]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[cleanup] Misc cleanup and refactor (#2173)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
1 import calendar
2 import copy
3 import datetime
4 import functools
5 import hashlib
6 import itertools
7 import json
8 import math
9 import os.path
10 import random
11 import re
12 import sys
13 import threading
14 import time
15 import traceback
16
17 from .common import InfoExtractor, SearchInfoExtractor
18 from ..compat import (
19 compat_chr,
20 compat_HTTPError,
21 compat_parse_qs,
22 compat_str,
23 compat_urllib_parse_unquote_plus,
24 compat_urllib_parse_urlencode,
25 compat_urllib_parse_urlparse,
26 compat_urlparse,
27 )
28 from ..jsinterp import JSInterpreter
29 from ..utils import (
30 NO_DEFAULT,
31 ExtractorError,
32 bug_reports_message,
33 clean_html,
34 datetime_from_str,
35 dict_get,
36 error_to_compat_str,
37 float_or_none,
38 format_field,
39 get_first,
40 int_or_none,
41 is_html,
42 join_nonempty,
43 js_to_json,
44 mimetype2ext,
45 network_exceptions,
46 orderedSet,
47 parse_codecs,
48 parse_count,
49 parse_duration,
50 parse_iso8601,
51 parse_qs,
52 qualities,
53 remove_end,
54 remove_start,
55 smuggle_url,
56 str_or_none,
57 str_to_int,
58 strftime_or_none,
59 traverse_obj,
60 try_get,
61 unescapeHTML,
62 unified_strdate,
63 unified_timestamp,
64 unsmuggle_url,
65 update_url_query,
66 url_or_none,
67 urljoin,
68 variadic,
69 )
70
71 # any clients starting with _ cannot be explicity requested by the user
72 INNERTUBE_CLIENTS = {
73 'web': {
74 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
75 'INNERTUBE_CONTEXT': {
76 'client': {
77 'clientName': 'WEB',
78 'clientVersion': '2.20211221.00.00',
79 }
80 },
81 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
82 },
83 'web_embedded': {
84 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
85 'INNERTUBE_CONTEXT': {
86 'client': {
87 'clientName': 'WEB_EMBEDDED_PLAYER',
88 'clientVersion': '1.20211215.00.01',
89 },
90 },
91 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
92 },
93 'web_music': {
94 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
95 'INNERTUBE_HOST': 'music.youtube.com',
96 'INNERTUBE_CONTEXT': {
97 'client': {
98 'clientName': 'WEB_REMIX',
99 'clientVersion': '1.20211213.00.00',
100 }
101 },
102 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
103 },
104 'web_creator': {
105 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
106 'INNERTUBE_CONTEXT': {
107 'client': {
108 'clientName': 'WEB_CREATOR',
109 'clientVersion': '1.20211220.02.00',
110 }
111 },
112 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
113 },
114 'android': {
115 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
116 'INNERTUBE_CONTEXT': {
117 'client': {
118 'clientName': 'ANDROID',
119 'clientVersion': '16.49',
120 }
121 },
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
123 'REQUIRE_JS_PLAYER': False
124 },
125 'android_embedded': {
126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
127 'INNERTUBE_CONTEXT': {
128 'client': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
130 'clientVersion': '16.49',
131 },
132 },
133 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
134 'REQUIRE_JS_PLAYER': False
135 },
136 'android_music': {
137 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
138 'INNERTUBE_CONTEXT': {
139 'client': {
140 'clientName': 'ANDROID_MUSIC',
141 'clientVersion': '4.57',
142 }
143 },
144 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
145 'REQUIRE_JS_PLAYER': False
146 },
147 'android_creator': {
148 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
149 'INNERTUBE_CONTEXT': {
150 'client': {
151 'clientName': 'ANDROID_CREATOR',
152 'clientVersion': '21.47',
153 },
154 },
155 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
156 'REQUIRE_JS_PLAYER': False
157 },
158 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
159 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
160 'ios': {
161 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
162 'INNERTUBE_CONTEXT': {
163 'client': {
164 'clientName': 'IOS',
165 'clientVersion': '16.46',
166 'deviceModel': 'iPhone14,3',
167 }
168 },
169 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
170 'REQUIRE_JS_PLAYER': False
171 },
172 'ios_embedded': {
173 'INNERTUBE_CONTEXT': {
174 'client': {
175 'clientName': 'IOS_MESSAGES_EXTENSION',
176 'clientVersion': '16.46',
177 'deviceModel': 'iPhone14,3',
178 },
179 },
180 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
181 'REQUIRE_JS_PLAYER': False
182 },
183 'ios_music': {
184 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
185 'INNERTUBE_CONTEXT': {
186 'client': {
187 'clientName': 'IOS_MUSIC',
188 'clientVersion': '4.57',
189 },
190 },
191 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
192 'REQUIRE_JS_PLAYER': False
193 },
194 'ios_creator': {
195 'INNERTUBE_CONTEXT': {
196 'client': {
197 'clientName': 'IOS_CREATOR',
198 'clientVersion': '21.47',
199 },
200 },
201 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
202 'REQUIRE_JS_PLAYER': False
203 },
204 # mweb has 'ultralow' formats
205 # See: https://github.com/yt-dlp/yt-dlp/pull/557
206 'mweb': {
207 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
208 'INNERTUBE_CONTEXT': {
209 'client': {
210 'clientName': 'MWEB',
211 'clientVersion': '2.20211221.01.00',
212 }
213 },
214 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
215 },
216 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
217 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
218 'tv_embedded': {
219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
220 'INNERTUBE_CONTEXT': {
221 'client': {
222 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
223 'clientVersion': '2.0',
224 },
225 },
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
227 },
228 }
229
230
231 def _split_innertube_client(client_name):
232 variant, *base = client_name.rsplit('.', 1)
233 if base:
234 return variant, base[0], variant
235 base, *variant = client_name.split('_', 1)
236 return client_name, base, variant[0] if variant else None
237
238
239 def build_innertube_clients():
240 THIRD_PARTY = {
241 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
242 }
243 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
244 priority = qualities(BASE_CLIENTS[::-1])
245
246 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
247 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
248 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
249 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
250 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
251
252 _, base_client, variant = _split_innertube_client(client)
253 ytcfg['priority'] = 10 * priority(base_client)
254
255 if not variant:
256 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
257 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
258 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
259 embedscreen['priority'] -= 3
260 elif variant == 'embedded':
261 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
262 ytcfg['priority'] -= 2
263 else:
264 ytcfg['priority'] -= 3
265
266
267 build_innertube_clients()
268
269
270 class YoutubeBaseInfoExtractor(InfoExtractor):
271 """Provide base functions for Youtube extractors"""
272
273 _RESERVED_NAMES = (
274 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
275 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
276 r'browse|oembed|get_video_info|iframe_api|s/player|'
277 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
278
279 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
280
281 # _NETRC_MACHINE = 'youtube'
282
283 # If True it will raise an error if no login info is provided
284 _LOGIN_REQUIRED = False
285
286 _INVIDIOUS_SITES = (
287 # invidious-redirect websites
288 r'(?:www\.)?redirect\.invidious\.io',
289 r'(?:(?:www|dev)\.)?invidio\.us',
290 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
291 r'(?:www\.)?invidious\.pussthecat\.org',
292 r'(?:www\.)?invidious\.zee\.li',
293 r'(?:www\.)?invidious\.ethibox\.fr',
294 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
295 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
296 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
297 # youtube-dl invidious instances list
298 r'(?:(?:www|no)\.)?invidiou\.sh',
299 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
300 r'(?:www\.)?invidious\.kabi\.tk',
301 r'(?:www\.)?invidious\.mastodon\.host',
302 r'(?:www\.)?invidious\.zapashcanon\.fr',
303 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
304 r'(?:www\.)?invidious\.tinfoil-hat\.net',
305 r'(?:www\.)?invidious\.himiko\.cloud',
306 r'(?:www\.)?invidious\.reallyancient\.tech',
307 r'(?:www\.)?invidious\.tube',
308 r'(?:www\.)?invidiou\.site',
309 r'(?:www\.)?invidious\.site',
310 r'(?:www\.)?invidious\.xyz',
311 r'(?:www\.)?invidious\.nixnet\.xyz',
312 r'(?:www\.)?invidious\.048596\.xyz',
313 r'(?:www\.)?invidious\.drycat\.fr',
314 r'(?:www\.)?inv\.skyn3t\.in',
315 r'(?:www\.)?tube\.poal\.co',
316 r'(?:www\.)?tube\.connect\.cafe',
317 r'(?:www\.)?vid\.wxzm\.sx',
318 r'(?:www\.)?vid\.mint\.lgbt',
319 r'(?:www\.)?vid\.puffyan\.us',
320 r'(?:www\.)?yewtu\.be',
321 r'(?:www\.)?yt\.elukerio\.org',
322 r'(?:www\.)?yt\.lelux\.fi',
323 r'(?:www\.)?invidious\.ggc-project\.de',
324 r'(?:www\.)?yt\.maisputain\.ovh',
325 r'(?:www\.)?ytprivate\.com',
326 r'(?:www\.)?invidious\.13ad\.de',
327 r'(?:www\.)?invidious\.toot\.koeln',
328 r'(?:www\.)?invidious\.fdn\.fr',
329 r'(?:www\.)?watch\.nettohikari\.com',
330 r'(?:www\.)?invidious\.namazso\.eu',
331 r'(?:www\.)?invidious\.silkky\.cloud',
332 r'(?:www\.)?invidious\.exonip\.de',
333 r'(?:www\.)?invidious\.riverside\.rocks',
334 r'(?:www\.)?invidious\.blamefran\.net',
335 r'(?:www\.)?invidious\.moomoo\.de',
336 r'(?:www\.)?ytb\.trom\.tf',
337 r'(?:www\.)?yt\.cyberhost\.uk',
338 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
339 r'(?:www\.)?qklhadlycap4cnod\.onion',
340 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
341 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
342 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
343 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
344 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
345 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
346 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
347 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
348 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
349 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
350 )
351
352 def _initialize_consent(self):
353 cookies = self._get_cookies('https://www.youtube.com/')
354 if cookies.get('__Secure-3PSID'):
355 return
356 consent_id = None
357 consent = cookies.get('CONSENT')
358 if consent:
359 if 'YES' in consent.value:
360 return
361 consent_id = self._search_regex(
362 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
363 if not consent_id:
364 consent_id = random.randint(100, 999)
365 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
366
367 def _initialize_pref(self):
368 cookies = self._get_cookies('https://www.youtube.com/')
369 pref_cookie = cookies.get('PREF')
370 pref = {}
371 if pref_cookie:
372 try:
373 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
374 except ValueError:
375 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
376 pref.update({'hl': 'en', 'tz': 'UTC'})
377 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
378
379 def _real_initialize(self):
380 self._initialize_pref()
381 self._initialize_consent()
382 self._check_login_required()
383
384 def _check_login_required(self):
385 if (self._LOGIN_REQUIRED
386 and self.get_param('cookiefile') is None
387 and self.get_param('cookiesfrombrowser') is None):
388 self.raise_login_required('Login details are needed to download this content', method='cookies')
389
390 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
391 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
392 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
393
394 def _get_default_ytcfg(self, client='web'):
395 return copy.deepcopy(INNERTUBE_CLIENTS[client])
396
397 def _get_innertube_host(self, client='web'):
398 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
399
400 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
401 # try_get but with fallback to default ytcfg client values when present
402 _func = lambda y: try_get(y, getter, expected_type)
403 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
404
405 def _extract_client_name(self, ytcfg, default_client='web'):
406 return self._ytcfg_get_safe(
407 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
408 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
409
410 def _extract_client_version(self, ytcfg, default_client='web'):
411 return self._ytcfg_get_safe(
412 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
413 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
414
415 def _extract_api_key(self, ytcfg=None, default_client='web'):
416 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
417
418 def _extract_context(self, ytcfg=None, default_client='web'):
419 context = get_first(
420 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
421 # Enforce language and tz for extraction
422 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
423 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
424 return context
425
426 _SAPISID = None
427
428 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
429 time_now = round(time.time())
430 if self._SAPISID is None:
431 yt_cookies = self._get_cookies('https://www.youtube.com')
432 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
433 # See: https://github.com/yt-dlp/yt-dlp/issues/393
434 sapisid_cookie = dict_get(
435 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
436 if sapisid_cookie and sapisid_cookie.value:
437 self._SAPISID = sapisid_cookie.value
438 self.write_debug('Extracted SAPISID cookie')
439 # SAPISID cookie is required if not already present
440 if not yt_cookies.get('SAPISID'):
441 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
442 self._set_cookie(
443 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
444 else:
445 self._SAPISID = False
446 if not self._SAPISID:
447 return None
448 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
449 sapisidhash = hashlib.sha1(
450 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
451 return f'SAPISIDHASH {time_now}_{sapisidhash}'
452
453 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
454 note='Downloading API JSON', errnote='Unable to download API page',
455 context=None, api_key=None, api_hostname=None, default_client='web'):
456
457 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
458 data.update(query)
459 real_headers = self.generate_api_headers(default_client=default_client)
460 real_headers.update({'content-type': 'application/json'})
461 if headers:
462 real_headers.update(headers)
463 return self._download_json(
464 f'https://{api_hostname or self._get_innertube_host(default_client)}/youtubei/v1/{ep}',
465 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
466 data=json.dumps(data).encode('utf8'), headers=real_headers,
467 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
468
469 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
470 data = self._search_regex(
471 (fr'{self._YT_INITIAL_DATA_RE}\s*{self._YT_INITIAL_BOUNDARY_RE}',
472 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
473 if data:
474 return self._parse_json(data, item_id, fatal=fatal)
475
476 @staticmethod
477 def _extract_session_index(*data):
478 """
479 Index of current account in account list.
480 See: https://github.com/yt-dlp/yt-dlp/pull/519
481 """
482 for ytcfg in data:
483 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
484 if session_index is not None:
485 return session_index
486
487 # Deprecated?
488 def _extract_identity_token(self, ytcfg=None, webpage=None):
489 if ytcfg:
490 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
491 if token:
492 return token
493 if webpage:
494 return self._search_regex(
495 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
496 'identity token', default=None, fatal=False)
497
498 @staticmethod
499 def _extract_account_syncid(*args):
500 """
501 Extract syncId required to download private playlists of secondary channels
502 @params response and/or ytcfg
503 """
504 for data in args:
505 # ytcfg includes channel_syncid if on secondary channel
506 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
507 if delegated_sid:
508 return delegated_sid
509 sync_ids = (try_get(
510 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
511 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
512 if len(sync_ids) >= 2 and sync_ids[1]:
513 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
514 # and just "user_syncid||" for primary channel. We only want the channel_syncid
515 return sync_ids[0]
516
517 @staticmethod
518 def _extract_visitor_data(*args):
519 """
520 Extracts visitorData from an API response or ytcfg
521 Appears to be used to track session state
522 """
523 return get_first(
524 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
525 expected_type=str)
526
527 @property
528 def is_authenticated(self):
529 return bool(self._generate_sapisidhash_header())
530
531 def extract_ytcfg(self, video_id, webpage):
532 if not webpage:
533 return {}
534 return self._parse_json(
535 self._search_regex(
536 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
537 default='{}'), video_id, fatal=False) or {}
538
539 def generate_api_headers(
540 self, *, ytcfg=None, account_syncid=None, session_index=None,
541 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
542
543 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
544 headers = {
545 'X-YouTube-Client-Name': compat_str(
546 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
547 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
548 'Origin': origin,
549 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
550 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
551 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
552 }
553 if session_index is None:
554 session_index = self._extract_session_index(ytcfg)
555 if account_syncid or session_index is not None:
556 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
557
558 auth = self._generate_sapisidhash_header(origin)
559 if auth is not None:
560 headers['Authorization'] = auth
561 headers['X-Origin'] = origin
562 return {h: v for h, v in headers.items() if v is not None}
563
564 def _download_ytcfg(self, client, video_id):
565 url = {
566 'web': 'https://www.youtube.com',
567 'web_music': 'https://music.youtube.com',
568 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
569 }.get(client)
570 if not url:
571 return {}
572 webpage = self._download_webpage(
573 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
574 return self.extract_ytcfg(video_id, webpage) or {}
575
576 @staticmethod
577 def _build_api_continuation_query(continuation, ctp=None):
578 query = {
579 'continuation': continuation
580 }
581 # TODO: Inconsistency with clickTrackingParams.
582 # Currently we have a fixed ctp contained within context (from ytcfg)
583 # and a ctp in root query for continuation.
584 if ctp:
585 query['clickTracking'] = {'clickTrackingParams': ctp}
586 return query
587
588 @classmethod
589 def _extract_next_continuation_data(cls, renderer):
590 next_continuation = try_get(
591 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
592 lambda x: x['continuation']['reloadContinuationData']), dict)
593 if not next_continuation:
594 return
595 continuation = next_continuation.get('continuation')
596 if not continuation:
597 return
598 ctp = next_continuation.get('clickTrackingParams')
599 return cls._build_api_continuation_query(continuation, ctp)
600
601 @classmethod
602 def _extract_continuation_ep_data(cls, continuation_ep: dict):
603 if isinstance(continuation_ep, dict):
604 continuation = try_get(
605 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
606 if not continuation:
607 return
608 ctp = continuation_ep.get('clickTrackingParams')
609 return cls._build_api_continuation_query(continuation, ctp)
610
611 @classmethod
612 def _extract_continuation(cls, renderer):
613 next_continuation = cls._extract_next_continuation_data(renderer)
614 if next_continuation:
615 return next_continuation
616
617 contents = []
618 for key in ('contents', 'items'):
619 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
620
621 for content in contents:
622 if not isinstance(content, dict):
623 continue
624 continuation_ep = try_get(
625 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
626 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
627 dict)
628 continuation = cls._extract_continuation_ep_data(continuation_ep)
629 if continuation:
630 return continuation
631
632 @classmethod
633 def _extract_alerts(cls, data):
634 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
635 if not isinstance(alert_dict, dict):
636 continue
637 for alert in alert_dict.values():
638 alert_type = alert.get('type')
639 if not alert_type:
640 continue
641 message = cls._get_text(alert, 'text')
642 if message:
643 yield alert_type, message
644
645 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
646 errors = []
647 warnings = []
648 for alert_type, alert_message in alerts:
649 if alert_type.lower() == 'error' and fatal:
650 errors.append([alert_type, alert_message])
651 else:
652 warnings.append([alert_type, alert_message])
653
654 for alert_type, alert_message in (warnings + errors[:-1]):
655 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
656 if errors:
657 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
658
659 def _extract_and_report_alerts(self, data, *args, **kwargs):
660 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
661
662 def _extract_badges(self, renderer: dict):
663 badges = set()
664 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
665 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
666 if label:
667 badges.add(label.lower())
668 return badges
669
670 @staticmethod
671 def _get_text(data, *path_list, max_runs=None):
672 for path in path_list or [None]:
673 if path is None:
674 obj = [data]
675 else:
676 obj = traverse_obj(data, path, default=[])
677 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
678 obj = [obj]
679 for item in obj:
680 text = try_get(item, lambda x: x['simpleText'], compat_str)
681 if text:
682 return text
683 runs = try_get(item, lambda x: x['runs'], list) or []
684 if not runs and isinstance(item, list):
685 runs = item
686
687 runs = runs[:min(len(runs), max_runs or len(runs))]
688 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
689 if text:
690 return text
691
692 def _get_count(self, data, *path_list):
693 count_text = self._get_text(data, *path_list) or ''
694 count = parse_count(count_text)
695 if count is None:
696 count = str_to_int(
697 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
698 return count
699
700 @staticmethod
701 def _extract_thumbnails(data, *path_list):
702 """
703 Extract thumbnails from thumbnails dict
704 @param path_list: path list to level that contains 'thumbnails' key
705 """
706 thumbnails = []
707 for path in path_list or [()]:
708 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
709 thumbnail_url = url_or_none(thumbnail.get('url'))
710 if not thumbnail_url:
711 continue
712 # Sometimes youtube gives a wrong thumbnail URL. See:
713 # https://github.com/yt-dlp/yt-dlp/issues/233
714 # https://github.com/ytdl-org/youtube-dl/issues/28023
715 if 'maxresdefault' in thumbnail_url:
716 thumbnail_url = thumbnail_url.split('?')[0]
717 thumbnails.append({
718 'url': thumbnail_url,
719 'height': int_or_none(thumbnail.get('height')),
720 'width': int_or_none(thumbnail.get('width')),
721 })
722 return thumbnails
723
724 @staticmethod
725 def extract_relative_time(relative_time_text):
726 """
727 Extracts a relative time from string and converts to dt object
728 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
729 """
730 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)
731 if mobj:
732 start = mobj.group('start')
733 if start:
734 return datetime_from_str(start)
735 try:
736 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
737 except ValueError:
738 return None
739
740 def _extract_time_text(self, renderer, *path_list):
741 """@returns (timestamp, time_text)"""
742 text = self._get_text(renderer, *path_list) or ''
743 dt = self.extract_relative_time(text)
744 timestamp = None
745 if isinstance(dt, datetime.datetime):
746 timestamp = calendar.timegm(dt.timetuple())
747
748 if timestamp is None:
749 timestamp = (
750 unified_timestamp(text) or unified_timestamp(
751 self._search_regex(
752 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
753 text.lower(), 'time text', default=None)))
754
755 if text and timestamp is None:
756 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
757 return timestamp, text
758
759 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
760 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
761 default_client='web'):
762 response = None
763 last_error = None
764 count = -1
765 retries = self.get_param('extractor_retries', 3)
766 if check_get_keys is None:
767 check_get_keys = []
768 while count < retries:
769 count += 1
770 if last_error:
771 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
772 try:
773 response = self._call_api(
774 ep=ep, fatal=True, headers=headers,
775 video_id=item_id, query=query,
776 context=self._extract_context(ytcfg, default_client),
777 api_key=self._extract_api_key(ytcfg, default_client),
778 api_hostname=api_hostname, default_client=default_client,
779 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
780 except ExtractorError as e:
781 if isinstance(e.cause, network_exceptions):
782 if isinstance(e.cause, compat_HTTPError):
783 first_bytes = e.cause.read(512)
784 if not is_html(first_bytes):
785 yt_error = try_get(
786 self._parse_json(
787 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
788 lambda x: x['error']['message'], compat_str)
789 if yt_error:
790 self._report_alerts([('ERROR', yt_error)], fatal=False)
791 # Downloading page may result in intermittent 5xx HTTP error
792 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
793 # We also want to catch all other network exceptions since errors in later pages can be troublesome
794 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
795 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
796 last_error = error_to_compat_str(e.cause or e.msg)
797 if count < retries:
798 continue
799 if fatal:
800 raise
801 else:
802 self.report_warning(error_to_compat_str(e))
803 return
804
805 else:
806 try:
807 self._extract_and_report_alerts(response, only_once=True)
808 except ExtractorError as e:
809 # YouTube servers may return errors we want to retry on in a 200 OK response
810 # See: https://github.com/yt-dlp/yt-dlp/issues/839
811 if 'unknown error' in e.msg.lower():
812 last_error = e.msg
813 continue
814 if fatal:
815 raise
816 self.report_warning(error_to_compat_str(e))
817 return
818 if not check_get_keys or dict_get(response, check_get_keys):
819 break
820 # Youtube sometimes sends incomplete data
821 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
822 last_error = 'Incomplete data received'
823 if count >= retries:
824 if fatal:
825 raise ExtractorError(last_error)
826 else:
827 self.report_warning(last_error)
828 return
829 return response
830
831 @staticmethod
832 def is_music_url(url):
833 return re.match(r'https?://music\.youtube\.com/', url) is not None
834
835 def _extract_video(self, renderer):
836 video_id = renderer.get('videoId')
837 title = self._get_text(renderer, 'title')
838 description = self._get_text(renderer, 'descriptionSnippet')
839 duration = parse_duration(self._get_text(
840 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
841 if duration is None:
842 duration = parse_duration(self._search_regex(
843 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
844 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
845 video_id, default=None, group='duration'))
846
847 view_count = self._get_count(renderer, 'viewCountText')
848
849 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
850 channel_id = traverse_obj(
851 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
852 expected_type=str, get_all=False)
853 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
854 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
855 overlay_style = traverse_obj(
856 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
857 get_all=False, expected_type=str)
858 badges = self._extract_badges(renderer)
859 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
860 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
861 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
862 expected_type=str)) or ''
863 url = f'https://www.youtube.com/watch?v={video_id}'
864 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
865 url = f'https://www.youtube.com/shorts/{video_id}'
866
867 return {
868 '_type': 'url',
869 'ie_key': YoutubeIE.ie_key(),
870 'id': video_id,
871 'url': url,
872 'title': title,
873 'description': description,
874 'duration': duration,
875 'view_count': view_count,
876 'uploader': uploader,
877 'channel_id': channel_id,
878 'thumbnails': thumbnails,
879 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
880 if self._configuration_arg('approximate_date', ie_key='youtubetab')
881 else None),
882 'live_status': ('is_upcoming' if scheduled_timestamp is not None
883 else 'was_live' if 'streamed' in time_text.lower()
884 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
885 else None),
886 'release_timestamp': scheduled_timestamp,
887 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
888 }
889
890
891 class YoutubeIE(YoutubeBaseInfoExtractor):
892 IE_DESC = 'YouTube'
893 _VALID_URL = r"""(?x)^
894 (
895 (?:https?://|//) # http(s):// or protocol-independent URL
896 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
897 (?:www\.)?deturl\.com/www\.youtube\.com|
898 (?:www\.)?pwnyoutube\.com|
899 (?:www\.)?hooktube\.com|
900 (?:www\.)?yourepeat\.com|
901 tube\.majestyc\.net|
902 %(invidious)s|
903 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
904 (?:.*?\#/)? # handle anchor (#/) redirect urls
905 (?: # the various things that can precede the ID:
906 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
907 |(?: # or the v= param in all its forms
908 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
909 (?:\?|\#!?) # the params delimiter ? or # or #!
910 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
911 v=
912 )
913 ))
914 |(?:
915 youtu\.be| # just youtu.be/xxxx
916 vid\.plus| # or vid.plus/xxxx
917 zwearz\.com/watch| # or zwearz.com/watch/xxxx
918 %(invidious)s
919 )/
920 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
921 )
922 )? # all until now is optional -> you can pass the naked ID
923 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
924 (?(1).+)? # if we found the ID, everything can follow
925 (?:\#|$)""" % {
926 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
927 }
928 _PLAYER_INFO_RE = (
929 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
930 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$',
931 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
932 )
933 _formats = {
934 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
935 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
936 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
937 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
938 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
939 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
940 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
941 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
942 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
943 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
944 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
945 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
946 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
947 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
948 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
949 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
950 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
951 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
952
953
954 # 3D videos
955 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
956 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
957 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
958 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
959 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
960 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
961 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
962
963 # Apple HTTP Live Streaming
964 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
965 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
966 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
967 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
968 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
969 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
970 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
971 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
972
973 # DASH mp4 video
974 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
975 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
978 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
979 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
980 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
983 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
984 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
985 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
986
987 # Dash mp4 audio
988 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
989 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
990 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
991 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
992 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
993 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
994 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
995
996 # Dash webm
997 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
999 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1000 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1003 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1004 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1013 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1015 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1016 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1017 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1019
1020 # Dash webm audio
1021 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1022 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1023
1024 # Dash webm audio with opus inside
1025 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1026 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1027 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1028
1029 # RTMP (unnamed)
1030 '_rtmp': {'protocol': 'rtmp'},
1031
1032 # av01 video only formats sometimes served with "unknown" codecs
1033 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1034 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1035 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1036 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1037 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1038 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1039 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1040 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1041 }
1042 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1043
1044 _GEO_BYPASS = False
1045
1046 IE_NAME = 'youtube'
1047 _TESTS = [
1048 {
1049 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1050 'info_dict': {
1051 'id': 'BaW_jenozKc',
1052 'ext': 'mp4',
1053 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1054 'uploader': 'Philipp Hagemeister',
1055 'uploader_id': 'phihag',
1056 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1057 'channel': 'Philipp Hagemeister',
1058 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1059 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1060 'upload_date': '20121002',
1061 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1062 'categories': ['Science & Technology'],
1063 'tags': ['youtube-dl'],
1064 'duration': 10,
1065 'view_count': int,
1066 'like_count': int,
1067 'availability': 'public',
1068 'playable_in_embed': True,
1069 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1070 'live_status': 'not_live',
1071 'age_limit': 0,
1072 'start_time': 1,
1073 'end_time': 9,
1074 'channel_follower_count': int
1075 }
1076 },
1077 {
1078 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1079 'note': 'Embed-only video (#1746)',
1080 'info_dict': {
1081 'id': 'yZIXLfi8CZQ',
1082 'ext': 'mp4',
1083 'upload_date': '20120608',
1084 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1085 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1086 'uploader': 'SET India',
1087 'uploader_id': 'setindia',
1088 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1089 'age_limit': 18,
1090 },
1091 'skip': 'Private video',
1092 },
1093 {
1094 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1095 'note': 'Use the first video ID in the URL',
1096 'info_dict': {
1097 'id': 'BaW_jenozKc',
1098 'ext': 'mp4',
1099 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1100 'uploader': 'Philipp Hagemeister',
1101 'uploader_id': 'phihag',
1102 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1103 'channel': 'Philipp Hagemeister',
1104 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1105 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1106 'upload_date': '20121002',
1107 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1108 'categories': ['Science & Technology'],
1109 'tags': ['youtube-dl'],
1110 'duration': 10,
1111 'view_count': int,
1112 'like_count': int,
1113 'availability': 'public',
1114 'playable_in_embed': True,
1115 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1116 'live_status': 'not_live',
1117 'age_limit': 0,
1118 'channel_follower_count': int
1119 },
1120 'params': {
1121 'skip_download': True,
1122 },
1123 },
1124 {
1125 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1126 'note': '256k DASH audio (format 141) via DASH manifest',
1127 'info_dict': {
1128 'id': 'a9LDPn-MO4I',
1129 'ext': 'm4a',
1130 'upload_date': '20121002',
1131 'uploader_id': '8KVIDEO',
1132 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1133 'description': '',
1134 'uploader': '8KVIDEO',
1135 'title': 'UHDTV TEST 8K VIDEO.mp4'
1136 },
1137 'params': {
1138 'youtube_include_dash_manifest': True,
1139 'format': '141',
1140 },
1141 'skip': 'format 141 not served anymore',
1142 },
1143 # DASH manifest with encrypted signature
1144 {
1145 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1146 'info_dict': {
1147 'id': 'IB3lcPjvWLA',
1148 'ext': 'm4a',
1149 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1150 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1151 'duration': 244,
1152 'uploader': 'AfrojackVEVO',
1153 'uploader_id': 'AfrojackVEVO',
1154 'upload_date': '20131011',
1155 'abr': 129.495,
1156 'like_count': int,
1157 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1158 'playable_in_embed': True,
1159 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1160 'view_count': int,
1161 'track': 'The Spark',
1162 'live_status': 'not_live',
1163 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1164 'channel': 'Afrojack',
1165 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1166 'tags': 'count:19',
1167 'availability': 'public',
1168 'categories': ['Music'],
1169 'age_limit': 0,
1170 'alt_title': 'The Spark',
1171 'channel_follower_count': int
1172 },
1173 'params': {
1174 'youtube_include_dash_manifest': True,
1175 'format': '141/bestaudio[ext=m4a]',
1176 },
1177 },
1178 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1179 {
1180 'note': 'Embed allowed age-gate video',
1181 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1182 'info_dict': {
1183 'id': 'HtVdAasjOgU',
1184 'ext': 'mp4',
1185 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1186 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1187 'duration': 142,
1188 'uploader': 'The Witcher',
1189 'uploader_id': 'WitcherGame',
1190 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1191 'upload_date': '20140605',
1192 'age_limit': 18,
1193 'categories': ['Gaming'],
1194 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1195 'availability': 'needs_auth',
1196 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1197 'like_count': int,
1198 'channel': 'The Witcher',
1199 'live_status': 'not_live',
1200 'tags': 'count:17',
1201 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1202 'playable_in_embed': True,
1203 'view_count': int,
1204 'channel_follower_count': int
1205 },
1206 },
1207 {
1208 'note': 'Age-gate video with embed allowed in public site',
1209 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1210 'info_dict': {
1211 'id': 'HsUATh_Nc2U',
1212 'ext': 'mp4',
1213 'title': 'Godzilla 2 (Official Video)',
1214 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1215 'upload_date': '20200408',
1216 'uploader_id': 'FlyingKitty900',
1217 'uploader': 'FlyingKitty',
1218 'age_limit': 18,
1219 'availability': 'needs_auth',
1220 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1221 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1222 'channel': 'FlyingKitty',
1223 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1224 'view_count': int,
1225 'categories': ['Entertainment'],
1226 'live_status': 'not_live',
1227 'tags': ['Flyingkitty', 'godzilla 2'],
1228 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1229 'like_count': int,
1230 'duration': 177,
1231 'playable_in_embed': True,
1232 'channel_follower_count': int
1233 },
1234 },
1235 {
1236 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1237 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1238 'info_dict': {
1239 'id': 'Tq92D6wQ1mg',
1240 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1241 'ext': 'mp4',
1242 'upload_date': '20191228',
1243 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1244 'uploader': 'Projekt Melody',
1245 'description': 'md5:17eccca93a786d51bc67646756894066',
1246 'age_limit': 18,
1247 'like_count': int,
1248 'availability': 'needs_auth',
1249 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1250 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1251 'view_count': int,
1252 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1253 'channel': 'Projekt Melody',
1254 'live_status': 'not_live',
1255 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1256 'playable_in_embed': True,
1257 'categories': ['Entertainment'],
1258 'duration': 106,
1259 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1260 'channel_follower_count': int
1261 },
1262 },
1263 {
1264 'note': 'Non-Agegated non-embeddable video',
1265 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1266 'info_dict': {
1267 'id': 'MeJVWBSsPAY',
1268 'ext': 'mp4',
1269 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1270 'uploader': 'Herr Lurik',
1271 'uploader_id': 'st3in234',
1272 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1273 'upload_date': '20130730',
1274 'track': 'Such mich find mich',
1275 'age_limit': 0,
1276 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1277 'like_count': int,
1278 'playable_in_embed': False,
1279 'creator': 'OOMPH!',
1280 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1281 'view_count': int,
1282 'alt_title': 'Such mich find mich',
1283 'duration': 210,
1284 'channel': 'Herr Lurik',
1285 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1286 'categories': ['Music'],
1287 'availability': 'public',
1288 'uploader_url': 'http://www.youtube.com/user/st3in234',
1289 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1290 'live_status': 'not_live',
1291 'artist': 'OOMPH!',
1292 'channel_follower_count': int
1293 },
1294 },
1295 {
1296 'note': 'Non-bypassable age-gated video',
1297 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1298 'only_matching': True,
1299 },
1300 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1301 # YouTube Red ad is not captured for creator
1302 {
1303 'url': '__2ABJjxzNo',
1304 'info_dict': {
1305 'id': '__2ABJjxzNo',
1306 'ext': 'mp4',
1307 'duration': 266,
1308 'upload_date': '20100430',
1309 'uploader_id': 'deadmau5',
1310 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1311 'creator': 'deadmau5',
1312 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1313 'uploader': 'deadmau5',
1314 'title': 'Deadmau5 - Some Chords (HD)',
1315 'alt_title': 'Some Chords',
1316 'availability': 'public',
1317 'tags': 'count:14',
1318 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1319 'view_count': int,
1320 'live_status': 'not_live',
1321 'channel': 'deadmau5',
1322 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1323 'like_count': int,
1324 'track': 'Some Chords',
1325 'artist': 'deadmau5',
1326 'playable_in_embed': True,
1327 'age_limit': 0,
1328 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1329 'categories': ['Music'],
1330 'album': 'Some Chords',
1331 'channel_follower_count': int
1332 },
1333 'expected_warnings': [
1334 'DASH manifest missing',
1335 ]
1336 },
1337 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1338 {
1339 'url': 'lqQg6PlCWgI',
1340 'info_dict': {
1341 'id': 'lqQg6PlCWgI',
1342 'ext': 'mp4',
1343 'duration': 6085,
1344 'upload_date': '20150827',
1345 'uploader_id': 'olympic',
1346 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1347 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1348 'uploader': 'Olympics',
1349 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1350 'like_count': int,
1351 'release_timestamp': 1343767800,
1352 'playable_in_embed': True,
1353 'categories': ['Sports'],
1354 'release_date': '20120731',
1355 'channel': 'Olympics',
1356 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1357 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1358 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1359 'age_limit': 0,
1360 'availability': 'public',
1361 'live_status': 'was_live',
1362 'view_count': int,
1363 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1364 'channel_follower_count': int
1365 },
1366 'params': {
1367 'skip_download': 'requires avconv',
1368 }
1369 },
1370 # Non-square pixels
1371 {
1372 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1373 'info_dict': {
1374 'id': '_b-2C3KPAM0',
1375 'ext': 'mp4',
1376 'stretched_ratio': 16 / 9.,
1377 'duration': 85,
1378 'upload_date': '20110310',
1379 'uploader_id': 'AllenMeow',
1380 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1381 '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',
1382 'uploader': '孫ᄋᄅ',
1383 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1384 'playable_in_embed': True,
1385 'channel': '孫ᄋᄅ',
1386 'age_limit': 0,
1387 'tags': 'count:11',
1388 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1389 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1390 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1391 'view_count': int,
1392 'categories': ['People & Blogs'],
1393 'like_count': int,
1394 'live_status': 'not_live',
1395 'availability': 'unlisted',
1396 'channel_follower_count': int
1397 },
1398 },
1399 # url_encoded_fmt_stream_map is empty string
1400 {
1401 'url': 'qEJwOuvDf7I',
1402 'info_dict': {
1403 'id': 'qEJwOuvDf7I',
1404 'ext': 'webm',
1405 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1406 'description': '',
1407 'upload_date': '20150404',
1408 'uploader_id': 'spbelect',
1409 'uploader': 'Наблюдатели Петербурга',
1410 },
1411 'params': {
1412 'skip_download': 'requires avconv',
1413 },
1414 'skip': 'This live event has ended.',
1415 },
1416 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1417 {
1418 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1419 'info_dict': {
1420 'id': 'FIl7x6_3R5Y',
1421 'ext': 'webm',
1422 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1423 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1424 'duration': 220,
1425 'upload_date': '20150625',
1426 'uploader_id': 'dorappi2000',
1427 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1428 'uploader': 'dorappi2000',
1429 'formats': 'mincount:31',
1430 },
1431 'skip': 'not actual anymore',
1432 },
1433 # DASH manifest with segment_list
1434 {
1435 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1436 'md5': '8ce563a1d667b599d21064e982ab9e31',
1437 'info_dict': {
1438 'id': 'CsmdDsKjzN8',
1439 'ext': 'mp4',
1440 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1441 'uploader': 'Airtek',
1442 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1443 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1444 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1445 },
1446 'params': {
1447 'youtube_include_dash_manifest': True,
1448 'format': '135', # bestvideo
1449 },
1450 'skip': 'This live event has ended.',
1451 },
1452 {
1453 # Multifeed videos (multiple cameras), URL is for Main Camera
1454 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1455 'info_dict': {
1456 'id': 'jvGDaLqkpTg',
1457 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1458 'description': 'md5:e03b909557865076822aa169218d6a5d',
1459 },
1460 'playlist': [{
1461 'info_dict': {
1462 'id': 'jvGDaLqkpTg',
1463 'ext': 'mp4',
1464 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1465 'description': 'md5:e03b909557865076822aa169218d6a5d',
1466 'duration': 10643,
1467 'upload_date': '20161111',
1468 'uploader': 'Team PGP',
1469 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1470 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1471 },
1472 }, {
1473 'info_dict': {
1474 'id': '3AKt1R1aDnw',
1475 'ext': 'mp4',
1476 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1477 'description': 'md5:e03b909557865076822aa169218d6a5d',
1478 'duration': 10991,
1479 'upload_date': '20161111',
1480 'uploader': 'Team PGP',
1481 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1482 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1483 },
1484 }, {
1485 'info_dict': {
1486 'id': 'RtAMM00gpVc',
1487 'ext': 'mp4',
1488 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1489 'description': 'md5:e03b909557865076822aa169218d6a5d',
1490 'duration': 10995,
1491 'upload_date': '20161111',
1492 'uploader': 'Team PGP',
1493 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1494 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1495 },
1496 }, {
1497 'info_dict': {
1498 'id': '6N2fdlP3C5U',
1499 'ext': 'mp4',
1500 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1501 'description': 'md5:e03b909557865076822aa169218d6a5d',
1502 'duration': 10990,
1503 'upload_date': '20161111',
1504 'uploader': 'Team PGP',
1505 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1506 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1507 },
1508 }],
1509 'params': {
1510 'skip_download': True,
1511 },
1512 'skip': 'Not multifeed anymore',
1513 },
1514 {
1515 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1516 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1517 'info_dict': {
1518 'id': 'gVfLd0zydlo',
1519 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1520 },
1521 'playlist_count': 2,
1522 'skip': 'Not multifeed anymore',
1523 },
1524 {
1525 'url': 'https://vid.plus/FlRa-iH7PGw',
1526 'only_matching': True,
1527 },
1528 {
1529 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1530 'only_matching': True,
1531 },
1532 {
1533 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1534 # Also tests cut-off URL expansion in video description (see
1535 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1536 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1537 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1538 'info_dict': {
1539 'id': 'lsguqyKfVQg',
1540 'ext': 'mp4',
1541 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1542 'alt_title': 'Dark Walk',
1543 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1544 'duration': 133,
1545 'upload_date': '20151119',
1546 'uploader_id': 'IronSoulElf',
1547 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1548 'uploader': 'IronSoulElf',
1549 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1550 'track': 'Dark Walk',
1551 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1552 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1553 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1554 'categories': ['Film & Animation'],
1555 'view_count': int,
1556 'live_status': 'not_live',
1557 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1558 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1559 'tags': 'count:13',
1560 'availability': 'public',
1561 'channel': 'IronSoulElf',
1562 'playable_in_embed': True,
1563 'like_count': int,
1564 'age_limit': 0,
1565 'channel_follower_count': int
1566 },
1567 'params': {
1568 'skip_download': True,
1569 },
1570 },
1571 {
1572 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1573 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1574 'only_matching': True,
1575 },
1576 {
1577 # Video with yt:stretch=17:0
1578 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1579 'info_dict': {
1580 'id': 'Q39EVAstoRM',
1581 'ext': 'mp4',
1582 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1583 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1584 'upload_date': '20151107',
1585 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1586 'uploader': 'CH GAMER DROID',
1587 },
1588 'params': {
1589 'skip_download': True,
1590 },
1591 'skip': 'This video does not exist.',
1592 },
1593 {
1594 # Video with incomplete 'yt:stretch=16:'
1595 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1596 'only_matching': True,
1597 },
1598 {
1599 # Video licensed under Creative Commons
1600 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1601 'info_dict': {
1602 'id': 'M4gD1WSo5mA',
1603 'ext': 'mp4',
1604 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1605 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1606 'duration': 721,
1607 'upload_date': '20150128',
1608 'uploader_id': 'BerkmanCenter',
1609 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1610 'uploader': 'The Berkman Klein Center for Internet & Society',
1611 'license': 'Creative Commons Attribution license (reuse allowed)',
1612 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1613 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1614 'like_count': int,
1615 'age_limit': 0,
1616 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1617 'channel': 'The Berkman Klein Center for Internet & Society',
1618 'availability': 'public',
1619 'view_count': int,
1620 'categories': ['Education'],
1621 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1622 'live_status': 'not_live',
1623 'playable_in_embed': True,
1624 'channel_follower_count': int
1625 },
1626 'params': {
1627 'skip_download': True,
1628 },
1629 },
1630 {
1631 # Channel-like uploader_url
1632 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1633 'info_dict': {
1634 'id': 'eQcmzGIKrzg',
1635 'ext': 'mp4',
1636 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1637 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1638 'duration': 4060,
1639 'upload_date': '20151120',
1640 'uploader': 'Bernie Sanders',
1641 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1642 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1643 'license': 'Creative Commons Attribution license (reuse allowed)',
1644 'playable_in_embed': True,
1645 'tags': 'count:12',
1646 'like_count': int,
1647 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1648 'age_limit': 0,
1649 'availability': 'public',
1650 'categories': ['News & Politics'],
1651 'channel': 'Bernie Sanders',
1652 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1653 'view_count': int,
1654 'live_status': 'not_live',
1655 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1656 'channel_follower_count': int
1657 },
1658 'params': {
1659 'skip_download': True,
1660 },
1661 },
1662 {
1663 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1664 'only_matching': True,
1665 },
1666 {
1667 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1668 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1669 'only_matching': True,
1670 },
1671 {
1672 # Rental video preview
1673 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1674 'info_dict': {
1675 'id': 'uGpuVWrhIzE',
1676 'ext': 'mp4',
1677 'title': 'Piku - Trailer',
1678 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1679 'upload_date': '20150811',
1680 'uploader': 'FlixMatrix',
1681 'uploader_id': 'FlixMatrixKaravan',
1682 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1683 'license': 'Standard YouTube License',
1684 },
1685 'params': {
1686 'skip_download': True,
1687 },
1688 'skip': 'This video is not available.',
1689 },
1690 {
1691 # YouTube Red video with episode data
1692 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1693 'info_dict': {
1694 'id': 'iqKdEhx-dD4',
1695 'ext': 'mp4',
1696 'title': 'Isolation - Mind Field (Ep 1)',
1697 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1698 'duration': 2085,
1699 'upload_date': '20170118',
1700 'uploader': 'Vsauce',
1701 'uploader_id': 'Vsauce',
1702 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1703 'series': 'Mind Field',
1704 'season_number': 1,
1705 'episode_number': 1,
1706 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1707 'tags': 'count:12',
1708 'view_count': int,
1709 'availability': 'public',
1710 'age_limit': 0,
1711 'channel': 'Vsauce',
1712 'episode': 'Episode 1',
1713 'categories': ['Entertainment'],
1714 'season': 'Season 1',
1715 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1716 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1717 'like_count': int,
1718 'playable_in_embed': True,
1719 'live_status': 'not_live',
1720 'channel_follower_count': int
1721 },
1722 'params': {
1723 'skip_download': True,
1724 },
1725 'expected_warnings': [
1726 'Skipping DASH manifest',
1727 ],
1728 },
1729 {
1730 # The following content has been identified by the YouTube community
1731 # as inappropriate or offensive to some audiences.
1732 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1733 'info_dict': {
1734 'id': '6SJNVb0GnPI',
1735 'ext': 'mp4',
1736 'title': 'Race Differences in Intelligence',
1737 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1738 'duration': 965,
1739 'upload_date': '20140124',
1740 'uploader': 'New Century Foundation',
1741 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1742 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1743 },
1744 'params': {
1745 'skip_download': True,
1746 },
1747 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1748 },
1749 {
1750 # itag 212
1751 'url': '1t24XAntNCY',
1752 'only_matching': True,
1753 },
1754 {
1755 # geo restricted to JP
1756 'url': 'sJL6WA-aGkQ',
1757 'only_matching': True,
1758 },
1759 {
1760 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1761 'only_matching': True,
1762 },
1763 {
1764 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1765 'only_matching': True,
1766 },
1767 {
1768 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1769 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1770 'only_matching': True,
1771 },
1772 {
1773 # DRM protected
1774 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1775 'only_matching': True,
1776 },
1777 {
1778 # Video with unsupported adaptive stream type formats
1779 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1780 'info_dict': {
1781 'id': 'Z4Vy8R84T1U',
1782 'ext': 'mp4',
1783 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1784 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1785 'duration': 433,
1786 'upload_date': '20130923',
1787 'uploader': 'Amelia Putri Harwita',
1788 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1789 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1790 'formats': 'maxcount:10',
1791 },
1792 'params': {
1793 'skip_download': True,
1794 'youtube_include_dash_manifest': False,
1795 },
1796 'skip': 'not actual anymore',
1797 },
1798 {
1799 # Youtube Music Auto-generated description
1800 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1801 'info_dict': {
1802 'id': 'MgNrAu2pzNs',
1803 'ext': 'mp4',
1804 'title': 'Voyeur Girl',
1805 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1806 'upload_date': '20190312',
1807 'uploader': 'Stephen - Topic',
1808 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1809 'artist': 'Stephen',
1810 'track': 'Voyeur Girl',
1811 'album': 'it\'s too much love to know my dear',
1812 'release_date': '20190313',
1813 'release_year': 2019,
1814 'alt_title': 'Voyeur Girl',
1815 'view_count': int,
1816 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1817 'playable_in_embed': True,
1818 'like_count': int,
1819 'categories': ['Music'],
1820 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1821 'channel': 'Stephen',
1822 'availability': 'public',
1823 'creator': 'Stephen',
1824 'duration': 169,
1825 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1826 'age_limit': 0,
1827 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1828 'tags': 'count:11',
1829 'live_status': 'not_live',
1830 'channel_follower_count': int
1831 },
1832 'params': {
1833 'skip_download': True,
1834 },
1835 },
1836 {
1837 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1838 'only_matching': True,
1839 },
1840 {
1841 # invalid -> valid video id redirection
1842 'url': 'DJztXj2GPfl',
1843 'info_dict': {
1844 'id': 'DJztXj2GPfk',
1845 'ext': 'mp4',
1846 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1847 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1848 'upload_date': '20090125',
1849 'uploader': 'Prochorowka',
1850 'uploader_id': 'Prochorowka',
1851 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1852 'artist': 'Panjabi MC',
1853 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1854 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1855 },
1856 'params': {
1857 'skip_download': True,
1858 },
1859 'skip': 'Video unavailable',
1860 },
1861 {
1862 # empty description results in an empty string
1863 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1864 'info_dict': {
1865 'id': 'x41yOUIvK2k',
1866 'ext': 'mp4',
1867 'title': 'IMG 3456',
1868 'description': '',
1869 'upload_date': '20170613',
1870 'uploader_id': 'ElevageOrVert',
1871 'uploader': 'ElevageOrVert',
1872 'view_count': int,
1873 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1874 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1875 'like_count': int,
1876 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1877 'tags': [],
1878 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1879 'availability': 'public',
1880 'age_limit': 0,
1881 'categories': ['Pets & Animals'],
1882 'duration': 7,
1883 'playable_in_embed': True,
1884 'live_status': 'not_live',
1885 'channel': 'ElevageOrVert',
1886 'channel_follower_count': int
1887 },
1888 'params': {
1889 'skip_download': True,
1890 },
1891 },
1892 {
1893 # with '};' inside yt initial data (see [1])
1894 # see [2] for an example with '};' inside ytInitialPlayerResponse
1895 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1896 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1897 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1898 'info_dict': {
1899 'id': 'CHqg6qOn4no',
1900 'ext': 'mp4',
1901 'title': 'Part 77 Sort a list of simple types in c#',
1902 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1903 'upload_date': '20130831',
1904 'uploader_id': 'kudvenkat',
1905 'uploader': 'kudvenkat',
1906 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1907 'like_count': int,
1908 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1909 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1910 'live_status': 'not_live',
1911 'categories': ['Education'],
1912 'availability': 'public',
1913 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1914 'tags': 'count:12',
1915 'playable_in_embed': True,
1916 'age_limit': 0,
1917 'view_count': int,
1918 'duration': 522,
1919 'channel': 'kudvenkat',
1920 'channel_follower_count': int
1921 },
1922 'params': {
1923 'skip_download': True,
1924 },
1925 },
1926 {
1927 # another example of '};' in ytInitialData
1928 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1929 'only_matching': True,
1930 },
1931 {
1932 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1933 'only_matching': True,
1934 },
1935 {
1936 # https://github.com/ytdl-org/youtube-dl/pull/28094
1937 'url': 'OtqTfy26tG0',
1938 'info_dict': {
1939 'id': 'OtqTfy26tG0',
1940 'ext': 'mp4',
1941 'title': 'Burn Out',
1942 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1943 'upload_date': '20141120',
1944 'uploader': 'The Cinematic Orchestra - Topic',
1945 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1946 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1947 'artist': 'The Cinematic Orchestra',
1948 'track': 'Burn Out',
1949 'album': 'Every Day',
1950 'like_count': int,
1951 'live_status': 'not_live',
1952 'alt_title': 'Burn Out',
1953 'duration': 614,
1954 'age_limit': 0,
1955 'view_count': int,
1956 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'creator': 'The Cinematic Orchestra',
1958 'channel': 'The Cinematic Orchestra',
1959 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1960 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1961 'availability': 'public',
1962 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1963 'categories': ['Music'],
1964 'playable_in_embed': True,
1965 'channel_follower_count': int
1966 },
1967 'params': {
1968 'skip_download': True,
1969 },
1970 },
1971 {
1972 # controversial video, only works with bpctr when authenticated with cookies
1973 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1974 'only_matching': True,
1975 },
1976 {
1977 # controversial video, requires bpctr/contentCheckOk
1978 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1979 'info_dict': {
1980 'id': 'SZJvDhaSDnc',
1981 'ext': 'mp4',
1982 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1983 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1984 'uploader': 'CBS Mornings',
1985 'uploader_id': 'CBSThisMorning',
1986 'upload_date': '20140716',
1987 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1988 'duration': 170,
1989 'categories': ['News & Politics'],
1990 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1991 'view_count': int,
1992 'channel': 'CBS Mornings',
1993 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1994 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1995 'age_limit': 18,
1996 'availability': 'needs_auth',
1997 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1998 'like_count': int,
1999 'live_status': 'not_live',
2000 'playable_in_embed': True,
2001 'channel_follower_count': int
2002 }
2003 },
2004 {
2005 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2006 'url': 'cBvYw8_A0vQ',
2007 'info_dict': {
2008 'id': 'cBvYw8_A0vQ',
2009 'ext': 'mp4',
2010 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2011 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2012 'upload_date': '20201120',
2013 'uploader': 'Walk around Japan',
2014 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2015 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2016 'duration': 1456,
2017 'categories': ['Travel & Events'],
2018 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2019 'view_count': int,
2020 'channel': 'Walk around Japan',
2021 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2022 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2023 'age_limit': 0,
2024 'availability': 'public',
2025 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2026 'live_status': 'not_live',
2027 'playable_in_embed': True,
2028 'channel_follower_count': int
2029 },
2030 'params': {
2031 'skip_download': True,
2032 },
2033 }, {
2034 # Has multiple audio streams
2035 'url': 'WaOKSUlf4TM',
2036 'only_matching': True
2037 }, {
2038 # Requires Premium: has format 141 when requested using YTM url
2039 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2040 'only_matching': True
2041 }, {
2042 # multiple subtitles with same lang_code
2043 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2044 'only_matching': True,
2045 }, {
2046 # Force use android client fallback
2047 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2048 'info_dict': {
2049 'id': 'YOelRv7fMxY',
2050 'title': 'DIGGING A SECRET TUNNEL Part 1',
2051 'ext': '3gp',
2052 'upload_date': '20210624',
2053 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2054 'uploader': 'colinfurze',
2055 'uploader_id': 'colinfurze',
2056 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2057 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2058 'duration': 596,
2059 'categories': ['Entertainment'],
2060 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2061 'view_count': int,
2062 'channel': 'colinfurze',
2063 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2064 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2065 'age_limit': 0,
2066 'availability': 'public',
2067 'like_count': int,
2068 'live_status': 'not_live',
2069 'playable_in_embed': True,
2070 'channel_follower_count': int
2071 },
2072 'params': {
2073 'format': '17', # 3gp format available on android
2074 'extractor_args': {'youtube': {'player_client': ['android']}},
2075 },
2076 },
2077 {
2078 # Skip download of additional client configs (remix client config in this case)
2079 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2080 'only_matching': True,
2081 'params': {
2082 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2083 },
2084 }, {
2085 # shorts
2086 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2087 'only_matching': True,
2088 }, {
2089 'note': 'Storyboards',
2090 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2091 'info_dict': {
2092 'id': '5KLPxDtMqe8',
2093 'ext': 'mhtml',
2094 'format_id': 'sb0',
2095 'title': 'Your Brain is Plastic',
2096 'uploader_id': 'scishow',
2097 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2098 'upload_date': '20140324',
2099 'uploader': 'SciShow',
2100 'like_count': int,
2101 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2102 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2103 'view_count': int,
2104 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2105 'playable_in_embed': True,
2106 'tags': 'count:12',
2107 'uploader_url': 'http://www.youtube.com/user/scishow',
2108 'availability': 'public',
2109 'channel': 'SciShow',
2110 'live_status': 'not_live',
2111 'duration': 248,
2112 'categories': ['Education'],
2113 'age_limit': 0,
2114 'channel_follower_count': int
2115 }, 'params': {'format': 'mhtml', 'skip_download': True}
2116 }, {
2117 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2118 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2119 'info_dict': {
2120 'id': '2NUZ8W2llS4',
2121 'ext': 'mp4',
2122 'title': 'The NP that test your phone performance 🙂',
2123 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2124 'uploader': 'Leon Nguyen',
2125 'uploader_id': 'VNSXIII',
2126 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2127 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2128 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2129 'duration': 21,
2130 'view_count': int,
2131 'age_limit': 0,
2132 'categories': ['Gaming'],
2133 'tags': 'count:23',
2134 'playable_in_embed': True,
2135 'live_status': 'not_live',
2136 'upload_date': '20220103',
2137 'like_count': int,
2138 'availability': 'public',
2139 'channel': 'Leon Nguyen',
2140 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2141 'channel_follower_count': int
2142 }
2143 }, {
2144 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2145 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2146 'info_dict': {
2147 'id': 'mzZzzBU6lrM',
2148 'ext': 'mp4',
2149 'title': 'I Met GeorgeNotFound In Real Life...',
2150 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2151 'uploader': 'Quackity',
2152 'uploader_id': 'QuackityHQ',
2153 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2154 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2155 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2156 'duration': 955,
2157 'view_count': int,
2158 'age_limit': 0,
2159 'categories': ['Entertainment'],
2160 'tags': 'count:26',
2161 'playable_in_embed': True,
2162 'live_status': 'not_live',
2163 'release_timestamp': 1641172509,
2164 'release_date': '20220103',
2165 'upload_date': '20220103',
2166 'like_count': int,
2167 'availability': 'public',
2168 'channel': 'Quackity',
2169 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2170 'channel_follower_count': int
2171 }
2172 },
2173 { # continuous livestream. Microformat upload date should be preferred.
2174 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2175 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2176 'info_dict': {
2177 'id': 'kgx4WGK0oNU',
2178 '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}',
2179 'ext': 'mp4',
2180 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2181 'availability': 'public',
2182 'age_limit': 0,
2183 'release_timestamp': 1637975704,
2184 'upload_date': '20210619',
2185 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2186 'live_status': 'is_live',
2187 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2188 'uploader': '阿鲍Abao',
2189 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2190 'channel': 'Abao in Tokyo',
2191 'channel_follower_count': int,
2192 'release_date': '20211127',
2193 'tags': 'count:39',
2194 'categories': ['People & Blogs'],
2195 'like_count': int,
2196 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2197 'view_count': int,
2198 'playable_in_embed': True,
2199 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2200 },
2201 'params': {'skip_download': True}
2202 },
2203 ]
2204
2205 @classmethod
2206 def suitable(cls, url):
2207 from ..utils import parse_qs
2208
2209 qs = parse_qs(url)
2210 if qs.get('list', [None])[0]:
2211 return False
2212 return super().suitable(url)
2213
2214 def __init__(self, *args, **kwargs):
2215 super().__init__(*args, **kwargs)
2216 self._code_cache = {}
2217 self._player_cache = {}
2218
2219 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2220 lock = threading.Lock()
2221
2222 is_live = True
2223 start_time = time.time()
2224 formats = [f for f in formats if f.get('is_from_start')]
2225
2226 def refetch_manifest(format_id, delay):
2227 nonlocal formats, start_time, is_live
2228 if time.time() <= start_time + delay:
2229 return
2230
2231 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2232 video_details = traverse_obj(
2233 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2234 microformats = traverse_obj(
2235 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2236 expected_type=dict, default=[])
2237 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
2238 start_time = time.time()
2239
2240 def mpd_feed(format_id, delay):
2241 """
2242 @returns (manifest_url, manifest_stream_number, is_live) or None
2243 """
2244 with lock:
2245 refetch_manifest(format_id, delay)
2246
2247 f = next((f for f in formats if f['format_id'] == format_id), None)
2248 if not f:
2249 if not is_live:
2250 self.to_screen(f'{video_id}: Video is no longer live')
2251 else:
2252 self.report_warning(
2253 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2254 return None
2255 return f['manifest_url'], f['manifest_stream_number'], is_live
2256
2257 for f in formats:
2258 f['is_live'] = True
2259 f['protocol'] = 'http_dash_segments_generator'
2260 f['fragments'] = functools.partial(
2261 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2262
2263 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2264 FETCH_SPAN, MAX_DURATION = 5, 432000
2265
2266 mpd_url, stream_number, is_live = None, None, True
2267
2268 begin_index = 0
2269 download_start_time = ctx.get('start') or time.time()
2270
2271 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2272 if lack_early_segments:
2273 self.report_warning(bug_reports_message(
2274 'Starting download from the last 120 hours of the live stream since '
2275 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2276 lack_early_segments = True
2277
2278 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2279 fragments, fragment_base_url = None, None
2280
2281 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2282 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2283 # Obtain from MPD's maximum seq value
2284 old_mpd_url = mpd_url
2285 last_error = ctx.pop('last_error', None)
2286 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2287 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2288 or (mpd_url, stream_number, False))
2289 if not refresh_sequence:
2290 if expire_fast and not is_live:
2291 return False, last_seq
2292 elif old_mpd_url == mpd_url:
2293 return True, last_seq
2294 try:
2295 fmts, _ = self._extract_mpd_formats_and_subtitles(
2296 mpd_url, None, note=False, errnote=False, fatal=False)
2297 except ExtractorError:
2298 fmts = None
2299 if not fmts:
2300 no_fragment_score += 2
2301 return False, last_seq
2302 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2303 fragments = fmt_info['fragments']
2304 fragment_base_url = fmt_info['fragment_base_url']
2305 assert fragment_base_url
2306
2307 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2308 return True, _last_seq
2309
2310 while is_live:
2311 fetch_time = time.time()
2312 if no_fragment_score > 30:
2313 return
2314 if last_segment_url:
2315 # Obtain from "X-Head-Seqnum" header value from each segment
2316 try:
2317 urlh = self._request_webpage(
2318 last_segment_url, None, note=False, errnote=False, fatal=False)
2319 except ExtractorError:
2320 urlh = None
2321 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2322 if last_seq is None:
2323 no_fragment_score += 2
2324 last_segment_url = None
2325 continue
2326 else:
2327 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2328 no_fragment_score += 2
2329 if not should_continue:
2330 continue
2331
2332 if known_idx > last_seq:
2333 last_segment_url = None
2334 continue
2335
2336 last_seq += 1
2337
2338 if begin_index < 0 and known_idx < 0:
2339 # skip from the start when it's negative value
2340 known_idx = last_seq + begin_index
2341 if lack_early_segments:
2342 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2343 try:
2344 for idx in range(known_idx, last_seq):
2345 # do not update sequence here or you'll get skipped some part of it
2346 should_continue, _ = _extract_sequence_from_mpd(False, False)
2347 if not should_continue:
2348 known_idx = idx - 1
2349 raise ExtractorError('breaking out of outer loop')
2350 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2351 yield {
2352 'url': last_segment_url,
2353 }
2354 if known_idx == last_seq:
2355 no_fragment_score += 5
2356 else:
2357 no_fragment_score = 0
2358 known_idx = last_seq
2359 except ExtractorError:
2360 continue
2361
2362 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2363
2364 def _extract_player_url(self, *ytcfgs, webpage=None):
2365 player_url = traverse_obj(
2366 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2367 get_all=False, expected_type=compat_str)
2368 if not player_url:
2369 return
2370 return urljoin('https://www.youtube.com', player_url)
2371
2372 def _download_player_url(self, video_id, fatal=False):
2373 res = self._download_webpage(
2374 'https://www.youtube.com/iframe_api',
2375 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2376 if res:
2377 player_version = self._search_regex(
2378 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2379 if player_version:
2380 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2381
2382 def _signature_cache_id(self, example_sig):
2383 """ Return a string representation of a signature """
2384 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
2385
2386 @classmethod
2387 def _extract_player_info(cls, player_url):
2388 for player_re in cls._PLAYER_INFO_RE:
2389 id_m = re.search(player_re, player_url)
2390 if id_m:
2391 break
2392 else:
2393 raise ExtractorError('Cannot identify player %r' % player_url)
2394 return id_m.group('id')
2395
2396 def _load_player(self, video_id, player_url, fatal=True):
2397 player_id = self._extract_player_info(player_url)
2398 if player_id not in self._code_cache:
2399 code = self._download_webpage(
2400 player_url, video_id, fatal=fatal,
2401 note='Downloading player ' + player_id,
2402 errnote='Download of %s failed' % player_url)
2403 if code:
2404 self._code_cache[player_id] = code
2405 return self._code_cache.get(player_id)
2406
2407 def _extract_signature_function(self, video_id, player_url, example_sig):
2408 player_id = self._extract_player_info(player_url)
2409
2410 # Read from filesystem cache
2411 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2412 assert os.path.basename(func_id) == func_id
2413
2414 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
2415 if cache_spec is not None:
2416 return lambda s: ''.join(s[i] for i in cache_spec)
2417
2418 code = self._load_player(video_id, player_url)
2419 if code:
2420 res = self._parse_sig_js(code)
2421
2422 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2423 cache_res = res(test_string)
2424 cache_spec = [ord(c) for c in cache_res]
2425
2426 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2427 return res
2428
2429 def _print_sig_code(self, func, example_sig):
2430 if not self.get_param('youtube_print_sig_code'):
2431 return
2432
2433 def gen_sig_code(idxs):
2434 def _genslice(start, end, step):
2435 starts = '' if start == 0 else str(start)
2436 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2437 steps = '' if step == 1 else (':%d' % step)
2438 return f's[{starts}{ends}{steps}]'
2439
2440 step = None
2441 # Quelch pyflakes warnings - start will be set when step is set
2442 start = '(Never used)'
2443 for i, prev in zip(idxs[1:], idxs[:-1]):
2444 if step is not None:
2445 if i - prev == step:
2446 continue
2447 yield _genslice(start, prev, step)
2448 step = None
2449 continue
2450 if i - prev in [-1, 1]:
2451 step = i - prev
2452 start = prev
2453 continue
2454 else:
2455 yield 's[%d]' % prev
2456 if step is None:
2457 yield 's[%d]' % i
2458 else:
2459 yield _genslice(start, i, step)
2460
2461 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2462 cache_res = func(test_string)
2463 cache_spec = [ord(c) for c in cache_res]
2464 expr_code = ' + '.join(gen_sig_code(cache_spec))
2465 signature_id_tuple = '(%s)' % (
2466 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
2467 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2468 ' return %s\n') % (signature_id_tuple, expr_code)
2469 self.to_screen('Extracted signature function:\n' + code)
2470
2471 def _parse_sig_js(self, jscode):
2472 funcname = self._search_regex(
2473 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2474 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2475 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2476 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2477 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}\(a,\d+\)',
2478 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\(\s*""\s*\)',
2479 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2480 # Obsolete patterns
2481 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2482 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2483 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2484 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2485 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2486 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2487 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2488 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2489 jscode, 'Initial JS player signature function name', group='sig')
2490
2491 jsi = JSInterpreter(jscode)
2492 initial_function = jsi.extract_function(funcname)
2493 return lambda s: initial_function([s])
2494
2495 def _decrypt_signature(self, s, video_id, player_url):
2496 """Turn the encrypted s field into a working signature"""
2497
2498 if player_url is None:
2499 raise ExtractorError('Cannot decrypt signature without player_url')
2500
2501 try:
2502 player_id = (player_url, self._signature_cache_id(s))
2503 if player_id not in self._player_cache:
2504 func = self._extract_signature_function(
2505 video_id, player_url, s
2506 )
2507 self._player_cache[player_id] = func
2508 func = self._player_cache[player_id]
2509 self._print_sig_code(func, s)
2510 return func(s)
2511 except Exception as e:
2512 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2513
2514 def _decrypt_nsig(self, s, video_id, player_url):
2515 """Turn the encrypted n field into a working signature"""
2516 if player_url is None:
2517 raise ExtractorError('Cannot decrypt nsig without player_url')
2518 player_url = urljoin('https://www.youtube.com', player_url)
2519
2520 sig_id = ('nsig_value', s)
2521 if sig_id in self._player_cache:
2522 return self._player_cache[sig_id]
2523
2524 try:
2525 player_id = ('nsig', player_url)
2526 if player_id not in self._player_cache:
2527 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2528 func = self._player_cache[player_id]
2529 self._player_cache[sig_id] = func(s)
2530 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2531 return self._player_cache[sig_id]
2532 except Exception as e:
2533 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2534
2535 def _extract_n_function_name(self, jscode):
2536 nfunc, idx = self._search_regex(
2537 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2538 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2539 if not idx:
2540 return nfunc
2541 return json.loads(js_to_json(self._search_regex(
2542 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
2543 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
2544
2545 def _extract_n_function(self, video_id, player_url):
2546 player_id = self._extract_player_info(player_url)
2547 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2548
2549 if func_code:
2550 jsi = JSInterpreter(func_code)
2551 else:
2552 jscode = self._load_player(video_id, player_url)
2553 funcname = self._extract_n_function_name(jscode)
2554 jsi = JSInterpreter(jscode)
2555 func_code = jsi.extract_function_code(funcname)
2556 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2557
2558 if self.get_param('youtube_print_sig_code'):
2559 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2560
2561 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2562
2563 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2564 """
2565 Extract signatureTimestamp (sts)
2566 Required to tell API what sig/player version is in use.
2567 """
2568 sts = None
2569 if isinstance(ytcfg, dict):
2570 sts = int_or_none(ytcfg.get('STS'))
2571
2572 if not sts:
2573 # Attempt to extract from player
2574 if player_url is None:
2575 error_msg = 'Cannot extract signature timestamp without player_url.'
2576 if fatal:
2577 raise ExtractorError(error_msg)
2578 self.report_warning(error_msg)
2579 return
2580 code = self._load_player(video_id, player_url, fatal=fatal)
2581 if code:
2582 sts = int_or_none(self._search_regex(
2583 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2584 'JS player signature timestamp', group='sts', fatal=fatal))
2585 return sts
2586
2587 def _mark_watched(self, video_id, player_responses):
2588 playback_url = get_first(
2589 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2590 expected_type=url_or_none)
2591 if not playback_url:
2592 self.report_warning('Unable to mark watched')
2593 return
2594 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2595 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2596
2597 # cpn generation algorithm is reverse engineered from base.js.
2598 # In fact it works even with dummy cpn.
2599 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2600 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2601
2602 qs.update({
2603 'ver': ['2'],
2604 'cpn': [cpn],
2605 })
2606 playback_url = compat_urlparse.urlunparse(
2607 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2608
2609 self._download_webpage(
2610 playback_url, video_id, 'Marking watched',
2611 'Unable to mark watched', fatal=False)
2612
2613 @staticmethod
2614 def _extract_urls(webpage):
2615 # Embedded YouTube player
2616 entries = [
2617 unescapeHTML(mobj.group('url'))
2618 for mobj in re.finditer(r'''(?x)
2619 (?:
2620 <iframe[^>]+?src=|
2621 data-video-url=|
2622 <embed[^>]+?src=|
2623 embedSWF\(?:\s*|
2624 <object[^>]+data=|
2625 new\s+SWFObject\(
2626 )
2627 (["\'])
2628 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2629 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2630 \1''', webpage)]
2631
2632 # lazyYT YouTube embed
2633 entries.extend(list(map(
2634 unescapeHTML,
2635 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2636
2637 # Wordpress "YouTube Video Importer" plugin
2638 matches = re.findall(r'''(?x)<div[^>]+
2639 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2640 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2641 entries.extend(m[-1] for m in matches)
2642
2643 return entries
2644
2645 @staticmethod
2646 def _extract_url(webpage):
2647 urls = YoutubeIE._extract_urls(webpage)
2648 return urls[0] if urls else None
2649
2650 @classmethod
2651 def extract_id(cls, url):
2652 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2653 if mobj is None:
2654 raise ExtractorError('Invalid URL: %s' % url)
2655 return mobj.group('id')
2656
2657 def _extract_chapters_from_json(self, data, duration):
2658 chapter_list = traverse_obj(
2659 data, (
2660 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2661 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2662 ), expected_type=list)
2663
2664 return self._extract_chapters(
2665 chapter_list,
2666 chapter_time=lambda chapter: float_or_none(
2667 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2668 chapter_title=lambda chapter: traverse_obj(
2669 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2670 duration=duration)
2671
2672 def _extract_chapters_from_engagement_panel(self, data, duration):
2673 content_list = traverse_obj(
2674 data,
2675 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2676 expected_type=list, default=[])
2677 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2678 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2679
2680 return next((
2681 filter(None, (
2682 self._extract_chapters(
2683 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2684 chapter_time, chapter_title, duration)
2685 for contents in content_list
2686 ))), [])
2687
2688 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2689 chapters = []
2690 last_chapter = {'start_time': 0}
2691 for idx, chapter in enumerate(chapter_list or []):
2692 title = chapter_title(chapter)
2693 start_time = chapter_time(chapter)
2694 if start_time is None:
2695 continue
2696 last_chapter['end_time'] = start_time
2697 if start_time < last_chapter['start_time']:
2698 if idx == 1:
2699 chapters.pop()
2700 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2701 else:
2702 self.report_warning(f'Invalid start time for chapter "{title}"')
2703 continue
2704 last_chapter = {'start_time': start_time, 'title': title}
2705 chapters.append(last_chapter)
2706 last_chapter['end_time'] = duration
2707 return chapters
2708
2709 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2710 return self._parse_json(self._search_regex(
2711 (fr'{regex}\s*{self._YT_INITIAL_BOUNDARY_RE}',
2712 regex), webpage, name, default='{}'), video_id, fatal=False)
2713
2714 def _extract_comment(self, comment_renderer, parent=None):
2715 comment_id = comment_renderer.get('commentId')
2716 if not comment_id:
2717 return
2718
2719 text = self._get_text(comment_renderer, 'contentText')
2720
2721 # note: timestamp is an estimate calculated from the current time and time_text
2722 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2723 author = self._get_text(comment_renderer, 'authorText')
2724 author_id = try_get(comment_renderer,
2725 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2726
2727 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2728 lambda x: x['likeCount']), compat_str)) or 0
2729 author_thumbnail = try_get(comment_renderer,
2730 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2731
2732 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2733 is_favorited = 'creatorHeart' in (try_get(
2734 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2735 return {
2736 'id': comment_id,
2737 'text': text,
2738 'timestamp': timestamp,
2739 'time_text': time_text,
2740 'like_count': votes,
2741 'is_favorited': is_favorited,
2742 'author': author,
2743 'author_id': author_id,
2744 'author_thumbnail': author_thumbnail,
2745 'author_is_uploader': author_is_uploader,
2746 'parent': parent or 'root'
2747 }
2748
2749 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2750
2751 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2752
2753 def extract_header(contents):
2754 _continuation = None
2755 for content in contents:
2756 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2757 expected_comment_count = self._get_count(
2758 comments_header_renderer, 'countText', 'commentsCount')
2759
2760 if expected_comment_count:
2761 tracker['est_total'] = expected_comment_count
2762 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2763 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2764
2765 sort_menu_item = try_get(
2766 comments_header_renderer,
2767 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2768 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2769
2770 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2771 if not _continuation:
2772 continue
2773
2774 sort_text = str_or_none(sort_menu_item.get('title'))
2775 if not sort_text:
2776 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2777 self.to_screen('Sorting comments by %s' % sort_text.lower())
2778 break
2779 return _continuation
2780
2781 def extract_thread(contents):
2782 if not parent:
2783 tracker['current_page_thread'] = 0
2784 for content in contents:
2785 if not parent and tracker['total_parent_comments'] >= max_parents:
2786 yield
2787 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2788 comment_renderer = get_first(
2789 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2790 expected_type=dict, default={})
2791
2792 comment = self._extract_comment(comment_renderer, parent)
2793 if not comment:
2794 continue
2795
2796 tracker['running_total'] += 1
2797 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2798 yield comment
2799
2800 # Attempt to get the replies
2801 comment_replies_renderer = try_get(
2802 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2803
2804 if comment_replies_renderer:
2805 tracker['current_page_thread'] += 1
2806 comment_entries_iter = self._comment_entries(
2807 comment_replies_renderer, ytcfg, video_id,
2808 parent=comment.get('id'), tracker=tracker)
2809 yield from itertools.islice(comment_entries_iter, min(
2810 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2811
2812 # Keeps track of counts across recursive calls
2813 if not tracker:
2814 tracker = dict(
2815 running_total=0,
2816 est_total=0,
2817 current_page_thread=0,
2818 total_parent_comments=0,
2819 total_reply_comments=0)
2820
2821 # TODO: Deprecated
2822 # YouTube comments have a max depth of 2
2823 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2824 if max_depth:
2825 self._downloader.deprecation_warning(
2826 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2827 if max_depth == 1 and parent:
2828 return
2829
2830 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2831 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2832
2833 continuation = self._extract_continuation(root_continuation_data)
2834 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2835 if message and not parent:
2836 self.report_warning(message, video_id=video_id)
2837
2838 response = None
2839 is_first_continuation = parent is None
2840
2841 for page_num in itertools.count(0):
2842 if not continuation:
2843 break
2844 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2845 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2846 if page_num == 0:
2847 if is_first_continuation:
2848 note_prefix = 'Downloading comment section API JSON'
2849 else:
2850 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2851 tracker['current_page_thread'], comment_prog_str)
2852 else:
2853 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2854 ' ' if parent else '', ' replies' if parent else '',
2855 page_num, comment_prog_str)
2856
2857 response = self._extract_response(
2858 item_id=None, query=continuation,
2859 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2860 check_get_keys='onResponseReceivedEndpoints')
2861
2862 continuation_contents = traverse_obj(
2863 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2864
2865 continuation = None
2866 for continuation_section in continuation_contents:
2867 continuation_items = traverse_obj(
2868 continuation_section,
2869 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2870 get_all=False, expected_type=list) or []
2871 if is_first_continuation:
2872 continuation = extract_header(continuation_items)
2873 is_first_continuation = False
2874 if continuation:
2875 break
2876 continue
2877
2878 for entry in extract_thread(continuation_items):
2879 if not entry:
2880 return
2881 yield entry
2882 continuation = self._extract_continuation({'contents': continuation_items})
2883 if continuation:
2884 break
2885
2886 def _get_comments(self, ytcfg, video_id, contents, webpage):
2887 """Entry for comment extraction"""
2888 def _real_comment_extract(contents):
2889 renderer = next((
2890 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2891 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2892 yield from self._comment_entries(renderer, ytcfg, video_id)
2893
2894 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2895 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2896
2897 @staticmethod
2898 def _get_checkok_params():
2899 return {'contentCheckOk': True, 'racyCheckOk': True}
2900
2901 @classmethod
2902 def _generate_player_context(cls, sts=None):
2903 context = {
2904 'html5Preference': 'HTML5_PREF_WANTS',
2905 }
2906 if sts is not None:
2907 context['signatureTimestamp'] = sts
2908 return {
2909 'playbackContext': {
2910 'contentPlaybackContext': context
2911 },
2912 **cls._get_checkok_params()
2913 }
2914
2915 @staticmethod
2916 def _is_agegated(player_response):
2917 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2918 return True
2919
2920 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2921 AGE_GATE_REASONS = (
2922 'confirm your age', 'age-restricted', 'inappropriate', # reason
2923 'age_verification_required', 'age_check_required', # status
2924 )
2925 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2926
2927 @staticmethod
2928 def _is_unplayable(player_response):
2929 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2930
2931 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2932
2933 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2934 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2935 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2936 headers = self.generate_api_headers(
2937 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2938
2939 yt_query = {'videoId': video_id}
2940 yt_query.update(self._generate_player_context(sts))
2941 return self._extract_response(
2942 item_id=video_id, ep='player', query=yt_query,
2943 ytcfg=player_ytcfg, headers=headers, fatal=True,
2944 default_client=client,
2945 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2946 ) or None
2947
2948 def _get_requested_clients(self, url, smuggled_data):
2949 requested_clients = []
2950 default = ['android', 'web']
2951 allowed_clients = sorted(
2952 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
2953 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2954 for client in self._configuration_arg('player_client'):
2955 if client in allowed_clients:
2956 requested_clients.append(client)
2957 elif client == 'default':
2958 requested_clients.extend(default)
2959 elif client == 'all':
2960 requested_clients.extend(allowed_clients)
2961 else:
2962 self.report_warning(f'Skipping unsupported client {client}')
2963 if not requested_clients:
2964 requested_clients = default
2965
2966 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2967 requested_clients.extend(
2968 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2969
2970 return orderedSet(requested_clients)
2971
2972 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2973 initial_pr = None
2974 if webpage:
2975 initial_pr = self._extract_yt_initial_variable(
2976 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2977 video_id, 'initial player response')
2978
2979 all_clients = set(clients)
2980 clients = clients[::-1]
2981 prs = []
2982
2983 def append_client(*client_names):
2984 """ Append the first client name that exists but not already used """
2985 for client_name in client_names:
2986 actual_client = _split_innertube_client(client_name)[0]
2987 if actual_client in INNERTUBE_CLIENTS:
2988 if actual_client not in all_clients:
2989 clients.append(client_name)
2990 all_clients.add(actual_client)
2991 return
2992
2993 # Android player_response does not have microFormats which are needed for
2994 # extraction of some data. So we return the initial_pr with formats
2995 # stripped out even if not requested by the user
2996 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2997 if initial_pr:
2998 pr = dict(initial_pr)
2999 pr['streamingData'] = None
3000 prs.append(pr)
3001
3002 last_error = None
3003 tried_iframe_fallback = False
3004 player_url = None
3005 while clients:
3006 client, base_client, variant = _split_innertube_client(clients.pop())
3007 player_ytcfg = master_ytcfg if client == 'web' else {}
3008 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3009 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3010
3011 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3012 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3013 if 'js' in self._configuration_arg('player_skip'):
3014 require_js_player = False
3015 player_url = None
3016
3017 if not player_url and not tried_iframe_fallback and require_js_player:
3018 player_url = self._download_player_url(video_id)
3019 tried_iframe_fallback = True
3020
3021 try:
3022 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3023 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3024 except ExtractorError as e:
3025 if last_error:
3026 self.report_warning(last_error)
3027 last_error = e
3028 continue
3029
3030 if pr:
3031 prs.append(pr)
3032
3033 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3034 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3035 append_client(f'{base_client}_creator')
3036 elif self._is_agegated(pr):
3037 if variant == 'tv_embedded':
3038 append_client(f'{base_client}_embedded')
3039 elif not variant:
3040 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3041
3042 if last_error:
3043 if not len(prs):
3044 raise last_error
3045 self.report_warning(last_error)
3046 return prs, player_url
3047
3048 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
3049 itags, stream_ids = {}, []
3050 itag_qualities, res_qualities = {}, {}
3051 q = qualities([
3052 # Normally tiny is the smallest video-only formats. But
3053 # audio-only formats with unknown quality may get tagged as tiny
3054 'tiny',
3055 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3056 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3057 ])
3058 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3059
3060 for fmt in streaming_formats:
3061 if fmt.get('targetDurationSec'):
3062 continue
3063
3064 itag = str_or_none(fmt.get('itag'))
3065 audio_track = fmt.get('audioTrack') or {}
3066 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3067 if stream_id in stream_ids:
3068 continue
3069
3070 quality = fmt.get('quality')
3071 height = int_or_none(fmt.get('height'))
3072 if quality == 'tiny' or not quality:
3073 quality = fmt.get('audioQuality', '').lower() or quality
3074 # The 3gp format (17) in android client has a quality of "small",
3075 # but is actually worse than other formats
3076 if itag == '17':
3077 quality = 'tiny'
3078 if quality:
3079 if itag:
3080 itag_qualities[itag] = quality
3081 if height:
3082 res_qualities[height] = quality
3083 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3084 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3085 # number of fragment that would subsequently requested with (`&sq=N`)
3086 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3087 continue
3088
3089 fmt_url = fmt.get('url')
3090 if not fmt_url:
3091 sc = compat_parse_qs(fmt.get('signatureCipher'))
3092 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3093 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3094 if not (sc and fmt_url and encrypted_sig):
3095 continue
3096 if not player_url:
3097 continue
3098 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3099 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3100 fmt_url += '&' + sp + '=' + signature
3101
3102 query = parse_qs(fmt_url)
3103 throttled = False
3104 if query.get('n'):
3105 try:
3106 fmt_url = update_url_query(fmt_url, {
3107 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3108 except ExtractorError as e:
3109 self.report_warning(
3110 f'nsig extraction failed: You may experience throttling for some formats\n'
3111 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
3112 throttled = True
3113
3114 if itag:
3115 itags[itag] = 'https'
3116 stream_ids.append(stream_id)
3117
3118 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3119 language_preference = (
3120 10 if audio_track.get('audioIsDefault') and 10
3121 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3122 else -1)
3123 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3124 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3125 # Make sure to avoid false positives with small duration differences.
3126 # Eg: __2ABJjxzNo, ySuUZEjARPY
3127 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3128 if is_damaged:
3129 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3130 dct = {
3131 'asr': int_or_none(fmt.get('audioSampleRate')),
3132 'filesize': int_or_none(fmt.get('contentLength')),
3133 'format_id': itag,
3134 'format_note': join_nonempty(
3135 '%s%s' % (audio_track.get('displayName') or '',
3136 ' (default)' if language_preference > 0 else ''),
3137 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3138 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3139 'source_preference': -10 if throttled else -1,
3140 'fps': int_or_none(fmt.get('fps')) or None,
3141 'height': height,
3142 'quality': q(quality),
3143 'has_drm': bool(fmt.get('drmFamilies')),
3144 'tbr': tbr,
3145 'url': fmt_url,
3146 'width': int_or_none(fmt.get('width')),
3147 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3148 'desc' if language_preference < -1 else ''),
3149 'language_preference': language_preference,
3150 # Strictly de-prioritize damaged and 3gp formats
3151 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3152 }
3153 mime_mobj = re.match(
3154 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3155 if mime_mobj:
3156 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3157 dct.update(parse_codecs(mime_mobj.group(2)))
3158 no_audio = dct.get('acodec') == 'none'
3159 no_video = dct.get('vcodec') == 'none'
3160 if no_audio:
3161 dct['vbr'] = tbr
3162 if no_video:
3163 dct['abr'] = tbr
3164 if no_audio or no_video:
3165 dct['downloader_options'] = {
3166 # Youtube throttles chunks >~10M
3167 'http_chunk_size': 10485760,
3168 }
3169 if dct.get('ext'):
3170 dct['container'] = dct['ext'] + '_dash'
3171 yield dct
3172
3173 live_from_start = is_live and self.get_param('live_from_start')
3174 skip_manifests = self._configuration_arg('skip')
3175 if not self.get_param('youtube_include_hls_manifest', True):
3176 skip_manifests.append('hls')
3177 get_dash = 'dash' not in skip_manifests and (
3178 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3179 get_hls = not live_from_start and 'hls' not in skip_manifests
3180
3181 def process_manifest_format(f, proto, itag):
3182 if itag in itags:
3183 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3184 return False
3185 itag = f'{itag}-{proto}'
3186 if itag:
3187 f['format_id'] = itag
3188 itags[itag] = proto
3189
3190 f['quality'] = next((
3191 q(qdict[val])
3192 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3193 if val in qdict), -1)
3194 return True
3195
3196 for sd in streaming_data:
3197 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3198 if hls_manifest_url:
3199 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3200 if process_manifest_format(f, 'hls', self._search_regex(
3201 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3202 yield f
3203
3204 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3205 if dash_manifest_url:
3206 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3207 if process_manifest_format(f, 'dash', f['format_id']):
3208 f['filesize'] = int_or_none(self._search_regex(
3209 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3210 if live_from_start:
3211 f['is_from_start'] = True
3212
3213 yield f
3214
3215 def _extract_storyboard(self, player_responses, duration):
3216 spec = get_first(
3217 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3218 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3219 if not base_url:
3220 return
3221 L = len(spec) - 1
3222 for i, args in enumerate(spec):
3223 args = args.split('#')
3224 counts = list(map(int_or_none, args[:5]))
3225 if len(args) != 8 or not all(counts):
3226 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3227 continue
3228 width, height, frame_count, cols, rows = counts
3229 N, sigh = args[6:]
3230
3231 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3232 fragment_count = frame_count / (cols * rows)
3233 fragment_duration = duration / fragment_count
3234 yield {
3235 'format_id': f'sb{i}',
3236 'format_note': 'storyboard',
3237 'ext': 'mhtml',
3238 'protocol': 'mhtml',
3239 'acodec': 'none',
3240 'vcodec': 'none',
3241 'url': url,
3242 'width': width,
3243 'height': height,
3244 'fragments': [{
3245 'url': url.replace('$M', str(j)),
3246 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3247 } for j in range(math.ceil(fragment_count))],
3248 }
3249
3250 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3251 webpage = None
3252 if 'webpage' not in self._configuration_arg('player_skip'):
3253 webpage = self._download_webpage(
3254 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3255
3256 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3257
3258 player_responses, player_url = self._extract_player_responses(
3259 self._get_requested_clients(url, smuggled_data),
3260 video_id, webpage, master_ytcfg)
3261
3262 return webpage, master_ytcfg, player_responses, player_url
3263
3264 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3265 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3266 is_live = get_first(video_details, 'isLive')
3267 if is_live is None:
3268 is_live = get_first(live_broadcast_details, 'isLiveNow')
3269
3270 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3271 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
3272
3273 return live_broadcast_details, is_live, streaming_data, formats
3274
3275 def _real_extract(self, url):
3276 url, smuggled_data = unsmuggle_url(url, {})
3277 video_id = self._match_id(url)
3278
3279 base_url = self.http_scheme() + '//www.youtube.com/'
3280 webpage_url = base_url + 'watch?v=' + video_id
3281
3282 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3283
3284 playability_statuses = traverse_obj(
3285 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3286
3287 trailer_video_id = get_first(
3288 playability_statuses,
3289 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3290 expected_type=str)
3291 if trailer_video_id:
3292 return self.url_result(
3293 trailer_video_id, self.ie_key(), trailer_video_id)
3294
3295 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3296 if webpage else (lambda x: None))
3297
3298 video_details = traverse_obj(
3299 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3300 microformats = traverse_obj(
3301 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3302 expected_type=dict, default=[])
3303 video_title = (
3304 get_first(video_details, 'title')
3305 or self._get_text(microformats, (..., 'title'))
3306 or search_meta(['og:title', 'twitter:title', 'title']))
3307 video_description = get_first(video_details, 'shortDescription')
3308
3309 multifeed_metadata_list = get_first(
3310 player_responses,
3311 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3312 expected_type=str)
3313 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3314 if self.get_param('noplaylist'):
3315 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3316 else:
3317 entries = []
3318 feed_ids = []
3319 for feed in multifeed_metadata_list.split(','):
3320 # Unquote should take place before split on comma (,) since textual
3321 # fields may contain comma as well (see
3322 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3323 feed_data = compat_parse_qs(
3324 compat_urllib_parse_unquote_plus(feed))
3325
3326 def feed_entry(name):
3327 return try_get(
3328 feed_data, lambda x: x[name][0], compat_str)
3329
3330 feed_id = feed_entry('id')
3331 if not feed_id:
3332 continue
3333 feed_title = feed_entry('title')
3334 title = video_title
3335 if feed_title:
3336 title += ' (%s)' % feed_title
3337 entries.append({
3338 '_type': 'url_transparent',
3339 'ie_key': 'Youtube',
3340 'url': smuggle_url(
3341 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3342 {'force_singlefeed': True}),
3343 'title': title,
3344 })
3345 feed_ids.append(feed_id)
3346 self.to_screen(
3347 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3348 % (', '.join(feed_ids), video_id))
3349 return self.playlist_result(
3350 entries, video_id, video_title, video_description)
3351
3352 duration = int_or_none(
3353 get_first(video_details, 'lengthSeconds')
3354 or get_first(microformats, 'lengthSeconds')
3355 or parse_duration(search_meta('duration'))) or None
3356
3357 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3358 video_id, microformats, video_details, player_responses, player_url, duration)
3359
3360 if not formats:
3361 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3362 self.report_drm(video_id)
3363 pemr = get_first(
3364 playability_statuses,
3365 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3366 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3367 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3368 if subreason:
3369 if subreason == 'The uploader has not made this video available in your country.':
3370 countries = get_first(microformats, 'availableCountries')
3371 if not countries:
3372 regions_allowed = search_meta('regionsAllowed')
3373 countries = regions_allowed.split(',') if regions_allowed else None
3374 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3375 reason += f'. {subreason}'
3376 if reason:
3377 self.raise_no_formats(reason, expected=True)
3378
3379 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3380 if not keywords and webpage:
3381 keywords = [
3382 unescapeHTML(m.group('content'))
3383 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3384 for keyword in keywords:
3385 if keyword.startswith('yt:stretch='):
3386 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3387 if mobj:
3388 # NB: float is intentional for forcing float division
3389 w, h = (float(v) for v in mobj.groups())
3390 if w > 0 and h > 0:
3391 ratio = w / h
3392 for f in formats:
3393 if f.get('vcodec') != 'none':
3394 f['stretched_ratio'] = ratio
3395 break
3396 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3397 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3398 if thumbnail_url:
3399 thumbnails.append({
3400 'url': thumbnail_url,
3401 })
3402 original_thumbnails = thumbnails.copy()
3403
3404 # The best resolution thumbnails sometimes does not appear in the webpage
3405 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3406 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3407 thumbnail_names = [
3408 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3409 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3410 'mqdefault', 'mq1', 'mq2', 'mq3',
3411 'default', '1', '2', '3'
3412 ]
3413 n_thumbnail_names = len(thumbnail_names)
3414 thumbnails.extend({
3415 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3416 video_id=video_id, name=name, ext=ext,
3417 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3418 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3419 for thumb in thumbnails:
3420 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3421 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3422 self._remove_duplicate_formats(thumbnails)
3423 self._downloader._sort_thumbnails(original_thumbnails)
3424
3425 category = get_first(microformats, 'category') or search_meta('genre')
3426 channel_id = str_or_none(
3427 get_first(video_details, 'channelId')
3428 or get_first(microformats, 'externalChannelId')
3429 or search_meta('channelId'))
3430 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3431
3432 live_content = get_first(video_details, 'isLiveContent')
3433 is_upcoming = get_first(video_details, 'isUpcoming')
3434 if is_live is None:
3435 if is_upcoming or live_content is False:
3436 is_live = False
3437 if is_upcoming is None and (live_content or is_live):
3438 is_upcoming = False
3439 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3440 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3441 if not duration and live_end_time and live_start_time:
3442 duration = live_end_time - live_start_time
3443
3444 if is_live and self.get_param('live_from_start'):
3445 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3446
3447 formats.extend(self._extract_storyboard(player_responses, duration))
3448
3449 # Source is given priority since formats that throttle are given lower source_preference
3450 # When throttling issue is fully fixed, remove this
3451 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3452
3453 info = {
3454 'id': video_id,
3455 'title': video_title,
3456 'formats': formats,
3457 'thumbnails': thumbnails,
3458 # The best thumbnail that we are sure exists. Prevents unnecessary
3459 # URL checking if user don't care about getting the best possible thumbnail
3460 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3461 'description': video_description,
3462 'uploader': get_first(video_details, 'author'),
3463 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3464 'uploader_url': owner_profile_url,
3465 'channel_id': channel_id,
3466 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3467 'duration': duration,
3468 'view_count': int_or_none(
3469 get_first((video_details, microformats), (..., 'viewCount'))
3470 or search_meta('interactionCount')),
3471 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3472 'age_limit': 18 if (
3473 get_first(microformats, 'isFamilySafe') is False
3474 or search_meta('isFamilyFriendly') == 'false'
3475 or search_meta('og:restrictions:age') == '18+') else 0,
3476 'webpage_url': webpage_url,
3477 'categories': [category] if category else None,
3478 'tags': keywords,
3479 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3480 'is_live': is_live,
3481 'was_live': (False if is_live or is_upcoming or live_content is False
3482 else None if is_live is None or is_upcoming is None
3483 else live_content),
3484 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3485 'release_timestamp': live_start_time,
3486 }
3487
3488 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3489 if pctr:
3490 def get_lang_code(track):
3491 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3492 or track.get('languageCode'))
3493
3494 # Converted into dicts to remove duplicates
3495 captions = {
3496 get_lang_code(sub): sub
3497 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3498 translation_languages = {
3499 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3500 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3501
3502 def process_language(container, base_url, lang_code, sub_name, query):
3503 lang_subs = container.setdefault(lang_code, [])
3504 for fmt in self._SUBTITLE_FORMATS:
3505 query.update({
3506 'fmt': fmt,
3507 })
3508 lang_subs.append({
3509 'ext': fmt,
3510 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3511 'name': sub_name,
3512 })
3513
3514 subtitles, automatic_captions = {}, {}
3515 for lang_code, caption_track in captions.items():
3516 base_url = caption_track.get('baseUrl')
3517 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3518 if not base_url:
3519 continue
3520 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3521 if caption_track.get('kind') != 'asr':
3522 if not lang_code:
3523 continue
3524 process_language(
3525 subtitles, base_url, lang_code, lang_name, {})
3526 if not caption_track.get('isTranslatable'):
3527 continue
3528 for trans_code, trans_name in translation_languages.items():
3529 if not trans_code:
3530 continue
3531 orig_trans_code = trans_code
3532 if caption_track.get('kind') != 'asr':
3533 if 'translated_subs' in self._configuration_arg('skip'):
3534 continue
3535 trans_code += f'-{lang_code}'
3536 trans_name += format_field(lang_name, template=' from %s')
3537 # Add an "-orig" label to the original language so that it can be distinguished.
3538 # The subs are returned without "-orig" as well for compatibility
3539 if lang_code == f'a-{orig_trans_code}':
3540 process_language(
3541 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3542 # Setting tlang=lang returns damaged subtitles.
3543 process_language(automatic_captions, base_url, trans_code, trans_name,
3544 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
3545 info['automatic_captions'] = automatic_captions
3546 info['subtitles'] = subtitles
3547
3548 parsed_url = compat_urllib_parse_urlparse(url)
3549 for component in [parsed_url.fragment, parsed_url.query]:
3550 query = compat_parse_qs(component)
3551 for k, v in query.items():
3552 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3553 d_k += '_time'
3554 if d_k not in info and k in s_ks:
3555 info[d_k] = parse_duration(query[k][0])
3556
3557 # Youtube Music Auto-generated description
3558 if video_description:
3559 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
3560 if mobj:
3561 release_year = mobj.group('release_year')
3562 release_date = mobj.group('release_date')
3563 if release_date:
3564 release_date = release_date.replace('-', '')
3565 if not release_year:
3566 release_year = release_date[:4]
3567 info.update({
3568 'album': mobj.group('album'.strip()),
3569 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3570 'track': mobj.group('track').strip(),
3571 'release_date': release_date,
3572 'release_year': int_or_none(release_year),
3573 })
3574
3575 initial_data = None
3576 if webpage:
3577 initial_data = self._extract_yt_initial_variable(
3578 webpage, self._YT_INITIAL_DATA_RE, video_id,
3579 'yt initial data')
3580 if not initial_data:
3581 query = {'videoId': video_id}
3582 query.update(self._get_checkok_params())
3583 initial_data = self._extract_response(
3584 item_id=video_id, ep='next', fatal=False,
3585 ytcfg=master_ytcfg, query=query,
3586 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3587 note='Downloading initial data API JSON')
3588
3589 try: # This will error if there is no livechat
3590 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3591 except (KeyError, IndexError, TypeError):
3592 pass
3593 else:
3594 info.setdefault('subtitles', {})['live_chat'] = [{
3595 'url': f'https://www.youtube.com/watch?v={video_id}', # url is needed to set cookies
3596 'video_id': video_id,
3597 'ext': 'json',
3598 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3599 }]
3600
3601 if initial_data:
3602 info['chapters'] = (
3603 self._extract_chapters_from_json(initial_data, duration)
3604 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3605 or None)
3606
3607 contents = traverse_obj(
3608 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3609 expected_type=list, default=[])
3610
3611 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3612 if vpir:
3613 stl = vpir.get('superTitleLink')
3614 if stl:
3615 stl = self._get_text(stl)
3616 if try_get(
3617 vpir,
3618 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3619 info['location'] = stl
3620 else:
3621 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
3622 if mobj:
3623 info.update({
3624 'series': mobj.group(1),
3625 'season_number': int(mobj.group(2)),
3626 'episode_number': int(mobj.group(3)),
3627 })
3628 for tlb in (try_get(
3629 vpir,
3630 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3631 list) or []):
3632 tbr = tlb.get('toggleButtonRenderer') or {}
3633 for getter, regex in [(
3634 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3635 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3636 lambda x: x['accessibility'],
3637 lambda x: x['accessibilityData']['accessibilityData'],
3638 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3639 label = (try_get(tbr, getter, dict) or {}).get('label')
3640 if label:
3641 mobj = re.match(regex, label)
3642 if mobj:
3643 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3644 break
3645 sbr_tooltip = try_get(
3646 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3647 if sbr_tooltip:
3648 like_count, dislike_count = sbr_tooltip.split(' / ')
3649 info.update({
3650 'like_count': str_to_int(like_count),
3651 'dislike_count': str_to_int(dislike_count),
3652 })
3653 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3654 if vsir:
3655 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3656 info.update({
3657 'channel': self._get_text(vor, 'title'),
3658 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3659
3660 rows = try_get(
3661 vsir,
3662 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3663 list) or []
3664 multiple_songs = False
3665 for row in rows:
3666 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3667 multiple_songs = True
3668 break
3669 for row in rows:
3670 mrr = row.get('metadataRowRenderer') or {}
3671 mrr_title = mrr.get('title')
3672 if not mrr_title:
3673 continue
3674 mrr_title = self._get_text(mrr, 'title')
3675 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3676 if mrr_title == 'License':
3677 info['license'] = mrr_contents_text
3678 elif not multiple_songs:
3679 if mrr_title == 'Album':
3680 info['album'] = mrr_contents_text
3681 elif mrr_title == 'Artist':
3682 info['artist'] = mrr_contents_text
3683 elif mrr_title == 'Song':
3684 info['track'] = mrr_contents_text
3685
3686 fallbacks = {
3687 'channel': 'uploader',
3688 'channel_id': 'uploader_id',
3689 'channel_url': 'uploader_url',
3690 }
3691
3692 # The upload date for scheduled, live and past live streams / premieres in microformats
3693 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3694 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3695 upload_date = (
3696 unified_strdate(get_first(microformats, 'uploadDate'))
3697 or unified_strdate(search_meta('uploadDate')))
3698 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3699 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3700 info['upload_date'] = upload_date
3701
3702 for to, frm in fallbacks.items():
3703 if not info.get(to):
3704 info[to] = info.get(frm)
3705
3706 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3707 v = info.get(s_k)
3708 if v:
3709 info[d_k] = v
3710
3711 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3712 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3713 is_membersonly = None
3714 is_premium = None
3715 if initial_data and is_private is not None:
3716 is_membersonly = False
3717 is_premium = False
3718 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3719 badge_labels = set()
3720 for content in contents:
3721 if not isinstance(content, dict):
3722 continue
3723 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3724 for badge_label in badge_labels:
3725 if badge_label.lower() == 'members only':
3726 is_membersonly = True
3727 elif badge_label.lower() == 'premium':
3728 is_premium = True
3729 elif badge_label.lower() == 'unlisted':
3730 is_unlisted = True
3731
3732 info['availability'] = self._availability(
3733 is_private=is_private,
3734 needs_premium=is_premium,
3735 needs_subscription=is_membersonly,
3736 needs_auth=info['age_limit'] >= 18,
3737 is_unlisted=None if is_private is None else is_unlisted)
3738
3739 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3740
3741 self.mark_watched(video_id, player_responses)
3742
3743 return info
3744
3745
3746 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3747
3748 @staticmethod
3749 def passthrough_smuggled_data(func):
3750 def _smuggle(entries, smuggled_data):
3751 for entry in entries:
3752 # TODO: Convert URL to music.youtube instead.
3753 # Do we need to passthrough any other smuggled_data?
3754 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3755 yield entry
3756
3757 @functools.wraps(func)
3758 def wrapper(self, url):
3759 url, smuggled_data = unsmuggle_url(url, {})
3760 if self.is_music_url(url):
3761 smuggled_data['is_music_url'] = True
3762 info_dict = func(self, url, smuggled_data)
3763 if smuggled_data and info_dict.get('entries'):
3764 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3765 return info_dict
3766 return wrapper
3767
3768 def _extract_channel_id(self, webpage):
3769 channel_id = self._html_search_meta(
3770 'channelId', webpage, 'channel id', default=None)
3771 if channel_id:
3772 return channel_id
3773 channel_url = self._html_search_meta(
3774 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3775 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3776 'twitter:app:url:googleplay'), webpage, 'channel url')
3777 return self._search_regex(
3778 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3779 channel_url, 'channel id')
3780
3781 @staticmethod
3782 def _extract_basic_item_renderer(item):
3783 # Modified from _extract_grid_item_renderer
3784 known_basic_renderers = (
3785 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3786 )
3787 for key, renderer in item.items():
3788 if not isinstance(renderer, dict):
3789 continue
3790 elif key in known_basic_renderers:
3791 return renderer
3792 elif key.startswith('grid') and key.endswith('Renderer'):
3793 return renderer
3794
3795 def _grid_entries(self, grid_renderer):
3796 for item in grid_renderer['items']:
3797 if not isinstance(item, dict):
3798 continue
3799 renderer = self._extract_basic_item_renderer(item)
3800 if not isinstance(renderer, dict):
3801 continue
3802 title = self._get_text(renderer, 'title')
3803
3804 # playlist
3805 playlist_id = renderer.get('playlistId')
3806 if playlist_id:
3807 yield self.url_result(
3808 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3809 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3810 video_title=title)
3811 continue
3812 # video
3813 video_id = renderer.get('videoId')
3814 if video_id:
3815 yield self._extract_video(renderer)
3816 continue
3817 # channel
3818 channel_id = renderer.get('channelId')
3819 if channel_id:
3820 yield self.url_result(
3821 'https://www.youtube.com/channel/%s' % channel_id,
3822 ie=YoutubeTabIE.ie_key(), video_title=title)
3823 continue
3824 # generic endpoint URL support
3825 ep_url = urljoin('https://www.youtube.com/', try_get(
3826 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3827 compat_str))
3828 if ep_url:
3829 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3830 if ie.suitable(ep_url):
3831 yield self.url_result(
3832 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3833 break
3834
3835 def _music_reponsive_list_entry(self, renderer):
3836 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3837 if video_id:
3838 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3839 ie=YoutubeIE.ie_key(), video_id=video_id)
3840 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3841 if playlist_id:
3842 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3843 if video_id:
3844 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3845 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3846 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3847 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3848 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3849 if browse_id:
3850 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3851 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3852
3853 def _shelf_entries_from_content(self, shelf_renderer):
3854 content = shelf_renderer.get('content')
3855 if not isinstance(content, dict):
3856 return
3857 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3858 if renderer:
3859 # TODO: add support for nested playlists so each shelf is processed
3860 # as separate playlist
3861 # TODO: this includes only first N items
3862 yield from self._grid_entries(renderer)
3863 renderer = content.get('horizontalListRenderer')
3864 if renderer:
3865 # TODO
3866 pass
3867
3868 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3869 ep = try_get(
3870 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3871 compat_str)
3872 shelf_url = urljoin('https://www.youtube.com', ep)
3873 if shelf_url:
3874 # Skipping links to another channels, note that checking for
3875 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3876 # will not work
3877 if skip_channels and '/channels?' in shelf_url:
3878 return
3879 title = self._get_text(shelf_renderer, 'title')
3880 yield self.url_result(shelf_url, video_title=title)
3881 # Shelf may not contain shelf URL, fallback to extraction from content
3882 yield from self._shelf_entries_from_content(shelf_renderer)
3883
3884 def _playlist_entries(self, video_list_renderer):
3885 for content in video_list_renderer['contents']:
3886 if not isinstance(content, dict):
3887 continue
3888 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3889 if not isinstance(renderer, dict):
3890 continue
3891 video_id = renderer.get('videoId')
3892 if not video_id:
3893 continue
3894 yield self._extract_video(renderer)
3895
3896 def _rich_entries(self, rich_grid_renderer):
3897 renderer = try_get(
3898 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3899 video_id = renderer.get('videoId')
3900 if not video_id:
3901 return
3902 yield self._extract_video(renderer)
3903
3904 def _video_entry(self, video_renderer):
3905 video_id = video_renderer.get('videoId')
3906 if video_id:
3907 return self._extract_video(video_renderer)
3908
3909 def _hashtag_tile_entry(self, hashtag_tile_renderer):
3910 url = urljoin('https://youtube.com', traverse_obj(
3911 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
3912 if url:
3913 return self.url_result(
3914 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
3915
3916 def _post_thread_entries(self, post_thread_renderer):
3917 post_renderer = try_get(
3918 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3919 if not post_renderer:
3920 return
3921 # video attachment
3922 video_renderer = try_get(
3923 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3924 video_id = video_renderer.get('videoId')
3925 if video_id:
3926 entry = self._extract_video(video_renderer)
3927 if entry:
3928 yield entry
3929 # playlist attachment
3930 playlist_id = try_get(
3931 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
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 # inline video links
3937 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3938 for run in runs:
3939 if not isinstance(run, dict):
3940 continue
3941 ep_url = try_get(
3942 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3943 if not ep_url:
3944 continue
3945 if not YoutubeIE.suitable(ep_url):
3946 continue
3947 ep_video_id = YoutubeIE._match_id(ep_url)
3948 if video_id == ep_video_id:
3949 continue
3950 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3951
3952 def _post_thread_continuation_entries(self, post_thread_continuation):
3953 contents = post_thread_continuation.get('contents')
3954 if not isinstance(contents, list):
3955 return
3956 for content in contents:
3957 renderer = content.get('backstagePostThreadRenderer')
3958 if not isinstance(renderer, dict):
3959 continue
3960 yield from self._post_thread_entries(renderer)
3961
3962 r''' # unused
3963 def _rich_grid_entries(self, contents):
3964 for content in contents:
3965 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3966 if video_renderer:
3967 entry = self._video_entry(video_renderer)
3968 if entry:
3969 yield entry
3970 '''
3971
3972 def _extract_entries(self, parent_renderer, continuation_list):
3973 # continuation_list is modified in-place with continuation_list = [continuation_token]
3974 continuation_list[:] = [None]
3975 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3976 for content in contents:
3977 if not isinstance(content, dict):
3978 continue
3979 is_renderer = traverse_obj(
3980 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3981 expected_type=dict)
3982 if not is_renderer:
3983 renderer = content.get('richItemRenderer')
3984 if renderer:
3985 for entry in self._rich_entries(renderer):
3986 yield entry
3987 continuation_list[0] = self._extract_continuation(parent_renderer)
3988 continue
3989 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3990 for isr_content in isr_contents:
3991 if not isinstance(isr_content, dict):
3992 continue
3993
3994 known_renderers = {
3995 'playlistVideoListRenderer': self._playlist_entries,
3996 'gridRenderer': self._grid_entries,
3997 'reelShelfRenderer': self._grid_entries,
3998 'shelfRenderer': self._shelf_entries,
3999 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4000 'backstagePostThreadRenderer': self._post_thread_entries,
4001 'videoRenderer': lambda x: [self._video_entry(x)],
4002 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4003 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4004 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4005 }
4006 for key, renderer in isr_content.items():
4007 if key not in known_renderers:
4008 continue
4009 for entry in known_renderers[key](renderer):
4010 if entry:
4011 yield entry
4012 continuation_list[0] = self._extract_continuation(renderer)
4013 break
4014
4015 if not continuation_list[0]:
4016 continuation_list[0] = self._extract_continuation(is_renderer)
4017
4018 if not continuation_list[0]:
4019 continuation_list[0] = self._extract_continuation(parent_renderer)
4020
4021 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4022 continuation_list = [None]
4023 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4024 tab_content = try_get(tab, lambda x: x['content'], dict)
4025 if not tab_content:
4026 return
4027 parent_renderer = (
4028 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4029 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4030 yield from extract_entries(parent_renderer)
4031 continuation = continuation_list[0]
4032
4033 for page_num in itertools.count(1):
4034 if not continuation:
4035 break
4036 headers = self.generate_api_headers(
4037 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4038 response = self._extract_response(
4039 item_id=f'{item_id} page {page_num}',
4040 query=continuation, headers=headers, ytcfg=ytcfg,
4041 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4042
4043 if not response:
4044 break
4045 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4046 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4047 visitor_data = self._extract_visitor_data(response) or visitor_data
4048
4049 known_continuation_renderers = {
4050 'playlistVideoListContinuation': self._playlist_entries,
4051 'gridContinuation': self._grid_entries,
4052 'itemSectionContinuation': self._post_thread_continuation_entries,
4053 'sectionListContinuation': extract_entries, # for feeds
4054 }
4055 continuation_contents = try_get(
4056 response, lambda x: x['continuationContents'], dict) or {}
4057 continuation_renderer = None
4058 for key, value in continuation_contents.items():
4059 if key not in known_continuation_renderers:
4060 continue
4061 continuation_renderer = value
4062 continuation_list = [None]
4063 yield from known_continuation_renderers[key](continuation_renderer)
4064 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4065 break
4066 if continuation_renderer:
4067 continue
4068
4069 known_renderers = {
4070 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4071 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4072 'gridVideoRenderer': (self._grid_entries, 'items'),
4073 'gridChannelRenderer': (self._grid_entries, 'items'),
4074 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4075 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4076 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4077 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
4078 }
4079 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4080 continuation_items = try_get(
4081 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
4082 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4083 video_items_renderer = None
4084 for key, value in continuation_item.items():
4085 if key not in known_renderers:
4086 continue
4087 video_items_renderer = {known_renderers[key][1]: continuation_items}
4088 continuation_list = [None]
4089 yield from known_renderers[key][0](video_items_renderer)
4090 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4091 break
4092 if video_items_renderer:
4093 continue
4094 break
4095
4096 @staticmethod
4097 def _extract_selected_tab(tabs, fatal=True):
4098 for tab in tabs:
4099 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4100 if renderer.get('selected') is True:
4101 return renderer
4102 else:
4103 if fatal:
4104 raise ExtractorError('Unable to find selected tab')
4105
4106 def _extract_uploader(self, data):
4107 uploader = {}
4108 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4109 owner = try_get(
4110 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4111 if owner:
4112 owner_text = owner.get('text')
4113 uploader['uploader'] = self._search_regex(
4114 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
4115 uploader['uploader_id'] = try_get(
4116 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4117 uploader['uploader_url'] = urljoin(
4118 'https://www.youtube.com/',
4119 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
4120 return {k: v for k, v in uploader.items() if v is not None}
4121
4122 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4123 playlist_id = title = description = channel_url = channel_name = channel_id = None
4124 tags = []
4125
4126 selected_tab = self._extract_selected_tab(tabs)
4127 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4128 renderer = try_get(
4129 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4130 if renderer:
4131 channel_name = renderer.get('title')
4132 channel_url = renderer.get('channelUrl')
4133 channel_id = renderer.get('externalId')
4134 else:
4135 renderer = try_get(
4136 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
4137
4138 if renderer:
4139 title = renderer.get('title')
4140 description = renderer.get('description', '')
4141 playlist_id = channel_id
4142 tags = renderer.get('keywords', '').split()
4143
4144 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4145 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4146 def _get_uncropped(url):
4147 return url_or_none((url or '').split('=')[0] + '=s0')
4148
4149 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4150 if avatar_thumbnails:
4151 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4152 if uncropped_avatar:
4153 avatar_thumbnails.append({
4154 'url': uncropped_avatar,
4155 'id': 'avatar_uncropped',
4156 'preference': 1
4157 })
4158
4159 channel_banners = self._extract_thumbnails(
4160 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4161 for banner in channel_banners:
4162 banner['preference'] = -10
4163
4164 if channel_banners:
4165 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4166 if uncropped_banner:
4167 channel_banners.append({
4168 'url': uncropped_banner,
4169 'id': 'banner_uncropped',
4170 'preference': -5
4171 })
4172
4173 primary_thumbnails = self._extract_thumbnails(
4174 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4175
4176 if playlist_id is None:
4177 playlist_id = item_id
4178
4179 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4180 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
4181 if title is None:
4182 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4183 title += format_field(selected_tab, 'title', ' - %s')
4184 title += format_field(selected_tab, 'expandedText', ' - %s')
4185
4186 metadata = {
4187 'playlist_id': playlist_id,
4188 'playlist_title': title,
4189 'playlist_description': description,
4190 'uploader': channel_name,
4191 'uploader_id': channel_id,
4192 'uploader_url': channel_url,
4193 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4194 'tags': tags,
4195 'view_count': self._get_count(playlist_stats, 1),
4196 'availability': self._extract_availability(data),
4197 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4198 'playlist_count': self._get_count(playlist_stats, 0),
4199 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4200 }
4201 if not channel_id:
4202 metadata.update(self._extract_uploader(data))
4203 metadata.update({
4204 'channel': metadata['uploader'],
4205 'channel_id': metadata['uploader_id'],
4206 'channel_url': metadata['uploader_url']})
4207 return self.playlist_result(
4208 self._entries(
4209 selected_tab, playlist_id, ytcfg,
4210 self._extract_account_syncid(ytcfg, data),
4211 self._extract_visitor_data(data, ytcfg)),
4212 **metadata)
4213
4214 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4215 first_id = last_id = response = None
4216 for page_num in itertools.count(1):
4217 videos = list(self._playlist_entries(playlist))
4218 if not videos:
4219 return
4220 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4221 if start >= len(videos):
4222 return
4223 for video in videos[start:]:
4224 if video['id'] == first_id:
4225 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4226 return
4227 yield video
4228 first_id = first_id or videos[0]['id']
4229 last_id = videos[-1]['id']
4230 watch_endpoint = try_get(
4231 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4232 headers = self.generate_api_headers(
4233 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4234 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4235 query = {
4236 'playlistId': playlist_id,
4237 'videoId': watch_endpoint.get('videoId') or last_id,
4238 'index': watch_endpoint.get('index') or len(videos),
4239 'params': watch_endpoint.get('params') or 'OAE%3D'
4240 }
4241 response = self._extract_response(
4242 item_id='%s page %d' % (playlist_id, page_num),
4243 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4244 check_get_keys='contents'
4245 )
4246 playlist = try_get(
4247 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4248
4249 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4250 title = playlist.get('title') or try_get(
4251 data, lambda x: x['titleText']['simpleText'], compat_str)
4252 playlist_id = playlist.get('playlistId') or item_id
4253
4254 # Delegating everything except mix playlists to regular tab-based playlist URL
4255 playlist_url = urljoin(url, try_get(
4256 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4257 compat_str))
4258 if playlist_url and playlist_url != url:
4259 return self.url_result(
4260 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4261 video_title=title)
4262
4263 return self.playlist_result(
4264 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4265 playlist_id=playlist_id, playlist_title=title)
4266
4267 def _extract_availability(self, data):
4268 """
4269 Gets the availability of a given playlist/tab.
4270 Note: Unless YouTube tells us explicitly, we do not assume it is public
4271 @param data: response
4272 """
4273 is_private = is_unlisted = None
4274 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4275 badge_labels = self._extract_badges(renderer)
4276
4277 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4278 privacy_dropdown_entries = try_get(
4279 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4280 for renderer_dict in privacy_dropdown_entries:
4281 is_selected = try_get(
4282 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4283 if not is_selected:
4284 continue
4285 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4286 if label:
4287 badge_labels.add(label.lower())
4288 break
4289
4290 for badge_label in badge_labels:
4291 if badge_label == 'unlisted':
4292 is_unlisted = True
4293 elif badge_label == 'private':
4294 is_private = True
4295 elif badge_label == 'public':
4296 is_unlisted = is_private = False
4297 return self._availability(is_private, False, False, False, is_unlisted)
4298
4299 @staticmethod
4300 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4301 sidebar_renderer = try_get(
4302 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4303 for item in sidebar_renderer:
4304 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4305 if renderer:
4306 return renderer
4307
4308 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4309 """
4310 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4311 """
4312 browse_id = params = None
4313 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4314 if not renderer:
4315 return
4316 menu_renderer = try_get(
4317 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4318 for menu_item in menu_renderer:
4319 if not isinstance(menu_item, dict):
4320 continue
4321 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4322 text = try_get(
4323 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4324 if not text or text.lower() != 'show unavailable videos':
4325 continue
4326 browse_endpoint = try_get(
4327 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4328 browse_id = browse_endpoint.get('browseId')
4329 params = browse_endpoint.get('params')
4330 break
4331
4332 headers = self.generate_api_headers(
4333 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4334 visitor_data=self._extract_visitor_data(data, ytcfg))
4335 query = {
4336 'params': params or 'wgYCCAA=',
4337 'browseId': browse_id or 'VL%s' % item_id
4338 }
4339 return self._extract_response(
4340 item_id=item_id, headers=headers, query=query,
4341 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4342 note='Downloading API JSON with unavailable videos')
4343
4344 @property
4345 def skip_webpage(self):
4346 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4347
4348 def _extract_webpage(self, url, item_id, fatal=True):
4349 retries = self.get_param('extractor_retries', 3)
4350 count = -1
4351 webpage = data = last_error = None
4352 while count < retries:
4353 count += 1
4354 # Sometimes youtube returns a webpage with incomplete ytInitialData
4355 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4356 if last_error:
4357 self.report_warning('%s. Retrying ...' % last_error)
4358 try:
4359 webpage = self._download_webpage(
4360 url, item_id,
4361 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4362 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4363 except ExtractorError as e:
4364 if isinstance(e.cause, network_exceptions):
4365 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4366 last_error = error_to_compat_str(e.cause or e.msg)
4367 if count < retries:
4368 continue
4369 if fatal:
4370 raise
4371 self.report_warning(error_to_compat_str(e))
4372 break
4373 else:
4374 try:
4375 self._extract_and_report_alerts(data)
4376 except ExtractorError as e:
4377 if fatal:
4378 raise
4379 self.report_warning(error_to_compat_str(e))
4380 break
4381
4382 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4383 break
4384
4385 last_error = 'Incomplete yt initial data received'
4386 if count >= retries:
4387 if fatal:
4388 raise ExtractorError(last_error)
4389 self.report_warning(last_error)
4390 break
4391
4392 return webpage, data
4393
4394 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4395 """Use if failed to extract ytcfg (and data) from initial webpage"""
4396 if not ytcfg and self.is_authenticated:
4397 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4398 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4399 raise ExtractorError(
4400 f'{msg}. If you are not downloading private content, or '
4401 'your cookies are only for the first account and channel,'
4402 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4403 expected=True)
4404 self.report_warning(msg, only_once=True)
4405
4406 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4407 data = None
4408 if not self.skip_webpage:
4409 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4410 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4411 # Reject webpage data if redirected to home page without explicitly requesting
4412 selected_tab = self._extract_selected_tab(traverse_obj(
4413 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4414 if (url != 'https://www.youtube.com/feed/recommended'
4415 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4416 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4417 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4418 if fatal:
4419 raise ExtractorError(msg, expected=True)
4420 self.report_warning(msg, only_once=True)
4421 if not data:
4422 self._report_playlist_authcheck(ytcfg, fatal=fatal)
4423 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4424 return data, ytcfg
4425
4426 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4427 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4428 resolve_response = self._extract_response(
4429 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4430 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4431 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4432 for ep_key, ep in endpoints.items():
4433 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4434 if params:
4435 return self._extract_response(
4436 item_id=item_id, query=params, ep=ep, headers=headers,
4437 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4438 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4439 err_note = 'Failed to resolve url (does the playlist exist?)'
4440 if fatal:
4441 raise ExtractorError(err_note, expected=True)
4442 self.report_warning(err_note, item_id)
4443
4444 _SEARCH_PARAMS = None
4445
4446 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4447 data = {'query': query}
4448 if params is NO_DEFAULT:
4449 params = self._SEARCH_PARAMS
4450 if params:
4451 data['params'] = params
4452
4453 content_keys = (
4454 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4455 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4456 # ytmusic search
4457 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4458 ('continuationContents', ),
4459 )
4460 display_id = f'query "{query}"'
4461 check_get_keys = tuple({keys[0] for keys in content_keys})
4462 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4463 self._report_playlist_authcheck(ytcfg, fatal=False)
4464
4465 continuation_list = [None]
4466 search = None
4467 for page_num in itertools.count(1):
4468 data.update(continuation_list[0] or {})
4469 headers = self.generate_api_headers(
4470 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
4471 search = self._extract_response(
4472 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4473 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
4474 slr_contents = traverse_obj(search, *content_keys)
4475 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4476 if not continuation_list[0]:
4477 break
4478
4479
4480 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4481 IE_DESC = 'YouTube Tabs'
4482 _VALID_URL = r'''(?x:
4483 https?://
4484 (?:\w+\.)?
4485 (?:
4486 youtube(?:kids)?\.com|
4487 %(invidious)s
4488 )/
4489 (?:
4490 (?P<channel_type>channel|c|user|browse)/|
4491 (?P<not_channel>
4492 feed/|hashtag/|
4493 (?:playlist|watch)\?.*?\blist=
4494 )|
4495 (?!(?:%(reserved_names)s)\b) # Direct URLs
4496 )
4497 (?P<id>[^/?\#&]+)
4498 )''' % {
4499 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4500 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4501 }
4502 IE_NAME = 'youtube:tab'
4503
4504 _TESTS = [{
4505 'note': 'playlists, multipage',
4506 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4507 'playlist_mincount': 94,
4508 'info_dict': {
4509 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4510 'title': 'Igor Kleiner - Playlists',
4511 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4512 'uploader': 'Igor Kleiner',
4513 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4514 'channel': 'Igor Kleiner',
4515 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4516 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4517 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4518 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4519 'channel_follower_count': int
4520 },
4521 }, {
4522 'note': 'playlists, multipage, different order',
4523 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4524 'playlist_mincount': 94,
4525 'info_dict': {
4526 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4527 'title': 'Igor Kleiner - Playlists',
4528 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4529 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4530 'uploader': 'Igor Kleiner',
4531 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4532 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4533 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4534 'channel': 'Igor Kleiner',
4535 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4536 'channel_follower_count': int
4537 },
4538 }, {
4539 'note': 'playlists, series',
4540 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4541 'playlist_mincount': 5,
4542 'info_dict': {
4543 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4544 'title': '3Blue1Brown - Playlists',
4545 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4546 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4547 'uploader': '3Blue1Brown',
4548 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4549 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4550 'channel': '3Blue1Brown',
4551 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4552 'tags': ['Mathematics'],
4553 'channel_follower_count': int
4554 },
4555 }, {
4556 'note': 'playlists, singlepage',
4557 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4558 'playlist_mincount': 4,
4559 'info_dict': {
4560 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4561 'title': 'ThirstForScience - Playlists',
4562 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4563 'uploader': 'ThirstForScience',
4564 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4565 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4566 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4567 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4568 'tags': 'count:13',
4569 'channel': 'ThirstForScience',
4570 'channel_follower_count': int
4571 }
4572 }, {
4573 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4574 'only_matching': True,
4575 }, {
4576 'note': 'basic, single video playlist',
4577 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4578 'info_dict': {
4579 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4580 'uploader': 'Sergey M.',
4581 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4582 'title': 'youtube-dl public playlist',
4583 'description': '',
4584 'tags': [],
4585 'view_count': int,
4586 'modified_date': '20201130',
4587 'channel': 'Sergey M.',
4588 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4589 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4590 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4591 },
4592 'playlist_count': 1,
4593 }, {
4594 'note': 'empty playlist',
4595 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4596 'info_dict': {
4597 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4598 'uploader': 'Sergey M.',
4599 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4600 'title': 'youtube-dl empty playlist',
4601 'tags': [],
4602 'channel': 'Sergey M.',
4603 'description': '',
4604 'modified_date': '20160902',
4605 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4606 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4607 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4608 },
4609 'playlist_count': 0,
4610 }, {
4611 'note': 'Home tab',
4612 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4613 'info_dict': {
4614 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4615 'title': 'lex will - Home',
4616 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4617 'uploader': 'lex will',
4618 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4619 'channel': 'lex will',
4620 'tags': ['bible', 'history', 'prophesy'],
4621 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4622 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4623 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4624 'channel_follower_count': int
4625 },
4626 'playlist_mincount': 2,
4627 }, {
4628 'note': 'Videos tab',
4629 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4630 'info_dict': {
4631 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4632 'title': 'lex will - Videos',
4633 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4634 'uploader': 'lex will',
4635 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4636 'tags': ['bible', 'history', 'prophesy'],
4637 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4638 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4639 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4640 'channel': 'lex will',
4641 'channel_follower_count': int
4642 },
4643 'playlist_mincount': 975,
4644 }, {
4645 'note': 'Videos tab, sorted by popular',
4646 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4647 'info_dict': {
4648 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4649 'title': 'lex will - Videos',
4650 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4651 'uploader': 'lex will',
4652 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4653 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4654 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4655 'channel': 'lex will',
4656 'tags': ['bible', 'history', 'prophesy'],
4657 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4658 'channel_follower_count': int
4659 },
4660 'playlist_mincount': 199,
4661 }, {
4662 'note': 'Playlists tab',
4663 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4664 'info_dict': {
4665 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4666 'title': 'lex will - Playlists',
4667 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4668 'uploader': 'lex will',
4669 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4670 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4671 'channel': 'lex will',
4672 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4673 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4674 'tags': ['bible', 'history', 'prophesy'],
4675 'channel_follower_count': int
4676 },
4677 'playlist_mincount': 17,
4678 }, {
4679 'note': 'Community tab',
4680 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4681 'info_dict': {
4682 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4683 'title': 'lex will - Community',
4684 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4685 'uploader': 'lex will',
4686 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4687 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4688 'channel': 'lex will',
4689 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4690 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4691 'tags': ['bible', 'history', 'prophesy'],
4692 'channel_follower_count': int
4693 },
4694 'playlist_mincount': 18,
4695 }, {
4696 'note': 'Channels tab',
4697 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4698 'info_dict': {
4699 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4700 'title': 'lex will - Channels',
4701 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4702 'uploader': 'lex will',
4703 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4704 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4705 'channel': 'lex will',
4706 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4707 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4708 'tags': ['bible', 'history', 'prophesy'],
4709 'channel_follower_count': int
4710 },
4711 'playlist_mincount': 12,
4712 }, {
4713 'note': 'Search tab',
4714 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4715 'playlist_mincount': 40,
4716 'info_dict': {
4717 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4718 'title': '3Blue1Brown - Search - linear algebra',
4719 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4720 'uploader': '3Blue1Brown',
4721 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4722 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4723 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4724 'tags': ['Mathematics'],
4725 'channel': '3Blue1Brown',
4726 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4727 'channel_follower_count': int
4728 },
4729 }, {
4730 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4731 'only_matching': True,
4732 }, {
4733 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4734 'only_matching': True,
4735 }, {
4736 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4737 'only_matching': True,
4738 }, {
4739 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4740 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4741 'info_dict': {
4742 'title': '29C3: Not my department',
4743 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4744 'uploader': 'Christiaan008',
4745 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4746 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4747 'tags': [],
4748 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4749 'view_count': int,
4750 'modified_date': '20150605',
4751 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4752 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4753 'channel': 'Christiaan008',
4754 },
4755 'playlist_count': 96,
4756 }, {
4757 'note': 'Large playlist',
4758 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4759 'info_dict': {
4760 'title': 'Uploads from Cauchemar',
4761 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4762 'uploader': 'Cauchemar',
4763 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4764 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4765 'tags': [],
4766 'modified_date': r're:\d{8}',
4767 'channel': 'Cauchemar',
4768 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4769 'view_count': int,
4770 'description': '',
4771 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4772 },
4773 'playlist_mincount': 1123,
4774 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4775 }, {
4776 'note': 'even larger playlist, 8832 videos',
4777 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4778 'only_matching': True,
4779 }, {
4780 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4781 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4782 'info_dict': {
4783 'title': 'Uploads from Interstellar Movie',
4784 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4785 'uploader': 'Interstellar Movie',
4786 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4787 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4788 'tags': [],
4789 'view_count': int,
4790 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4791 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4792 'channel': 'Interstellar Movie',
4793 'description': '',
4794 'modified_date': r're:\d{8}',
4795 },
4796 'playlist_mincount': 21,
4797 }, {
4798 'note': 'Playlist with "show unavailable videos" button',
4799 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4800 'info_dict': {
4801 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4802 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4803 'uploader': 'Phim Siêu Nhân Nhật Bản',
4804 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4805 'view_count': int,
4806 'channel': 'Phim Siêu Nhân Nhật Bản',
4807 'tags': [],
4808 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4809 'description': '',
4810 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4811 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4812 'modified_date': r're:\d{8}',
4813 },
4814 'playlist_mincount': 200,
4815 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4816 }, {
4817 'note': 'Playlist with unavailable videos in page 7',
4818 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4819 'info_dict': {
4820 'title': 'Uploads from BlankTV',
4821 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4822 'uploader': 'BlankTV',
4823 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4824 'channel': 'BlankTV',
4825 'channel_url': 'https://www.youtube.com/c/blanktv',
4826 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4827 'view_count': int,
4828 'tags': [],
4829 'uploader_url': 'https://www.youtube.com/c/blanktv',
4830 'modified_date': r're:\d{8}',
4831 'description': '',
4832 },
4833 'playlist_mincount': 1000,
4834 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4835 }, {
4836 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4837 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4838 'info_dict': {
4839 'title': 'Data Analysis with Dr Mike Pound',
4840 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4841 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4842 'uploader': 'Computerphile',
4843 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4844 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4845 'tags': [],
4846 'view_count': int,
4847 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4848 'channel_url': 'https://www.youtube.com/user/Computerphile',
4849 'channel': 'Computerphile',
4850 },
4851 'playlist_mincount': 11,
4852 }, {
4853 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4854 'only_matching': True,
4855 }, {
4856 'note': 'Playlist URL that does not actually serve a playlist',
4857 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4858 'info_dict': {
4859 'id': 'FqZTN594JQw',
4860 'ext': 'webm',
4861 'title': "Smiley's People 01 detective, Adventure Series, Action",
4862 'uploader': 'STREEM',
4863 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4864 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4865 'upload_date': '20150526',
4866 'license': 'Standard YouTube License',
4867 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4868 'categories': ['People & Blogs'],
4869 'tags': list,
4870 'view_count': int,
4871 'like_count': int,
4872 },
4873 'params': {
4874 'skip_download': True,
4875 },
4876 'skip': 'This video is not available.',
4877 'add_ie': [YoutubeIE.ie_key()],
4878 }, {
4879 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4880 'only_matching': True,
4881 }, {
4882 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4883 'only_matching': True,
4884 }, {
4885 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4886 'info_dict': {
4887 'id': 'GgL890LIznQ', # This will keep changing
4888 'ext': 'mp4',
4889 'title': str,
4890 'uploader': 'Sky News',
4891 'uploader_id': 'skynews',
4892 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4893 'upload_date': r're:\d{8}',
4894 'description': str,
4895 'categories': ['News & Politics'],
4896 'tags': list,
4897 'like_count': int,
4898 'release_timestamp': 1642502819,
4899 'channel': 'Sky News',
4900 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4901 'age_limit': 0,
4902 'view_count': int,
4903 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4904 'playable_in_embed': True,
4905 'release_date': '20220118',
4906 'availability': 'public',
4907 'live_status': 'is_live',
4908 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4909 'channel_follower_count': int
4910 },
4911 'params': {
4912 'skip_download': True,
4913 },
4914 'expected_warnings': ['Ignoring subtitle tracks found in '],
4915 }, {
4916 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4917 'info_dict': {
4918 'id': 'a48o2S1cPoo',
4919 'ext': 'mp4',
4920 'title': 'The Young Turks - Live Main Show',
4921 'uploader': 'The Young Turks',
4922 'uploader_id': 'TheYoungTurks',
4923 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4924 'upload_date': '20150715',
4925 'license': 'Standard YouTube License',
4926 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4927 'categories': ['News & Politics'],
4928 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4929 'like_count': int,
4930 },
4931 'params': {
4932 'skip_download': True,
4933 },
4934 'only_matching': True,
4935 }, {
4936 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4937 'only_matching': True,
4938 }, {
4939 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4940 'only_matching': True,
4941 }, {
4942 'note': 'A channel that is not live. Should raise error',
4943 'url': 'https://www.youtube.com/user/numberphile/live',
4944 'only_matching': True,
4945 }, {
4946 'url': 'https://www.youtube.com/feed/trending',
4947 'only_matching': True,
4948 }, {
4949 'url': 'https://www.youtube.com/feed/library',
4950 'only_matching': True,
4951 }, {
4952 'url': 'https://www.youtube.com/feed/history',
4953 'only_matching': True,
4954 }, {
4955 'url': 'https://www.youtube.com/feed/subscriptions',
4956 'only_matching': True,
4957 }, {
4958 'url': 'https://www.youtube.com/feed/watch_later',
4959 'only_matching': True,
4960 }, {
4961 'note': 'Recommended - redirects to home page.',
4962 'url': 'https://www.youtube.com/feed/recommended',
4963 'only_matching': True,
4964 }, {
4965 'note': 'inline playlist with not always working continuations',
4966 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4967 'only_matching': True,
4968 }, {
4969 'url': 'https://www.youtube.com/course',
4970 'only_matching': True,
4971 }, {
4972 'url': 'https://www.youtube.com/zsecurity',
4973 'only_matching': True,
4974 }, {
4975 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4976 'only_matching': True,
4977 }, {
4978 'url': 'https://www.youtube.com/TheYoungTurks/live',
4979 'only_matching': True,
4980 }, {
4981 'url': 'https://www.youtube.com/hashtag/cctv9',
4982 'info_dict': {
4983 'id': 'cctv9',
4984 'title': '#cctv9',
4985 'tags': [],
4986 },
4987 'playlist_mincount': 350,
4988 }, {
4989 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4990 'only_matching': True,
4991 }, {
4992 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4993 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4994 'only_matching': True
4995 }, {
4996 'note': '/browse/ should redirect to /channel/',
4997 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4998 'only_matching': True
4999 }, {
5000 'note': 'VLPL, should redirect to playlist?list=PL...',
5001 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5002 'info_dict': {
5003 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5004 'uploader': 'NoCopyrightSounds',
5005 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5006 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5007 'title': 'NCS Releases',
5008 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5009 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5010 'modified_date': r're:\d{8}',
5011 'view_count': int,
5012 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5013 'tags': [],
5014 'channel': 'NoCopyrightSounds',
5015 },
5016 'playlist_mincount': 166,
5017 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5018 }, {
5019 'note': 'Topic, should redirect to playlist?list=UU...',
5020 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5021 'info_dict': {
5022 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5023 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5024 'title': 'Uploads from Royalty Free Music - Topic',
5025 'uploader': 'Royalty Free Music - Topic',
5026 'tags': [],
5027 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5028 'channel': 'Royalty Free Music - Topic',
5029 'view_count': int,
5030 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5031 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5032 'modified_date': r're:\d{8}',
5033 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5034 'description': '',
5035 },
5036 'expected_warnings': [
5037 'The URL does not have a videos tab',
5038 r'[Uu]navailable videos (are|will be) hidden',
5039 ],
5040 'playlist_mincount': 101,
5041 }, {
5042 'note': 'Topic without a UU playlist',
5043 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5044 'info_dict': {
5045 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5046 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5047 'tags': [],
5048 },
5049 'expected_warnings': [
5050 'the playlist redirect gave error',
5051 ],
5052 'playlist_mincount': 9,
5053 }, {
5054 'note': 'Youtube music Album',
5055 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5056 'info_dict': {
5057 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5058 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5059 'tags': [],
5060 'view_count': int,
5061 'description': '',
5062 'availability': 'unlisted',
5063 'modified_date': r're:\d{8}',
5064 },
5065 'playlist_count': 50,
5066 }, {
5067 'note': 'unlisted single video playlist',
5068 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5069 'info_dict': {
5070 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5071 'uploader': 'colethedj',
5072 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5073 'title': 'yt-dlp unlisted playlist test',
5074 'availability': 'unlisted',
5075 'tags': [],
5076 'modified_date': '20211208',
5077 'channel': 'colethedj',
5078 'view_count': int,
5079 'description': '',
5080 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5081 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5082 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5083 },
5084 'playlist_count': 1,
5085 }, {
5086 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5087 'url': 'https://www.youtube.com/feed/recommended',
5088 'info_dict': {
5089 'id': 'recommended',
5090 'title': 'recommended',
5091 'tags': [],
5092 },
5093 'playlist_mincount': 50,
5094 'params': {
5095 'skip_download': True,
5096 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5097 },
5098 }, {
5099 'note': 'API Fallback: /videos tab, sorted by oldest first',
5100 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5101 'info_dict': {
5102 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5103 'title': 'Cody\'sLab - Videos',
5104 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5105 'uploader': 'Cody\'sLab',
5106 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5107 'channel': 'Cody\'sLab',
5108 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5109 'tags': [],
5110 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5111 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5112 'channel_follower_count': int
5113 },
5114 'playlist_mincount': 650,
5115 'params': {
5116 'skip_download': True,
5117 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5118 },
5119 }, {
5120 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5121 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5122 'info_dict': {
5123 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5124 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5125 'title': 'Uploads from Royalty Free Music - Topic',
5126 'uploader': 'Royalty Free Music - Topic',
5127 'modified_date': r're:\d{8}',
5128 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5129 'description': '',
5130 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5131 'tags': [],
5132 'channel': 'Royalty Free Music - Topic',
5133 'view_count': int,
5134 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5135 },
5136 'expected_warnings': [
5137 'does not have a videos tab',
5138 r'[Uu]navailable videos (are|will be) hidden',
5139 ],
5140 'playlist_mincount': 101,
5141 'params': {
5142 'skip_download': True,
5143 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5144 },
5145 }, {
5146 'note': 'non-standard redirect to regional channel',
5147 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5148 'only_matching': True
5149 }, {
5150 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5151 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5152 'info_dict': {
5153 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5154 'modified_date': '20220407',
5155 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5156 'tags': [],
5157 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5158 'uploader': 'pukkandan',
5159 'availability': 'unlisted',
5160 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5161 'channel': 'pukkandan',
5162 'description': 'Test for collaborative playlist',
5163 'title': 'yt-dlp test - collaborative playlist',
5164 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5165 },
5166 'playlist_mincount': 2
5167 }]
5168
5169 @classmethod
5170 def suitable(cls, url):
5171 return False if YoutubeIE.suitable(url) else super().suitable(url)
5172
5173 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5174
5175 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5176 def _real_extract(self, url, smuggled_data):
5177 item_id = self._match_id(url)
5178 url = compat_urlparse.urlunparse(
5179 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
5180 compat_opts = self.get_param('compat_opts', [])
5181
5182 def get_mobj(url):
5183 mobj = self._URL_RE.match(url).groupdict()
5184 mobj.update((k, '') for k, v in mobj.items() if v is None)
5185 return mobj
5186
5187 mobj, redirect_warning = get_mobj(url), None
5188 # Youtube returns incomplete data if tabname is not lower case
5189 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5190 if is_channel:
5191 if smuggled_data.get('is_music_url'):
5192 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5193 item_id = item_id[2:]
5194 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5195 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5196 mdata = self._extract_tab_endpoint(
5197 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5198 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5199 get_all=False, expected_type=compat_str)
5200 if not murl:
5201 raise ExtractorError('Failed to resolve album to playlist')
5202 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5203 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5204 pre = f'https://www.youtube.com/channel/{item_id}'
5205
5206 original_tab_name = tab
5207 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5208 # Home URLs should redirect to /videos/
5209 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5210 'To download only the videos in the home page, add a "/featured" to the URL')
5211 tab = '/videos'
5212
5213 url = ''.join((pre, tab, post))
5214 mobj = get_mobj(url)
5215
5216 # Handle both video/playlist URLs
5217 qs = parse_qs(url)
5218 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
5219
5220 if not video_id and mobj['not_channel'].startswith('watch'):
5221 if not playlist_id:
5222 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5223 raise ExtractorError('Unable to recognize tab page')
5224 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5225 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5226 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5227 mobj = get_mobj(url)
5228
5229 if video_id and playlist_id:
5230 if self.get_param('noplaylist'):
5231 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5232 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5233 ie=YoutubeIE.ie_key(), video_id=video_id)
5234 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5235
5236 data, ytcfg = self._extract_data(url, item_id)
5237
5238 # YouTube may provide a non-standard redirect to the regional channel
5239 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5240 redirect_url = traverse_obj(
5241 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5242 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5243 redirect_url = ''.join((
5244 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5245 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5246 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5247
5248 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5249 if tabs:
5250 selected_tab = self._extract_selected_tab(tabs)
5251 selected_tab_name = selected_tab.get('title', '').lower()
5252 if selected_tab_name == 'home':
5253 selected_tab_name = 'featured'
5254 requested_tab_name = mobj['tab'][1:]
5255 if 'no-youtube-channel-redirect' not in compat_opts:
5256 if requested_tab_name == 'live':
5257 # Live tab should have redirected to the video
5258 raise ExtractorError('The channel is not currently live', expected=True)
5259 if requested_tab_name not in ('', selected_tab_name):
5260 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5261 if not original_tab_name:
5262 if item_id[:2] == 'UC':
5263 # Topic channels don't have /videos. Use the equivalent playlist instead
5264 pl_id = f'UU{item_id[2:]}'
5265 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5266 try:
5267 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5268 except ExtractorError:
5269 redirect_warning += ' and the playlist redirect gave error'
5270 else:
5271 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5272 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5273 if selected_tab_name and selected_tab_name != requested_tab_name:
5274 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5275 else:
5276 raise ExtractorError(redirect_warning, expected=True)
5277
5278 if redirect_warning:
5279 self.to_screen(redirect_warning)
5280 self.write_debug(f'Final URL: {url}')
5281
5282 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5283 if 'no-youtube-unavailable-videos' not in compat_opts:
5284 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5285 self._extract_and_report_alerts(data, only_once=True)
5286 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5287 if tabs:
5288 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5289
5290 playlist = traverse_obj(
5291 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5292 if playlist:
5293 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5294
5295 video_id = traverse_obj(
5296 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5297 if video_id:
5298 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5299 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5300 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5301 ie=YoutubeIE.ie_key(), video_id=video_id)
5302
5303 raise ExtractorError('Unable to recognize tab page')
5304
5305
5306 class YoutubePlaylistIE(InfoExtractor):
5307 IE_DESC = 'YouTube playlists'
5308 _VALID_URL = r'''(?x)(?:
5309 (?:https?://)?
5310 (?:\w+\.)?
5311 (?:
5312 (?:
5313 youtube(?:kids)?\.com|
5314 %(invidious)s
5315 )
5316 /.*?\?.*?\blist=
5317 )?
5318 (?P<id>%(playlist_id)s)
5319 )''' % {
5320 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5321 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5322 }
5323 IE_NAME = 'youtube:playlist'
5324 _TESTS = [{
5325 'note': 'issue #673',
5326 'url': 'PLBB231211A4F62143',
5327 'info_dict': {
5328 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5329 'id': 'PLBB231211A4F62143',
5330 'uploader': 'Wickman',
5331 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5332 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5333 'view_count': int,
5334 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5335 'modified_date': r're:\d{8}',
5336 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5337 'channel': 'Wickman',
5338 'tags': [],
5339 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5340 },
5341 'playlist_mincount': 29,
5342 }, {
5343 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5344 'info_dict': {
5345 'title': 'YDL_safe_search',
5346 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5347 },
5348 'playlist_count': 2,
5349 'skip': 'This playlist is private',
5350 }, {
5351 'note': 'embedded',
5352 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5353 'playlist_count': 4,
5354 'info_dict': {
5355 'title': 'JODA15',
5356 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5357 'uploader': 'milan',
5358 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5359 'description': '',
5360 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5361 'tags': [],
5362 'modified_date': '20140919',
5363 'view_count': int,
5364 'channel': 'milan',
5365 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5366 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5367 },
5368 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5369 }, {
5370 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5371 'playlist_mincount': 654,
5372 'info_dict': {
5373 'title': '2018 Chinese New Singles (11/6 updated)',
5374 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5375 'uploader': 'LBK',
5376 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5377 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5378 'channel': 'LBK',
5379 'view_count': int,
5380 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5381 'tags': [],
5382 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5383 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5384 'modified_date': r're:\d{8}',
5385 },
5386 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5387 }, {
5388 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5389 'only_matching': True,
5390 }, {
5391 # music album playlist
5392 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5393 'only_matching': True,
5394 }]
5395
5396 @classmethod
5397 def suitable(cls, url):
5398 if YoutubeTabIE.suitable(url):
5399 return False
5400 from ..utils import parse_qs
5401 qs = parse_qs(url)
5402 if qs.get('v', [None])[0]:
5403 return False
5404 return super().suitable(url)
5405
5406 def _real_extract(self, url):
5407 playlist_id = self._match_id(url)
5408 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5409 url = update_url_query(
5410 'https://www.youtube.com/playlist',
5411 parse_qs(url) or {'list': playlist_id})
5412 if is_music_url:
5413 url = smuggle_url(url, {'is_music_url': True})
5414 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5415
5416
5417 class YoutubeYtBeIE(InfoExtractor):
5418 IE_DESC = 'youtu.be'
5419 _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}
5420 _TESTS = [{
5421 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5422 'info_dict': {
5423 'id': 'yeWKywCrFtk',
5424 'ext': 'mp4',
5425 'title': 'Small Scale Baler and Braiding Rugs',
5426 'uploader': 'Backus-Page House Museum',
5427 'uploader_id': 'backuspagemuseum',
5428 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5429 'upload_date': '20161008',
5430 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5431 'categories': ['Nonprofits & Activism'],
5432 'tags': list,
5433 'like_count': int,
5434 'age_limit': 0,
5435 'playable_in_embed': True,
5436 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5437 'channel': 'Backus-Page House Museum',
5438 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5439 'live_status': 'not_live',
5440 'view_count': int,
5441 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5442 'availability': 'public',
5443 'duration': 59,
5444 },
5445 'params': {
5446 'noplaylist': True,
5447 'skip_download': True,
5448 },
5449 }, {
5450 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5451 'only_matching': True,
5452 }]
5453
5454 def _real_extract(self, url):
5455 mobj = self._match_valid_url(url)
5456 video_id = mobj.group('id')
5457 playlist_id = mobj.group('playlist_id')
5458 return self.url_result(
5459 update_url_query('https://www.youtube.com/watch', {
5460 'v': video_id,
5461 'list': playlist_id,
5462 'feature': 'youtu.be',
5463 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5464
5465
5466 class YoutubeLivestreamEmbedIE(InfoExtractor):
5467 IE_DESC = 'YouTube livestream embeds'
5468 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5469 _TESTS = [{
5470 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5471 'only_matching': True,
5472 }]
5473
5474 def _real_extract(self, url):
5475 channel_id = self._match_id(url)
5476 return self.url_result(
5477 f'https://www.youtube.com/channel/{channel_id}/live',
5478 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5479
5480
5481 class YoutubeYtUserIE(InfoExtractor):
5482 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5483 IE_NAME = 'youtube:user'
5484 _VALID_URL = r'ytuser:(?P<id>.+)'
5485 _TESTS = [{
5486 'url': 'ytuser:phihag',
5487 'only_matching': True,
5488 }]
5489
5490 def _real_extract(self, url):
5491 user_id = self._match_id(url)
5492 return self.url_result(
5493 'https://www.youtube.com/user/%s/videos' % user_id,
5494 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5495
5496
5497 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5498 IE_NAME = 'youtube:favorites'
5499 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5500 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5501 _LOGIN_REQUIRED = True
5502 _TESTS = [{
5503 'url': ':ytfav',
5504 'only_matching': True,
5505 }, {
5506 'url': ':ytfavorites',
5507 'only_matching': True,
5508 }]
5509
5510 def _real_extract(self, url):
5511 return self.url_result(
5512 'https://www.youtube.com/playlist?list=LL',
5513 ie=YoutubeTabIE.ie_key())
5514
5515
5516 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5517 IE_NAME = 'youtube:notif'
5518 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5519 _VALID_URL = r':ytnotif(?:ication)?s?'
5520 _LOGIN_REQUIRED = True
5521 _TESTS = [{
5522 'url': ':ytnotif',
5523 'only_matching': True,
5524 }, {
5525 'url': ':ytnotifications',
5526 'only_matching': True,
5527 }]
5528
5529 def _extract_notification_menu(self, response, continuation_list):
5530 notification_list = traverse_obj(
5531 response,
5532 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5533 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5534 expected_type=list) or []
5535 continuation_list[0] = None
5536 for item in notification_list:
5537 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5538 if entry:
5539 yield entry
5540 continuation = item.get('continuationItemRenderer')
5541 if continuation:
5542 continuation_list[0] = continuation
5543
5544 def _extract_notification_renderer(self, notification):
5545 video_id = traverse_obj(
5546 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5547 url = f'https://www.youtube.com/watch?v={video_id}'
5548 channel_id = None
5549 if not video_id:
5550 browse_ep = traverse_obj(
5551 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5552 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5553 post_id = self._search_regex(
5554 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5555 'post id', default=None)
5556 if not channel_id or not post_id:
5557 return
5558 # The direct /post url redirects to this in the browser
5559 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5560
5561 channel = traverse_obj(
5562 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5563 expected_type=str)
5564 title = self._search_regex(
5565 rf'{re.escape(channel)} [^:]+: (.+)', self._get_text(notification, 'shortMessage'),
5566 'video title', default=None)
5567 if title:
5568 title = title.replace('\xad', '') # remove soft hyphens
5569 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5570 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5571 else None)
5572 return {
5573 '_type': 'url',
5574 'url': url,
5575 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5576 'video_id': video_id,
5577 'title': title,
5578 'channel_id': channel_id,
5579 'channel': channel,
5580 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5581 'upload_date': upload_date,
5582 }
5583
5584 def _notification_menu_entries(self, ytcfg):
5585 continuation_list = [None]
5586 response = None
5587 for page in itertools.count(1):
5588 ctoken = traverse_obj(
5589 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5590 response = self._extract_response(
5591 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5592 ep='notification/get_notification_menu', check_get_keys='actions',
5593 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5594 yield from self._extract_notification_menu(response, continuation_list)
5595 if not continuation_list[0]:
5596 break
5597
5598 def _real_extract(self, url):
5599 display_id = 'notifications'
5600 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5601 self._report_playlist_authcheck(ytcfg)
5602 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5603
5604
5605 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5606 IE_DESC = 'YouTube search'
5607 IE_NAME = 'youtube:search'
5608 _SEARCH_KEY = 'ytsearch'
5609 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5610 _TESTS = [{
5611 'url': 'ytsearch5:youtube-dl test video',
5612 'playlist_count': 5,
5613 'info_dict': {
5614 'id': 'youtube-dl test video',
5615 'title': 'youtube-dl test video',
5616 }
5617 }]
5618
5619
5620 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5621 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5622 _SEARCH_KEY = 'ytsearchdate'
5623 IE_DESC = 'YouTube search, newest videos first'
5624 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5625 _TESTS = [{
5626 'url': 'ytsearchdate5:youtube-dl test video',
5627 'playlist_count': 5,
5628 'info_dict': {
5629 'id': 'youtube-dl test video',
5630 'title': 'youtube-dl test video',
5631 }
5632 }]
5633
5634
5635 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5636 IE_DESC = 'YouTube search URLs with sorting and filter support'
5637 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5638 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5639 _TESTS = [{
5640 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5641 'playlist_mincount': 5,
5642 'info_dict': {
5643 'id': 'youtube-dl test video',
5644 'title': 'youtube-dl test video',
5645 }
5646 }, {
5647 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5648 'playlist_mincount': 5,
5649 'info_dict': {
5650 'id': 'python',
5651 'title': 'python',
5652 }
5653 }, {
5654 'url': 'https://www.youtube.com/results?search_query=%23cats',
5655 'playlist_mincount': 1,
5656 'info_dict': {
5657 'id': '#cats',
5658 'title': '#cats',
5659 'entries': [{
5660 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5661 'title': '#cats',
5662 }],
5663 },
5664 }, {
5665 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5666 'only_matching': True,
5667 }]
5668
5669 def _real_extract(self, url):
5670 qs = parse_qs(url)
5671 query = (qs.get('search_query') or qs.get('q'))[0]
5672 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5673
5674
5675 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5676 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
5677 IE_NAME = 'youtube:music:search_url'
5678 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5679 _TESTS = [{
5680 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5681 'playlist_count': 16,
5682 'info_dict': {
5683 'id': 'royalty free music',
5684 'title': 'royalty free music',
5685 }
5686 }, {
5687 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5688 'playlist_mincount': 30,
5689 'info_dict': {
5690 'id': 'royalty free music - songs',
5691 'title': 'royalty free music - songs',
5692 },
5693 'params': {'extract_flat': 'in_playlist'}
5694 }, {
5695 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5696 'playlist_mincount': 30,
5697 'info_dict': {
5698 'id': 'royalty free music - community playlists',
5699 'title': 'royalty free music - community playlists',
5700 },
5701 'params': {'extract_flat': 'in_playlist'}
5702 }]
5703
5704 _SECTIONS = {
5705 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5706 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5707 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5708 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5709 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5710 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5711 }
5712
5713 def _real_extract(self, url):
5714 qs = parse_qs(url)
5715 query = (qs.get('search_query') or qs.get('q'))[0]
5716 params = qs.get('sp', (None,))[0]
5717 if params:
5718 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5719 else:
5720 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5721 params = self._SECTIONS.get(section)
5722 if not params:
5723 section = None
5724 title = join_nonempty(query, section, delim=' - ')
5725 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
5726
5727
5728 class YoutubeFeedsInfoExtractor(InfoExtractor):
5729 """
5730 Base class for feed extractors
5731 Subclasses must define the _FEED_NAME property.
5732 """
5733 _LOGIN_REQUIRED = True
5734
5735 def _real_initialize(self):
5736 YoutubeBaseInfoExtractor._check_login_required(self)
5737
5738 @property
5739 def IE_NAME(self):
5740 return 'youtube:%s' % self._FEED_NAME
5741
5742 def _real_extract(self, url):
5743 return self.url_result(
5744 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
5745
5746
5747 class YoutubeWatchLaterIE(InfoExtractor):
5748 IE_NAME = 'youtube:watchlater'
5749 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5750 _VALID_URL = r':ytwatchlater'
5751 _TESTS = [{
5752 'url': ':ytwatchlater',
5753 'only_matching': True,
5754 }]
5755
5756 def _real_extract(self, url):
5757 return self.url_result(
5758 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5759
5760
5761 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5762 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5763 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5764 _FEED_NAME = 'recommended'
5765 _LOGIN_REQUIRED = False
5766 _TESTS = [{
5767 'url': ':ytrec',
5768 'only_matching': True,
5769 }, {
5770 'url': ':ytrecommended',
5771 'only_matching': True,
5772 }, {
5773 'url': 'https://youtube.com',
5774 'only_matching': True,
5775 }]
5776
5777
5778 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5779 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5780 _VALID_URL = r':ytsub(?:scription)?s?'
5781 _FEED_NAME = 'subscriptions'
5782 _TESTS = [{
5783 'url': ':ytsubs',
5784 'only_matching': True,
5785 }, {
5786 'url': ':ytsubscriptions',
5787 'only_matching': True,
5788 }]
5789
5790
5791 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5792 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5793 _VALID_URL = r':ythis(?:tory)?'
5794 _FEED_NAME = 'history'
5795 _TESTS = [{
5796 'url': ':ythistory',
5797 'only_matching': True,
5798 }]
5799
5800
5801 class YoutubeTruncatedURLIE(InfoExtractor):
5802 IE_NAME = 'youtube:truncated_url'
5803 IE_DESC = False # Do not list
5804 _VALID_URL = r'''(?x)
5805 (?:https?://)?
5806 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5807 (?:watch\?(?:
5808 feature=[a-z_]+|
5809 annotation_id=annotation_[^&]+|
5810 x-yt-cl=[0-9]+|
5811 hl=[^&]*|
5812 t=[0-9]+
5813 )?
5814 |
5815 attribution_link\?a=[^&]+
5816 )
5817 $
5818 '''
5819
5820 _TESTS = [{
5821 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5822 'only_matching': True,
5823 }, {
5824 'url': 'https://www.youtube.com/watch?',
5825 'only_matching': True,
5826 }, {
5827 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5828 'only_matching': True,
5829 }, {
5830 'url': 'https://www.youtube.com/watch?feature=foo',
5831 'only_matching': True,
5832 }, {
5833 'url': 'https://www.youtube.com/watch?hl=en-GB',
5834 'only_matching': True,
5835 }, {
5836 'url': 'https://www.youtube.com/watch?t=2372',
5837 'only_matching': True,
5838 }]
5839
5840 def _real_extract(self, url):
5841 raise ExtractorError(
5842 'Did you forget to quote the URL? Remember that & is a meta '
5843 'character in most shells, so you want to put the URL in quotes, '
5844 'like youtube-dl '
5845 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5846 ' or simply youtube-dl BaW_jenozKc .',
5847 expected=True)
5848
5849
5850 class YoutubeClipIE(InfoExtractor):
5851 IE_NAME = 'youtube:clip'
5852 IE_DESC = False # Do not list
5853 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5854
5855 def _real_extract(self, url):
5856 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5857 return self.url_result(url, 'Generic')
5858
5859
5860 class YoutubeTruncatedIDIE(InfoExtractor):
5861 IE_NAME = 'youtube:truncated_id'
5862 IE_DESC = False # Do not list
5863 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5864
5865 _TESTS = [{
5866 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5867 'only_matching': True,
5868 }]
5869
5870 def _real_extract(self, url):
5871 video_id = self._match_id(url)
5872 raise ExtractorError(
5873 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
5874 expected=True)