]> jfr.im git - yt-dlp.git/blame_incremental - yt_dlp/extractor/youtube.py
[metadataparser] Don't set `None` when the field didn't match
[yt-dlp.git] / yt_dlp / extractor / youtube.py
... / ...
CommitLineData
1import base64
2import calendar
3import copy
4import datetime
5import hashlib
6import itertools
7import json
8import math
9import os.path
10import random
11import re
12import sys
13import threading
14import time
15import traceback
16import urllib.error
17import urllib.parse
18
19from .common import InfoExtractor, SearchInfoExtractor
20from ..compat import functools
21from ..jsinterp import JSInterpreter
22from ..utils import (
23 NO_DEFAULT,
24 ExtractorError,
25 UserNotLive,
26 bug_reports_message,
27 classproperty,
28 clean_html,
29 datetime_from_str,
30 dict_get,
31 error_to_compat_str,
32 float_or_none,
33 format_field,
34 get_first,
35 int_or_none,
36 is_html,
37 join_nonempty,
38 js_to_json,
39 mimetype2ext,
40 network_exceptions,
41 orderedSet,
42 parse_codecs,
43 parse_count,
44 parse_duration,
45 parse_iso8601,
46 parse_qs,
47 qualities,
48 remove_end,
49 remove_start,
50 smuggle_url,
51 str_or_none,
52 str_to_int,
53 strftime_or_none,
54 traverse_obj,
55 try_get,
56 unescapeHTML,
57 unified_strdate,
58 unified_timestamp,
59 unsmuggle_url,
60 update_url_query,
61 url_or_none,
62 urljoin,
63 variadic,
64)
65
66# any clients starting with _ cannot be explicitly requested by the user
67INNERTUBE_CLIENTS = {
68 'web': {
69 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
70 'INNERTUBE_CONTEXT': {
71 'client': {
72 'clientName': 'WEB',
73 'clientVersion': '2.20211221.00.00',
74 }
75 },
76 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
77 },
78 'web_embedded': {
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
81 'client': {
82 'clientName': 'WEB_EMBEDDED_PLAYER',
83 'clientVersion': '1.20211215.00.01',
84 },
85 },
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
87 },
88 'web_music': {
89 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
90 'INNERTUBE_HOST': 'music.youtube.com',
91 'INNERTUBE_CONTEXT': {
92 'client': {
93 'clientName': 'WEB_REMIX',
94 'clientVersion': '1.20211213.00.00',
95 }
96 },
97 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
98 },
99 'web_creator': {
100 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
101 'INNERTUBE_CONTEXT': {
102 'client': {
103 'clientName': 'WEB_CREATOR',
104 'clientVersion': '1.20211220.02.00',
105 }
106 },
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
108 },
109 'android': {
110 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
111 'INNERTUBE_CONTEXT': {
112 'client': {
113 'clientName': 'ANDROID',
114 'clientVersion': '16.49',
115 }
116 },
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
118 'REQUIRE_JS_PLAYER': False
119 },
120 'android_embedded': {
121 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
122 'INNERTUBE_CONTEXT': {
123 'client': {
124 'clientName': 'ANDROID_EMBEDDED_PLAYER',
125 'clientVersion': '16.49',
126 },
127 },
128 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
129 'REQUIRE_JS_PLAYER': False
130 },
131 'android_music': {
132 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
133 'INNERTUBE_CONTEXT': {
134 'client': {
135 'clientName': 'ANDROID_MUSIC',
136 'clientVersion': '4.57',
137 }
138 },
139 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
140 'REQUIRE_JS_PLAYER': False
141 },
142 'android_creator': {
143 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
144 'INNERTUBE_CONTEXT': {
145 'client': {
146 'clientName': 'ANDROID_CREATOR',
147 'clientVersion': '21.47',
148 },
149 },
150 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
151 'REQUIRE_JS_PLAYER': False
152 },
153 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
154 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
155 'ios': {
156 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
157 'INNERTUBE_CONTEXT': {
158 'client': {
159 'clientName': 'IOS',
160 'clientVersion': '16.46',
161 'deviceModel': 'iPhone14,3',
162 }
163 },
164 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
165 'REQUIRE_JS_PLAYER': False
166 },
167 'ios_embedded': {
168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS_MESSAGES_EXTENSION',
171 'clientVersion': '16.46',
172 'deviceModel': 'iPhone14,3',
173 },
174 },
175 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
176 'REQUIRE_JS_PLAYER': False
177 },
178 'ios_music': {
179 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MUSIC',
183 'clientVersion': '4.57',
184 },
185 },
186 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
187 'REQUIRE_JS_PLAYER': False
188 },
189 'ios_creator': {
190 'INNERTUBE_CONTEXT': {
191 'client': {
192 'clientName': 'IOS_CREATOR',
193 'clientVersion': '21.47',
194 },
195 },
196 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
197 'REQUIRE_JS_PLAYER': False
198 },
199 # mweb has 'ultralow' formats
200 # See: https://github.com/yt-dlp/yt-dlp/pull/557
201 'mweb': {
202 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
203 'INNERTUBE_CONTEXT': {
204 'client': {
205 'clientName': 'MWEB',
206 'clientVersion': '2.20211221.01.00',
207 }
208 },
209 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
210 },
211 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
212 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
213 'tv_embedded': {
214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
215 'INNERTUBE_CONTEXT': {
216 'client': {
217 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
218 'clientVersion': '2.0',
219 },
220 },
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
222 },
223}
224
225
226def _split_innertube_client(client_name):
227 variant, *base = client_name.rsplit('.', 1)
228 if base:
229 return variant, base[0], variant
230 base, *variant = client_name.split('_', 1)
231 return client_name, base, variant[0] if variant else None
232
233
234def build_innertube_clients():
235 THIRD_PARTY = {
236 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
237 }
238 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
239 priority = qualities(BASE_CLIENTS[::-1])
240
241 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
242 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
243 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
244 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
245 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
246
247 _, base_client, variant = _split_innertube_client(client)
248 ytcfg['priority'] = 10 * priority(base_client)
249
250 if not variant:
251 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
252 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
253 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
254 embedscreen['priority'] -= 3
255 elif variant == 'embedded':
256 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
257 ytcfg['priority'] -= 2
258 else:
259 ytcfg['priority'] -= 3
260
261
262build_innertube_clients()
263
264
265class YoutubeBaseInfoExtractor(InfoExtractor):
266 """Provide base functions for Youtube extractors"""
267
268 _RESERVED_NAMES = (
269 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
270 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
271 r'browse|oembed|get_video_info|iframe_api|s/player|'
272 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
273
274 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
275
276 # _NETRC_MACHINE = 'youtube'
277
278 # If True it will raise an error if no login info is provided
279 _LOGIN_REQUIRED = False
280
281 _INVIDIOUS_SITES = (
282 # invidious-redirect websites
283 r'(?:www\.)?redirect\.invidious\.io',
284 r'(?:(?:www|dev)\.)?invidio\.us',
285 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
286 r'(?:www\.)?invidious\.pussthecat\.org',
287 r'(?:www\.)?invidious\.zee\.li',
288 r'(?:www\.)?invidious\.ethibox\.fr',
289 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
290 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
291 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
292 # youtube-dl invidious instances list
293 r'(?:(?:www|no)\.)?invidiou\.sh',
294 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
295 r'(?:www\.)?invidious\.kabi\.tk',
296 r'(?:www\.)?invidious\.mastodon\.host',
297 r'(?:www\.)?invidious\.zapashcanon\.fr',
298 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
299 r'(?:www\.)?invidious\.tinfoil-hat\.net',
300 r'(?:www\.)?invidious\.himiko\.cloud',
301 r'(?:www\.)?invidious\.reallyancient\.tech',
302 r'(?:www\.)?invidious\.tube',
303 r'(?:www\.)?invidiou\.site',
304 r'(?:www\.)?invidious\.site',
305 r'(?:www\.)?invidious\.xyz',
306 r'(?:www\.)?invidious\.nixnet\.xyz',
307 r'(?:www\.)?invidious\.048596\.xyz',
308 r'(?:www\.)?invidious\.drycat\.fr',
309 r'(?:www\.)?inv\.skyn3t\.in',
310 r'(?:www\.)?tube\.poal\.co',
311 r'(?:www\.)?tube\.connect\.cafe',
312 r'(?:www\.)?vid\.wxzm\.sx',
313 r'(?:www\.)?vid\.mint\.lgbt',
314 r'(?:www\.)?vid\.puffyan\.us',
315 r'(?:www\.)?yewtu\.be',
316 r'(?:www\.)?yt\.elukerio\.org',
317 r'(?:www\.)?yt\.lelux\.fi',
318 r'(?:www\.)?invidious\.ggc-project\.de',
319 r'(?:www\.)?yt\.maisputain\.ovh',
320 r'(?:www\.)?ytprivate\.com',
321 r'(?:www\.)?invidious\.13ad\.de',
322 r'(?:www\.)?invidious\.toot\.koeln',
323 r'(?:www\.)?invidious\.fdn\.fr',
324 r'(?:www\.)?watch\.nettohikari\.com',
325 r'(?:www\.)?invidious\.namazso\.eu',
326 r'(?:www\.)?invidious\.silkky\.cloud',
327 r'(?:www\.)?invidious\.exonip\.de',
328 r'(?:www\.)?invidious\.riverside\.rocks',
329 r'(?:www\.)?invidious\.blamefran\.net',
330 r'(?:www\.)?invidious\.moomoo\.de',
331 r'(?:www\.)?ytb\.trom\.tf',
332 r'(?:www\.)?yt\.cyberhost\.uk',
333 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
334 r'(?:www\.)?qklhadlycap4cnod\.onion',
335 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
336 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
337 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
338 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
339 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
340 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
341 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
342 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
343 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
344 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
345 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
346 r'(?:www\.)?piped\.kavin\.rocks',
347 r'(?:www\.)?piped\.silkky\.cloud',
348 r'(?:www\.)?piped\.tokhmi\.xyz',
349 r'(?:www\.)?piped\.moomoo\.me',
350 r'(?:www\.)?il\.ax',
351 r'(?:www\.)?piped\.syncpundit\.com',
352 r'(?:www\.)?piped\.mha\.fi',
353 r'(?:www\.)?piped\.mint\.lgbt',
354 r'(?:www\.)?piped\.privacy\.com\.de',
355 )
356
357 def _initialize_consent(self):
358 cookies = self._get_cookies('https://www.youtube.com/')
359 if cookies.get('__Secure-3PSID'):
360 return
361 consent_id = None
362 consent = cookies.get('CONSENT')
363 if consent:
364 if 'YES' in consent.value:
365 return
366 consent_id = self._search_regex(
367 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
368 if not consent_id:
369 consent_id = random.randint(100, 999)
370 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
371
372 def _initialize_pref(self):
373 cookies = self._get_cookies('https://www.youtube.com/')
374 pref_cookie = cookies.get('PREF')
375 pref = {}
376 if pref_cookie:
377 try:
378 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
379 except ValueError:
380 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
381 pref.update({'hl': 'en', 'tz': 'UTC'})
382 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
383
384 def _real_initialize(self):
385 self._initialize_pref()
386 self._initialize_consent()
387 self._check_login_required()
388
389 def _check_login_required(self):
390 if self._LOGIN_REQUIRED and not self._cookies_passed:
391 self.raise_login_required('Login details are needed to download this content', method='cookies')
392
393 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
394 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
395
396 def _get_default_ytcfg(self, client='web'):
397 return copy.deepcopy(INNERTUBE_CLIENTS[client])
398
399 def _get_innertube_host(self, client='web'):
400 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
401
402 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
403 # try_get but with fallback to default ytcfg client values when present
404 _func = lambda y: try_get(y, getter, expected_type)
405 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
406
407 def _extract_client_name(self, ytcfg, default_client='web'):
408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
411
412 def _extract_client_version(self, ytcfg, default_client='web'):
413 return self._ytcfg_get_safe(
414 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
415 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
416
417 def _select_api_hostname(self, req_api_hostname, default_client=None):
418 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
419 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
420
421 def _extract_api_key(self, ytcfg=None, default_client='web'):
422 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
423
424 def _extract_context(self, ytcfg=None, default_client='web'):
425 context = get_first(
426 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
427 # Enforce language and tz for extraction
428 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
429 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
430 return context
431
432 _SAPISID = None
433
434 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
435 time_now = round(time.time())
436 if self._SAPISID is None:
437 yt_cookies = self._get_cookies('https://www.youtube.com')
438 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
439 # See: https://github.com/yt-dlp/yt-dlp/issues/393
440 sapisid_cookie = dict_get(
441 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
442 if sapisid_cookie and sapisid_cookie.value:
443 self._SAPISID = sapisid_cookie.value
444 self.write_debug('Extracted SAPISID cookie')
445 # SAPISID cookie is required if not already present
446 if not yt_cookies.get('SAPISID'):
447 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
448 self._set_cookie(
449 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
450 else:
451 self._SAPISID = False
452 if not self._SAPISID:
453 return None
454 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
455 sapisidhash = hashlib.sha1(
456 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
457 return f'SAPISIDHASH {time_now}_{sapisidhash}'
458
459 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
460 note='Downloading API JSON', errnote='Unable to download API page',
461 context=None, api_key=None, api_hostname=None, default_client='web'):
462
463 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
464 data.update(query)
465 real_headers = self.generate_api_headers(default_client=default_client)
466 real_headers.update({'content-type': 'application/json'})
467 if headers:
468 real_headers.update(headers)
469 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
470 or api_key or self._extract_api_key(default_client=default_client))
471 return self._download_json(
472 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
473 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
474 data=json.dumps(data).encode('utf8'), headers=real_headers,
475 query={'key': api_key, 'prettyPrint': 'false'})
476
477 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
478 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
479
480 @staticmethod
481 def _extract_session_index(*data):
482 """
483 Index of current account in account list.
484 See: https://github.com/yt-dlp/yt-dlp/pull/519
485 """
486 for ytcfg in data:
487 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
488 if session_index is not None:
489 return session_index
490
491 # Deprecated?
492 def _extract_identity_token(self, ytcfg=None, webpage=None):
493 if ytcfg:
494 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
495 if token:
496 return token
497 if webpage:
498 return self._search_regex(
499 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
500 'identity token', default=None, fatal=False)
501
502 @staticmethod
503 def _extract_account_syncid(*args):
504 """
505 Extract syncId required to download private playlists of secondary channels
506 @params response and/or ytcfg
507 """
508 for data in args:
509 # ytcfg includes channel_syncid if on secondary channel
510 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
511 if delegated_sid:
512 return delegated_sid
513 sync_ids = (try_get(
514 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
515 lambda x: x['DATASYNC_ID']), str) or '').split('||')
516 if len(sync_ids) >= 2 and sync_ids[1]:
517 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
518 # and just "user_syncid||" for primary channel. We only want the channel_syncid
519 return sync_ids[0]
520
521 @staticmethod
522 def _extract_visitor_data(*args):
523 """
524 Extracts visitorData from an API response or ytcfg
525 Appears to be used to track session state
526 """
527 return get_first(
528 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
529 expected_type=str)
530
531 @functools.cached_property
532 def is_authenticated(self):
533 return bool(self._generate_sapisidhash_header())
534
535 def extract_ytcfg(self, video_id, webpage):
536 if not webpage:
537 return {}
538 return self._parse_json(
539 self._search_regex(
540 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
541 default='{}'), video_id, fatal=False) or {}
542
543 def generate_api_headers(
544 self, *, ytcfg=None, account_syncid=None, session_index=None,
545 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
546
547 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
548 headers = {
549 'X-YouTube-Client-Name': str(
550 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
551 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
552 'Origin': origin,
553 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
554 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
555 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
556 }
557 if session_index is None:
558 session_index = self._extract_session_index(ytcfg)
559 if account_syncid or session_index is not None:
560 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
561
562 auth = self._generate_sapisidhash_header(origin)
563 if auth is not None:
564 headers['Authorization'] = auth
565 headers['X-Origin'] = origin
566 return {h: v for h, v in headers.items() if v is not None}
567
568 def _download_ytcfg(self, client, video_id):
569 url = {
570 'web': 'https://www.youtube.com',
571 'web_music': 'https://music.youtube.com',
572 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
573 }.get(client)
574 if not url:
575 return {}
576 webpage = self._download_webpage(
577 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
578 return self.extract_ytcfg(video_id, webpage) or {}
579
580 @staticmethod
581 def _build_api_continuation_query(continuation, ctp=None):
582 query = {
583 'continuation': continuation
584 }
585 # TODO: Inconsistency with clickTrackingParams.
586 # Currently we have a fixed ctp contained within context (from ytcfg)
587 # and a ctp in root query for continuation.
588 if ctp:
589 query['clickTracking'] = {'clickTrackingParams': ctp}
590 return query
591
592 @classmethod
593 def _extract_next_continuation_data(cls, renderer):
594 next_continuation = try_get(
595 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
596 lambda x: x['continuation']['reloadContinuationData']), dict)
597 if not next_continuation:
598 return
599 continuation = next_continuation.get('continuation')
600 if not continuation:
601 return
602 ctp = next_continuation.get('clickTrackingParams')
603 return cls._build_api_continuation_query(continuation, ctp)
604
605 @classmethod
606 def _extract_continuation_ep_data(cls, continuation_ep: dict):
607 if isinstance(continuation_ep, dict):
608 continuation = try_get(
609 continuation_ep, lambda x: x['continuationCommand']['token'], str)
610 if not continuation:
611 return
612 ctp = continuation_ep.get('clickTrackingParams')
613 return cls._build_api_continuation_query(continuation, ctp)
614
615 @classmethod
616 def _extract_continuation(cls, renderer):
617 next_continuation = cls._extract_next_continuation_data(renderer)
618 if next_continuation:
619 return next_continuation
620
621 contents = []
622 for key in ('contents', 'items'):
623 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
624
625 for content in contents:
626 if not isinstance(content, dict):
627 continue
628 continuation_ep = try_get(
629 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
630 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
631 dict)
632 continuation = cls._extract_continuation_ep_data(continuation_ep)
633 if continuation:
634 return continuation
635
636 @classmethod
637 def _extract_alerts(cls, data):
638 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
639 if not isinstance(alert_dict, dict):
640 continue
641 for alert in alert_dict.values():
642 alert_type = alert.get('type')
643 if not alert_type:
644 continue
645 message = cls._get_text(alert, 'text')
646 if message:
647 yield alert_type, message
648
649 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
650 errors = []
651 warnings = []
652 for alert_type, alert_message in alerts:
653 if alert_type.lower() == 'error' and fatal:
654 errors.append([alert_type, alert_message])
655 else:
656 warnings.append([alert_type, alert_message])
657
658 for alert_type, alert_message in (warnings + errors[:-1]):
659 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
660 if errors:
661 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
662
663 def _extract_and_report_alerts(self, data, *args, **kwargs):
664 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
665
666 def _extract_badges(self, renderer: dict):
667 badges = set()
668 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
669 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
670 if label:
671 badges.add(label.lower())
672 return badges
673
674 @staticmethod
675 def _get_text(data, *path_list, max_runs=None):
676 for path in path_list or [None]:
677 if path is None:
678 obj = [data]
679 else:
680 obj = traverse_obj(data, path, default=[])
681 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
682 obj = [obj]
683 for item in obj:
684 text = try_get(item, lambda x: x['simpleText'], str)
685 if text:
686 return text
687 runs = try_get(item, lambda x: x['runs'], list) or []
688 if not runs and isinstance(item, list):
689 runs = item
690
691 runs = runs[:min(len(runs), max_runs or len(runs))]
692 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
693 if text:
694 return text
695
696 def _get_count(self, data, *path_list):
697 count_text = self._get_text(data, *path_list) or ''
698 count = parse_count(count_text)
699 if count is None:
700 count = str_to_int(
701 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
702 return count
703
704 @staticmethod
705 def _extract_thumbnails(data, *path_list):
706 """
707 Extract thumbnails from thumbnails dict
708 @param path_list: path list to level that contains 'thumbnails' key
709 """
710 thumbnails = []
711 for path in path_list or [()]:
712 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
713 thumbnail_url = url_or_none(thumbnail.get('url'))
714 if not thumbnail_url:
715 continue
716 # Sometimes youtube gives a wrong thumbnail URL. See:
717 # https://github.com/yt-dlp/yt-dlp/issues/233
718 # https://github.com/ytdl-org/youtube-dl/issues/28023
719 if 'maxresdefault' in thumbnail_url:
720 thumbnail_url = thumbnail_url.split('?')[0]
721 thumbnails.append({
722 'url': thumbnail_url,
723 'height': int_or_none(thumbnail.get('height')),
724 'width': int_or_none(thumbnail.get('width')),
725 })
726 return thumbnails
727
728 @staticmethod
729 def extract_relative_time(relative_time_text):
730 """
731 Extracts a relative time from string and converts to dt object
732 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
733 """
734 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)
735 if mobj:
736 start = mobj.group('start')
737 if start:
738 return datetime_from_str(start)
739 try:
740 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
741 except ValueError:
742 return None
743
744 def _extract_time_text(self, renderer, *path_list):
745 """@returns (timestamp, time_text)"""
746 text = self._get_text(renderer, *path_list) or ''
747 dt = self.extract_relative_time(text)
748 timestamp = None
749 if isinstance(dt, datetime.datetime):
750 timestamp = calendar.timegm(dt.timetuple())
751
752 if timestamp is None:
753 timestamp = (
754 unified_timestamp(text) or unified_timestamp(
755 self._search_regex(
756 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
757 text.lower(), 'time text', default=None)))
758
759 if text and timestamp is None:
760 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
761 return timestamp, text
762
763 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
764 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
765 default_client='web'):
766 response = None
767 last_error = None
768 count = -1
769 retries = self.get_param('extractor_retries', 3)
770 if check_get_keys is None:
771 check_get_keys = []
772 while count < retries:
773 count += 1
774 if last_error:
775 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
776 try:
777 response = self._call_api(
778 ep=ep, fatal=True, headers=headers,
779 video_id=item_id, query=query,
780 context=self._extract_context(ytcfg, default_client),
781 api_key=self._extract_api_key(ytcfg, default_client),
782 api_hostname=api_hostname, default_client=default_client,
783 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
784 except ExtractorError as e:
785 if isinstance(e.cause, network_exceptions):
786 if isinstance(e.cause, urllib.error.HTTPError):
787 first_bytes = e.cause.read(512)
788 if not is_html(first_bytes):
789 yt_error = try_get(
790 self._parse_json(
791 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
792 lambda x: x['error']['message'], str)
793 if yt_error:
794 self._report_alerts([('ERROR', yt_error)], fatal=False)
795 # Downloading page may result in intermittent 5xx HTTP error
796 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
797 # We also want to catch all other network exceptions since errors in later pages can be troublesome
798 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
799 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
800 last_error = error_to_compat_str(e.cause or e.msg)
801 if count < retries:
802 continue
803 if fatal:
804 raise
805 else:
806 self.report_warning(error_to_compat_str(e))
807 return
808
809 else:
810 try:
811 self._extract_and_report_alerts(response, only_once=True)
812 except ExtractorError as e:
813 # YouTube servers may return errors we want to retry on in a 200 OK response
814 # See: https://github.com/yt-dlp/yt-dlp/issues/839
815 if 'unknown error' in e.msg.lower():
816 last_error = e.msg
817 continue
818 if fatal:
819 raise
820 self.report_warning(error_to_compat_str(e))
821 return
822 if not check_get_keys or dict_get(response, check_get_keys):
823 break
824 # Youtube sometimes sends incomplete data
825 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
826 last_error = 'Incomplete data received'
827 if count >= retries:
828 if fatal:
829 raise ExtractorError(last_error)
830 else:
831 self.report_warning(last_error)
832 return
833 return response
834
835 @staticmethod
836 def is_music_url(url):
837 return re.match(r'https?://music\.youtube\.com/', url) is not None
838
839 def _extract_video(self, renderer):
840 video_id = renderer.get('videoId')
841 title = self._get_text(renderer, 'title')
842 description = self._get_text(renderer, 'descriptionSnippet')
843 duration = parse_duration(self._get_text(
844 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
845 if duration is None:
846 duration = parse_duration(self._search_regex(
847 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
848 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
849 video_id, default=None, group='duration'))
850
851 view_count = self._get_count(renderer, 'viewCountText')
852
853 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
854 channel_id = traverse_obj(
855 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
856 expected_type=str, get_all=False)
857 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
858 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
859 overlay_style = traverse_obj(
860 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
861 get_all=False, expected_type=str)
862 badges = self._extract_badges(renderer)
863 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
864 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
865 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
866 expected_type=str)) or ''
867 url = f'https://www.youtube.com/watch?v={video_id}'
868 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
869 url = f'https://www.youtube.com/shorts/{video_id}'
870
871 return {
872 '_type': 'url',
873 'ie_key': YoutubeIE.ie_key(),
874 'id': video_id,
875 'url': url,
876 'title': title,
877 'description': description,
878 'duration': duration,
879 'view_count': view_count,
880 'uploader': uploader,
881 'channel_id': channel_id,
882 'thumbnails': thumbnails,
883 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
884 if self._configuration_arg('approximate_date', ie_key='youtubetab')
885 else None),
886 'live_status': ('is_upcoming' if scheduled_timestamp is not None
887 else 'was_live' if 'streamed' in time_text.lower()
888 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
889 else None),
890 'release_timestamp': scheduled_timestamp,
891 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
892 }
893
894
895class YoutubeIE(YoutubeBaseInfoExtractor):
896 IE_DESC = 'YouTube'
897 _VALID_URL = r"""(?x)^
898 (
899 (?:https?://|//) # http(s):// or protocol-independent URL
900 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
901 (?:www\.)?deturl\.com/www\.youtube\.com|
902 (?:www\.)?pwnyoutube\.com|
903 (?:www\.)?hooktube\.com|
904 (?:www\.)?yourepeat\.com|
905 tube\.majestyc\.net|
906 %(invidious)s|
907 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
908 (?:.*?\#/)? # handle anchor (#/) redirect urls
909 (?: # the various things that can precede the ID:
910 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
911 |(?: # or the v= param in all its forms
912 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
913 (?:\?|\#!?) # the params delimiter ? or # or #!
914 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
915 v=
916 )
917 ))
918 |(?:
919 youtu\.be| # just youtu.be/xxxx
920 vid\.plus| # or vid.plus/xxxx
921 zwearz\.com/watch| # or zwearz.com/watch/xxxx
922 %(invidious)s
923 )/
924 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
925 )
926 )? # all until now is optional -> you can pass the naked ID
927 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
928 (?(1).+)? # if we found the ID, everything can follow
929 (?:\#|$)""" % {
930 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
931 }
932 _PLAYER_INFO_RE = (
933 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
934 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$',
935 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
936 )
937 _formats = {
938 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
939 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
940 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
941 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
942 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
943 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
944 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
945 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
946 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
947 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
948 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
949 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
950 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
951 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
952 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
953 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
954 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
955 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
956
957
958 # 3D videos
959 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
960 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
961 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
962 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
963 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
964 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
965 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
966
967 # Apple HTTP Live Streaming
968 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
969 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
970 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
971 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
972 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
973 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
974 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
975 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
976
977 # DASH mp4 video
978 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
979 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
983 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
984 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
985 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
988 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
989 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
990
991 # Dash mp4 audio
992 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
993 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
994 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
995 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
996 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
997 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
998 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
999
1000 # Dash webm
1001 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1003 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1004 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1005 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1006 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1007 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1008 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1015 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1017 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1019 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1020 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1021 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1023
1024 # Dash webm audio
1025 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1026 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1027
1028 # Dash webm audio with opus inside
1029 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1030 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1031 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1032
1033 # RTMP (unnamed)
1034 '_rtmp': {'protocol': 'rtmp'},
1035
1036 # av01 video only formats sometimes served with "unknown" codecs
1037 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1038 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1039 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1040 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1041 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1042 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1043 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1044 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1045 }
1046 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1047
1048 _GEO_BYPASS = False
1049
1050 IE_NAME = 'youtube'
1051 _TESTS = [
1052 {
1053 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1054 'info_dict': {
1055 'id': 'BaW_jenozKc',
1056 'ext': 'mp4',
1057 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1058 'uploader': 'Philipp Hagemeister',
1059 'uploader_id': 'phihag',
1060 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1061 'channel': 'Philipp Hagemeister',
1062 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1063 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1064 'upload_date': '20121002',
1065 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1066 'categories': ['Science & Technology'],
1067 'tags': ['youtube-dl'],
1068 'duration': 10,
1069 'view_count': int,
1070 'like_count': int,
1071 'availability': 'public',
1072 'playable_in_embed': True,
1073 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1074 'live_status': 'not_live',
1075 'age_limit': 0,
1076 'start_time': 1,
1077 'end_time': 9,
1078 'comment_count': int,
1079 'channel_follower_count': int
1080 }
1081 },
1082 {
1083 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1084 'note': 'Embed-only video (#1746)',
1085 'info_dict': {
1086 'id': 'yZIXLfi8CZQ',
1087 'ext': 'mp4',
1088 'upload_date': '20120608',
1089 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1090 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1091 'uploader': 'SET India',
1092 'uploader_id': 'setindia',
1093 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1094 'age_limit': 18,
1095 },
1096 'skip': 'Private video',
1097 },
1098 {
1099 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1100 'note': 'Use the first video ID in the URL',
1101 'info_dict': {
1102 'id': 'BaW_jenozKc',
1103 'ext': 'mp4',
1104 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1105 'uploader': 'Philipp Hagemeister',
1106 'uploader_id': 'phihag',
1107 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1108 'channel': 'Philipp Hagemeister',
1109 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1110 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1111 'upload_date': '20121002',
1112 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1113 'categories': ['Science & Technology'],
1114 'tags': ['youtube-dl'],
1115 'duration': 10,
1116 'view_count': int,
1117 'like_count': int,
1118 'availability': 'public',
1119 'playable_in_embed': True,
1120 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1121 'live_status': 'not_live',
1122 'age_limit': 0,
1123 'comment_count': int,
1124 'channel_follower_count': int
1125 },
1126 'params': {
1127 'skip_download': True,
1128 },
1129 },
1130 {
1131 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1132 'note': '256k DASH audio (format 141) via DASH manifest',
1133 'info_dict': {
1134 'id': 'a9LDPn-MO4I',
1135 'ext': 'm4a',
1136 'upload_date': '20121002',
1137 'uploader_id': '8KVIDEO',
1138 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1139 'description': '',
1140 'uploader': '8KVIDEO',
1141 'title': 'UHDTV TEST 8K VIDEO.mp4'
1142 },
1143 'params': {
1144 'youtube_include_dash_manifest': True,
1145 'format': '141',
1146 },
1147 'skip': 'format 141 not served anymore',
1148 },
1149 # DASH manifest with encrypted signature
1150 {
1151 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1152 'info_dict': {
1153 'id': 'IB3lcPjvWLA',
1154 'ext': 'm4a',
1155 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1156 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1157 'duration': 244,
1158 'uploader': 'AfrojackVEVO',
1159 'uploader_id': 'AfrojackVEVO',
1160 'upload_date': '20131011',
1161 'abr': 129.495,
1162 'like_count': int,
1163 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1164 'playable_in_embed': True,
1165 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1166 'view_count': int,
1167 'track': 'The Spark',
1168 'live_status': 'not_live',
1169 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1170 'channel': 'Afrojack',
1171 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1172 'tags': 'count:19',
1173 'availability': 'public',
1174 'categories': ['Music'],
1175 'age_limit': 0,
1176 'alt_title': 'The Spark',
1177 'channel_follower_count': int
1178 },
1179 'params': {
1180 'youtube_include_dash_manifest': True,
1181 'format': '141/bestaudio[ext=m4a]',
1182 },
1183 },
1184 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1185 {
1186 'note': 'Embed allowed age-gate video',
1187 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1188 'info_dict': {
1189 'id': 'HtVdAasjOgU',
1190 'ext': 'mp4',
1191 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1192 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1193 'duration': 142,
1194 'uploader': 'The Witcher',
1195 'uploader_id': 'WitcherGame',
1196 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1197 'upload_date': '20140605',
1198 'age_limit': 18,
1199 'categories': ['Gaming'],
1200 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1201 'availability': 'needs_auth',
1202 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1203 'like_count': int,
1204 'channel': 'The Witcher',
1205 'live_status': 'not_live',
1206 'tags': 'count:17',
1207 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1208 'playable_in_embed': True,
1209 'view_count': int,
1210 'channel_follower_count': int
1211 },
1212 },
1213 {
1214 'note': 'Age-gate video with embed allowed in public site',
1215 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1216 'info_dict': {
1217 'id': 'HsUATh_Nc2U',
1218 'ext': 'mp4',
1219 'title': 'Godzilla 2 (Official Video)',
1220 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1221 'upload_date': '20200408',
1222 'uploader_id': 'FlyingKitty900',
1223 'uploader': 'FlyingKitty',
1224 'age_limit': 18,
1225 'availability': 'needs_auth',
1226 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1227 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1228 'channel': 'FlyingKitty',
1229 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1230 'view_count': int,
1231 'categories': ['Entertainment'],
1232 'live_status': 'not_live',
1233 'tags': ['Flyingkitty', 'godzilla 2'],
1234 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1235 'like_count': int,
1236 'duration': 177,
1237 'playable_in_embed': True,
1238 'channel_follower_count': int
1239 },
1240 },
1241 {
1242 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1243 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1244 'info_dict': {
1245 'id': 'Tq92D6wQ1mg',
1246 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1247 'ext': 'mp4',
1248 'upload_date': '20191228',
1249 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1250 'uploader': 'Projekt Melody',
1251 'description': 'md5:17eccca93a786d51bc67646756894066',
1252 'age_limit': 18,
1253 'like_count': int,
1254 'availability': 'needs_auth',
1255 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1256 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1257 'view_count': int,
1258 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1259 'channel': 'Projekt Melody',
1260 'live_status': 'not_live',
1261 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1262 'playable_in_embed': True,
1263 'categories': ['Entertainment'],
1264 'duration': 106,
1265 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1266 'comment_count': int,
1267 'channel_follower_count': int
1268 },
1269 },
1270 {
1271 'note': 'Non-Agegated non-embeddable video',
1272 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1273 'info_dict': {
1274 'id': 'MeJVWBSsPAY',
1275 'ext': 'mp4',
1276 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1277 'uploader': 'Herr Lurik',
1278 'uploader_id': 'st3in234',
1279 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1280 'upload_date': '20130730',
1281 'track': 'Such mich find mich',
1282 'age_limit': 0,
1283 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1284 'like_count': int,
1285 'playable_in_embed': False,
1286 'creator': 'OOMPH!',
1287 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1288 'view_count': int,
1289 'alt_title': 'Such mich find mich',
1290 'duration': 210,
1291 'channel': 'Herr Lurik',
1292 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1293 'categories': ['Music'],
1294 'availability': 'public',
1295 'uploader_url': 'http://www.youtube.com/user/st3in234',
1296 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1297 'live_status': 'not_live',
1298 'artist': 'OOMPH!',
1299 'channel_follower_count': int
1300 },
1301 },
1302 {
1303 'note': 'Non-bypassable age-gated video',
1304 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1305 'only_matching': True,
1306 },
1307 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1308 # YouTube Red ad is not captured for creator
1309 {
1310 'url': '__2ABJjxzNo',
1311 'info_dict': {
1312 'id': '__2ABJjxzNo',
1313 'ext': 'mp4',
1314 'duration': 266,
1315 'upload_date': '20100430',
1316 'uploader_id': 'deadmau5',
1317 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1318 'creator': 'deadmau5',
1319 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1320 'uploader': 'deadmau5',
1321 'title': 'Deadmau5 - Some Chords (HD)',
1322 'alt_title': 'Some Chords',
1323 'availability': 'public',
1324 'tags': 'count:14',
1325 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1326 'view_count': int,
1327 'live_status': 'not_live',
1328 'channel': 'deadmau5',
1329 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1330 'like_count': int,
1331 'track': 'Some Chords',
1332 'artist': 'deadmau5',
1333 'playable_in_embed': True,
1334 'age_limit': 0,
1335 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1336 'categories': ['Music'],
1337 'album': 'Some Chords',
1338 'channel_follower_count': int
1339 },
1340 'expected_warnings': [
1341 'DASH manifest missing',
1342 ]
1343 },
1344 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1345 {
1346 'url': 'lqQg6PlCWgI',
1347 'info_dict': {
1348 'id': 'lqQg6PlCWgI',
1349 'ext': 'mp4',
1350 'duration': 6085,
1351 'upload_date': '20150827',
1352 'uploader_id': 'olympic',
1353 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1354 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1355 'uploader': 'Olympics',
1356 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1357 'like_count': int,
1358 'release_timestamp': 1343767800,
1359 'playable_in_embed': True,
1360 'categories': ['Sports'],
1361 'release_date': '20120731',
1362 'channel': 'Olympics',
1363 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1364 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1365 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1366 'age_limit': 0,
1367 'availability': 'public',
1368 'live_status': 'was_live',
1369 'view_count': int,
1370 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1371 'channel_follower_count': int
1372 },
1373 'params': {
1374 'skip_download': 'requires avconv',
1375 }
1376 },
1377 # Non-square pixels
1378 {
1379 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1380 'info_dict': {
1381 'id': '_b-2C3KPAM0',
1382 'ext': 'mp4',
1383 'stretched_ratio': 16 / 9.,
1384 'duration': 85,
1385 'upload_date': '20110310',
1386 'uploader_id': 'AllenMeow',
1387 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1388 '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',
1389 'uploader': '孫ᄋᄅ',
1390 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1391 'playable_in_embed': True,
1392 'channel': '孫ᄋᄅ',
1393 'age_limit': 0,
1394 'tags': 'count:11',
1395 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1396 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1397 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1398 'view_count': int,
1399 'categories': ['People & Blogs'],
1400 'like_count': int,
1401 'live_status': 'not_live',
1402 'availability': 'unlisted',
1403 'comment_count': int,
1404 'channel_follower_count': int
1405 },
1406 },
1407 # url_encoded_fmt_stream_map is empty string
1408 {
1409 'url': 'qEJwOuvDf7I',
1410 'info_dict': {
1411 'id': 'qEJwOuvDf7I',
1412 'ext': 'webm',
1413 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1414 'description': '',
1415 'upload_date': '20150404',
1416 'uploader_id': 'spbelect',
1417 'uploader': 'Наблюдатели Петербурга',
1418 },
1419 'params': {
1420 'skip_download': 'requires avconv',
1421 },
1422 'skip': 'This live event has ended.',
1423 },
1424 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1425 {
1426 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1427 'info_dict': {
1428 'id': 'FIl7x6_3R5Y',
1429 'ext': 'webm',
1430 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1431 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1432 'duration': 220,
1433 'upload_date': '20150625',
1434 'uploader_id': 'dorappi2000',
1435 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1436 'uploader': 'dorappi2000',
1437 'formats': 'mincount:31',
1438 },
1439 'skip': 'not actual anymore',
1440 },
1441 # DASH manifest with segment_list
1442 {
1443 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1444 'md5': '8ce563a1d667b599d21064e982ab9e31',
1445 'info_dict': {
1446 'id': 'CsmdDsKjzN8',
1447 'ext': 'mp4',
1448 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1449 'uploader': 'Airtek',
1450 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1451 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1452 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1453 },
1454 'params': {
1455 'youtube_include_dash_manifest': True,
1456 'format': '135', # bestvideo
1457 },
1458 'skip': 'This live event has ended.',
1459 },
1460 {
1461 # Multifeed videos (multiple cameras), URL is for Main Camera
1462 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1463 'info_dict': {
1464 'id': 'jvGDaLqkpTg',
1465 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1466 'description': 'md5:e03b909557865076822aa169218d6a5d',
1467 },
1468 'playlist': [{
1469 'info_dict': {
1470 'id': 'jvGDaLqkpTg',
1471 'ext': 'mp4',
1472 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1473 'description': 'md5:e03b909557865076822aa169218d6a5d',
1474 'duration': 10643,
1475 'upload_date': '20161111',
1476 'uploader': 'Team PGP',
1477 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1478 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1479 },
1480 }, {
1481 'info_dict': {
1482 'id': '3AKt1R1aDnw',
1483 'ext': 'mp4',
1484 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1485 'description': 'md5:e03b909557865076822aa169218d6a5d',
1486 'duration': 10991,
1487 'upload_date': '20161111',
1488 'uploader': 'Team PGP',
1489 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1490 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1491 },
1492 }, {
1493 'info_dict': {
1494 'id': 'RtAMM00gpVc',
1495 'ext': 'mp4',
1496 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1497 'description': 'md5:e03b909557865076822aa169218d6a5d',
1498 'duration': 10995,
1499 'upload_date': '20161111',
1500 'uploader': 'Team PGP',
1501 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1502 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1503 },
1504 }, {
1505 'info_dict': {
1506 'id': '6N2fdlP3C5U',
1507 'ext': 'mp4',
1508 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1509 'description': 'md5:e03b909557865076822aa169218d6a5d',
1510 'duration': 10990,
1511 'upload_date': '20161111',
1512 'uploader': 'Team PGP',
1513 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1514 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1515 },
1516 }],
1517 'params': {
1518 'skip_download': True,
1519 },
1520 'skip': 'Not multifeed anymore',
1521 },
1522 {
1523 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1524 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1525 'info_dict': {
1526 'id': 'gVfLd0zydlo',
1527 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1528 },
1529 'playlist_count': 2,
1530 'skip': 'Not multifeed anymore',
1531 },
1532 {
1533 'url': 'https://vid.plus/FlRa-iH7PGw',
1534 'only_matching': True,
1535 },
1536 {
1537 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1538 'only_matching': True,
1539 },
1540 {
1541 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1542 # Also tests cut-off URL expansion in video description (see
1543 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1544 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1545 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1546 'info_dict': {
1547 'id': 'lsguqyKfVQg',
1548 'ext': 'mp4',
1549 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1550 'alt_title': 'Dark Walk',
1551 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1552 'duration': 133,
1553 'upload_date': '20151119',
1554 'uploader_id': 'IronSoulElf',
1555 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1556 'uploader': 'IronSoulElf',
1557 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1558 'track': 'Dark Walk',
1559 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1560 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1561 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1562 'categories': ['Film & Animation'],
1563 'view_count': int,
1564 'live_status': 'not_live',
1565 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1566 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1567 'tags': 'count:13',
1568 'availability': 'public',
1569 'channel': 'IronSoulElf',
1570 'playable_in_embed': True,
1571 'like_count': int,
1572 'age_limit': 0,
1573 'channel_follower_count': int
1574 },
1575 'params': {
1576 'skip_download': True,
1577 },
1578 },
1579 {
1580 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1581 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1582 'only_matching': True,
1583 },
1584 {
1585 # Video with yt:stretch=17:0
1586 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1587 'info_dict': {
1588 'id': 'Q39EVAstoRM',
1589 'ext': 'mp4',
1590 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1591 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1592 'upload_date': '20151107',
1593 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1594 'uploader': 'CH GAMER DROID',
1595 },
1596 'params': {
1597 'skip_download': True,
1598 },
1599 'skip': 'This video does not exist.',
1600 },
1601 {
1602 # Video with incomplete 'yt:stretch=16:'
1603 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1604 'only_matching': True,
1605 },
1606 {
1607 # Video licensed under Creative Commons
1608 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1609 'info_dict': {
1610 'id': 'M4gD1WSo5mA',
1611 'ext': 'mp4',
1612 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1613 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1614 'duration': 721,
1615 'upload_date': '20150128',
1616 'uploader_id': 'BerkmanCenter',
1617 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1618 'uploader': 'The Berkman Klein Center for Internet & Society',
1619 'license': 'Creative Commons Attribution license (reuse allowed)',
1620 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1621 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1622 'like_count': int,
1623 'age_limit': 0,
1624 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1625 'channel': 'The Berkman Klein Center for Internet & Society',
1626 'availability': 'public',
1627 'view_count': int,
1628 'categories': ['Education'],
1629 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1630 'live_status': 'not_live',
1631 'playable_in_embed': True,
1632 'comment_count': int,
1633 'channel_follower_count': int
1634 },
1635 'params': {
1636 'skip_download': True,
1637 },
1638 },
1639 {
1640 # Channel-like uploader_url
1641 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1642 'info_dict': {
1643 'id': 'eQcmzGIKrzg',
1644 'ext': 'mp4',
1645 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1646 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1647 'duration': 4060,
1648 'upload_date': '20151120',
1649 'uploader': 'Bernie Sanders',
1650 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1651 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1652 'license': 'Creative Commons Attribution license (reuse allowed)',
1653 'playable_in_embed': True,
1654 'tags': 'count:12',
1655 'like_count': int,
1656 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1657 'age_limit': 0,
1658 'availability': 'public',
1659 'categories': ['News & Politics'],
1660 'channel': 'Bernie Sanders',
1661 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1662 'view_count': int,
1663 'live_status': 'not_live',
1664 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1665 'comment_count': int,
1666 'channel_follower_count': int
1667 },
1668 'params': {
1669 'skip_download': True,
1670 },
1671 },
1672 {
1673 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1674 'only_matching': True,
1675 },
1676 {
1677 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1678 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1679 'only_matching': True,
1680 },
1681 {
1682 # Rental video preview
1683 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1684 'info_dict': {
1685 'id': 'uGpuVWrhIzE',
1686 'ext': 'mp4',
1687 'title': 'Piku - Trailer',
1688 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1689 'upload_date': '20150811',
1690 'uploader': 'FlixMatrix',
1691 'uploader_id': 'FlixMatrixKaravan',
1692 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1693 'license': 'Standard YouTube License',
1694 },
1695 'params': {
1696 'skip_download': True,
1697 },
1698 'skip': 'This video is not available.',
1699 },
1700 {
1701 # YouTube Red video with episode data
1702 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1703 'info_dict': {
1704 'id': 'iqKdEhx-dD4',
1705 'ext': 'mp4',
1706 'title': 'Isolation - Mind Field (Ep 1)',
1707 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1708 'duration': 2085,
1709 'upload_date': '20170118',
1710 'uploader': 'Vsauce',
1711 'uploader_id': 'Vsauce',
1712 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1713 'series': 'Mind Field',
1714 'season_number': 1,
1715 'episode_number': 1,
1716 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1717 'tags': 'count:12',
1718 'view_count': int,
1719 'availability': 'public',
1720 'age_limit': 0,
1721 'channel': 'Vsauce',
1722 'episode': 'Episode 1',
1723 'categories': ['Entertainment'],
1724 'season': 'Season 1',
1725 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1726 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1727 'like_count': int,
1728 'playable_in_embed': True,
1729 'live_status': 'not_live',
1730 'channel_follower_count': int
1731 },
1732 'params': {
1733 'skip_download': True,
1734 },
1735 'expected_warnings': [
1736 'Skipping DASH manifest',
1737 ],
1738 },
1739 {
1740 # The following content has been identified by the YouTube community
1741 # as inappropriate or offensive to some audiences.
1742 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1743 'info_dict': {
1744 'id': '6SJNVb0GnPI',
1745 'ext': 'mp4',
1746 'title': 'Race Differences in Intelligence',
1747 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1748 'duration': 965,
1749 'upload_date': '20140124',
1750 'uploader': 'New Century Foundation',
1751 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1752 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1753 },
1754 'params': {
1755 'skip_download': True,
1756 },
1757 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1758 },
1759 {
1760 # itag 212
1761 'url': '1t24XAntNCY',
1762 'only_matching': True,
1763 },
1764 {
1765 # geo restricted to JP
1766 'url': 'sJL6WA-aGkQ',
1767 'only_matching': True,
1768 },
1769 {
1770 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1771 'only_matching': True,
1772 },
1773 {
1774 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1775 'only_matching': True,
1776 },
1777 {
1778 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1779 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1780 'only_matching': True,
1781 },
1782 {
1783 # DRM protected
1784 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1785 'only_matching': True,
1786 },
1787 {
1788 # Video with unsupported adaptive stream type formats
1789 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1790 'info_dict': {
1791 'id': 'Z4Vy8R84T1U',
1792 'ext': 'mp4',
1793 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1794 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1795 'duration': 433,
1796 'upload_date': '20130923',
1797 'uploader': 'Amelia Putri Harwita',
1798 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1800 'formats': 'maxcount:10',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 'youtube_include_dash_manifest': False,
1805 },
1806 'skip': 'not actual anymore',
1807 },
1808 {
1809 # Youtube Music Auto-generated description
1810 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1811 'info_dict': {
1812 'id': 'MgNrAu2pzNs',
1813 'ext': 'mp4',
1814 'title': 'Voyeur Girl',
1815 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1816 'upload_date': '20190312',
1817 'uploader': 'Stephen - Topic',
1818 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1819 'artist': 'Stephen',
1820 'track': 'Voyeur Girl',
1821 'album': 'it\'s too much love to know my dear',
1822 'release_date': '20190313',
1823 'release_year': 2019,
1824 'alt_title': 'Voyeur Girl',
1825 'view_count': int,
1826 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1827 'playable_in_embed': True,
1828 'like_count': int,
1829 'categories': ['Music'],
1830 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1831 'channel': 'Stephen',
1832 'availability': 'public',
1833 'creator': 'Stephen',
1834 'duration': 169,
1835 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1836 'age_limit': 0,
1837 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1838 'tags': 'count:11',
1839 'live_status': 'not_live',
1840 'channel_follower_count': int
1841 },
1842 'params': {
1843 'skip_download': True,
1844 },
1845 },
1846 {
1847 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1848 'only_matching': True,
1849 },
1850 {
1851 # invalid -> valid video id redirection
1852 'url': 'DJztXj2GPfl',
1853 'info_dict': {
1854 'id': 'DJztXj2GPfk',
1855 'ext': 'mp4',
1856 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1857 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1858 'upload_date': '20090125',
1859 'uploader': 'Prochorowka',
1860 'uploader_id': 'Prochorowka',
1861 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1862 'artist': 'Panjabi MC',
1863 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1864 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1865 },
1866 'params': {
1867 'skip_download': True,
1868 },
1869 'skip': 'Video unavailable',
1870 },
1871 {
1872 # empty description results in an empty string
1873 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1874 'info_dict': {
1875 'id': 'x41yOUIvK2k',
1876 'ext': 'mp4',
1877 'title': 'IMG 3456',
1878 'description': '',
1879 'upload_date': '20170613',
1880 'uploader_id': 'ElevageOrVert',
1881 'uploader': 'ElevageOrVert',
1882 'view_count': int,
1883 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1884 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1885 'like_count': int,
1886 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1887 'tags': [],
1888 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1889 'availability': 'public',
1890 'age_limit': 0,
1891 'categories': ['Pets & Animals'],
1892 'duration': 7,
1893 'playable_in_embed': True,
1894 'live_status': 'not_live',
1895 'channel': 'ElevageOrVert',
1896 'channel_follower_count': int
1897 },
1898 'params': {
1899 'skip_download': True,
1900 },
1901 },
1902 {
1903 # with '};' inside yt initial data (see [1])
1904 # see [2] for an example with '};' inside ytInitialPlayerResponse
1905 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1906 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1907 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1908 'info_dict': {
1909 'id': 'CHqg6qOn4no',
1910 'ext': 'mp4',
1911 'title': 'Part 77 Sort a list of simple types in c#',
1912 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1913 'upload_date': '20130831',
1914 'uploader_id': 'kudvenkat',
1915 'uploader': 'kudvenkat',
1916 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1917 'like_count': int,
1918 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1919 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1920 'live_status': 'not_live',
1921 'categories': ['Education'],
1922 'availability': 'public',
1923 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1924 'tags': 'count:12',
1925 'playable_in_embed': True,
1926 'age_limit': 0,
1927 'view_count': int,
1928 'duration': 522,
1929 'channel': 'kudvenkat',
1930 'comment_count': int,
1931 'channel_follower_count': int
1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
1936 },
1937 {
1938 # another example of '};' in ytInitialData
1939 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1940 'only_matching': True,
1941 },
1942 {
1943 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1944 'only_matching': True,
1945 },
1946 {
1947 # https://github.com/ytdl-org/youtube-dl/pull/28094
1948 'url': 'OtqTfy26tG0',
1949 'info_dict': {
1950 'id': 'OtqTfy26tG0',
1951 'ext': 'mp4',
1952 'title': 'Burn Out',
1953 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1954 'upload_date': '20141120',
1955 'uploader': 'The Cinematic Orchestra - Topic',
1956 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1958 'artist': 'The Cinematic Orchestra',
1959 'track': 'Burn Out',
1960 'album': 'Every Day',
1961 'like_count': int,
1962 'live_status': 'not_live',
1963 'alt_title': 'Burn Out',
1964 'duration': 614,
1965 'age_limit': 0,
1966 'view_count': int,
1967 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1968 'creator': 'The Cinematic Orchestra',
1969 'channel': 'The Cinematic Orchestra',
1970 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1971 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1972 'availability': 'public',
1973 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1974 'categories': ['Music'],
1975 'playable_in_embed': True,
1976 'channel_follower_count': int
1977 },
1978 'params': {
1979 'skip_download': True,
1980 },
1981 },
1982 {
1983 # controversial video, only works with bpctr when authenticated with cookies
1984 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1985 'only_matching': True,
1986 },
1987 {
1988 # controversial video, requires bpctr/contentCheckOk
1989 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1990 'info_dict': {
1991 'id': 'SZJvDhaSDnc',
1992 'ext': 'mp4',
1993 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1994 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1995 'uploader': 'CBS Mornings',
1996 'uploader_id': 'CBSThisMorning',
1997 'upload_date': '20140716',
1998 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1999 'duration': 170,
2000 'categories': ['News & Politics'],
2001 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2002 'view_count': int,
2003 'channel': 'CBS Mornings',
2004 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2005 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2006 'age_limit': 18,
2007 'availability': 'needs_auth',
2008 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2009 'like_count': int,
2010 'live_status': 'not_live',
2011 'playable_in_embed': True,
2012 'channel_follower_count': int
2013 }
2014 },
2015 {
2016 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2017 'url': 'cBvYw8_A0vQ',
2018 'info_dict': {
2019 'id': 'cBvYw8_A0vQ',
2020 'ext': 'mp4',
2021 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2022 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2023 'upload_date': '20201120',
2024 'uploader': 'Walk around Japan',
2025 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2026 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2027 'duration': 1456,
2028 'categories': ['Travel & Events'],
2029 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2030 'view_count': int,
2031 'channel': 'Walk around Japan',
2032 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2033 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2034 'age_limit': 0,
2035 'availability': 'public',
2036 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2037 'live_status': 'not_live',
2038 'playable_in_embed': True,
2039 'channel_follower_count': int
2040 },
2041 'params': {
2042 'skip_download': True,
2043 },
2044 }, {
2045 # Has multiple audio streams
2046 'url': 'WaOKSUlf4TM',
2047 'only_matching': True
2048 }, {
2049 # Requires Premium: has format 141 when requested using YTM url
2050 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2051 'only_matching': True
2052 }, {
2053 # multiple subtitles with same lang_code
2054 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2055 'only_matching': True,
2056 }, {
2057 # Force use android client fallback
2058 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2059 'info_dict': {
2060 'id': 'YOelRv7fMxY',
2061 'title': 'DIGGING A SECRET TUNNEL Part 1',
2062 'ext': '3gp',
2063 'upload_date': '20210624',
2064 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2065 'uploader': 'colinfurze',
2066 'uploader_id': 'colinfurze',
2067 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2068 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2069 'duration': 596,
2070 'categories': ['Entertainment'],
2071 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2072 'view_count': int,
2073 'channel': 'colinfurze',
2074 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2075 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2076 'age_limit': 0,
2077 'availability': 'public',
2078 'like_count': int,
2079 'live_status': 'not_live',
2080 'playable_in_embed': True,
2081 'channel_follower_count': int
2082 },
2083 'params': {
2084 'format': '17', # 3gp format available on android
2085 'extractor_args': {'youtube': {'player_client': ['android']}},
2086 },
2087 },
2088 {
2089 # Skip download of additional client configs (remix client config in this case)
2090 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2091 'only_matching': True,
2092 'params': {
2093 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2094 },
2095 }, {
2096 # shorts
2097 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2098 'only_matching': True,
2099 }, {
2100 'note': 'Storyboards',
2101 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2102 'info_dict': {
2103 'id': '5KLPxDtMqe8',
2104 'ext': 'mhtml',
2105 'format_id': 'sb0',
2106 'title': 'Your Brain is Plastic',
2107 'uploader_id': 'scishow',
2108 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2109 'upload_date': '20140324',
2110 'uploader': 'SciShow',
2111 'like_count': int,
2112 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2113 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2114 'view_count': int,
2115 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2116 'playable_in_embed': True,
2117 'tags': 'count:12',
2118 'uploader_url': 'http://www.youtube.com/user/scishow',
2119 'availability': 'public',
2120 'channel': 'SciShow',
2121 'live_status': 'not_live',
2122 'duration': 248,
2123 'categories': ['Education'],
2124 'age_limit': 0,
2125 'channel_follower_count': int
2126 }, 'params': {'format': 'mhtml', 'skip_download': True}
2127 }, {
2128 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2129 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2130 'info_dict': {
2131 'id': '2NUZ8W2llS4',
2132 'ext': 'mp4',
2133 'title': 'The NP that test your phone performance 🙂',
2134 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2135 'uploader': 'Leon Nguyen',
2136 'uploader_id': 'VNSXIII',
2137 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2138 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2139 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2140 'duration': 21,
2141 'view_count': int,
2142 'age_limit': 0,
2143 'categories': ['Gaming'],
2144 'tags': 'count:23',
2145 'playable_in_embed': True,
2146 'live_status': 'not_live',
2147 'upload_date': '20220103',
2148 'like_count': int,
2149 'availability': 'public',
2150 'channel': 'Leon Nguyen',
2151 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2152 'comment_count': int,
2153 'channel_follower_count': int
2154 }
2155 }, {
2156 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2157 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2158 'info_dict': {
2159 'id': 'mzZzzBU6lrM',
2160 'ext': 'mp4',
2161 'title': 'I Met GeorgeNotFound In Real Life...',
2162 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2163 'uploader': 'Quackity',
2164 'uploader_id': 'QuackityHQ',
2165 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2166 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2167 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2168 'duration': 955,
2169 'view_count': int,
2170 'age_limit': 0,
2171 'categories': ['Entertainment'],
2172 'tags': 'count:26',
2173 'playable_in_embed': True,
2174 'live_status': 'not_live',
2175 'release_timestamp': 1641172509,
2176 'release_date': '20220103',
2177 'upload_date': '20220103',
2178 'like_count': int,
2179 'availability': 'public',
2180 'channel': 'Quackity',
2181 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2182 'channel_follower_count': int
2183 }
2184 },
2185 { # continuous livestream. Microformat upload date should be preferred.
2186 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2187 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2188 'info_dict': {
2189 'id': 'kgx4WGK0oNU',
2190 '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}',
2191 'ext': 'mp4',
2192 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2193 'availability': 'public',
2194 'age_limit': 0,
2195 'release_timestamp': 1637975704,
2196 'upload_date': '20210619',
2197 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2198 'live_status': 'is_live',
2199 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2200 'uploader': '阿鲍Abao',
2201 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2202 'channel': 'Abao in Tokyo',
2203 'channel_follower_count': int,
2204 'release_date': '20211127',
2205 'tags': 'count:39',
2206 'categories': ['People & Blogs'],
2207 'like_count': int,
2208 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2209 'view_count': int,
2210 'playable_in_embed': True,
2211 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2212 },
2213 'params': {'skip_download': True}
2214 }, {
2215 # Story. Requires specific player params to work.
2216 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2217 'info_dict': {
2218 'id': 'vv8qTUWmulI',
2219 'ext': 'mp4',
2220 'availability': 'unlisted',
2221 'view_count': int,
2222 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2223 'upload_date': '20220526',
2224 'categories': ['Education'],
2225 'title': 'Story',
2226 'channel': 'IT\'S HISTORY',
2227 'description': '',
2228 'uploader_id': 'BlastfromthePast',
2229 'duration': 12,
2230 'uploader': 'IT\'S HISTORY',
2231 'playable_in_embed': True,
2232 'age_limit': 0,
2233 'live_status': 'not_live',
2234 'tags': [],
2235 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2236 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2237 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2238 },
2239 'skip': 'stories get removed after some period of time',
2240 }, {
2241 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2242 'info_dict': {
2243 'id': 'tjjjtzRLHvA',
2244 'ext': 'mp4',
2245 'title': 'ハッシュタグ無し };if window.ytcsi',
2246 'upload_date': '20220323',
2247 'like_count': int,
2248 'availability': 'unlisted',
2249 'channel': 'nao20010128nao',
2250 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2251 'age_limit': 0,
2252 'uploader': 'nao20010128nao',
2253 'uploader_id': 'nao20010128nao',
2254 'categories': ['Music'],
2255 'view_count': int,
2256 'description': '',
2257 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2258 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2259 'live_status': 'not_live',
2260 'playable_in_embed': True,
2261 'channel_follower_count': int,
2262 'duration': 6,
2263 'tags': [],
2264 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2265 }
2266 }
2267 ]
2268
2269 @classmethod
2270 def suitable(cls, url):
2271 from ..utils import parse_qs
2272
2273 qs = parse_qs(url)
2274 if qs.get('list', [None])[0]:
2275 return False
2276 return super().suitable(url)
2277
2278 def __init__(self, *args, **kwargs):
2279 super().__init__(*args, **kwargs)
2280 self._code_cache = {}
2281 self._player_cache = {}
2282
2283 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2284 lock = threading.Lock()
2285
2286 is_live = True
2287 start_time = time.time()
2288 formats = [f for f in formats if f.get('is_from_start')]
2289
2290 def refetch_manifest(format_id, delay):
2291 nonlocal formats, start_time, is_live
2292 if time.time() <= start_time + delay:
2293 return
2294
2295 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2296 video_details = traverse_obj(
2297 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2298 microformats = traverse_obj(
2299 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2300 expected_type=dict, default=[])
2301 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
2302 start_time = time.time()
2303
2304 def mpd_feed(format_id, delay):
2305 """
2306 @returns (manifest_url, manifest_stream_number, is_live) or None
2307 """
2308 with lock:
2309 refetch_manifest(format_id, delay)
2310
2311 f = next((f for f in formats if f['format_id'] == format_id), None)
2312 if not f:
2313 if not is_live:
2314 self.to_screen(f'{video_id}: Video is no longer live')
2315 else:
2316 self.report_warning(
2317 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2318 return None
2319 return f['manifest_url'], f['manifest_stream_number'], is_live
2320
2321 for f in formats:
2322 f['is_live'] = True
2323 f['protocol'] = 'http_dash_segments_generator'
2324 f['fragments'] = functools.partial(
2325 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2326
2327 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2328 FETCH_SPAN, MAX_DURATION = 5, 432000
2329
2330 mpd_url, stream_number, is_live = None, None, True
2331
2332 begin_index = 0
2333 download_start_time = ctx.get('start') or time.time()
2334
2335 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2336 if lack_early_segments:
2337 self.report_warning(bug_reports_message(
2338 'Starting download from the last 120 hours of the live stream since '
2339 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2340 lack_early_segments = True
2341
2342 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2343 fragments, fragment_base_url = None, None
2344
2345 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2346 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2347 # Obtain from MPD's maximum seq value
2348 old_mpd_url = mpd_url
2349 last_error = ctx.pop('last_error', None)
2350 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2351 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2352 or (mpd_url, stream_number, False))
2353 if not refresh_sequence:
2354 if expire_fast and not is_live:
2355 return False, last_seq
2356 elif old_mpd_url == mpd_url:
2357 return True, last_seq
2358 try:
2359 fmts, _ = self._extract_mpd_formats_and_subtitles(
2360 mpd_url, None, note=False, errnote=False, fatal=False)
2361 except ExtractorError:
2362 fmts = None
2363 if not fmts:
2364 no_fragment_score += 2
2365 return False, last_seq
2366 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2367 fragments = fmt_info['fragments']
2368 fragment_base_url = fmt_info['fragment_base_url']
2369 assert fragment_base_url
2370
2371 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2372 return True, _last_seq
2373
2374 while is_live:
2375 fetch_time = time.time()
2376 if no_fragment_score > 30:
2377 return
2378 if last_segment_url:
2379 # Obtain from "X-Head-Seqnum" header value from each segment
2380 try:
2381 urlh = self._request_webpage(
2382 last_segment_url, None, note=False, errnote=False, fatal=False)
2383 except ExtractorError:
2384 urlh = None
2385 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2386 if last_seq is None:
2387 no_fragment_score += 2
2388 last_segment_url = None
2389 continue
2390 else:
2391 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2392 no_fragment_score += 2
2393 if not should_continue:
2394 continue
2395
2396 if known_idx > last_seq:
2397 last_segment_url = None
2398 continue
2399
2400 last_seq += 1
2401
2402 if begin_index < 0 and known_idx < 0:
2403 # skip from the start when it's negative value
2404 known_idx = last_seq + begin_index
2405 if lack_early_segments:
2406 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2407 try:
2408 for idx in range(known_idx, last_seq):
2409 # do not update sequence here or you'll get skipped some part of it
2410 should_continue, _ = _extract_sequence_from_mpd(False, False)
2411 if not should_continue:
2412 known_idx = idx - 1
2413 raise ExtractorError('breaking out of outer loop')
2414 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2415 yield {
2416 'url': last_segment_url,
2417 'fragment_count': last_seq,
2418 }
2419 if known_idx == last_seq:
2420 no_fragment_score += 5
2421 else:
2422 no_fragment_score = 0
2423 known_idx = last_seq
2424 except ExtractorError:
2425 continue
2426
2427 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2428
2429 def _extract_player_url(self, *ytcfgs, webpage=None):
2430 player_url = traverse_obj(
2431 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2432 get_all=False, expected_type=str)
2433 if not player_url:
2434 return
2435 return urljoin('https://www.youtube.com', player_url)
2436
2437 def _download_player_url(self, video_id, fatal=False):
2438 res = self._download_webpage(
2439 'https://www.youtube.com/iframe_api',
2440 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2441 if res:
2442 player_version = self._search_regex(
2443 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2444 if player_version:
2445 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2446
2447 def _signature_cache_id(self, example_sig):
2448 """ Return a string representation of a signature """
2449 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2450
2451 @classmethod
2452 def _extract_player_info(cls, player_url):
2453 for player_re in cls._PLAYER_INFO_RE:
2454 id_m = re.search(player_re, player_url)
2455 if id_m:
2456 break
2457 else:
2458 raise ExtractorError('Cannot identify player %r' % player_url)
2459 return id_m.group('id')
2460
2461 def _load_player(self, video_id, player_url, fatal=True):
2462 player_id = self._extract_player_info(player_url)
2463 if player_id not in self._code_cache:
2464 code = self._download_webpage(
2465 player_url, video_id, fatal=fatal,
2466 note='Downloading player ' + player_id,
2467 errnote='Download of %s failed' % player_url)
2468 if code:
2469 self._code_cache[player_id] = code
2470 return self._code_cache.get(player_id)
2471
2472 def _extract_signature_function(self, video_id, player_url, example_sig):
2473 player_id = self._extract_player_info(player_url)
2474
2475 # Read from filesystem cache
2476 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2477 assert os.path.basename(func_id) == func_id
2478
2479 self.write_debug(f'Extracting signature function {func_id}')
2480 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
2481 if cache_spec is not None:
2482 return lambda s: ''.join(s[i] for i in cache_spec)
2483
2484 code = self._load_player(video_id, player_url)
2485 if code:
2486 res = self._parse_sig_js(code)
2487
2488 test_string = ''.join(map(chr, range(len(example_sig))))
2489 cache_res = res(test_string)
2490 cache_spec = [ord(c) for c in cache_res]
2491
2492 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2493 return res
2494
2495 def _print_sig_code(self, func, example_sig):
2496 if not self.get_param('youtube_print_sig_code'):
2497 return
2498
2499 def gen_sig_code(idxs):
2500 def _genslice(start, end, step):
2501 starts = '' if start == 0 else str(start)
2502 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2503 steps = '' if step == 1 else (':%d' % step)
2504 return f's[{starts}{ends}{steps}]'
2505
2506 step = None
2507 # Quelch pyflakes warnings - start will be set when step is set
2508 start = '(Never used)'
2509 for i, prev in zip(idxs[1:], idxs[:-1]):
2510 if step is not None:
2511 if i - prev == step:
2512 continue
2513 yield _genslice(start, prev, step)
2514 step = None
2515 continue
2516 if i - prev in [-1, 1]:
2517 step = i - prev
2518 start = prev
2519 continue
2520 else:
2521 yield 's[%d]' % prev
2522 if step is None:
2523 yield 's[%d]' % i
2524 else:
2525 yield _genslice(start, i, step)
2526
2527 test_string = ''.join(map(chr, range(len(example_sig))))
2528 cache_res = func(test_string)
2529 cache_spec = [ord(c) for c in cache_res]
2530 expr_code = ' + '.join(gen_sig_code(cache_spec))
2531 signature_id_tuple = '(%s)' % (
2532 ', '.join(str(len(p)) for p in example_sig.split('.')))
2533 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2534 ' return %s\n') % (signature_id_tuple, expr_code)
2535 self.to_screen('Extracted signature function:\n' + code)
2536
2537 def _parse_sig_js(self, jscode):
2538 funcname = self._search_regex(
2539 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2540 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2541 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2542 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2543 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}\(a,\d+\)',
2544 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\(\s*""\s*\)',
2545 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2546 # Obsolete patterns
2547 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2548 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2549 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2550 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2551 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2552 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2553 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2554 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2555 jscode, 'Initial JS player signature function name', group='sig')
2556
2557 jsi = JSInterpreter(jscode)
2558 initial_function = jsi.extract_function(funcname)
2559 return lambda s: initial_function([s])
2560
2561 def _decrypt_signature(self, s, video_id, player_url):
2562 """Turn the encrypted s field into a working signature"""
2563 try:
2564 player_id = (player_url, self._signature_cache_id(s))
2565 if player_id not in self._player_cache:
2566 func = self._extract_signature_function(video_id, player_url, s)
2567 self._player_cache[player_id] = func
2568 func = self._player_cache[player_id]
2569 self._print_sig_code(func, s)
2570 return func(s)
2571 except Exception as e:
2572 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2573
2574 def _decrypt_nsig(self, s, video_id, player_url):
2575 """Turn the encrypted n field into a working signature"""
2576 if player_url is None:
2577 raise ExtractorError('Cannot decrypt nsig without player_url')
2578 player_url = urljoin('https://www.youtube.com', player_url)
2579
2580 sig_id = ('nsig_value', s)
2581 if sig_id in self._player_cache:
2582 return self._player_cache[sig_id]
2583
2584 try:
2585 player_id = ('nsig', player_url)
2586 if player_id not in self._player_cache:
2587 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2588 func = self._player_cache[player_id]
2589 self._player_cache[sig_id] = func(s)
2590 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2591 return self._player_cache[sig_id]
2592 except Exception as e:
2593 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2594
2595 def _extract_n_function_name(self, jscode):
2596 nfunc, idx = self._search_regex(
2597 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2598 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2599 if not idx:
2600 return nfunc
2601 return json.loads(js_to_json(self._search_regex(
2602 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
2603 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
2604
2605 def _extract_n_function(self, video_id, player_url):
2606 player_id = self._extract_player_info(player_url)
2607 func_code = self.cache.load('youtube-nsig', player_id)
2608
2609 if func_code:
2610 jsi = JSInterpreter(func_code)
2611 else:
2612 jscode = self._load_player(video_id, player_url)
2613 funcname = self._extract_n_function_name(jscode)
2614 jsi = JSInterpreter(jscode)
2615 func_code = jsi.extract_function_code(funcname)
2616 self.cache.store('youtube-nsig', player_id, func_code)
2617
2618 if self.get_param('youtube_print_sig_code'):
2619 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2620
2621 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2622
2623 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2624 """
2625 Extract signatureTimestamp (sts)
2626 Required to tell API what sig/player version is in use.
2627 """
2628 sts = None
2629 if isinstance(ytcfg, dict):
2630 sts = int_or_none(ytcfg.get('STS'))
2631
2632 if not sts:
2633 # Attempt to extract from player
2634 if player_url is None:
2635 error_msg = 'Cannot extract signature timestamp without player_url.'
2636 if fatal:
2637 raise ExtractorError(error_msg)
2638 self.report_warning(error_msg)
2639 return
2640 code = self._load_player(video_id, player_url, fatal=fatal)
2641 if code:
2642 sts = int_or_none(self._search_regex(
2643 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2644 'JS player signature timestamp', group='sts', fatal=fatal))
2645 return sts
2646
2647 def _mark_watched(self, video_id, player_responses):
2648 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2649 label = 'fully ' if is_full else ''
2650 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2651 expected_type=url_or_none)
2652 if not url:
2653 self.report_warning(f'Unable to mark {label}watched')
2654 return
2655 parsed_url = urllib.parse.urlparse(url)
2656 qs = urllib.parse.parse_qs(parsed_url.query)
2657
2658 # cpn generation algorithm is reverse engineered from base.js.
2659 # In fact it works even with dummy cpn.
2660 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2661 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2662
2663 # # more consistent results setting it to right before the end
2664 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2665
2666 qs.update({
2667 'ver': ['2'],
2668 'cpn': [cpn],
2669 'cmt': video_length,
2670 'el': 'detailpage', # otherwise defaults to "shorts"
2671 })
2672
2673 if is_full:
2674 # these seem to mark watchtime "history" in the real world
2675 # they're required, so send in a single value
2676 qs.update({
2677 'st': video_length,
2678 'et': video_length,
2679 })
2680
2681 url = urllib.parse.urlunparse(
2682 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2683
2684 self._download_webpage(
2685 url, video_id, f'Marking {label}watched',
2686 'Unable to mark watched', fatal=False)
2687
2688 @staticmethod
2689 def _extract_urls(webpage):
2690 # Embedded YouTube player
2691 entries = [
2692 unescapeHTML(mobj.group('url'))
2693 for mobj in re.finditer(r'''(?x)
2694 (?:
2695 <iframe[^>]+?src=|
2696 data-video-url=|
2697 <embed[^>]+?src=|
2698 embedSWF\(?:\s*|
2699 <object[^>]+data=|
2700 new\s+SWFObject\(
2701 )
2702 (["\'])
2703 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2704 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2705 \1''', webpage)]
2706
2707 # lazyYT YouTube embed
2708 entries.extend(list(map(
2709 unescapeHTML,
2710 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2711
2712 # Wordpress "YouTube Video Importer" plugin
2713 matches = re.findall(r'''(?x)<div[^>]+
2714 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2715 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2716 entries.extend(m[-1] for m in matches)
2717
2718 return entries
2719
2720 @staticmethod
2721 def _extract_url(webpage):
2722 urls = YoutubeIE._extract_urls(webpage)
2723 return urls[0] if urls else None
2724
2725 @classmethod
2726 def extract_id(cls, url):
2727 video_id = cls.get_temp_id(url)
2728 if not video_id:
2729 raise ExtractorError(f'Invalid URL: {url}')
2730 return video_id
2731
2732 def _extract_chapters_from_json(self, data, duration):
2733 chapter_list = traverse_obj(
2734 data, (
2735 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2736 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2737 ), expected_type=list)
2738
2739 return self._extract_chapters(
2740 chapter_list,
2741 chapter_time=lambda chapter: float_or_none(
2742 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2743 chapter_title=lambda chapter: traverse_obj(
2744 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2745 duration=duration)
2746
2747 def _extract_chapters_from_engagement_panel(self, data, duration):
2748 content_list = traverse_obj(
2749 data,
2750 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2751 expected_type=list, default=[])
2752 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2753 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2754
2755 return next(filter(None, (
2756 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2757 chapter_time, chapter_title, duration)
2758 for contents in content_list)), [])
2759
2760 def _extract_chapters_from_description(self, description, duration):
2761 return self._extract_chapters(
2762 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2763 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2764 duration=duration, strict=False)
2765
2766 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2767 if not duration:
2768 return
2769 chapter_list = [{
2770 'start_time': chapter_time(chapter),
2771 'title': chapter_title(chapter),
2772 } for chapter in chapter_list or []]
2773 if not strict:
2774 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2775
2776 chapters = [{'start_time': 0}]
2777 for idx, chapter in enumerate(chapter_list):
2778 if chapter['start_time'] is None:
2779 self.report_warning(f'Incomplete chapter {idx}')
2780 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2781 chapters.append(chapter)
2782 else:
2783 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
2784 return chapters[1:]
2785
2786 def _extract_comment(self, comment_renderer, parent=None):
2787 comment_id = comment_renderer.get('commentId')
2788 if not comment_id:
2789 return
2790
2791 text = self._get_text(comment_renderer, 'contentText')
2792
2793 # note: timestamp is an estimate calculated from the current time and time_text
2794 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2795 author = self._get_text(comment_renderer, 'authorText')
2796 author_id = try_get(comment_renderer,
2797 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
2798
2799 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2800 lambda x: x['likeCount']), str)) or 0
2801 author_thumbnail = try_get(comment_renderer,
2802 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
2803
2804 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2805 is_favorited = 'creatorHeart' in (try_get(
2806 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2807 return {
2808 'id': comment_id,
2809 'text': text,
2810 'timestamp': timestamp,
2811 'time_text': time_text,
2812 'like_count': votes,
2813 'is_favorited': is_favorited,
2814 'author': author,
2815 'author_id': author_id,
2816 'author_thumbnail': author_thumbnail,
2817 'author_is_uploader': author_is_uploader,
2818 'parent': parent or 'root'
2819 }
2820
2821 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2822
2823 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2824
2825 def extract_header(contents):
2826 _continuation = None
2827 for content in contents:
2828 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2829 expected_comment_count = self._get_count(
2830 comments_header_renderer, 'countText', 'commentsCount')
2831
2832 if expected_comment_count:
2833 tracker['est_total'] = expected_comment_count
2834 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2835 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2836
2837 sort_menu_item = try_get(
2838 comments_header_renderer,
2839 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2840 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2841
2842 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2843 if not _continuation:
2844 continue
2845
2846 sort_text = str_or_none(sort_menu_item.get('title'))
2847 if not sort_text:
2848 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2849 self.to_screen('Sorting comments by %s' % sort_text.lower())
2850 break
2851 return _continuation
2852
2853 def extract_thread(contents):
2854 if not parent:
2855 tracker['current_page_thread'] = 0
2856 for content in contents:
2857 if not parent and tracker['total_parent_comments'] >= max_parents:
2858 yield
2859 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2860 comment_renderer = get_first(
2861 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2862 expected_type=dict, default={})
2863
2864 comment = self._extract_comment(comment_renderer, parent)
2865 if not comment:
2866 continue
2867
2868 tracker['running_total'] += 1
2869 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2870 yield comment
2871
2872 # Attempt to get the replies
2873 comment_replies_renderer = try_get(
2874 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2875
2876 if comment_replies_renderer:
2877 tracker['current_page_thread'] += 1
2878 comment_entries_iter = self._comment_entries(
2879 comment_replies_renderer, ytcfg, video_id,
2880 parent=comment.get('id'), tracker=tracker)
2881 yield from itertools.islice(comment_entries_iter, min(
2882 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2883
2884 # Keeps track of counts across recursive calls
2885 if not tracker:
2886 tracker = dict(
2887 running_total=0,
2888 est_total=0,
2889 current_page_thread=0,
2890 total_parent_comments=0,
2891 total_reply_comments=0)
2892
2893 # TODO: Deprecated
2894 # YouTube comments have a max depth of 2
2895 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2896 if max_depth:
2897 self._downloader.deprecation_warning(
2898 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2899 if max_depth == 1 and parent:
2900 return
2901
2902 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2903 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2904
2905 continuation = self._extract_continuation(root_continuation_data)
2906
2907 response = None
2908 is_forced_continuation = False
2909 is_first_continuation = parent is None
2910 if is_first_continuation and not continuation:
2911 # Sometimes you can get comments by generating the continuation yourself,
2912 # even if YouTube initially reports them being disabled - e.g. stories comments.
2913 # Note: if the comment section is actually disabled, YouTube may return a response with
2914 # required check_get_keys missing. So we will disable that check initially in this case.
2915 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2916 is_forced_continuation = True
2917
2918 for page_num in itertools.count(0):
2919 if not continuation:
2920 break
2921 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2922 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2923 if page_num == 0:
2924 if is_first_continuation:
2925 note_prefix = 'Downloading comment section API JSON'
2926 else:
2927 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2928 tracker['current_page_thread'], comment_prog_str)
2929 else:
2930 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2931 ' ' if parent else '', ' replies' if parent else '',
2932 page_num, comment_prog_str)
2933
2934 response = self._extract_response(
2935 item_id=None, query=continuation,
2936 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2937 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2938 is_forced_continuation = False
2939 continuation_contents = traverse_obj(
2940 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2941
2942 continuation = None
2943 for continuation_section in continuation_contents:
2944 continuation_items = traverse_obj(
2945 continuation_section,
2946 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2947 get_all=False, expected_type=list) or []
2948 if is_first_continuation:
2949 continuation = extract_header(continuation_items)
2950 is_first_continuation = False
2951 if continuation:
2952 break
2953 continue
2954
2955 for entry in extract_thread(continuation_items):
2956 if not entry:
2957 return
2958 yield entry
2959 continuation = self._extract_continuation({'contents': continuation_items})
2960 if continuation:
2961 break
2962
2963 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2964 if message and not parent and tracker['running_total'] == 0:
2965 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2966
2967 @staticmethod
2968 def _generate_comment_continuation(video_id):
2969 """
2970 Generates initial comment section continuation token from given video id
2971 """
2972 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2973 return base64.b64encode(token.encode()).decode()
2974
2975 def _get_comments(self, ytcfg, video_id, contents, webpage):
2976 """Entry for comment extraction"""
2977 def _real_comment_extract(contents):
2978 renderer = next((
2979 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2980 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2981 yield from self._comment_entries(renderer, ytcfg, video_id)
2982
2983 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2984 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2985
2986 @staticmethod
2987 def _get_checkok_params():
2988 return {'contentCheckOk': True, 'racyCheckOk': True}
2989
2990 @classmethod
2991 def _generate_player_context(cls, sts=None):
2992 context = {
2993 'html5Preference': 'HTML5_PREF_WANTS',
2994 }
2995 if sts is not None:
2996 context['signatureTimestamp'] = sts
2997 return {
2998 'playbackContext': {
2999 'contentPlaybackContext': context
3000 },
3001 **cls._get_checkok_params()
3002 }
3003
3004 @staticmethod
3005 def _is_agegated(player_response):
3006 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3007 return True
3008
3009 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3010 AGE_GATE_REASONS = (
3011 'confirm your age', 'age-restricted', 'inappropriate', # reason
3012 'age_verification_required', 'age_check_required', # status
3013 )
3014 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3015
3016 @staticmethod
3017 def _is_unplayable(player_response):
3018 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3019
3020 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
3021
3022 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3023 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3024 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3025 headers = self.generate_api_headers(
3026 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3027
3028 yt_query = {
3029 'videoId': video_id,
3030 'params': '8AEB' # enable stories
3031 }
3032 yt_query.update(self._generate_player_context(sts))
3033 return self._extract_response(
3034 item_id=video_id, ep='player', query=yt_query,
3035 ytcfg=player_ytcfg, headers=headers, fatal=True,
3036 default_client=client,
3037 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3038 ) or None
3039
3040 def _get_requested_clients(self, url, smuggled_data):
3041 requested_clients = []
3042 default = ['android', 'web']
3043 allowed_clients = sorted(
3044 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3045 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3046 for client in self._configuration_arg('player_client'):
3047 if client in allowed_clients:
3048 requested_clients.append(client)
3049 elif client == 'default':
3050 requested_clients.extend(default)
3051 elif client == 'all':
3052 requested_clients.extend(allowed_clients)
3053 else:
3054 self.report_warning(f'Skipping unsupported client {client}')
3055 if not requested_clients:
3056 requested_clients = default
3057
3058 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3059 requested_clients.extend(
3060 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3061
3062 return orderedSet(requested_clients)
3063
3064 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
3065 initial_pr = None
3066 if webpage:
3067 initial_pr = self._search_json(
3068 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3069
3070 all_clients = set(clients)
3071 clients = clients[::-1]
3072 prs = []
3073
3074 def append_client(*client_names):
3075 """ Append the first client name that exists but not already used """
3076 for client_name in client_names:
3077 actual_client = _split_innertube_client(client_name)[0]
3078 if actual_client in INNERTUBE_CLIENTS:
3079 if actual_client not in all_clients:
3080 clients.append(client_name)
3081 all_clients.add(actual_client)
3082 return
3083
3084 # Android player_response does not have microFormats which are needed for
3085 # extraction of some data. So we return the initial_pr with formats
3086 # stripped out even if not requested by the user
3087 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3088 if initial_pr:
3089 pr = dict(initial_pr)
3090 pr['streamingData'] = None
3091 prs.append(pr)
3092
3093 last_error = None
3094 tried_iframe_fallback = False
3095 player_url = None
3096 while clients:
3097 client, base_client, variant = _split_innertube_client(clients.pop())
3098 player_ytcfg = master_ytcfg if client == 'web' else {}
3099 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3100 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3101
3102 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3103 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3104 if 'js' in self._configuration_arg('player_skip'):
3105 require_js_player = False
3106 player_url = None
3107
3108 if not player_url and not tried_iframe_fallback and require_js_player:
3109 player_url = self._download_player_url(video_id)
3110 tried_iframe_fallback = True
3111
3112 try:
3113 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3114 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3115 except ExtractorError as e:
3116 if last_error:
3117 self.report_warning(last_error)
3118 last_error = e
3119 continue
3120
3121 if pr:
3122 prs.append(pr)
3123
3124 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3125 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3126 append_client(f'{base_client}_creator')
3127 elif self._is_agegated(pr):
3128 if variant == 'tv_embedded':
3129 append_client(f'{base_client}_embedded')
3130 elif not variant:
3131 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3132
3133 if last_error:
3134 if not len(prs):
3135 raise last_error
3136 self.report_warning(last_error)
3137 return prs, player_url
3138
3139 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
3140 itags, stream_ids = {}, []
3141 itag_qualities, res_qualities = {}, {}
3142 q = qualities([
3143 # Normally tiny is the smallest video-only formats. But
3144 # audio-only formats with unknown quality may get tagged as tiny
3145 'tiny',
3146 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3147 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3148 ])
3149 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3150
3151 for fmt in streaming_formats:
3152 if fmt.get('targetDurationSec'):
3153 continue
3154
3155 itag = str_or_none(fmt.get('itag'))
3156 audio_track = fmt.get('audioTrack') or {}
3157 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3158 if stream_id in stream_ids:
3159 continue
3160
3161 quality = fmt.get('quality')
3162 height = int_or_none(fmt.get('height'))
3163 if quality == 'tiny' or not quality:
3164 quality = fmt.get('audioQuality', '').lower() or quality
3165 # The 3gp format (17) in android client has a quality of "small",
3166 # but is actually worse than other formats
3167 if itag == '17':
3168 quality = 'tiny'
3169 if quality:
3170 if itag:
3171 itag_qualities[itag] = quality
3172 if height:
3173 res_qualities[height] = quality
3174 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3175 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3176 # number of fragment that would subsequently requested with (`&sq=N`)
3177 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3178 continue
3179
3180 fmt_url = fmt.get('url')
3181 if not fmt_url:
3182 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3183 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3184 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3185 if not all((sc, fmt_url, player_url, encrypted_sig)):
3186 continue
3187 try:
3188 fmt_url += '&%s=%s' % (
3189 traverse_obj(sc, ('sp', -1)) or 'signature',
3190 self._decrypt_signature(encrypted_sig, video_id, player_url)
3191 )
3192 except ExtractorError as e:
3193 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3194 self.write_debug(e, only_once=True)
3195 continue
3196
3197 query = parse_qs(fmt_url)
3198 throttled = False
3199 if query.get('n'):
3200 try:
3201 fmt_url = update_url_query(fmt_url, {
3202 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3203 except ExtractorError as e:
3204 self.report_warning(
3205 'nsig extraction failed: You may experience throttling for some formats\n'
3206 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3207 self.write_debug(e, only_once=True)
3208 throttled = True
3209
3210 if itag:
3211 itags[itag] = 'https'
3212 stream_ids.append(stream_id)
3213
3214 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3215 language_preference = (
3216 10 if audio_track.get('audioIsDefault') and 10
3217 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3218 else -1)
3219 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3220 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3221 # Make sure to avoid false positives with small duration differences.
3222 # Eg: __2ABJjxzNo, ySuUZEjARPY
3223 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3224 if is_damaged:
3225 self.report_warning(
3226 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3227 dct = {
3228 'asr': int_or_none(fmt.get('audioSampleRate')),
3229 'filesize': int_or_none(fmt.get('contentLength')),
3230 'format_id': itag,
3231 'format_note': join_nonempty(
3232 '%s%s' % (audio_track.get('displayName') or '',
3233 ' (default)' if language_preference > 0 else ''),
3234 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3235 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3236 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3237 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3238 'fps': int_or_none(fmt.get('fps')) or None,
3239 'height': height,
3240 'quality': q(quality),
3241 'has_drm': bool(fmt.get('drmFamilies')),
3242 'tbr': tbr,
3243 'url': fmt_url,
3244 'width': int_or_none(fmt.get('width')),
3245 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3246 'desc' if language_preference < -1 else ''),
3247 'language_preference': language_preference,
3248 # Strictly de-prioritize damaged and 3gp formats
3249 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3250 }
3251 mime_mobj = re.match(
3252 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3253 if mime_mobj:
3254 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3255 dct.update(parse_codecs(mime_mobj.group(2)))
3256 no_audio = dct.get('acodec') == 'none'
3257 no_video = dct.get('vcodec') == 'none'
3258 if no_audio:
3259 dct['vbr'] = tbr
3260 if no_video:
3261 dct['abr'] = tbr
3262 if no_audio or no_video:
3263 dct['downloader_options'] = {
3264 # Youtube throttles chunks >~10M
3265 'http_chunk_size': 10485760,
3266 }
3267 if dct.get('ext'):
3268 dct['container'] = dct['ext'] + '_dash'
3269 yield dct
3270
3271 live_from_start = is_live and self.get_param('live_from_start')
3272 skip_manifests = self._configuration_arg('skip')
3273 if not self.get_param('youtube_include_hls_manifest', True):
3274 skip_manifests.append('hls')
3275 if not self.get_param('youtube_include_dash_manifest', True):
3276 skip_manifests.append('dash')
3277 get_dash = 'dash' not in skip_manifests and (
3278 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3279 get_hls = not live_from_start and 'hls' not in skip_manifests
3280
3281 def process_manifest_format(f, proto, itag):
3282 if itag in itags:
3283 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3284 return False
3285 itag = f'{itag}-{proto}'
3286 if itag:
3287 f['format_id'] = itag
3288 itags[itag] = proto
3289
3290 f['quality'] = next((
3291 q(qdict[val])
3292 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3293 if val in qdict), -1)
3294 return True
3295
3296 for sd in streaming_data:
3297 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3298 if hls_manifest_url:
3299 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3300 if process_manifest_format(f, 'hls', self._search_regex(
3301 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3302 yield f
3303
3304 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3305 if dash_manifest_url:
3306 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3307 if process_manifest_format(f, 'dash', f['format_id']):
3308 f['filesize'] = int_or_none(self._search_regex(
3309 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3310 if live_from_start:
3311 f['is_from_start'] = True
3312
3313 yield f
3314
3315 def _extract_storyboard(self, player_responses, duration):
3316 spec = get_first(
3317 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3318 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3319 if not base_url:
3320 return
3321 L = len(spec) - 1
3322 for i, args in enumerate(spec):
3323 args = args.split('#')
3324 counts = list(map(int_or_none, args[:5]))
3325 if len(args) != 8 or not all(counts):
3326 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3327 continue
3328 width, height, frame_count, cols, rows = counts
3329 N, sigh = args[6:]
3330
3331 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3332 fragment_count = frame_count / (cols * rows)
3333 fragment_duration = duration / fragment_count
3334 yield {
3335 'format_id': f'sb{i}',
3336 'format_note': 'storyboard',
3337 'ext': 'mhtml',
3338 'protocol': 'mhtml',
3339 'acodec': 'none',
3340 'vcodec': 'none',
3341 'url': url,
3342 'width': width,
3343 'height': height,
3344 'fps': frame_count / duration,
3345 'rows': rows,
3346 'columns': cols,
3347 'fragments': [{
3348 'url': url.replace('$M', str(j)),
3349 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3350 } for j in range(math.ceil(fragment_count))],
3351 }
3352
3353 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3354 webpage = None
3355 if 'webpage' not in self._configuration_arg('player_skip'):
3356 webpage = self._download_webpage(
3357 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
3358
3359 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3360
3361 player_responses, player_url = self._extract_player_responses(
3362 self._get_requested_clients(url, smuggled_data),
3363 video_id, webpage, master_ytcfg)
3364
3365 return webpage, master_ytcfg, player_responses, player_url
3366
3367 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3368 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3369 is_live = get_first(video_details, 'isLive')
3370 if is_live is None:
3371 is_live = get_first(live_broadcast_details, 'isLiveNow')
3372
3373 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3374 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
3375
3376 return live_broadcast_details, is_live, streaming_data, formats
3377
3378 def _real_extract(self, url):
3379 url, smuggled_data = unsmuggle_url(url, {})
3380 video_id = self._match_id(url)
3381
3382 base_url = self.http_scheme() + '//www.youtube.com/'
3383 webpage_url = base_url + 'watch?v=' + video_id
3384
3385 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3386
3387 playability_statuses = traverse_obj(
3388 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3389
3390 trailer_video_id = get_first(
3391 playability_statuses,
3392 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3393 expected_type=str)
3394 if trailer_video_id:
3395 return self.url_result(
3396 trailer_video_id, self.ie_key(), trailer_video_id)
3397
3398 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3399 if webpage else (lambda x: None))
3400
3401 video_details = traverse_obj(
3402 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3403 microformats = traverse_obj(
3404 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3405 expected_type=dict, default=[])
3406 video_title = (
3407 get_first(video_details, 'title')
3408 or self._get_text(microformats, (..., 'title'))
3409 or search_meta(['og:title', 'twitter:title', 'title']))
3410 video_description = get_first(video_details, 'shortDescription')
3411
3412 multifeed_metadata_list = get_first(
3413 player_responses,
3414 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3415 expected_type=str)
3416 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3417 if self.get_param('noplaylist'):
3418 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3419 else:
3420 entries = []
3421 feed_ids = []
3422 for feed in multifeed_metadata_list.split(','):
3423 # Unquote should take place before split on comma (,) since textual
3424 # fields may contain comma as well (see
3425 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3426 feed_data = urllib.parse.parse_qs(
3427 urllib.parse.unquote_plus(feed))
3428
3429 def feed_entry(name):
3430 return try_get(
3431 feed_data, lambda x: x[name][0], str)
3432
3433 feed_id = feed_entry('id')
3434 if not feed_id:
3435 continue
3436 feed_title = feed_entry('title')
3437 title = video_title
3438 if feed_title:
3439 title += ' (%s)' % feed_title
3440 entries.append({
3441 '_type': 'url_transparent',
3442 'ie_key': 'Youtube',
3443 'url': smuggle_url(
3444 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3445 {'force_singlefeed': True}),
3446 'title': title,
3447 })
3448 feed_ids.append(feed_id)
3449 self.to_screen(
3450 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3451 % (', '.join(feed_ids), video_id))
3452 return self.playlist_result(
3453 entries, video_id, video_title, video_description)
3454
3455 duration = int_or_none(
3456 get_first(video_details, 'lengthSeconds')
3457 or get_first(microformats, 'lengthSeconds')
3458 or parse_duration(search_meta('duration'))) or None
3459
3460 if get_first(video_details, 'isPostLiveDvr'):
3461 self.write_debug('Video is in Post-Live Manifestless mode')
3462 if (duration or 0) > 4 * 3600:
3463 self.report_warning(
3464 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3465 'This is a known issue and patches are welcome')
3466
3467 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3468 video_id, microformats, video_details, player_responses, player_url, duration)
3469
3470 if not formats:
3471 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3472 self.report_drm(video_id)
3473 pemr = get_first(
3474 playability_statuses,
3475 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3476 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3477 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3478 if subreason:
3479 if subreason == 'The uploader has not made this video available in your country.':
3480 countries = get_first(microformats, 'availableCountries')
3481 if not countries:
3482 regions_allowed = search_meta('regionsAllowed')
3483 countries = regions_allowed.split(',') if regions_allowed else None
3484 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3485 reason += f'. {subreason}'
3486 if reason:
3487 self.raise_no_formats(reason, expected=True)
3488
3489 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3490 if not keywords and webpage:
3491 keywords = [
3492 unescapeHTML(m.group('content'))
3493 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3494 for keyword in keywords:
3495 if keyword.startswith('yt:stretch='):
3496 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3497 if mobj:
3498 # NB: float is intentional for forcing float division
3499 w, h = (float(v) for v in mobj.groups())
3500 if w > 0 and h > 0:
3501 ratio = w / h
3502 for f in formats:
3503 if f.get('vcodec') != 'none':
3504 f['stretched_ratio'] = ratio
3505 break
3506 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3507 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3508 if thumbnail_url:
3509 thumbnails.append({
3510 'url': thumbnail_url,
3511 })
3512 original_thumbnails = thumbnails.copy()
3513
3514 # The best resolution thumbnails sometimes does not appear in the webpage
3515 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3516 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3517 thumbnail_names = [
3518 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3519 # in resolution, these are not the custom thumbnail. So de-prioritize them
3520 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3521 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3522 ]
3523 n_thumbnail_names = len(thumbnail_names)
3524 thumbnails.extend({
3525 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3526 video_id=video_id, name=name, ext=ext,
3527 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3528 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3529 for thumb in thumbnails:
3530 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3531 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3532 self._remove_duplicate_formats(thumbnails)
3533 self._downloader._sort_thumbnails(original_thumbnails)
3534
3535 category = get_first(microformats, 'category') or search_meta('genre')
3536 channel_id = str_or_none(
3537 get_first(video_details, 'channelId')
3538 or get_first(microformats, 'externalChannelId')
3539 or search_meta('channelId'))
3540 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3541
3542 live_content = get_first(video_details, 'isLiveContent')
3543 is_upcoming = get_first(video_details, 'isUpcoming')
3544 if is_live is None:
3545 if is_upcoming or live_content is False:
3546 is_live = False
3547 if is_upcoming is None and (live_content or is_live):
3548 is_upcoming = False
3549 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3550 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3551 if not duration and live_end_time and live_start_time:
3552 duration = live_end_time - live_start_time
3553
3554 if is_live and self.get_param('live_from_start'):
3555 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3556
3557 formats.extend(self._extract_storyboard(player_responses, duration))
3558
3559 # Source is given priority since formats that throttle are given lower source_preference
3560 # When throttling issue is fully fixed, remove this
3561 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3562
3563 info = {
3564 'id': video_id,
3565 'title': video_title,
3566 'formats': formats,
3567 'thumbnails': thumbnails,
3568 # The best thumbnail that we are sure exists. Prevents unnecessary
3569 # URL checking if user don't care about getting the best possible thumbnail
3570 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3571 'description': video_description,
3572 'uploader': get_first(video_details, 'author'),
3573 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3574 'uploader_url': owner_profile_url,
3575 'channel_id': channel_id,
3576 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
3577 'duration': duration,
3578 'view_count': int_or_none(
3579 get_first((video_details, microformats), (..., 'viewCount'))
3580 or search_meta('interactionCount')),
3581 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3582 'age_limit': 18 if (
3583 get_first(microformats, 'isFamilySafe') is False
3584 or search_meta('isFamilyFriendly') == 'false'
3585 or search_meta('og:restrictions:age') == '18+') else 0,
3586 'webpage_url': webpage_url,
3587 'categories': [category] if category else None,
3588 'tags': keywords,
3589 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3590 'is_live': is_live,
3591 'was_live': (False if is_live or is_upcoming or live_content is False
3592 else None if is_live is None or is_upcoming is None
3593 else live_content),
3594 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3595 'release_timestamp': live_start_time,
3596 }
3597
3598 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3599 if pctr:
3600 def get_lang_code(track):
3601 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3602 or track.get('languageCode'))
3603
3604 # Converted into dicts to remove duplicates
3605 captions = {
3606 get_lang_code(sub): sub
3607 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3608 translation_languages = {
3609 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3610 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3611
3612 def process_language(container, base_url, lang_code, sub_name, query):
3613 lang_subs = container.setdefault(lang_code, [])
3614 for fmt in self._SUBTITLE_FORMATS:
3615 query.update({
3616 'fmt': fmt,
3617 })
3618 lang_subs.append({
3619 'ext': fmt,
3620 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3621 'name': sub_name,
3622 })
3623
3624 subtitles, automatic_captions = {}, {}
3625 for lang_code, caption_track in captions.items():
3626 base_url = caption_track.get('baseUrl')
3627 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3628 if not base_url:
3629 continue
3630 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3631 if caption_track.get('kind') != 'asr':
3632 if not lang_code:
3633 continue
3634 process_language(
3635 subtitles, base_url, lang_code, lang_name, {})
3636 if not caption_track.get('isTranslatable'):
3637 continue
3638 for trans_code, trans_name in translation_languages.items():
3639 if not trans_code:
3640 continue
3641 orig_trans_code = trans_code
3642 if caption_track.get('kind') != 'asr':
3643 if 'translated_subs' in self._configuration_arg('skip'):
3644 continue
3645 trans_code += f'-{lang_code}'
3646 trans_name += format_field(lang_name, None, ' from %s')
3647 # Add an "-orig" label to the original language so that it can be distinguished.
3648 # The subs are returned without "-orig" as well for compatibility
3649 if lang_code == f'a-{orig_trans_code}':
3650 process_language(
3651 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3652 # Setting tlang=lang returns damaged subtitles.
3653 process_language(automatic_captions, base_url, trans_code, trans_name,
3654 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
3655 info['automatic_captions'] = automatic_captions
3656 info['subtitles'] = subtitles
3657
3658 parsed_url = urllib.parse.urlparse(url)
3659 for component in [parsed_url.fragment, parsed_url.query]:
3660 query = urllib.parse.parse_qs(component)
3661 for k, v in query.items():
3662 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3663 d_k += '_time'
3664 if d_k not in info and k in s_ks:
3665 info[d_k] = parse_duration(query[k][0])
3666
3667 # Youtube Music Auto-generated description
3668 if video_description:
3669 mobj = re.search(
3670 r'''(?xs)
3671 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3672 (?P<album>[^\n]+)
3673 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3674 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3675 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3676 .+\nAuto-generated\ by\ YouTube\.\s*$
3677 ''', video_description)
3678 if mobj:
3679 release_year = mobj.group('release_year')
3680 release_date = mobj.group('release_date')
3681 if release_date:
3682 release_date = release_date.replace('-', '')
3683 if not release_year:
3684 release_year = release_date[:4]
3685 info.update({
3686 'album': mobj.group('album'.strip()),
3687 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3688 'track': mobj.group('track').strip(),
3689 'release_date': release_date,
3690 'release_year': int_or_none(release_year),
3691 })
3692
3693 initial_data = None
3694 if webpage:
3695 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
3696 if not initial_data:
3697 query = {'videoId': video_id}
3698 query.update(self._get_checkok_params())
3699 initial_data = self._extract_response(
3700 item_id=video_id, ep='next', fatal=False,
3701 ytcfg=master_ytcfg, query=query,
3702 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3703 note='Downloading initial data API JSON')
3704
3705 info['comment_count'] = traverse_obj(initial_data, (
3706 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3707 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3708 ), (
3709 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3710 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3711 ), expected_type=int_or_none, get_all=False)
3712
3713 try: # This will error if there is no livechat
3714 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3715 except (KeyError, IndexError, TypeError):
3716 pass
3717 else:
3718 info.setdefault('subtitles', {})['live_chat'] = [{
3719 # url is needed to set cookies
3720 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3721 'video_id': video_id,
3722 'ext': 'json',
3723 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3724 }]
3725
3726 if initial_data:
3727 info['chapters'] = (
3728 self._extract_chapters_from_json(initial_data, duration)
3729 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3730 or self._extract_chapters_from_description(video_description, duration)
3731 or None)
3732
3733 contents = traverse_obj(
3734 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3735 expected_type=list, default=[])
3736
3737 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3738 if vpir:
3739 stl = vpir.get('superTitleLink')
3740 if stl:
3741 stl = self._get_text(stl)
3742 if try_get(
3743 vpir,
3744 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3745 info['location'] = stl
3746 else:
3747 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
3748 if mobj:
3749 info.update({
3750 'series': mobj.group(1),
3751 'season_number': int(mobj.group(2)),
3752 'episode_number': int(mobj.group(3)),
3753 })
3754 for tlb in (try_get(
3755 vpir,
3756 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3757 list) or []):
3758 tbr = tlb.get('toggleButtonRenderer') or {}
3759 for getter, regex in [(
3760 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3761 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3762 lambda x: x['accessibility'],
3763 lambda x: x['accessibilityData']['accessibilityData'],
3764 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3765 label = (try_get(tbr, getter, dict) or {}).get('label')
3766 if label:
3767 mobj = re.match(regex, label)
3768 if mobj:
3769 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3770 break
3771 sbr_tooltip = try_get(
3772 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3773 if sbr_tooltip:
3774 like_count, dislike_count = sbr_tooltip.split(' / ')
3775 info.update({
3776 'like_count': str_to_int(like_count),
3777 'dislike_count': str_to_int(dislike_count),
3778 })
3779 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3780 if vsir:
3781 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3782 info.update({
3783 'channel': self._get_text(vor, 'title'),
3784 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3785
3786 rows = try_get(
3787 vsir,
3788 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3789 list) or []
3790 multiple_songs = False
3791 for row in rows:
3792 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3793 multiple_songs = True
3794 break
3795 for row in rows:
3796 mrr = row.get('metadataRowRenderer') or {}
3797 mrr_title = mrr.get('title')
3798 if not mrr_title:
3799 continue
3800 mrr_title = self._get_text(mrr, 'title')
3801 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3802 if mrr_title == 'License':
3803 info['license'] = mrr_contents_text
3804 elif not multiple_songs:
3805 if mrr_title == 'Album':
3806 info['album'] = mrr_contents_text
3807 elif mrr_title == 'Artist':
3808 info['artist'] = mrr_contents_text
3809 elif mrr_title == 'Song':
3810 info['track'] = mrr_contents_text
3811
3812 fallbacks = {
3813 'channel': 'uploader',
3814 'channel_id': 'uploader_id',
3815 'channel_url': 'uploader_url',
3816 }
3817
3818 # The upload date for scheduled, live and past live streams / premieres in microformats
3819 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3820 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3821 upload_date = (
3822 unified_strdate(get_first(microformats, 'uploadDate'))
3823 or unified_strdate(search_meta('uploadDate')))
3824 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3825 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
3826 info['upload_date'] = upload_date
3827
3828 for to, frm in fallbacks.items():
3829 if not info.get(to):
3830 info[to] = info.get(frm)
3831
3832 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3833 v = info.get(s_k)
3834 if v:
3835 info[d_k] = v
3836
3837 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3838 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3839 is_membersonly = None
3840 is_premium = None
3841 if initial_data and is_private is not None:
3842 is_membersonly = False
3843 is_premium = False
3844 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3845 badge_labels = set()
3846 for content in contents:
3847 if not isinstance(content, dict):
3848 continue
3849 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3850 for badge_label in badge_labels:
3851 if badge_label.lower() == 'members only':
3852 is_membersonly = True
3853 elif badge_label.lower() == 'premium':
3854 is_premium = True
3855 elif badge_label.lower() == 'unlisted':
3856 is_unlisted = True
3857
3858 info['availability'] = self._availability(
3859 is_private=is_private,
3860 needs_premium=is_premium,
3861 needs_subscription=is_membersonly,
3862 needs_auth=info['age_limit'] >= 18,
3863 is_unlisted=None if is_private is None else is_unlisted)
3864
3865 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3866
3867 self.mark_watched(video_id, player_responses)
3868
3869 return info
3870
3871
3872class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3873
3874 @staticmethod
3875 def passthrough_smuggled_data(func):
3876 def _smuggle(entries, smuggled_data):
3877 for entry in entries:
3878 # TODO: Convert URL to music.youtube instead.
3879 # Do we need to passthrough any other smuggled_data?
3880 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3881 yield entry
3882
3883 @functools.wraps(func)
3884 def wrapper(self, url):
3885 url, smuggled_data = unsmuggle_url(url, {})
3886 if self.is_music_url(url):
3887 smuggled_data['is_music_url'] = True
3888 info_dict = func(self, url, smuggled_data)
3889 if smuggled_data and info_dict.get('entries'):
3890 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3891 return info_dict
3892 return wrapper
3893
3894 def _extract_channel_id(self, webpage):
3895 channel_id = self._html_search_meta(
3896 'channelId', webpage, 'channel id', default=None)
3897 if channel_id:
3898 return channel_id
3899 channel_url = self._html_search_meta(
3900 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3901 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3902 'twitter:app:url:googleplay'), webpage, 'channel url')
3903 return self._search_regex(
3904 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3905 channel_url, 'channel id')
3906
3907 @staticmethod
3908 def _extract_basic_item_renderer(item):
3909 # Modified from _extract_grid_item_renderer
3910 known_basic_renderers = (
3911 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3912 )
3913 for key, renderer in item.items():
3914 if not isinstance(renderer, dict):
3915 continue
3916 elif key in known_basic_renderers:
3917 return renderer
3918 elif key.startswith('grid') and key.endswith('Renderer'):
3919 return renderer
3920
3921 def _grid_entries(self, grid_renderer):
3922 for item in grid_renderer['items']:
3923 if not isinstance(item, dict):
3924 continue
3925 renderer = self._extract_basic_item_renderer(item)
3926 if not isinstance(renderer, dict):
3927 continue
3928 title = self._get_text(renderer, 'title')
3929
3930 # playlist
3931 playlist_id = renderer.get('playlistId')
3932 if playlist_id:
3933 yield self.url_result(
3934 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3935 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3936 video_title=title)
3937 continue
3938 # video
3939 video_id = renderer.get('videoId')
3940 if video_id:
3941 yield self._extract_video(renderer)
3942 continue
3943 # channel
3944 channel_id = renderer.get('channelId')
3945 if channel_id:
3946 yield self.url_result(
3947 'https://www.youtube.com/channel/%s' % channel_id,
3948 ie=YoutubeTabIE.ie_key(), video_title=title)
3949 continue
3950 # generic endpoint URL support
3951 ep_url = urljoin('https://www.youtube.com/', try_get(
3952 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3953 str))
3954 if ep_url:
3955 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3956 if ie.suitable(ep_url):
3957 yield self.url_result(
3958 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3959 break
3960
3961 def _music_reponsive_list_entry(self, renderer):
3962 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3963 if video_id:
3964 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3965 ie=YoutubeIE.ie_key(), video_id=video_id)
3966 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3967 if playlist_id:
3968 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3969 if video_id:
3970 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3971 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3972 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3973 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3974 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3975 if browse_id:
3976 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3977 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3978
3979 def _shelf_entries_from_content(self, shelf_renderer):
3980 content = shelf_renderer.get('content')
3981 if not isinstance(content, dict):
3982 return
3983 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3984 if renderer:
3985 # TODO: add support for nested playlists so each shelf is processed
3986 # as separate playlist
3987 # TODO: this includes only first N items
3988 yield from self._grid_entries(renderer)
3989 renderer = content.get('horizontalListRenderer')
3990 if renderer:
3991 # TODO
3992 pass
3993
3994 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3995 ep = try_get(
3996 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3997 str)
3998 shelf_url = urljoin('https://www.youtube.com', ep)
3999 if shelf_url:
4000 # Skipping links to another channels, note that checking for
4001 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4002 # will not work
4003 if skip_channels and '/channels?' in shelf_url:
4004 return
4005 title = self._get_text(shelf_renderer, 'title')
4006 yield self.url_result(shelf_url, video_title=title)
4007 # Shelf may not contain shelf URL, fallback to extraction from content
4008 yield from self._shelf_entries_from_content(shelf_renderer)
4009
4010 def _playlist_entries(self, video_list_renderer):
4011 for content in video_list_renderer['contents']:
4012 if not isinstance(content, dict):
4013 continue
4014 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4015 if not isinstance(renderer, dict):
4016 continue
4017 video_id = renderer.get('videoId')
4018 if not video_id:
4019 continue
4020 yield self._extract_video(renderer)
4021
4022 def _rich_entries(self, rich_grid_renderer):
4023 renderer = try_get(
4024 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
4025 video_id = renderer.get('videoId')
4026 if not video_id:
4027 return
4028 yield self._extract_video(renderer)
4029
4030 def _video_entry(self, video_renderer):
4031 video_id = video_renderer.get('videoId')
4032 if video_id:
4033 return self._extract_video(video_renderer)
4034
4035 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4036 url = urljoin('https://youtube.com', traverse_obj(
4037 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4038 if url:
4039 return self.url_result(
4040 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4041
4042 def _post_thread_entries(self, post_thread_renderer):
4043 post_renderer = try_get(
4044 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4045 if not post_renderer:
4046 return
4047 # video attachment
4048 video_renderer = try_get(
4049 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4050 video_id = video_renderer.get('videoId')
4051 if video_id:
4052 entry = self._extract_video(video_renderer)
4053 if entry:
4054 yield entry
4055 # playlist attachment
4056 playlist_id = try_get(
4057 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
4058 if playlist_id:
4059 yield self.url_result(
4060 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4061 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4062 # inline video links
4063 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4064 for run in runs:
4065 if not isinstance(run, dict):
4066 continue
4067 ep_url = try_get(
4068 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
4069 if not ep_url:
4070 continue
4071 if not YoutubeIE.suitable(ep_url):
4072 continue
4073 ep_video_id = YoutubeIE._match_id(ep_url)
4074 if video_id == ep_video_id:
4075 continue
4076 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
4077
4078 def _post_thread_continuation_entries(self, post_thread_continuation):
4079 contents = post_thread_continuation.get('contents')
4080 if not isinstance(contents, list):
4081 return
4082 for content in contents:
4083 renderer = content.get('backstagePostThreadRenderer')
4084 if isinstance(renderer, dict):
4085 yield from self._post_thread_entries(renderer)
4086 continue
4087 renderer = content.get('videoRenderer')
4088 if isinstance(renderer, dict):
4089 yield self._video_entry(renderer)
4090
4091 r''' # unused
4092 def _rich_grid_entries(self, contents):
4093 for content in contents:
4094 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4095 if video_renderer:
4096 entry = self._video_entry(video_renderer)
4097 if entry:
4098 yield entry
4099 '''
4100
4101 def _extract_entries(self, parent_renderer, continuation_list):
4102 # continuation_list is modified in-place with continuation_list = [continuation_token]
4103 continuation_list[:] = [None]
4104 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4105 for content in contents:
4106 if not isinstance(content, dict):
4107 continue
4108 is_renderer = traverse_obj(
4109 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4110 expected_type=dict)
4111 if not is_renderer:
4112 renderer = content.get('richItemRenderer')
4113 if renderer:
4114 for entry in self._rich_entries(renderer):
4115 yield entry
4116 continuation_list[0] = self._extract_continuation(parent_renderer)
4117 continue
4118 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4119 for isr_content in isr_contents:
4120 if not isinstance(isr_content, dict):
4121 continue
4122
4123 known_renderers = {
4124 'playlistVideoListRenderer': self._playlist_entries,
4125 'gridRenderer': self._grid_entries,
4126 'reelShelfRenderer': self._grid_entries,
4127 'shelfRenderer': self._shelf_entries,
4128 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4129 'backstagePostThreadRenderer': self._post_thread_entries,
4130 'videoRenderer': lambda x: [self._video_entry(x)],
4131 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4132 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4133 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4134 }
4135 for key, renderer in isr_content.items():
4136 if key not in known_renderers:
4137 continue
4138 for entry in known_renderers[key](renderer):
4139 if entry:
4140 yield entry
4141 continuation_list[0] = self._extract_continuation(renderer)
4142 break
4143
4144 if not continuation_list[0]:
4145 continuation_list[0] = self._extract_continuation(is_renderer)
4146
4147 if not continuation_list[0]:
4148 continuation_list[0] = self._extract_continuation(parent_renderer)
4149
4150 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4151 continuation_list = [None]
4152 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4153 tab_content = try_get(tab, lambda x: x['content'], dict)
4154 if not tab_content:
4155 return
4156 parent_renderer = (
4157 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4158 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4159 yield from extract_entries(parent_renderer)
4160 continuation = continuation_list[0]
4161
4162 for page_num in itertools.count(1):
4163 if not continuation:
4164 break
4165 headers = self.generate_api_headers(
4166 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4167 response = self._extract_response(
4168 item_id=f'{item_id} page {page_num}',
4169 query=continuation, headers=headers, ytcfg=ytcfg,
4170 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4171
4172 if not response:
4173 break
4174 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4175 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4176 visitor_data = self._extract_visitor_data(response) or visitor_data
4177
4178 known_continuation_renderers = {
4179 'playlistVideoListContinuation': self._playlist_entries,
4180 'gridContinuation': self._grid_entries,
4181 'itemSectionContinuation': self._post_thread_continuation_entries,
4182 'sectionListContinuation': extract_entries, # for feeds
4183 }
4184 continuation_contents = try_get(
4185 response, lambda x: x['continuationContents'], dict) or {}
4186 continuation_renderer = None
4187 for key, value in continuation_contents.items():
4188 if key not in known_continuation_renderers:
4189 continue
4190 continuation_renderer = value
4191 continuation_list = [None]
4192 yield from known_continuation_renderers[key](continuation_renderer)
4193 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4194 break
4195 if continuation_renderer:
4196 continue
4197
4198 known_renderers = {
4199 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4200 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4201 'gridVideoRenderer': (self._grid_entries, 'items'),
4202 'gridChannelRenderer': (self._grid_entries, 'items'),
4203 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4204 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4205 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4206 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
4207 }
4208 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4209 continuation_items = try_get(
4210 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
4211 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4212 video_items_renderer = None
4213 for key, value in continuation_item.items():
4214 if key not in known_renderers:
4215 continue
4216 video_items_renderer = {known_renderers[key][1]: continuation_items}
4217 continuation_list = [None]
4218 yield from known_renderers[key][0](video_items_renderer)
4219 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4220 break
4221 if video_items_renderer:
4222 continue
4223 break
4224
4225 @staticmethod
4226 def _extract_selected_tab(tabs, fatal=True):
4227 for tab in tabs:
4228 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4229 if renderer.get('selected') is True:
4230 return renderer
4231 else:
4232 if fatal:
4233 raise ExtractorError('Unable to find selected tab')
4234
4235 def _extract_uploader(self, data):
4236 uploader = {}
4237 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4238 owner = try_get(
4239 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4240 if owner:
4241 owner_text = owner.get('text')
4242 uploader['uploader'] = self._search_regex(
4243 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
4244 uploader['uploader_id'] = try_get(
4245 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
4246 uploader['uploader_url'] = urljoin(
4247 'https://www.youtube.com/',
4248 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4249 return {k: v for k, v in uploader.items() if v is not None}
4250
4251 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4252 playlist_id = title = description = channel_url = channel_name = channel_id = None
4253 tags = []
4254
4255 selected_tab = self._extract_selected_tab(tabs)
4256 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4257 renderer = try_get(
4258 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4259 if renderer:
4260 channel_name = renderer.get('title')
4261 channel_url = renderer.get('channelUrl')
4262 channel_id = renderer.get('externalId')
4263 else:
4264 renderer = try_get(
4265 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
4266
4267 if renderer:
4268 title = renderer.get('title')
4269 description = renderer.get('description', '')
4270 playlist_id = channel_id
4271 tags = renderer.get('keywords', '').split()
4272
4273 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4274 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4275 def _get_uncropped(url):
4276 return url_or_none((url or '').split('=')[0] + '=s0')
4277
4278 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4279 if avatar_thumbnails:
4280 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4281 if uncropped_avatar:
4282 avatar_thumbnails.append({
4283 'url': uncropped_avatar,
4284 'id': 'avatar_uncropped',
4285 'preference': 1
4286 })
4287
4288 channel_banners = self._extract_thumbnails(
4289 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4290 for banner in channel_banners:
4291 banner['preference'] = -10
4292
4293 if channel_banners:
4294 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4295 if uncropped_banner:
4296 channel_banners.append({
4297 'url': uncropped_banner,
4298 'id': 'banner_uncropped',
4299 'preference': -5
4300 })
4301
4302 primary_thumbnails = self._extract_thumbnails(
4303 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4304
4305 if playlist_id is None:
4306 playlist_id = item_id
4307
4308 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4309 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
4310 if title is None:
4311 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4312 title += format_field(selected_tab, 'title', ' - %s')
4313 title += format_field(selected_tab, 'expandedText', ' - %s')
4314
4315 metadata = {
4316 'playlist_id': playlist_id,
4317 'playlist_title': title,
4318 'playlist_description': description,
4319 'uploader': channel_name,
4320 'uploader_id': channel_id,
4321 'uploader_url': channel_url,
4322 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4323 'tags': tags,
4324 'view_count': self._get_count(playlist_stats, 1),
4325 'availability': self._extract_availability(data),
4326 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4327 'playlist_count': self._get_count(playlist_stats, 0),
4328 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4329 }
4330 if not channel_id:
4331 metadata.update(self._extract_uploader(data))
4332 metadata.update({
4333 'channel': metadata['uploader'],
4334 'channel_id': metadata['uploader_id'],
4335 'channel_url': metadata['uploader_url']})
4336 return self.playlist_result(
4337 self._entries(
4338 selected_tab, playlist_id, ytcfg,
4339 self._extract_account_syncid(ytcfg, data),
4340 self._extract_visitor_data(data, ytcfg)),
4341 **metadata)
4342
4343 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
4344 first_id = last_id = response = None
4345 for page_num in itertools.count(1):
4346 videos = list(self._playlist_entries(playlist))
4347 if not videos:
4348 return
4349 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4350 if start >= len(videos):
4351 return
4352 yield from videos[start:]
4353 first_id = first_id or videos[0]['id']
4354 last_id = videos[-1]['id']
4355 watch_endpoint = try_get(
4356 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4357 headers = self.generate_api_headers(
4358 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4359 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4360 query = {
4361 'playlistId': playlist_id,
4362 'videoId': watch_endpoint.get('videoId') or last_id,
4363 'index': watch_endpoint.get('index') or len(videos),
4364 'params': watch_endpoint.get('params') or 'OAE%3D'
4365 }
4366 response = self._extract_response(
4367 item_id='%s page %d' % (playlist_id, page_num),
4368 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4369 check_get_keys='contents'
4370 )
4371 playlist = try_get(
4372 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4373
4374 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4375 title = playlist.get('title') or try_get(
4376 data, lambda x: x['titleText']['simpleText'], str)
4377 playlist_id = playlist.get('playlistId') or item_id
4378
4379 # Delegating everything except mix playlists to regular tab-based playlist URL
4380 playlist_url = urljoin(url, try_get(
4381 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4382 str))
4383
4384 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4385 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4386 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4387
4388 if playlist_url and playlist_url != url and not is_known_unviewable:
4389 return self.url_result(
4390 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4391 video_title=title)
4392
4393 return self.playlist_result(
4394 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
4395 playlist_id=playlist_id, playlist_title=title)
4396
4397 def _extract_availability(self, data):
4398 """
4399 Gets the availability of a given playlist/tab.
4400 Note: Unless YouTube tells us explicitly, we do not assume it is public
4401 @param data: response
4402 """
4403 is_private = is_unlisted = None
4404 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4405 badge_labels = self._extract_badges(renderer)
4406
4407 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4408 privacy_dropdown_entries = try_get(
4409 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4410 for renderer_dict in privacy_dropdown_entries:
4411 is_selected = try_get(
4412 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4413 if not is_selected:
4414 continue
4415 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4416 if label:
4417 badge_labels.add(label.lower())
4418 break
4419
4420 for badge_label in badge_labels:
4421 if badge_label == 'unlisted':
4422 is_unlisted = True
4423 elif badge_label == 'private':
4424 is_private = True
4425 elif badge_label == 'public':
4426 is_unlisted = is_private = False
4427 return self._availability(is_private, False, False, False, is_unlisted)
4428
4429 @staticmethod
4430 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4431 sidebar_renderer = try_get(
4432 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4433 for item in sidebar_renderer:
4434 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4435 if renderer:
4436 return renderer
4437
4438 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4439 """
4440 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4441 """
4442 browse_id = params = None
4443 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4444 if not renderer:
4445 return
4446 menu_renderer = try_get(
4447 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4448 for menu_item in menu_renderer:
4449 if not isinstance(menu_item, dict):
4450 continue
4451 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4452 text = try_get(
4453 nav_item_renderer, lambda x: x['text']['simpleText'], str)
4454 if not text or text.lower() != 'show unavailable videos':
4455 continue
4456 browse_endpoint = try_get(
4457 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4458 browse_id = browse_endpoint.get('browseId')
4459 params = browse_endpoint.get('params')
4460 break
4461
4462 headers = self.generate_api_headers(
4463 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4464 visitor_data=self._extract_visitor_data(data, ytcfg))
4465 query = {
4466 'params': params or 'wgYCCAA=',
4467 'browseId': browse_id or 'VL%s' % item_id
4468 }
4469 return self._extract_response(
4470 item_id=item_id, headers=headers, query=query,
4471 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4472 note='Downloading API JSON with unavailable videos')
4473
4474 @functools.cached_property
4475 def skip_webpage(self):
4476 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4477
4478 def _extract_webpage(self, url, item_id, fatal=True):
4479 retries = self.get_param('extractor_retries', 3)
4480 count = -1
4481 webpage = data = last_error = None
4482 while count < retries:
4483 count += 1
4484 # Sometimes youtube returns a webpage with incomplete ytInitialData
4485 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4486 if last_error:
4487 self.report_warning('%s. Retrying ...' % last_error)
4488 try:
4489 webpage = self._download_webpage(
4490 url, item_id,
4491 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4492 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4493 except ExtractorError as e:
4494 if isinstance(e.cause, network_exceptions):
4495 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
4496 last_error = error_to_compat_str(e.cause or e.msg)
4497 if count < retries:
4498 continue
4499 if fatal:
4500 raise
4501 self.report_warning(error_to_compat_str(e))
4502 break
4503 else:
4504 try:
4505 self._extract_and_report_alerts(data)
4506 except ExtractorError as e:
4507 if fatal:
4508 raise
4509 self.report_warning(error_to_compat_str(e))
4510 break
4511
4512 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4513 break
4514
4515 last_error = 'Incomplete yt initial data received'
4516 if count >= retries:
4517 if fatal:
4518 raise ExtractorError(last_error)
4519 self.report_warning(last_error)
4520 break
4521
4522 return webpage, data
4523
4524 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4525 """Use if failed to extract ytcfg (and data) from initial webpage"""
4526 if not ytcfg and self.is_authenticated:
4527 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4528 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4529 raise ExtractorError(
4530 f'{msg}. If you are not downloading private content, or '
4531 'your cookies are only for the first account and channel,'
4532 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4533 expected=True)
4534 self.report_warning(msg, only_once=True)
4535
4536 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4537 data = None
4538 if not self.skip_webpage:
4539 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4540 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4541 # Reject webpage data if redirected to home page without explicitly requesting
4542 selected_tab = self._extract_selected_tab(traverse_obj(
4543 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4544 if (url != 'https://www.youtube.com/feed/recommended'
4545 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4546 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4547 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4548 if fatal:
4549 raise ExtractorError(msg, expected=True)
4550 self.report_warning(msg, only_once=True)
4551 if not data:
4552 self._report_playlist_authcheck(ytcfg, fatal=fatal)
4553 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4554 return data, ytcfg
4555
4556 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4557 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4558 resolve_response = self._extract_response(
4559 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4560 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4561 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4562 for ep_key, ep in endpoints.items():
4563 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4564 if params:
4565 return self._extract_response(
4566 item_id=item_id, query=params, ep=ep, headers=headers,
4567 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4568 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4569 err_note = 'Failed to resolve url (does the playlist exist?)'
4570 if fatal:
4571 raise ExtractorError(err_note, expected=True)
4572 self.report_warning(err_note, item_id)
4573
4574 _SEARCH_PARAMS = None
4575
4576 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4577 data = {'query': query}
4578 if params is NO_DEFAULT:
4579 params = self._SEARCH_PARAMS
4580 if params:
4581 data['params'] = params
4582
4583 content_keys = (
4584 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4585 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4586 # ytmusic search
4587 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4588 ('continuationContents', ),
4589 )
4590 display_id = f'query "{query}"'
4591 check_get_keys = tuple({keys[0] for keys in content_keys})
4592 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4593 self._report_playlist_authcheck(ytcfg, fatal=False)
4594
4595 continuation_list = [None]
4596 search = None
4597 for page_num in itertools.count(1):
4598 data.update(continuation_list[0] or {})
4599 headers = self.generate_api_headers(
4600 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
4601 search = self._extract_response(
4602 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4603 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
4604 slr_contents = traverse_obj(search, *content_keys)
4605 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4606 if not continuation_list[0]:
4607 break
4608
4609
4610class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4611 IE_DESC = 'YouTube Tabs'
4612 _VALID_URL = r'''(?x:
4613 https?://
4614 (?:\w+\.)?
4615 (?:
4616 youtube(?:kids)?\.com|
4617 %(invidious)s
4618 )/
4619 (?:
4620 (?P<channel_type>channel|c|user|browse)/|
4621 (?P<not_channel>
4622 feed/|hashtag/|
4623 (?:playlist|watch)\?.*?\blist=
4624 )|
4625 (?!(?:%(reserved_names)s)\b) # Direct URLs
4626 )
4627 (?P<id>[^/?\#&]+)
4628 )''' % {
4629 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4630 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4631 }
4632 IE_NAME = 'youtube:tab'
4633
4634 _TESTS = [{
4635 'note': 'playlists, multipage',
4636 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4637 'playlist_mincount': 94,
4638 'info_dict': {
4639 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4640 'title': 'Igor Kleiner - Playlists',
4641 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4642 'uploader': 'Igor Kleiner',
4643 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4644 'channel': 'Igor Kleiner',
4645 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4646 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4647 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4648 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4649 'channel_follower_count': int
4650 },
4651 }, {
4652 'note': 'playlists, multipage, different order',
4653 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4654 'playlist_mincount': 94,
4655 'info_dict': {
4656 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4657 'title': 'Igor Kleiner - Playlists',
4658 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4659 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4660 'uploader': 'Igor Kleiner',
4661 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4662 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4663 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4664 'channel': 'Igor Kleiner',
4665 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4666 'channel_follower_count': int
4667 },
4668 }, {
4669 'note': 'playlists, series',
4670 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4671 'playlist_mincount': 5,
4672 'info_dict': {
4673 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4674 'title': '3Blue1Brown - Playlists',
4675 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4676 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4677 'uploader': '3Blue1Brown',
4678 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4679 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4680 'channel': '3Blue1Brown',
4681 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4682 'tags': ['Mathematics'],
4683 'channel_follower_count': int
4684 },
4685 }, {
4686 'note': 'playlists, singlepage',
4687 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4688 'playlist_mincount': 4,
4689 'info_dict': {
4690 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4691 'title': 'ThirstForScience - Playlists',
4692 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4693 'uploader': 'ThirstForScience',
4694 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4695 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4696 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4697 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4698 'tags': 'count:13',
4699 'channel': 'ThirstForScience',
4700 'channel_follower_count': int
4701 }
4702 }, {
4703 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4704 'only_matching': True,
4705 }, {
4706 'note': 'basic, single video playlist',
4707 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4708 'info_dict': {
4709 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4710 'uploader': 'Sergey M.',
4711 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4712 'title': 'youtube-dl public playlist',
4713 'description': '',
4714 'tags': [],
4715 'view_count': int,
4716 'modified_date': '20201130',
4717 'channel': 'Sergey M.',
4718 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4719 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4720 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4721 },
4722 'playlist_count': 1,
4723 }, {
4724 'note': 'empty playlist',
4725 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4726 'info_dict': {
4727 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4728 'uploader': 'Sergey M.',
4729 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4730 'title': 'youtube-dl empty playlist',
4731 'tags': [],
4732 'channel': 'Sergey M.',
4733 'description': '',
4734 'modified_date': '20160902',
4735 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4736 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4737 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4738 },
4739 'playlist_count': 0,
4740 }, {
4741 'note': 'Home tab',
4742 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4743 'info_dict': {
4744 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4745 'title': 'lex will - Home',
4746 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4747 'uploader': 'lex will',
4748 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4749 'channel': 'lex will',
4750 'tags': ['bible', 'history', 'prophesy'],
4751 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4752 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4753 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4754 'channel_follower_count': int
4755 },
4756 'playlist_mincount': 2,
4757 }, {
4758 'note': 'Videos tab',
4759 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4760 'info_dict': {
4761 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4762 'title': 'lex will - Videos',
4763 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4764 'uploader': 'lex will',
4765 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4766 'tags': ['bible', 'history', 'prophesy'],
4767 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4768 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4769 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4770 'channel': 'lex will',
4771 'channel_follower_count': int
4772 },
4773 'playlist_mincount': 975,
4774 }, {
4775 'note': 'Videos tab, sorted by popular',
4776 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4777 'info_dict': {
4778 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4779 'title': 'lex will - Videos',
4780 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4781 'uploader': 'lex will',
4782 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4783 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4784 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4785 'channel': 'lex will',
4786 'tags': ['bible', 'history', 'prophesy'],
4787 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4788 'channel_follower_count': int
4789 },
4790 'playlist_mincount': 199,
4791 }, {
4792 'note': 'Playlists tab',
4793 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4794 'info_dict': {
4795 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4796 'title': 'lex will - Playlists',
4797 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4798 'uploader': 'lex will',
4799 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4801 'channel': 'lex will',
4802 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4803 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4804 'tags': ['bible', 'history', 'prophesy'],
4805 'channel_follower_count': int
4806 },
4807 'playlist_mincount': 17,
4808 }, {
4809 'note': 'Community tab',
4810 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4811 'info_dict': {
4812 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4813 'title': 'lex will - Community',
4814 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4815 'uploader': 'lex will',
4816 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4817 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4818 'channel': 'lex will',
4819 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4820 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4821 'tags': ['bible', 'history', 'prophesy'],
4822 'channel_follower_count': int
4823 },
4824 'playlist_mincount': 18,
4825 }, {
4826 'note': 'Channels tab',
4827 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4828 'info_dict': {
4829 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'title': 'lex will - Channels',
4831 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4832 'uploader': 'lex will',
4833 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4835 'channel': 'lex will',
4836 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4837 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4838 'tags': ['bible', 'history', 'prophesy'],
4839 'channel_follower_count': int
4840 },
4841 'playlist_mincount': 12,
4842 }, {
4843 'note': 'Search tab',
4844 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4845 'playlist_mincount': 40,
4846 'info_dict': {
4847 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4848 'title': '3Blue1Brown - Search - linear algebra',
4849 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4850 'uploader': '3Blue1Brown',
4851 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4852 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4853 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4854 'tags': ['Mathematics'],
4855 'channel': '3Blue1Brown',
4856 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4857 'channel_follower_count': int
4858 },
4859 }, {
4860 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4861 'only_matching': True,
4862 }, {
4863 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4864 'only_matching': True,
4865 }, {
4866 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4867 'only_matching': True,
4868 }, {
4869 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4870 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4871 'info_dict': {
4872 'title': '29C3: Not my department',
4873 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4874 'uploader': 'Christiaan008',
4875 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4876 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4877 'tags': [],
4878 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4879 'view_count': int,
4880 'modified_date': '20150605',
4881 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4882 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4883 'channel': 'Christiaan008',
4884 },
4885 'playlist_count': 96,
4886 }, {
4887 'note': 'Large playlist',
4888 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4889 'info_dict': {
4890 'title': 'Uploads from Cauchemar',
4891 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4892 'uploader': 'Cauchemar',
4893 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4894 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4895 'tags': [],
4896 'modified_date': r're:\d{8}',
4897 'channel': 'Cauchemar',
4898 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4899 'view_count': int,
4900 'description': '',
4901 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4902 },
4903 'playlist_mincount': 1123,
4904 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4905 }, {
4906 'note': 'even larger playlist, 8832 videos',
4907 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4908 'only_matching': True,
4909 }, {
4910 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4911 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4912 'info_dict': {
4913 'title': 'Uploads from Interstellar Movie',
4914 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4915 'uploader': 'Interstellar Movie',
4916 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4917 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4918 'tags': [],
4919 'view_count': int,
4920 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4921 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4922 'channel': 'Interstellar Movie',
4923 'description': '',
4924 'modified_date': r're:\d{8}',
4925 },
4926 'playlist_mincount': 21,
4927 }, {
4928 'note': 'Playlist with "show unavailable videos" button',
4929 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4930 'info_dict': {
4931 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4932 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4933 'uploader': 'Phim Siêu Nhân Nhật Bản',
4934 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4935 'view_count': int,
4936 'channel': 'Phim Siêu Nhân Nhật Bản',
4937 'tags': [],
4938 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4939 'description': '',
4940 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4941 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4942 'modified_date': r're:\d{8}',
4943 },
4944 'playlist_mincount': 200,
4945 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4946 }, {
4947 'note': 'Playlist with unavailable videos in page 7',
4948 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4949 'info_dict': {
4950 'title': 'Uploads from BlankTV',
4951 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4952 'uploader': 'BlankTV',
4953 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4954 'channel': 'BlankTV',
4955 'channel_url': 'https://www.youtube.com/c/blanktv',
4956 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4957 'view_count': int,
4958 'tags': [],
4959 'uploader_url': 'https://www.youtube.com/c/blanktv',
4960 'modified_date': r're:\d{8}',
4961 'description': '',
4962 },
4963 'playlist_mincount': 1000,
4964 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4965 }, {
4966 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4967 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4968 'info_dict': {
4969 'title': 'Data Analysis with Dr Mike Pound',
4970 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4971 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4972 'uploader': 'Computerphile',
4973 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4974 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4975 'tags': [],
4976 'view_count': int,
4977 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4978 'channel_url': 'https://www.youtube.com/user/Computerphile',
4979 'channel': 'Computerphile',
4980 },
4981 'playlist_mincount': 11,
4982 }, {
4983 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4984 'only_matching': True,
4985 }, {
4986 'note': 'Playlist URL that does not actually serve a playlist',
4987 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4988 'info_dict': {
4989 'id': 'FqZTN594JQw',
4990 'ext': 'webm',
4991 'title': "Smiley's People 01 detective, Adventure Series, Action",
4992 'uploader': 'STREEM',
4993 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4994 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4995 'upload_date': '20150526',
4996 'license': 'Standard YouTube License',
4997 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4998 'categories': ['People & Blogs'],
4999 'tags': list,
5000 'view_count': int,
5001 'like_count': int,
5002 },
5003 'params': {
5004 'skip_download': True,
5005 },
5006 'skip': 'This video is not available.',
5007 'add_ie': [YoutubeIE.ie_key()],
5008 }, {
5009 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5010 'only_matching': True,
5011 }, {
5012 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5013 'only_matching': True,
5014 }, {
5015 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5016 'info_dict': {
5017 'id': 'Wq15eF5vCbI', # This will keep changing
5018 'ext': 'mp4',
5019 'title': str,
5020 'uploader': 'Sky News',
5021 'uploader_id': 'skynews',
5022 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5023 'upload_date': r're:\d{8}',
5024 'description': str,
5025 'categories': ['News & Politics'],
5026 'tags': list,
5027 'like_count': int,
5028 'release_timestamp': 1642502819,
5029 'channel': 'Sky News',
5030 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5031 'age_limit': 0,
5032 'view_count': int,
5033 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5034 'playable_in_embed': True,
5035 'release_date': '20220118',
5036 'availability': 'public',
5037 'live_status': 'is_live',
5038 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5039 'channel_follower_count': int
5040 },
5041 'params': {
5042 'skip_download': True,
5043 },
5044 'expected_warnings': ['Ignoring subtitle tracks found in '],
5045 }, {
5046 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5047 'info_dict': {
5048 'id': 'a48o2S1cPoo',
5049 'ext': 'mp4',
5050 'title': 'The Young Turks - Live Main Show',
5051 'uploader': 'The Young Turks',
5052 'uploader_id': 'TheYoungTurks',
5053 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5054 'upload_date': '20150715',
5055 'license': 'Standard YouTube License',
5056 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5057 'categories': ['News & Politics'],
5058 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5059 'like_count': int,
5060 },
5061 'params': {
5062 'skip_download': True,
5063 },
5064 'only_matching': True,
5065 }, {
5066 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5067 'only_matching': True,
5068 }, {
5069 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5070 'only_matching': True,
5071 }, {
5072 'note': 'A channel that is not live. Should raise error',
5073 'url': 'https://www.youtube.com/user/numberphile/live',
5074 'only_matching': True,
5075 }, {
5076 'url': 'https://www.youtube.com/feed/trending',
5077 'only_matching': True,
5078 }, {
5079 'url': 'https://www.youtube.com/feed/library',
5080 'only_matching': True,
5081 }, {
5082 'url': 'https://www.youtube.com/feed/history',
5083 'only_matching': True,
5084 }, {
5085 'url': 'https://www.youtube.com/feed/subscriptions',
5086 'only_matching': True,
5087 }, {
5088 'url': 'https://www.youtube.com/feed/watch_later',
5089 'only_matching': True,
5090 }, {
5091 'note': 'Recommended - redirects to home page.',
5092 'url': 'https://www.youtube.com/feed/recommended',
5093 'only_matching': True,
5094 }, {
5095 'note': 'inline playlist with not always working continuations',
5096 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5097 'only_matching': True,
5098 }, {
5099 'url': 'https://www.youtube.com/course',
5100 'only_matching': True,
5101 }, {
5102 'url': 'https://www.youtube.com/zsecurity',
5103 'only_matching': True,
5104 }, {
5105 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5106 'only_matching': True,
5107 }, {
5108 'url': 'https://www.youtube.com/TheYoungTurks/live',
5109 'only_matching': True,
5110 }, {
5111 'url': 'https://www.youtube.com/hashtag/cctv9',
5112 'info_dict': {
5113 'id': 'cctv9',
5114 'title': '#cctv9',
5115 'tags': [],
5116 },
5117 'playlist_mincount': 350,
5118 }, {
5119 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5120 'only_matching': True,
5121 }, {
5122 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5123 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5124 'only_matching': True
5125 }, {
5126 'note': '/browse/ should redirect to /channel/',
5127 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5128 'only_matching': True
5129 }, {
5130 'note': 'VLPL, should redirect to playlist?list=PL...',
5131 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5132 'info_dict': {
5133 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5134 'uploader': 'NoCopyrightSounds',
5135 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5136 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5137 'title': 'NCS : All Releases 💿',
5138 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5139 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5140 'modified_date': r're:\d{8}',
5141 'view_count': int,
5142 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5143 'tags': [],
5144 'channel': 'NoCopyrightSounds',
5145 },
5146 'playlist_mincount': 166,
5147 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5148 }, {
5149 'note': 'Topic, should redirect to playlist?list=UU...',
5150 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5151 'info_dict': {
5152 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5153 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5154 'title': 'Uploads from Royalty Free Music - Topic',
5155 'uploader': 'Royalty Free Music - Topic',
5156 'tags': [],
5157 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5158 'channel': 'Royalty Free Music - Topic',
5159 'view_count': int,
5160 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5161 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5162 'modified_date': r're:\d{8}',
5163 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5164 'description': '',
5165 },
5166 'expected_warnings': [
5167 'The URL does not have a videos tab',
5168 r'[Uu]navailable videos (are|will be) hidden',
5169 ],
5170 'playlist_mincount': 101,
5171 }, {
5172 'note': 'Topic without a UU playlist',
5173 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5174 'info_dict': {
5175 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5176 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5177 'tags': [],
5178 },
5179 'expected_warnings': [
5180 'the playlist redirect gave error',
5181 ],
5182 'playlist_mincount': 9,
5183 }, {
5184 'note': 'Youtube music Album',
5185 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5186 'info_dict': {
5187 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5188 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5189 'tags': [],
5190 'view_count': int,
5191 'description': '',
5192 'availability': 'unlisted',
5193 'modified_date': r're:\d{8}',
5194 },
5195 'playlist_count': 50,
5196 }, {
5197 'note': 'unlisted single video playlist',
5198 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5199 'info_dict': {
5200 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5201 'uploader': 'colethedj',
5202 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5203 'title': 'yt-dlp unlisted playlist test',
5204 'availability': 'unlisted',
5205 'tags': [],
5206 'modified_date': '20220418',
5207 'channel': 'colethedj',
5208 'view_count': int,
5209 'description': '',
5210 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5211 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5212 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5213 },
5214 'playlist_count': 1,
5215 }, {
5216 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5217 'url': 'https://www.youtube.com/feed/recommended',
5218 'info_dict': {
5219 'id': 'recommended',
5220 'title': 'recommended',
5221 'tags': [],
5222 },
5223 'playlist_mincount': 50,
5224 'params': {
5225 'skip_download': True,
5226 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5227 },
5228 }, {
5229 'note': 'API Fallback: /videos tab, sorted by oldest first',
5230 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5231 'info_dict': {
5232 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5233 'title': 'Cody\'sLab - Videos',
5234 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5235 'uploader': 'Cody\'sLab',
5236 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5237 'channel': 'Cody\'sLab',
5238 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5239 'tags': [],
5240 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5241 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5242 'channel_follower_count': int
5243 },
5244 'playlist_mincount': 650,
5245 'params': {
5246 'skip_download': True,
5247 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5248 },
5249 }, {
5250 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5251 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5252 'info_dict': {
5253 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5254 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5255 'title': 'Uploads from Royalty Free Music - Topic',
5256 'uploader': 'Royalty Free Music - Topic',
5257 'modified_date': r're:\d{8}',
5258 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5259 'description': '',
5260 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5261 'tags': [],
5262 'channel': 'Royalty Free Music - Topic',
5263 'view_count': int,
5264 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5265 },
5266 'expected_warnings': [
5267 'does not have a videos tab',
5268 r'[Uu]navailable videos (are|will be) hidden',
5269 ],
5270 'playlist_mincount': 101,
5271 'params': {
5272 'skip_download': True,
5273 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5274 },
5275 }, {
5276 'note': 'non-standard redirect to regional channel',
5277 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5278 'only_matching': True
5279 }, {
5280 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5281 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5282 'info_dict': {
5283 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5284 'modified_date': '20220407',
5285 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5286 'tags': [],
5287 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5288 'uploader': 'pukkandan',
5289 'availability': 'unlisted',
5290 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5291 'channel': 'pukkandan',
5292 'description': 'Test for collaborative playlist',
5293 'title': 'yt-dlp test - collaborative playlist',
5294 'view_count': int,
5295 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5296 },
5297 'playlist_mincount': 2
5298 }]
5299
5300 @classmethod
5301 def suitable(cls, url):
5302 return False if YoutubeIE.suitable(url) else super().suitable(url)
5303
5304 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5305
5306 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5307 def _real_extract(self, url, smuggled_data):
5308 item_id = self._match_id(url)
5309 url = urllib.parse.urlunparse(
5310 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
5311 compat_opts = self.get_param('compat_opts', [])
5312
5313 def get_mobj(url):
5314 mobj = self._URL_RE.match(url).groupdict()
5315 mobj.update((k, '') for k, v in mobj.items() if v is None)
5316 return mobj
5317
5318 mobj, redirect_warning = get_mobj(url), None
5319 # Youtube returns incomplete data if tabname is not lower case
5320 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5321 if is_channel:
5322 if smuggled_data.get('is_music_url'):
5323 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5324 item_id = item_id[2:]
5325 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5326 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5327 mdata = self._extract_tab_endpoint(
5328 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5329 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5330 get_all=False, expected_type=str)
5331 if not murl:
5332 raise ExtractorError('Failed to resolve album to playlist')
5333 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5334 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5335 pre = f'https://www.youtube.com/channel/{item_id}'
5336
5337 original_tab_name = tab
5338 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5339 # Home URLs should redirect to /videos/
5340 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5341 'To download only the videos in the home page, add a "/featured" to the URL')
5342 tab = '/videos'
5343
5344 url = ''.join((pre, tab, post))
5345 mobj = get_mobj(url)
5346
5347 # Handle both video/playlist URLs
5348 qs = parse_qs(url)
5349 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
5350
5351 if not video_id and mobj['not_channel'].startswith('watch'):
5352 if not playlist_id:
5353 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5354 raise ExtractorError('Unable to recognize tab page')
5355 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5356 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5357 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5358 mobj = get_mobj(url)
5359
5360 if video_id and playlist_id:
5361 if self.get_param('noplaylist'):
5362 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5363 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5364 ie=YoutubeIE.ie_key(), video_id=video_id)
5365 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5366
5367 data, ytcfg = self._extract_data(url, item_id)
5368
5369 # YouTube may provide a non-standard redirect to the regional channel
5370 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5371 redirect_url = traverse_obj(
5372 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5373 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5374 redirect_url = ''.join((
5375 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5376 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5377 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5378
5379 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5380 if tabs:
5381 selected_tab = self._extract_selected_tab(tabs)
5382 selected_tab_name = selected_tab.get('title', '').lower()
5383 if selected_tab_name == 'home':
5384 selected_tab_name = 'featured'
5385 requested_tab_name = mobj['tab'][1:]
5386 if 'no-youtube-channel-redirect' not in compat_opts:
5387 if requested_tab_name == 'live': # Live tab should have redirected to the video
5388 raise UserNotLive(video_id=mobj['id'])
5389 if requested_tab_name not in ('', selected_tab_name):
5390 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5391 if not original_tab_name:
5392 if item_id[:2] == 'UC':
5393 # Topic channels don't have /videos. Use the equivalent playlist instead
5394 pl_id = f'UU{item_id[2:]}'
5395 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5396 try:
5397 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5398 except ExtractorError:
5399 redirect_warning += ' and the playlist redirect gave error'
5400 else:
5401 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5402 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5403 if selected_tab_name and selected_tab_name != requested_tab_name:
5404 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5405 else:
5406 raise ExtractorError(redirect_warning, expected=True)
5407
5408 if redirect_warning:
5409 self.to_screen(redirect_warning)
5410 self.write_debug(f'Final URL: {url}')
5411
5412 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5413 if 'no-youtube-unavailable-videos' not in compat_opts:
5414 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5415 self._extract_and_report_alerts(data, only_once=True)
5416 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5417 if tabs:
5418 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5419
5420 playlist = traverse_obj(
5421 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5422 if playlist:
5423 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5424
5425 video_id = traverse_obj(
5426 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5427 if video_id:
5428 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5429 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5430 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5431 ie=YoutubeIE.ie_key(), video_id=video_id)
5432
5433 raise ExtractorError('Unable to recognize tab page')
5434
5435
5436class YoutubePlaylistIE(InfoExtractor):
5437 IE_DESC = 'YouTube playlists'
5438 _VALID_URL = r'''(?x)(?:
5439 (?:https?://)?
5440 (?:\w+\.)?
5441 (?:
5442 (?:
5443 youtube(?:kids)?\.com|
5444 %(invidious)s
5445 )
5446 /.*?\?.*?\blist=
5447 )?
5448 (?P<id>%(playlist_id)s)
5449 )''' % {
5450 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5451 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5452 }
5453 IE_NAME = 'youtube:playlist'
5454 _TESTS = [{
5455 'note': 'issue #673',
5456 'url': 'PLBB231211A4F62143',
5457 'info_dict': {
5458 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5459 'id': 'PLBB231211A4F62143',
5460 'uploader': 'Wickman',
5461 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5462 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5463 'view_count': int,
5464 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5465 'modified_date': r're:\d{8}',
5466 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5467 'channel': 'Wickman',
5468 'tags': [],
5469 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5470 },
5471 'playlist_mincount': 29,
5472 }, {
5473 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5474 'info_dict': {
5475 'title': 'YDL_safe_search',
5476 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5477 },
5478 'playlist_count': 2,
5479 'skip': 'This playlist is private',
5480 }, {
5481 'note': 'embedded',
5482 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5483 'playlist_count': 4,
5484 'info_dict': {
5485 'title': 'JODA15',
5486 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5487 'uploader': 'milan',
5488 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5489 'description': '',
5490 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5491 'tags': [],
5492 'modified_date': '20140919',
5493 'view_count': int,
5494 'channel': 'milan',
5495 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5496 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5497 },
5498 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5499 }, {
5500 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5501 'playlist_mincount': 455,
5502 'info_dict': {
5503 'title': '2018 Chinese New Singles (11/6 updated)',
5504 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5505 'uploader': 'LBK',
5506 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5507 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5508 'channel': 'LBK',
5509 'view_count': int,
5510 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5511 'tags': [],
5512 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5513 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5514 'modified_date': r're:\d{8}',
5515 },
5516 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5517 }, {
5518 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5519 'only_matching': True,
5520 }, {
5521 # music album playlist
5522 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5523 'only_matching': True,
5524 }]
5525
5526 @classmethod
5527 def suitable(cls, url):
5528 if YoutubeTabIE.suitable(url):
5529 return False
5530 from ..utils import parse_qs
5531 qs = parse_qs(url)
5532 if qs.get('v', [None])[0]:
5533 return False
5534 return super().suitable(url)
5535
5536 def _real_extract(self, url):
5537 playlist_id = self._match_id(url)
5538 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5539 url = update_url_query(
5540 'https://www.youtube.com/playlist',
5541 parse_qs(url) or {'list': playlist_id})
5542 if is_music_url:
5543 url = smuggle_url(url, {'is_music_url': True})
5544 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5545
5546
5547class YoutubeYtBeIE(InfoExtractor):
5548 IE_DESC = 'youtu.be'
5549 _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}
5550 _TESTS = [{
5551 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5552 'info_dict': {
5553 'id': 'yeWKywCrFtk',
5554 'ext': 'mp4',
5555 'title': 'Small Scale Baler and Braiding Rugs',
5556 'uploader': 'Backus-Page House Museum',
5557 'uploader_id': 'backuspagemuseum',
5558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5559 'upload_date': '20161008',
5560 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5561 'categories': ['Nonprofits & Activism'],
5562 'tags': list,
5563 'like_count': int,
5564 'age_limit': 0,
5565 'playable_in_embed': True,
5566 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5567 'channel': 'Backus-Page House Museum',
5568 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5569 'live_status': 'not_live',
5570 'view_count': int,
5571 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5572 'availability': 'public',
5573 'duration': 59,
5574 'comment_count': int,
5575 'channel_follower_count': int
5576 },
5577 'params': {
5578 'noplaylist': True,
5579 'skip_download': True,
5580 },
5581 }, {
5582 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5583 'only_matching': True,
5584 }]
5585
5586 def _real_extract(self, url):
5587 mobj = self._match_valid_url(url)
5588 video_id = mobj.group('id')
5589 playlist_id = mobj.group('playlist_id')
5590 return self.url_result(
5591 update_url_query('https://www.youtube.com/watch', {
5592 'v': video_id,
5593 'list': playlist_id,
5594 'feature': 'youtu.be',
5595 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5596
5597
5598class YoutubeLivestreamEmbedIE(InfoExtractor):
5599 IE_DESC = 'YouTube livestream embeds'
5600 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5601 _TESTS = [{
5602 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5603 'only_matching': True,
5604 }]
5605
5606 def _real_extract(self, url):
5607 channel_id = self._match_id(url)
5608 return self.url_result(
5609 f'https://www.youtube.com/channel/{channel_id}/live',
5610 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5611
5612
5613class YoutubeYtUserIE(InfoExtractor):
5614 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5615 IE_NAME = 'youtube:user'
5616 _VALID_URL = r'ytuser:(?P<id>.+)'
5617 _TESTS = [{
5618 'url': 'ytuser:phihag',
5619 'only_matching': True,
5620 }]
5621
5622 def _real_extract(self, url):
5623 user_id = self._match_id(url)
5624 return self.url_result(
5625 'https://www.youtube.com/user/%s/videos' % user_id,
5626 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5627
5628
5629class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5630 IE_NAME = 'youtube:favorites'
5631 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5632 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5633 _LOGIN_REQUIRED = True
5634 _TESTS = [{
5635 'url': ':ytfav',
5636 'only_matching': True,
5637 }, {
5638 'url': ':ytfavorites',
5639 'only_matching': True,
5640 }]
5641
5642 def _real_extract(self, url):
5643 return self.url_result(
5644 'https://www.youtube.com/playlist?list=LL',
5645 ie=YoutubeTabIE.ie_key())
5646
5647
5648class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5649 IE_NAME = 'youtube:notif'
5650 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5651 _VALID_URL = r':ytnotif(?:ication)?s?'
5652 _LOGIN_REQUIRED = True
5653 _TESTS = [{
5654 'url': ':ytnotif',
5655 'only_matching': True,
5656 }, {
5657 'url': ':ytnotifications',
5658 'only_matching': True,
5659 }]
5660
5661 def _extract_notification_menu(self, response, continuation_list):
5662 notification_list = traverse_obj(
5663 response,
5664 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5665 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5666 expected_type=list) or []
5667 continuation_list[0] = None
5668 for item in notification_list:
5669 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5670 if entry:
5671 yield entry
5672 continuation = item.get('continuationItemRenderer')
5673 if continuation:
5674 continuation_list[0] = continuation
5675
5676 def _extract_notification_renderer(self, notification):
5677 video_id = traverse_obj(
5678 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5679 url = f'https://www.youtube.com/watch?v={video_id}'
5680 channel_id = None
5681 if not video_id:
5682 browse_ep = traverse_obj(
5683 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5684 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5685 post_id = self._search_regex(
5686 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5687 'post id', default=None)
5688 if not channel_id or not post_id:
5689 return
5690 # The direct /post url redirects to this in the browser
5691 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5692
5693 channel = traverse_obj(
5694 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5695 expected_type=str)
5696 notification_title = self._get_text(notification, 'shortMessage')
5697 if notification_title:
5698 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5699 # TODO: handle recommended videos
5700 title = self._search_regex(
5701 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
5702 'video title', default=None)
5703 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5704 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5705 else None)
5706 return {
5707 '_type': 'url',
5708 'url': url,
5709 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5710 'video_id': video_id,
5711 'title': title,
5712 'channel_id': channel_id,
5713 'channel': channel,
5714 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5715 'upload_date': upload_date,
5716 }
5717
5718 def _notification_menu_entries(self, ytcfg):
5719 continuation_list = [None]
5720 response = None
5721 for page in itertools.count(1):
5722 ctoken = traverse_obj(
5723 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5724 response = self._extract_response(
5725 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5726 ep='notification/get_notification_menu', check_get_keys='actions',
5727 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5728 yield from self._extract_notification_menu(response, continuation_list)
5729 if not continuation_list[0]:
5730 break
5731
5732 def _real_extract(self, url):
5733 display_id = 'notifications'
5734 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5735 self._report_playlist_authcheck(ytcfg)
5736 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5737
5738
5739class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5740 IE_DESC = 'YouTube search'
5741 IE_NAME = 'youtube:search'
5742 _SEARCH_KEY = 'ytsearch'
5743 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5744 _TESTS = [{
5745 'url': 'ytsearch5:youtube-dl test video',
5746 'playlist_count': 5,
5747 'info_dict': {
5748 'id': 'youtube-dl test video',
5749 'title': 'youtube-dl test video',
5750 }
5751 }]
5752
5753
5754class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5755 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5756 _SEARCH_KEY = 'ytsearchdate'
5757 IE_DESC = 'YouTube search, newest videos first'
5758 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5759 _TESTS = [{
5760 'url': 'ytsearchdate5:youtube-dl test video',
5761 'playlist_count': 5,
5762 'info_dict': {
5763 'id': 'youtube-dl test video',
5764 'title': 'youtube-dl test video',
5765 }
5766 }]
5767
5768
5769class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5770 IE_DESC = 'YouTube search URLs with sorting and filter support'
5771 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5772 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5773 _TESTS = [{
5774 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5775 'playlist_mincount': 5,
5776 'info_dict': {
5777 'id': 'youtube-dl test video',
5778 'title': 'youtube-dl test video',
5779 }
5780 }, {
5781 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5782 'playlist_mincount': 5,
5783 'info_dict': {
5784 'id': 'python',
5785 'title': 'python',
5786 }
5787 }, {
5788 'url': 'https://www.youtube.com/results?search_query=%23cats',
5789 'playlist_mincount': 1,
5790 'info_dict': {
5791 'id': '#cats',
5792 'title': '#cats',
5793 # The test suite does not have support for nested playlists
5794 # 'entries': [{
5795 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5796 # 'title': '#cats',
5797 # }],
5798 },
5799 }, {
5800 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5801 'only_matching': True,
5802 }]
5803
5804 def _real_extract(self, url):
5805 qs = parse_qs(url)
5806 query = (qs.get('search_query') or qs.get('q'))[0]
5807 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5808
5809
5810class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5811 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
5812 IE_NAME = 'youtube:music:search_url'
5813 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5814 _TESTS = [{
5815 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5816 'playlist_count': 16,
5817 'info_dict': {
5818 'id': 'royalty free music',
5819 'title': 'royalty free music',
5820 }
5821 }, {
5822 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5823 'playlist_mincount': 30,
5824 'info_dict': {
5825 'id': 'royalty free music - songs',
5826 'title': 'royalty free music - songs',
5827 },
5828 'params': {'extract_flat': 'in_playlist'}
5829 }, {
5830 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5831 'playlist_mincount': 30,
5832 'info_dict': {
5833 'id': 'royalty free music - community playlists',
5834 'title': 'royalty free music - community playlists',
5835 },
5836 'params': {'extract_flat': 'in_playlist'}
5837 }]
5838
5839 _SECTIONS = {
5840 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5841 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5842 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5843 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5844 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5845 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5846 }
5847
5848 def _real_extract(self, url):
5849 qs = parse_qs(url)
5850 query = (qs.get('search_query') or qs.get('q'))[0]
5851 params = qs.get('sp', (None,))[0]
5852 if params:
5853 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5854 else:
5855 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
5856 params = self._SECTIONS.get(section)
5857 if not params:
5858 section = None
5859 title = join_nonempty(query, section, delim=' - ')
5860 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
5861
5862
5863class YoutubeFeedsInfoExtractor(InfoExtractor):
5864 """
5865 Base class for feed extractors
5866 Subclasses must re-define the _FEED_NAME property.
5867 """
5868 _LOGIN_REQUIRED = True
5869 _FEED_NAME = 'feeds'
5870
5871 def _real_initialize(self):
5872 YoutubeBaseInfoExtractor._check_login_required(self)
5873
5874 @classproperty
5875 def IE_NAME(self):
5876 return f'youtube:{self._FEED_NAME}'
5877
5878 def _real_extract(self, url):
5879 return self.url_result(
5880 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
5881
5882
5883class YoutubeWatchLaterIE(InfoExtractor):
5884 IE_NAME = 'youtube:watchlater'
5885 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5886 _VALID_URL = r':ytwatchlater'
5887 _TESTS = [{
5888 'url': ':ytwatchlater',
5889 'only_matching': True,
5890 }]
5891
5892 def _real_extract(self, url):
5893 return self.url_result(
5894 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5895
5896
5897class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5898 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5899 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5900 _FEED_NAME = 'recommended'
5901 _LOGIN_REQUIRED = False
5902 _TESTS = [{
5903 'url': ':ytrec',
5904 'only_matching': True,
5905 }, {
5906 'url': ':ytrecommended',
5907 'only_matching': True,
5908 }, {
5909 'url': 'https://youtube.com',
5910 'only_matching': True,
5911 }]
5912
5913
5914class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5915 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5916 _VALID_URL = r':ytsub(?:scription)?s?'
5917 _FEED_NAME = 'subscriptions'
5918 _TESTS = [{
5919 'url': ':ytsubs',
5920 'only_matching': True,
5921 }, {
5922 'url': ':ytsubscriptions',
5923 'only_matching': True,
5924 }]
5925
5926
5927class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5928 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5929 _VALID_URL = r':ythis(?:tory)?'
5930 _FEED_NAME = 'history'
5931 _TESTS = [{
5932 'url': ':ythistory',
5933 'only_matching': True,
5934 }]
5935
5936
5937class YoutubeStoriesIE(InfoExtractor):
5938 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5939 IE_NAME = 'youtube:stories'
5940 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5941 _TESTS = [{
5942 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5943 'only_matching': True,
5944 }]
5945
5946 def _real_extract(self, url):
5947 playlist_id = f'RLTD{self._match_id(url)}'
5948 return self.url_result(
5949 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5950 ie=YoutubeTabIE, video_id=playlist_id)
5951
5952
5953class YoutubeTruncatedURLIE(InfoExtractor):
5954 IE_NAME = 'youtube:truncated_url'
5955 IE_DESC = False # Do not list
5956 _VALID_URL = r'''(?x)
5957 (?:https?://)?
5958 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5959 (?:watch\?(?:
5960 feature=[a-z_]+|
5961 annotation_id=annotation_[^&]+|
5962 x-yt-cl=[0-9]+|
5963 hl=[^&]*|
5964 t=[0-9]+
5965 )?
5966 |
5967 attribution_link\?a=[^&]+
5968 )
5969 $
5970 '''
5971
5972 _TESTS = [{
5973 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5974 'only_matching': True,
5975 }, {
5976 'url': 'https://www.youtube.com/watch?',
5977 'only_matching': True,
5978 }, {
5979 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5980 'only_matching': True,
5981 }, {
5982 'url': 'https://www.youtube.com/watch?feature=foo',
5983 'only_matching': True,
5984 }, {
5985 'url': 'https://www.youtube.com/watch?hl=en-GB',
5986 'only_matching': True,
5987 }, {
5988 'url': 'https://www.youtube.com/watch?t=2372',
5989 'only_matching': True,
5990 }]
5991
5992 def _real_extract(self, url):
5993 raise ExtractorError(
5994 'Did you forget to quote the URL? Remember that & is a meta '
5995 'character in most shells, so you want to put the URL in quotes, '
5996 'like youtube-dl '
5997 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5998 ' or simply youtube-dl BaW_jenozKc .',
5999 expected=True)
6000
6001
6002class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
6003 IE_NAME = 'youtube:clip'
6004 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6005 _TESTS = [{
6006 # FIXME: Other metadata should be extracted from the clip, not from the base video
6007 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6008 'info_dict': {
6009 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6010 'ext': 'mp4',
6011 'section_start': 29.0,
6012 'section_end': 39.7,
6013 'duration': 10.7,
6014 'age_limit': 0,
6015 'availability': 'public',
6016 'categories': ['Gaming'],
6017 'channel': 'Scott The Woz',
6018 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6019 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6020 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6021 'like_count': int,
6022 'playable_in_embed': True,
6023 'tags': 'count:17',
6024 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6025 'title': 'Mobile Games on Console - Scott The Woz',
6026 'upload_date': '20210920',
6027 'uploader': 'Scott The Woz',
6028 'uploader_id': 'scottthewoz',
6029 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6030 'view_count': int,
6031 'live_status': 'not_live',
6032 'channel_follower_count': int
6033 }
6034 }]
6035
6036 def _real_extract(self, url):
6037 clip_id = self._match_id(url)
6038 _, data = self._extract_webpage(url, clip_id)
6039
6040 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6041 if not video_id:
6042 raise ExtractorError('Unable to find video ID')
6043
6044 clip_data = traverse_obj(data, (
6045 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6046 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6047 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6048 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6049
6050 return {
6051 '_type': 'url_transparent',
6052 'url': f'https://www.youtube.com/watch?v={video_id}',
6053 'ie_key': YoutubeIE.ie_key(),
6054 'id': clip_id,
6055 'section_start': int(clip_data['startTimeMs']) / 1000,
6056 'section_end': int(clip_data['endTimeMs']) / 1000,
6057 }
6058
6059
6060class YoutubeTruncatedIDIE(InfoExtractor):
6061 IE_NAME = 'youtube:truncated_id'
6062 IE_DESC = False # Do not list
6063 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6064
6065 _TESTS = [{
6066 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6067 'only_matching': True,
6068 }]
6069
6070 def _real_extract(self, url):
6071 video_id = self._match_id(url)
6072 raise ExtractorError(
6073 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
6074 expected=True)