]> jfr.im git - yt-dlp.git/blame_incremental - yt_dlp/extractor/youtube.py
[LnkIE] Add extractor (#2408)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
... / ...
CommitLineData
1# coding: utf-8
2
3from __future__ import unicode_literals
4
5import calendar
6import copy
7import datetime
8import functools
9import hashlib
10import itertools
11import json
12import math
13import os.path
14import random
15import re
16import sys
17import time
18import traceback
19import threading
20
21from .common import InfoExtractor, SearchInfoExtractor
22from ..compat import (
23 compat_chr,
24 compat_HTTPError,
25 compat_parse_qs,
26 compat_str,
27 compat_urllib_parse_unquote_plus,
28 compat_urllib_parse_urlencode,
29 compat_urllib_parse_urlparse,
30 compat_urlparse,
31)
32from ..jsinterp import JSInterpreter
33from ..utils import (
34 bug_reports_message,
35 clean_html,
36 datetime_from_str,
37 dict_get,
38 error_to_compat_str,
39 ExtractorError,
40 float_or_none,
41 format_field,
42 int_or_none,
43 is_html,
44 join_nonempty,
45 mimetype2ext,
46 network_exceptions,
47 NO_DEFAULT,
48 orderedSet,
49 parse_codecs,
50 parse_count,
51 parse_duration,
52 parse_iso8601,
53 parse_qs,
54 qualities,
55 remove_end,
56 remove_start,
57 smuggle_url,
58 str_or_none,
59 str_to_int,
60 strftime_or_none,
61 traverse_obj,
62 try_get,
63 unescapeHTML,
64 unified_strdate,
65 unified_timestamp,
66 unsmuggle_url,
67 update_url_query,
68 url_or_none,
69 urljoin,
70 variadic,
71)
72
73
74def get_first(obj, keys, **kwargs):
75 return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
76
77
78# any clients starting with _ cannot be explicity requested by the user
79INNERTUBE_CLIENTS = {
80 'web': {
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
83 'client': {
84 'clientName': 'WEB',
85 'clientVersion': '2.20211221.00.00',
86 }
87 },
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
89 },
90 'web_embedded': {
91 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
92 'INNERTUBE_CONTEXT': {
93 'client': {
94 'clientName': 'WEB_EMBEDDED_PLAYER',
95 'clientVersion': '1.20211215.00.01',
96 },
97 },
98 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
99 },
100 'web_music': {
101 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
102 'INNERTUBE_HOST': 'music.youtube.com',
103 'INNERTUBE_CONTEXT': {
104 'client': {
105 'clientName': 'WEB_REMIX',
106 'clientVersion': '1.20211213.00.00',
107 }
108 },
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
110 },
111 'web_creator': {
112 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
113 'INNERTUBE_CONTEXT': {
114 'client': {
115 'clientName': 'WEB_CREATOR',
116 'clientVersion': '1.20211220.02.00',
117 }
118 },
119 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
120 },
121 'android': {
122 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
123 'INNERTUBE_CONTEXT': {
124 'client': {
125 'clientName': 'ANDROID',
126 'clientVersion': '16.49',
127 }
128 },
129 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
130 'REQUIRE_JS_PLAYER': False
131 },
132 'android_embedded': {
133 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
134 'INNERTUBE_CONTEXT': {
135 'client': {
136 'clientName': 'ANDROID_EMBEDDED_PLAYER',
137 'clientVersion': '16.49',
138 },
139 },
140 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
141 'REQUIRE_JS_PLAYER': False
142 },
143 'android_music': {
144 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
145 'INNERTUBE_CONTEXT': {
146 'client': {
147 'clientName': 'ANDROID_MUSIC',
148 'clientVersion': '4.57',
149 }
150 },
151 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
152 'REQUIRE_JS_PLAYER': False
153 },
154 'android_creator': {
155 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
156 'INNERTUBE_CONTEXT': {
157 'client': {
158 'clientName': 'ANDROID_CREATOR',
159 'clientVersion': '21.47',
160 },
161 },
162 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
163 'REQUIRE_JS_PLAYER': False
164 },
165 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
166 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
167 'ios': {
168 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
169 'INNERTUBE_CONTEXT': {
170 'client': {
171 'clientName': 'IOS',
172 'clientVersion': '16.46',
173 'deviceModel': 'iPhone14,3',
174 }
175 },
176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
178 },
179 'ios_embedded': {
180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
183 'clientVersion': '16.46',
184 'deviceModel': 'iPhone14,3',
185 },
186 },
187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
189 },
190 'ios_music': {
191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_MUSIC',
195 'clientVersion': '4.57',
196 },
197 },
198 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
199 'REQUIRE_JS_PLAYER': False
200 },
201 'ios_creator': {
202 'INNERTUBE_CONTEXT': {
203 'client': {
204 'clientName': 'IOS_CREATOR',
205 'clientVersion': '21.47',
206 },
207 },
208 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
209 'REQUIRE_JS_PLAYER': False
210 },
211 # mweb has 'ultralow' formats
212 # See: https://github.com/yt-dlp/yt-dlp/pull/557
213 'mweb': {
214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
215 'INNERTUBE_CONTEXT': {
216 'client': {
217 'clientName': 'MWEB',
218 'clientVersion': '2.20211221.01.00',
219 }
220 },
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
222 }
223}
224
225
226def build_innertube_clients():
227 third_party = {
228 'embedUrl': 'https://google.com', # Can be any valid URL
229 }
230 base_clients = ('android', 'web', 'ios', 'mweb')
231 priority = qualities(base_clients[::-1])
232
233 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
234 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
235 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
236 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
237 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
238 ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
239
240 if client in base_clients:
241 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
242 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
243 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
244 agegate_ytcfg['priority'] -= 1
245 elif client.endswith('_embedded'):
246 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
247 ytcfg['priority'] -= 2
248 else:
249 ytcfg['priority'] -= 3
250
251
252build_innertube_clients()
253
254
255class YoutubeBaseInfoExtractor(InfoExtractor):
256 """Provide base functions for Youtube extractors"""
257
258 _RESERVED_NAMES = (
259 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
260 r'shorts|movies|results|shared|hashtag|trending|feed|feeds|'
261 r'browse|oembed|get_video_info|iframe_api|s/player|'
262 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
263
264 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
265
266 _NETRC_MACHINE = 'youtube'
267
268 # If True it will raise an error if no login info is provided
269 _LOGIN_REQUIRED = False
270
271 _INVIDIOUS_SITES = (
272 # invidious-redirect websites
273 r'(?:www\.)?redirect\.invidious\.io',
274 r'(?:(?:www|dev)\.)?invidio\.us',
275 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
276 r'(?:www\.)?invidious\.pussthecat\.org',
277 r'(?:www\.)?invidious\.zee\.li',
278 r'(?:www\.)?invidious\.ethibox\.fr',
279 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
280 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
281 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
282 # youtube-dl invidious instances list
283 r'(?:(?:www|no)\.)?invidiou\.sh',
284 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
285 r'(?:www\.)?invidious\.kabi\.tk',
286 r'(?:www\.)?invidious\.mastodon\.host',
287 r'(?:www\.)?invidious\.zapashcanon\.fr',
288 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
289 r'(?:www\.)?invidious\.tinfoil-hat\.net',
290 r'(?:www\.)?invidious\.himiko\.cloud',
291 r'(?:www\.)?invidious\.reallyancient\.tech',
292 r'(?:www\.)?invidious\.tube',
293 r'(?:www\.)?invidiou\.site',
294 r'(?:www\.)?invidious\.site',
295 r'(?:www\.)?invidious\.xyz',
296 r'(?:www\.)?invidious\.nixnet\.xyz',
297 r'(?:www\.)?invidious\.048596\.xyz',
298 r'(?:www\.)?invidious\.drycat\.fr',
299 r'(?:www\.)?inv\.skyn3t\.in',
300 r'(?:www\.)?tube\.poal\.co',
301 r'(?:www\.)?tube\.connect\.cafe',
302 r'(?:www\.)?vid\.wxzm\.sx',
303 r'(?:www\.)?vid\.mint\.lgbt',
304 r'(?:www\.)?vid\.puffyan\.us',
305 r'(?:www\.)?yewtu\.be',
306 r'(?:www\.)?yt\.elukerio\.org',
307 r'(?:www\.)?yt\.lelux\.fi',
308 r'(?:www\.)?invidious\.ggc-project\.de',
309 r'(?:www\.)?yt\.maisputain\.ovh',
310 r'(?:www\.)?ytprivate\.com',
311 r'(?:www\.)?invidious\.13ad\.de',
312 r'(?:www\.)?invidious\.toot\.koeln',
313 r'(?:www\.)?invidious\.fdn\.fr',
314 r'(?:www\.)?watch\.nettohikari\.com',
315 r'(?:www\.)?invidious\.namazso\.eu',
316 r'(?:www\.)?invidious\.silkky\.cloud',
317 r'(?:www\.)?invidious\.exonip\.de',
318 r'(?:www\.)?invidious\.riverside\.rocks',
319 r'(?:www\.)?invidious\.blamefran\.net',
320 r'(?:www\.)?invidious\.moomoo\.de',
321 r'(?:www\.)?ytb\.trom\.tf',
322 r'(?:www\.)?yt\.cyberhost\.uk',
323 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
324 r'(?:www\.)?qklhadlycap4cnod\.onion',
325 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
326 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
327 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
328 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
329 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
330 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
331 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
332 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
333 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
334 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
335 )
336
337 def _login(self):
338 """
339 Attempt to log in to YouTube.
340 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
341 """
342
343 if (self._LOGIN_REQUIRED
344 and self.get_param('cookiefile') is None
345 and self.get_param('cookiesfrombrowser') is None):
346 self.raise_login_required(
347 'Login details are needed to download this content', method='cookies')
348 username, password = self._get_login_info()
349 if username:
350 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
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._login()
383
384 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
385 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
387
388 def _get_default_ytcfg(self, client='web'):
389 return copy.deepcopy(INNERTUBE_CLIENTS[client])
390
391 def _get_innertube_host(self, client='web'):
392 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
393
394 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
395 # try_get but with fallback to default ytcfg client values when present
396 _func = lambda y: try_get(y, getter, expected_type)
397 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
398
399 def _extract_client_name(self, ytcfg, default_client='web'):
400 return self._ytcfg_get_safe(
401 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
402 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
403
404 def _extract_client_version(self, ytcfg, default_client='web'):
405 return self._ytcfg_get_safe(
406 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
407 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
408
409 def _extract_api_key(self, ytcfg=None, default_client='web'):
410 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
411
412 def _extract_context(self, ytcfg=None, default_client='web'):
413 context = get_first(
414 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
415 # Enforce language and tz for extraction
416 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
417 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
418 return context
419
420 _SAPISID = None
421
422 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
423 time_now = round(time.time())
424 if self._SAPISID is None:
425 yt_cookies = self._get_cookies('https://www.youtube.com')
426 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
427 # See: https://github.com/yt-dlp/yt-dlp/issues/393
428 sapisid_cookie = dict_get(
429 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
430 if sapisid_cookie and sapisid_cookie.value:
431 self._SAPISID = sapisid_cookie.value
432 self.write_debug('Extracted SAPISID cookie')
433 # SAPISID cookie is required if not already present
434 if not yt_cookies.get('SAPISID'):
435 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
436 self._set_cookie(
437 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
438 else:
439 self._SAPISID = False
440 if not self._SAPISID:
441 return None
442 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
443 sapisidhash = hashlib.sha1(
444 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
445 return f'SAPISIDHASH {time_now}_{sapisidhash}'
446
447 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
448 note='Downloading API JSON', errnote='Unable to download API page',
449 context=None, api_key=None, api_hostname=None, default_client='web'):
450
451 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
452 data.update(query)
453 real_headers = self.generate_api_headers(default_client=default_client)
454 real_headers.update({'content-type': 'application/json'})
455 if headers:
456 real_headers.update(headers)
457 return self._download_json(
458 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
459 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
460 data=json.dumps(data).encode('utf8'), headers=real_headers,
461 query={'key': api_key or self._extract_api_key()})
462
463 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
464 data = self._search_regex(
465 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
466 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
467 if data:
468 return self._parse_json(data, item_id, fatal=fatal)
469
470 @staticmethod
471 def _extract_session_index(*data):
472 """
473 Index of current account in account list.
474 See: https://github.com/yt-dlp/yt-dlp/pull/519
475 """
476 for ytcfg in data:
477 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
478 if session_index is not None:
479 return session_index
480
481 # Deprecated?
482 def _extract_identity_token(self, ytcfg=None, webpage=None):
483 if ytcfg:
484 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
485 if token:
486 return token
487 if webpage:
488 return self._search_regex(
489 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
490 'identity token', default=None, fatal=False)
491
492 @staticmethod
493 def _extract_account_syncid(*args):
494 """
495 Extract syncId required to download private playlists of secondary channels
496 @params response and/or ytcfg
497 """
498 for data in args:
499 # ytcfg includes channel_syncid if on secondary channel
500 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
501 if delegated_sid:
502 return delegated_sid
503 sync_ids = (try_get(
504 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
505 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
506 if len(sync_ids) >= 2 and sync_ids[1]:
507 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
508 # and just "user_syncid||" for primary channel. We only want the channel_syncid
509 return sync_ids[0]
510
511 @staticmethod
512 def _extract_visitor_data(*args):
513 """
514 Extracts visitorData from an API response or ytcfg
515 Appears to be used to track session state
516 """
517 return get_first(
518 args, (('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))),
519 expected_type=str)
520
521 @property
522 def is_authenticated(self):
523 return bool(self._generate_sapisidhash_header())
524
525 def extract_ytcfg(self, video_id, webpage):
526 if not webpage:
527 return {}
528 return self._parse_json(
529 self._search_regex(
530 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
531 default='{}'), video_id, fatal=False) or {}
532
533 def generate_api_headers(
534 self, *, ytcfg=None, account_syncid=None, session_index=None,
535 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
536
537 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
538 headers = {
539 'X-YouTube-Client-Name': compat_str(
540 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
541 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
542 'Origin': origin,
543 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
544 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
545 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
546 }
547 if session_index is None:
548 session_index = self._extract_session_index(ytcfg)
549 if account_syncid or session_index is not None:
550 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
551
552 auth = self._generate_sapisidhash_header(origin)
553 if auth is not None:
554 headers['Authorization'] = auth
555 headers['X-Origin'] = origin
556 return {h: v for h, v in headers.items() if v is not None}
557
558 @staticmethod
559 def _build_api_continuation_query(continuation, ctp=None):
560 query = {
561 'continuation': continuation
562 }
563 # TODO: Inconsistency with clickTrackingParams.
564 # Currently we have a fixed ctp contained within context (from ytcfg)
565 # and a ctp in root query for continuation.
566 if ctp:
567 query['clickTracking'] = {'clickTrackingParams': ctp}
568 return query
569
570 @classmethod
571 def _extract_next_continuation_data(cls, renderer):
572 next_continuation = try_get(
573 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
574 lambda x: x['continuation']['reloadContinuationData']), dict)
575 if not next_continuation:
576 return
577 continuation = next_continuation.get('continuation')
578 if not continuation:
579 return
580 ctp = next_continuation.get('clickTrackingParams')
581 return cls._build_api_continuation_query(continuation, ctp)
582
583 @classmethod
584 def _extract_continuation_ep_data(cls, continuation_ep: dict):
585 if isinstance(continuation_ep, dict):
586 continuation = try_get(
587 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
588 if not continuation:
589 return
590 ctp = continuation_ep.get('clickTrackingParams')
591 return cls._build_api_continuation_query(continuation, ctp)
592
593 @classmethod
594 def _extract_continuation(cls, renderer):
595 next_continuation = cls._extract_next_continuation_data(renderer)
596 if next_continuation:
597 return next_continuation
598
599 contents = []
600 for key in ('contents', 'items'):
601 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
602
603 for content in contents:
604 if not isinstance(content, dict):
605 continue
606 continuation_ep = try_get(
607 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
608 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
609 dict)
610 continuation = cls._extract_continuation_ep_data(continuation_ep)
611 if continuation:
612 return continuation
613
614 @classmethod
615 def _extract_alerts(cls, data):
616 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
617 if not isinstance(alert_dict, dict):
618 continue
619 for alert in alert_dict.values():
620 alert_type = alert.get('type')
621 if not alert_type:
622 continue
623 message = cls._get_text(alert, 'text')
624 if message:
625 yield alert_type, message
626
627 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
628 errors = []
629 warnings = []
630 for alert_type, alert_message in alerts:
631 if alert_type.lower() == 'error' and fatal:
632 errors.append([alert_type, alert_message])
633 else:
634 warnings.append([alert_type, alert_message])
635
636 for alert_type, alert_message in (warnings + errors[:-1]):
637 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
638 if errors:
639 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
640
641 def _extract_and_report_alerts(self, data, *args, **kwargs):
642 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
643
644 def _extract_badges(self, renderer: dict):
645 badges = set()
646 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
647 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
648 if label:
649 badges.add(label.lower())
650 return badges
651
652 @staticmethod
653 def _get_text(data, *path_list, max_runs=None):
654 for path in path_list or [None]:
655 if path is None:
656 obj = [data]
657 else:
658 obj = traverse_obj(data, path, default=[])
659 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
660 obj = [obj]
661 for item in obj:
662 text = try_get(item, lambda x: x['simpleText'], compat_str)
663 if text:
664 return text
665 runs = try_get(item, lambda x: x['runs'], list) or []
666 if not runs and isinstance(item, list):
667 runs = item
668
669 runs = runs[:min(len(runs), max_runs or len(runs))]
670 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
671 if text:
672 return text
673
674 def _get_count(self, data, *path_list):
675 count_text = self._get_text(data, *path_list) or ''
676 count = parse_count(count_text)
677 if count is None:
678 count = str_to_int(
679 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
680 return count
681
682 @staticmethod
683 def _extract_thumbnails(data, *path_list):
684 """
685 Extract thumbnails from thumbnails dict
686 @param path_list: path list to level that contains 'thumbnails' key
687 """
688 thumbnails = []
689 for path in path_list or [()]:
690 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
691 thumbnail_url = url_or_none(thumbnail.get('url'))
692 if not thumbnail_url:
693 continue
694 # Sometimes youtube gives a wrong thumbnail URL. See:
695 # https://github.com/yt-dlp/yt-dlp/issues/233
696 # https://github.com/ytdl-org/youtube-dl/issues/28023
697 if 'maxresdefault' in thumbnail_url:
698 thumbnail_url = thumbnail_url.split('?')[0]
699 thumbnails.append({
700 'url': thumbnail_url,
701 'height': int_or_none(thumbnail.get('height')),
702 'width': int_or_none(thumbnail.get('width')),
703 })
704 return thumbnails
705
706 @staticmethod
707 def extract_relative_time(relative_time_text):
708 """
709 Extracts a relative time from string and converts to dt object
710 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
711 """
712 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)
713 if mobj:
714 start = mobj.group('start')
715 if start:
716 return datetime_from_str(start)
717 try:
718 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
719 except ValueError:
720 return None
721
722 def _extract_time_text(self, renderer, *path_list):
723 text = self._get_text(renderer, *path_list) or ''
724 dt = self.extract_relative_time(text)
725 timestamp = None
726 if isinstance(dt, datetime.datetime):
727 timestamp = calendar.timegm(dt.timetuple())
728
729 if timestamp is None:
730 timestamp = (
731 unified_timestamp(text) or unified_timestamp(
732 self._search_regex(
733 (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
734 text.lower(), 'time text', default=None)))
735
736 if text and timestamp is None:
737 self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
738 return timestamp, text
739
740 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
741 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
742 default_client='web'):
743 response = None
744 last_error = None
745 count = -1
746 retries = self.get_param('extractor_retries', 3)
747 if check_get_keys is None:
748 check_get_keys = []
749 while count < retries:
750 count += 1
751 if last_error:
752 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
753 try:
754 response = self._call_api(
755 ep=ep, fatal=True, headers=headers,
756 video_id=item_id, query=query,
757 context=self._extract_context(ytcfg, default_client),
758 api_key=self._extract_api_key(ytcfg, default_client),
759 api_hostname=api_hostname, default_client=default_client,
760 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
761 except ExtractorError as e:
762 if isinstance(e.cause, network_exceptions):
763 if isinstance(e.cause, compat_HTTPError) and not is_html(e.cause.read(512)):
764 e.cause.seek(0)
765 yt_error = try_get(
766 self._parse_json(e.cause.read().decode(), item_id, fatal=False),
767 lambda x: x['error']['message'], compat_str)
768 if yt_error:
769 self._report_alerts([('ERROR', yt_error)], fatal=False)
770 # Downloading page may result in intermittent 5xx HTTP error
771 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
772 # We also want to catch all other network exceptions since errors in later pages can be troublesome
773 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
774 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
775 last_error = error_to_compat_str(e.cause or e.msg)
776 if count < retries:
777 continue
778 if fatal:
779 raise
780 else:
781 self.report_warning(error_to_compat_str(e))
782 return
783
784 else:
785 try:
786 self._extract_and_report_alerts(response, only_once=True)
787 except ExtractorError as e:
788 # YouTube servers may return errors we want to retry on in a 200 OK response
789 # See: https://github.com/yt-dlp/yt-dlp/issues/839
790 if 'unknown error' in e.msg.lower():
791 last_error = e.msg
792 continue
793 if fatal:
794 raise
795 self.report_warning(error_to_compat_str(e))
796 return
797 if not check_get_keys or dict_get(response, check_get_keys):
798 break
799 # Youtube sometimes sends incomplete data
800 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
801 last_error = 'Incomplete data received'
802 if count >= retries:
803 if fatal:
804 raise ExtractorError(last_error)
805 else:
806 self.report_warning(last_error)
807 return
808 return response
809
810 @staticmethod
811 def is_music_url(url):
812 return re.match(r'https?://music\.youtube\.com/', url) is not None
813
814 def _extract_video(self, renderer):
815 video_id = renderer.get('videoId')
816 title = self._get_text(renderer, 'title')
817 description = self._get_text(renderer, 'descriptionSnippet')
818 duration = parse_duration(self._get_text(
819 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
820 view_count = self._get_count(renderer, 'viewCountText')
821
822 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
823 channel_id = traverse_obj(
824 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
825 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
826 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
827 overlay_style = traverse_obj(
828 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
829 badges = self._extract_badges(renderer)
830 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
831
832 return {
833 '_type': 'url',
834 'ie_key': YoutubeIE.ie_key(),
835 'id': video_id,
836 'url': f'https://www.youtube.com/watch?v={video_id}',
837 'title': title,
838 'description': description,
839 'duration': duration,
840 'view_count': view_count,
841 'uploader': uploader,
842 'channel_id': channel_id,
843 'thumbnails': thumbnails,
844 # 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
845 'live_status': ('is_upcoming' if scheduled_timestamp is not None
846 else 'was_live' if 'streamed' in time_text.lower()
847 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
848 else None),
849 'release_timestamp': scheduled_timestamp,
850 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
851 }
852
853
854class YoutubeIE(YoutubeBaseInfoExtractor):
855 IE_DESC = 'YouTube'
856 _VALID_URL = r"""(?x)^
857 (
858 (?:https?://|//) # http(s):// or protocol-independent URL
859 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
860 (?:www\.)?deturl\.com/www\.youtube\.com|
861 (?:www\.)?pwnyoutube\.com|
862 (?:www\.)?hooktube\.com|
863 (?:www\.)?yourepeat\.com|
864 tube\.majestyc\.net|
865 %(invidious)s|
866 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
867 (?:.*?\#/)? # handle anchor (#/) redirect urls
868 (?: # the various things that can precede the ID:
869 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
870 |(?: # or the v= param in all its forms
871 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
872 (?:\?|\#!?) # the params delimiter ? or # or #!
873 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
874 v=
875 )
876 ))
877 |(?:
878 youtu\.be| # just youtu.be/xxxx
879 vid\.plus| # or vid.plus/xxxx
880 zwearz\.com/watch| # or zwearz.com/watch/xxxx
881 %(invidious)s
882 )/
883 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
884 )
885 )? # all until now is optional -> you can pass the naked ID
886 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
887 (?(1).+)? # if we found the ID, everything can follow
888 (?:\#|$)""" % {
889 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
890 }
891 _PLAYER_INFO_RE = (
892 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
893 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
894 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
895 )
896 _formats = {
897 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
898 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
899 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
900 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
901 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
902 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
903 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
904 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
905 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
906 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
907 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
908 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
909 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
910 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
911 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
912 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
913 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
914 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
915
916
917 # 3D videos
918 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
919 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
920 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
921 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
922 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
923 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
924 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
925
926 # Apple HTTP Live Streaming
927 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
928 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
929 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
930 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
931 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
932 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
933 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
934 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
935
936 # DASH mp4 video
937 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
938 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
939 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
940 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
942 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
943 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
944 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
945 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
946 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
947 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
948 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
949
950 # Dash mp4 audio
951 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
952 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
953 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
954 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
955 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
956 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
957 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
958
959 # Dash webm
960 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
961 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
962 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
963 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
967 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
968 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
969 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
970 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
976 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
977 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
978 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
979 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
980 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
981 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
982
983 # Dash webm audio
984 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
985 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
986
987 # Dash webm audio with opus inside
988 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
989 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
990 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
991
992 # RTMP (unnamed)
993 '_rtmp': {'protocol': 'rtmp'},
994
995 # av01 video only formats sometimes served with "unknown" codecs
996 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
997 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
998 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
999 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1000 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1001 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1002 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1003 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1004 }
1005 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1006
1007 _GEO_BYPASS = False
1008
1009 IE_NAME = 'youtube'
1010 _TESTS = [
1011 {
1012 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1013 'info_dict': {
1014 'id': 'BaW_jenozKc',
1015 'ext': 'mp4',
1016 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1017 'uploader': 'Philipp Hagemeister',
1018 'uploader_id': 'phihag',
1019 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1020 'channel': 'Philipp Hagemeister',
1021 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1022 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1023 'upload_date': '20121002',
1024 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1025 'categories': ['Science & Technology'],
1026 'tags': ['youtube-dl'],
1027 'duration': 10,
1028 'view_count': int,
1029 'like_count': int,
1030 'availability': 'public',
1031 'playable_in_embed': True,
1032 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1033 'live_status': 'not_live',
1034 'age_limit': 0,
1035 'start_time': 1,
1036 'end_time': 9,
1037 }
1038 },
1039 {
1040 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1041 'note': 'Embed-only video (#1746)',
1042 'info_dict': {
1043 'id': 'yZIXLfi8CZQ',
1044 'ext': 'mp4',
1045 'upload_date': '20120608',
1046 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1047 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1048 'uploader': 'SET India',
1049 'uploader_id': 'setindia',
1050 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1051 'age_limit': 18,
1052 },
1053 'skip': 'Private video',
1054 },
1055 {
1056 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1057 'note': 'Use the first video ID in the URL',
1058 'info_dict': {
1059 'id': 'BaW_jenozKc',
1060 'ext': 'mp4',
1061 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1062 'uploader': 'Philipp Hagemeister',
1063 'uploader_id': 'phihag',
1064 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1065 'channel': 'Philipp Hagemeister',
1066 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1067 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1068 'upload_date': '20121002',
1069 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1070 'categories': ['Science & Technology'],
1071 'tags': ['youtube-dl'],
1072 'duration': 10,
1073 'view_count': int,
1074 'like_count': int,
1075 'availability': 'public',
1076 'playable_in_embed': True,
1077 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1078 'live_status': 'not_live',
1079 'age_limit': 0,
1080 },
1081 'params': {
1082 'skip_download': True,
1083 },
1084 },
1085 {
1086 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1087 'note': '256k DASH audio (format 141) via DASH manifest',
1088 'info_dict': {
1089 'id': 'a9LDPn-MO4I',
1090 'ext': 'm4a',
1091 'upload_date': '20121002',
1092 'uploader_id': '8KVIDEO',
1093 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1094 'description': '',
1095 'uploader': '8KVIDEO',
1096 'title': 'UHDTV TEST 8K VIDEO.mp4'
1097 },
1098 'params': {
1099 'youtube_include_dash_manifest': True,
1100 'format': '141',
1101 },
1102 'skip': 'format 141 not served anymore',
1103 },
1104 # DASH manifest with encrypted signature
1105 {
1106 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1107 'info_dict': {
1108 'id': 'IB3lcPjvWLA',
1109 'ext': 'm4a',
1110 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1111 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1112 'duration': 244,
1113 'uploader': 'AfrojackVEVO',
1114 'uploader_id': 'AfrojackVEVO',
1115 'upload_date': '20131011',
1116 'abr': 129.495,
1117 'like_count': int,
1118 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1119 'playable_in_embed': True,
1120 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1121 'view_count': int,
1122 'track': 'The Spark',
1123 'live_status': 'not_live',
1124 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1125 'channel': 'Afrojack',
1126 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1127 'tags': 'count:19',
1128 'availability': 'public',
1129 'categories': ['Music'],
1130 'age_limit': 0,
1131 'alt_title': 'The Spark',
1132 },
1133 'params': {
1134 'youtube_include_dash_manifest': True,
1135 'format': '141/bestaudio[ext=m4a]',
1136 },
1137 },
1138 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1139 {
1140 'note': 'Embed allowed age-gate video',
1141 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1142 'info_dict': {
1143 'id': 'HtVdAasjOgU',
1144 'ext': 'mp4',
1145 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1146 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1147 'duration': 142,
1148 'uploader': 'The Witcher',
1149 'uploader_id': 'WitcherGame',
1150 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1151 'upload_date': '20140605',
1152 'age_limit': 18,
1153 'categories': ['Gaming'],
1154 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1155 'availability': 'needs_auth',
1156 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1157 'like_count': int,
1158 'channel': 'The Witcher',
1159 'live_status': 'not_live',
1160 'tags': 'count:17',
1161 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1162 'playable_in_embed': True,
1163 'view_count': int,
1164 },
1165 },
1166 {
1167 'note': 'Age-gate video with embed allowed in public site',
1168 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1169 'info_dict': {
1170 'id': 'HsUATh_Nc2U',
1171 'ext': 'mp4',
1172 'title': 'Godzilla 2 (Official Video)',
1173 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1174 'upload_date': '20200408',
1175 'uploader_id': 'FlyingKitty900',
1176 'uploader': 'FlyingKitty',
1177 'age_limit': 18,
1178 'availability': 'needs_auth',
1179 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1180 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1181 'channel': 'FlyingKitty',
1182 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1183 'view_count': int,
1184 'categories': ['Entertainment'],
1185 'live_status': 'not_live',
1186 'tags': ['Flyingkitty', 'godzilla 2'],
1187 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1188 'like_count': int,
1189 'duration': 177,
1190 'playable_in_embed': True,
1191 },
1192 },
1193 {
1194 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1195 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1196 'info_dict': {
1197 'id': 'Tq92D6wQ1mg',
1198 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1199 'ext': 'mp4',
1200 'upload_date': '20191227',
1201 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1202 'uploader': 'Projekt Melody',
1203 'description': 'md5:17eccca93a786d51bc67646756894066',
1204 'age_limit': 18,
1205 'like_count': int,
1206 'availability': 'needs_auth',
1207 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1208 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1209 'view_count': int,
1210 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1211 'channel': 'Projekt Melody',
1212 'live_status': 'not_live',
1213 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1214 'playable_in_embed': True,
1215 'categories': ['Entertainment'],
1216 'duration': 106,
1217 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1218 },
1219 },
1220 {
1221 'note': 'Non-Agegated non-embeddable video',
1222 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1223 'info_dict': {
1224 'id': 'MeJVWBSsPAY',
1225 'ext': 'mp4',
1226 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1227 'uploader': 'Herr Lurik',
1228 'uploader_id': 'st3in234',
1229 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1230 'upload_date': '20130730',
1231 'track': 'Such mich find mich',
1232 'age_limit': 0,
1233 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1234 'like_count': int,
1235 'playable_in_embed': False,
1236 'creator': 'OOMPH!',
1237 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1238 'view_count': int,
1239 'alt_title': 'Such mich find mich',
1240 'duration': 210,
1241 'channel': 'Herr Lurik',
1242 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1243 'categories': ['Music'],
1244 'availability': 'public',
1245 'uploader_url': 'http://www.youtube.com/user/st3in234',
1246 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1247 'live_status': 'not_live',
1248 'artist': 'OOMPH!',
1249 },
1250 },
1251 {
1252 'note': 'Non-bypassable age-gated video',
1253 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1254 'only_matching': True,
1255 },
1256 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1257 # YouTube Red ad is not captured for creator
1258 {
1259 'url': '__2ABJjxzNo',
1260 'info_dict': {
1261 'id': '__2ABJjxzNo',
1262 'ext': 'mp4',
1263 'duration': 266,
1264 'upload_date': '20100430',
1265 'uploader_id': 'deadmau5',
1266 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1267 'creator': 'deadmau5',
1268 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1269 'uploader': 'deadmau5',
1270 'title': 'Deadmau5 - Some Chords (HD)',
1271 'alt_title': 'Some Chords',
1272 'availability': 'public',
1273 'tags': 'count:14',
1274 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1275 'view_count': int,
1276 'live_status': 'not_live',
1277 'channel': 'deadmau5',
1278 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1279 'like_count': int,
1280 'track': 'Some Chords',
1281 'artist': 'deadmau5',
1282 'playable_in_embed': True,
1283 'age_limit': 0,
1284 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1285 'categories': ['Music'],
1286 'album': 'Some Chords',
1287 },
1288 'expected_warnings': [
1289 'DASH manifest missing',
1290 ]
1291 },
1292 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1293 {
1294 'url': 'lqQg6PlCWgI',
1295 'info_dict': {
1296 'id': 'lqQg6PlCWgI',
1297 'ext': 'mp4',
1298 'duration': 6085,
1299 'upload_date': '20150827',
1300 'uploader_id': 'olympic',
1301 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1302 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1303 'uploader': 'Olympics',
1304 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1305 'like_count': int,
1306 'release_timestamp': 1343767800,
1307 'playable_in_embed': True,
1308 'categories': ['Sports'],
1309 'release_date': '20120731',
1310 'channel': 'Olympics',
1311 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1312 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1313 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1314 'age_limit': 0,
1315 'availability': 'public',
1316 'live_status': 'was_live',
1317 'view_count': int,
1318 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1319 },
1320 'params': {
1321 'skip_download': 'requires avconv',
1322 }
1323 },
1324 # Non-square pixels
1325 {
1326 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1327 'info_dict': {
1328 'id': '_b-2C3KPAM0',
1329 'ext': 'mp4',
1330 'stretched_ratio': 16 / 9.,
1331 'duration': 85,
1332 'upload_date': '20110310',
1333 'uploader_id': 'AllenMeow',
1334 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1335 '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',
1336 'uploader': '孫ᄋᄅ',
1337 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1338 'playable_in_embed': True,
1339 'channel': '孫ᄋᄅ',
1340 'age_limit': 0,
1341 'tags': 'count:11',
1342 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1343 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1344 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1345 'view_count': int,
1346 'categories': ['People & Blogs'],
1347 'like_count': int,
1348 'live_status': 'not_live',
1349 'availability': 'unlisted',
1350 },
1351 },
1352 # url_encoded_fmt_stream_map is empty string
1353 {
1354 'url': 'qEJwOuvDf7I',
1355 'info_dict': {
1356 'id': 'qEJwOuvDf7I',
1357 'ext': 'webm',
1358 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1359 'description': '',
1360 'upload_date': '20150404',
1361 'uploader_id': 'spbelect',
1362 'uploader': 'Наблюдатели Петербурга',
1363 },
1364 'params': {
1365 'skip_download': 'requires avconv',
1366 },
1367 'skip': 'This live event has ended.',
1368 },
1369 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1370 {
1371 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1372 'info_dict': {
1373 'id': 'FIl7x6_3R5Y',
1374 'ext': 'webm',
1375 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1376 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1377 'duration': 220,
1378 'upload_date': '20150625',
1379 'uploader_id': 'dorappi2000',
1380 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1381 'uploader': 'dorappi2000',
1382 'formats': 'mincount:31',
1383 },
1384 'skip': 'not actual anymore',
1385 },
1386 # DASH manifest with segment_list
1387 {
1388 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1389 'md5': '8ce563a1d667b599d21064e982ab9e31',
1390 'info_dict': {
1391 'id': 'CsmdDsKjzN8',
1392 'ext': 'mp4',
1393 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1394 'uploader': 'Airtek',
1395 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1396 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1397 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1398 },
1399 'params': {
1400 'youtube_include_dash_manifest': True,
1401 'format': '135', # bestvideo
1402 },
1403 'skip': 'This live event has ended.',
1404 },
1405 {
1406 # Multifeed videos (multiple cameras), URL is for Main Camera
1407 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1408 'info_dict': {
1409 'id': 'jvGDaLqkpTg',
1410 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1411 'description': 'md5:e03b909557865076822aa169218d6a5d',
1412 },
1413 'playlist': [{
1414 'info_dict': {
1415 'id': 'jvGDaLqkpTg',
1416 'ext': 'mp4',
1417 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1418 'description': 'md5:e03b909557865076822aa169218d6a5d',
1419 'duration': 10643,
1420 'upload_date': '20161111',
1421 'uploader': 'Team PGP',
1422 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1423 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1424 },
1425 }, {
1426 'info_dict': {
1427 'id': '3AKt1R1aDnw',
1428 'ext': 'mp4',
1429 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1430 'description': 'md5:e03b909557865076822aa169218d6a5d',
1431 'duration': 10991,
1432 'upload_date': '20161111',
1433 'uploader': 'Team PGP',
1434 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1435 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1436 },
1437 }, {
1438 'info_dict': {
1439 'id': 'RtAMM00gpVc',
1440 'ext': 'mp4',
1441 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1442 'description': 'md5:e03b909557865076822aa169218d6a5d',
1443 'duration': 10995,
1444 'upload_date': '20161111',
1445 'uploader': 'Team PGP',
1446 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1447 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1448 },
1449 }, {
1450 'info_dict': {
1451 'id': '6N2fdlP3C5U',
1452 'ext': 'mp4',
1453 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1454 'description': 'md5:e03b909557865076822aa169218d6a5d',
1455 'duration': 10990,
1456 'upload_date': '20161111',
1457 'uploader': 'Team PGP',
1458 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1460 },
1461 }],
1462 'params': {
1463 'skip_download': True,
1464 },
1465 'skip': 'Not multifeed anymore',
1466 },
1467 {
1468 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1469 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1470 'info_dict': {
1471 'id': 'gVfLd0zydlo',
1472 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1473 },
1474 'playlist_count': 2,
1475 'skip': 'Not multifeed anymore',
1476 },
1477 {
1478 'url': 'https://vid.plus/FlRa-iH7PGw',
1479 'only_matching': True,
1480 },
1481 {
1482 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1483 'only_matching': True,
1484 },
1485 {
1486 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1487 # Also tests cut-off URL expansion in video description (see
1488 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1489 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1490 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1491 'info_dict': {
1492 'id': 'lsguqyKfVQg',
1493 'ext': 'mp4',
1494 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1495 'alt_title': 'Dark Walk',
1496 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1497 'duration': 133,
1498 'upload_date': '20151119',
1499 'uploader_id': 'IronSoulElf',
1500 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1501 'uploader': 'IronSoulElf',
1502 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1503 'track': 'Dark Walk',
1504 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1505 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1506 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1507 'categories': ['Film & Animation'],
1508 'view_count': int,
1509 'live_status': 'not_live',
1510 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1511 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1512 'tags': 'count:13',
1513 'availability': 'public',
1514 'channel': 'IronSoulElf',
1515 'playable_in_embed': True,
1516 'like_count': int,
1517 'age_limit': 0,
1518 },
1519 'params': {
1520 'skip_download': True,
1521 },
1522 },
1523 {
1524 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1525 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1526 'only_matching': True,
1527 },
1528 {
1529 # Video with yt:stretch=17:0
1530 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1531 'info_dict': {
1532 'id': 'Q39EVAstoRM',
1533 'ext': 'mp4',
1534 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1535 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1536 'upload_date': '20151107',
1537 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1538 'uploader': 'CH GAMER DROID',
1539 },
1540 'params': {
1541 'skip_download': True,
1542 },
1543 'skip': 'This video does not exist.',
1544 },
1545 {
1546 # Video with incomplete 'yt:stretch=16:'
1547 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1548 'only_matching': True,
1549 },
1550 {
1551 # Video licensed under Creative Commons
1552 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1553 'info_dict': {
1554 'id': 'M4gD1WSo5mA',
1555 'ext': 'mp4',
1556 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1557 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1558 'duration': 721,
1559 'upload_date': '20150127',
1560 'uploader_id': 'BerkmanCenter',
1561 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1562 'uploader': 'The Berkman Klein Center for Internet & Society',
1563 'license': 'Creative Commons Attribution license (reuse allowed)',
1564 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1565 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1566 'like_count': int,
1567 'age_limit': 0,
1568 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1569 'channel': 'The Berkman Klein Center for Internet & Society',
1570 'availability': 'public',
1571 'view_count': int,
1572 'categories': ['Education'],
1573 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1574 'live_status': 'not_live',
1575 'playable_in_embed': True,
1576 },
1577 'params': {
1578 'skip_download': True,
1579 },
1580 },
1581 {
1582 # Channel-like uploader_url
1583 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1584 'info_dict': {
1585 'id': 'eQcmzGIKrzg',
1586 'ext': 'mp4',
1587 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1588 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1589 'duration': 4060,
1590 'upload_date': '20151119',
1591 'uploader': 'Bernie Sanders',
1592 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1593 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1594 'license': 'Creative Commons Attribution license (reuse allowed)',
1595 'playable_in_embed': True,
1596 'tags': 'count:12',
1597 'like_count': int,
1598 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1599 'age_limit': 0,
1600 'availability': 'public',
1601 'categories': ['News & Politics'],
1602 'channel': 'Bernie Sanders',
1603 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1604 'view_count': int,
1605 'live_status': 'not_live',
1606 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1607 },
1608 'params': {
1609 'skip_download': True,
1610 },
1611 },
1612 {
1613 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1614 'only_matching': True,
1615 },
1616 {
1617 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1618 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1619 'only_matching': True,
1620 },
1621 {
1622 # Rental video preview
1623 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1624 'info_dict': {
1625 'id': 'uGpuVWrhIzE',
1626 'ext': 'mp4',
1627 'title': 'Piku - Trailer',
1628 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1629 'upload_date': '20150811',
1630 'uploader': 'FlixMatrix',
1631 'uploader_id': 'FlixMatrixKaravan',
1632 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1633 'license': 'Standard YouTube License',
1634 },
1635 'params': {
1636 'skip_download': True,
1637 },
1638 'skip': 'This video is not available.',
1639 },
1640 {
1641 # YouTube Red video with episode data
1642 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1643 'info_dict': {
1644 'id': 'iqKdEhx-dD4',
1645 'ext': 'mp4',
1646 'title': 'Isolation - Mind Field (Ep 1)',
1647 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1648 'duration': 2085,
1649 'upload_date': '20170118',
1650 'uploader': 'Vsauce',
1651 'uploader_id': 'Vsauce',
1652 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1653 'series': 'Mind Field',
1654 'season_number': 1,
1655 'episode_number': 1,
1656 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1657 'tags': 'count:12',
1658 'view_count': int,
1659 'availability': 'public',
1660 'age_limit': 0,
1661 'channel': 'Vsauce',
1662 'episode': 'Episode 1',
1663 'categories': ['Entertainment'],
1664 'season': 'Season 1',
1665 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1666 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1667 'like_count': int,
1668 'playable_in_embed': True,
1669 'live_status': 'not_live',
1670 },
1671 'params': {
1672 'skip_download': True,
1673 },
1674 'expected_warnings': [
1675 'Skipping DASH manifest',
1676 ],
1677 },
1678 {
1679 # The following content has been identified by the YouTube community
1680 # as inappropriate or offensive to some audiences.
1681 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1682 'info_dict': {
1683 'id': '6SJNVb0GnPI',
1684 'ext': 'mp4',
1685 'title': 'Race Differences in Intelligence',
1686 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1687 'duration': 965,
1688 'upload_date': '20140124',
1689 'uploader': 'New Century Foundation',
1690 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1691 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1692 },
1693 'params': {
1694 'skip_download': True,
1695 },
1696 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1697 },
1698 {
1699 # itag 212
1700 'url': '1t24XAntNCY',
1701 'only_matching': True,
1702 },
1703 {
1704 # geo restricted to JP
1705 'url': 'sJL6WA-aGkQ',
1706 'only_matching': True,
1707 },
1708 {
1709 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1710 'only_matching': True,
1711 },
1712 {
1713 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1714 'only_matching': True,
1715 },
1716 {
1717 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1718 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1719 'only_matching': True,
1720 },
1721 {
1722 # DRM protected
1723 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1724 'only_matching': True,
1725 },
1726 {
1727 # Video with unsupported adaptive stream type formats
1728 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1729 'info_dict': {
1730 'id': 'Z4Vy8R84T1U',
1731 'ext': 'mp4',
1732 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1733 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1734 'duration': 433,
1735 'upload_date': '20130923',
1736 'uploader': 'Amelia Putri Harwita',
1737 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1738 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1739 'formats': 'maxcount:10',
1740 },
1741 'params': {
1742 'skip_download': True,
1743 'youtube_include_dash_manifest': False,
1744 },
1745 'skip': 'not actual anymore',
1746 },
1747 {
1748 # Youtube Music Auto-generated description
1749 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1750 'info_dict': {
1751 'id': 'MgNrAu2pzNs',
1752 'ext': 'mp4',
1753 'title': 'Voyeur Girl',
1754 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1755 'upload_date': '20190312',
1756 'uploader': 'Stephen - Topic',
1757 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1758 'artist': 'Stephen',
1759 'track': 'Voyeur Girl',
1760 'album': 'it\'s too much love to know my dear',
1761 'release_date': '20190313',
1762 'release_year': 2019,
1763 'alt_title': 'Voyeur Girl',
1764 'view_count': int,
1765 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1766 'playable_in_embed': True,
1767 'like_count': int,
1768 'categories': ['Music'],
1769 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1770 'channel': 'Stephen',
1771 'availability': 'public',
1772 'creator': 'Stephen',
1773 'duration': 169,
1774 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1775 'age_limit': 0,
1776 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1777 'tags': 'count:11',
1778 'live_status': 'not_live',
1779 },
1780 'params': {
1781 'skip_download': True,
1782 },
1783 },
1784 {
1785 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1786 'only_matching': True,
1787 },
1788 {
1789 # invalid -> valid video id redirection
1790 'url': 'DJztXj2GPfl',
1791 'info_dict': {
1792 'id': 'DJztXj2GPfk',
1793 'ext': 'mp4',
1794 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1795 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1796 'upload_date': '20090125',
1797 'uploader': 'Prochorowka',
1798 'uploader_id': 'Prochorowka',
1799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1800 'artist': 'Panjabi MC',
1801 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1802 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1803 },
1804 'params': {
1805 'skip_download': True,
1806 },
1807 'skip': 'Video unavailable',
1808 },
1809 {
1810 # empty description results in an empty string
1811 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1812 'info_dict': {
1813 'id': 'x41yOUIvK2k',
1814 'ext': 'mp4',
1815 'title': 'IMG 3456',
1816 'description': '',
1817 'upload_date': '20170613',
1818 'uploader_id': 'ElevageOrVert',
1819 'uploader': 'ElevageOrVert',
1820 'view_count': int,
1821 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1822 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1823 'like_count': int,
1824 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1825 'tags': [],
1826 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1827 'availability': 'public',
1828 'age_limit': 0,
1829 'categories': ['Pets & Animals'],
1830 'duration': 7,
1831 'playable_in_embed': True,
1832 'live_status': 'not_live',
1833 'channel': 'ElevageOrVert',
1834 },
1835 'params': {
1836 'skip_download': True,
1837 },
1838 },
1839 {
1840 # with '};' inside yt initial data (see [1])
1841 # see [2] for an example with '};' inside ytInitialPlayerResponse
1842 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1843 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1844 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1845 'info_dict': {
1846 'id': 'CHqg6qOn4no',
1847 'ext': 'mp4',
1848 'title': 'Part 77 Sort a list of simple types in c#',
1849 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1850 'upload_date': '20130831',
1851 'uploader_id': 'kudvenkat',
1852 'uploader': 'kudvenkat',
1853 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1854 'like_count': int,
1855 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1856 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1857 'live_status': 'not_live',
1858 'categories': ['Education'],
1859 'availability': 'public',
1860 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1861 'tags': 'count:12',
1862 'playable_in_embed': True,
1863 'age_limit': 0,
1864 'view_count': int,
1865 'duration': 522,
1866 'channel': 'kudvenkat',
1867 },
1868 'params': {
1869 'skip_download': True,
1870 },
1871 },
1872 {
1873 # another example of '};' in ytInitialData
1874 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1875 'only_matching': True,
1876 },
1877 {
1878 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1879 'only_matching': True,
1880 },
1881 {
1882 # https://github.com/ytdl-org/youtube-dl/pull/28094
1883 'url': 'OtqTfy26tG0',
1884 'info_dict': {
1885 'id': 'OtqTfy26tG0',
1886 'ext': 'mp4',
1887 'title': 'Burn Out',
1888 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1889 'upload_date': '20141120',
1890 'uploader': 'The Cinematic Orchestra - Topic',
1891 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1892 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1893 'artist': 'The Cinematic Orchestra',
1894 'track': 'Burn Out',
1895 'album': 'Every Day',
1896 'like_count': int,
1897 'live_status': 'not_live',
1898 'alt_title': 'Burn Out',
1899 'duration': 614,
1900 'age_limit': 0,
1901 'view_count': int,
1902 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1903 'creator': 'The Cinematic Orchestra',
1904 'channel': 'The Cinematic Orchestra',
1905 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1906 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1907 'availability': 'public',
1908 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1909 'categories': ['Music'],
1910 'playable_in_embed': True,
1911 },
1912 'params': {
1913 'skip_download': True,
1914 },
1915 },
1916 {
1917 # controversial video, only works with bpctr when authenticated with cookies
1918 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1919 'only_matching': True,
1920 },
1921 {
1922 # controversial video, requires bpctr/contentCheckOk
1923 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1924 'info_dict': {
1925 'id': 'SZJvDhaSDnc',
1926 'ext': 'mp4',
1927 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1928 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1929 'uploader': 'CBS Mornings',
1930 'uploader_id': 'CBSThisMorning',
1931 'upload_date': '20140716',
1932 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1933 'duration': 170,
1934 'categories': ['News & Politics'],
1935 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1936 'view_count': int,
1937 'channel': 'CBS Mornings',
1938 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1939 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1940 'age_limit': 18,
1941 'availability': 'needs_auth',
1942 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1943 'like_count': int,
1944 'live_status': 'not_live',
1945 'playable_in_embed': True,
1946 }
1947 },
1948 {
1949 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1950 'url': 'cBvYw8_A0vQ',
1951 'info_dict': {
1952 'id': 'cBvYw8_A0vQ',
1953 'ext': 'mp4',
1954 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1955 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1956 'upload_date': '20201120',
1957 'uploader': 'Walk around Japan',
1958 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1959 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1960 'duration': 1456,
1961 'categories': ['Travel & Events'],
1962 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1963 'view_count': int,
1964 'channel': 'Walk around Japan',
1965 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1966 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1967 'age_limit': 0,
1968 'availability': 'public',
1969 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1970 'live_status': 'not_live',
1971 'playable_in_embed': True,
1972 },
1973 'params': {
1974 'skip_download': True,
1975 },
1976 }, {
1977 # Has multiple audio streams
1978 'url': 'WaOKSUlf4TM',
1979 'only_matching': True
1980 }, {
1981 # Requires Premium: has format 141 when requested using YTM url
1982 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1983 'only_matching': True
1984 }, {
1985 # multiple subtitles with same lang_code
1986 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1987 'only_matching': True,
1988 }, {
1989 # Force use android client fallback
1990 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1991 'info_dict': {
1992 'id': 'YOelRv7fMxY',
1993 'title': 'DIGGING A SECRET TUNNEL Part 1',
1994 'ext': '3gp',
1995 'upload_date': '20210624',
1996 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1997 'uploader': 'colinfurze',
1998 'uploader_id': 'colinfurze',
1999 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2000 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2001 'duration': 596,
2002 'categories': ['Entertainment'],
2003 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2004 'view_count': int,
2005 'channel': 'colinfurze',
2006 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2007 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2008 'age_limit': 0,
2009 'availability': 'public',
2010 'like_count': int,
2011 'live_status': 'not_live',
2012 'playable_in_embed': True,
2013 },
2014 'params': {
2015 'format': '17', # 3gp format available on android
2016 'extractor_args': {'youtube': {'player_client': ['android']}},
2017 },
2018 },
2019 {
2020 # Skip download of additional client configs (remix client config in this case)
2021 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2022 'only_matching': True,
2023 'params': {
2024 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2025 },
2026 }, {
2027 # shorts
2028 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2029 'only_matching': True,
2030 }, {
2031 'note': 'Storyboards',
2032 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2033 'info_dict': {
2034 'id': '5KLPxDtMqe8',
2035 'ext': 'mhtml',
2036 'format_id': 'sb0',
2037 'title': 'Your Brain is Plastic',
2038 'uploader_id': 'scishow',
2039 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2040 'upload_date': '20140324',
2041 'uploader': 'SciShow',
2042 'like_count': int,
2043 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2044 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2045 'view_count': int,
2046 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2047 'playable_in_embed': True,
2048 'tags': 'count:12',
2049 'uploader_url': 'http://www.youtube.com/user/scishow',
2050 'availability': 'public',
2051 'channel': 'SciShow',
2052 'live_status': 'not_live',
2053 'duration': 248,
2054 'categories': ['Education'],
2055 'age_limit': 0,
2056 }, 'params': {'format': 'mhtml', 'skip_download': True}
2057 }
2058 ]
2059
2060 @classmethod
2061 def suitable(cls, url):
2062 from ..utils import parse_qs
2063
2064 qs = parse_qs(url)
2065 if qs.get('list', [None])[0]:
2066 return False
2067 return super(YoutubeIE, cls).suitable(url)
2068
2069 def __init__(self, *args, **kwargs):
2070 super(YoutubeIE, self).__init__(*args, **kwargs)
2071 self._code_cache = {}
2072 self._player_cache = {}
2073
2074 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2075 lock = threading.Lock()
2076
2077 is_live = True
2078 start_time = time.time()
2079 formats = [f for f in formats if f.get('is_from_start')]
2080
2081 def refetch_manifest(format_id, delay):
2082 nonlocal formats, start_time, is_live
2083 if time.time() <= start_time + delay:
2084 return
2085
2086 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2087 video_details = traverse_obj(
2088 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2089 microformats = traverse_obj(
2090 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2091 expected_type=dict, default=[])
2092 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
2093 start_time = time.time()
2094
2095 def mpd_feed(format_id, delay):
2096 """
2097 @returns (manifest_url, manifest_stream_number, is_live) or None
2098 """
2099 with lock:
2100 refetch_manifest(format_id, delay)
2101
2102 f = next((f for f in formats if f['format_id'] == format_id), None)
2103 if not f:
2104 if not is_live:
2105 self.to_screen(f'{video_id}: Video is no longer live')
2106 else:
2107 self.report_warning(
2108 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2109 return None
2110 return f['manifest_url'], f['manifest_stream_number'], is_live
2111
2112 for f in formats:
2113 f['protocol'] = 'http_dash_segments_generator'
2114 f['fragments'] = functools.partial(
2115 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2116
2117 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2118 FETCH_SPAN, MAX_DURATION = 5, 432000
2119
2120 mpd_url, stream_number, is_live = None, None, True
2121
2122 begin_index = 0
2123 download_start_time = ctx.get('start') or time.time()
2124
2125 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2126 if lack_early_segments:
2127 self.report_warning(bug_reports_message(
2128 'Starting download from the last 120 hours of the live stream since '
2129 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2130 lack_early_segments = True
2131
2132 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2133 fragments, fragment_base_url = None, None
2134
2135 def _extract_sequence_from_mpd(refresh_sequence):
2136 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2137 # Obtain from MPD's maximum seq value
2138 old_mpd_url = mpd_url
2139 last_error = ctx.pop('last_error', None)
2140 expire_fast = last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2141 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2142 or (mpd_url, stream_number, False))
2143 if not refresh_sequence:
2144 if expire_fast and not is_live:
2145 return False, last_seq
2146 elif old_mpd_url == mpd_url:
2147 return True, last_seq
2148 try:
2149 fmts, _ = self._extract_mpd_formats_and_subtitles(
2150 mpd_url, None, note=False, errnote=False, fatal=False)
2151 except ExtractorError:
2152 fmts = None
2153 if not fmts:
2154 no_fragment_score += 1
2155 return False, last_seq
2156 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2157 fragments = fmt_info['fragments']
2158 fragment_base_url = fmt_info['fragment_base_url']
2159 assert fragment_base_url
2160
2161 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2162 return True, _last_seq
2163
2164 while is_live:
2165 fetch_time = time.time()
2166 if no_fragment_score > 30:
2167 return
2168 if last_segment_url:
2169 # Obtain from "X-Head-Seqnum" header value from each segment
2170 try:
2171 urlh = self._request_webpage(
2172 last_segment_url, None, note=False, errnote=False, fatal=False)
2173 except ExtractorError:
2174 urlh = None
2175 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2176 if last_seq is None:
2177 no_fragment_score += 1
2178 last_segment_url = None
2179 continue
2180 else:
2181 should_continue, last_seq = _extract_sequence_from_mpd(True)
2182 if not should_continue:
2183 continue
2184
2185 if known_idx > last_seq:
2186 last_segment_url = None
2187 continue
2188
2189 last_seq += 1
2190
2191 if begin_index < 0 and known_idx < 0:
2192 # skip from the start when it's negative value
2193 known_idx = last_seq + begin_index
2194 if lack_early_segments:
2195 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2196 try:
2197 for idx in range(known_idx, last_seq):
2198 # do not update sequence here or you'll get skipped some part of it
2199 should_continue, _ = _extract_sequence_from_mpd(False)
2200 if not should_continue:
2201 known_idx = idx - 1
2202 raise ExtractorError('breaking out of outer loop')
2203 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2204 yield {
2205 'url': last_segment_url,
2206 }
2207 if known_idx == last_seq:
2208 no_fragment_score += 5
2209 else:
2210 no_fragment_score = 0
2211 known_idx = last_seq
2212 except ExtractorError:
2213 continue
2214
2215 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2216
2217 def _extract_player_url(self, *ytcfgs, webpage=None):
2218 player_url = traverse_obj(
2219 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2220 get_all=False, expected_type=compat_str)
2221 if not player_url:
2222 return
2223 if player_url.startswith('//'):
2224 player_url = 'https:' + player_url
2225 elif not re.match(r'https?://', player_url):
2226 player_url = compat_urlparse.urljoin(
2227 'https://www.youtube.com', player_url)
2228 return player_url
2229
2230 def _download_player_url(self, video_id, fatal=False):
2231 res = self._download_webpage(
2232 'https://www.youtube.com/iframe_api',
2233 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2234 if res:
2235 player_version = self._search_regex(
2236 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2237 if player_version:
2238 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2239
2240 def _signature_cache_id(self, example_sig):
2241 """ Return a string representation of a signature """
2242 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
2243
2244 @classmethod
2245 def _extract_player_info(cls, player_url):
2246 for player_re in cls._PLAYER_INFO_RE:
2247 id_m = re.search(player_re, player_url)
2248 if id_m:
2249 break
2250 else:
2251 raise ExtractorError('Cannot identify player %r' % player_url)
2252 return id_m.group('id')
2253
2254 def _load_player(self, video_id, player_url, fatal=True):
2255 player_id = self._extract_player_info(player_url)
2256 if player_id not in self._code_cache:
2257 code = self._download_webpage(
2258 player_url, video_id, fatal=fatal,
2259 note='Downloading player ' + player_id,
2260 errnote='Download of %s failed' % player_url)
2261 if code:
2262 self._code_cache[player_id] = code
2263 return self._code_cache.get(player_id)
2264
2265 def _extract_signature_function(self, video_id, player_url, example_sig):
2266 player_id = self._extract_player_info(player_url)
2267
2268 # Read from filesystem cache
2269 func_id = 'js_%s_%s' % (
2270 player_id, self._signature_cache_id(example_sig))
2271 assert os.path.basename(func_id) == func_id
2272
2273 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
2274 if cache_spec is not None:
2275 return lambda s: ''.join(s[i] for i in cache_spec)
2276
2277 code = self._load_player(video_id, player_url)
2278 if code:
2279 res = self._parse_sig_js(code)
2280
2281 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2282 cache_res = res(test_string)
2283 cache_spec = [ord(c) for c in cache_res]
2284
2285 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2286 return res
2287
2288 def _print_sig_code(self, func, example_sig):
2289 if not self.get_param('youtube_print_sig_code'):
2290 return
2291
2292 def gen_sig_code(idxs):
2293 def _genslice(start, end, step):
2294 starts = '' if start == 0 else str(start)
2295 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2296 steps = '' if step == 1 else (':%d' % step)
2297 return 's[%s%s%s]' % (starts, ends, steps)
2298
2299 step = None
2300 # Quelch pyflakes warnings - start will be set when step is set
2301 start = '(Never used)'
2302 for i, prev in zip(idxs[1:], idxs[:-1]):
2303 if step is not None:
2304 if i - prev == step:
2305 continue
2306 yield _genslice(start, prev, step)
2307 step = None
2308 continue
2309 if i - prev in [-1, 1]:
2310 step = i - prev
2311 start = prev
2312 continue
2313 else:
2314 yield 's[%d]' % prev
2315 if step is None:
2316 yield 's[%d]' % i
2317 else:
2318 yield _genslice(start, i, step)
2319
2320 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2321 cache_res = func(test_string)
2322 cache_spec = [ord(c) for c in cache_res]
2323 expr_code = ' + '.join(gen_sig_code(cache_spec))
2324 signature_id_tuple = '(%s)' % (
2325 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
2326 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2327 ' return %s\n') % (signature_id_tuple, expr_code)
2328 self.to_screen('Extracted signature function:\n' + code)
2329
2330 def _parse_sig_js(self, jscode):
2331 funcname = self._search_regex(
2332 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2333 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2334 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2335 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2336 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}\(a,\d+\)',
2337 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\(\s*""\s*\)',
2338 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2339 # Obsolete patterns
2340 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2341 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2342 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2343 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2344 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2345 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2346 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2347 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2348 jscode, 'Initial JS player signature function name', group='sig')
2349
2350 jsi = JSInterpreter(jscode)
2351 initial_function = jsi.extract_function(funcname)
2352 return lambda s: initial_function([s])
2353
2354 def _decrypt_signature(self, s, video_id, player_url):
2355 """Turn the encrypted s field into a working signature"""
2356
2357 if player_url is None:
2358 raise ExtractorError('Cannot decrypt signature without player_url')
2359
2360 try:
2361 player_id = (player_url, self._signature_cache_id(s))
2362 if player_id not in self._player_cache:
2363 func = self._extract_signature_function(
2364 video_id, player_url, s
2365 )
2366 self._player_cache[player_id] = func
2367 func = self._player_cache[player_id]
2368 self._print_sig_code(func, s)
2369 return func(s)
2370 except Exception as e:
2371 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2372
2373 def _decrypt_nsig(self, s, video_id, player_url):
2374 """Turn the encrypted n field into a working signature"""
2375 if player_url is None:
2376 raise ExtractorError('Cannot decrypt nsig without player_url')
2377 if player_url.startswith('//'):
2378 player_url = 'https:' + player_url
2379 elif not re.match(r'https?://', player_url):
2380 player_url = compat_urlparse.urljoin(
2381 'https://www.youtube.com', player_url)
2382
2383 sig_id = ('nsig_value', s)
2384 if sig_id in self._player_cache:
2385 return self._player_cache[sig_id]
2386
2387 try:
2388 player_id = ('nsig', player_url)
2389 if player_id not in self._player_cache:
2390 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2391 func = self._player_cache[player_id]
2392 self._player_cache[sig_id] = func(s)
2393 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2394 return self._player_cache[sig_id]
2395 except Exception as e:
2396 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2397
2398 def _extract_n_function_name(self, jscode):
2399 return self._search_regex(
2400 (r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})\([a-zA-Z0-9]\)',),
2401 jscode, 'Initial JS player n function name', group='nfunc')
2402
2403 def _extract_n_function(self, video_id, player_url):
2404 player_id = self._extract_player_info(player_url)
2405 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2406
2407 if func_code:
2408 jsi = JSInterpreter(func_code)
2409 else:
2410 jscode = self._load_player(video_id, player_url)
2411 funcname = self._extract_n_function_name(jscode)
2412 jsi = JSInterpreter(jscode)
2413 func_code = jsi.extract_function_code(funcname)
2414 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2415
2416 if self.get_param('youtube_print_sig_code'):
2417 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2418
2419 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2420
2421 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2422 """
2423 Extract signatureTimestamp (sts)
2424 Required to tell API what sig/player version is in use.
2425 """
2426 sts = None
2427 if isinstance(ytcfg, dict):
2428 sts = int_or_none(ytcfg.get('STS'))
2429
2430 if not sts:
2431 # Attempt to extract from player
2432 if player_url is None:
2433 error_msg = 'Cannot extract signature timestamp without player_url.'
2434 if fatal:
2435 raise ExtractorError(error_msg)
2436 self.report_warning(error_msg)
2437 return
2438 code = self._load_player(video_id, player_url, fatal=fatal)
2439 if code:
2440 sts = int_or_none(self._search_regex(
2441 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2442 'JS player signature timestamp', group='sts', fatal=fatal))
2443 return sts
2444
2445 def _mark_watched(self, video_id, player_responses):
2446 playback_url = get_first(
2447 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2448 expected_type=url_or_none)
2449 if not playback_url:
2450 self.report_warning('Unable to mark watched')
2451 return
2452 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2453 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2454
2455 # cpn generation algorithm is reverse engineered from base.js.
2456 # In fact it works even with dummy cpn.
2457 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2458 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2459
2460 qs.update({
2461 'ver': ['2'],
2462 'cpn': [cpn],
2463 })
2464 playback_url = compat_urlparse.urlunparse(
2465 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2466
2467 self._download_webpage(
2468 playback_url, video_id, 'Marking watched',
2469 'Unable to mark watched', fatal=False)
2470
2471 @staticmethod
2472 def _extract_urls(webpage):
2473 # Embedded YouTube player
2474 entries = [
2475 unescapeHTML(mobj.group('url'))
2476 for mobj in re.finditer(r'''(?x)
2477 (?:
2478 <iframe[^>]+?src=|
2479 data-video-url=|
2480 <embed[^>]+?src=|
2481 embedSWF\(?:\s*|
2482 <object[^>]+data=|
2483 new\s+SWFObject\(
2484 )
2485 (["\'])
2486 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2487 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2488 \1''', webpage)]
2489
2490 # lazyYT YouTube embed
2491 entries.extend(list(map(
2492 unescapeHTML,
2493 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2494
2495 # Wordpress "YouTube Video Importer" plugin
2496 matches = re.findall(r'''(?x)<div[^>]+
2497 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2498 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2499 entries.extend(m[-1] for m in matches)
2500
2501 return entries
2502
2503 @staticmethod
2504 def _extract_url(webpage):
2505 urls = YoutubeIE._extract_urls(webpage)
2506 return urls[0] if urls else None
2507
2508 @classmethod
2509 def extract_id(cls, url):
2510 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2511 if mobj is None:
2512 raise ExtractorError('Invalid URL: %s' % url)
2513 return mobj.group('id')
2514
2515 def _extract_chapters_from_json(self, data, duration):
2516 chapter_list = traverse_obj(
2517 data, (
2518 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2519 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2520 ), expected_type=list)
2521
2522 return self._extract_chapters(
2523 chapter_list,
2524 chapter_time=lambda chapter: float_or_none(
2525 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2526 chapter_title=lambda chapter: traverse_obj(
2527 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2528 duration=duration)
2529
2530 def _extract_chapters_from_engagement_panel(self, data, duration):
2531 content_list = traverse_obj(
2532 data,
2533 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2534 expected_type=list, default=[])
2535 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2536 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2537
2538 return next((
2539 filter(None, (
2540 self._extract_chapters(
2541 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2542 chapter_time, chapter_title, duration)
2543 for contents in content_list
2544 ))), [])
2545
2546 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2547 chapters = []
2548 last_chapter = {'start_time': 0}
2549 for idx, chapter in enumerate(chapter_list or []):
2550 title = chapter_title(chapter)
2551 start_time = chapter_time(chapter)
2552 if start_time is None:
2553 continue
2554 last_chapter['end_time'] = start_time
2555 if start_time < last_chapter['start_time']:
2556 if idx == 1:
2557 chapters.pop()
2558 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2559 else:
2560 self.report_warning(f'Invalid start time for chapter "{title}"')
2561 continue
2562 last_chapter = {'start_time': start_time, 'title': title}
2563 chapters.append(last_chapter)
2564 last_chapter['end_time'] = duration
2565 return chapters
2566
2567 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2568 return self._parse_json(self._search_regex(
2569 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2570 regex), webpage, name, default='{}'), video_id, fatal=False)
2571
2572 def _extract_comment(self, comment_renderer, parent=None):
2573 comment_id = comment_renderer.get('commentId')
2574 if not comment_id:
2575 return
2576
2577 text = self._get_text(comment_renderer, 'contentText')
2578
2579 # note: timestamp is an estimate calculated from the current time and time_text
2580 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2581 author = self._get_text(comment_renderer, 'authorText')
2582 author_id = try_get(comment_renderer,
2583 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2584
2585 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2586 lambda x: x['likeCount']), compat_str)) or 0
2587 author_thumbnail = try_get(comment_renderer,
2588 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2589
2590 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2591 is_favorited = 'creatorHeart' in (try_get(
2592 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2593 return {
2594 'id': comment_id,
2595 'text': text,
2596 'timestamp': timestamp,
2597 'time_text': time_text,
2598 'like_count': votes,
2599 'is_favorited': is_favorited,
2600 'author': author,
2601 'author_id': author_id,
2602 'author_thumbnail': author_thumbnail,
2603 'author_is_uploader': author_is_uploader,
2604 'parent': parent or 'root'
2605 }
2606
2607 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2608
2609 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2610
2611 def extract_header(contents):
2612 _continuation = None
2613 for content in contents:
2614 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2615 expected_comment_count = self._get_count(
2616 comments_header_renderer, 'countText', 'commentsCount')
2617
2618 if expected_comment_count:
2619 tracker['est_total'] = expected_comment_count
2620 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2621 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2622
2623 sort_menu_item = try_get(
2624 comments_header_renderer,
2625 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2626 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2627
2628 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2629 if not _continuation:
2630 continue
2631
2632 sort_text = str_or_none(sort_menu_item.get('title'))
2633 if not sort_text:
2634 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2635 self.to_screen('Sorting comments by %s' % sort_text.lower())
2636 break
2637 return _continuation
2638
2639 def extract_thread(contents):
2640 if not parent:
2641 tracker['current_page_thread'] = 0
2642 for content in contents:
2643 if not parent and tracker['total_parent_comments'] >= max_parents:
2644 yield
2645 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2646 comment_renderer = get_first(
2647 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2648 expected_type=dict, default={})
2649
2650 comment = self._extract_comment(comment_renderer, parent)
2651 if not comment:
2652 continue
2653
2654 tracker['running_total'] += 1
2655 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2656 yield comment
2657
2658 # Attempt to get the replies
2659 comment_replies_renderer = try_get(
2660 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2661
2662 if comment_replies_renderer:
2663 tracker['current_page_thread'] += 1
2664 comment_entries_iter = self._comment_entries(
2665 comment_replies_renderer, ytcfg, video_id,
2666 parent=comment.get('id'), tracker=tracker)
2667 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2668 yield reply_comment
2669
2670 # Keeps track of counts across recursive calls
2671 if not tracker:
2672 tracker = dict(
2673 running_total=0,
2674 est_total=0,
2675 current_page_thread=0,
2676 total_parent_comments=0,
2677 total_reply_comments=0)
2678
2679 # TODO: Deprecated
2680 # YouTube comments have a max depth of 2
2681 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2682 if max_depth:
2683 self._downloader.deprecation_warning(
2684 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2685 if max_depth == 1 and parent:
2686 return
2687
2688 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2689 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2690
2691 continuation = self._extract_continuation(root_continuation_data)
2692 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2693 if message and not parent:
2694 self.report_warning(message, video_id=video_id)
2695
2696 response = None
2697 is_first_continuation = parent is None
2698
2699 for page_num in itertools.count(0):
2700 if not continuation:
2701 break
2702 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2703 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2704 if page_num == 0:
2705 if is_first_continuation:
2706 note_prefix = 'Downloading comment section API JSON'
2707 else:
2708 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2709 tracker['current_page_thread'], comment_prog_str)
2710 else:
2711 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2712 ' ' if parent else '', ' replies' if parent else '',
2713 page_num, comment_prog_str)
2714
2715 response = self._extract_response(
2716 item_id=None, query=continuation,
2717 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2718 check_get_keys='onResponseReceivedEndpoints')
2719
2720 continuation_contents = traverse_obj(
2721 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2722
2723 continuation = None
2724 for continuation_section in continuation_contents:
2725 continuation_items = traverse_obj(
2726 continuation_section,
2727 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2728 get_all=False, expected_type=list) or []
2729 if is_first_continuation:
2730 continuation = extract_header(continuation_items)
2731 is_first_continuation = False
2732 if continuation:
2733 break
2734 continue
2735
2736 for entry in extract_thread(continuation_items):
2737 if not entry:
2738 return
2739 yield entry
2740 continuation = self._extract_continuation({'contents': continuation_items})
2741 if continuation:
2742 break
2743
2744 def _get_comments(self, ytcfg, video_id, contents, webpage):
2745 """Entry for comment extraction"""
2746 def _real_comment_extract(contents):
2747 renderer = next((
2748 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2749 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2750 yield from self._comment_entries(renderer, ytcfg, video_id)
2751
2752 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2753 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2754
2755 @staticmethod
2756 def _get_checkok_params():
2757 return {'contentCheckOk': True, 'racyCheckOk': True}
2758
2759 @classmethod
2760 def _generate_player_context(cls, sts=None):
2761 context = {
2762 'html5Preference': 'HTML5_PREF_WANTS',
2763 }
2764 if sts is not None:
2765 context['signatureTimestamp'] = sts
2766 return {
2767 'playbackContext': {
2768 'contentPlaybackContext': context
2769 },
2770 **cls._get_checkok_params()
2771 }
2772
2773 @staticmethod
2774 def _is_agegated(player_response):
2775 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2776 return True
2777
2778 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2779 AGE_GATE_REASONS = (
2780 'confirm your age', 'age-restricted', 'inappropriate', # reason
2781 'age_verification_required', 'age_check_required', # status
2782 )
2783 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2784
2785 @staticmethod
2786 def _is_unplayable(player_response):
2787 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2788
2789 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2790
2791 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2792 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2793 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2794 headers = self.generate_api_headers(
2795 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2796
2797 yt_query = {'videoId': video_id}
2798 yt_query.update(self._generate_player_context(sts))
2799 return self._extract_response(
2800 item_id=video_id, ep='player', query=yt_query,
2801 ytcfg=player_ytcfg, headers=headers, fatal=True,
2802 default_client=client,
2803 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2804 ) or None
2805
2806 def _get_requested_clients(self, url, smuggled_data):
2807 requested_clients = []
2808 default = ['android', 'web']
2809 allowed_clients = sorted(
2810 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2811 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2812 for client in self._configuration_arg('player_client'):
2813 if client in allowed_clients:
2814 requested_clients.append(client)
2815 elif client == 'default':
2816 requested_clients.extend(default)
2817 elif client == 'all':
2818 requested_clients.extend(allowed_clients)
2819 else:
2820 self.report_warning(f'Skipping unsupported client {client}')
2821 if not requested_clients:
2822 requested_clients = default
2823
2824 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2825 requested_clients.extend(
2826 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2827
2828 return orderedSet(requested_clients)
2829
2830 def _extract_player_ytcfg(self, client, video_id):
2831 url = {
2832 'web_music': 'https://music.youtube.com',
2833 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2834 }.get(client)
2835 if not url:
2836 return {}
2837 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
2838 return self.extract_ytcfg(video_id, webpage) or {}
2839
2840 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2841 initial_pr = None
2842 if webpage:
2843 initial_pr = self._extract_yt_initial_variable(
2844 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2845 video_id, 'initial player response')
2846
2847 original_clients = clients
2848 clients = clients[::-1]
2849 prs = []
2850
2851 def append_client(client_name):
2852 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2853 clients.append(client_name)
2854
2855 # Android player_response does not have microFormats which are needed for
2856 # extraction of some data. So we return the initial_pr with formats
2857 # stripped out even if not requested by the user
2858 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2859 if initial_pr:
2860 pr = dict(initial_pr)
2861 pr['streamingData'] = None
2862 prs.append(pr)
2863
2864 last_error = None
2865 tried_iframe_fallback = False
2866 player_url = None
2867 while clients:
2868 client = clients.pop()
2869 player_ytcfg = master_ytcfg if client == 'web' else {}
2870 if 'configs' not in self._configuration_arg('player_skip'):
2871 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
2872
2873 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2874 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2875 if 'js' in self._configuration_arg('player_skip'):
2876 require_js_player = False
2877 player_url = None
2878
2879 if not player_url and not tried_iframe_fallback and require_js_player:
2880 player_url = self._download_player_url(video_id)
2881 tried_iframe_fallback = True
2882
2883 try:
2884 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
2885 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
2886 except ExtractorError as e:
2887 if last_error:
2888 self.report_warning(last_error)
2889 last_error = e
2890 continue
2891
2892 if pr:
2893 prs.append(pr)
2894
2895 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
2896 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
2897 append_client(client.replace('_agegate', '_creator'))
2898 elif self._is_agegated(pr):
2899 append_client(f'{client}_agegate')
2900
2901 if last_error:
2902 if not len(prs):
2903 raise last_error
2904 self.report_warning(last_error)
2905 return prs, player_url
2906
2907 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2908 itags, stream_ids = {}, []
2909 itag_qualities, res_qualities = {}, {}
2910 q = qualities([
2911 # Normally tiny is the smallest video-only formats. But
2912 # audio-only formats with unknown quality may get tagged as tiny
2913 'tiny',
2914 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2915 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2916 ])
2917 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
2918
2919 for fmt in streaming_formats:
2920 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2921 continue
2922
2923 itag = str_or_none(fmt.get('itag'))
2924 audio_track = fmt.get('audioTrack') or {}
2925 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2926 if stream_id in stream_ids:
2927 continue
2928
2929 quality = fmt.get('quality')
2930 height = int_or_none(fmt.get('height'))
2931 if quality == 'tiny' or not quality:
2932 quality = fmt.get('audioQuality', '').lower() or quality
2933 # The 3gp format (17) in android client has a quality of "small",
2934 # but is actually worse than other formats
2935 if itag == '17':
2936 quality = 'tiny'
2937 if quality:
2938 if itag:
2939 itag_qualities[itag] = quality
2940 if height:
2941 res_qualities[height] = quality
2942 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2943 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2944 # number of fragment that would subsequently requested with (`&sq=N`)
2945 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2946 continue
2947
2948 fmt_url = fmt.get('url')
2949 if not fmt_url:
2950 sc = compat_parse_qs(fmt.get('signatureCipher'))
2951 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2952 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2953 if not (sc and fmt_url and encrypted_sig):
2954 continue
2955 if not player_url:
2956 continue
2957 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2958 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2959 fmt_url += '&' + sp + '=' + signature
2960
2961 query = parse_qs(fmt_url)
2962 throttled = False
2963 if query.get('n'):
2964 try:
2965 fmt_url = update_url_query(fmt_url, {
2966 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2967 except ExtractorError as e:
2968 self.report_warning(
2969 f'nsig extraction failed: You may experience throttling for some formats\n'
2970 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
2971 throttled = True
2972
2973 if itag:
2974 itags[itag] = 'https'
2975 stream_ids.append(stream_id)
2976
2977 tbr = float_or_none(
2978 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
2979 dct = {
2980 'asr': int_or_none(fmt.get('audioSampleRate')),
2981 'filesize': int_or_none(fmt.get('contentLength')),
2982 'format_id': itag,
2983 'format_note': join_nonempty(
2984 '%s%s' % (audio_track.get('displayName') or '',
2985 ' (default)' if audio_track.get('audioIsDefault') else ''),
2986 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
2987 throttled and 'THROTTLED', delim=', '),
2988 'source_preference': -10 if throttled else -1,
2989 'fps': int_or_none(fmt.get('fps')) or None,
2990 'height': height,
2991 'quality': q(quality),
2992 'tbr': tbr,
2993 'url': fmt_url,
2994 'width': int_or_none(fmt.get('width')),
2995 'language': audio_track.get('id', '').split('.')[0],
2996 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
2997 }
2998 mime_mobj = re.match(
2999 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3000 if mime_mobj:
3001 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3002 dct.update(parse_codecs(mime_mobj.group(2)))
3003 no_audio = dct.get('acodec') == 'none'
3004 no_video = dct.get('vcodec') == 'none'
3005 if no_audio:
3006 dct['vbr'] = tbr
3007 if no_video:
3008 dct['abr'] = tbr
3009 if no_audio or no_video:
3010 dct['downloader_options'] = {
3011 # Youtube throttles chunks >~10M
3012 'http_chunk_size': 10485760,
3013 }
3014 if dct.get('ext'):
3015 dct['container'] = dct['ext'] + '_dash'
3016 yield dct
3017
3018 live_from_start = is_live and self.get_param('live_from_start')
3019 skip_manifests = self._configuration_arg('skip')
3020 if not self.get_param('youtube_include_hls_manifest', True):
3021 skip_manifests.append('hls')
3022 get_dash = 'dash' not in skip_manifests and (
3023 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3024 get_hls = not live_from_start and 'hls' not in skip_manifests
3025
3026 def process_manifest_format(f, proto, itag):
3027 if itag in itags:
3028 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3029 return False
3030 itag = f'{itag}-{proto}'
3031 if itag:
3032 f['format_id'] = itag
3033 itags[itag] = proto
3034
3035 f['quality'] = next((
3036 q(qdict[val])
3037 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3038 if val in qdict), -1)
3039 return True
3040
3041 for sd in streaming_data:
3042 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3043 if hls_manifest_url:
3044 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3045 if process_manifest_format(f, 'hls', self._search_regex(
3046 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3047 yield f
3048
3049 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3050 if dash_manifest_url:
3051 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3052 if process_manifest_format(f, 'dash', f['format_id']):
3053 f['filesize'] = int_or_none(self._search_regex(
3054 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3055 if live_from_start:
3056 f['is_from_start'] = True
3057
3058 yield f
3059
3060 def _extract_storyboard(self, player_responses, duration):
3061 spec = get_first(
3062 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3063 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3064 if not base_url:
3065 return
3066 L = len(spec) - 1
3067 for i, args in enumerate(spec):
3068 args = args.split('#')
3069 counts = list(map(int_or_none, args[:5]))
3070 if len(args) != 8 or not all(counts):
3071 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3072 continue
3073 width, height, frame_count, cols, rows = counts
3074 N, sigh = args[6:]
3075
3076 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3077 fragment_count = frame_count / (cols * rows)
3078 fragment_duration = duration / fragment_count
3079 yield {
3080 'format_id': f'sb{i}',
3081 'format_note': 'storyboard',
3082 'ext': 'mhtml',
3083 'protocol': 'mhtml',
3084 'acodec': 'none',
3085 'vcodec': 'none',
3086 'url': url,
3087 'width': width,
3088 'height': height,
3089 'fragments': [{
3090 'path': url.replace('$M', str(j)),
3091 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3092 } for j in range(math.ceil(fragment_count))],
3093 }
3094
3095 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3096 webpage = None
3097 if 'webpage' not in self._configuration_arg('player_skip'):
3098 webpage = self._download_webpage(
3099 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3100
3101 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3102
3103 player_responses, player_url = self._extract_player_responses(
3104 self._get_requested_clients(url, smuggled_data),
3105 video_id, webpage, master_ytcfg)
3106
3107 return webpage, master_ytcfg, player_responses, player_url
3108
3109 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3110 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3111 is_live = get_first(video_details, 'isLive')
3112 if is_live is None:
3113 is_live = get_first(live_broadcast_details, 'isLiveNow')
3114
3115 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3116 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3117
3118 return live_broadcast_details, is_live, streaming_data, formats
3119
3120 def _real_extract(self, url):
3121 url, smuggled_data = unsmuggle_url(url, {})
3122 video_id = self._match_id(url)
3123
3124 base_url = self.http_scheme() + '//www.youtube.com/'
3125 webpage_url = base_url + 'watch?v=' + video_id
3126
3127 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3128
3129 playability_statuses = traverse_obj(
3130 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3131
3132 trailer_video_id = get_first(
3133 playability_statuses,
3134 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3135 expected_type=str)
3136 if trailer_video_id:
3137 return self.url_result(
3138 trailer_video_id, self.ie_key(), trailer_video_id)
3139
3140 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3141 if webpage else (lambda x: None))
3142
3143 video_details = traverse_obj(
3144 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3145 microformats = traverse_obj(
3146 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3147 expected_type=dict, default=[])
3148 video_title = (
3149 get_first(video_details, 'title')
3150 or self._get_text(microformats, (..., 'title'))
3151 or search_meta(['og:title', 'twitter:title', 'title']))
3152 video_description = get_first(video_details, 'shortDescription')
3153
3154 multifeed_metadata_list = get_first(
3155 player_responses,
3156 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3157 expected_type=str)
3158 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3159 if self.get_param('noplaylist'):
3160 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3161 else:
3162 entries = []
3163 feed_ids = []
3164 for feed in multifeed_metadata_list.split(','):
3165 # Unquote should take place before split on comma (,) since textual
3166 # fields may contain comma as well (see
3167 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3168 feed_data = compat_parse_qs(
3169 compat_urllib_parse_unquote_plus(feed))
3170
3171 def feed_entry(name):
3172 return try_get(
3173 feed_data, lambda x: x[name][0], compat_str)
3174
3175 feed_id = feed_entry('id')
3176 if not feed_id:
3177 continue
3178 feed_title = feed_entry('title')
3179 title = video_title
3180 if feed_title:
3181 title += ' (%s)' % feed_title
3182 entries.append({
3183 '_type': 'url_transparent',
3184 'ie_key': 'Youtube',
3185 'url': smuggle_url(
3186 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3187 {'force_singlefeed': True}),
3188 'title': title,
3189 })
3190 feed_ids.append(feed_id)
3191 self.to_screen(
3192 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3193 % (', '.join(feed_ids), video_id))
3194 return self.playlist_result(
3195 entries, video_id, video_title, video_description)
3196
3197 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
3198
3199 if not formats:
3200 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3201 self.report_drm(video_id)
3202 pemr = get_first(
3203 playability_statuses,
3204 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3205 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3206 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3207 if subreason:
3208 if subreason == 'The uploader has not made this video available in your country.':
3209 countries = get_first(microformats, 'availableCountries')
3210 if not countries:
3211 regions_allowed = search_meta('regionsAllowed')
3212 countries = regions_allowed.split(',') if regions_allowed else None
3213 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3214 reason += f'. {subreason}'
3215 if reason:
3216 self.raise_no_formats(reason, expected=True)
3217
3218 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3219 if not keywords and webpage:
3220 keywords = [
3221 unescapeHTML(m.group('content'))
3222 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3223 for keyword in keywords:
3224 if keyword.startswith('yt:stretch='):
3225 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3226 if mobj:
3227 # NB: float is intentional for forcing float division
3228 w, h = (float(v) for v in mobj.groups())
3229 if w > 0 and h > 0:
3230 ratio = w / h
3231 for f in formats:
3232 if f.get('vcodec') != 'none':
3233 f['stretched_ratio'] = ratio
3234 break
3235 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3236 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3237 if thumbnail_url:
3238 thumbnails.append({
3239 'url': thumbnail_url,
3240 })
3241 original_thumbnails = thumbnails.copy()
3242
3243 # The best resolution thumbnails sometimes does not appear in the webpage
3244 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3245 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3246 thumbnail_names = [
3247 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3248 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3249 'mqdefault', 'mq1', 'mq2', 'mq3',
3250 'default', '1', '2', '3'
3251 ]
3252 n_thumbnail_names = len(thumbnail_names)
3253 thumbnails.extend({
3254 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3255 video_id=video_id, name=name, ext=ext,
3256 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3257 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3258 for thumb in thumbnails:
3259 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3260 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3261 self._remove_duplicate_formats(thumbnails)
3262 self._downloader._sort_thumbnails(original_thumbnails)
3263
3264 category = get_first(microformats, 'category') or search_meta('genre')
3265 channel_id = str_or_none(
3266 get_first(video_details, 'channelId')
3267 or get_first(microformats, 'externalChannelId')
3268 or search_meta('channelId'))
3269 duration = int_or_none(
3270 get_first(video_details, 'lengthSeconds')
3271 or get_first(microformats, 'lengthSeconds')
3272 or parse_duration(search_meta('duration'))) or None
3273 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3274
3275 live_content = get_first(video_details, 'isLiveContent')
3276 is_upcoming = get_first(video_details, 'isUpcoming')
3277 if is_live is None:
3278 if is_upcoming or live_content is False:
3279 is_live = False
3280 if is_upcoming is None and (live_content or is_live):
3281 is_upcoming = False
3282 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3283 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3284 if not duration and live_end_time and live_start_time:
3285 duration = live_end_time - live_start_time
3286
3287 if is_live and self.get_param('live_from_start'):
3288 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3289
3290 formats.extend(self._extract_storyboard(player_responses, duration))
3291
3292 # Source is given priority since formats that throttle are given lower source_preference
3293 # When throttling issue is fully fixed, remove this
3294 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3295
3296 info = {
3297 'id': video_id,
3298 'title': video_title,
3299 'formats': formats,
3300 'thumbnails': thumbnails,
3301 # The best thumbnail that we are sure exists. Prevents unnecessary
3302 # URL checking if user don't care about getting the best possible thumbnail
3303 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3304 'description': video_description,
3305 'upload_date': unified_strdate(
3306 get_first(microformats, 'uploadDate')
3307 or search_meta('uploadDate')),
3308 'uploader': get_first(video_details, 'author'),
3309 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3310 'uploader_url': owner_profile_url,
3311 'channel_id': channel_id,
3312 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
3313 'duration': duration,
3314 'view_count': int_or_none(
3315 get_first((video_details, microformats), (..., 'viewCount'))
3316 or search_meta('interactionCount')),
3317 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3318 'age_limit': 18 if (
3319 get_first(microformats, 'isFamilySafe') is False
3320 or search_meta('isFamilyFriendly') == 'false'
3321 or search_meta('og:restrictions:age') == '18+') else 0,
3322 'webpage_url': webpage_url,
3323 'categories': [category] if category else None,
3324 'tags': keywords,
3325 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3326 'is_live': is_live,
3327 'was_live': (False if is_live or is_upcoming or live_content is False
3328 else None if is_live is None or is_upcoming is None
3329 else live_content),
3330 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3331 'release_timestamp': live_start_time,
3332 }
3333
3334 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3335 if pctr:
3336 def get_lang_code(track):
3337 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3338 or track.get('languageCode'))
3339
3340 # Converted into dicts to remove duplicates
3341 captions = {
3342 get_lang_code(sub): sub
3343 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3344 translation_languages = {
3345 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3346 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3347
3348 def process_language(container, base_url, lang_code, sub_name, query):
3349 lang_subs = container.setdefault(lang_code, [])
3350 for fmt in self._SUBTITLE_FORMATS:
3351 query.update({
3352 'fmt': fmt,
3353 })
3354 lang_subs.append({
3355 'ext': fmt,
3356 'url': update_url_query(base_url, query),
3357 'name': sub_name,
3358 })
3359
3360 subtitles, automatic_captions = {}, {}
3361 for lang_code, caption_track in captions.items():
3362 base_url = caption_track.get('baseUrl')
3363 if not base_url:
3364 continue
3365 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3366 if caption_track.get('kind') != 'asr':
3367 if not lang_code:
3368 continue
3369 process_language(
3370 subtitles, base_url, lang_code, lang_name, {})
3371 if not caption_track.get('isTranslatable'):
3372 continue
3373 for trans_code, trans_name in translation_languages.items():
3374 if not trans_code:
3375 continue
3376 if caption_track.get('kind') != 'asr':
3377 trans_code += f'-{lang_code}'
3378 trans_name += format_field(lang_name, template=' from %s')
3379 process_language(
3380 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3381 info['automatic_captions'] = automatic_captions
3382 info['subtitles'] = subtitles
3383
3384 parsed_url = compat_urllib_parse_urlparse(url)
3385 for component in [parsed_url.fragment, parsed_url.query]:
3386 query = compat_parse_qs(component)
3387 for k, v in query.items():
3388 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3389 d_k += '_time'
3390 if d_k not in info and k in s_ks:
3391 info[d_k] = parse_duration(query[k][0])
3392
3393 # Youtube Music Auto-generated description
3394 if video_description:
3395 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)
3396 if mobj:
3397 release_year = mobj.group('release_year')
3398 release_date = mobj.group('release_date')
3399 if release_date:
3400 release_date = release_date.replace('-', '')
3401 if not release_year:
3402 release_year = release_date[:4]
3403 info.update({
3404 'album': mobj.group('album'.strip()),
3405 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3406 'track': mobj.group('track').strip(),
3407 'release_date': release_date,
3408 'release_year': int_or_none(release_year),
3409 })
3410
3411 initial_data = None
3412 if webpage:
3413 initial_data = self._extract_yt_initial_variable(
3414 webpage, self._YT_INITIAL_DATA_RE, video_id,
3415 'yt initial data')
3416 if not initial_data:
3417 query = {'videoId': video_id}
3418 query.update(self._get_checkok_params())
3419 initial_data = self._extract_response(
3420 item_id=video_id, ep='next', fatal=False,
3421 ytcfg=master_ytcfg, query=query,
3422 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3423 note='Downloading initial data API JSON')
3424
3425 try:
3426 # This will error if there is no livechat
3427 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3428 info.setdefault('subtitles', {})['live_chat'] = [{
3429 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3430 'video_id': video_id,
3431 'ext': 'json',
3432 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3433 }]
3434 except (KeyError, IndexError, TypeError):
3435 pass
3436
3437 if initial_data:
3438 info['chapters'] = (
3439 self._extract_chapters_from_json(initial_data, duration)
3440 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3441 or None)
3442
3443 contents = try_get(
3444 initial_data,
3445 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3446 list) or []
3447 for content in contents:
3448 vpir = content.get('videoPrimaryInfoRenderer')
3449 if vpir:
3450 stl = vpir.get('superTitleLink')
3451 if stl:
3452 stl = self._get_text(stl)
3453 if try_get(
3454 vpir,
3455 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3456 info['location'] = stl
3457 else:
3458 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3459 if mobj:
3460 info.update({
3461 'series': mobj.group(1),
3462 'season_number': int(mobj.group(2)),
3463 'episode_number': int(mobj.group(3)),
3464 })
3465 for tlb in (try_get(
3466 vpir,
3467 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3468 list) or []):
3469 tbr = tlb.get('toggleButtonRenderer') or {}
3470 for getter, regex in [(
3471 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3472 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3473 lambda x: x['accessibility'],
3474 lambda x: x['accessibilityData']['accessibilityData'],
3475 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3476 label = (try_get(tbr, getter, dict) or {}).get('label')
3477 if label:
3478 mobj = re.match(regex, label)
3479 if mobj:
3480 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3481 break
3482 sbr_tooltip = try_get(
3483 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3484 if sbr_tooltip:
3485 like_count, dislike_count = sbr_tooltip.split(' / ')
3486 info.update({
3487 'like_count': str_to_int(like_count),
3488 'dislike_count': str_to_int(dislike_count),
3489 })
3490 vsir = content.get('videoSecondaryInfoRenderer')
3491 if vsir:
3492 info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title'))
3493 rows = try_get(
3494 vsir,
3495 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3496 list) or []
3497 multiple_songs = False
3498 for row in rows:
3499 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3500 multiple_songs = True
3501 break
3502 for row in rows:
3503 mrr = row.get('metadataRowRenderer') or {}
3504 mrr_title = mrr.get('title')
3505 if not mrr_title:
3506 continue
3507 mrr_title = self._get_text(mrr, 'title')
3508 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3509 if mrr_title == 'License':
3510 info['license'] = mrr_contents_text
3511 elif not multiple_songs:
3512 if mrr_title == 'Album':
3513 info['album'] = mrr_contents_text
3514 elif mrr_title == 'Artist':
3515 info['artist'] = mrr_contents_text
3516 elif mrr_title == 'Song':
3517 info['track'] = mrr_contents_text
3518
3519 fallbacks = {
3520 'channel': 'uploader',
3521 'channel_id': 'uploader_id',
3522 'channel_url': 'uploader_url',
3523 }
3524 for to, frm in fallbacks.items():
3525 if not info.get(to):
3526 info[to] = info.get(frm)
3527
3528 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3529 v = info.get(s_k)
3530 if v:
3531 info[d_k] = v
3532
3533 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3534 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3535 is_membersonly = None
3536 is_premium = None
3537 if initial_data and is_private is not None:
3538 is_membersonly = False
3539 is_premium = False
3540 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3541 badge_labels = set()
3542 for content in contents:
3543 if not isinstance(content, dict):
3544 continue
3545 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3546 for badge_label in badge_labels:
3547 if badge_label.lower() == 'members only':
3548 is_membersonly = True
3549 elif badge_label.lower() == 'premium':
3550 is_premium = True
3551 elif badge_label.lower() == 'unlisted':
3552 is_unlisted = True
3553
3554 info['availability'] = self._availability(
3555 is_private=is_private,
3556 needs_premium=is_premium,
3557 needs_subscription=is_membersonly,
3558 needs_auth=info['age_limit'] >= 18,
3559 is_unlisted=None if is_private is None else is_unlisted)
3560
3561 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3562
3563 self.mark_watched(video_id, player_responses)
3564
3565 return info
3566
3567
3568class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3569
3570 def _extract_channel_id(self, webpage):
3571 channel_id = self._html_search_meta(
3572 'channelId', webpage, 'channel id', default=None)
3573 if channel_id:
3574 return channel_id
3575 channel_url = self._html_search_meta(
3576 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3577 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3578 'twitter:app:url:googleplay'), webpage, 'channel url')
3579 return self._search_regex(
3580 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3581 channel_url, 'channel id')
3582
3583 @staticmethod
3584 def _extract_basic_item_renderer(item):
3585 # Modified from _extract_grid_item_renderer
3586 known_basic_renderers = (
3587 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3588 )
3589 for key, renderer in item.items():
3590 if not isinstance(renderer, dict):
3591 continue
3592 elif key in known_basic_renderers:
3593 return renderer
3594 elif key.startswith('grid') and key.endswith('Renderer'):
3595 return renderer
3596
3597 def _grid_entries(self, grid_renderer):
3598 for item in grid_renderer['items']:
3599 if not isinstance(item, dict):
3600 continue
3601 renderer = self._extract_basic_item_renderer(item)
3602 if not isinstance(renderer, dict):
3603 continue
3604 title = self._get_text(renderer, 'title')
3605
3606 # playlist
3607 playlist_id = renderer.get('playlistId')
3608 if playlist_id:
3609 yield self.url_result(
3610 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3611 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3612 video_title=title)
3613 continue
3614 # video
3615 video_id = renderer.get('videoId')
3616 if video_id:
3617 yield self._extract_video(renderer)
3618 continue
3619 # channel
3620 channel_id = renderer.get('channelId')
3621 if channel_id:
3622 yield self.url_result(
3623 'https://www.youtube.com/channel/%s' % channel_id,
3624 ie=YoutubeTabIE.ie_key(), video_title=title)
3625 continue
3626 # generic endpoint URL support
3627 ep_url = urljoin('https://www.youtube.com/', try_get(
3628 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3629 compat_str))
3630 if ep_url:
3631 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3632 if ie.suitable(ep_url):
3633 yield self.url_result(
3634 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3635 break
3636
3637 def _shelf_entries_from_content(self, shelf_renderer):
3638 content = shelf_renderer.get('content')
3639 if not isinstance(content, dict):
3640 return
3641 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3642 if renderer:
3643 # TODO: add support for nested playlists so each shelf is processed
3644 # as separate playlist
3645 # TODO: this includes only first N items
3646 for entry in self._grid_entries(renderer):
3647 yield entry
3648 renderer = content.get('horizontalListRenderer')
3649 if renderer:
3650 # TODO
3651 pass
3652
3653 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3654 ep = try_get(
3655 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3656 compat_str)
3657 shelf_url = urljoin('https://www.youtube.com', ep)
3658 if shelf_url:
3659 # Skipping links to another channels, note that checking for
3660 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3661 # will not work
3662 if skip_channels and '/channels?' in shelf_url:
3663 return
3664 title = self._get_text(shelf_renderer, 'title')
3665 yield self.url_result(shelf_url, video_title=title)
3666 # Shelf may not contain shelf URL, fallback to extraction from content
3667 for entry in self._shelf_entries_from_content(shelf_renderer):
3668 yield entry
3669
3670 def _playlist_entries(self, video_list_renderer):
3671 for content in video_list_renderer['contents']:
3672 if not isinstance(content, dict):
3673 continue
3674 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3675 if not isinstance(renderer, dict):
3676 continue
3677 video_id = renderer.get('videoId')
3678 if not video_id:
3679 continue
3680 yield self._extract_video(renderer)
3681
3682 def _rich_entries(self, rich_grid_renderer):
3683 renderer = try_get(
3684 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3685 video_id = renderer.get('videoId')
3686 if not video_id:
3687 return
3688 yield self._extract_video(renderer)
3689
3690 def _video_entry(self, video_renderer):
3691 video_id = video_renderer.get('videoId')
3692 if video_id:
3693 return self._extract_video(video_renderer)
3694
3695 def _post_thread_entries(self, post_thread_renderer):
3696 post_renderer = try_get(
3697 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3698 if not post_renderer:
3699 return
3700 # video attachment
3701 video_renderer = try_get(
3702 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3703 video_id = video_renderer.get('videoId')
3704 if video_id:
3705 entry = self._extract_video(video_renderer)
3706 if entry:
3707 yield entry
3708 # playlist attachment
3709 playlist_id = try_get(
3710 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3711 if playlist_id:
3712 yield self.url_result(
3713 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3714 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3715 # inline video links
3716 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3717 for run in runs:
3718 if not isinstance(run, dict):
3719 continue
3720 ep_url = try_get(
3721 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3722 if not ep_url:
3723 continue
3724 if not YoutubeIE.suitable(ep_url):
3725 continue
3726 ep_video_id = YoutubeIE._match_id(ep_url)
3727 if video_id == ep_video_id:
3728 continue
3729 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3730
3731 def _post_thread_continuation_entries(self, post_thread_continuation):
3732 contents = post_thread_continuation.get('contents')
3733 if not isinstance(contents, list):
3734 return
3735 for content in contents:
3736 renderer = content.get('backstagePostThreadRenderer')
3737 if not isinstance(renderer, dict):
3738 continue
3739 for entry in self._post_thread_entries(renderer):
3740 yield entry
3741
3742 r''' # unused
3743 def _rich_grid_entries(self, contents):
3744 for content in contents:
3745 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3746 if video_renderer:
3747 entry = self._video_entry(video_renderer)
3748 if entry:
3749 yield entry
3750 '''
3751 def _extract_entries(self, parent_renderer, continuation_list):
3752 # continuation_list is modified in-place with continuation_list = [continuation_token]
3753 continuation_list[:] = [None]
3754 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3755 for content in contents:
3756 if not isinstance(content, dict):
3757 continue
3758 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3759 if not is_renderer:
3760 renderer = content.get('richItemRenderer')
3761 if renderer:
3762 for entry in self._rich_entries(renderer):
3763 yield entry
3764 continuation_list[0] = self._extract_continuation(parent_renderer)
3765 continue
3766 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3767 for isr_content in isr_contents:
3768 if not isinstance(isr_content, dict):
3769 continue
3770
3771 known_renderers = {
3772 'playlistVideoListRenderer': self._playlist_entries,
3773 'gridRenderer': self._grid_entries,
3774 'shelfRenderer': lambda x: self._shelf_entries(x),
3775 'backstagePostThreadRenderer': self._post_thread_entries,
3776 'videoRenderer': lambda x: [self._video_entry(x)],
3777 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3778 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
3779 }
3780 for key, renderer in isr_content.items():
3781 if key not in known_renderers:
3782 continue
3783 for entry in known_renderers[key](renderer):
3784 if entry:
3785 yield entry
3786 continuation_list[0] = self._extract_continuation(renderer)
3787 break
3788
3789 if not continuation_list[0]:
3790 continuation_list[0] = self._extract_continuation(is_renderer)
3791
3792 if not continuation_list[0]:
3793 continuation_list[0] = self._extract_continuation(parent_renderer)
3794
3795 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3796 continuation_list = [None]
3797 extract_entries = lambda x: self._extract_entries(x, continuation_list)
3798 tab_content = try_get(tab, lambda x: x['content'], dict)
3799 if not tab_content:
3800 return
3801 parent_renderer = (
3802 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3803 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3804 for entry in extract_entries(parent_renderer):
3805 yield entry
3806 continuation = continuation_list[0]
3807
3808 for page_num in itertools.count(1):
3809 if not continuation:
3810 break
3811 headers = self.generate_api_headers(
3812 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
3813 response = self._extract_response(
3814 item_id='%s page %s' % (item_id, page_num),
3815 query=continuation, headers=headers, ytcfg=ytcfg,
3816 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3817
3818 if not response:
3819 break
3820 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3821 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3822 visitor_data = self._extract_visitor_data(response) or visitor_data
3823
3824 known_continuation_renderers = {
3825 'playlistVideoListContinuation': self._playlist_entries,
3826 'gridContinuation': self._grid_entries,
3827 'itemSectionContinuation': self._post_thread_continuation_entries,
3828 'sectionListContinuation': extract_entries, # for feeds
3829 }
3830 continuation_contents = try_get(
3831 response, lambda x: x['continuationContents'], dict) or {}
3832 continuation_renderer = None
3833 for key, value in continuation_contents.items():
3834 if key not in known_continuation_renderers:
3835 continue
3836 continuation_renderer = value
3837 continuation_list = [None]
3838 for entry in known_continuation_renderers[key](continuation_renderer):
3839 yield entry
3840 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3841 break
3842 if continuation_renderer:
3843 continue
3844
3845 known_renderers = {
3846 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3847 'gridVideoRenderer': (self._grid_entries, 'items'),
3848 'gridChannelRenderer': (self._grid_entries, 'items'),
3849 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3850 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3851 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3852 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3853 }
3854 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3855 continuation_items = try_get(
3856 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3857 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3858 video_items_renderer = None
3859 for key, value in continuation_item.items():
3860 if key not in known_renderers:
3861 continue
3862 video_items_renderer = {known_renderers[key][1]: continuation_items}
3863 continuation_list = [None]
3864 for entry in known_renderers[key][0](video_items_renderer):
3865 yield entry
3866 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3867 break
3868 if video_items_renderer:
3869 continue
3870 break
3871
3872 @staticmethod
3873 def _extract_selected_tab(tabs):
3874 for tab in tabs:
3875 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3876 if renderer.get('selected') is True:
3877 return renderer
3878 else:
3879 raise ExtractorError('Unable to find selected tab')
3880
3881 @classmethod
3882 def _extract_uploader(cls, data):
3883 uploader = {}
3884 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3885 owner = try_get(
3886 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3887 if owner:
3888 uploader['uploader'] = owner.get('text')
3889 uploader['uploader_id'] = try_get(
3890 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3891 uploader['uploader_url'] = urljoin(
3892 'https://www.youtube.com/',
3893 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3894 return {k: v for k, v in uploader.items() if v is not None}
3895
3896 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
3897 playlist_id = title = description = channel_url = channel_name = channel_id = None
3898 tags = []
3899
3900 selected_tab = self._extract_selected_tab(tabs)
3901 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
3902 renderer = try_get(
3903 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3904 if renderer:
3905 channel_name = renderer.get('title')
3906 channel_url = renderer.get('channelUrl')
3907 channel_id = renderer.get('externalId')
3908 else:
3909 renderer = try_get(
3910 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3911
3912 if renderer:
3913 title = renderer.get('title')
3914 description = renderer.get('description', '')
3915 playlist_id = channel_id
3916 tags = renderer.get('keywords', '').split()
3917
3918 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
3919 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
3920 def _get_uncropped(url):
3921 return url_or_none((url or '').split('=')[0] + '=s0')
3922
3923 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
3924 if avatar_thumbnails:
3925 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
3926 if uncropped_avatar:
3927 avatar_thumbnails.append({
3928 'url': uncropped_avatar,
3929 'id': 'avatar_uncropped',
3930 'preference': 1
3931 })
3932
3933 channel_banners = self._extract_thumbnails(
3934 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
3935 for banner in channel_banners:
3936 banner['preference'] = -10
3937
3938 if channel_banners:
3939 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
3940 if uncropped_banner:
3941 channel_banners.append({
3942 'url': uncropped_banner,
3943 'id': 'banner_uncropped',
3944 'preference': -5
3945 })
3946
3947 primary_thumbnails = self._extract_thumbnails(
3948 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
3949
3950 if playlist_id is None:
3951 playlist_id = item_id
3952
3953 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
3954 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
3955 if title is None:
3956 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
3957 title += format_field(selected_tab, 'title', ' - %s')
3958 title += format_field(selected_tab, 'expandedText', ' - %s')
3959
3960 metadata = {
3961 'playlist_id': playlist_id,
3962 'playlist_title': title,
3963 'playlist_description': description,
3964 'uploader': channel_name,
3965 'uploader_id': channel_id,
3966 'uploader_url': channel_url,
3967 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
3968 'tags': tags,
3969 'view_count': self._get_count(playlist_stats, 1),
3970 'availability': self._extract_availability(data),
3971 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
3972 'playlist_count': self._get_count(playlist_stats, 0)
3973 }
3974 if not channel_id:
3975 metadata.update(self._extract_uploader(data))
3976 metadata.update({
3977 'channel': metadata['uploader'],
3978 'channel_id': metadata['uploader_id'],
3979 'channel_url': metadata['uploader_url']})
3980 return self.playlist_result(
3981 self._entries(
3982 selected_tab, playlist_id, ytcfg,
3983 self._extract_account_syncid(ytcfg, data),
3984 self._extract_visitor_data(data, ytcfg)),
3985 **metadata)
3986
3987 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
3988 first_id = last_id = response = None
3989 for page_num in itertools.count(1):
3990 videos = list(self._playlist_entries(playlist))
3991 if not videos:
3992 return
3993 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3994 if start >= len(videos):
3995 return
3996 for video in videos[start:]:
3997 if video['id'] == first_id:
3998 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3999 return
4000 yield video
4001 first_id = first_id or videos[0]['id']
4002 last_id = videos[-1]['id']
4003 watch_endpoint = try_get(
4004 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4005 headers = self.generate_api_headers(
4006 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4007 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4008 query = {
4009 'playlistId': playlist_id,
4010 'videoId': watch_endpoint.get('videoId') or last_id,
4011 'index': watch_endpoint.get('index') or len(videos),
4012 'params': watch_endpoint.get('params') or 'OAE%3D'
4013 }
4014 response = self._extract_response(
4015 item_id='%s page %d' % (playlist_id, page_num),
4016 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4017 check_get_keys='contents'
4018 )
4019 playlist = try_get(
4020 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4021
4022 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4023 title = playlist.get('title') or try_get(
4024 data, lambda x: x['titleText']['simpleText'], compat_str)
4025 playlist_id = playlist.get('playlistId') or item_id
4026
4027 # Delegating everything except mix playlists to regular tab-based playlist URL
4028 playlist_url = urljoin(url, try_get(
4029 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4030 compat_str))
4031 if playlist_url and playlist_url != url:
4032 return self.url_result(
4033 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4034 video_title=title)
4035
4036 return self.playlist_result(
4037 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4038 playlist_id=playlist_id, playlist_title=title)
4039
4040 def _extract_availability(self, data):
4041 """
4042 Gets the availability of a given playlist/tab.
4043 Note: Unless YouTube tells us explicitly, we do not assume it is public
4044 @param data: response
4045 """
4046 is_private = is_unlisted = None
4047 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4048 badge_labels = self._extract_badges(renderer)
4049
4050 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4051 privacy_dropdown_entries = try_get(
4052 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4053 for renderer_dict in privacy_dropdown_entries:
4054 is_selected = try_get(
4055 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4056 if not is_selected:
4057 continue
4058 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4059 if label:
4060 badge_labels.add(label.lower())
4061 break
4062
4063 for badge_label in badge_labels:
4064 if badge_label == 'unlisted':
4065 is_unlisted = True
4066 elif badge_label == 'private':
4067 is_private = True
4068 elif badge_label == 'public':
4069 is_unlisted = is_private = False
4070 return self._availability(is_private, False, False, False, is_unlisted)
4071
4072 @staticmethod
4073 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4074 sidebar_renderer = try_get(
4075 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4076 for item in sidebar_renderer:
4077 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4078 if renderer:
4079 return renderer
4080
4081 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4082 """
4083 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4084 """
4085 browse_id = params = None
4086 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4087 if not renderer:
4088 return
4089 menu_renderer = try_get(
4090 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4091 for menu_item in menu_renderer:
4092 if not isinstance(menu_item, dict):
4093 continue
4094 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4095 text = try_get(
4096 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4097 if not text or text.lower() != 'show unavailable videos':
4098 continue
4099 browse_endpoint = try_get(
4100 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4101 browse_id = browse_endpoint.get('browseId')
4102 params = browse_endpoint.get('params')
4103 break
4104
4105 headers = self.generate_api_headers(
4106 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4107 visitor_data=self._extract_visitor_data(data, ytcfg))
4108 query = {
4109 'params': params or 'wgYCCAA=',
4110 'browseId': browse_id or 'VL%s' % item_id
4111 }
4112 return self._extract_response(
4113 item_id=item_id, headers=headers, query=query,
4114 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4115 note='Downloading API JSON with unavailable videos')
4116
4117 def _extract_webpage(self, url, item_id, fatal=True):
4118 retries = self.get_param('extractor_retries', 3)
4119 count = -1
4120 webpage = data = last_error = None
4121 while count < retries:
4122 count += 1
4123 # Sometimes youtube returns a webpage with incomplete ytInitialData
4124 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4125 if last_error:
4126 self.report_warning('%s. Retrying ...' % last_error)
4127 try:
4128 webpage = self._download_webpage(
4129 url, item_id,
4130 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4131 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4132 except ExtractorError as e:
4133 if isinstance(e.cause, network_exceptions):
4134 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4135 last_error = error_to_compat_str(e.cause or e.msg)
4136 if count < retries:
4137 continue
4138 if fatal:
4139 raise
4140 self.report_warning(error_to_compat_str(e))
4141 break
4142 else:
4143 try:
4144 self._extract_and_report_alerts(data)
4145 except ExtractorError as e:
4146 if fatal:
4147 raise
4148 self.report_warning(error_to_compat_str(e))
4149 break
4150
4151 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4152 break
4153
4154 last_error = 'Incomplete yt initial data received'
4155 if count >= retries:
4156 if fatal:
4157 raise ExtractorError(last_error)
4158 self.report_warning(last_error)
4159 break
4160
4161 return webpage, data
4162
4163 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4164 data = None
4165 if 'webpage' not in self._configuration_arg('skip'):
4166 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4167 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4168 if not data:
4169 if not ytcfg and self.is_authenticated:
4170 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4171 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4172 raise ExtractorError(
4173 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4174 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4175 expected=True)
4176 self.report_warning(msg, only_once=True)
4177 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4178 return data, ytcfg
4179
4180 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4181 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4182 resolve_response = self._extract_response(
4183 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4184 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4185 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4186 for ep_key, ep in endpoints.items():
4187 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4188 if params:
4189 return self._extract_response(
4190 item_id=item_id, query=params, ep=ep, headers=headers,
4191 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4192 check_get_keys=('contents', 'currentVideoEndpoint'))
4193 err_note = 'Failed to resolve url (does the playlist exist?)'
4194 if fatal:
4195 raise ExtractorError(err_note, expected=True)
4196 self.report_warning(err_note, item_id)
4197
4198 @staticmethod
4199 def _smuggle_data(entries, data):
4200 for entry in entries:
4201 if data:
4202 entry['url'] = smuggle_url(entry['url'], data)
4203 yield entry
4204
4205 _SEARCH_PARAMS = None
4206
4207 def _search_results(self, query, params=NO_DEFAULT):
4208 data = {'query': query}
4209 if params is NO_DEFAULT:
4210 params = self._SEARCH_PARAMS
4211 if params:
4212 data['params'] = params
4213 continuation_list = [None]
4214 for page_num in itertools.count(1):
4215 data.update(continuation_list[0] or {})
4216 search = self._extract_response(
4217 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4218 check_get_keys=('contents', 'onResponseReceivedCommands'))
4219 slr_contents = try_get(
4220 search,
4221 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4222 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4223 list)
4224 yield from self._extract_entries({'contents': slr_contents}, continuation_list)
4225 if not continuation_list[0]:
4226 break
4227
4228
4229class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4230 IE_DESC = 'YouTube Tabs'
4231 _VALID_URL = r'''(?x:
4232 https?://
4233 (?:\w+\.)?
4234 (?:
4235 youtube(?:kids)?\.com|
4236 %(invidious)s
4237 )/
4238 (?:
4239 (?P<channel_type>channel|c|user|browse)/|
4240 (?P<not_channel>
4241 feed/|hashtag/|
4242 (?:playlist|watch)\?.*?\blist=
4243 )|
4244 (?!(?:%(reserved_names)s)\b) # Direct URLs
4245 )
4246 (?P<id>[^/?\#&]+)
4247 )''' % {
4248 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4249 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4250 }
4251 IE_NAME = 'youtube:tab'
4252
4253 _TESTS = [{
4254 'note': 'playlists, multipage',
4255 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4256 'playlist_mincount': 94,
4257 'info_dict': {
4258 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4259 'title': 'Igor Kleiner - Playlists',
4260 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4261 'uploader': 'Igor Kleiner',
4262 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4263 'channel': 'Igor Kleiner',
4264 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4265 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4266 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4267 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4268 },
4269 }, {
4270 'note': 'playlists, multipage, different order',
4271 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4272 'playlist_mincount': 94,
4273 'info_dict': {
4274 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4275 'title': 'Igor Kleiner - Playlists',
4276 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4277 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4278 'uploader': 'Igor Kleiner',
4279 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4280 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4281 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4282 'channel': 'Igor Kleiner',
4283 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4284 },
4285 }, {
4286 'note': 'playlists, series',
4287 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4288 'playlist_mincount': 5,
4289 'info_dict': {
4290 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4291 'title': '3Blue1Brown - Playlists',
4292 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4293 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4294 'uploader': '3Blue1Brown',
4295 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4296 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4297 'channel': '3Blue1Brown',
4298 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4299 'tags': ['Mathematics'],
4300 },
4301 }, {
4302 'note': 'playlists, singlepage',
4303 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4304 'playlist_mincount': 4,
4305 'info_dict': {
4306 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4307 'title': 'ThirstForScience - Playlists',
4308 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4309 'uploader': 'ThirstForScience',
4310 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4311 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4312 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4313 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4314 'tags': 'count:13',
4315 'channel': 'ThirstForScience',
4316 }
4317 }, {
4318 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4319 'only_matching': True,
4320 }, {
4321 'note': 'basic, single video playlist',
4322 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4323 'info_dict': {
4324 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4325 'uploader': 'Sergey M.',
4326 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4327 'title': 'youtube-dl public playlist',
4328 'description': '',
4329 'tags': [],
4330 'view_count': int,
4331 'modified_date': '20201130',
4332 'channel': 'Sergey M.',
4333 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4334 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4335 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4336 },
4337 'playlist_count': 1,
4338 }, {
4339 'note': 'empty playlist',
4340 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4341 'info_dict': {
4342 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4343 'uploader': 'Sergey M.',
4344 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4345 'title': 'youtube-dl empty playlist',
4346 'tags': [],
4347 'channel': 'Sergey M.',
4348 'description': '',
4349 'modified_date': '20160902',
4350 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4351 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4352 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4353 },
4354 'playlist_count': 0,
4355 }, {
4356 'note': 'Home tab',
4357 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4358 'info_dict': {
4359 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4360 'title': 'lex will - Home',
4361 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4362 'uploader': 'lex will',
4363 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4364 'channel': 'lex will',
4365 'tags': ['bible', 'history', 'prophesy'],
4366 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4367 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4368 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4369 },
4370 'playlist_mincount': 2,
4371 }, {
4372 'note': 'Videos tab',
4373 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4374 'info_dict': {
4375 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4376 'title': 'lex will - Videos',
4377 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4378 'uploader': 'lex will',
4379 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4380 'tags': ['bible', 'history', 'prophesy'],
4381 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4382 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4383 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4384 'channel': 'lex will',
4385 },
4386 'playlist_mincount': 975,
4387 }, {
4388 'note': 'Videos tab, sorted by popular',
4389 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4390 'info_dict': {
4391 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4392 'title': 'lex will - Videos',
4393 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4394 'uploader': 'lex will',
4395 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4396 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4397 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4398 'channel': 'lex will',
4399 'tags': ['bible', 'history', 'prophesy'],
4400 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4401 },
4402 'playlist_mincount': 199,
4403 }, {
4404 'note': 'Playlists tab',
4405 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4406 'info_dict': {
4407 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4408 'title': 'lex will - Playlists',
4409 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4410 'uploader': 'lex will',
4411 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4412 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4413 'channel': 'lex will',
4414 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4415 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4416 'tags': ['bible', 'history', 'prophesy'],
4417 },
4418 'playlist_mincount': 17,
4419 }, {
4420 'note': 'Community tab',
4421 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4422 'info_dict': {
4423 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4424 'title': 'lex will - Community',
4425 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4426 'uploader': 'lex will',
4427 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4428 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4429 'channel': 'lex will',
4430 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4431 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4432 'tags': ['bible', 'history', 'prophesy'],
4433 },
4434 'playlist_mincount': 18,
4435 }, {
4436 'note': 'Channels tab',
4437 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4438 'info_dict': {
4439 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4440 'title': 'lex will - Channels',
4441 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4442 'uploader': 'lex will',
4443 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4444 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4445 'channel': 'lex will',
4446 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4447 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4448 'tags': ['bible', 'history', 'prophesy'],
4449 },
4450 'playlist_mincount': 12,
4451 }, {
4452 'note': 'Search tab',
4453 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4454 'playlist_mincount': 40,
4455 'info_dict': {
4456 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4457 'title': '3Blue1Brown - Search - linear algebra',
4458 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4459 'uploader': '3Blue1Brown',
4460 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4461 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4462 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4463 'tags': ['Mathematics'],
4464 'channel': '3Blue1Brown',
4465 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4466 },
4467 }, {
4468 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4469 'only_matching': True,
4470 }, {
4471 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4472 'only_matching': True,
4473 }, {
4474 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4475 'only_matching': True,
4476 }, {
4477 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4478 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4479 'info_dict': {
4480 'title': '29C3: Not my department',
4481 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4482 'uploader': 'Christiaan008',
4483 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4484 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4485 'tags': [],
4486 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4487 'view_count': int,
4488 'modified_date': '20150605',
4489 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4490 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4491 'channel': 'Christiaan008',
4492 },
4493 'playlist_count': 96,
4494 }, {
4495 'note': 'Large playlist',
4496 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4497 'info_dict': {
4498 'title': 'Uploads from Cauchemar',
4499 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4500 'uploader': 'Cauchemar',
4501 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4502 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4503 'tags': [],
4504 'modified_date': r're:\d{8}',
4505 'channel': 'Cauchemar',
4506 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4507 'view_count': int,
4508 'description': '',
4509 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4510 },
4511 'playlist_mincount': 1123,
4512 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4513 }, {
4514 'note': 'even larger playlist, 8832 videos',
4515 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4516 'only_matching': True,
4517 }, {
4518 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4519 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4520 'info_dict': {
4521 'title': 'Uploads from Interstellar Movie',
4522 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4523 'uploader': 'Interstellar Movie',
4524 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4525 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4526 'tags': [],
4527 'view_count': int,
4528 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4529 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4530 'channel': 'Interstellar Movie',
4531 'description': '',
4532 'modified_date': r're:\d{8}',
4533 },
4534 'playlist_mincount': 21,
4535 }, {
4536 'note': 'Playlist with "show unavailable videos" button',
4537 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4538 'info_dict': {
4539 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4540 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4541 'uploader': 'Phim Siêu Nhân Nhật Bản',
4542 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4543 'view_count': int,
4544 'channel': 'Phim Siêu Nhân Nhật Bản',
4545 'tags': [],
4546 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4547 'description': '',
4548 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4549 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4550 'modified_date': r're:\d{8}',
4551 },
4552 'playlist_mincount': 200,
4553 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4554 }, {
4555 'note': 'Playlist with unavailable videos in page 7',
4556 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4557 'info_dict': {
4558 'title': 'Uploads from BlankTV',
4559 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4560 'uploader': 'BlankTV',
4561 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4562 'channel': 'BlankTV',
4563 'channel_url': 'https://www.youtube.com/c/blanktv',
4564 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4565 'view_count': int,
4566 'tags': [],
4567 'uploader_url': 'https://www.youtube.com/c/blanktv',
4568 'modified_date': r're:\d{8}',
4569 'description': '',
4570 },
4571 'playlist_mincount': 1000,
4572 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4573 }, {
4574 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4575 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4576 'info_dict': {
4577 'title': 'Data Analysis with Dr Mike Pound',
4578 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4579 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4580 'uploader': 'Computerphile',
4581 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4582 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4583 'tags': [],
4584 'view_count': int,
4585 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4586 'channel_url': 'https://www.youtube.com/user/Computerphile',
4587 'channel': 'Computerphile',
4588 },
4589 'playlist_mincount': 11,
4590 }, {
4591 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4592 'only_matching': True,
4593 }, {
4594 'note': 'Playlist URL that does not actually serve a playlist',
4595 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4596 'info_dict': {
4597 'id': 'FqZTN594JQw',
4598 'ext': 'webm',
4599 'title': "Smiley's People 01 detective, Adventure Series, Action",
4600 'uploader': 'STREEM',
4601 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4602 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4603 'upload_date': '20150526',
4604 'license': 'Standard YouTube License',
4605 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4606 'categories': ['People & Blogs'],
4607 'tags': list,
4608 'view_count': int,
4609 'like_count': int,
4610 },
4611 'params': {
4612 'skip_download': True,
4613 },
4614 'skip': 'This video is not available.',
4615 'add_ie': [YoutubeIE.ie_key()],
4616 }, {
4617 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4618 'only_matching': True,
4619 }, {
4620 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4621 'only_matching': True,
4622 }, {
4623 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4624 'info_dict': {
4625 'id': 'zpsbVPFwsqk', # This will keep changing
4626 'ext': 'mp4',
4627 'title': str,
4628 'uploader': 'Sky News',
4629 'uploader_id': 'skynews',
4630 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4631 'upload_date': r're:\d{8}',
4632 'description': str,
4633 'categories': ['News & Politics'],
4634 'tags': list,
4635 'like_count': int,
4636 'release_timestamp': 1640164857,
4637 'channel': 'Sky News',
4638 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4639 'age_limit': 0,
4640 'view_count': int,
4641 'thumbnail': 'https://i.ytimg.com/vi/zpsbVPFwsqk/maxresdefault_live.jpg',
4642 'playable_in_embed': True,
4643 'release_date': '20211222',
4644 'availability': 'public',
4645 'live_status': 'is_live',
4646 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4647 },
4648 'params': {
4649 'skip_download': True,
4650 },
4651 'expected_warnings': ['Ignoring subtitle tracks found in '],
4652 }, {
4653 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4654 'info_dict': {
4655 'id': 'a48o2S1cPoo',
4656 'ext': 'mp4',
4657 'title': 'The Young Turks - Live Main Show',
4658 'uploader': 'The Young Turks',
4659 'uploader_id': 'TheYoungTurks',
4660 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4661 'upload_date': '20150715',
4662 'license': 'Standard YouTube License',
4663 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4664 'categories': ['News & Politics'],
4665 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4666 'like_count': int,
4667 },
4668 'params': {
4669 'skip_download': True,
4670 },
4671 'only_matching': True,
4672 }, {
4673 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4674 'only_matching': True,
4675 }, {
4676 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4677 'only_matching': True,
4678 }, {
4679 'note': 'A channel that is not live. Should raise error',
4680 'url': 'https://www.youtube.com/user/numberphile/live',
4681 'only_matching': True,
4682 }, {
4683 'url': 'https://www.youtube.com/feed/trending',
4684 'only_matching': True,
4685 }, {
4686 'url': 'https://www.youtube.com/feed/library',
4687 'only_matching': True,
4688 }, {
4689 'url': 'https://www.youtube.com/feed/history',
4690 'only_matching': True,
4691 }, {
4692 'url': 'https://www.youtube.com/feed/subscriptions',
4693 'only_matching': True,
4694 }, {
4695 'url': 'https://www.youtube.com/feed/watch_later',
4696 'only_matching': True,
4697 }, {
4698 'note': 'Recommended - redirects to home page.',
4699 'url': 'https://www.youtube.com/feed/recommended',
4700 'only_matching': True,
4701 }, {
4702 'note': 'inline playlist with not always working continuations',
4703 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4704 'only_matching': True,
4705 }, {
4706 'url': 'https://www.youtube.com/course',
4707 'only_matching': True,
4708 }, {
4709 'url': 'https://www.youtube.com/zsecurity',
4710 'only_matching': True,
4711 }, {
4712 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4713 'only_matching': True,
4714 }, {
4715 'url': 'https://www.youtube.com/TheYoungTurks/live',
4716 'only_matching': True,
4717 }, {
4718 'url': 'https://www.youtube.com/hashtag/cctv9',
4719 'info_dict': {
4720 'id': 'cctv9',
4721 'title': '#cctv9',
4722 'tags': [],
4723 },
4724 'playlist_mincount': 350,
4725 }, {
4726 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4727 'only_matching': True,
4728 }, {
4729 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4730 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4731 'only_matching': True
4732 }, {
4733 'note': '/browse/ should redirect to /channel/',
4734 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4735 'only_matching': True
4736 }, {
4737 'note': 'VLPL, should redirect to playlist?list=PL...',
4738 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4739 'info_dict': {
4740 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4741 'uploader': 'NoCopyrightSounds',
4742 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4743 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4744 'title': 'NCS Releases',
4745 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4746 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4747 'modified_date': r're:\d{8}',
4748 'view_count': int,
4749 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4750 'tags': [],
4751 'channel': 'NoCopyrightSounds',
4752 },
4753 'playlist_mincount': 166,
4754 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4755 }, {
4756 'note': 'Topic, should redirect to playlist?list=UU...',
4757 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4758 'info_dict': {
4759 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4760 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4761 'title': 'Uploads from Royalty Free Music - Topic',
4762 'uploader': 'Royalty Free Music - Topic',
4763 'tags': [],
4764 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4765 'channel': 'Royalty Free Music - Topic',
4766 'view_count': int,
4767 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4768 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4769 'modified_date': r're:\d{8}',
4770 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4771 'description': '',
4772 },
4773 'expected_warnings': [
4774 'The URL does not have a videos tab',
4775 r'[Uu]navailable videos (are|will be) hidden',
4776 ],
4777 'playlist_mincount': 101,
4778 }, {
4779 'note': 'Topic without a UU playlist',
4780 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4781 'info_dict': {
4782 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4783 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
4784 'tags': [],
4785 },
4786 'expected_warnings': [
4787 'the playlist redirect gave error',
4788 ],
4789 'playlist_mincount': 9,
4790 }, {
4791 'note': 'Youtube music Album',
4792 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4793 'info_dict': {
4794 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4795 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
4796 'tags': [],
4797 'view_count': int,
4798 'description': '',
4799 'availability': 'unlisted',
4800 'modified_date': r're:\d{8}',
4801 },
4802 'playlist_count': 50,
4803 }, {
4804 'note': 'unlisted single video playlist',
4805 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4806 'info_dict': {
4807 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4808 'uploader': 'colethedj',
4809 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4810 'title': 'yt-dlp unlisted playlist test',
4811 'availability': 'unlisted',
4812 'tags': [],
4813 'modified_date': '20211208',
4814 'channel': 'colethedj',
4815 'view_count': int,
4816 'description': '',
4817 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4818 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4819 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4820 },
4821 'playlist_count': 1,
4822 }, {
4823 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4824 'url': 'https://www.youtube.com/feed/recommended',
4825 'info_dict': {
4826 'id': 'recommended',
4827 'title': 'recommended',
4828 },
4829 'playlist_mincount': 50,
4830 'params': {
4831 'skip_download': True,
4832 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4833 },
4834 }, {
4835 'note': 'API Fallback: /videos tab, sorted by oldest first',
4836 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4837 'info_dict': {
4838 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4839 'title': 'Cody\'sLab - Videos',
4840 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4841 'uploader': 'Cody\'sLab',
4842 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4843 'channel': 'Cody\'sLab',
4844 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4845 'tags': [],
4846 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4847 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4848 },
4849 'playlist_mincount': 650,
4850 'params': {
4851 'skip_download': True,
4852 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4853 },
4854 }, {
4855 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4856 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4857 'info_dict': {
4858 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4859 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4860 'title': 'Uploads from Royalty Free Music - Topic',
4861 'uploader': 'Royalty Free Music - Topic',
4862 'modified_date': r're:\d{8}',
4863 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4864 'description': '',
4865 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4866 'tags': [],
4867 'channel': 'Royalty Free Music - Topic',
4868 'view_count': int,
4869 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4870 },
4871 'expected_warnings': [
4872 'does not have a videos tab',
4873 r'[Uu]navailable videos (are|will be) hidden',
4874 ],
4875 'playlist_mincount': 101,
4876 'params': {
4877 'skip_download': True,
4878 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4879 },
4880 }]
4881
4882 @classmethod
4883 def suitable(cls, url):
4884 return False if YoutubeIE.suitable(url) else super(
4885 YoutubeTabIE, cls).suitable(url)
4886
4887 def _real_extract(self, url):
4888 url, smuggled_data = unsmuggle_url(url, {})
4889 if self.is_music_url(url):
4890 smuggled_data['is_music_url'] = True
4891 info_dict = self.__real_extract(url, smuggled_data)
4892 if info_dict.get('entries'):
4893 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4894 return info_dict
4895
4896 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
4897
4898 def __real_extract(self, url, smuggled_data):
4899 item_id = self._match_id(url)
4900 url = compat_urlparse.urlunparse(
4901 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
4902 compat_opts = self.get_param('compat_opts', [])
4903
4904 def get_mobj(url):
4905 mobj = self._URL_RE.match(url).groupdict()
4906 mobj.update((k, '') for k, v in mobj.items() if v is None)
4907 return mobj
4908
4909 mobj, redirect_warning = get_mobj(url), None
4910 # Youtube returns incomplete data if tabname is not lower case
4911 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4912 if is_channel:
4913 if smuggled_data.get('is_music_url'):
4914 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
4915 item_id = item_id[2:]
4916 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
4917 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
4918 mdata = self._extract_tab_endpoint(
4919 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
4920 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
4921 get_all=False, expected_type=compat_str)
4922 if not murl:
4923 raise ExtractorError('Failed to resolve album to playlist')
4924 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
4925 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
4926 pre = f'https://www.youtube.com/channel/{item_id}'
4927
4928 original_tab_name = tab
4929 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4930 # Home URLs should redirect to /videos/
4931 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
4932 'To download only the videos in the home page, add a "/featured" to the URL')
4933 tab = '/videos'
4934
4935 url = ''.join((pre, tab, post))
4936 mobj = get_mobj(url)
4937
4938 # Handle both video/playlist URLs
4939 qs = parse_qs(url)
4940 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
4941
4942 if not video_id and mobj['not_channel'].startswith('watch'):
4943 if not playlist_id:
4944 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
4945 raise ExtractorError('Unable to recognize tab page')
4946 # Common mistake: https://www.youtube.com/watch?list=playlist_id
4947 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
4948 url = f'https://www.youtube.com/playlist?list={playlist_id}'
4949 mobj = get_mobj(url)
4950
4951 if video_id and playlist_id:
4952 if self.get_param('noplaylist'):
4953 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
4954 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
4955 ie=YoutubeIE.ie_key(), video_id=video_id)
4956 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
4957
4958 data, ytcfg = self._extract_data(url, item_id)
4959
4960 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
4961 if tabs:
4962 selected_tab = self._extract_selected_tab(tabs)
4963 selected_tab_name = selected_tab.get('title', '').lower()
4964 if selected_tab_name == 'home':
4965 selected_tab_name = 'featured'
4966 requested_tab_name = mobj['tab'][1:]
4967 if 'no-youtube-channel-redirect' not in compat_opts:
4968 if requested_tab_name == 'live':
4969 # Live tab should have redirected to the video
4970 raise ExtractorError('The channel is not currently live', expected=True)
4971 if requested_tab_name not in ('', selected_tab_name):
4972 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
4973 if not original_tab_name:
4974 if item_id[:2] == 'UC':
4975 # Topic channels don't have /videos. Use the equivalent playlist instead
4976 pl_id = f'UU{item_id[2:]}'
4977 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
4978 try:
4979 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
4980 except ExtractorError:
4981 redirect_warning += ' and the playlist redirect gave error'
4982 else:
4983 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
4984 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
4985 if selected_tab_name and selected_tab_name != requested_tab_name:
4986 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
4987 else:
4988 raise ExtractorError(redirect_warning, expected=True)
4989
4990 if redirect_warning:
4991 self.to_screen(redirect_warning)
4992 self.write_debug(f'Final URL: {url}')
4993
4994 # YouTube sometimes provides a button to reload playlist with unavailable videos.
4995 if 'no-youtube-unavailable-videos' not in compat_opts:
4996 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
4997 self._extract_and_report_alerts(data, only_once=True)
4998 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
4999 if tabs:
5000 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5001
5002 playlist = traverse_obj(
5003 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5004 if playlist:
5005 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5006
5007 video_id = traverse_obj(
5008 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5009 if video_id:
5010 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5011 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5012 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5013 ie=YoutubeIE.ie_key(), video_id=video_id)
5014
5015 raise ExtractorError('Unable to recognize tab page')
5016
5017
5018class YoutubePlaylistIE(InfoExtractor):
5019 IE_DESC = 'YouTube playlists'
5020 _VALID_URL = r'''(?x)(?:
5021 (?:https?://)?
5022 (?:\w+\.)?
5023 (?:
5024 (?:
5025 youtube(?:kids)?\.com|
5026 %(invidious)s
5027 )
5028 /.*?\?.*?\blist=
5029 )?
5030 (?P<id>%(playlist_id)s)
5031 )''' % {
5032 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5033 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5034 }
5035 IE_NAME = 'youtube:playlist'
5036 _TESTS = [{
5037 'note': 'issue #673',
5038 'url': 'PLBB231211A4F62143',
5039 'info_dict': {
5040 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5041 'id': 'PLBB231211A4F62143',
5042 'uploader': 'Wickman',
5043 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5044 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5045 'view_count': int,
5046 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5047 'modified_date': r're:\d{8}',
5048 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5049 'channel': 'Wickman',
5050 'tags': [],
5051 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5052 },
5053 'playlist_mincount': 29,
5054 }, {
5055 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5056 'info_dict': {
5057 'title': 'YDL_safe_search',
5058 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5059 },
5060 'playlist_count': 2,
5061 'skip': 'This playlist is private',
5062 }, {
5063 'note': 'embedded',
5064 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5065 'playlist_count': 4,
5066 'info_dict': {
5067 'title': 'JODA15',
5068 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5069 'uploader': 'milan',
5070 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5071 'description': '',
5072 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5073 'tags': [],
5074 'modified_date': '20140919',
5075 'view_count': int,
5076 'channel': 'milan',
5077 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5078 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5079 },
5080 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5081 }, {
5082 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5083 'playlist_mincount': 654,
5084 'info_dict': {
5085 'title': '2018 Chinese New Singles (11/6 updated)',
5086 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5087 'uploader': 'LBK',
5088 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5089 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5090 'channel': 'LBK',
5091 'view_count': int,
5092 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5093 'tags': [],
5094 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5095 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5096 'modified_date': r're:\d{8}',
5097 },
5098 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5099 }, {
5100 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5101 'only_matching': True,
5102 }, {
5103 # music album playlist
5104 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5105 'only_matching': True,
5106 }]
5107
5108 @classmethod
5109 def suitable(cls, url):
5110 if YoutubeTabIE.suitable(url):
5111 return False
5112 from ..utils import parse_qs
5113 qs = parse_qs(url)
5114 if qs.get('v', [None])[0]:
5115 return False
5116 return super(YoutubePlaylistIE, cls).suitable(url)
5117
5118 def _real_extract(self, url):
5119 playlist_id = self._match_id(url)
5120 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5121 url = update_url_query(
5122 'https://www.youtube.com/playlist',
5123 parse_qs(url) or {'list': playlist_id})
5124 if is_music_url:
5125 url = smuggle_url(url, {'is_music_url': True})
5126 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5127
5128
5129class YoutubeYtBeIE(InfoExtractor):
5130 IE_DESC = 'youtu.be'
5131 _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}
5132 _TESTS = [{
5133 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5134 'info_dict': {
5135 'id': 'yeWKywCrFtk',
5136 'ext': 'mp4',
5137 'title': 'Small Scale Baler and Braiding Rugs',
5138 'uploader': 'Backus-Page House Museum',
5139 'uploader_id': 'backuspagemuseum',
5140 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5141 'upload_date': '20161008',
5142 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5143 'categories': ['Nonprofits & Activism'],
5144 'tags': list,
5145 'like_count': int,
5146 'age_limit': 0,
5147 'playable_in_embed': True,
5148 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5149 'channel': 'Backus-Page House Museum',
5150 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5151 'live_status': 'not_live',
5152 'view_count': int,
5153 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5154 'availability': 'public',
5155 'duration': 59,
5156 },
5157 'params': {
5158 'noplaylist': True,
5159 'skip_download': True,
5160 },
5161 }, {
5162 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5163 'only_matching': True,
5164 }]
5165
5166 def _real_extract(self, url):
5167 mobj = self._match_valid_url(url)
5168 video_id = mobj.group('id')
5169 playlist_id = mobj.group('playlist_id')
5170 return self.url_result(
5171 update_url_query('https://www.youtube.com/watch', {
5172 'v': video_id,
5173 'list': playlist_id,
5174 'feature': 'youtu.be',
5175 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5176
5177
5178class YoutubeLivestreamEmbedIE(InfoExtractor):
5179 IE_DESC = 'YouTube livestream embeds'
5180 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5181 _TESTS = [{
5182 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5183 'only_matching': True,
5184 }]
5185
5186 def _real_extract(self, url):
5187 channel_id = self._match_id(url)
5188 return self.url_result(
5189 f'https://www.youtube.com/channel/{channel_id}/live',
5190 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5191
5192
5193class YoutubeYtUserIE(InfoExtractor):
5194 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5195 IE_NAME = 'youtube:user'
5196 _VALID_URL = r'ytuser:(?P<id>.+)'
5197 _TESTS = [{
5198 'url': 'ytuser:phihag',
5199 'only_matching': True,
5200 }]
5201
5202 def _real_extract(self, url):
5203 user_id = self._match_id(url)
5204 return self.url_result(
5205 'https://www.youtube.com/user/%s/videos' % user_id,
5206 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5207
5208
5209class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5210 IE_NAME = 'youtube:favorites'
5211 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5212 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5213 _LOGIN_REQUIRED = True
5214 _TESTS = [{
5215 'url': ':ytfav',
5216 'only_matching': True,
5217 }, {
5218 'url': ':ytfavorites',
5219 'only_matching': True,
5220 }]
5221
5222 def _real_extract(self, url):
5223 return self.url_result(
5224 'https://www.youtube.com/playlist?list=LL',
5225 ie=YoutubeTabIE.ie_key())
5226
5227
5228class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5229 IE_DESC = 'YouTube search'
5230 IE_NAME = 'youtube:search'
5231 _SEARCH_KEY = 'ytsearch'
5232 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5233 _TESTS = []
5234
5235
5236class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5237 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5238 _SEARCH_KEY = 'ytsearchdate'
5239 IE_DESC = 'YouTube search, newest videos first'
5240 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5241
5242
5243class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5244 IE_DESC = 'YouTube search URLs with sorting and filter support'
5245 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5246 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
5247 _TESTS = [{
5248 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5249 'playlist_mincount': 5,
5250 'info_dict': {
5251 'id': 'youtube-dl test video',
5252 'title': 'youtube-dl test video',
5253 }
5254 }, {
5255 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5256 'playlist_mincount': 5,
5257 'info_dict': {
5258 'id': 'python',
5259 'title': 'python',
5260 }
5261
5262 }, {
5263 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5264 'only_matching': True,
5265 }]
5266
5267 def _real_extract(self, url):
5268 qs = parse_qs(url)
5269 query = (qs.get('search_query') or qs.get('q'))[0]
5270 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5271
5272
5273class YoutubeFeedsInfoExtractor(YoutubeTabIE):
5274 """
5275 Base class for feed extractors
5276 Subclasses must define the _FEED_NAME property.
5277 """
5278 _LOGIN_REQUIRED = True
5279 _TESTS = []
5280
5281 @property
5282 def IE_NAME(self):
5283 return 'youtube:%s' % self._FEED_NAME
5284
5285 def _real_extract(self, url):
5286 return self.url_result(
5287 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
5288 ie=YoutubeTabIE.ie_key())
5289
5290
5291class YoutubeWatchLaterIE(InfoExtractor):
5292 IE_NAME = 'youtube:watchlater'
5293 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5294 _VALID_URL = r':ytwatchlater'
5295 _TESTS = [{
5296 'url': ':ytwatchlater',
5297 'only_matching': True,
5298 }]
5299
5300 def _real_extract(self, url):
5301 return self.url_result(
5302 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5303
5304
5305class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5306 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5307 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5308 _FEED_NAME = 'recommended'
5309 _LOGIN_REQUIRED = False
5310 _TESTS = [{
5311 'url': ':ytrec',
5312 'only_matching': True,
5313 }, {
5314 'url': ':ytrecommended',
5315 'only_matching': True,
5316 }, {
5317 'url': 'https://youtube.com',
5318 'only_matching': True,
5319 }]
5320
5321
5322class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5323 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5324 _VALID_URL = r':ytsub(?:scription)?s?'
5325 _FEED_NAME = 'subscriptions'
5326 _TESTS = [{
5327 'url': ':ytsubs',
5328 'only_matching': True,
5329 }, {
5330 'url': ':ytsubscriptions',
5331 'only_matching': True,
5332 }]
5333
5334
5335class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5336 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5337 _VALID_URL = r':ythis(?:tory)?'
5338 _FEED_NAME = 'history'
5339 _TESTS = [{
5340 'url': ':ythistory',
5341 'only_matching': True,
5342 }]
5343
5344
5345class YoutubeTruncatedURLIE(InfoExtractor):
5346 IE_NAME = 'youtube:truncated_url'
5347 IE_DESC = False # Do not list
5348 _VALID_URL = r'''(?x)
5349 (?:https?://)?
5350 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5351 (?:watch\?(?:
5352 feature=[a-z_]+|
5353 annotation_id=annotation_[^&]+|
5354 x-yt-cl=[0-9]+|
5355 hl=[^&]*|
5356 t=[0-9]+
5357 )?
5358 |
5359 attribution_link\?a=[^&]+
5360 )
5361 $
5362 '''
5363
5364 _TESTS = [{
5365 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5366 'only_matching': True,
5367 }, {
5368 'url': 'https://www.youtube.com/watch?',
5369 'only_matching': True,
5370 }, {
5371 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5372 'only_matching': True,
5373 }, {
5374 'url': 'https://www.youtube.com/watch?feature=foo',
5375 'only_matching': True,
5376 }, {
5377 'url': 'https://www.youtube.com/watch?hl=en-GB',
5378 'only_matching': True,
5379 }, {
5380 'url': 'https://www.youtube.com/watch?t=2372',
5381 'only_matching': True,
5382 }]
5383
5384 def _real_extract(self, url):
5385 raise ExtractorError(
5386 'Did you forget to quote the URL? Remember that & is a meta '
5387 'character in most shells, so you want to put the URL in quotes, '
5388 'like youtube-dl '
5389 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5390 ' or simply youtube-dl BaW_jenozKc .',
5391 expected=True)
5392
5393
5394class YoutubeClipIE(InfoExtractor):
5395 IE_NAME = 'youtube:clip'
5396 IE_DESC = False # Do not list
5397 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5398
5399 def _real_extract(self, url):
5400 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5401 return self.url_result(url, 'Generic')
5402
5403
5404class YoutubeTruncatedIDIE(InfoExtractor):
5405 IE_NAME = 'youtube:truncated_id'
5406 IE_DESC = False # Do not list
5407 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5408
5409 _TESTS = [{
5410 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5411 'only_matching': True,
5412 }]
5413
5414 def _real_extract(self, url):
5415 video_id = self._match_id(url)
5416 raise ExtractorError(
5417 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5418 expected=True)