feed/recommended'
4874 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4875 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4876 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4877 if fatal:
4878 raise ExtractorError(msg, expected=True)
4879 self.report_warning(msg, only_once=True)
4880 if not data:
4881 self._report_playlist_authcheck(ytcfg, fatal=fatal)
4882 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4883 return data, ytcfg
4884
4885 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4886 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4887 resolve_response = self._extract_response(
4888 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4889 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4890 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4891 for ep_key, ep in endpoints.items():
4892 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4893 if params:
4894 return self._extract_response(
4895 item_id=item_id, query=params, ep=ep, headers=headers,
4896 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4897 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4898 err_note = 'Failed to resolve url (does the playlist exist?)'
4899 if fatal:
4900 raise ExtractorError(err_note, expected=True)
4901 self.report_warning(err_note, item_id)
4902
4903 _SEARCH_PARAMS = None
4904
4905 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4906 data = {'query': query}
4907 if params is NO_DEFAULT:
4908 params = self._SEARCH_PARAMS
4909 if params:
4910 data['params'] = params
4911
4912 content_keys = (
4913 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4914 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4915 # ytmusic search
4916 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4917 ('continuationContents', ),
4918 )
4919 display_id = f'query "{query}"'
4920 check_get_keys = tuple({keys[0] for keys in content_keys})
4921 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4922 self._report_playlist_authcheck(ytcfg, fatal=False)
4923
4924 continuation_list = [None]
4925 search = None
4926 for page_num in itertools.count(1):
4927 data.update(continuation_list[0] or {})
4928 headers = self.generate_api_headers(
4929 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
4930 search = self._extract_response(
4931 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4932 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
4933 slr_contents = traverse_obj(search, *content_keys)
4934 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4935 if not continuation_list[0]:
4936 break
4937
4938
4939 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4940 IE_DESC = 'YouTube Tabs'
4941 _VALID_URL = r'''(?x:
4942 https?://
4943 (?:\w+\.)?
4944 (?:
4945 youtube(?:kids)?\.com|
4946 %(invidious)s
4947 )/
4948 (?:
4949 (?P<channel_type>channel|c|user|browse)/|
4950 (?P<not_channel>
4951 feed/|hashtag/|
4952 (?:playlist|watch)\?.*?\blist=
4953 )|
4954 (?!(?:%(reserved_names)s)\b) # Direct URLs
4955 )
4956 (?P<id>[^/?\#&]+)
4957 )''' % {
4958 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4959 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4960 }
4961 IE_NAME = 'youtube:tab'
4962
4963 _TESTS = [{
4964 'note': 'playlists, multipage',
4965 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4966 'playlist_mincount': 94,
4967 'info_dict': {
4968 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4969 'title': 'Igor Kleiner - Playlists',
4970 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4971 'uploader': 'Igor Kleiner',
4972 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4973 'channel': 'Igor Kleiner',
4974 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4975 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4976 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4977 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4978 'channel_follower_count': int
4979 },
4980 }, {
4981 'note': 'playlists, multipage, different order',
4982 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4983 'playlist_mincount': 94,
4984 'info_dict': {
4985 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4986 'title': 'Igor Kleiner - Playlists',
4987 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4988 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4989 'uploader': 'Igor Kleiner',
4990 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4991 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4992 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4993 'channel': 'Igor Kleiner',
4994 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4995 'channel_follower_count': int
4996 },
4997 }, {
4998 'note': 'playlists, series',
4999 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5000 'playlist_mincount': 5,
5001 'info_dict': {
5002 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5003 'title': '3Blue1Brown - Playlists',
5004 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5005 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5006 'uploader': '3Blue1Brown',
5007 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5008 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5009 'channel': '3Blue1Brown',
5010 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5011 'tags': ['Mathematics'],
5012 'channel_follower_count': int
5013 },
5014 }, {
5015 'note': 'playlists, singlepage',
5016 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5017 'playlist_mincount': 4,
5018 'info_dict': {
5019 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5020 'title': 'ThirstForScience - Playlists',
5021 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5022 'uploader': 'ThirstForScience',
5023 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5024 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5025 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5026 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5027 'tags': 'count:13',
5028 'channel': 'ThirstForScience',
5029 'channel_follower_count': int
5030 }
5031 }, {
5032 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5033 'only_matching': True,
5034 }, {
5035 'note': 'basic, single video playlist',
5036 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5037 'info_dict': {
5038 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5039 'uploader': 'Sergey M.',
5040 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5041 'title': 'youtube-dl public playlist',
5042 'description': '',
5043 'tags': [],
5044 'view_count': int,
5045 'modified_date': '20201130',
5046 'channel': 'Sergey M.',
5047 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5048 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5049 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5050 'availability': 'public',
5051 },
5052 'playlist_count': 1,
5053 }, {
5054 'note': 'empty playlist',
5055 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5056 'info_dict': {
5057 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5058 'uploader': 'Sergey M.',
5059 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5060 'title': 'youtube-dl empty playlist',
5061 'tags': [],
5062 'channel': 'Sergey M.',
5063 'description': '',
5064 'modified_date': '20160902',
5065 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5066 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5067 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5068 'availability': 'public',
5069 },
5070 'playlist_count': 0,
5071 }, {
5072 'note': 'Home tab',
5073 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5074 'info_dict': {
5075 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5076 'title': 'lex will - Home',
5077 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5078 'uploader': 'lex will',
5079 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5080 'channel': 'lex will',
5081 'tags': ['bible', 'history', 'prophesy'],
5082 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5083 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5084 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5085 'channel_follower_count': int
5086 },
5087 'playlist_mincount': 2,
5088 }, {
5089 'note': 'Videos tab',
5090 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5091 'info_dict': {
5092 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5093 'title': 'lex will - Videos',
5094 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5095 'uploader': 'lex will',
5096 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5097 'tags': ['bible', 'history', 'prophesy'],
5098 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5099 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5100 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5101 'channel': 'lex will',
5102 'channel_follower_count': int
5103 },
5104 'playlist_mincount': 975,
5105 }, {
5106 'note': 'Videos tab, sorted by popular',
5107 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5108 'info_dict': {
5109 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5110 'title': 'lex will - Videos',
5111 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5112 'uploader': 'lex will',
5113 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5114 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5115 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5116 'channel': 'lex will',
5117 'tags': ['bible', 'history', 'prophesy'],
5118 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5119 'channel_follower_count': int
5120 },
5121 'playlist_mincount': 199,
5122 }, {
5123 'note': 'Playlists tab',
5124 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5125 'info_dict': {
5126 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5127 'title': 'lex will - Playlists',
5128 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5129 'uploader': 'lex will',
5130 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5131 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5132 'channel': 'lex will',
5133 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5134 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5135 'tags': ['bible', 'history', 'prophesy'],
5136 'channel_follower_count': int
5137 },
5138 'playlist_mincount': 17,
5139 }, {
5140 'note': 'Community tab',
5141 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5142 'info_dict': {
5143 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5144 'title': 'lex will - Community',
5145 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5146 'uploader': 'lex will',
5147 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5148 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5149 'channel': 'lex will',
5150 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5151 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5152 'tags': ['bible', 'history', 'prophesy'],
5153 'channel_follower_count': int
5154 },
5155 'playlist_mincount': 18,
5156 }, {
5157 'note': 'Channels tab',
5158 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5159 'info_dict': {
5160 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5161 'title': 'lex will - Channels',
5162 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5163 'uploader': 'lex will',
5164 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5165 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5166 'channel': 'lex will',
5167 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5168 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5169 'tags': ['bible', 'history', 'prophesy'],
5170 'channel_follower_count': int
5171 },
5172 'playlist_mincount': 12,
5173 }, {
5174 'note': 'Search tab',
5175 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5176 'playlist_mincount': 40,
5177 'info_dict': {
5178 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5179 'title': '3Blue1Brown - Search - linear algebra',
5180 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5181 'uploader': '3Blue1Brown',
5182 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5183 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5184 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5185 'tags': ['Mathematics'],
5186 'channel': '3Blue1Brown',
5187 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5188 'channel_follower_count': int
5189 },
5190 }, {
5191 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5192 'only_matching': True,
5193 }, {
5194 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5195 'only_matching': True,
5196 }, {
5197 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5198 'only_matching': True,
5199 }, {
5200 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5201 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5202 'info_dict': {
5203 'title': '29C3: Not my department',
5204 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5205 'uploader': 'Christiaan008',
5206 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5207 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5208 'tags': [],
5209 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5210 'view_count': int,
5211 'modified_date': '20150605',
5212 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5213 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5214 'channel': 'Christiaan008',
5215 'availability': 'public',
5216 },
5217 'playlist_count': 96,
5218 }, {
5219 'note': 'Large playlist',
5220 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5221 'info_dict': {
5222 'title': 'Uploads from Cauchemar',
5223 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5224 'uploader': 'Cauchemar',
5225 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5226 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5227 'tags': [],
5228 'modified_date': r're:\d{8}',
5229 'channel': 'Cauchemar',
5230 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5231 'view_count': int,
5232 'description': '',
5233 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5234 'availability': 'public',
5235 },
5236 'playlist_mincount': 1123,
5237 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5238 }, {
5239 'note': 'even larger playlist, 8832 videos',
5240 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5241 'only_matching': True,
5242 }, {
5243 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5244 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5245 'info_dict': {
5246 'title': 'Uploads from Interstellar Movie',
5247 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5248 'uploader': 'Interstellar Movie',
5249 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5250 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5251 'tags': [],
5252 'view_count': int,
5253 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5254 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5255 'channel': 'Interstellar Movie',
5256 'description': '',
5257 'modified_date': r're:\d{8}',
5258 'availability': 'public',
5259 },
5260 'playlist_mincount': 21,
5261 }, {
5262 'note': 'Playlist with "show unavailable videos" button',
5263 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5264 'info_dict': {
5265 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5266 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5267 'uploader': 'Phim Siêu Nhân Nhật Bản',
5268 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5269 'view_count': int,
5270 'channel': 'Phim Siêu Nhân Nhật Bản',
5271 'tags': [],
5272 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5273 'description': '',
5274 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5275 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5276 'modified_date': r're:\d{8}',
5277 'availability': 'public',
5278 },
5279 'playlist_mincount': 200,
5280 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5281 }, {
5282 'note': 'Playlist with unavailable videos in page 7',
5283 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5284 'info_dict': {
5285 'title': 'Uploads from BlankTV',
5286 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5287 'uploader': 'BlankTV',
5288 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5289 'channel': 'BlankTV',
5290 'channel_url': 'https://www.youtube.com/c/blanktv',
5291 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5292 'view_count': int,
5293 'tags': [],
5294 'uploader_url': 'https://www.youtube.com/c/blanktv',
5295 'modified_date': r're:\d{8}',
5296 'description': '',
5297 'availability': 'public',
5298 },
5299 'playlist_mincount': 1000,
5300 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5301 }, {
5302 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5303 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5304 'info_dict': {
5305 'title': 'Data Analysis with Dr Mike Pound',
5306 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5307 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5308 'uploader': 'Computerphile',
5309 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5310 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5311 'tags': [],
5312 'view_count': int,
5313 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5314 'channel_url': 'https://www.youtube.com/user/Computerphile',
5315 'channel': 'Computerphile',
5316 'availability': 'public',
5317 },
5318 'playlist_mincount': 11,
5319 }, {
5320 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5321 'only_matching': True,
5322 }, {
5323 'note': 'Playlist URL that does not actually serve a playlist',
5324 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5325 'info_dict': {
5326 'id': 'FqZTN594JQw',
5327 'ext': 'webm',
5328 'title': "Smiley's People 01 detective, Adventure Series, Action",
5329 'uploader': 'STREEM',
5330 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5331 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5332 'upload_date': '20150526',
5333 'license': 'Standard YouTube License',
5334 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5335 'categories': ['People & Blogs'],
5336 'tags': list,
5337 'view_count': int,
5338 'like_count': int,
5339 },
5340 'params': {
5341 'skip_download': True,
5342 },
5343 'skip': 'This video is not available.',
5344 'add_ie': [YoutubeIE.ie_key()],
5345 }, {
5346 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5347 'only_matching': True,
5348 }, {
5349 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5350 'only_matching': True,
5351 }, {
5352 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5353 'info_dict': {
5354 'id': 'Wq15eF5vCbI', # This will keep changing
5355 'ext': 'mp4',
5356 'title': str,
5357 'uploader': 'Sky News',
5358 'uploader_id': 'skynews',
5359 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5360 'upload_date': r're:\d{8}',
5361 'description': str,
5362 'categories': ['News & Politics'],
5363 'tags': list,
5364 'like_count': int,
5365 'release_timestamp': 1642502819,
5366 'channel': 'Sky News',
5367 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5368 'age_limit': 0,
5369 'view_count': int,
5370 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5371 'playable_in_embed': True,
5372 'release_date': '20220118',
5373 'availability': 'public',
5374 'live_status': 'is_live',
5375 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5376 'channel_follower_count': int
5377 },
5378 'params': {
5379 'skip_download': True,
5380 },
5381 'expected_warnings': ['Ignoring subtitle tracks found in '],
5382 }, {
5383 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5384 'info_dict': {
5385 'id': 'a48o2S1cPoo',
5386 'ext': 'mp4',
5387 'title': 'The Young Turks - Live Main Show',
5388 'uploader': 'The Young Turks',
5389 'uploader_id': 'TheYoungTurks',
5390 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5391 'upload_date': '20150715',
5392 'license': 'Standard YouTube License',
5393 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5394 'categories': ['News & Politics'],
5395 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5396 'like_count': int,
5397 },
5398 'params': {
5399 'skip_download': True,
5400 },
5401 'only_matching': True,
5402 }, {
5403 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5404 'only_matching': True,
5405 }, {
5406 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5407 'only_matching': True,
5408 }, {
5409 'note': 'A channel that is not live. Should raise error',
5410 'url': 'https://www.youtube.com/user/numberphile/live',
5411 'only_matching': True,
5412 }, {
5413 'url': 'https://www.youtube.com/feed/trending',
5414 'only_matching': True,
5415 }, {
5416 'url': 'https://www.youtube.com/feed/library',
5417 'only_matching': True,
5418 }, {
5419 'url': 'https://www.youtube.com/feed/history',
5420 'only_matching': True,
5421 }, {
5422 'url': 'https://www.youtube.com/feed/subscriptions',
5423 'only_matching': True,
5424 }, {
5425 'url': 'https://www.youtube.com/feed/watch_later',
5426 'only_matching': True,
5427 }, {
5428 'note': 'Recommended - redirects to home page.',
5429 'url': 'https://www.youtube.com/feed/recommended',
5430 'only_matching': True,
5431 }, {
5432 'note': 'inline playlist with not always working continuations',
5433 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5434 'only_matching': True,
5435 }, {
5436 'url': 'https://www.youtube.com/course',
5437 'only_matching': True,
5438 }, {
5439 'url': 'https://www.youtube.com/zsecurity',
5440 'only_matching': True,
5441 }, {
5442 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5443 'only_matching': True,
5444 }, {
5445 'url': 'https://www.youtube.com/TheYoungTurks/live',
5446 'only_matching': True,
5447 }, {
5448 'url': 'https://www.youtube.com/hashtag/cctv9',
5449 'info_dict': {
5450 'id': 'cctv9',
5451 'title': '#cctv9',
5452 'tags': [],
5453 },
5454 'playlist_mincount': 350,
5455 }, {
5456 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5457 'only_matching': True,
5458 }, {
5459 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5460 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5461 'only_matching': True
5462 }, {
5463 'note': '/browse/ should redirect to /channel/',
5464 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5465 'only_matching': True
5466 }, {
5467 'note': 'VLPL, should redirect to playlist?list=PL...',
5468 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5469 'info_dict': {
5470 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5471 'uploader': 'NoCopyrightSounds',
5472 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5473 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5474 'title': 'NCS : All Releases 💿',
5475 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5476 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5477 'modified_date': r're:\d{8}',
5478 'view_count': int,
5479 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5480 'tags': [],
5481 'channel': 'NoCopyrightSounds',
5482 'availability': 'public',
5483 },
5484 'playlist_mincount': 166,
5485 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5486 }, {
5487 'note': 'Topic, should redirect to playlist?list=UU...',
5488 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5489 'info_dict': {
5490 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5491 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5492 'title': 'Uploads from Royalty Free Music - Topic',
5493 'uploader': 'Royalty Free Music - Topic',
5494 'tags': [],
5495 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5496 'channel': 'Royalty Free Music - Topic',
5497 'view_count': int,
5498 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5499 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5500 'modified_date': r're:\d{8}',
5501 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5502 'description': '',
5503 'availability': 'public',
5504 },
5505 'expected_warnings': [
5506 'The URL does not have a videos tab',
5507 r'[Uu]navailable videos (are|will be) hidden',
5508 ],
5509 'playlist_mincount': 101,
5510 }, {
5511 'note': 'Topic without a UU playlist',
5512 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5513 'info_dict': {
5514 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5515 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5516 'tags': [],
5517 },
5518 'expected_warnings': [
5519 'the playlist redirect gave error',
5520 ],
5521 'playlist_mincount': 9,
5522 }, {
5523 'note': 'Youtube music Album',
5524 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5525 'info_dict': {
5526 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5527 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5528 'tags': [],
5529 'view_count': int,
5530 'description': '',
5531 'availability': 'unlisted',
5532 'modified_date': r're:\d{8}',
5533 },
5534 'playlist_count': 50,
5535 }, {
5536 'note': 'unlisted single video playlist',
5537 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5538 'info_dict': {
5539 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5540 'uploader': 'colethedj',
5541 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5542 'title': 'yt-dlp unlisted playlist test',
5543 'availability': 'unlisted',
5544 'tags': [],
5545 'modified_date': '20220418',
5546 'channel': 'colethedj',
5547 'view_count': int,
5548 'description': '',
5549 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5550 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5551 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5552 },
5553 'playlist_count': 1,
5554 }, {
5555 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5556 'url': 'https://www.youtube.com/feed/recommended',
5557 'info_dict': {
5558 'id': 'recommended',
5559 'title': 'recommended',
5560 'tags': [],
5561 },
5562 'playlist_mincount': 50,
5563 'params': {
5564 'skip_download': True,
5565 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5566 },
5567 }, {
5568 'note': 'API Fallback: /videos tab, sorted by oldest first',
5569 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5570 'info_dict': {
5571 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5572 'title': 'Cody\'sLab - Videos',
5573 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5574 'uploader': 'Cody\'sLab',
5575 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5576 'channel': 'Cody\'sLab',
5577 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5578 'tags': [],
5579 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5580 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5581 'channel_follower_count': int
5582 },
5583 'playlist_mincount': 650,
5584 'params': {
5585 'skip_download': True,
5586 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5587 },
5588 }, {
5589 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5590 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5591 'info_dict': {
5592 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5593 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5594 'title': 'Uploads from Royalty Free Music - Topic',
5595 'uploader': 'Royalty Free Music - Topic',
5596 'modified_date': r're:\d{8}',
5597 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5598 'description': '',
5599 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5600 'tags': [],
5601 'channel': 'Royalty Free Music - Topic',
5602 'view_count': int,
5603 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5604 'availability': 'public',
5605 },
5606 'expected_warnings': [
5607 'does not have a videos tab',
5608 r'[Uu]navailable videos (are|will be) hidden',
5609 ],
5610 'playlist_mincount': 101,
5611 'params': {
5612 'skip_download': True,
5613 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5614 },
5615 }, {
5616 'note': 'non-standard redirect to regional channel',
5617 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5618 'only_matching': True
5619 }, {
5620 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5621 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5622 'info_dict': {
5623 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5624 'modified_date': '20220407',
5625 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5626 'tags': [],
5627 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5628 'uploader': 'pukkandan',
5629 'availability': 'unlisted',
5630 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5631 'channel': 'pukkandan',
5632 'description': 'Test for collaborative playlist',
5633 'title': 'yt-dlp test - collaborative playlist',
5634 'view_count': int,
5635 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5636 },
5637 'playlist_mincount': 2
5638 }, {
5639 'note': 'translated tab name',
5640 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5641 'info_dict': {
5642 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5643 'tags': [],
5644 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5645 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5646 'description': '',
5647 'title': 'cole-dlp-test-acc - 再生リスト',
5648 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5649 'uploader': 'cole-dlp-test-acc',
5650 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5651 'channel': 'cole-dlp-test-acc',
5652 },
5653 'playlist_mincount': 1,
5654 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5655 'expected_warnings': ['Preferring "ja"'],
5656 }, {
5657 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5658 'note': 'preferred lang set with playlist with translated video titles',
5659 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5660 'info_dict': {
5661 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5662 'tags': [],
5663 'view_count': int,
5664 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5665 'uploader': 'cole-dlp-test-acc',
5666 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5667 'channel': 'cole-dlp-test-acc',
5668 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5669 'description': 'test',
5670 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5671 'title': 'dlp test playlist',
5672 'availability': 'public',
5673 },
5674 'playlist_mincount': 1,
5675 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5676 'expected_warnings': ['Preferring "ja"'],
5677 }, {
5678 # shorts audio pivot for 2GtVksBMYFM.
5679 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5680 'info_dict': {
5681 'id': 'sfv_audio_pivot',
5682 'title': 'sfv_audio_pivot',
5683 'tags': [],
5684 },
5685 'playlist_mincount': 50,
5686
5687 }]
5688
5689 @classmethod
5690 def suitable(cls, url):
5691 return False if YoutubeIE.suitable(url) else super().suitable(url)
5692
5693 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5694
5695 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5696 def _real_extract(self, url, smuggled_data):
5697 item_id = self._match_id(url)
5698 url = urllib.parse.urlunparse(
5699 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
5700 compat_opts = self.get_param('compat_opts', [])
5701
5702 def get_mobj(url):
5703 mobj = self._URL_RE.match(url).groupdict()
5704 mobj.update((k, '') for k, v in mobj.items() if v is None)
5705 return mobj
5706
5707 mobj, redirect_warning = get_mobj(url), None
5708 # Youtube returns incomplete data if tabname is not lower case
5709 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5710 if is_channel:
5711 if smuggled_data.get('is_music_url'):
5712 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5713 item_id = item_id[2:]
5714 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5715 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5716 mdata = self._extract_tab_endpoint(
5717 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5718 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5719 get_all=False, expected_type=str)
5720 if not murl:
5721 raise ExtractorError('Failed to resolve album to playlist')
5722 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5723 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5724 pre = f'https://www.youtube.com/channel/{item_id}'
5725
5726 original_tab_name = tab
5727 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5728 # Home URLs should redirect to /videos/
5729 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5730 'To download only the videos in the home page, add a "/featured" to the URL')
5731 tab = '/videos'
5732
5733 url = ''.join((pre, tab, post))
5734 mobj = get_mobj(url)
5735
5736 # Handle both video/playlist URLs
5737 qs = parse_qs(url)
5738 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
5739
5740 if not video_id and mobj['not_channel'].startswith('watch'):
5741 if not playlist_id:
5742 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5743 raise ExtractorError('Unable to recognize tab page')
5744 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5745 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5746 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5747 mobj = get_mobj(url)
5748
5749 if video_id and playlist_id:
5750 if self.get_param('noplaylist'):
5751 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5752 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5753 ie=YoutubeIE.ie_key(), video_id=video_id)
5754 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5755
5756 data, ytcfg = self._extract_data(url, item_id)
5757
5758 # YouTube may provide a non-standard redirect to the regional channel
5759 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5760 redirect_url = traverse_obj(
5761 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5762 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5763 redirect_url = ''.join((
5764 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5765 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5766 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5767
5768 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5769 if tabs:
5770 selected_tab = self._extract_selected_tab(tabs)
5771 selected_tab_url = urljoin(
5772 url, traverse_obj(selected_tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5773 translated_tab_name = selected_tab.get('title', '').lower()
5774
5775 # Prefer tab name from tab url as it is always in en,
5776 # but only when preferred lang is set as it may not extract reliably in all cases.
5777 selected_tab_name = (self._preferred_lang in (None, 'en') and translated_tab_name
5778 or selected_tab_url and get_mobj(selected_tab_url)['tab'][1:] # primary
5779 or translated_tab_name)
5780
5781 if selected_tab_name == 'home':
5782 selected_tab_name = 'featured'
5783 requested_tab_name = mobj['tab'][1:]
5784
5785 if 'no-youtube-channel-redirect' not in compat_opts:
5786 if requested_tab_name == 'live': # Live tab should have redirected to the video
5787 raise UserNotLive(video_id=mobj['id'])
5788 if requested_tab_name not in ('', selected_tab_name):
5789 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5790 if not original_tab_name:
5791 if item_id[:2] == 'UC':
5792 # Topic channels don't have /videos. Use the equivalent playlist instead
5793 pl_id = f'UU{item_id[2:]}'
5794 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5795 try:
5796 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5797 except ExtractorError:
5798 redirect_warning += ' and the playlist redirect gave error'
5799 else:
5800 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5801 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5802 if selected_tab_name and selected_tab_name != requested_tab_name:
5803 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5804 else:
5805 raise ExtractorError(redirect_warning, expected=True)
5806
5807 if redirect_warning:
5808 self.to_screen(redirect_warning)
5809 self.write_debug(f'Final URL: {url}')
5810
5811 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5812 if 'no-youtube-unavailable-videos' not in compat_opts:
5813 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5814 self._extract_and_report_alerts(data, only_once=True)
5815 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5816 if tabs:
5817 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5818
5819 playlist = traverse_obj(
5820 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5821 if playlist:
5822 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5823
5824 video_id = traverse_obj(
5825 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5826 if video_id:
5827 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5828 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5829 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5830 ie=YoutubeIE.ie_key(), video_id=video_id)
5831
5832 raise ExtractorError('Unable to recognize tab page')
5833
5834
5835 class YoutubePlaylistIE(InfoExtractor):
5836 IE_DESC = 'YouTube playlists'
5837 _VALID_URL = r'''(?x)(?:
5838 (?:https?://)?
5839 (?:\w+\.)?
5840 (?:
5841 (?:
5842 youtube(?:kids)?\.com|
5843 %(invidious)s
5844 )
5845 /.*?\?.*?\blist=
5846 )?
5847 (?P<id>%(playlist_id)s)
5848 )''' % {
5849 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5850 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5851 }
5852 IE_NAME = 'youtube:playlist'
5853 _TESTS = [{
5854 'note': 'issue #673',
5855 'url': 'PLBB231211A4F62143',
5856 'info_dict': {
5857 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5858 'id': 'PLBB231211A4F62143',
5859 'uploader': 'Wickman',
5860 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5861 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5862 'view_count': int,
5863 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5864 'modified_date': r're:\d{8}',
5865 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5866 'channel': 'Wickman',
5867 'tags': [],
5868 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5869 },
5870 'playlist_mincount': 29,
5871 }, {
5872 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5873 'info_dict': {
5874 'title': 'YDL_safe_search',
5875 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5876 },
5877 'playlist_count': 2,
5878 'skip': 'This playlist is private',
5879 }, {
5880 'note': 'embedded',
5881 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5882 'playlist_count': 4,
5883 'info_dict': {
5884 'title': 'JODA15',
5885 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5886 'uploader': 'milan',
5887 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5888 'description': '',
5889 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5890 'tags': [],
5891 'modified_date': '20140919',
5892 'view_count': int,
5893 'channel': 'milan',
5894 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5895 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5896 'availability': 'public',
5897 },
5898 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5899 }, {
5900 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5901 'playlist_mincount': 455,
5902 'info_dict': {
5903 'title': '2018 Chinese New Singles (11/6 updated)',
5904 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5905 'uploader': 'LBK',
5906 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5907 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5908 'channel': 'LBK',
5909 'view_count': int,
5910 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5911 'tags': [],
5912 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5913 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5914 'modified_date': r're:\d{8}',
5915 'availability': 'public',
5916 },
5917 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5918 }, {
5919 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5920 'only_matching': True,
5921 }, {
5922 # music album playlist
5923 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5924 'only_matching': True,
5925 }]
5926
5927 @classmethod
5928 def suitable(cls, url):
5929 if YoutubeTabIE.suitable(url):
5930 return False
5931 from ..utils import parse_qs
5932 qs = parse_qs(url)
5933 if qs.get('v', [None])[0]:
5934 return False
5935 return super().suitable(url)
5936
5937 def _real_extract(self, url):
5938 playlist_id = self._match_id(url)
5939 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5940 url = update_url_query(
5941 'https://www.youtube.com/playlist',
5942 parse_qs(url) or {'list': playlist_id})
5943 if is_music_url:
5944 url = smuggle_url(url, {'is_music_url': True})
5945 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5946
5947
5948 class YoutubeYtBeIE(InfoExtractor):
5949 IE_DESC = 'youtu.be'
5950 _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}
5951 _TESTS = [{
5952 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5953 'info_dict': {
5954 'id': 'yeWKywCrFtk',
5955 'ext': 'mp4',
5956 'title': 'Small Scale Baler and Braiding Rugs',
5957 'uploader': 'Backus-Page House Museum',
5958 'uploader_id': 'backuspagemuseum',
5959 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5960 'upload_date': '20161008',
5961 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5962 'categories': ['Nonprofits & Activism'],
5963 'tags': list,
5964 'like_count': int,
5965 'age_limit': 0,
5966 'playable_in_embed': True,
5967 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5968 'channel': 'Backus-Page House Museum',
5969 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5970 'live_status': 'not_live',
5971 'view_count': int,
5972 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5973 'availability': 'public',
5974 'duration': 59,
5975 'comment_count': int,
5976 'channel_follower_count': int
5977 },
5978 'params': {
5979 'noplaylist': True,
5980 'skip_download': True,
5981 },
5982 }, {
5983 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5984 'only_matching': True,
5985 }]
5986
5987 def _real_extract(self, url):
5988 mobj = self._match_valid_url(url)
5989 video_id = mobj.group('id')
5990 playlist_id = mobj.group('playlist_id')
5991 return self.url_result(
5992 update_url_query('https://www.youtube.com/watch', {
5993 'v': video_id,
5994 'list': playlist_id,
5995 'feature': 'youtu.be',
5996 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5997
5998
5999 class YoutubeLivestreamEmbedIE(InfoExtractor):
6000 IE_DESC = 'YouTube livestream embeds'
6001 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6002 _TESTS = [{
6003 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6004 'only_matching': True,
6005 }]
6006
6007 def _real_extract(self, url):
6008 channel_id = self._match_id(url)
6009 return self.url_result(
6010 f'https://www.youtube.com/channel/{channel_id}/live',
6011 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6012
6013
6014 class YoutubeYtUserIE(InfoExtractor):
6015 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
6016 IE_NAME = 'youtube:user'
6017 _VALID_URL = r'ytuser:(?P<id>.+)'
6018 _TESTS = [{
6019 'url': 'ytuser:phihag',
6020 'only_matching': True,
6021 }]
6022
6023 def _real_extract(self, url):
6024 user_id = self._match_id(url)
6025 return self.url_result(
6026 'https://www.youtube.com/user/%s/videos' % user_id,
6027 ie=YoutubeTabIE.ie_key(), video_id=user_id)
6028
6029
6030 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
6031 IE_NAME = 'youtube:favorites'
6032 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6033 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6034 _LOGIN_REQUIRED = True
6035 _TESTS = [{
6036 'url': ':ytfav',
6037 'only_matching': True,
6038 }, {
6039 'url': ':ytfavorites',
6040 'only_matching': True,
6041 }]
6042
6043 def _real_extract(self, url):
6044 return self.url_result(
6045 'https://www.youtube.com/playlist?list=LL',
6046 ie=YoutubeTabIE.ie_key())
6047
6048
6049 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6050 IE_NAME = 'youtube:notif'
6051 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6052 _VALID_URL = r':ytnotif(?:ication)?s?'
6053 _LOGIN_REQUIRED = True
6054 _TESTS = [{
6055 'url': ':ytnotif',
6056 'only_matching': True,
6057 }, {
6058 'url': ':ytnotifications',
6059 'only_matching': True,
6060 }]
6061
6062 def _extract_notification_menu(self, response, continuation_list):
6063 notification_list = traverse_obj(
6064 response,
6065 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6066 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6067 expected_type=list) or []
6068 continuation_list[0] = None
6069 for item in notification_list:
6070 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6071 if entry:
6072 yield entry
6073 continuation = item.get('continuationItemRenderer')
6074 if continuation:
6075 continuation_list[0] = continuation
6076
6077 def _extract_notification_renderer(self, notification):
6078 video_id = traverse_obj(
6079 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6080 url = f'https://www.youtube.com/watch?v={video_id}'
6081 channel_id = None
6082 if not video_id:
6083 browse_ep = traverse_obj(
6084 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6085 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6086 post_id = self._search_regex(
6087 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6088 'post id', default=None)
6089 if not channel_id or not post_id:
6090 return
6091 # The direct /post url redirects to this in the browser
6092 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6093
6094 channel = traverse_obj(
6095 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6096 expected_type=str)
6097 notification_title = self._get_text(notification, 'shortMessage')
6098 if notification_title:
6099 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6100 # TODO: handle recommended videos
6101 title = self._search_regex(
6102 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
6103 'video title', default=None)
6104 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6105 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6106 else None)
6107 return {
6108 '_type': 'url',
6109 'url': url,
6110 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6111 'video_id': video_id,
6112 'title': title,
6113 'channel_id': channel_id,
6114 'channel': channel,
6115 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6116 'timestamp': timestamp,
6117 }
6118
6119 def _notification_menu_entries(self, ytcfg):
6120 continuation_list = [None]
6121 response = None
6122 for page in itertools.count(1):
6123 ctoken = traverse_obj(
6124 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6125 response = self._extract_response(
6126 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6127 ep='notification/get_notification_menu', check_get_keys='actions',
6128 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6129 yield from self._extract_notification_menu(response, continuation_list)
6130 if not continuation_list[0]:
6131 break
6132
6133 def _real_extract(self, url):
6134 display_id = 'notifications'
6135 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6136 self._report_playlist_authcheck(ytcfg)
6137 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6138
6139
6140 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6141 IE_DESC = 'YouTube search'
6142 IE_NAME = 'youtube:search'
6143 _SEARCH_KEY = 'ytsearch'
6144 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
6145 _TESTS = [{
6146 'url': 'ytsearch5:youtube-dl test video',
6147 'playlist_count': 5,
6148 'info_dict': {
6149 'id': 'youtube-dl test video',
6150 'title': 'youtube-dl test video',
6151 }
6152 }]
6153
6154
6155 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6156 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
6157 _SEARCH_KEY = 'ytsearchdate'
6158 IE_DESC = 'YouTube search, newest videos first'
6159 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
6160 _TESTS = [{
6161 'url': 'ytsearchdate5:youtube-dl test video',
6162 'playlist_count': 5,
6163 'info_dict': {
6164 'id': 'youtube-dl test video',
6165 'title': 'youtube-dl test video',
6166 }
6167 }]
6168
6169
6170 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
6171 IE_DESC = 'YouTube search URLs with sorting and filter support'
6172 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
6173 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6174 _TESTS = [{
6175 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6176 'playlist_mincount': 5,
6177 'info_dict': {
6178 'id': 'youtube-dl test video',
6179 'title': 'youtube-dl test video',
6180 }
6181 }, {
6182 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6183 'playlist_mincount': 5,
6184 'info_dict': {
6185 'id': 'python',
6186 'title': 'python',
6187 }
6188 }, {
6189 'url': 'https://www.youtube.com/results?search_query=%23cats',
6190 'playlist_mincount': 1,
6191 'info_dict': {
6192 'id': '#cats',
6193 'title': '#cats',
6194 # The test suite does not have support for nested playlists
6195 # 'entries': [{
6196 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6197 # 'title': '#cats',
6198 # }],
6199 },
6200 }, {
6201 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6202 'only_matching': True,
6203 }]
6204
6205 def _real_extract(self, url):
6206 qs = parse_qs(url)
6207 query = (qs.get('search_query') or qs.get('q'))[0]
6208 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
6209
6210
6211 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
6212 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
6213 IE_NAME = 'youtube:music:search_url'
6214 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6215 _TESTS = [{
6216 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6217 'playlist_count': 16,
6218 'info_dict': {
6219 'id': 'royalty free music',
6220 'title': 'royalty free music',
6221 }
6222 }, {
6223 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6224 'playlist_mincount': 30,
6225 'info_dict': {
6226 'id': 'royalty free music - songs',
6227 'title': 'royalty free music - songs',
6228 },
6229 'params': {'extract_flat': 'in_playlist'}
6230 }, {
6231 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6232 'playlist_mincount': 30,
6233 'info_dict': {
6234 'id': 'royalty free music - community playlists',
6235 'title': 'royalty free music - community playlists',
6236 },
6237 'params': {'extract_flat': 'in_playlist'}
6238 }]
6239
6240 _SECTIONS = {
6241 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6242 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6243 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6244 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6245 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6246 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6247 }
6248
6249 def _real_extract(self, url):
6250 qs = parse_qs(url)
6251 query = (qs.get('search_query') or qs.get('q'))[0]
6252 params = qs.get('sp', (None,))[0]
6253 if params:
6254 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6255 else:
6256 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
6257 params = self._SECTIONS.get(section)
6258 if not params:
6259 section = None
6260 title = join_nonempty(query, section, delim=' - ')
6261 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
6262
6263
6264 class YoutubeFeedsInfoExtractor(InfoExtractor):
6265 """
6266 Base class for feed extractors
6267 Subclasses must re-define the _FEED_NAME property.
6268 """
6269 _LOGIN_REQUIRED = True
6270 _FEED_NAME = 'feeds'
6271
6272 def _real_initialize(self):
6273 YoutubeBaseInfoExtractor._check_login_required(self)
6274
6275 @classproperty
6276 def IE_NAME(self):
6277 return f'youtube:{self._FEED_NAME}'
6278
6279 def _real_extract(self, url):
6280 return self.url_result(
6281 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
6282
6283
6284 class YoutubeWatchLaterIE(InfoExtractor):
6285 IE_NAME = 'youtube:watchlater'
6286 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6287 _VALID_URL = r':ytwatchlater'
6288 _TESTS = [{
6289 'url': ':ytwatchlater',
6290 'only_matching': True,
6291 }]
6292
6293 def _real_extract(self, url):
6294 return self.url_result(
6295 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
6296
6297
6298 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
6299 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
6300 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6301 _FEED_NAME = 'recommended'
6302 _LOGIN_REQUIRED = False
6303 _TESTS = [{
6304 'url': ':ytrec',
6305 'only_matching': True,
6306 }, {
6307 'url': ':ytrecommended',
6308 'only_matching': True,
6309 }, {
6310 'url': 'https://youtube.com',
6311 'only_matching': True,
6312 }]
6313
6314
6315 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
6316 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6317 _VALID_URL = r':ytsub(?:scription)?s?'
6318 _FEED_NAME = 'subscriptions'
6319 _TESTS = [{
6320 'url': ':ytsubs',
6321 'only_matching': True,
6322 }, {
6323 'url': ':ytsubscriptions',
6324 'only_matching': True,
6325 }]
6326
6327
6328 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
6329 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
6330 _VALID_URL = r':ythis(?:tory)?'
6331 _FEED_NAME = 'history'
6332 _TESTS = [{
6333 'url': ':ythistory',
6334 'only_matching': True,
6335 }]
6336
6337
6338 class YoutubeStoriesIE(InfoExtractor):
6339 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6340 IE_NAME = 'youtube:stories'
6341 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6342 _TESTS = [{
6343 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6344 'only_matching': True,
6345 }]
6346
6347 def _real_extract(self, url):
6348 playlist_id = f'RLTD{self._match_id(url)}'
6349 return self.url_result(
6350 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6351 ie=YoutubeTabIE, video_id=playlist_id)
6352
6353
6354 class YoutubeShortsAudioPivotIE(InfoExtractor):
6355 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6356 IE_NAME = 'youtube:shorts:pivot:audio'
6357 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6358 _TESTS = [{
6359 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6360 'only_matching': True,
6361 }]
6362
6363 @staticmethod
6364 def _generate_audio_pivot_params(video_id):
6365 """
6366 Generates sfv_audio_pivot browse params for this video id
6367 """
6368 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6369 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6370
6371 def _real_extract(self, url):
6372 video_id = self._match_id(url)
6373 return self.url_result(
6374 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6375 ie=YoutubeTabIE)
6376
6377
6378 class YoutubeTruncatedURLIE(InfoExtractor):
6379 IE_NAME = 'youtube:truncated_url'
6380 IE_DESC = False # Do not list
6381 _VALID_URL = r'''(?x)
6382 (?:https?://)?
6383 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6384 (?:watch\?(?:
6385 feature=[a-z_]+|
6386 annotation_id=annotation_[^&]+|
6387 x-yt-cl=[0-9]+|
6388 hl=[^&]*|
6389 t=[0-9]+
6390 )?
6391 |
6392 attribution_link\?a=[^&]+
6393 )
6394 $
6395 '''
6396
6397 _TESTS = [{
6398 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6399 'only_matching': True,
6400 }, {
6401 'url': 'https://www.youtube.com/watch?',
6402 'only_matching': True,
6403 }, {
6404 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6405 'only_matching': True,
6406 }, {
6407 'url': 'https://www.youtube.com/watch?feature=foo',
6408 'only_matching': True,
6409 }, {
6410 'url': 'https://www.youtube.com/watch?hl=en-GB',
6411 'only_matching': True,
6412 }, {
6413 'url': 'https://www.youtube.com/watch?t=2372',
6414 'only_matching': True,
6415 }]
6416
6417 def _real_extract(self, url):
6418 raise ExtractorError(
6419 'Did you forget to quote the URL? Remember that & is a meta '
6420 'character in most shells, so you want to put the URL in quotes, '
6421 'like youtube-dl '
6422 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6423 ' or simply youtube-dl BaW_jenozKc .',
6424 expected=True)
6425
6426
6427 class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6428 IE_NAME = 'youtube:clip'
6429 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6430 _TESTS = [{
6431 # FIXME: Other metadata should be extracted from the clip, not from the base video
6432 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6433 'info_dict': {
6434 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6435 'ext': 'mp4',
6436 'section_start': 29.0,
6437 'section_end': 39.7,
6438 'duration': 10.7,
6439 'age_limit': 0,
6440 'availability': 'public',
6441 'categories': ['Gaming'],
6442 'channel': 'Scott The Woz',
6443 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6444 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6445 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6446 'like_count': int,
6447 'playable_in_embed': True,
6448 'tags': 'count:17',
6449 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6450 'title': 'Mobile Games on Console - Scott The Woz',
6451 'upload_date': '20210920',
6452 'uploader': 'Scott The Woz',
6453 'uploader_id': 'scottthewoz',
6454 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6455 'view_count': int,
6456 'live_status': 'not_live',
6457 'channel_follower_count': int
6458 }
6459 }]
6460
6461 def _real_extract(self, url):
6462 clip_id = self._match_id(url)
6463 _, data = self._extract_webpage(url, clip_id)
6464
6465 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6466 if not video_id:
6467 raise ExtractorError('Unable to find video ID')
6468
6469 clip_data = traverse_obj(data, (
6470 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6471 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6472 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6473 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6474
6475 return {
6476 '_type': 'url_transparent',
6477 'url': f'https://www.youtube.com/watch?v={video_id}',
6478 'ie_key': YoutubeIE.ie_key(),
6479 'id': clip_id,
6480 'section_start': int(clip_data['startTimeMs']) / 1000,
6481 'section_end': int(clip_data['endTimeMs']) / 1000,
6482 }
6483
6484
6485 class YoutubeTruncatedIDIE(InfoExtractor):
6486 IE_NAME = 'youtube:truncated_id'
6487 IE_DESC = False # Do not list
6488 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6489
6490 _TESTS = [{
6491 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6492 'only_matching': True,
6493 }]
6494
6495 def _real_extract(self, url):
6496 video_id = self._match_id(url)
6497 raise ExtractorError(
6498 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
6499 expected=True)