]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/youtube.py
[youtube:tab] Follow redirect to regional channel (#2884)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import calendar
6 import copy
7 import datetime
8 import functools
9 import hashlib
10 import itertools
11 import json
12 import math
13 import os.path
14 import random
15 import re
16 import sys
17 import time
18 import traceback
19 import threading
20
21 from .common import InfoExtractor, SearchInfoExtractor
22 from ..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 )
32 from ..jsinterp import JSInterpreter
33 from ..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 js_to_json,
46 mimetype2ext,
47 network_exceptions,
48 NO_DEFAULT,
49 orderedSet,
50 parse_codecs,
51 parse_count,
52 parse_duration,
53 parse_iso8601,
54 parse_qs,
55 qualities,
56 remove_end,
57 remove_start,
58 smuggle_url,
59 str_or_none,
60 str_to_int,
61 strftime_or_none,
62 traverse_obj,
63 try_get,
64 unescapeHTML,
65 unified_strdate,
66 unified_timestamp,
67 unsmuggle_url,
68 update_url_query,
69 url_or_none,
70 urljoin,
71 variadic,
72 )
73
74
75 def get_first(obj, keys, **kwargs):
76 return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
77
78
79 # any clients starting with _ cannot be explicity requested by the user
80 INNERTUBE_CLIENTS = {
81 'web': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB',
86 'clientVersion': '2.20211221.00.00',
87 }
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
90 },
91 'web_embedded': {
92 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
93 'INNERTUBE_CONTEXT': {
94 'client': {
95 'clientName': 'WEB_EMBEDDED_PLAYER',
96 'clientVersion': '1.20211215.00.01',
97 },
98 },
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
100 },
101 'web_music': {
102 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
103 'INNERTUBE_HOST': 'music.youtube.com',
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_REMIX',
107 'clientVersion': '1.20211213.00.00',
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
111 },
112 'web_creator': {
113 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'WEB_CREATOR',
117 'clientVersion': '1.20211220.02.00',
118 }
119 },
120 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
121 },
122 'android': {
123 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
124 'INNERTUBE_CONTEXT': {
125 'client': {
126 'clientName': 'ANDROID',
127 'clientVersion': '16.49',
128 }
129 },
130 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
131 'REQUIRE_JS_PLAYER': False
132 },
133 'android_embedded': {
134 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
135 'INNERTUBE_CONTEXT': {
136 'client': {
137 'clientName': 'ANDROID_EMBEDDED_PLAYER',
138 'clientVersion': '16.49',
139 },
140 },
141 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
142 'REQUIRE_JS_PLAYER': False
143 },
144 'android_music': {
145 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
146 'INNERTUBE_CONTEXT': {
147 'client': {
148 'clientName': 'ANDROID_MUSIC',
149 'clientVersion': '4.57',
150 }
151 },
152 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
153 'REQUIRE_JS_PLAYER': False
154 },
155 'android_creator': {
156 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
157 'INNERTUBE_CONTEXT': {
158 'client': {
159 'clientName': 'ANDROID_CREATOR',
160 'clientVersion': '21.47',
161 },
162 },
163 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
164 'REQUIRE_JS_PLAYER': False
165 },
166 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
167 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
168 'ios': {
169 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS',
173 'clientVersion': '16.46',
174 'deviceModel': 'iPhone14,3',
175 }
176 },
177 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
178 'REQUIRE_JS_PLAYER': False
179 },
180 'ios_embedded': {
181 'INNERTUBE_CONTEXT': {
182 'client': {
183 'clientName': 'IOS_MESSAGES_EXTENSION',
184 'clientVersion': '16.46',
185 'deviceModel': 'iPhone14,3',
186 },
187 },
188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
190 },
191 'ios_music': {
192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
196 'clientVersion': '4.57',
197 },
198 },
199 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
200 'REQUIRE_JS_PLAYER': False
201 },
202 'ios_creator': {
203 'INNERTUBE_CONTEXT': {
204 'client': {
205 'clientName': 'IOS_CREATOR',
206 'clientVersion': '21.47',
207 },
208 },
209 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
210 'REQUIRE_JS_PLAYER': False
211 },
212 # mweb has 'ultralow' formats
213 # See: https://github.com/yt-dlp/yt-dlp/pull/557
214 'mweb': {
215 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
216 'INNERTUBE_CONTEXT': {
217 'client': {
218 'clientName': 'MWEB',
219 'clientVersion': '2.20211221.01.00',
220 }
221 },
222 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
223 }
224 }
225
226
227 def build_innertube_clients():
228 THIRD_PARTY = {
229 'embedUrl': 'https://google.com', # Can be any valid URL
230 }
231 BASE_CLIENTS = ('android', 'web', 'ios', 'mweb')
232 priority = qualities(BASE_CLIENTS[::-1])
233
234 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
235 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
236 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
237 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
238 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
239
240 base_client, *variant = client.split('_')
241 ytcfg['priority'] = 10 * priority(base_client)
242
243 if variant == ['embedded']:
244 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
245 INNERTUBE_CLIENTS[f'{base_client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
246 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
247 agegate_ytcfg['priority'] -= 1
248 ytcfg['priority'] -= 2
249 elif variant:
250 ytcfg['priority'] -= 3
251
252
253 build_innertube_clients()
254
255
256 class YoutubeBaseInfoExtractor(InfoExtractor):
257 """Provide base functions for Youtube extractors"""
258
259 _RESERVED_NAMES = (
260 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
261 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
262 r'browse|oembed|get_video_info|iframe_api|s/player|'
263 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
264
265 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
266
267 _NETRC_MACHINE = 'youtube'
268
269 # If True it will raise an error if no login info is provided
270 _LOGIN_REQUIRED = False
271
272 _INVIDIOUS_SITES = (
273 # invidious-redirect websites
274 r'(?:www\.)?redirect\.invidious\.io',
275 r'(?:(?:www|dev)\.)?invidio\.us',
276 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
277 r'(?:www\.)?invidious\.pussthecat\.org',
278 r'(?:www\.)?invidious\.zee\.li',
279 r'(?:www\.)?invidious\.ethibox\.fr',
280 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
281 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
282 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
283 # youtube-dl invidious instances list
284 r'(?:(?:www|no)\.)?invidiou\.sh',
285 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
286 r'(?:www\.)?invidious\.kabi\.tk',
287 r'(?:www\.)?invidious\.mastodon\.host',
288 r'(?:www\.)?invidious\.zapashcanon\.fr',
289 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
290 r'(?:www\.)?invidious\.tinfoil-hat\.net',
291 r'(?:www\.)?invidious\.himiko\.cloud',
292 r'(?:www\.)?invidious\.reallyancient\.tech',
293 r'(?:www\.)?invidious\.tube',
294 r'(?:www\.)?invidiou\.site',
295 r'(?:www\.)?invidious\.site',
296 r'(?:www\.)?invidious\.xyz',
297 r'(?:www\.)?invidious\.nixnet\.xyz',
298 r'(?:www\.)?invidious\.048596\.xyz',
299 r'(?:www\.)?invidious\.drycat\.fr',
300 r'(?:www\.)?inv\.skyn3t\.in',
301 r'(?:www\.)?tube\.poal\.co',
302 r'(?:www\.)?tube\.connect\.cafe',
303 r'(?:www\.)?vid\.wxzm\.sx',
304 r'(?:www\.)?vid\.mint\.lgbt',
305 r'(?:www\.)?vid\.puffyan\.us',
306 r'(?:www\.)?yewtu\.be',
307 r'(?:www\.)?yt\.elukerio\.org',
308 r'(?:www\.)?yt\.lelux\.fi',
309 r'(?:www\.)?invidious\.ggc-project\.de',
310 r'(?:www\.)?yt\.maisputain\.ovh',
311 r'(?:www\.)?ytprivate\.com',
312 r'(?:www\.)?invidious\.13ad\.de',
313 r'(?:www\.)?invidious\.toot\.koeln',
314 r'(?:www\.)?invidious\.fdn\.fr',
315 r'(?:www\.)?watch\.nettohikari\.com',
316 r'(?:www\.)?invidious\.namazso\.eu',
317 r'(?:www\.)?invidious\.silkky\.cloud',
318 r'(?:www\.)?invidious\.exonip\.de',
319 r'(?:www\.)?invidious\.riverside\.rocks',
320 r'(?:www\.)?invidious\.blamefran\.net',
321 r'(?:www\.)?invidious\.moomoo\.de',
322 r'(?:www\.)?ytb\.trom\.tf',
323 r'(?:www\.)?yt\.cyberhost\.uk',
324 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
325 r'(?:www\.)?qklhadlycap4cnod\.onion',
326 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
327 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
328 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
329 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
330 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
331 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
332 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
333 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
334 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
335 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
336 )
337
338 def _login(self):
339 """
340 Attempt to log in to YouTube.
341 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
342 """
343
344 if (self._LOGIN_REQUIRED
345 and self.get_param('cookiefile') is None
346 and self.get_param('cookiesfrombrowser') is None):
347 self.raise_login_required(
348 'Login details are needed to download this content', method='cookies')
349 username, password = self._get_login_info()
350 if username:
351 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
352
353 def _initialize_consent(self):
354 cookies = self._get_cookies('https://www.youtube.com/')
355 if cookies.get('__Secure-3PSID'):
356 return
357 consent_id = None
358 consent = cookies.get('CONSENT')
359 if consent:
360 if 'YES' in consent.value:
361 return
362 consent_id = self._search_regex(
363 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
364 if not consent_id:
365 consent_id = random.randint(100, 999)
366 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
367
368 def _initialize_pref(self):
369 cookies = self._get_cookies('https://www.youtube.com/')
370 pref_cookie = cookies.get('PREF')
371 pref = {}
372 if pref_cookie:
373 try:
374 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
375 except ValueError:
376 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
377 pref.update({'hl': 'en', 'tz': 'UTC'})
378 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
379
380 def _real_initialize(self):
381 self._initialize_pref()
382 self._initialize_consent()
383 self._login()
384
385 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
387 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
388
389 def _get_default_ytcfg(self, client='web'):
390 return copy.deepcopy(INNERTUBE_CLIENTS[client])
391
392 def _get_innertube_host(self, client='web'):
393 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
394
395 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
396 # try_get but with fallback to default ytcfg client values when present
397 _func = lambda y: try_get(y, getter, expected_type)
398 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
399
400 def _extract_client_name(self, ytcfg, default_client='web'):
401 return self._ytcfg_get_safe(
402 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
403 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
404
405 def _extract_client_version(self, ytcfg, default_client='web'):
406 return self._ytcfg_get_safe(
407 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
408 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
409
410 def _extract_api_key(self, ytcfg=None, default_client='web'):
411 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
412
413 def _extract_context(self, ytcfg=None, default_client='web'):
414 context = get_first(
415 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
416 # Enforce language and tz for extraction
417 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
418 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
419 return context
420
421 _SAPISID = None
422
423 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
424 time_now = round(time.time())
425 if self._SAPISID is None:
426 yt_cookies = self._get_cookies('https://www.youtube.com')
427 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
428 # See: https://github.com/yt-dlp/yt-dlp/issues/393
429 sapisid_cookie = dict_get(
430 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
431 if sapisid_cookie and sapisid_cookie.value:
432 self._SAPISID = sapisid_cookie.value
433 self.write_debug('Extracted SAPISID cookie')
434 # SAPISID cookie is required if not already present
435 if not yt_cookies.get('SAPISID'):
436 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
437 self._set_cookie(
438 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
439 else:
440 self._SAPISID = False
441 if not self._SAPISID:
442 return None
443 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
444 sapisidhash = hashlib.sha1(
445 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
446 return f'SAPISIDHASH {time_now}_{sapisidhash}'
447
448 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
449 note='Downloading API JSON', errnote='Unable to download API page',
450 context=None, api_key=None, api_hostname=None, default_client='web'):
451
452 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
453 data.update(query)
454 real_headers = self.generate_api_headers(default_client=default_client)
455 real_headers.update({'content-type': 'application/json'})
456 if headers:
457 real_headers.update(headers)
458 return self._download_json(
459 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
460 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
461 data=json.dumps(data).encode('utf8'), headers=real_headers,
462 query={'key': api_key or self._extract_api_key()})
463
464 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
465 data = self._search_regex(
466 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
467 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
468 if data:
469 return self._parse_json(data, item_id, fatal=fatal)
470
471 @staticmethod
472 def _extract_session_index(*data):
473 """
474 Index of current account in account list.
475 See: https://github.com/yt-dlp/yt-dlp/pull/519
476 """
477 for ytcfg in data:
478 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
479 if session_index is not None:
480 return session_index
481
482 # Deprecated?
483 def _extract_identity_token(self, ytcfg=None, webpage=None):
484 if ytcfg:
485 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
486 if token:
487 return token
488 if webpage:
489 return self._search_regex(
490 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
491 'identity token', default=None, fatal=False)
492
493 @staticmethod
494 def _extract_account_syncid(*args):
495 """
496 Extract syncId required to download private playlists of secondary channels
497 @params response and/or ytcfg
498 """
499 for data in args:
500 # ytcfg includes channel_syncid if on secondary channel
501 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
502 if delegated_sid:
503 return delegated_sid
504 sync_ids = (try_get(
505 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
506 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
507 if len(sync_ids) >= 2 and sync_ids[1]:
508 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
509 # and just "user_syncid||" for primary channel. We only want the channel_syncid
510 return sync_ids[0]
511
512 @staticmethod
513 def _extract_visitor_data(*args):
514 """
515 Extracts visitorData from an API response or ytcfg
516 Appears to be used to track session state
517 """
518 return get_first(
519 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
520 expected_type=str)
521
522 @property
523 def is_authenticated(self):
524 return bool(self._generate_sapisidhash_header())
525
526 def extract_ytcfg(self, video_id, webpage):
527 if not webpage:
528 return {}
529 return self._parse_json(
530 self._search_regex(
531 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
532 default='{}'), video_id, fatal=False) or {}
533
534 def generate_api_headers(
535 self, *, ytcfg=None, account_syncid=None, session_index=None,
536 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
537
538 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
539 headers = {
540 'X-YouTube-Client-Name': compat_str(
541 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
542 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
543 'Origin': origin,
544 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
545 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
546 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
547 }
548 if session_index is None:
549 session_index = self._extract_session_index(ytcfg)
550 if account_syncid or session_index is not None:
551 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
552
553 auth = self._generate_sapisidhash_header(origin)
554 if auth is not None:
555 headers['Authorization'] = auth
556 headers['X-Origin'] = origin
557 return {h: v for h, v in headers.items() if v is not None}
558
559 @staticmethod
560 def _build_api_continuation_query(continuation, ctp=None):
561 query = {
562 'continuation': continuation
563 }
564 # TODO: Inconsistency with clickTrackingParams.
565 # Currently we have a fixed ctp contained within context (from ytcfg)
566 # and a ctp in root query for continuation.
567 if ctp:
568 query['clickTracking'] = {'clickTrackingParams': ctp}
569 return query
570
571 @classmethod
572 def _extract_next_continuation_data(cls, renderer):
573 next_continuation = try_get(
574 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
575 lambda x: x['continuation']['reloadContinuationData']), dict)
576 if not next_continuation:
577 return
578 continuation = next_continuation.get('continuation')
579 if not continuation:
580 return
581 ctp = next_continuation.get('clickTrackingParams')
582 return cls._build_api_continuation_query(continuation, ctp)
583
584 @classmethod
585 def _extract_continuation_ep_data(cls, continuation_ep: dict):
586 if isinstance(continuation_ep, dict):
587 continuation = try_get(
588 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
589 if not continuation:
590 return
591 ctp = continuation_ep.get('clickTrackingParams')
592 return cls._build_api_continuation_query(continuation, ctp)
593
594 @classmethod
595 def _extract_continuation(cls, renderer):
596 next_continuation = cls._extract_next_continuation_data(renderer)
597 if next_continuation:
598 return next_continuation
599
600 contents = []
601 for key in ('contents', 'items'):
602 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
603
604 for content in contents:
605 if not isinstance(content, dict):
606 continue
607 continuation_ep = try_get(
608 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
609 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
610 dict)
611 continuation = cls._extract_continuation_ep_data(continuation_ep)
612 if continuation:
613 return continuation
614
615 @classmethod
616 def _extract_alerts(cls, data):
617 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
618 if not isinstance(alert_dict, dict):
619 continue
620 for alert in alert_dict.values():
621 alert_type = alert.get('type')
622 if not alert_type:
623 continue
624 message = cls._get_text(alert, 'text')
625 if message:
626 yield alert_type, message
627
628 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
629 errors = []
630 warnings = []
631 for alert_type, alert_message in alerts:
632 if alert_type.lower() == 'error' and fatal:
633 errors.append([alert_type, alert_message])
634 else:
635 warnings.append([alert_type, alert_message])
636
637 for alert_type, alert_message in (warnings + errors[:-1]):
638 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
639 if errors:
640 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
641
642 def _extract_and_report_alerts(self, data, *args, **kwargs):
643 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
644
645 def _extract_badges(self, renderer: dict):
646 badges = set()
647 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
648 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
649 if label:
650 badges.add(label.lower())
651 return badges
652
653 @staticmethod
654 def _get_text(data, *path_list, max_runs=None):
655 for path in path_list or [None]:
656 if path is None:
657 obj = [data]
658 else:
659 obj = traverse_obj(data, path, default=[])
660 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
661 obj = [obj]
662 for item in obj:
663 text = try_get(item, lambda x: x['simpleText'], compat_str)
664 if text:
665 return text
666 runs = try_get(item, lambda x: x['runs'], list) or []
667 if not runs and isinstance(item, list):
668 runs = item
669
670 runs = runs[:min(len(runs), max_runs or len(runs))]
671 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
672 if text:
673 return text
674
675 def _get_count(self, data, *path_list):
676 count_text = self._get_text(data, *path_list) or ''
677 count = parse_count(count_text)
678 if count is None:
679 count = str_to_int(
680 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
681 return count
682
683 @staticmethod
684 def _extract_thumbnails(data, *path_list):
685 """
686 Extract thumbnails from thumbnails dict
687 @param path_list: path list to level that contains 'thumbnails' key
688 """
689 thumbnails = []
690 for path in path_list or [()]:
691 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
692 thumbnail_url = url_or_none(thumbnail.get('url'))
693 if not thumbnail_url:
694 continue
695 # Sometimes youtube gives a wrong thumbnail URL. See:
696 # https://github.com/yt-dlp/yt-dlp/issues/233
697 # https://github.com/ytdl-org/youtube-dl/issues/28023
698 if 'maxresdefault' in thumbnail_url:
699 thumbnail_url = thumbnail_url.split('?')[0]
700 thumbnails.append({
701 'url': thumbnail_url,
702 'height': int_or_none(thumbnail.get('height')),
703 'width': int_or_none(thumbnail.get('width')),
704 })
705 return thumbnails
706
707 @staticmethod
708 def extract_relative_time(relative_time_text):
709 """
710 Extracts a relative time from string and converts to dt object
711 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
712 """
713 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)
714 if mobj:
715 start = mobj.group('start')
716 if start:
717 return datetime_from_str(start)
718 try:
719 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
720 except ValueError:
721 return None
722
723 def _extract_time_text(self, renderer, *path_list):
724 text = self._get_text(renderer, *path_list) or ''
725 dt = self.extract_relative_time(text)
726 timestamp = None
727 if isinstance(dt, datetime.datetime):
728 timestamp = calendar.timegm(dt.timetuple())
729
730 if timestamp is None:
731 timestamp = (
732 unified_timestamp(text) or unified_timestamp(
733 self._search_regex(
734 (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
735 text.lower(), 'time text', default=None)))
736
737 if text and timestamp is None:
738 self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
739 return timestamp, text
740
741 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
742 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
743 default_client='web'):
744 response = None
745 last_error = None
746 count = -1
747 retries = self.get_param('extractor_retries', 3)
748 if check_get_keys is None:
749 check_get_keys = []
750 while count < retries:
751 count += 1
752 if last_error:
753 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
754 try:
755 response = self._call_api(
756 ep=ep, fatal=True, headers=headers,
757 video_id=item_id, query=query,
758 context=self._extract_context(ytcfg, default_client),
759 api_key=self._extract_api_key(ytcfg, default_client),
760 api_hostname=api_hostname, default_client=default_client,
761 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
762 except ExtractorError as e:
763 if isinstance(e.cause, network_exceptions):
764 if isinstance(e.cause, compat_HTTPError):
765 first_bytes = e.cause.read(512)
766 if not is_html(first_bytes):
767 yt_error = try_get(
768 self._parse_json(
769 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
770 lambda x: x['error']['message'], compat_str)
771 if yt_error:
772 self._report_alerts([('ERROR', yt_error)], fatal=False)
773 # Downloading page may result in intermittent 5xx HTTP error
774 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
775 # We also want to catch all other network exceptions since errors in later pages can be troublesome
776 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
777 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
778 last_error = error_to_compat_str(e.cause or e.msg)
779 if count < retries:
780 continue
781 if fatal:
782 raise
783 else:
784 self.report_warning(error_to_compat_str(e))
785 return
786
787 else:
788 try:
789 self._extract_and_report_alerts(response, only_once=True)
790 except ExtractorError as e:
791 # YouTube servers may return errors we want to retry on in a 200 OK response
792 # See: https://github.com/yt-dlp/yt-dlp/issues/839
793 if 'unknown error' in e.msg.lower():
794 last_error = e.msg
795 continue
796 if fatal:
797 raise
798 self.report_warning(error_to_compat_str(e))
799 return
800 if not check_get_keys or dict_get(response, check_get_keys):
801 break
802 # Youtube sometimes sends incomplete data
803 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
804 last_error = 'Incomplete data received'
805 if count >= retries:
806 if fatal:
807 raise ExtractorError(last_error)
808 else:
809 self.report_warning(last_error)
810 return
811 return response
812
813 @staticmethod
814 def is_music_url(url):
815 return re.match(r'https?://music\.youtube\.com/', url) is not None
816
817 def _extract_video(self, renderer):
818 video_id = renderer.get('videoId')
819 title = self._get_text(renderer, 'title')
820 description = self._get_text(renderer, 'descriptionSnippet')
821 duration = parse_duration(self._get_text(
822 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
823 view_count = self._get_count(renderer, 'viewCountText')
824
825 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
826 channel_id = traverse_obj(
827 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
828 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
829 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
830 overlay_style = traverse_obj(
831 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
832 badges = self._extract_badges(renderer)
833 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
834
835 return {
836 '_type': 'url',
837 'ie_key': YoutubeIE.ie_key(),
838 'id': video_id,
839 'url': f'https://www.youtube.com/watch?v={video_id}',
840 'title': title,
841 'description': description,
842 'duration': duration,
843 'view_count': view_count,
844 'uploader': uploader,
845 'channel_id': channel_id,
846 'thumbnails': thumbnails,
847 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
848 'live_status': ('is_upcoming' if scheduled_timestamp is not None
849 else 'was_live' if 'streamed' in time_text.lower()
850 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
851 else None),
852 'release_timestamp': scheduled_timestamp,
853 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
854 }
855
856
857 class YoutubeIE(YoutubeBaseInfoExtractor):
858 IE_DESC = 'YouTube'
859 _VALID_URL = r"""(?x)^
860 (
861 (?:https?://|//) # http(s):// or protocol-independent URL
862 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
863 (?:www\.)?deturl\.com/www\.youtube\.com|
864 (?:www\.)?pwnyoutube\.com|
865 (?:www\.)?hooktube\.com|
866 (?:www\.)?yourepeat\.com|
867 tube\.majestyc\.net|
868 %(invidious)s|
869 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
870 (?:.*?\#/)? # handle anchor (#/) redirect urls
871 (?: # the various things that can precede the ID:
872 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
873 |(?: # or the v= param in all its forms
874 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
875 (?:\?|\#!?) # the params delimiter ? or # or #!
876 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
877 v=
878 )
879 ))
880 |(?:
881 youtu\.be| # just youtu.be/xxxx
882 vid\.plus| # or vid.plus/xxxx
883 zwearz\.com/watch| # or zwearz.com/watch/xxxx
884 %(invidious)s
885 )/
886 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
887 )
888 )? # all until now is optional -> you can pass the naked ID
889 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
890 (?(1).+)? # if we found the ID, everything can follow
891 (?:\#|$)""" % {
892 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
893 }
894 _PLAYER_INFO_RE = (
895 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
896 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
897 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
898 )
899 _formats = {
900 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
901 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
902 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
903 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
904 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
905 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
906 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
907 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
908 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
909 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
910 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
911 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
912 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
913 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
914 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
915 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
916 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
917 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
918
919
920 # 3D videos
921 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
922 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
923 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
924 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
925 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
926 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
927 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
928
929 # Apple HTTP Live Streaming
930 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
931 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
932 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
933 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
934 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
935 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
936 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
937 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
938
939 # DASH mp4 video
940 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
942 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
943 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
944 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
945 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
946 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
947 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
948 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
949 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
950 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
951 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
952
953 # Dash mp4 audio
954 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
955 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
956 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
957 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
958 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
959 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
960 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
961
962 # Dash webm
963 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
967 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
968 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
969 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
970 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
976 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
977 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
978 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
979 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
980 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
981 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
982 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
983 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
984 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
985
986 # Dash webm audio
987 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
988 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
989
990 # Dash webm audio with opus inside
991 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
992 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
993 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
994
995 # RTMP (unnamed)
996 '_rtmp': {'protocol': 'rtmp'},
997
998 # av01 video only formats sometimes served with "unknown" codecs
999 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1000 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1001 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1002 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1003 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1004 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1005 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1006 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1007 }
1008 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1009
1010 _GEO_BYPASS = False
1011
1012 IE_NAME = 'youtube'
1013 _TESTS = [
1014 {
1015 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1016 'info_dict': {
1017 'id': 'BaW_jenozKc',
1018 'ext': 'mp4',
1019 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1020 'uploader': 'Philipp Hagemeister',
1021 'uploader_id': 'phihag',
1022 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1023 'channel': 'Philipp Hagemeister',
1024 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1025 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1026 'upload_date': '20121002',
1027 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1028 'categories': ['Science & Technology'],
1029 'tags': ['youtube-dl'],
1030 'duration': 10,
1031 'view_count': int,
1032 'like_count': int,
1033 'availability': 'public',
1034 'playable_in_embed': True,
1035 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1036 'live_status': 'not_live',
1037 'age_limit': 0,
1038 'start_time': 1,
1039 'end_time': 9,
1040 'channel_follower_count': int
1041 }
1042 },
1043 {
1044 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1045 'note': 'Embed-only video (#1746)',
1046 'info_dict': {
1047 'id': 'yZIXLfi8CZQ',
1048 'ext': 'mp4',
1049 'upload_date': '20120608',
1050 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1051 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1052 'uploader': 'SET India',
1053 'uploader_id': 'setindia',
1054 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1055 'age_limit': 18,
1056 },
1057 'skip': 'Private video',
1058 },
1059 {
1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1061 'note': 'Use the first video ID in the URL',
1062 'info_dict': {
1063 'id': 'BaW_jenozKc',
1064 'ext': 'mp4',
1065 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1066 'uploader': 'Philipp Hagemeister',
1067 'uploader_id': 'phihag',
1068 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1069 'channel': 'Philipp Hagemeister',
1070 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1071 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1072 'upload_date': '20121002',
1073 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1074 'categories': ['Science & Technology'],
1075 'tags': ['youtube-dl'],
1076 'duration': 10,
1077 'view_count': int,
1078 'like_count': int,
1079 'availability': 'public',
1080 'playable_in_embed': True,
1081 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1082 'live_status': 'not_live',
1083 'age_limit': 0,
1084 'channel_follower_count': int
1085 },
1086 'params': {
1087 'skip_download': True,
1088 },
1089 },
1090 {
1091 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1092 'note': '256k DASH audio (format 141) via DASH manifest',
1093 'info_dict': {
1094 'id': 'a9LDPn-MO4I',
1095 'ext': 'm4a',
1096 'upload_date': '20121002',
1097 'uploader_id': '8KVIDEO',
1098 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1099 'description': '',
1100 'uploader': '8KVIDEO',
1101 'title': 'UHDTV TEST 8K VIDEO.mp4'
1102 },
1103 'params': {
1104 'youtube_include_dash_manifest': True,
1105 'format': '141',
1106 },
1107 'skip': 'format 141 not served anymore',
1108 },
1109 # DASH manifest with encrypted signature
1110 {
1111 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1112 'info_dict': {
1113 'id': 'IB3lcPjvWLA',
1114 'ext': 'm4a',
1115 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1116 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1117 'duration': 244,
1118 'uploader': 'AfrojackVEVO',
1119 'uploader_id': 'AfrojackVEVO',
1120 'upload_date': '20131011',
1121 'abr': 129.495,
1122 'like_count': int,
1123 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1124 'playable_in_embed': True,
1125 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1126 'view_count': int,
1127 'track': 'The Spark',
1128 'live_status': 'not_live',
1129 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1130 'channel': 'Afrojack',
1131 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1132 'tags': 'count:19',
1133 'availability': 'public',
1134 'categories': ['Music'],
1135 'age_limit': 0,
1136 'alt_title': 'The Spark',
1137 'channel_follower_count': int
1138 },
1139 'params': {
1140 'youtube_include_dash_manifest': True,
1141 'format': '141/bestaudio[ext=m4a]',
1142 },
1143 },
1144 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1145 {
1146 'note': 'Embed allowed age-gate video',
1147 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1148 'info_dict': {
1149 'id': 'HtVdAasjOgU',
1150 'ext': 'mp4',
1151 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1152 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1153 'duration': 142,
1154 'uploader': 'The Witcher',
1155 'uploader_id': 'WitcherGame',
1156 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1157 'upload_date': '20140605',
1158 'age_limit': 18,
1159 'categories': ['Gaming'],
1160 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1161 'availability': 'needs_auth',
1162 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1163 'like_count': int,
1164 'channel': 'The Witcher',
1165 'live_status': 'not_live',
1166 'tags': 'count:17',
1167 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1168 'playable_in_embed': True,
1169 'view_count': int,
1170 'channel_follower_count': int
1171 },
1172 },
1173 {
1174 'note': 'Age-gate video with embed allowed in public site',
1175 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1176 'info_dict': {
1177 'id': 'HsUATh_Nc2U',
1178 'ext': 'mp4',
1179 'title': 'Godzilla 2 (Official Video)',
1180 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1181 'upload_date': '20200408',
1182 'uploader_id': 'FlyingKitty900',
1183 'uploader': 'FlyingKitty',
1184 'age_limit': 18,
1185 'availability': 'needs_auth',
1186 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1187 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1188 'channel': 'FlyingKitty',
1189 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1190 'view_count': int,
1191 'categories': ['Entertainment'],
1192 'live_status': 'not_live',
1193 'tags': ['Flyingkitty', 'godzilla 2'],
1194 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1195 'like_count': int,
1196 'duration': 177,
1197 'playable_in_embed': True,
1198 'channel_follower_count': int
1199 },
1200 },
1201 {
1202 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1203 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1204 'info_dict': {
1205 'id': 'Tq92D6wQ1mg',
1206 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1207 'ext': 'mp4',
1208 'upload_date': '20191227',
1209 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1210 'uploader': 'Projekt Melody',
1211 'description': 'md5:17eccca93a786d51bc67646756894066',
1212 'age_limit': 18,
1213 'like_count': int,
1214 'availability': 'needs_auth',
1215 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1216 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1217 'view_count': int,
1218 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1219 'channel': 'Projekt Melody',
1220 'live_status': 'not_live',
1221 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1222 'playable_in_embed': True,
1223 'categories': ['Entertainment'],
1224 'duration': 106,
1225 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1226 'channel_follower_count': int
1227 },
1228 },
1229 {
1230 'note': 'Non-Agegated non-embeddable video',
1231 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1232 'info_dict': {
1233 'id': 'MeJVWBSsPAY',
1234 'ext': 'mp4',
1235 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1236 'uploader': 'Herr Lurik',
1237 'uploader_id': 'st3in234',
1238 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1239 'upload_date': '20130730',
1240 'track': 'Such mich find mich',
1241 'age_limit': 0,
1242 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1243 'like_count': int,
1244 'playable_in_embed': False,
1245 'creator': 'OOMPH!',
1246 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1247 'view_count': int,
1248 'alt_title': 'Such mich find mich',
1249 'duration': 210,
1250 'channel': 'Herr Lurik',
1251 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1252 'categories': ['Music'],
1253 'availability': 'public',
1254 'uploader_url': 'http://www.youtube.com/user/st3in234',
1255 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1256 'live_status': 'not_live',
1257 'artist': 'OOMPH!',
1258 'channel_follower_count': int
1259 },
1260 },
1261 {
1262 'note': 'Non-bypassable age-gated video',
1263 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1264 'only_matching': True,
1265 },
1266 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1267 # YouTube Red ad is not captured for creator
1268 {
1269 'url': '__2ABJjxzNo',
1270 'info_dict': {
1271 'id': '__2ABJjxzNo',
1272 'ext': 'mp4',
1273 'duration': 266,
1274 'upload_date': '20100430',
1275 'uploader_id': 'deadmau5',
1276 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1277 'creator': 'deadmau5',
1278 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1279 'uploader': 'deadmau5',
1280 'title': 'Deadmau5 - Some Chords (HD)',
1281 'alt_title': 'Some Chords',
1282 'availability': 'public',
1283 'tags': 'count:14',
1284 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1285 'view_count': int,
1286 'live_status': 'not_live',
1287 'channel': 'deadmau5',
1288 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1289 'like_count': int,
1290 'track': 'Some Chords',
1291 'artist': 'deadmau5',
1292 'playable_in_embed': True,
1293 'age_limit': 0,
1294 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1295 'categories': ['Music'],
1296 'album': 'Some Chords',
1297 'channel_follower_count': int
1298 },
1299 'expected_warnings': [
1300 'DASH manifest missing',
1301 ]
1302 },
1303 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1304 {
1305 'url': 'lqQg6PlCWgI',
1306 'info_dict': {
1307 'id': 'lqQg6PlCWgI',
1308 'ext': 'mp4',
1309 'duration': 6085,
1310 'upload_date': '20150827',
1311 'uploader_id': 'olympic',
1312 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1313 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1314 'uploader': 'Olympics',
1315 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1316 'like_count': int,
1317 'release_timestamp': 1343767800,
1318 'playable_in_embed': True,
1319 'categories': ['Sports'],
1320 'release_date': '20120731',
1321 'channel': 'Olympics',
1322 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1323 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1324 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1325 'age_limit': 0,
1326 'availability': 'public',
1327 'live_status': 'was_live',
1328 'view_count': int,
1329 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1330 'channel_follower_count': int
1331 },
1332 'params': {
1333 'skip_download': 'requires avconv',
1334 }
1335 },
1336 # Non-square pixels
1337 {
1338 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1339 'info_dict': {
1340 'id': '_b-2C3KPAM0',
1341 'ext': 'mp4',
1342 'stretched_ratio': 16 / 9.,
1343 'duration': 85,
1344 'upload_date': '20110310',
1345 'uploader_id': 'AllenMeow',
1346 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1347 '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',
1348 'uploader': '孫ᄋᄅ',
1349 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1350 'playable_in_embed': True,
1351 'channel': '孫ᄋᄅ',
1352 'age_limit': 0,
1353 'tags': 'count:11',
1354 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1355 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1356 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1357 'view_count': int,
1358 'categories': ['People & Blogs'],
1359 'like_count': int,
1360 'live_status': 'not_live',
1361 'availability': 'unlisted',
1362 'channel_follower_count': int
1363 },
1364 },
1365 # url_encoded_fmt_stream_map is empty string
1366 {
1367 'url': 'qEJwOuvDf7I',
1368 'info_dict': {
1369 'id': 'qEJwOuvDf7I',
1370 'ext': 'webm',
1371 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1372 'description': '',
1373 'upload_date': '20150404',
1374 'uploader_id': 'spbelect',
1375 'uploader': 'Наблюдатели Петербурга',
1376 },
1377 'params': {
1378 'skip_download': 'requires avconv',
1379 },
1380 'skip': 'This live event has ended.',
1381 },
1382 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1383 {
1384 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1385 'info_dict': {
1386 'id': 'FIl7x6_3R5Y',
1387 'ext': 'webm',
1388 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1389 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1390 'duration': 220,
1391 'upload_date': '20150625',
1392 'uploader_id': 'dorappi2000',
1393 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1394 'uploader': 'dorappi2000',
1395 'formats': 'mincount:31',
1396 },
1397 'skip': 'not actual anymore',
1398 },
1399 # DASH manifest with segment_list
1400 {
1401 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1402 'md5': '8ce563a1d667b599d21064e982ab9e31',
1403 'info_dict': {
1404 'id': 'CsmdDsKjzN8',
1405 'ext': 'mp4',
1406 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1407 'uploader': 'Airtek',
1408 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1409 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1410 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1411 },
1412 'params': {
1413 'youtube_include_dash_manifest': True,
1414 'format': '135', # bestvideo
1415 },
1416 'skip': 'This live event has ended.',
1417 },
1418 {
1419 # Multifeed videos (multiple cameras), URL is for Main Camera
1420 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1421 'info_dict': {
1422 'id': 'jvGDaLqkpTg',
1423 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1424 'description': 'md5:e03b909557865076822aa169218d6a5d',
1425 },
1426 'playlist': [{
1427 'info_dict': {
1428 'id': 'jvGDaLqkpTg',
1429 'ext': 'mp4',
1430 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1431 'description': 'md5:e03b909557865076822aa169218d6a5d',
1432 'duration': 10643,
1433 'upload_date': '20161111',
1434 'uploader': 'Team PGP',
1435 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1436 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1437 },
1438 }, {
1439 'info_dict': {
1440 'id': '3AKt1R1aDnw',
1441 'ext': 'mp4',
1442 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1443 'description': 'md5:e03b909557865076822aa169218d6a5d',
1444 'duration': 10991,
1445 'upload_date': '20161111',
1446 'uploader': 'Team PGP',
1447 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1448 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1449 },
1450 }, {
1451 'info_dict': {
1452 'id': 'RtAMM00gpVc',
1453 'ext': 'mp4',
1454 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1455 'description': 'md5:e03b909557865076822aa169218d6a5d',
1456 'duration': 10995,
1457 'upload_date': '20161111',
1458 'uploader': 'Team PGP',
1459 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1460 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1461 },
1462 }, {
1463 'info_dict': {
1464 'id': '6N2fdlP3C5U',
1465 'ext': 'mp4',
1466 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1467 'description': 'md5:e03b909557865076822aa169218d6a5d',
1468 'duration': 10990,
1469 'upload_date': '20161111',
1470 'uploader': 'Team PGP',
1471 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1472 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1473 },
1474 }],
1475 'params': {
1476 'skip_download': True,
1477 },
1478 'skip': 'Not multifeed anymore',
1479 },
1480 {
1481 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1482 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1483 'info_dict': {
1484 'id': 'gVfLd0zydlo',
1485 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1486 },
1487 'playlist_count': 2,
1488 'skip': 'Not multifeed anymore',
1489 },
1490 {
1491 'url': 'https://vid.plus/FlRa-iH7PGw',
1492 'only_matching': True,
1493 },
1494 {
1495 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1496 'only_matching': True,
1497 },
1498 {
1499 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1500 # Also tests cut-off URL expansion in video description (see
1501 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1502 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1503 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1504 'info_dict': {
1505 'id': 'lsguqyKfVQg',
1506 'ext': 'mp4',
1507 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1508 'alt_title': 'Dark Walk',
1509 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1510 'duration': 133,
1511 'upload_date': '20151119',
1512 'uploader_id': 'IronSoulElf',
1513 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1514 'uploader': 'IronSoulElf',
1515 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1516 'track': 'Dark Walk',
1517 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1518 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1519 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1520 'categories': ['Film & Animation'],
1521 'view_count': int,
1522 'live_status': 'not_live',
1523 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1524 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1525 'tags': 'count:13',
1526 'availability': 'public',
1527 'channel': 'IronSoulElf',
1528 'playable_in_embed': True,
1529 'like_count': int,
1530 'age_limit': 0,
1531 'channel_follower_count': int
1532 },
1533 'params': {
1534 'skip_download': True,
1535 },
1536 },
1537 {
1538 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1539 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1540 'only_matching': True,
1541 },
1542 {
1543 # Video with yt:stretch=17:0
1544 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1545 'info_dict': {
1546 'id': 'Q39EVAstoRM',
1547 'ext': 'mp4',
1548 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1549 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1550 'upload_date': '20151107',
1551 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1552 'uploader': 'CH GAMER DROID',
1553 },
1554 'params': {
1555 'skip_download': True,
1556 },
1557 'skip': 'This video does not exist.',
1558 },
1559 {
1560 # Video with incomplete 'yt:stretch=16:'
1561 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1562 'only_matching': True,
1563 },
1564 {
1565 # Video licensed under Creative Commons
1566 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1567 'info_dict': {
1568 'id': 'M4gD1WSo5mA',
1569 'ext': 'mp4',
1570 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1571 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1572 'duration': 721,
1573 'upload_date': '20150127',
1574 'uploader_id': 'BerkmanCenter',
1575 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1576 'uploader': 'The Berkman Klein Center for Internet & Society',
1577 'license': 'Creative Commons Attribution license (reuse allowed)',
1578 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1579 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1580 'like_count': int,
1581 'age_limit': 0,
1582 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1583 'channel': 'The Berkman Klein Center for Internet & Society',
1584 'availability': 'public',
1585 'view_count': int,
1586 'categories': ['Education'],
1587 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1588 'live_status': 'not_live',
1589 'playable_in_embed': True,
1590 'channel_follower_count': int
1591 },
1592 'params': {
1593 'skip_download': True,
1594 },
1595 },
1596 {
1597 # Channel-like uploader_url
1598 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1599 'info_dict': {
1600 'id': 'eQcmzGIKrzg',
1601 'ext': 'mp4',
1602 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1603 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1604 'duration': 4060,
1605 'upload_date': '20151119',
1606 'uploader': 'Bernie Sanders',
1607 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1609 'license': 'Creative Commons Attribution license (reuse allowed)',
1610 'playable_in_embed': True,
1611 'tags': 'count:12',
1612 'like_count': int,
1613 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1614 'age_limit': 0,
1615 'availability': 'public',
1616 'categories': ['News & Politics'],
1617 'channel': 'Bernie Sanders',
1618 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1619 'view_count': int,
1620 'live_status': 'not_live',
1621 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1622 'channel_follower_count': int
1623 },
1624 'params': {
1625 'skip_download': True,
1626 },
1627 },
1628 {
1629 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1630 'only_matching': True,
1631 },
1632 {
1633 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1634 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1635 'only_matching': True,
1636 },
1637 {
1638 # Rental video preview
1639 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1640 'info_dict': {
1641 'id': 'uGpuVWrhIzE',
1642 'ext': 'mp4',
1643 'title': 'Piku - Trailer',
1644 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1645 'upload_date': '20150811',
1646 'uploader': 'FlixMatrix',
1647 'uploader_id': 'FlixMatrixKaravan',
1648 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1649 'license': 'Standard YouTube License',
1650 },
1651 'params': {
1652 'skip_download': True,
1653 },
1654 'skip': 'This video is not available.',
1655 },
1656 {
1657 # YouTube Red video with episode data
1658 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1659 'info_dict': {
1660 'id': 'iqKdEhx-dD4',
1661 'ext': 'mp4',
1662 'title': 'Isolation - Mind Field (Ep 1)',
1663 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1664 'duration': 2085,
1665 'upload_date': '20170118',
1666 'uploader': 'Vsauce',
1667 'uploader_id': 'Vsauce',
1668 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1669 'series': 'Mind Field',
1670 'season_number': 1,
1671 'episode_number': 1,
1672 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1673 'tags': 'count:12',
1674 'view_count': int,
1675 'availability': 'public',
1676 'age_limit': 0,
1677 'channel': 'Vsauce',
1678 'episode': 'Episode 1',
1679 'categories': ['Entertainment'],
1680 'season': 'Season 1',
1681 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1682 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1683 'like_count': int,
1684 'playable_in_embed': True,
1685 'live_status': 'not_live',
1686 'channel_follower_count': int
1687 },
1688 'params': {
1689 'skip_download': True,
1690 },
1691 'expected_warnings': [
1692 'Skipping DASH manifest',
1693 ],
1694 },
1695 {
1696 # The following content has been identified by the YouTube community
1697 # as inappropriate or offensive to some audiences.
1698 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1699 'info_dict': {
1700 'id': '6SJNVb0GnPI',
1701 'ext': 'mp4',
1702 'title': 'Race Differences in Intelligence',
1703 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1704 'duration': 965,
1705 'upload_date': '20140124',
1706 'uploader': 'New Century Foundation',
1707 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1709 },
1710 'params': {
1711 'skip_download': True,
1712 },
1713 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1714 },
1715 {
1716 # itag 212
1717 'url': '1t24XAntNCY',
1718 'only_matching': True,
1719 },
1720 {
1721 # geo restricted to JP
1722 'url': 'sJL6WA-aGkQ',
1723 'only_matching': True,
1724 },
1725 {
1726 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1727 'only_matching': True,
1728 },
1729 {
1730 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1731 'only_matching': True,
1732 },
1733 {
1734 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1735 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1736 'only_matching': True,
1737 },
1738 {
1739 # DRM protected
1740 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1741 'only_matching': True,
1742 },
1743 {
1744 # Video with unsupported adaptive stream type formats
1745 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1746 'info_dict': {
1747 'id': 'Z4Vy8R84T1U',
1748 'ext': 'mp4',
1749 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1750 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1751 'duration': 433,
1752 'upload_date': '20130923',
1753 'uploader': 'Amelia Putri Harwita',
1754 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1755 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1756 'formats': 'maxcount:10',
1757 },
1758 'params': {
1759 'skip_download': True,
1760 'youtube_include_dash_manifest': False,
1761 },
1762 'skip': 'not actual anymore',
1763 },
1764 {
1765 # Youtube Music Auto-generated description
1766 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1767 'info_dict': {
1768 'id': 'MgNrAu2pzNs',
1769 'ext': 'mp4',
1770 'title': 'Voyeur Girl',
1771 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1772 'upload_date': '20190312',
1773 'uploader': 'Stephen - Topic',
1774 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1775 'artist': 'Stephen',
1776 'track': 'Voyeur Girl',
1777 'album': 'it\'s too much love to know my dear',
1778 'release_date': '20190313',
1779 'release_year': 2019,
1780 'alt_title': 'Voyeur Girl',
1781 'view_count': int,
1782 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1783 'playable_in_embed': True,
1784 'like_count': int,
1785 'categories': ['Music'],
1786 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1787 'channel': 'Stephen',
1788 'availability': 'public',
1789 'creator': 'Stephen',
1790 'duration': 169,
1791 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1792 'age_limit': 0,
1793 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1794 'tags': 'count:11',
1795 'live_status': 'not_live',
1796 'channel_follower_count': int
1797 },
1798 'params': {
1799 'skip_download': True,
1800 },
1801 },
1802 {
1803 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1804 'only_matching': True,
1805 },
1806 {
1807 # invalid -> valid video id redirection
1808 'url': 'DJztXj2GPfl',
1809 'info_dict': {
1810 'id': 'DJztXj2GPfk',
1811 'ext': 'mp4',
1812 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1813 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1814 'upload_date': '20090125',
1815 'uploader': 'Prochorowka',
1816 'uploader_id': 'Prochorowka',
1817 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1818 'artist': 'Panjabi MC',
1819 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1820 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1821 },
1822 'params': {
1823 'skip_download': True,
1824 },
1825 'skip': 'Video unavailable',
1826 },
1827 {
1828 # empty description results in an empty string
1829 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1830 'info_dict': {
1831 'id': 'x41yOUIvK2k',
1832 'ext': 'mp4',
1833 'title': 'IMG 3456',
1834 'description': '',
1835 'upload_date': '20170613',
1836 'uploader_id': 'ElevageOrVert',
1837 'uploader': 'ElevageOrVert',
1838 'view_count': int,
1839 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1840 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1841 'like_count': int,
1842 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1843 'tags': [],
1844 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1845 'availability': 'public',
1846 'age_limit': 0,
1847 'categories': ['Pets & Animals'],
1848 'duration': 7,
1849 'playable_in_embed': True,
1850 'live_status': 'not_live',
1851 'channel': 'ElevageOrVert',
1852 'channel_follower_count': int
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
1857 },
1858 {
1859 # with '};' inside yt initial data (see [1])
1860 # see [2] for an example with '};' inside ytInitialPlayerResponse
1861 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1862 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1863 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1864 'info_dict': {
1865 'id': 'CHqg6qOn4no',
1866 'ext': 'mp4',
1867 'title': 'Part 77 Sort a list of simple types in c#',
1868 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1869 'upload_date': '20130831',
1870 'uploader_id': 'kudvenkat',
1871 'uploader': 'kudvenkat',
1872 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1873 'like_count': int,
1874 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1875 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1876 'live_status': 'not_live',
1877 'categories': ['Education'],
1878 'availability': 'public',
1879 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1880 'tags': 'count:12',
1881 'playable_in_embed': True,
1882 'age_limit': 0,
1883 'view_count': int,
1884 'duration': 522,
1885 'channel': 'kudvenkat',
1886 'channel_follower_count': int
1887 },
1888 'params': {
1889 'skip_download': True,
1890 },
1891 },
1892 {
1893 # another example of '};' in ytInitialData
1894 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1895 'only_matching': True,
1896 },
1897 {
1898 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1899 'only_matching': True,
1900 },
1901 {
1902 # https://github.com/ytdl-org/youtube-dl/pull/28094
1903 'url': 'OtqTfy26tG0',
1904 'info_dict': {
1905 'id': 'OtqTfy26tG0',
1906 'ext': 'mp4',
1907 'title': 'Burn Out',
1908 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1909 'upload_date': '20141120',
1910 'uploader': 'The Cinematic Orchestra - Topic',
1911 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1912 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1913 'artist': 'The Cinematic Orchestra',
1914 'track': 'Burn Out',
1915 'album': 'Every Day',
1916 'like_count': int,
1917 'live_status': 'not_live',
1918 'alt_title': 'Burn Out',
1919 'duration': 614,
1920 'age_limit': 0,
1921 'view_count': int,
1922 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1923 'creator': 'The Cinematic Orchestra',
1924 'channel': 'The Cinematic Orchestra',
1925 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1926 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1927 'availability': 'public',
1928 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1929 'categories': ['Music'],
1930 'playable_in_embed': True,
1931 'channel_follower_count': int
1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
1936 },
1937 {
1938 # controversial video, only works with bpctr when authenticated with cookies
1939 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1940 'only_matching': True,
1941 },
1942 {
1943 # controversial video, requires bpctr/contentCheckOk
1944 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1945 'info_dict': {
1946 'id': 'SZJvDhaSDnc',
1947 'ext': 'mp4',
1948 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1949 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1950 'uploader': 'CBS Mornings',
1951 'uploader_id': 'CBSThisMorning',
1952 'upload_date': '20140716',
1953 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1954 'duration': 170,
1955 'categories': ['News & Politics'],
1956 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1957 'view_count': int,
1958 'channel': 'CBS Mornings',
1959 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1960 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1961 'age_limit': 18,
1962 'availability': 'needs_auth',
1963 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1964 'like_count': int,
1965 'live_status': 'not_live',
1966 'playable_in_embed': True,
1967 'channel_follower_count': int
1968 }
1969 },
1970 {
1971 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1972 'url': 'cBvYw8_A0vQ',
1973 'info_dict': {
1974 'id': 'cBvYw8_A0vQ',
1975 'ext': 'mp4',
1976 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1977 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1978 'upload_date': '20201120',
1979 'uploader': 'Walk around Japan',
1980 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1981 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1982 'duration': 1456,
1983 'categories': ['Travel & Events'],
1984 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1985 'view_count': int,
1986 'channel': 'Walk around Japan',
1987 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1988 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1989 'age_limit': 0,
1990 'availability': 'public',
1991 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1992 'live_status': 'not_live',
1993 'playable_in_embed': True,
1994 'channel_follower_count': int
1995 },
1996 'params': {
1997 'skip_download': True,
1998 },
1999 }, {
2000 # Has multiple audio streams
2001 'url': 'WaOKSUlf4TM',
2002 'only_matching': True
2003 }, {
2004 # Requires Premium: has format 141 when requested using YTM url
2005 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2006 'only_matching': True
2007 }, {
2008 # multiple subtitles with same lang_code
2009 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2010 'only_matching': True,
2011 }, {
2012 # Force use android client fallback
2013 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2014 'info_dict': {
2015 'id': 'YOelRv7fMxY',
2016 'title': 'DIGGING A SECRET TUNNEL Part 1',
2017 'ext': '3gp',
2018 'upload_date': '20210624',
2019 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2020 'uploader': 'colinfurze',
2021 'uploader_id': 'colinfurze',
2022 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2023 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2024 'duration': 596,
2025 'categories': ['Entertainment'],
2026 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2027 'view_count': int,
2028 'channel': 'colinfurze',
2029 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2030 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2031 'age_limit': 0,
2032 'availability': 'public',
2033 'like_count': int,
2034 'live_status': 'not_live',
2035 'playable_in_embed': True,
2036 'channel_follower_count': int
2037 },
2038 'params': {
2039 'format': '17', # 3gp format available on android
2040 'extractor_args': {'youtube': {'player_client': ['android']}},
2041 },
2042 },
2043 {
2044 # Skip download of additional client configs (remix client config in this case)
2045 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2046 'only_matching': True,
2047 'params': {
2048 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2049 },
2050 }, {
2051 # shorts
2052 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2053 'only_matching': True,
2054 }, {
2055 'note': 'Storyboards',
2056 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2057 'info_dict': {
2058 'id': '5KLPxDtMqe8',
2059 'ext': 'mhtml',
2060 'format_id': 'sb0',
2061 'title': 'Your Brain is Plastic',
2062 'uploader_id': 'scishow',
2063 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2064 'upload_date': '20140324',
2065 'uploader': 'SciShow',
2066 'like_count': int,
2067 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2068 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2069 'view_count': int,
2070 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2071 'playable_in_embed': True,
2072 'tags': 'count:12',
2073 'uploader_url': 'http://www.youtube.com/user/scishow',
2074 'availability': 'public',
2075 'channel': 'SciShow',
2076 'live_status': 'not_live',
2077 'duration': 248,
2078 'categories': ['Education'],
2079 'age_limit': 0,
2080 'channel_follower_count': int
2081 }, 'params': {'format': 'mhtml', 'skip_download': True}
2082 }
2083 ]
2084
2085 @classmethod
2086 def suitable(cls, url):
2087 from ..utils import parse_qs
2088
2089 qs = parse_qs(url)
2090 if qs.get('list', [None])[0]:
2091 return False
2092 return super(YoutubeIE, cls).suitable(url)
2093
2094 def __init__(self, *args, **kwargs):
2095 super(YoutubeIE, self).__init__(*args, **kwargs)
2096 self._code_cache = {}
2097 self._player_cache = {}
2098
2099 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2100 lock = threading.Lock()
2101
2102 is_live = True
2103 start_time = time.time()
2104 formats = [f for f in formats if f.get('is_from_start')]
2105
2106 def refetch_manifest(format_id, delay):
2107 nonlocal formats, start_time, is_live
2108 if time.time() <= start_time + delay:
2109 return
2110
2111 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2112 video_details = traverse_obj(
2113 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2114 microformats = traverse_obj(
2115 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2116 expected_type=dict, default=[])
2117 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
2118 start_time = time.time()
2119
2120 def mpd_feed(format_id, delay):
2121 """
2122 @returns (manifest_url, manifest_stream_number, is_live) or None
2123 """
2124 with lock:
2125 refetch_manifest(format_id, delay)
2126
2127 f = next((f for f in formats if f['format_id'] == format_id), None)
2128 if not f:
2129 if not is_live:
2130 self.to_screen(f'{video_id}: Video is no longer live')
2131 else:
2132 self.report_warning(
2133 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2134 return None
2135 return f['manifest_url'], f['manifest_stream_number'], is_live
2136
2137 for f in formats:
2138 f['is_live'] = True
2139 f['protocol'] = 'http_dash_segments_generator'
2140 f['fragments'] = functools.partial(
2141 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2142
2143 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2144 FETCH_SPAN, MAX_DURATION = 5, 432000
2145
2146 mpd_url, stream_number, is_live = None, None, True
2147
2148 begin_index = 0
2149 download_start_time = ctx.get('start') or time.time()
2150
2151 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2152 if lack_early_segments:
2153 self.report_warning(bug_reports_message(
2154 'Starting download from the last 120 hours of the live stream since '
2155 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2156 lack_early_segments = True
2157
2158 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2159 fragments, fragment_base_url = None, None
2160
2161 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2162 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2163 # Obtain from MPD's maximum seq value
2164 old_mpd_url = mpd_url
2165 last_error = ctx.pop('last_error', None)
2166 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2167 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2168 or (mpd_url, stream_number, False))
2169 if not refresh_sequence:
2170 if expire_fast and not is_live:
2171 return False, last_seq
2172 elif old_mpd_url == mpd_url:
2173 return True, last_seq
2174 try:
2175 fmts, _ = self._extract_mpd_formats_and_subtitles(
2176 mpd_url, None, note=False, errnote=False, fatal=False)
2177 except ExtractorError:
2178 fmts = None
2179 if not fmts:
2180 no_fragment_score += 2
2181 return False, last_seq
2182 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2183 fragments = fmt_info['fragments']
2184 fragment_base_url = fmt_info['fragment_base_url']
2185 assert fragment_base_url
2186
2187 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2188 return True, _last_seq
2189
2190 while is_live:
2191 fetch_time = time.time()
2192 if no_fragment_score > 30:
2193 return
2194 if last_segment_url:
2195 # Obtain from "X-Head-Seqnum" header value from each segment
2196 try:
2197 urlh = self._request_webpage(
2198 last_segment_url, None, note=False, errnote=False, fatal=False)
2199 except ExtractorError:
2200 urlh = None
2201 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2202 if last_seq is None:
2203 no_fragment_score += 2
2204 last_segment_url = None
2205 continue
2206 else:
2207 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2208 no_fragment_score += 2
2209 if not should_continue:
2210 continue
2211
2212 if known_idx > last_seq:
2213 last_segment_url = None
2214 continue
2215
2216 last_seq += 1
2217
2218 if begin_index < 0 and known_idx < 0:
2219 # skip from the start when it's negative value
2220 known_idx = last_seq + begin_index
2221 if lack_early_segments:
2222 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2223 try:
2224 for idx in range(known_idx, last_seq):
2225 # do not update sequence here or you'll get skipped some part of it
2226 should_continue, _ = _extract_sequence_from_mpd(False, False)
2227 if not should_continue:
2228 known_idx = idx - 1
2229 raise ExtractorError('breaking out of outer loop')
2230 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2231 yield {
2232 'url': last_segment_url,
2233 }
2234 if known_idx == last_seq:
2235 no_fragment_score += 5
2236 else:
2237 no_fragment_score = 0
2238 known_idx = last_seq
2239 except ExtractorError:
2240 continue
2241
2242 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2243
2244 def _extract_player_url(self, *ytcfgs, webpage=None):
2245 player_url = traverse_obj(
2246 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2247 get_all=False, expected_type=compat_str)
2248 if not player_url:
2249 return
2250 return urljoin('https://www.youtube.com', player_url)
2251
2252 def _download_player_url(self, video_id, fatal=False):
2253 res = self._download_webpage(
2254 'https://www.youtube.com/iframe_api',
2255 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2256 if res:
2257 player_version = self._search_regex(
2258 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2259 if player_version:
2260 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2261
2262 def _signature_cache_id(self, example_sig):
2263 """ Return a string representation of a signature """
2264 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
2265
2266 @classmethod
2267 def _extract_player_info(cls, player_url):
2268 for player_re in cls._PLAYER_INFO_RE:
2269 id_m = re.search(player_re, player_url)
2270 if id_m:
2271 break
2272 else:
2273 raise ExtractorError('Cannot identify player %r' % player_url)
2274 return id_m.group('id')
2275
2276 def _load_player(self, video_id, player_url, fatal=True):
2277 player_id = self._extract_player_info(player_url)
2278 if player_id not in self._code_cache:
2279 code = self._download_webpage(
2280 player_url, video_id, fatal=fatal,
2281 note='Downloading player ' + player_id,
2282 errnote='Download of %s failed' % player_url)
2283 if code:
2284 self._code_cache[player_id] = code
2285 return self._code_cache.get(player_id)
2286
2287 def _extract_signature_function(self, video_id, player_url, example_sig):
2288 player_id = self._extract_player_info(player_url)
2289
2290 # Read from filesystem cache
2291 func_id = 'js_%s_%s' % (
2292 player_id, self._signature_cache_id(example_sig))
2293 assert os.path.basename(func_id) == func_id
2294
2295 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
2296 if cache_spec is not None:
2297 return lambda s: ''.join(s[i] for i in cache_spec)
2298
2299 code = self._load_player(video_id, player_url)
2300 if code:
2301 res = self._parse_sig_js(code)
2302
2303 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2304 cache_res = res(test_string)
2305 cache_spec = [ord(c) for c in cache_res]
2306
2307 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2308 return res
2309
2310 def _print_sig_code(self, func, example_sig):
2311 if not self.get_param('youtube_print_sig_code'):
2312 return
2313
2314 def gen_sig_code(idxs):
2315 def _genslice(start, end, step):
2316 starts = '' if start == 0 else str(start)
2317 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2318 steps = '' if step == 1 else (':%d' % step)
2319 return 's[%s%s%s]' % (starts, ends, steps)
2320
2321 step = None
2322 # Quelch pyflakes warnings - start will be set when step is set
2323 start = '(Never used)'
2324 for i, prev in zip(idxs[1:], idxs[:-1]):
2325 if step is not None:
2326 if i - prev == step:
2327 continue
2328 yield _genslice(start, prev, step)
2329 step = None
2330 continue
2331 if i - prev in [-1, 1]:
2332 step = i - prev
2333 start = prev
2334 continue
2335 else:
2336 yield 's[%d]' % prev
2337 if step is None:
2338 yield 's[%d]' % i
2339 else:
2340 yield _genslice(start, i, step)
2341
2342 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2343 cache_res = func(test_string)
2344 cache_spec = [ord(c) for c in cache_res]
2345 expr_code = ' + '.join(gen_sig_code(cache_spec))
2346 signature_id_tuple = '(%s)' % (
2347 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
2348 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2349 ' return %s\n') % (signature_id_tuple, expr_code)
2350 self.to_screen('Extracted signature function:\n' + code)
2351
2352 def _parse_sig_js(self, jscode):
2353 funcname = self._search_regex(
2354 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2355 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2356 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2357 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2358 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}\(a,\d+\)',
2359 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\(\s*""\s*\)',
2360 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2361 # Obsolete patterns
2362 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2363 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2364 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2365 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2366 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2367 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2368 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2369 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2370 jscode, 'Initial JS player signature function name', group='sig')
2371
2372 jsi = JSInterpreter(jscode)
2373 initial_function = jsi.extract_function(funcname)
2374 return lambda s: initial_function([s])
2375
2376 def _decrypt_signature(self, s, video_id, player_url):
2377 """Turn the encrypted s field into a working signature"""
2378
2379 if player_url is None:
2380 raise ExtractorError('Cannot decrypt signature without player_url')
2381
2382 try:
2383 player_id = (player_url, self._signature_cache_id(s))
2384 if player_id not in self._player_cache:
2385 func = self._extract_signature_function(
2386 video_id, player_url, s
2387 )
2388 self._player_cache[player_id] = func
2389 func = self._player_cache[player_id]
2390 self._print_sig_code(func, s)
2391 return func(s)
2392 except Exception as e:
2393 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2394
2395 def _decrypt_nsig(self, s, video_id, player_url):
2396 """Turn the encrypted n field into a working signature"""
2397 if player_url is None:
2398 raise ExtractorError('Cannot decrypt nsig without player_url')
2399 player_url = urljoin('https://www.youtube.com', player_url)
2400
2401 sig_id = ('nsig_value', s)
2402 if sig_id in self._player_cache:
2403 return self._player_cache[sig_id]
2404
2405 try:
2406 player_id = ('nsig', player_url)
2407 if player_id not in self._player_cache:
2408 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2409 func = self._player_cache[player_id]
2410 self._player_cache[sig_id] = func(s)
2411 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2412 return self._player_cache[sig_id]
2413 except Exception as e:
2414 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2415
2416 def _extract_n_function_name(self, jscode):
2417 nfunc, idx = self._search_regex(
2418 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2419 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2420 if not idx:
2421 return nfunc
2422 return json.loads(js_to_json(self._search_regex(
2423 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
2424 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
2425
2426 def _extract_n_function(self, video_id, player_url):
2427 player_id = self._extract_player_info(player_url)
2428 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2429
2430 if func_code:
2431 jsi = JSInterpreter(func_code)
2432 else:
2433 jscode = self._load_player(video_id, player_url)
2434 funcname = self._extract_n_function_name(jscode)
2435 jsi = JSInterpreter(jscode)
2436 func_code = jsi.extract_function_code(funcname)
2437 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2438
2439 if self.get_param('youtube_print_sig_code'):
2440 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2441
2442 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2443
2444 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2445 """
2446 Extract signatureTimestamp (sts)
2447 Required to tell API what sig/player version is in use.
2448 """
2449 sts = None
2450 if isinstance(ytcfg, dict):
2451 sts = int_or_none(ytcfg.get('STS'))
2452
2453 if not sts:
2454 # Attempt to extract from player
2455 if player_url is None:
2456 error_msg = 'Cannot extract signature timestamp without player_url.'
2457 if fatal:
2458 raise ExtractorError(error_msg)
2459 self.report_warning(error_msg)
2460 return
2461 code = self._load_player(video_id, player_url, fatal=fatal)
2462 if code:
2463 sts = int_or_none(self._search_regex(
2464 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2465 'JS player signature timestamp', group='sts', fatal=fatal))
2466 return sts
2467
2468 def _mark_watched(self, video_id, player_responses):
2469 playback_url = get_first(
2470 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2471 expected_type=url_or_none)
2472 if not playback_url:
2473 self.report_warning('Unable to mark watched')
2474 return
2475 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2476 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2477
2478 # cpn generation algorithm is reverse engineered from base.js.
2479 # In fact it works even with dummy cpn.
2480 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2481 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2482
2483 qs.update({
2484 'ver': ['2'],
2485 'cpn': [cpn],
2486 })
2487 playback_url = compat_urlparse.urlunparse(
2488 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2489
2490 self._download_webpage(
2491 playback_url, video_id, 'Marking watched',
2492 'Unable to mark watched', fatal=False)
2493
2494 @staticmethod
2495 def _extract_urls(webpage):
2496 # Embedded YouTube player
2497 entries = [
2498 unescapeHTML(mobj.group('url'))
2499 for mobj in re.finditer(r'''(?x)
2500 (?:
2501 <iframe[^>]+?src=|
2502 data-video-url=|
2503 <embed[^>]+?src=|
2504 embedSWF\(?:\s*|
2505 <object[^>]+data=|
2506 new\s+SWFObject\(
2507 )
2508 (["\'])
2509 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2510 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2511 \1''', webpage)]
2512
2513 # lazyYT YouTube embed
2514 entries.extend(list(map(
2515 unescapeHTML,
2516 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2517
2518 # Wordpress "YouTube Video Importer" plugin
2519 matches = re.findall(r'''(?x)<div[^>]+
2520 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2521 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2522 entries.extend(m[-1] for m in matches)
2523
2524 return entries
2525
2526 @staticmethod
2527 def _extract_url(webpage):
2528 urls = YoutubeIE._extract_urls(webpage)
2529 return urls[0] if urls else None
2530
2531 @classmethod
2532 def extract_id(cls, url):
2533 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2534 if mobj is None:
2535 raise ExtractorError('Invalid URL: %s' % url)
2536 return mobj.group('id')
2537
2538 def _extract_chapters_from_json(self, data, duration):
2539 chapter_list = traverse_obj(
2540 data, (
2541 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2542 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2543 ), expected_type=list)
2544
2545 return self._extract_chapters(
2546 chapter_list,
2547 chapter_time=lambda chapter: float_or_none(
2548 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2549 chapter_title=lambda chapter: traverse_obj(
2550 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2551 duration=duration)
2552
2553 def _extract_chapters_from_engagement_panel(self, data, duration):
2554 content_list = traverse_obj(
2555 data,
2556 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2557 expected_type=list, default=[])
2558 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2559 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2560
2561 return next((
2562 filter(None, (
2563 self._extract_chapters(
2564 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2565 chapter_time, chapter_title, duration)
2566 for contents in content_list
2567 ))), [])
2568
2569 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2570 chapters = []
2571 last_chapter = {'start_time': 0}
2572 for idx, chapter in enumerate(chapter_list or []):
2573 title = chapter_title(chapter)
2574 start_time = chapter_time(chapter)
2575 if start_time is None:
2576 continue
2577 last_chapter['end_time'] = start_time
2578 if start_time < last_chapter['start_time']:
2579 if idx == 1:
2580 chapters.pop()
2581 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2582 else:
2583 self.report_warning(f'Invalid start time for chapter "{title}"')
2584 continue
2585 last_chapter = {'start_time': start_time, 'title': title}
2586 chapters.append(last_chapter)
2587 last_chapter['end_time'] = duration
2588 return chapters
2589
2590 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2591 return self._parse_json(self._search_regex(
2592 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2593 regex), webpage, name, default='{}'), video_id, fatal=False)
2594
2595 def _extract_comment(self, comment_renderer, parent=None):
2596 comment_id = comment_renderer.get('commentId')
2597 if not comment_id:
2598 return
2599
2600 text = self._get_text(comment_renderer, 'contentText')
2601
2602 # note: timestamp is an estimate calculated from the current time and time_text
2603 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2604 author = self._get_text(comment_renderer, 'authorText')
2605 author_id = try_get(comment_renderer,
2606 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2607
2608 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2609 lambda x: x['likeCount']), compat_str)) or 0
2610 author_thumbnail = try_get(comment_renderer,
2611 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2612
2613 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2614 is_favorited = 'creatorHeart' in (try_get(
2615 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2616 return {
2617 'id': comment_id,
2618 'text': text,
2619 'timestamp': timestamp,
2620 'time_text': time_text,
2621 'like_count': votes,
2622 'is_favorited': is_favorited,
2623 'author': author,
2624 'author_id': author_id,
2625 'author_thumbnail': author_thumbnail,
2626 'author_is_uploader': author_is_uploader,
2627 'parent': parent or 'root'
2628 }
2629
2630 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2631
2632 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2633
2634 def extract_header(contents):
2635 _continuation = None
2636 for content in contents:
2637 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2638 expected_comment_count = self._get_count(
2639 comments_header_renderer, 'countText', 'commentsCount')
2640
2641 if expected_comment_count:
2642 tracker['est_total'] = expected_comment_count
2643 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2644 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2645
2646 sort_menu_item = try_get(
2647 comments_header_renderer,
2648 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2649 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2650
2651 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2652 if not _continuation:
2653 continue
2654
2655 sort_text = str_or_none(sort_menu_item.get('title'))
2656 if not sort_text:
2657 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2658 self.to_screen('Sorting comments by %s' % sort_text.lower())
2659 break
2660 return _continuation
2661
2662 def extract_thread(contents):
2663 if not parent:
2664 tracker['current_page_thread'] = 0
2665 for content in contents:
2666 if not parent and tracker['total_parent_comments'] >= max_parents:
2667 yield
2668 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2669 comment_renderer = get_first(
2670 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2671 expected_type=dict, default={})
2672
2673 comment = self._extract_comment(comment_renderer, parent)
2674 if not comment:
2675 continue
2676
2677 tracker['running_total'] += 1
2678 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2679 yield comment
2680
2681 # Attempt to get the replies
2682 comment_replies_renderer = try_get(
2683 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2684
2685 if comment_replies_renderer:
2686 tracker['current_page_thread'] += 1
2687 comment_entries_iter = self._comment_entries(
2688 comment_replies_renderer, ytcfg, video_id,
2689 parent=comment.get('id'), tracker=tracker)
2690 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2691 yield reply_comment
2692
2693 # Keeps track of counts across recursive calls
2694 if not tracker:
2695 tracker = dict(
2696 running_total=0,
2697 est_total=0,
2698 current_page_thread=0,
2699 total_parent_comments=0,
2700 total_reply_comments=0)
2701
2702 # TODO: Deprecated
2703 # YouTube comments have a max depth of 2
2704 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2705 if max_depth:
2706 self._downloader.deprecation_warning(
2707 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2708 if max_depth == 1 and parent:
2709 return
2710
2711 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2712 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2713
2714 continuation = self._extract_continuation(root_continuation_data)
2715 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2716 if message and not parent:
2717 self.report_warning(message, video_id=video_id)
2718
2719 response = None
2720 is_first_continuation = parent is None
2721
2722 for page_num in itertools.count(0):
2723 if not continuation:
2724 break
2725 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2726 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2727 if page_num == 0:
2728 if is_first_continuation:
2729 note_prefix = 'Downloading comment section API JSON'
2730 else:
2731 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2732 tracker['current_page_thread'], comment_prog_str)
2733 else:
2734 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2735 ' ' if parent else '', ' replies' if parent else '',
2736 page_num, comment_prog_str)
2737
2738 response = self._extract_response(
2739 item_id=None, query=continuation,
2740 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2741 check_get_keys='onResponseReceivedEndpoints')
2742
2743 continuation_contents = traverse_obj(
2744 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2745
2746 continuation = None
2747 for continuation_section in continuation_contents:
2748 continuation_items = traverse_obj(
2749 continuation_section,
2750 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2751 get_all=False, expected_type=list) or []
2752 if is_first_continuation:
2753 continuation = extract_header(continuation_items)
2754 is_first_continuation = False
2755 if continuation:
2756 break
2757 continue
2758
2759 for entry in extract_thread(continuation_items):
2760 if not entry:
2761 return
2762 yield entry
2763 continuation = self._extract_continuation({'contents': continuation_items})
2764 if continuation:
2765 break
2766
2767 def _get_comments(self, ytcfg, video_id, contents, webpage):
2768 """Entry for comment extraction"""
2769 def _real_comment_extract(contents):
2770 renderer = next((
2771 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2772 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2773 yield from self._comment_entries(renderer, ytcfg, video_id)
2774
2775 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2776 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2777
2778 @staticmethod
2779 def _get_checkok_params():
2780 return {'contentCheckOk': True, 'racyCheckOk': True}
2781
2782 @classmethod
2783 def _generate_player_context(cls, sts=None):
2784 context = {
2785 'html5Preference': 'HTML5_PREF_WANTS',
2786 }
2787 if sts is not None:
2788 context['signatureTimestamp'] = sts
2789 return {
2790 'playbackContext': {
2791 'contentPlaybackContext': context
2792 },
2793 **cls._get_checkok_params()
2794 }
2795
2796 @staticmethod
2797 def _is_agegated(player_response):
2798 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2799 return True
2800
2801 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2802 AGE_GATE_REASONS = (
2803 'confirm your age', 'age-restricted', 'inappropriate', # reason
2804 'age_verification_required', 'age_check_required', # status
2805 )
2806 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2807
2808 @staticmethod
2809 def _is_unplayable(player_response):
2810 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2811
2812 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2813
2814 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2815 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2816 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2817 headers = self.generate_api_headers(
2818 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2819
2820 yt_query = {'videoId': video_id}
2821 yt_query.update(self._generate_player_context(sts))
2822 return self._extract_response(
2823 item_id=video_id, ep='player', query=yt_query,
2824 ytcfg=player_ytcfg, headers=headers, fatal=True,
2825 default_client=client,
2826 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2827 ) or None
2828
2829 def _get_requested_clients(self, url, smuggled_data):
2830 requested_clients = []
2831 default = ['android', 'web']
2832 allowed_clients = sorted(
2833 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2834 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2835 for client in self._configuration_arg('player_client'):
2836 if client in allowed_clients:
2837 requested_clients.append(client)
2838 elif client == 'default':
2839 requested_clients.extend(default)
2840 elif client == 'all':
2841 requested_clients.extend(allowed_clients)
2842 else:
2843 self.report_warning(f'Skipping unsupported client {client}')
2844 if not requested_clients:
2845 requested_clients = default
2846
2847 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2848 requested_clients.extend(
2849 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2850
2851 return orderedSet(requested_clients)
2852
2853 def _extract_player_ytcfg(self, client, video_id):
2854 url = {
2855 'web_music': 'https://music.youtube.com',
2856 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2857 }.get(client)
2858 if not url:
2859 return {}
2860 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
2861 return self.extract_ytcfg(video_id, webpage) or {}
2862
2863 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2864 initial_pr = None
2865 if webpage:
2866 initial_pr = self._extract_yt_initial_variable(
2867 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2868 video_id, 'initial player response')
2869
2870 original_clients = clients
2871 clients = clients[::-1]
2872 prs = []
2873
2874 def append_client(client_name):
2875 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2876 clients.append(client_name)
2877
2878 # Android player_response does not have microFormats which are needed for
2879 # extraction of some data. So we return the initial_pr with formats
2880 # stripped out even if not requested by the user
2881 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2882 if initial_pr:
2883 pr = dict(initial_pr)
2884 pr['streamingData'] = None
2885 prs.append(pr)
2886
2887 last_error = None
2888 tried_iframe_fallback = False
2889 player_url = None
2890 while clients:
2891 client = clients.pop()
2892 player_ytcfg = master_ytcfg if client == 'web' else {}
2893 if 'configs' not in self._configuration_arg('player_skip'):
2894 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
2895
2896 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2897 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2898 if 'js' in self._configuration_arg('player_skip'):
2899 require_js_player = False
2900 player_url = None
2901
2902 if not player_url and not tried_iframe_fallback and require_js_player:
2903 player_url = self._download_player_url(video_id)
2904 tried_iframe_fallback = True
2905
2906 try:
2907 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
2908 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
2909 except ExtractorError as e:
2910 if last_error:
2911 self.report_warning(last_error)
2912 last_error = e
2913 continue
2914
2915 if pr:
2916 prs.append(pr)
2917
2918 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
2919 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
2920 append_client(client.replace('_agegate', '_creator'))
2921 elif self._is_agegated(pr):
2922 append_client(f'{client}_agegate')
2923
2924 if last_error:
2925 if not len(prs):
2926 raise last_error
2927 self.report_warning(last_error)
2928 return prs, player_url
2929
2930 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2931 itags, stream_ids = {}, []
2932 itag_qualities, res_qualities = {}, {}
2933 q = qualities([
2934 # Normally tiny is the smallest video-only formats. But
2935 # audio-only formats with unknown quality may get tagged as tiny
2936 'tiny',
2937 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2938 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2939 ])
2940 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
2941 approx_duration = max(traverse_obj(streaming_formats, (..., 'approxDurationMs'), expected_type=float_or_none) or [0]) or None
2942
2943 for fmt in streaming_formats:
2944 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2945 continue
2946
2947 itag = str_or_none(fmt.get('itag'))
2948 audio_track = fmt.get('audioTrack') or {}
2949 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2950 if stream_id in stream_ids:
2951 continue
2952
2953 quality = fmt.get('quality')
2954 height = int_or_none(fmt.get('height'))
2955 if quality == 'tiny' or not quality:
2956 quality = fmt.get('audioQuality', '').lower() or quality
2957 # The 3gp format (17) in android client has a quality of "small",
2958 # but is actually worse than other formats
2959 if itag == '17':
2960 quality = 'tiny'
2961 if quality:
2962 if itag:
2963 itag_qualities[itag] = quality
2964 if height:
2965 res_qualities[height] = quality
2966 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2967 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2968 # number of fragment that would subsequently requested with (`&sq=N`)
2969 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2970 continue
2971
2972 fmt_url = fmt.get('url')
2973 if not fmt_url:
2974 sc = compat_parse_qs(fmt.get('signatureCipher'))
2975 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2976 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2977 if not (sc and fmt_url and encrypted_sig):
2978 continue
2979 if not player_url:
2980 continue
2981 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2982 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2983 fmt_url += '&' + sp + '=' + signature
2984
2985 query = parse_qs(fmt_url)
2986 throttled = False
2987 if query.get('n'):
2988 try:
2989 fmt_url = update_url_query(fmt_url, {
2990 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2991 except ExtractorError as e:
2992 self.report_warning(
2993 f'nsig extraction failed: You may experience throttling for some formats\n'
2994 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
2995 throttled = True
2996
2997 if itag:
2998 itags[itag] = 'https'
2999 stream_ids.append(stream_id)
3000
3001 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3002 language_preference = (
3003 10 if audio_track.get('audioIsDefault') and 10
3004 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3005 else -1)
3006 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3007 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3008 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) < approx_duration - 10000)
3009 dct = {
3010 'asr': int_or_none(fmt.get('audioSampleRate')),
3011 'filesize': int_or_none(fmt.get('contentLength')),
3012 'format_id': itag,
3013 'format_note': join_nonempty(
3014 '%s%s' % (audio_track.get('displayName') or '',
3015 ' (default)' if language_preference > 0 else ''),
3016 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3017 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3018 'source_preference': -10 if throttled else -1,
3019 'fps': int_or_none(fmt.get('fps')) or None,
3020 'height': height,
3021 'quality': q(quality),
3022 'tbr': tbr,
3023 'url': fmt_url,
3024 'width': int_or_none(fmt.get('width')),
3025 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3026 'desc' if language_preference < -1 else ''),
3027 'language_preference': language_preference,
3028 'preference': -10 if is_damaged else None,
3029 }
3030 mime_mobj = re.match(
3031 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3032 if mime_mobj:
3033 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3034 dct.update(parse_codecs(mime_mobj.group(2)))
3035 no_audio = dct.get('acodec') == 'none'
3036 no_video = dct.get('vcodec') == 'none'
3037 if no_audio:
3038 dct['vbr'] = tbr
3039 if no_video:
3040 dct['abr'] = tbr
3041 if no_audio or no_video:
3042 dct['downloader_options'] = {
3043 # Youtube throttles chunks >~10M
3044 'http_chunk_size': 10485760,
3045 }
3046 if dct.get('ext'):
3047 dct['container'] = dct['ext'] + '_dash'
3048 yield dct
3049
3050 live_from_start = is_live and self.get_param('live_from_start')
3051 skip_manifests = self._configuration_arg('skip')
3052 if not self.get_param('youtube_include_hls_manifest', True):
3053 skip_manifests.append('hls')
3054 get_dash = 'dash' not in skip_manifests and (
3055 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3056 get_hls = not live_from_start and 'hls' not in skip_manifests
3057
3058 def process_manifest_format(f, proto, itag):
3059 if itag in itags:
3060 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3061 return False
3062 itag = f'{itag}-{proto}'
3063 if itag:
3064 f['format_id'] = itag
3065 itags[itag] = proto
3066
3067 f['quality'] = next((
3068 q(qdict[val])
3069 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3070 if val in qdict), -1)
3071 return True
3072
3073 for sd in streaming_data:
3074 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3075 if hls_manifest_url:
3076 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3077 if process_manifest_format(f, 'hls', self._search_regex(
3078 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3079 yield f
3080
3081 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3082 if dash_manifest_url:
3083 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3084 if process_manifest_format(f, 'dash', f['format_id']):
3085 f['filesize'] = int_or_none(self._search_regex(
3086 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3087 if live_from_start:
3088 f['is_from_start'] = True
3089
3090 yield f
3091
3092 def _extract_storyboard(self, player_responses, duration):
3093 spec = get_first(
3094 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3095 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3096 if not base_url:
3097 return
3098 L = len(spec) - 1
3099 for i, args in enumerate(spec):
3100 args = args.split('#')
3101 counts = list(map(int_or_none, args[:5]))
3102 if len(args) != 8 or not all(counts):
3103 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3104 continue
3105 width, height, frame_count, cols, rows = counts
3106 N, sigh = args[6:]
3107
3108 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3109 fragment_count = frame_count / (cols * rows)
3110 fragment_duration = duration / fragment_count
3111 yield {
3112 'format_id': f'sb{i}',
3113 'format_note': 'storyboard',
3114 'ext': 'mhtml',
3115 'protocol': 'mhtml',
3116 'acodec': 'none',
3117 'vcodec': 'none',
3118 'url': url,
3119 'width': width,
3120 'height': height,
3121 'fragments': [{
3122 'path': url.replace('$M', str(j)),
3123 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3124 } for j in range(math.ceil(fragment_count))],
3125 }
3126
3127 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3128 webpage = None
3129 if 'webpage' not in self._configuration_arg('player_skip'):
3130 webpage = self._download_webpage(
3131 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3132
3133 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3134
3135 player_responses, player_url = self._extract_player_responses(
3136 self._get_requested_clients(url, smuggled_data),
3137 video_id, webpage, master_ytcfg)
3138
3139 return webpage, master_ytcfg, player_responses, player_url
3140
3141 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3142 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3143 is_live = get_first(video_details, 'isLive')
3144 if is_live is None:
3145 is_live = get_first(live_broadcast_details, 'isLiveNow')
3146
3147 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3148 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3149
3150 return live_broadcast_details, is_live, streaming_data, formats
3151
3152 def _real_extract(self, url):
3153 url, smuggled_data = unsmuggle_url(url, {})
3154 video_id = self._match_id(url)
3155
3156 base_url = self.http_scheme() + '//www.youtube.com/'
3157 webpage_url = base_url + 'watch?v=' + video_id
3158
3159 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3160
3161 playability_statuses = traverse_obj(
3162 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3163
3164 trailer_video_id = get_first(
3165 playability_statuses,
3166 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3167 expected_type=str)
3168 if trailer_video_id:
3169 return self.url_result(
3170 trailer_video_id, self.ie_key(), trailer_video_id)
3171
3172 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3173 if webpage else (lambda x: None))
3174
3175 video_details = traverse_obj(
3176 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3177 microformats = traverse_obj(
3178 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3179 expected_type=dict, default=[])
3180 video_title = (
3181 get_first(video_details, 'title')
3182 or self._get_text(microformats, (..., 'title'))
3183 or search_meta(['og:title', 'twitter:title', 'title']))
3184 video_description = get_first(video_details, 'shortDescription')
3185
3186 multifeed_metadata_list = get_first(
3187 player_responses,
3188 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3189 expected_type=str)
3190 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3191 if self.get_param('noplaylist'):
3192 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3193 else:
3194 entries = []
3195 feed_ids = []
3196 for feed in multifeed_metadata_list.split(','):
3197 # Unquote should take place before split on comma (,) since textual
3198 # fields may contain comma as well (see
3199 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3200 feed_data = compat_parse_qs(
3201 compat_urllib_parse_unquote_plus(feed))
3202
3203 def feed_entry(name):
3204 return try_get(
3205 feed_data, lambda x: x[name][0], compat_str)
3206
3207 feed_id = feed_entry('id')
3208 if not feed_id:
3209 continue
3210 feed_title = feed_entry('title')
3211 title = video_title
3212 if feed_title:
3213 title += ' (%s)' % feed_title
3214 entries.append({
3215 '_type': 'url_transparent',
3216 'ie_key': 'Youtube',
3217 'url': smuggle_url(
3218 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3219 {'force_singlefeed': True}),
3220 'title': title,
3221 })
3222 feed_ids.append(feed_id)
3223 self.to_screen(
3224 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3225 % (', '.join(feed_ids), video_id))
3226 return self.playlist_result(
3227 entries, video_id, video_title, video_description)
3228
3229 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
3230
3231 if not formats:
3232 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3233 self.report_drm(video_id)
3234 pemr = get_first(
3235 playability_statuses,
3236 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3237 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3238 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3239 if subreason:
3240 if subreason == 'The uploader has not made this video available in your country.':
3241 countries = get_first(microformats, 'availableCountries')
3242 if not countries:
3243 regions_allowed = search_meta('regionsAllowed')
3244 countries = regions_allowed.split(',') if regions_allowed else None
3245 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3246 reason += f'. {subreason}'
3247 if reason:
3248 self.raise_no_formats(reason, expected=True)
3249
3250 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3251 if not keywords and webpage:
3252 keywords = [
3253 unescapeHTML(m.group('content'))
3254 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3255 for keyword in keywords:
3256 if keyword.startswith('yt:stretch='):
3257 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3258 if mobj:
3259 # NB: float is intentional for forcing float division
3260 w, h = (float(v) for v in mobj.groups())
3261 if w > 0 and h > 0:
3262 ratio = w / h
3263 for f in formats:
3264 if f.get('vcodec') != 'none':
3265 f['stretched_ratio'] = ratio
3266 break
3267 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3268 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3269 if thumbnail_url:
3270 thumbnails.append({
3271 'url': thumbnail_url,
3272 })
3273 original_thumbnails = thumbnails.copy()
3274
3275 # The best resolution thumbnails sometimes does not appear in the webpage
3276 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3277 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3278 thumbnail_names = [
3279 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3280 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3281 'mqdefault', 'mq1', 'mq2', 'mq3',
3282 'default', '1', '2', '3'
3283 ]
3284 n_thumbnail_names = len(thumbnail_names)
3285 thumbnails.extend({
3286 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3287 video_id=video_id, name=name, ext=ext,
3288 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3289 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3290 for thumb in thumbnails:
3291 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3292 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3293 self._remove_duplicate_formats(thumbnails)
3294 self._downloader._sort_thumbnails(original_thumbnails)
3295
3296 category = get_first(microformats, 'category') or search_meta('genre')
3297 channel_id = str_or_none(
3298 get_first(video_details, 'channelId')
3299 or get_first(microformats, 'externalChannelId')
3300 or search_meta('channelId'))
3301 duration = int_or_none(
3302 get_first(video_details, 'lengthSeconds')
3303 or get_first(microformats, 'lengthSeconds')
3304 or parse_duration(search_meta('duration'))) or None
3305 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3306
3307 live_content = get_first(video_details, 'isLiveContent')
3308 is_upcoming = get_first(video_details, 'isUpcoming')
3309 if is_live is None:
3310 if is_upcoming or live_content is False:
3311 is_live = False
3312 if is_upcoming is None and (live_content or is_live):
3313 is_upcoming = False
3314 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3315 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3316 if not duration and live_end_time and live_start_time:
3317 duration = live_end_time - live_start_time
3318
3319 if is_live and self.get_param('live_from_start'):
3320 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3321
3322 formats.extend(self._extract_storyboard(player_responses, duration))
3323
3324 # Source is given priority since formats that throttle are given lower source_preference
3325 # When throttling issue is fully fixed, remove this
3326 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3327
3328 info = {
3329 'id': video_id,
3330 'title': video_title,
3331 'formats': formats,
3332 'thumbnails': thumbnails,
3333 # The best thumbnail that we are sure exists. Prevents unnecessary
3334 # URL checking if user don't care about getting the best possible thumbnail
3335 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3336 'description': video_description,
3337 'upload_date': unified_strdate(
3338 get_first(microformats, 'uploadDate')
3339 or search_meta('uploadDate')),
3340 'uploader': get_first(video_details, 'author'),
3341 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3342 'uploader_url': owner_profile_url,
3343 'channel_id': channel_id,
3344 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3345 'duration': duration,
3346 'view_count': int_or_none(
3347 get_first((video_details, microformats), (..., 'viewCount'))
3348 or search_meta('interactionCount')),
3349 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3350 'age_limit': 18 if (
3351 get_first(microformats, 'isFamilySafe') is False
3352 or search_meta('isFamilyFriendly') == 'false'
3353 or search_meta('og:restrictions:age') == '18+') else 0,
3354 'webpage_url': webpage_url,
3355 'categories': [category] if category else None,
3356 'tags': keywords,
3357 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3358 'is_live': is_live,
3359 'was_live': (False if is_live or is_upcoming or live_content is False
3360 else None if is_live is None or is_upcoming is None
3361 else live_content),
3362 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3363 'release_timestamp': live_start_time,
3364 }
3365
3366 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3367 if pctr:
3368 def get_lang_code(track):
3369 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3370 or track.get('languageCode'))
3371
3372 # Converted into dicts to remove duplicates
3373 captions = {
3374 get_lang_code(sub): sub
3375 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3376 translation_languages = {
3377 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3378 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3379
3380 def process_language(container, base_url, lang_code, sub_name, query):
3381 lang_subs = container.setdefault(lang_code, [])
3382 for fmt in self._SUBTITLE_FORMATS:
3383 query.update({
3384 'fmt': fmt,
3385 })
3386 lang_subs.append({
3387 'ext': fmt,
3388 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3389 'name': sub_name,
3390 })
3391
3392 subtitles, automatic_captions = {}, {}
3393 for lang_code, caption_track in captions.items():
3394 base_url = caption_track.get('baseUrl')
3395 if not base_url:
3396 continue
3397 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3398 if caption_track.get('kind') != 'asr':
3399 if not lang_code:
3400 continue
3401 process_language(
3402 subtitles, base_url, lang_code, lang_name, {})
3403 if not caption_track.get('isTranslatable'):
3404 continue
3405 for trans_code, trans_name in translation_languages.items():
3406 if not trans_code:
3407 continue
3408 if caption_track.get('kind') != 'asr':
3409 trans_code += f'-{lang_code}'
3410 trans_name += format_field(lang_name, template=' from %s')
3411 process_language(
3412 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3413 if lang_code == f'a-{trans_code}':
3414 process_language(
3415 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {'tlang': trans_code})
3416 info['automatic_captions'] = automatic_captions
3417 info['subtitles'] = subtitles
3418
3419 parsed_url = compat_urllib_parse_urlparse(url)
3420 for component in [parsed_url.fragment, parsed_url.query]:
3421 query = compat_parse_qs(component)
3422 for k, v in query.items():
3423 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3424 d_k += '_time'
3425 if d_k not in info and k in s_ks:
3426 info[d_k] = parse_duration(query[k][0])
3427
3428 # Youtube Music Auto-generated description
3429 if video_description:
3430 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)
3431 if mobj:
3432 release_year = mobj.group('release_year')
3433 release_date = mobj.group('release_date')
3434 if release_date:
3435 release_date = release_date.replace('-', '')
3436 if not release_year:
3437 release_year = release_date[:4]
3438 info.update({
3439 'album': mobj.group('album'.strip()),
3440 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3441 'track': mobj.group('track').strip(),
3442 'release_date': release_date,
3443 'release_year': int_or_none(release_year),
3444 })
3445
3446 initial_data = None
3447 if webpage:
3448 initial_data = self._extract_yt_initial_variable(
3449 webpage, self._YT_INITIAL_DATA_RE, video_id,
3450 'yt initial data')
3451 if not initial_data:
3452 query = {'videoId': video_id}
3453 query.update(self._get_checkok_params())
3454 initial_data = self._extract_response(
3455 item_id=video_id, ep='next', fatal=False,
3456 ytcfg=master_ytcfg, query=query,
3457 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3458 note='Downloading initial data API JSON')
3459
3460 try:
3461 # This will error if there is no livechat
3462 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3463 info.setdefault('subtitles', {})['live_chat'] = [{
3464 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3465 'video_id': video_id,
3466 'ext': 'json',
3467 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3468 }]
3469 except (KeyError, IndexError, TypeError):
3470 pass
3471
3472 if initial_data:
3473 info['chapters'] = (
3474 self._extract_chapters_from_json(initial_data, duration)
3475 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3476 or None)
3477
3478 contents = try_get(
3479 initial_data,
3480 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3481 list) or []
3482 for content in contents:
3483 vpir = content.get('videoPrimaryInfoRenderer')
3484 if vpir:
3485 stl = vpir.get('superTitleLink')
3486 if stl:
3487 stl = self._get_text(stl)
3488 if try_get(
3489 vpir,
3490 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3491 info['location'] = stl
3492 else:
3493 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3494 if mobj:
3495 info.update({
3496 'series': mobj.group(1),
3497 'season_number': int(mobj.group(2)),
3498 'episode_number': int(mobj.group(3)),
3499 })
3500 for tlb in (try_get(
3501 vpir,
3502 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3503 list) or []):
3504 tbr = tlb.get('toggleButtonRenderer') or {}
3505 for getter, regex in [(
3506 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3507 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3508 lambda x: x['accessibility'],
3509 lambda x: x['accessibilityData']['accessibilityData'],
3510 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3511 label = (try_get(tbr, getter, dict) or {}).get('label')
3512 if label:
3513 mobj = re.match(regex, label)
3514 if mobj:
3515 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3516 break
3517 sbr_tooltip = try_get(
3518 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3519 if sbr_tooltip:
3520 like_count, dislike_count = sbr_tooltip.split(' / ')
3521 info.update({
3522 'like_count': str_to_int(like_count),
3523 'dislike_count': str_to_int(dislike_count),
3524 })
3525 vsir = content.get('videoSecondaryInfoRenderer')
3526 if vsir:
3527 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3528 info.update({
3529 'channel': self._get_text(vor, 'title'),
3530 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3531
3532 rows = try_get(
3533 vsir,
3534 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3535 list) or []
3536 multiple_songs = False
3537 for row in rows:
3538 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3539 multiple_songs = True
3540 break
3541 for row in rows:
3542 mrr = row.get('metadataRowRenderer') or {}
3543 mrr_title = mrr.get('title')
3544 if not mrr_title:
3545 continue
3546 mrr_title = self._get_text(mrr, 'title')
3547 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3548 if mrr_title == 'License':
3549 info['license'] = mrr_contents_text
3550 elif not multiple_songs:
3551 if mrr_title == 'Album':
3552 info['album'] = mrr_contents_text
3553 elif mrr_title == 'Artist':
3554 info['artist'] = mrr_contents_text
3555 elif mrr_title == 'Song':
3556 info['track'] = mrr_contents_text
3557
3558 fallbacks = {
3559 'channel': 'uploader',
3560 'channel_id': 'uploader_id',
3561 'channel_url': 'uploader_url',
3562 }
3563 for to, frm in fallbacks.items():
3564 if not info.get(to):
3565 info[to] = info.get(frm)
3566
3567 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3568 v = info.get(s_k)
3569 if v:
3570 info[d_k] = v
3571
3572 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3573 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3574 is_membersonly = None
3575 is_premium = None
3576 if initial_data and is_private is not None:
3577 is_membersonly = False
3578 is_premium = False
3579 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3580 badge_labels = set()
3581 for content in contents:
3582 if not isinstance(content, dict):
3583 continue
3584 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3585 for badge_label in badge_labels:
3586 if badge_label.lower() == 'members only':
3587 is_membersonly = True
3588 elif badge_label.lower() == 'premium':
3589 is_premium = True
3590 elif badge_label.lower() == 'unlisted':
3591 is_unlisted = True
3592
3593 info['availability'] = self._availability(
3594 is_private=is_private,
3595 needs_premium=is_premium,
3596 needs_subscription=is_membersonly,
3597 needs_auth=info['age_limit'] >= 18,
3598 is_unlisted=None if is_private is None else is_unlisted)
3599
3600 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3601
3602 self.mark_watched(video_id, player_responses)
3603
3604 return info
3605
3606
3607 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3608
3609 @staticmethod
3610 def passthrough_smuggled_data(func):
3611 def _smuggle(entries, smuggled_data):
3612 for entry in entries:
3613 # TODO: Convert URL to music.youtube instead.
3614 # Do we need to passthrough any other smuggled_data?
3615 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3616 yield entry
3617
3618 @functools.wraps(func)
3619 def wrapper(self, url):
3620 url, smuggled_data = unsmuggle_url(url, {})
3621 if self.is_music_url(url):
3622 smuggled_data['is_music_url'] = True
3623 info_dict = func(self, url, smuggled_data)
3624 if smuggled_data and info_dict.get('entries'):
3625 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3626 return info_dict
3627 return wrapper
3628
3629 def _extract_channel_id(self, webpage):
3630 channel_id = self._html_search_meta(
3631 'channelId', webpage, 'channel id', default=None)
3632 if channel_id:
3633 return channel_id
3634 channel_url = self._html_search_meta(
3635 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3636 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3637 'twitter:app:url:googleplay'), webpage, 'channel url')
3638 return self._search_regex(
3639 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3640 channel_url, 'channel id')
3641
3642 @staticmethod
3643 def _extract_basic_item_renderer(item):
3644 # Modified from _extract_grid_item_renderer
3645 known_basic_renderers = (
3646 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3647 )
3648 for key, renderer in item.items():
3649 if not isinstance(renderer, dict):
3650 continue
3651 elif key in known_basic_renderers:
3652 return renderer
3653 elif key.startswith('grid') and key.endswith('Renderer'):
3654 return renderer
3655
3656 def _grid_entries(self, grid_renderer):
3657 for item in grid_renderer['items']:
3658 if not isinstance(item, dict):
3659 continue
3660 renderer = self._extract_basic_item_renderer(item)
3661 if not isinstance(renderer, dict):
3662 continue
3663 title = self._get_text(renderer, 'title')
3664
3665 # playlist
3666 playlist_id = renderer.get('playlistId')
3667 if playlist_id:
3668 yield self.url_result(
3669 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3670 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3671 video_title=title)
3672 continue
3673 # video
3674 video_id = renderer.get('videoId')
3675 if video_id:
3676 yield self._extract_video(renderer)
3677 continue
3678 # channel
3679 channel_id = renderer.get('channelId')
3680 if channel_id:
3681 yield self.url_result(
3682 'https://www.youtube.com/channel/%s' % channel_id,
3683 ie=YoutubeTabIE.ie_key(), video_title=title)
3684 continue
3685 # generic endpoint URL support
3686 ep_url = urljoin('https://www.youtube.com/', try_get(
3687 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3688 compat_str))
3689 if ep_url:
3690 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3691 if ie.suitable(ep_url):
3692 yield self.url_result(
3693 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3694 break
3695
3696 def _music_reponsive_list_entry(self, renderer):
3697 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3698 if video_id:
3699 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3700 ie=YoutubeIE.ie_key(), video_id=video_id)
3701 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3702 if playlist_id:
3703 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3704 if video_id:
3705 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3706 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3707 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3708 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3709 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3710 if browse_id:
3711 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3712 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3713
3714 def _shelf_entries_from_content(self, shelf_renderer):
3715 content = shelf_renderer.get('content')
3716 if not isinstance(content, dict):
3717 return
3718 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3719 if renderer:
3720 # TODO: add support for nested playlists so each shelf is processed
3721 # as separate playlist
3722 # TODO: this includes only first N items
3723 for entry in self._grid_entries(renderer):
3724 yield entry
3725 renderer = content.get('horizontalListRenderer')
3726 if renderer:
3727 # TODO
3728 pass
3729
3730 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3731 ep = try_get(
3732 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3733 compat_str)
3734 shelf_url = urljoin('https://www.youtube.com', ep)
3735 if shelf_url:
3736 # Skipping links to another channels, note that checking for
3737 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3738 # will not work
3739 if skip_channels and '/channels?' in shelf_url:
3740 return
3741 title = self._get_text(shelf_renderer, 'title')
3742 yield self.url_result(shelf_url, video_title=title)
3743 # Shelf may not contain shelf URL, fallback to extraction from content
3744 for entry in self._shelf_entries_from_content(shelf_renderer):
3745 yield entry
3746
3747 def _playlist_entries(self, video_list_renderer):
3748 for content in video_list_renderer['contents']:
3749 if not isinstance(content, dict):
3750 continue
3751 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3752 if not isinstance(renderer, dict):
3753 continue
3754 video_id = renderer.get('videoId')
3755 if not video_id:
3756 continue
3757 yield self._extract_video(renderer)
3758
3759 def _rich_entries(self, rich_grid_renderer):
3760 renderer = try_get(
3761 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3762 video_id = renderer.get('videoId')
3763 if not video_id:
3764 return
3765 yield self._extract_video(renderer)
3766
3767 def _video_entry(self, video_renderer):
3768 video_id = video_renderer.get('videoId')
3769 if video_id:
3770 return self._extract_video(video_renderer)
3771
3772 def _post_thread_entries(self, post_thread_renderer):
3773 post_renderer = try_get(
3774 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3775 if not post_renderer:
3776 return
3777 # video attachment
3778 video_renderer = try_get(
3779 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3780 video_id = video_renderer.get('videoId')
3781 if video_id:
3782 entry = self._extract_video(video_renderer)
3783 if entry:
3784 yield entry
3785 # playlist attachment
3786 playlist_id = try_get(
3787 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3788 if playlist_id:
3789 yield self.url_result(
3790 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3791 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3792 # inline video links
3793 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3794 for run in runs:
3795 if not isinstance(run, dict):
3796 continue
3797 ep_url = try_get(
3798 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3799 if not ep_url:
3800 continue
3801 if not YoutubeIE.suitable(ep_url):
3802 continue
3803 ep_video_id = YoutubeIE._match_id(ep_url)
3804 if video_id == ep_video_id:
3805 continue
3806 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3807
3808 def _post_thread_continuation_entries(self, post_thread_continuation):
3809 contents = post_thread_continuation.get('contents')
3810 if not isinstance(contents, list):
3811 return
3812 for content in contents:
3813 renderer = content.get('backstagePostThreadRenderer')
3814 if not isinstance(renderer, dict):
3815 continue
3816 for entry in self._post_thread_entries(renderer):
3817 yield entry
3818
3819 r''' # unused
3820 def _rich_grid_entries(self, contents):
3821 for content in contents:
3822 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3823 if video_renderer:
3824 entry = self._video_entry(video_renderer)
3825 if entry:
3826 yield entry
3827 '''
3828 def _extract_entries(self, parent_renderer, continuation_list):
3829 # continuation_list is modified in-place with continuation_list = [continuation_token]
3830 continuation_list[:] = [None]
3831 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3832 for content in contents:
3833 if not isinstance(content, dict):
3834 continue
3835 is_renderer = traverse_obj(
3836 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3837 expected_type=dict)
3838 if not is_renderer:
3839 renderer = content.get('richItemRenderer')
3840 if renderer:
3841 for entry in self._rich_entries(renderer):
3842 yield entry
3843 continuation_list[0] = self._extract_continuation(parent_renderer)
3844 continue
3845 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3846 for isr_content in isr_contents:
3847 if not isinstance(isr_content, dict):
3848 continue
3849
3850 known_renderers = {
3851 'playlistVideoListRenderer': self._playlist_entries,
3852 'gridRenderer': self._grid_entries,
3853 'shelfRenderer': lambda x: self._shelf_entries(x),
3854 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
3855 'backstagePostThreadRenderer': self._post_thread_entries,
3856 'videoRenderer': lambda x: [self._video_entry(x)],
3857 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3858 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
3859 }
3860 for key, renderer in isr_content.items():
3861 if key not in known_renderers:
3862 continue
3863 for entry in known_renderers[key](renderer):
3864 if entry:
3865 yield entry
3866 continuation_list[0] = self._extract_continuation(renderer)
3867 break
3868
3869 if not continuation_list[0]:
3870 continuation_list[0] = self._extract_continuation(is_renderer)
3871
3872 if not continuation_list[0]:
3873 continuation_list[0] = self._extract_continuation(parent_renderer)
3874
3875 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3876 continuation_list = [None]
3877 extract_entries = lambda x: self._extract_entries(x, continuation_list)
3878 tab_content = try_get(tab, lambda x: x['content'], dict)
3879 if not tab_content:
3880 return
3881 parent_renderer = (
3882 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3883 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3884 for entry in extract_entries(parent_renderer):
3885 yield entry
3886 continuation = continuation_list[0]
3887
3888 for page_num in itertools.count(1):
3889 if not continuation:
3890 break
3891 headers = self.generate_api_headers(
3892 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
3893 response = self._extract_response(
3894 item_id='%s page %s' % (item_id, page_num),
3895 query=continuation, headers=headers, ytcfg=ytcfg,
3896 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3897
3898 if not response:
3899 break
3900 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3901 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3902 visitor_data = self._extract_visitor_data(response) or visitor_data
3903
3904 known_continuation_renderers = {
3905 'playlistVideoListContinuation': self._playlist_entries,
3906 'gridContinuation': self._grid_entries,
3907 'itemSectionContinuation': self._post_thread_continuation_entries,
3908 'sectionListContinuation': extract_entries, # for feeds
3909 }
3910 continuation_contents = try_get(
3911 response, lambda x: x['continuationContents'], dict) or {}
3912 continuation_renderer = None
3913 for key, value in continuation_contents.items():
3914 if key not in known_continuation_renderers:
3915 continue
3916 continuation_renderer = value
3917 continuation_list = [None]
3918 for entry in known_continuation_renderers[key](continuation_renderer):
3919 yield entry
3920 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3921 break
3922 if continuation_renderer:
3923 continue
3924
3925 known_renderers = {
3926 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3927 'gridVideoRenderer': (self._grid_entries, 'items'),
3928 'gridChannelRenderer': (self._grid_entries, 'items'),
3929 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3930 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3931 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3932 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3933 }
3934 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3935 continuation_items = try_get(
3936 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3937 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3938 video_items_renderer = None
3939 for key, value in continuation_item.items():
3940 if key not in known_renderers:
3941 continue
3942 video_items_renderer = {known_renderers[key][1]: continuation_items}
3943 continuation_list = [None]
3944 for entry in known_renderers[key][0](video_items_renderer):
3945 yield entry
3946 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3947 break
3948 if video_items_renderer:
3949 continue
3950 break
3951
3952 @staticmethod
3953 def _extract_selected_tab(tabs, fatal=True):
3954 for tab in tabs:
3955 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3956 if renderer.get('selected') is True:
3957 return renderer
3958 else:
3959 if fatal:
3960 raise ExtractorError('Unable to find selected tab')
3961
3962 @classmethod
3963 def _extract_uploader(cls, data):
3964 uploader = {}
3965 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3966 owner = try_get(
3967 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3968 if owner:
3969 uploader['uploader'] = owner.get('text')
3970 uploader['uploader_id'] = try_get(
3971 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3972 uploader['uploader_url'] = urljoin(
3973 'https://www.youtube.com/',
3974 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3975 return {k: v for k, v in uploader.items() if v is not None}
3976
3977 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
3978 playlist_id = title = description = channel_url = channel_name = channel_id = None
3979 tags = []
3980
3981 selected_tab = self._extract_selected_tab(tabs)
3982 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
3983 renderer = try_get(
3984 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3985 if renderer:
3986 channel_name = renderer.get('title')
3987 channel_url = renderer.get('channelUrl')
3988 channel_id = renderer.get('externalId')
3989 else:
3990 renderer = try_get(
3991 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3992
3993 if renderer:
3994 title = renderer.get('title')
3995 description = renderer.get('description', '')
3996 playlist_id = channel_id
3997 tags = renderer.get('keywords', '').split()
3998
3999 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4000 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4001 def _get_uncropped(url):
4002 return url_or_none((url or '').split('=')[0] + '=s0')
4003
4004 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4005 if avatar_thumbnails:
4006 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4007 if uncropped_avatar:
4008 avatar_thumbnails.append({
4009 'url': uncropped_avatar,
4010 'id': 'avatar_uncropped',
4011 'preference': 1
4012 })
4013
4014 channel_banners = self._extract_thumbnails(
4015 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4016 for banner in channel_banners:
4017 banner['preference'] = -10
4018
4019 if channel_banners:
4020 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4021 if uncropped_banner:
4022 channel_banners.append({
4023 'url': uncropped_banner,
4024 'id': 'banner_uncropped',
4025 'preference': -5
4026 })
4027
4028 primary_thumbnails = self._extract_thumbnails(
4029 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
4030
4031 if playlist_id is None:
4032 playlist_id = item_id
4033
4034 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4035 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
4036 if title is None:
4037 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4038 title += format_field(selected_tab, 'title', ' - %s')
4039 title += format_field(selected_tab, 'expandedText', ' - %s')
4040
4041 metadata = {
4042 'playlist_id': playlist_id,
4043 'playlist_title': title,
4044 'playlist_description': description,
4045 'uploader': channel_name,
4046 'uploader_id': channel_id,
4047 'uploader_url': channel_url,
4048 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4049 'tags': tags,
4050 'view_count': self._get_count(playlist_stats, 1),
4051 'availability': self._extract_availability(data),
4052 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4053 'playlist_count': self._get_count(playlist_stats, 0),
4054 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4055 }
4056 if not channel_id:
4057 metadata.update(self._extract_uploader(data))
4058 metadata.update({
4059 'channel': metadata['uploader'],
4060 'channel_id': metadata['uploader_id'],
4061 'channel_url': metadata['uploader_url']})
4062 return self.playlist_result(
4063 self._entries(
4064 selected_tab, playlist_id, ytcfg,
4065 self._extract_account_syncid(ytcfg, data),
4066 self._extract_visitor_data(data, ytcfg)),
4067 **metadata)
4068
4069 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4070 first_id = last_id = response = None
4071 for page_num in itertools.count(1):
4072 videos = list(self._playlist_entries(playlist))
4073 if not videos:
4074 return
4075 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4076 if start >= len(videos):
4077 return
4078 for video in videos[start:]:
4079 if video['id'] == first_id:
4080 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4081 return
4082 yield video
4083 first_id = first_id or videos[0]['id']
4084 last_id = videos[-1]['id']
4085 watch_endpoint = try_get(
4086 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4087 headers = self.generate_api_headers(
4088 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4089 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4090 query = {
4091 'playlistId': playlist_id,
4092 'videoId': watch_endpoint.get('videoId') or last_id,
4093 'index': watch_endpoint.get('index') or len(videos),
4094 'params': watch_endpoint.get('params') or 'OAE%3D'
4095 }
4096 response = self._extract_response(
4097 item_id='%s page %d' % (playlist_id, page_num),
4098 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4099 check_get_keys='contents'
4100 )
4101 playlist = try_get(
4102 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4103
4104 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4105 title = playlist.get('title') or try_get(
4106 data, lambda x: x['titleText']['simpleText'], compat_str)
4107 playlist_id = playlist.get('playlistId') or item_id
4108
4109 # Delegating everything except mix playlists to regular tab-based playlist URL
4110 playlist_url = urljoin(url, try_get(
4111 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4112 compat_str))
4113 if playlist_url and playlist_url != url:
4114 return self.url_result(
4115 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4116 video_title=title)
4117
4118 return self.playlist_result(
4119 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4120 playlist_id=playlist_id, playlist_title=title)
4121
4122 def _extract_availability(self, data):
4123 """
4124 Gets the availability of a given playlist/tab.
4125 Note: Unless YouTube tells us explicitly, we do not assume it is public
4126 @param data: response
4127 """
4128 is_private = is_unlisted = None
4129 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4130 badge_labels = self._extract_badges(renderer)
4131
4132 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4133 privacy_dropdown_entries = try_get(
4134 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4135 for renderer_dict in privacy_dropdown_entries:
4136 is_selected = try_get(
4137 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4138 if not is_selected:
4139 continue
4140 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4141 if label:
4142 badge_labels.add(label.lower())
4143 break
4144
4145 for badge_label in badge_labels:
4146 if badge_label == 'unlisted':
4147 is_unlisted = True
4148 elif badge_label == 'private':
4149 is_private = True
4150 elif badge_label == 'public':
4151 is_unlisted = is_private = False
4152 return self._availability(is_private, False, False, False, is_unlisted)
4153
4154 @staticmethod
4155 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4156 sidebar_renderer = try_get(
4157 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4158 for item in sidebar_renderer:
4159 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4160 if renderer:
4161 return renderer
4162
4163 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4164 """
4165 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4166 """
4167 browse_id = params = None
4168 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4169 if not renderer:
4170 return
4171 menu_renderer = try_get(
4172 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4173 for menu_item in menu_renderer:
4174 if not isinstance(menu_item, dict):
4175 continue
4176 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4177 text = try_get(
4178 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4179 if not text or text.lower() != 'show unavailable videos':
4180 continue
4181 browse_endpoint = try_get(
4182 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4183 browse_id = browse_endpoint.get('browseId')
4184 params = browse_endpoint.get('params')
4185 break
4186
4187 headers = self.generate_api_headers(
4188 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4189 visitor_data=self._extract_visitor_data(data, ytcfg))
4190 query = {
4191 'params': params or 'wgYCCAA=',
4192 'browseId': browse_id or 'VL%s' % item_id
4193 }
4194 return self._extract_response(
4195 item_id=item_id, headers=headers, query=query,
4196 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4197 note='Downloading API JSON with unavailable videos')
4198
4199 def _extract_webpage(self, url, item_id, fatal=True):
4200 retries = self.get_param('extractor_retries', 3)
4201 count = -1
4202 webpage = data = last_error = None
4203 while count < retries:
4204 count += 1
4205 # Sometimes youtube returns a webpage with incomplete ytInitialData
4206 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4207 if last_error:
4208 self.report_warning('%s. Retrying ...' % last_error)
4209 try:
4210 webpage = self._download_webpage(
4211 url, item_id,
4212 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4213 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4214 except ExtractorError as e:
4215 if isinstance(e.cause, network_exceptions):
4216 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4217 last_error = error_to_compat_str(e.cause or e.msg)
4218 if count < retries:
4219 continue
4220 if fatal:
4221 raise
4222 self.report_warning(error_to_compat_str(e))
4223 break
4224 else:
4225 try:
4226 self._extract_and_report_alerts(data)
4227 except ExtractorError as e:
4228 if fatal:
4229 raise
4230 self.report_warning(error_to_compat_str(e))
4231 break
4232
4233 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4234 break
4235
4236 last_error = 'Incomplete yt initial data received'
4237 if count >= retries:
4238 if fatal:
4239 raise ExtractorError(last_error)
4240 self.report_warning(last_error)
4241 break
4242
4243 return webpage, data
4244
4245 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4246 data = None
4247 if 'webpage' not in self._configuration_arg('skip'):
4248 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4249 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4250 # Reject webpage data if redirected to home page without explicitly requesting
4251 selected_tab = self._extract_selected_tab(traverse_obj(
4252 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4253 if (url != 'https://www.youtube.com/feed/recommended'
4254 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4255 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4256 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4257 if fatal:
4258 raise ExtractorError(msg, expected=True)
4259 self.report_warning(msg, only_once=True)
4260 if not data:
4261 if not ytcfg and self.is_authenticated:
4262 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4263 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4264 raise ExtractorError(
4265 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4266 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4267 expected=True)
4268 self.report_warning(msg, only_once=True)
4269 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4270 return data, ytcfg
4271
4272 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4273 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4274 resolve_response = self._extract_response(
4275 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4276 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4277 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4278 for ep_key, ep in endpoints.items():
4279 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4280 if params:
4281 return self._extract_response(
4282 item_id=item_id, query=params, ep=ep, headers=headers,
4283 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4284 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4285 err_note = 'Failed to resolve url (does the playlist exist?)'
4286 if fatal:
4287 raise ExtractorError(err_note, expected=True)
4288 self.report_warning(err_note, item_id)
4289
4290 _SEARCH_PARAMS = None
4291
4292 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4293 data = {'query': query}
4294 if params is NO_DEFAULT:
4295 params = self._SEARCH_PARAMS
4296 if params:
4297 data['params'] = params
4298
4299 content_keys = (
4300 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4301 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4302 # ytmusic search
4303 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4304 ('continuationContents', ),
4305 )
4306 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4307
4308 continuation_list = [None]
4309 for page_num in itertools.count(1):
4310 data.update(continuation_list[0] or {})
4311 search = self._extract_response(
4312 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4313 default_client=default_client, check_get_keys=check_get_keys)
4314 slr_contents = traverse_obj(search, *content_keys)
4315 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4316 if not continuation_list[0]:
4317 break
4318
4319
4320 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4321 IE_DESC = 'YouTube Tabs'
4322 _VALID_URL = r'''(?x:
4323 https?://
4324 (?:\w+\.)?
4325 (?:
4326 youtube(?:kids)?\.com|
4327 %(invidious)s
4328 )/
4329 (?:
4330 (?P<channel_type>channel|c|user|browse)/|
4331 (?P<not_channel>
4332 feed/|hashtag/|
4333 (?:playlist|watch)\?.*?\blist=
4334 )|
4335 (?!(?:%(reserved_names)s)\b) # Direct URLs
4336 )
4337 (?P<id>[^/?\#&]+)
4338 )''' % {
4339 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4340 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4341 }
4342 IE_NAME = 'youtube:tab'
4343
4344 _TESTS = [{
4345 'note': 'playlists, multipage',
4346 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4347 'playlist_mincount': 94,
4348 'info_dict': {
4349 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4350 'title': 'Igor Kleiner - Playlists',
4351 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4352 'uploader': 'Igor Kleiner',
4353 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4354 'channel': 'Igor Kleiner',
4355 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4356 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4357 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4358 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4359 'channel_follower_count': int
4360 },
4361 }, {
4362 'note': 'playlists, multipage, different order',
4363 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4364 'playlist_mincount': 94,
4365 'info_dict': {
4366 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4367 'title': 'Igor Kleiner - Playlists',
4368 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4369 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4370 'uploader': 'Igor Kleiner',
4371 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4372 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4373 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4374 'channel': 'Igor Kleiner',
4375 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4376 'channel_follower_count': int
4377 },
4378 }, {
4379 'note': 'playlists, series',
4380 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4381 'playlist_mincount': 5,
4382 'info_dict': {
4383 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4384 'title': '3Blue1Brown - Playlists',
4385 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4386 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4387 'uploader': '3Blue1Brown',
4388 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4389 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4390 'channel': '3Blue1Brown',
4391 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4392 'tags': ['Mathematics'],
4393 'channel_follower_count': int
4394 },
4395 }, {
4396 'note': 'playlists, singlepage',
4397 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4398 'playlist_mincount': 4,
4399 'info_dict': {
4400 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4401 'title': 'ThirstForScience - Playlists',
4402 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4403 'uploader': 'ThirstForScience',
4404 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4405 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4406 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4407 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4408 'tags': 'count:13',
4409 'channel': 'ThirstForScience',
4410 'channel_follower_count': int
4411 }
4412 }, {
4413 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4414 'only_matching': True,
4415 }, {
4416 'note': 'basic, single video playlist',
4417 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4418 'info_dict': {
4419 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4420 'uploader': 'Sergey M.',
4421 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4422 'title': 'youtube-dl public playlist',
4423 'description': '',
4424 'tags': [],
4425 'view_count': int,
4426 'modified_date': '20201130',
4427 'channel': 'Sergey M.',
4428 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4429 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4430 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4431 },
4432 'playlist_count': 1,
4433 }, {
4434 'note': 'empty playlist',
4435 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4436 'info_dict': {
4437 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4438 'uploader': 'Sergey M.',
4439 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4440 'title': 'youtube-dl empty playlist',
4441 'tags': [],
4442 'channel': 'Sergey M.',
4443 'description': '',
4444 'modified_date': '20160902',
4445 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4446 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4447 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4448 },
4449 'playlist_count': 0,
4450 }, {
4451 'note': 'Home tab',
4452 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4453 'info_dict': {
4454 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4455 'title': 'lex will - Home',
4456 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4457 'uploader': 'lex will',
4458 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4459 'channel': 'lex will',
4460 'tags': ['bible', 'history', 'prophesy'],
4461 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4462 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4463 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4464 'channel_follower_count': int
4465 },
4466 'playlist_mincount': 2,
4467 }, {
4468 'note': 'Videos tab',
4469 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4470 'info_dict': {
4471 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4472 'title': 'lex will - Videos',
4473 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4474 'uploader': 'lex will',
4475 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4476 'tags': ['bible', 'history', 'prophesy'],
4477 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4478 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4479 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4480 'channel': 'lex will',
4481 'channel_follower_count': int
4482 },
4483 'playlist_mincount': 975,
4484 }, {
4485 'note': 'Videos tab, sorted by popular',
4486 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4487 'info_dict': {
4488 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4489 'title': 'lex will - Videos',
4490 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4491 'uploader': 'lex will',
4492 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4493 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4494 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4495 'channel': 'lex will',
4496 'tags': ['bible', 'history', 'prophesy'],
4497 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4498 'channel_follower_count': int
4499 },
4500 'playlist_mincount': 199,
4501 }, {
4502 'note': 'Playlists tab',
4503 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4504 'info_dict': {
4505 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4506 'title': 'lex will - Playlists',
4507 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4508 'uploader': 'lex will',
4509 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4510 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4511 'channel': 'lex will',
4512 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4513 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4514 'tags': ['bible', 'history', 'prophesy'],
4515 'channel_follower_count': int
4516 },
4517 'playlist_mincount': 17,
4518 }, {
4519 'note': 'Community tab',
4520 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4521 'info_dict': {
4522 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4523 'title': 'lex will - Community',
4524 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4525 'uploader': 'lex will',
4526 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4527 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4528 'channel': 'lex will',
4529 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4530 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4531 'tags': ['bible', 'history', 'prophesy'],
4532 'channel_follower_count': int
4533 },
4534 'playlist_mincount': 18,
4535 }, {
4536 'note': 'Channels tab',
4537 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4538 'info_dict': {
4539 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4540 'title': 'lex will - Channels',
4541 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4542 'uploader': 'lex will',
4543 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4544 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4545 'channel': 'lex will',
4546 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4547 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4548 'tags': ['bible', 'history', 'prophesy'],
4549 'channel_follower_count': int
4550 },
4551 'playlist_mincount': 12,
4552 }, {
4553 'note': 'Search tab',
4554 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4555 'playlist_mincount': 40,
4556 'info_dict': {
4557 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4558 'title': '3Blue1Brown - Search - linear algebra',
4559 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4560 'uploader': '3Blue1Brown',
4561 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4562 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4563 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4564 'tags': ['Mathematics'],
4565 'channel': '3Blue1Brown',
4566 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4567 'channel_follower_count': int
4568 },
4569 }, {
4570 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4571 'only_matching': True,
4572 }, {
4573 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4574 'only_matching': True,
4575 }, {
4576 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4577 'only_matching': True,
4578 }, {
4579 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4580 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4581 'info_dict': {
4582 'title': '29C3: Not my department',
4583 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4584 'uploader': 'Christiaan008',
4585 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4586 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4587 'tags': [],
4588 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4589 'view_count': int,
4590 'modified_date': '20150605',
4591 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4592 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4593 'channel': 'Christiaan008',
4594 },
4595 'playlist_count': 96,
4596 }, {
4597 'note': 'Large playlist',
4598 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4599 'info_dict': {
4600 'title': 'Uploads from Cauchemar',
4601 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4602 'uploader': 'Cauchemar',
4603 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4604 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4605 'tags': [],
4606 'modified_date': r're:\d{8}',
4607 'channel': 'Cauchemar',
4608 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4609 'view_count': int,
4610 'description': '',
4611 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4612 },
4613 'playlist_mincount': 1123,
4614 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4615 }, {
4616 'note': 'even larger playlist, 8832 videos',
4617 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4618 'only_matching': True,
4619 }, {
4620 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4621 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4622 'info_dict': {
4623 'title': 'Uploads from Interstellar Movie',
4624 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4625 'uploader': 'Interstellar Movie',
4626 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4627 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4628 'tags': [],
4629 'view_count': int,
4630 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4631 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4632 'channel': 'Interstellar Movie',
4633 'description': '',
4634 'modified_date': r're:\d{8}',
4635 },
4636 'playlist_mincount': 21,
4637 }, {
4638 'note': 'Playlist with "show unavailable videos" button',
4639 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4640 'info_dict': {
4641 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4642 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4643 'uploader': 'Phim Siêu Nhân Nhật Bản',
4644 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4645 'view_count': int,
4646 'channel': 'Phim Siêu Nhân Nhật Bản',
4647 'tags': [],
4648 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4649 'description': '',
4650 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4651 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4652 'modified_date': r're:\d{8}',
4653 },
4654 'playlist_mincount': 200,
4655 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4656 }, {
4657 'note': 'Playlist with unavailable videos in page 7',
4658 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4659 'info_dict': {
4660 'title': 'Uploads from BlankTV',
4661 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4662 'uploader': 'BlankTV',
4663 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4664 'channel': 'BlankTV',
4665 'channel_url': 'https://www.youtube.com/c/blanktv',
4666 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4667 'view_count': int,
4668 'tags': [],
4669 'uploader_url': 'https://www.youtube.com/c/blanktv',
4670 'modified_date': r're:\d{8}',
4671 'description': '',
4672 },
4673 'playlist_mincount': 1000,
4674 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4675 }, {
4676 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4677 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4678 'info_dict': {
4679 'title': 'Data Analysis with Dr Mike Pound',
4680 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4681 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4682 'uploader': 'Computerphile',
4683 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4684 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4685 'tags': [],
4686 'view_count': int,
4687 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4688 'channel_url': 'https://www.youtube.com/user/Computerphile',
4689 'channel': 'Computerphile',
4690 },
4691 'playlist_mincount': 11,
4692 }, {
4693 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4694 'only_matching': True,
4695 }, {
4696 'note': 'Playlist URL that does not actually serve a playlist',
4697 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4698 'info_dict': {
4699 'id': 'FqZTN594JQw',
4700 'ext': 'webm',
4701 'title': "Smiley's People 01 detective, Adventure Series, Action",
4702 'uploader': 'STREEM',
4703 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4704 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4705 'upload_date': '20150526',
4706 'license': 'Standard YouTube License',
4707 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4708 'categories': ['People & Blogs'],
4709 'tags': list,
4710 'view_count': int,
4711 'like_count': int,
4712 },
4713 'params': {
4714 'skip_download': True,
4715 },
4716 'skip': 'This video is not available.',
4717 'add_ie': [YoutubeIE.ie_key()],
4718 }, {
4719 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4720 'only_matching': True,
4721 }, {
4722 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4723 'only_matching': True,
4724 }, {
4725 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4726 'info_dict': {
4727 'id': 'GgL890LIznQ', # This will keep changing
4728 'ext': 'mp4',
4729 'title': str,
4730 'uploader': 'Sky News',
4731 'uploader_id': 'skynews',
4732 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4733 'upload_date': r're:\d{8}',
4734 'description': str,
4735 'categories': ['News & Politics'],
4736 'tags': list,
4737 'like_count': int,
4738 'release_timestamp': 1642502819,
4739 'channel': 'Sky News',
4740 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4741 'age_limit': 0,
4742 'view_count': int,
4743 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4744 'playable_in_embed': True,
4745 'release_date': '20220118',
4746 'availability': 'public',
4747 'live_status': 'is_live',
4748 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4749 'channel_follower_count': int
4750 },
4751 'params': {
4752 'skip_download': True,
4753 },
4754 'expected_warnings': ['Ignoring subtitle tracks found in '],
4755 }, {
4756 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4757 'info_dict': {
4758 'id': 'a48o2S1cPoo',
4759 'ext': 'mp4',
4760 'title': 'The Young Turks - Live Main Show',
4761 'uploader': 'The Young Turks',
4762 'uploader_id': 'TheYoungTurks',
4763 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4764 'upload_date': '20150715',
4765 'license': 'Standard YouTube License',
4766 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4767 'categories': ['News & Politics'],
4768 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4769 'like_count': int,
4770 },
4771 'params': {
4772 'skip_download': True,
4773 },
4774 'only_matching': True,
4775 }, {
4776 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4777 'only_matching': True,
4778 }, {
4779 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4780 'only_matching': True,
4781 }, {
4782 'note': 'A channel that is not live. Should raise error',
4783 'url': 'https://www.youtube.com/user/numberphile/live',
4784 'only_matching': True,
4785 }, {
4786 'url': 'https://www.youtube.com/feed/trending',
4787 'only_matching': True,
4788 }, {
4789 'url': 'https://www.youtube.com/feed/library',
4790 'only_matching': True,
4791 }, {
4792 'url': 'https://www.youtube.com/feed/history',
4793 'only_matching': True,
4794 }, {
4795 'url': 'https://www.youtube.com/feed/subscriptions',
4796 'only_matching': True,
4797 }, {
4798 'url': 'https://www.youtube.com/feed/watch_later',
4799 'only_matching': True,
4800 }, {
4801 'note': 'Recommended - redirects to home page.',
4802 'url': 'https://www.youtube.com/feed/recommended',
4803 'only_matching': True,
4804 }, {
4805 'note': 'inline playlist with not always working continuations',
4806 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4807 'only_matching': True,
4808 }, {
4809 'url': 'https://www.youtube.com/course',
4810 'only_matching': True,
4811 }, {
4812 'url': 'https://www.youtube.com/zsecurity',
4813 'only_matching': True,
4814 }, {
4815 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4816 'only_matching': True,
4817 }, {
4818 'url': 'https://www.youtube.com/TheYoungTurks/live',
4819 'only_matching': True,
4820 }, {
4821 'url': 'https://www.youtube.com/hashtag/cctv9',
4822 'info_dict': {
4823 'id': 'cctv9',
4824 'title': '#cctv9',
4825 'tags': [],
4826 },
4827 'playlist_mincount': 350,
4828 }, {
4829 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4830 'only_matching': True,
4831 }, {
4832 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4833 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4834 'only_matching': True
4835 }, {
4836 'note': '/browse/ should redirect to /channel/',
4837 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4838 'only_matching': True
4839 }, {
4840 'note': 'VLPL, should redirect to playlist?list=PL...',
4841 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4842 'info_dict': {
4843 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4844 'uploader': 'NoCopyrightSounds',
4845 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4846 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4847 'title': 'NCS Releases',
4848 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4849 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4850 'modified_date': r're:\d{8}',
4851 'view_count': int,
4852 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4853 'tags': [],
4854 'channel': 'NoCopyrightSounds',
4855 },
4856 'playlist_mincount': 166,
4857 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4858 }, {
4859 'note': 'Topic, should redirect to playlist?list=UU...',
4860 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4861 'info_dict': {
4862 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4863 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4864 'title': 'Uploads from Royalty Free Music - Topic',
4865 'uploader': 'Royalty Free Music - Topic',
4866 'tags': [],
4867 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4868 'channel': 'Royalty Free Music - Topic',
4869 'view_count': int,
4870 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4871 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4872 'modified_date': r're:\d{8}',
4873 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4874 'description': '',
4875 },
4876 'expected_warnings': [
4877 'The URL does not have a videos tab',
4878 r'[Uu]navailable videos (are|will be) hidden',
4879 ],
4880 'playlist_mincount': 101,
4881 }, {
4882 'note': 'Topic without a UU playlist',
4883 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4884 'info_dict': {
4885 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4886 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
4887 'tags': [],
4888 },
4889 'expected_warnings': [
4890 'the playlist redirect gave error',
4891 ],
4892 'playlist_mincount': 9,
4893 }, {
4894 'note': 'Youtube music Album',
4895 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4896 'info_dict': {
4897 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4898 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
4899 'tags': [],
4900 'view_count': int,
4901 'description': '',
4902 'availability': 'unlisted',
4903 'modified_date': r're:\d{8}',
4904 },
4905 'playlist_count': 50,
4906 }, {
4907 'note': 'unlisted single video playlist',
4908 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4909 'info_dict': {
4910 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4911 'uploader': 'colethedj',
4912 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4913 'title': 'yt-dlp unlisted playlist test',
4914 'availability': 'unlisted',
4915 'tags': [],
4916 'modified_date': '20211208',
4917 'channel': 'colethedj',
4918 'view_count': int,
4919 'description': '',
4920 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4921 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4922 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4923 },
4924 'playlist_count': 1,
4925 }, {
4926 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4927 'url': 'https://www.youtube.com/feed/recommended',
4928 'info_dict': {
4929 'id': 'recommended',
4930 'title': 'recommended',
4931 'tags': [],
4932 },
4933 'playlist_mincount': 50,
4934 'params': {
4935 'skip_download': True,
4936 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4937 },
4938 }, {
4939 'note': 'API Fallback: /videos tab, sorted by oldest first',
4940 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4941 'info_dict': {
4942 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4943 'title': 'Cody\'sLab - Videos',
4944 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4945 'uploader': 'Cody\'sLab',
4946 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4947 'channel': 'Cody\'sLab',
4948 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4949 'tags': [],
4950 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4951 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4952 'channel_follower_count': int
4953 },
4954 'playlist_mincount': 650,
4955 'params': {
4956 'skip_download': True,
4957 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4958 },
4959 }, {
4960 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4961 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4962 'info_dict': {
4963 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4964 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4965 'title': 'Uploads from Royalty Free Music - Topic',
4966 'uploader': 'Royalty Free Music - Topic',
4967 'modified_date': r're:\d{8}',
4968 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4969 'description': '',
4970 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4971 'tags': [],
4972 'channel': 'Royalty Free Music - Topic',
4973 'view_count': int,
4974 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4975 },
4976 'expected_warnings': [
4977 'does not have a videos tab',
4978 r'[Uu]navailable videos (are|will be) hidden',
4979 ],
4980 'playlist_mincount': 101,
4981 'params': {
4982 'skip_download': True,
4983 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4984 },
4985 }, {
4986 'note': 'non-standard redirect to regional channel',
4987 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
4988 'only_matching': True
4989 }]
4990
4991 @classmethod
4992 def suitable(cls, url):
4993 return False if YoutubeIE.suitable(url) else super(
4994 YoutubeTabIE, cls).suitable(url)
4995
4996 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
4997
4998 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
4999 def _real_extract(self, url, smuggled_data):
5000 item_id = self._match_id(url)
5001 url = compat_urlparse.urlunparse(
5002 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
5003 compat_opts = self.get_param('compat_opts', [])
5004
5005 def get_mobj(url):
5006 mobj = self._URL_RE.match(url).groupdict()
5007 mobj.update((k, '') for k, v in mobj.items() if v is None)
5008 return mobj
5009
5010 mobj, redirect_warning = get_mobj(url), None
5011 # Youtube returns incomplete data if tabname is not lower case
5012 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5013 if is_channel:
5014 if smuggled_data.get('is_music_url'):
5015 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5016 item_id = item_id[2:]
5017 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5018 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5019 mdata = self._extract_tab_endpoint(
5020 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5021 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5022 get_all=False, expected_type=compat_str)
5023 if not murl:
5024 raise ExtractorError('Failed to resolve album to playlist')
5025 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5026 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5027 pre = f'https://www.youtube.com/channel/{item_id}'
5028
5029 original_tab_name = tab
5030 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5031 # Home URLs should redirect to /videos/
5032 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5033 'To download only the videos in the home page, add a "/featured" to the URL')
5034 tab = '/videos'
5035
5036 url = ''.join((pre, tab, post))
5037 mobj = get_mobj(url)
5038
5039 # Handle both video/playlist URLs
5040 qs = parse_qs(url)
5041 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
5042
5043 if not video_id and mobj['not_channel'].startswith('watch'):
5044 if not playlist_id:
5045 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5046 raise ExtractorError('Unable to recognize tab page')
5047 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5048 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5049 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5050 mobj = get_mobj(url)
5051
5052 if video_id and playlist_id:
5053 if self.get_param('noplaylist'):
5054 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5055 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5056 ie=YoutubeIE.ie_key(), video_id=video_id)
5057 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5058
5059 data, ytcfg = self._extract_data(url, item_id)
5060
5061 # YouTube may provide a non-standard redirect to the regional channel
5062 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5063 redirect_url = traverse_obj(
5064 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5065 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5066 redirect_url = ''.join((
5067 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5068 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5069 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5070
5071 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5072 if tabs:
5073 selected_tab = self._extract_selected_tab(tabs)
5074 selected_tab_name = selected_tab.get('title', '').lower()
5075 if selected_tab_name == 'home':
5076 selected_tab_name = 'featured'
5077 requested_tab_name = mobj['tab'][1:]
5078 if 'no-youtube-channel-redirect' not in compat_opts:
5079 if requested_tab_name == 'live':
5080 # Live tab should have redirected to the video
5081 raise ExtractorError('The channel is not currently live', expected=True)
5082 if requested_tab_name not in ('', selected_tab_name):
5083 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5084 if not original_tab_name:
5085 if item_id[:2] == 'UC':
5086 # Topic channels don't have /videos. Use the equivalent playlist instead
5087 pl_id = f'UU{item_id[2:]}'
5088 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5089 try:
5090 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5091 except ExtractorError:
5092 redirect_warning += ' and the playlist redirect gave error'
5093 else:
5094 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5095 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5096 if selected_tab_name and selected_tab_name != requested_tab_name:
5097 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5098 else:
5099 raise ExtractorError(redirect_warning, expected=True)
5100
5101 if redirect_warning:
5102 self.to_screen(redirect_warning)
5103 self.write_debug(f'Final URL: {url}')
5104
5105 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5106 if 'no-youtube-unavailable-videos' not in compat_opts:
5107 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5108 self._extract_and_report_alerts(data, only_once=True)
5109 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5110 if tabs:
5111 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5112
5113 playlist = traverse_obj(
5114 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5115 if playlist:
5116 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5117
5118 video_id = traverse_obj(
5119 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5120 if video_id:
5121 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5122 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5123 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5124 ie=YoutubeIE.ie_key(), video_id=video_id)
5125
5126 raise ExtractorError('Unable to recognize tab page')
5127
5128
5129 class YoutubePlaylistIE(InfoExtractor):
5130 IE_DESC = 'YouTube playlists'
5131 _VALID_URL = r'''(?x)(?:
5132 (?:https?://)?
5133 (?:\w+\.)?
5134 (?:
5135 (?:
5136 youtube(?:kids)?\.com|
5137 %(invidious)s
5138 )
5139 /.*?\?.*?\blist=
5140 )?
5141 (?P<id>%(playlist_id)s)
5142 )''' % {
5143 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5144 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5145 }
5146 IE_NAME = 'youtube:playlist'
5147 _TESTS = [{
5148 'note': 'issue #673',
5149 'url': 'PLBB231211A4F62143',
5150 'info_dict': {
5151 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5152 'id': 'PLBB231211A4F62143',
5153 'uploader': 'Wickman',
5154 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5155 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5156 'view_count': int,
5157 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5158 'modified_date': r're:\d{8}',
5159 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5160 'channel': 'Wickman',
5161 'tags': [],
5162 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5163 },
5164 'playlist_mincount': 29,
5165 }, {
5166 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5167 'info_dict': {
5168 'title': 'YDL_safe_search',
5169 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5170 },
5171 'playlist_count': 2,
5172 'skip': 'This playlist is private',
5173 }, {
5174 'note': 'embedded',
5175 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5176 'playlist_count': 4,
5177 'info_dict': {
5178 'title': 'JODA15',
5179 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5180 'uploader': 'milan',
5181 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5182 'description': '',
5183 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5184 'tags': [],
5185 'modified_date': '20140919',
5186 'view_count': int,
5187 'channel': 'milan',
5188 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5189 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5190 },
5191 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5192 }, {
5193 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5194 'playlist_mincount': 654,
5195 'info_dict': {
5196 'title': '2018 Chinese New Singles (11/6 updated)',
5197 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5198 'uploader': 'LBK',
5199 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5200 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5201 'channel': 'LBK',
5202 'view_count': int,
5203 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5204 'tags': [],
5205 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5206 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5207 'modified_date': r're:\d{8}',
5208 },
5209 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5210 }, {
5211 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5212 'only_matching': True,
5213 }, {
5214 # music album playlist
5215 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5216 'only_matching': True,
5217 }]
5218
5219 @classmethod
5220 def suitable(cls, url):
5221 if YoutubeTabIE.suitable(url):
5222 return False
5223 from ..utils import parse_qs
5224 qs = parse_qs(url)
5225 if qs.get('v', [None])[0]:
5226 return False
5227 return super(YoutubePlaylistIE, cls).suitable(url)
5228
5229 def _real_extract(self, url):
5230 playlist_id = self._match_id(url)
5231 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5232 url = update_url_query(
5233 'https://www.youtube.com/playlist',
5234 parse_qs(url) or {'list': playlist_id})
5235 if is_music_url:
5236 url = smuggle_url(url, {'is_music_url': True})
5237 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5238
5239
5240 class YoutubeYtBeIE(InfoExtractor):
5241 IE_DESC = 'youtu.be'
5242 _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}
5243 _TESTS = [{
5244 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5245 'info_dict': {
5246 'id': 'yeWKywCrFtk',
5247 'ext': 'mp4',
5248 'title': 'Small Scale Baler and Braiding Rugs',
5249 'uploader': 'Backus-Page House Museum',
5250 'uploader_id': 'backuspagemuseum',
5251 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5252 'upload_date': '20161008',
5253 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5254 'categories': ['Nonprofits & Activism'],
5255 'tags': list,
5256 'like_count': int,
5257 'age_limit': 0,
5258 'playable_in_embed': True,
5259 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5260 'channel': 'Backus-Page House Museum',
5261 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5262 'live_status': 'not_live',
5263 'view_count': int,
5264 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5265 'availability': 'public',
5266 'duration': 59,
5267 },
5268 'params': {
5269 'noplaylist': True,
5270 'skip_download': True,
5271 },
5272 }, {
5273 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5274 'only_matching': True,
5275 }]
5276
5277 def _real_extract(self, url):
5278 mobj = self._match_valid_url(url)
5279 video_id = mobj.group('id')
5280 playlist_id = mobj.group('playlist_id')
5281 return self.url_result(
5282 update_url_query('https://www.youtube.com/watch', {
5283 'v': video_id,
5284 'list': playlist_id,
5285 'feature': 'youtu.be',
5286 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5287
5288
5289 class YoutubeLivestreamEmbedIE(InfoExtractor):
5290 IE_DESC = 'YouTube livestream embeds'
5291 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5292 _TESTS = [{
5293 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5294 'only_matching': True,
5295 }]
5296
5297 def _real_extract(self, url):
5298 channel_id = self._match_id(url)
5299 return self.url_result(
5300 f'https://www.youtube.com/channel/{channel_id}/live',
5301 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5302
5303
5304 class YoutubeYtUserIE(InfoExtractor):
5305 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5306 IE_NAME = 'youtube:user'
5307 _VALID_URL = r'ytuser:(?P<id>.+)'
5308 _TESTS = [{
5309 'url': 'ytuser:phihag',
5310 'only_matching': True,
5311 }]
5312
5313 def _real_extract(self, url):
5314 user_id = self._match_id(url)
5315 return self.url_result(
5316 'https://www.youtube.com/user/%s/videos' % user_id,
5317 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5318
5319
5320 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5321 IE_NAME = 'youtube:favorites'
5322 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5323 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5324 _LOGIN_REQUIRED = True
5325 _TESTS = [{
5326 'url': ':ytfav',
5327 'only_matching': True,
5328 }, {
5329 'url': ':ytfavorites',
5330 'only_matching': True,
5331 }]
5332
5333 def _real_extract(self, url):
5334 return self.url_result(
5335 'https://www.youtube.com/playlist?list=LL',
5336 ie=YoutubeTabIE.ie_key())
5337
5338
5339 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5340 IE_DESC = 'YouTube search'
5341 IE_NAME = 'youtube:search'
5342 _SEARCH_KEY = 'ytsearch'
5343 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5344 _TESTS = [{
5345 'url': 'ytsearch5:youtube-dl test video',
5346 'playlist_count': 5,
5347 'info_dict': {
5348 'id': 'youtube-dl test video',
5349 'title': 'youtube-dl test video',
5350 }
5351 }]
5352
5353
5354 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5355 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5356 _SEARCH_KEY = 'ytsearchdate'
5357 IE_DESC = 'YouTube search, newest videos first'
5358 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5359 _TESTS = [{
5360 'url': 'ytsearchdate5:youtube-dl test video',
5361 'playlist_count': 5,
5362 'info_dict': {
5363 'id': 'youtube-dl test video',
5364 'title': 'youtube-dl test video',
5365 }
5366 }]
5367
5368
5369 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5370 IE_DESC = 'YouTube search URLs with sorting and filter support'
5371 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5372 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5373 _TESTS = [{
5374 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5375 'playlist_mincount': 5,
5376 'info_dict': {
5377 'id': 'youtube-dl test video',
5378 'title': 'youtube-dl test video',
5379 }
5380 }, {
5381 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5382 'playlist_mincount': 5,
5383 'info_dict': {
5384 'id': 'python',
5385 'title': 'python',
5386 }
5387
5388 }, {
5389 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5390 'only_matching': True,
5391 }]
5392
5393 def _real_extract(self, url):
5394 qs = parse_qs(url)
5395 query = (qs.get('search_query') or qs.get('q'))[0]
5396 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5397
5398
5399 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5400 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
5401 IE_NAME = 'youtube:music:search_url'
5402 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5403 _TESTS = [{
5404 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5405 'playlist_count': 16,
5406 'info_dict': {
5407 'id': 'royalty free music',
5408 'title': 'royalty free music',
5409 }
5410 }, {
5411 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5412 'playlist_mincount': 30,
5413 'info_dict': {
5414 'id': 'royalty free music - songs',
5415 'title': 'royalty free music - songs',
5416 },
5417 'params': {'extract_flat': 'in_playlist'}
5418 }, {
5419 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5420 'playlist_mincount': 30,
5421 'info_dict': {
5422 'id': 'royalty free music - community playlists',
5423 'title': 'royalty free music - community playlists',
5424 },
5425 'params': {'extract_flat': 'in_playlist'}
5426 }]
5427
5428 _SECTIONS = {
5429 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5430 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5431 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5432 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5433 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5434 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5435 }
5436
5437 def _real_extract(self, url):
5438 qs = parse_qs(url)
5439 query = (qs.get('search_query') or qs.get('q'))[0]
5440 params = qs.get('sp', (None,))[0]
5441 if params:
5442 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5443 else:
5444 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5445 params = self._SECTIONS.get(section)
5446 if not params:
5447 section = None
5448 title = join_nonempty(query, section, delim=' - ')
5449 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
5450
5451
5452 class YoutubeFeedsInfoExtractor(InfoExtractor):
5453 """
5454 Base class for feed extractors
5455 Subclasses must define the _FEED_NAME property.
5456 """
5457 _LOGIN_REQUIRED = True
5458 _TESTS = []
5459
5460 @property
5461 def IE_NAME(self):
5462 return 'youtube:%s' % self._FEED_NAME
5463
5464 def _real_extract(self, url):
5465 return self.url_result(
5466 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
5467
5468
5469 class YoutubeWatchLaterIE(InfoExtractor):
5470 IE_NAME = 'youtube:watchlater'
5471 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5472 _VALID_URL = r':ytwatchlater'
5473 _TESTS = [{
5474 'url': ':ytwatchlater',
5475 'only_matching': True,
5476 }]
5477
5478 def _real_extract(self, url):
5479 return self.url_result(
5480 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5481
5482
5483 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5484 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5485 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5486 _FEED_NAME = 'recommended'
5487 _LOGIN_REQUIRED = False
5488 _TESTS = [{
5489 'url': ':ytrec',
5490 'only_matching': True,
5491 }, {
5492 'url': ':ytrecommended',
5493 'only_matching': True,
5494 }, {
5495 'url': 'https://youtube.com',
5496 'only_matching': True,
5497 }]
5498
5499
5500 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5501 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5502 _VALID_URL = r':ytsub(?:scription)?s?'
5503 _FEED_NAME = 'subscriptions'
5504 _TESTS = [{
5505 'url': ':ytsubs',
5506 'only_matching': True,
5507 }, {
5508 'url': ':ytsubscriptions',
5509 'only_matching': True,
5510 }]
5511
5512
5513 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5514 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5515 _VALID_URL = r':ythis(?:tory)?'
5516 _FEED_NAME = 'history'
5517 _TESTS = [{
5518 'url': ':ythistory',
5519 'only_matching': True,
5520 }]
5521
5522
5523 class YoutubeTruncatedURLIE(InfoExtractor):
5524 IE_NAME = 'youtube:truncated_url'
5525 IE_DESC = False # Do not list
5526 _VALID_URL = r'''(?x)
5527 (?:https?://)?
5528 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5529 (?:watch\?(?:
5530 feature=[a-z_]+|
5531 annotation_id=annotation_[^&]+|
5532 x-yt-cl=[0-9]+|
5533 hl=[^&]*|
5534 t=[0-9]+
5535 )?
5536 |
5537 attribution_link\?a=[^&]+
5538 )
5539 $
5540 '''
5541
5542 _TESTS = [{
5543 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5544 'only_matching': True,
5545 }, {
5546 'url': 'https://www.youtube.com/watch?',
5547 'only_matching': True,
5548 }, {
5549 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5550 'only_matching': True,
5551 }, {
5552 'url': 'https://www.youtube.com/watch?feature=foo',
5553 'only_matching': True,
5554 }, {
5555 'url': 'https://www.youtube.com/watch?hl=en-GB',
5556 'only_matching': True,
5557 }, {
5558 'url': 'https://www.youtube.com/watch?t=2372',
5559 'only_matching': True,
5560 }]
5561
5562 def _real_extract(self, url):
5563 raise ExtractorError(
5564 'Did you forget to quote the URL? Remember that & is a meta '
5565 'character in most shells, so you want to put the URL in quotes, '
5566 'like youtube-dl '
5567 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5568 ' or simply youtube-dl BaW_jenozKc .',
5569 expected=True)
5570
5571
5572 class YoutubeClipIE(InfoExtractor):
5573 IE_NAME = 'youtube:clip'
5574 IE_DESC = False # Do not list
5575 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5576
5577 def _real_extract(self, url):
5578 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5579 return self.url_result(url, 'Generic')
5580
5581
5582 class YoutubeTruncatedIDIE(InfoExtractor):
5583 IE_NAME = 'youtube:truncated_id'
5584 IE_DESC = False # Do not list
5585 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5586
5587 _TESTS = [{
5588 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5589 'only_matching': True,
5590 }]
5591
5592 def _real_extract(self, url):
5593 video_id = self._match_id(url)
5594 raise ExtractorError(
5595 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5596 expected=True)