]> jfr.im git - yt-dlp.git/blame_incremental - yt_dlp/extractor/youtube.py
[EmbedThumbnail] Do not remove id3v1 tags
[yt-dlp.git] / yt_dlp / extractor / youtube.py
... / ...
CommitLineData
1# coding: utf-8
2
3from __future__ import unicode_literals
4
5import calendar
6import copy
7import datetime
8import functools
9import hashlib
10import itertools
11import json
12import math
13import os.path
14import random
15import re
16import sys
17import time
18import traceback
19import threading
20
21from .common import InfoExtractor, SearchInfoExtractor
22from ..compat import (
23 compat_chr,
24 compat_HTTPError,
25 compat_parse_qs,
26 compat_str,
27 compat_urllib_parse_unquote_plus,
28 compat_urllib_parse_urlencode,
29 compat_urllib_parse_urlparse,
30 compat_urlparse,
31)
32from ..jsinterp import JSInterpreter
33from ..utils import (
34 bug_reports_message,
35 clean_html,
36 datetime_from_str,
37 dict_get,
38 error_to_compat_str,
39 ExtractorError,
40 float_or_none,
41 format_field,
42 get_first,
43 int_or_none,
44 is_html,
45 join_nonempty,
46 js_to_json,
47 mimetype2ext,
48 network_exceptions,
49 NO_DEFAULT,
50 orderedSet,
51 parse_codecs,
52 parse_count,
53 parse_duration,
54 parse_iso8601,
55 parse_qs,
56 qualities,
57 remove_end,
58 remove_start,
59 smuggle_url,
60 str_or_none,
61 str_to_int,
62 strftime_or_none,
63 traverse_obj,
64 try_get,
65 unescapeHTML,
66 unified_strdate,
67 unified_timestamp,
68 unsmuggle_url,
69 update_url_query,
70 url_or_none,
71 urljoin,
72 variadic,
73)
74
75
76# any clients starting with _ cannot be explicity requested by the user
77INNERTUBE_CLIENTS = {
78 'web': {
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
81 'client': {
82 'clientName': 'WEB',
83 'clientVersion': '2.20211221.00.00',
84 }
85 },
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
87 },
88 'web_embedded': {
89 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_EMBEDDED_PLAYER',
93 'clientVersion': '1.20211215.00.01',
94 },
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
97 },
98 'web_music': {
99 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
100 'INNERTUBE_HOST': 'music.youtube.com',
101 'INNERTUBE_CONTEXT': {
102 'client': {
103 'clientName': 'WEB_REMIX',
104 'clientVersion': '1.20211213.00.00',
105 }
106 },
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
108 },
109 'web_creator': {
110 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
111 'INNERTUBE_CONTEXT': {
112 'client': {
113 'clientName': 'WEB_CREATOR',
114 'clientVersion': '1.20211220.02.00',
115 }
116 },
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
118 },
119 'android': {
120 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID',
124 'clientVersion': '16.49',
125 }
126 },
127 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
128 'REQUIRE_JS_PLAYER': False
129 },
130 'android_embedded': {
131 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
132 'INNERTUBE_CONTEXT': {
133 'client': {
134 'clientName': 'ANDROID_EMBEDDED_PLAYER',
135 'clientVersion': '16.49',
136 },
137 },
138 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
139 'REQUIRE_JS_PLAYER': False
140 },
141 'android_music': {
142 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_MUSIC',
146 'clientVersion': '4.57',
147 }
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
150 'REQUIRE_JS_PLAYER': False
151 },
152 'android_creator': {
153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
154 'INNERTUBE_CONTEXT': {
155 'client': {
156 'clientName': 'ANDROID_CREATOR',
157 'clientVersion': '21.47',
158 },
159 },
160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
162 },
163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
165 'ios': {
166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS',
170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
172 }
173 },
174 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
175 'REQUIRE_JS_PLAYER': False
176 },
177 'ios_embedded': {
178 'INNERTUBE_CONTEXT': {
179 'client': {
180 'clientName': 'IOS_MESSAGES_EXTENSION',
181 'clientVersion': '16.46',
182 'deviceModel': 'iPhone14,3',
183 },
184 },
185 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
186 'REQUIRE_JS_PLAYER': False
187 },
188 'ios_music': {
189 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
190 'INNERTUBE_CONTEXT': {
191 'client': {
192 'clientName': 'IOS_MUSIC',
193 'clientVersion': '4.57',
194 },
195 },
196 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
197 'REQUIRE_JS_PLAYER': False
198 },
199 'ios_creator': {
200 'INNERTUBE_CONTEXT': {
201 'client': {
202 'clientName': 'IOS_CREATOR',
203 'clientVersion': '21.47',
204 },
205 },
206 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
207 'REQUIRE_JS_PLAYER': False
208 },
209 # mweb has 'ultralow' formats
210 # See: https://github.com/yt-dlp/yt-dlp/pull/557
211 'mweb': {
212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
213 'INNERTUBE_CONTEXT': {
214 'client': {
215 'clientName': 'MWEB',
216 'clientVersion': '2.20211221.01.00',
217 }
218 },
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
220 },
221 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
222 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
223 'tv_embedded': {
224 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
225 'INNERTUBE_CONTEXT': {
226 'client': {
227 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
228 'clientVersion': '2.0',
229 },
230 },
231 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
232 },
233}
234
235
236def _split_innertube_client(client_name):
237 variant, *base = client_name.rsplit('.', 1)
238 if base:
239 return variant, base[0], variant
240 base, *variant = client_name.split('_', 1)
241 return client_name, base, variant[0] if variant else None
242
243
244def build_innertube_clients():
245 THIRD_PARTY = {
246 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
247 }
248 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
249 priority = qualities(BASE_CLIENTS[::-1])
250
251 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
252 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
253 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
254 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
255 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
256
257 _, base_client, variant = _split_innertube_client(client)
258 ytcfg['priority'] = 10 * priority(base_client)
259
260 if not variant:
261 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
262 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
263 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
264 embedscreen['priority'] -= 3
265 elif variant == 'embedded':
266 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
267 ytcfg['priority'] -= 2
268 else:
269 ytcfg['priority'] -= 3
270
271
272build_innertube_clients()
273
274
275class YoutubeBaseInfoExtractor(InfoExtractor):
276 """Provide base functions for Youtube extractors"""
277
278 _RESERVED_NAMES = (
279 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
280 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
281 r'browse|oembed|get_video_info|iframe_api|s/player|'
282 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
283
284 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
285
286 # _NETRC_MACHINE = 'youtube'
287
288 # If True it will raise an error if no login info is provided
289 _LOGIN_REQUIRED = False
290
291 _INVIDIOUS_SITES = (
292 # invidious-redirect websites
293 r'(?:www\.)?redirect\.invidious\.io',
294 r'(?:(?:www|dev)\.)?invidio\.us',
295 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
296 r'(?:www\.)?invidious\.pussthecat\.org',
297 r'(?:www\.)?invidious\.zee\.li',
298 r'(?:www\.)?invidious\.ethibox\.fr',
299 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
300 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
301 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
302 # youtube-dl invidious instances list
303 r'(?:(?:www|no)\.)?invidiou\.sh',
304 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
305 r'(?:www\.)?invidious\.kabi\.tk',
306 r'(?:www\.)?invidious\.mastodon\.host',
307 r'(?:www\.)?invidious\.zapashcanon\.fr',
308 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
309 r'(?:www\.)?invidious\.tinfoil-hat\.net',
310 r'(?:www\.)?invidious\.himiko\.cloud',
311 r'(?:www\.)?invidious\.reallyancient\.tech',
312 r'(?:www\.)?invidious\.tube',
313 r'(?:www\.)?invidiou\.site',
314 r'(?:www\.)?invidious\.site',
315 r'(?:www\.)?invidious\.xyz',
316 r'(?:www\.)?invidious\.nixnet\.xyz',
317 r'(?:www\.)?invidious\.048596\.xyz',
318 r'(?:www\.)?invidious\.drycat\.fr',
319 r'(?:www\.)?inv\.skyn3t\.in',
320 r'(?:www\.)?tube\.poal\.co',
321 r'(?:www\.)?tube\.connect\.cafe',
322 r'(?:www\.)?vid\.wxzm\.sx',
323 r'(?:www\.)?vid\.mint\.lgbt',
324 r'(?:www\.)?vid\.puffyan\.us',
325 r'(?:www\.)?yewtu\.be',
326 r'(?:www\.)?yt\.elukerio\.org',
327 r'(?:www\.)?yt\.lelux\.fi',
328 r'(?:www\.)?invidious\.ggc-project\.de',
329 r'(?:www\.)?yt\.maisputain\.ovh',
330 r'(?:www\.)?ytprivate\.com',
331 r'(?:www\.)?invidious\.13ad\.de',
332 r'(?:www\.)?invidious\.toot\.koeln',
333 r'(?:www\.)?invidious\.fdn\.fr',
334 r'(?:www\.)?watch\.nettohikari\.com',
335 r'(?:www\.)?invidious\.namazso\.eu',
336 r'(?:www\.)?invidious\.silkky\.cloud',
337 r'(?:www\.)?invidious\.exonip\.de',
338 r'(?:www\.)?invidious\.riverside\.rocks',
339 r'(?:www\.)?invidious\.blamefran\.net',
340 r'(?:www\.)?invidious\.moomoo\.de',
341 r'(?:www\.)?ytb\.trom\.tf',
342 r'(?:www\.)?yt\.cyberhost\.uk',
343 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
344 r'(?:www\.)?qklhadlycap4cnod\.onion',
345 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
346 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
347 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
348 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
349 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
350 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
351 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
352 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
353 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
354 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
355 )
356
357 def _initialize_consent(self):
358 cookies = self._get_cookies('https://www.youtube.com/')
359 if cookies.get('__Secure-3PSID'):
360 return
361 consent_id = None
362 consent = cookies.get('CONSENT')
363 if consent:
364 if 'YES' in consent.value:
365 return
366 consent_id = self._search_regex(
367 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
368 if not consent_id:
369 consent_id = random.randint(100, 999)
370 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
371
372 def _initialize_pref(self):
373 cookies = self._get_cookies('https://www.youtube.com/')
374 pref_cookie = cookies.get('PREF')
375 pref = {}
376 if pref_cookie:
377 try:
378 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
379 except ValueError:
380 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
381 pref.update({'hl': 'en', 'tz': 'UTC'})
382 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
383
384 def _real_initialize(self):
385 self._initialize_pref()
386 self._initialize_consent()
387 if (self._LOGIN_REQUIRED
388 and self.get_param('cookiefile') is None
389 and self.get_param('cookiesfrombrowser') is None):
390 self.raise_login_required('Login details are needed to download this content', method='cookies')
391
392 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
393 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
394 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
395
396 def _get_default_ytcfg(self, client='web'):
397 return copy.deepcopy(INNERTUBE_CLIENTS[client])
398
399 def _get_innertube_host(self, client='web'):
400 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
401
402 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
403 # try_get but with fallback to default ytcfg client values when present
404 _func = lambda y: try_get(y, getter, expected_type)
405 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
406
407 def _extract_client_name(self, ytcfg, default_client='web'):
408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
411
412 def _extract_client_version(self, ytcfg, default_client='web'):
413 return self._ytcfg_get_safe(
414 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
415 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
416
417 def _extract_api_key(self, ytcfg=None, default_client='web'):
418 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
419
420 def _extract_context(self, ytcfg=None, default_client='web'):
421 context = get_first(
422 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
423 # Enforce language and tz for extraction
424 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
425 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
426 return context
427
428 _SAPISID = None
429
430 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
431 time_now = round(time.time())
432 if self._SAPISID is None:
433 yt_cookies = self._get_cookies('https://www.youtube.com')
434 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
435 # See: https://github.com/yt-dlp/yt-dlp/issues/393
436 sapisid_cookie = dict_get(
437 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
438 if sapisid_cookie and sapisid_cookie.value:
439 self._SAPISID = sapisid_cookie.value
440 self.write_debug('Extracted SAPISID cookie')
441 # SAPISID cookie is required if not already present
442 if not yt_cookies.get('SAPISID'):
443 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
444 self._set_cookie(
445 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
446 else:
447 self._SAPISID = False
448 if not self._SAPISID:
449 return None
450 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
451 sapisidhash = hashlib.sha1(
452 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
453 return f'SAPISIDHASH {time_now}_{sapisidhash}'
454
455 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
456 note='Downloading API JSON', errnote='Unable to download API page',
457 context=None, api_key=None, api_hostname=None, default_client='web'):
458
459 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
460 data.update(query)
461 real_headers = self.generate_api_headers(default_client=default_client)
462 real_headers.update({'content-type': 'application/json'})
463 if headers:
464 real_headers.update(headers)
465 return self._download_json(
466 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
467 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
468 data=json.dumps(data).encode('utf8'), headers=real_headers,
469 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
470
471 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
472 data = self._search_regex(
473 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
474 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
475 if data:
476 return self._parse_json(data, item_id, fatal=fatal)
477
478 @staticmethod
479 def _extract_session_index(*data):
480 """
481 Index of current account in account list.
482 See: https://github.com/yt-dlp/yt-dlp/pull/519
483 """
484 for ytcfg in data:
485 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
486 if session_index is not None:
487 return session_index
488
489 # Deprecated?
490 def _extract_identity_token(self, ytcfg=None, webpage=None):
491 if ytcfg:
492 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
493 if token:
494 return token
495 if webpage:
496 return self._search_regex(
497 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
498 'identity token', default=None, fatal=False)
499
500 @staticmethod
501 def _extract_account_syncid(*args):
502 """
503 Extract syncId required to download private playlists of secondary channels
504 @params response and/or ytcfg
505 """
506 for data in args:
507 # ytcfg includes channel_syncid if on secondary channel
508 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
509 if delegated_sid:
510 return delegated_sid
511 sync_ids = (try_get(
512 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
513 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
514 if len(sync_ids) >= 2 and sync_ids[1]:
515 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
516 # and just "user_syncid||" for primary channel. We only want the channel_syncid
517 return sync_ids[0]
518
519 @staticmethod
520 def _extract_visitor_data(*args):
521 """
522 Extracts visitorData from an API response or ytcfg
523 Appears to be used to track session state
524 """
525 return get_first(
526 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
527 expected_type=str)
528
529 @property
530 def is_authenticated(self):
531 return bool(self._generate_sapisidhash_header())
532
533 def extract_ytcfg(self, video_id, webpage):
534 if not webpage:
535 return {}
536 return self._parse_json(
537 self._search_regex(
538 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
539 default='{}'), video_id, fatal=False) or {}
540
541 def generate_api_headers(
542 self, *, ytcfg=None, account_syncid=None, session_index=None,
543 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
544
545 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
546 headers = {
547 'X-YouTube-Client-Name': compat_str(
548 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
549 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
550 'Origin': origin,
551 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
552 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
553 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
554 }
555 if session_index is None:
556 session_index = self._extract_session_index(ytcfg)
557 if account_syncid or session_index is not None:
558 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
559
560 auth = self._generate_sapisidhash_header(origin)
561 if auth is not None:
562 headers['Authorization'] = auth
563 headers['X-Origin'] = origin
564 return {h: v for h, v in headers.items() if v is not None}
565
566 @staticmethod
567 def _build_api_continuation_query(continuation, ctp=None):
568 query = {
569 'continuation': continuation
570 }
571 # TODO: Inconsistency with clickTrackingParams.
572 # Currently we have a fixed ctp contained within context (from ytcfg)
573 # and a ctp in root query for continuation.
574 if ctp:
575 query['clickTracking'] = {'clickTrackingParams': ctp}
576 return query
577
578 @classmethod
579 def _extract_next_continuation_data(cls, renderer):
580 next_continuation = try_get(
581 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
582 lambda x: x['continuation']['reloadContinuationData']), dict)
583 if not next_continuation:
584 return
585 continuation = next_continuation.get('continuation')
586 if not continuation:
587 return
588 ctp = next_continuation.get('clickTrackingParams')
589 return cls._build_api_continuation_query(continuation, ctp)
590
591 @classmethod
592 def _extract_continuation_ep_data(cls, continuation_ep: dict):
593 if isinstance(continuation_ep, dict):
594 continuation = try_get(
595 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
596 if not continuation:
597 return
598 ctp = continuation_ep.get('clickTrackingParams')
599 return cls._build_api_continuation_query(continuation, ctp)
600
601 @classmethod
602 def _extract_continuation(cls, renderer):
603 next_continuation = cls._extract_next_continuation_data(renderer)
604 if next_continuation:
605 return next_continuation
606
607 contents = []
608 for key in ('contents', 'items'):
609 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
610
611 for content in contents:
612 if not isinstance(content, dict):
613 continue
614 continuation_ep = try_get(
615 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
616 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
617 dict)
618 continuation = cls._extract_continuation_ep_data(continuation_ep)
619 if continuation:
620 return continuation
621
622 @classmethod
623 def _extract_alerts(cls, data):
624 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
625 if not isinstance(alert_dict, dict):
626 continue
627 for alert in alert_dict.values():
628 alert_type = alert.get('type')
629 if not alert_type:
630 continue
631 message = cls._get_text(alert, 'text')
632 if message:
633 yield alert_type, message
634
635 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
636 errors = []
637 warnings = []
638 for alert_type, alert_message in alerts:
639 if alert_type.lower() == 'error' and fatal:
640 errors.append([alert_type, alert_message])
641 else:
642 warnings.append([alert_type, alert_message])
643
644 for alert_type, alert_message in (warnings + errors[:-1]):
645 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
646 if errors:
647 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
648
649 def _extract_and_report_alerts(self, data, *args, **kwargs):
650 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
651
652 def _extract_badges(self, renderer: dict):
653 badges = set()
654 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
655 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
656 if label:
657 badges.add(label.lower())
658 return badges
659
660 @staticmethod
661 def _get_text(data, *path_list, max_runs=None):
662 for path in path_list or [None]:
663 if path is None:
664 obj = [data]
665 else:
666 obj = traverse_obj(data, path, default=[])
667 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
668 obj = [obj]
669 for item in obj:
670 text = try_get(item, lambda x: x['simpleText'], compat_str)
671 if text:
672 return text
673 runs = try_get(item, lambda x: x['runs'], list) or []
674 if not runs and isinstance(item, list):
675 runs = item
676
677 runs = runs[:min(len(runs), max_runs or len(runs))]
678 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
679 if text:
680 return text
681
682 def _get_count(self, data, *path_list):
683 count_text = self._get_text(data, *path_list) or ''
684 count = parse_count(count_text)
685 if count is None:
686 count = str_to_int(
687 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
688 return count
689
690 @staticmethod
691 def _extract_thumbnails(data, *path_list):
692 """
693 Extract thumbnails from thumbnails dict
694 @param path_list: path list to level that contains 'thumbnails' key
695 """
696 thumbnails = []
697 for path in path_list or [()]:
698 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
699 thumbnail_url = url_or_none(thumbnail.get('url'))
700 if not thumbnail_url:
701 continue
702 # Sometimes youtube gives a wrong thumbnail URL. See:
703 # https://github.com/yt-dlp/yt-dlp/issues/233
704 # https://github.com/ytdl-org/youtube-dl/issues/28023
705 if 'maxresdefault' in thumbnail_url:
706 thumbnail_url = thumbnail_url.split('?')[0]
707 thumbnails.append({
708 'url': thumbnail_url,
709 'height': int_or_none(thumbnail.get('height')),
710 'width': int_or_none(thumbnail.get('width')),
711 })
712 return thumbnails
713
714 @staticmethod
715 def extract_relative_time(relative_time_text):
716 """
717 Extracts a relative time from string and converts to dt object
718 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
719 """
720 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)
721 if mobj:
722 start = mobj.group('start')
723 if start:
724 return datetime_from_str(start)
725 try:
726 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
727 except ValueError:
728 return None
729
730 def _extract_time_text(self, renderer, *path_list):
731 text = self._get_text(renderer, *path_list) or ''
732 dt = self.extract_relative_time(text)
733 timestamp = None
734 if isinstance(dt, datetime.datetime):
735 timestamp = calendar.timegm(dt.timetuple())
736
737 if timestamp is None:
738 timestamp = (
739 unified_timestamp(text) or unified_timestamp(
740 self._search_regex(
741 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
742 text.lower(), 'time text', default=None)))
743
744 if text and timestamp is None:
745 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
746 return timestamp, text
747
748 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
749 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
750 default_client='web'):
751 response = None
752 last_error = None
753 count = -1
754 retries = self.get_param('extractor_retries', 3)
755 if check_get_keys is None:
756 check_get_keys = []
757 while count < retries:
758 count += 1
759 if last_error:
760 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
761 try:
762 response = self._call_api(
763 ep=ep, fatal=True, headers=headers,
764 video_id=item_id, query=query,
765 context=self._extract_context(ytcfg, default_client),
766 api_key=self._extract_api_key(ytcfg, default_client),
767 api_hostname=api_hostname, default_client=default_client,
768 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
769 except ExtractorError as e:
770 if isinstance(e.cause, network_exceptions):
771 if isinstance(e.cause, compat_HTTPError):
772 first_bytes = e.cause.read(512)
773 if not is_html(first_bytes):
774 yt_error = try_get(
775 self._parse_json(
776 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
777 lambda x: x['error']['message'], compat_str)
778 if yt_error:
779 self._report_alerts([('ERROR', yt_error)], fatal=False)
780 # Downloading page may result in intermittent 5xx HTTP error
781 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
782 # We also want to catch all other network exceptions since errors in later pages can be troublesome
783 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
784 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
785 last_error = error_to_compat_str(e.cause or e.msg)
786 if count < retries:
787 continue
788 if fatal:
789 raise
790 else:
791 self.report_warning(error_to_compat_str(e))
792 return
793
794 else:
795 try:
796 self._extract_and_report_alerts(response, only_once=True)
797 except ExtractorError as e:
798 # YouTube servers may return errors we want to retry on in a 200 OK response
799 # See: https://github.com/yt-dlp/yt-dlp/issues/839
800 if 'unknown error' in e.msg.lower():
801 last_error = e.msg
802 continue
803 if fatal:
804 raise
805 self.report_warning(error_to_compat_str(e))
806 return
807 if not check_get_keys or dict_get(response, check_get_keys):
808 break
809 # Youtube sometimes sends incomplete data
810 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
811 last_error = 'Incomplete data received'
812 if count >= retries:
813 if fatal:
814 raise ExtractorError(last_error)
815 else:
816 self.report_warning(last_error)
817 return
818 return response
819
820 @staticmethod
821 def is_music_url(url):
822 return re.match(r'https?://music\.youtube\.com/', url) is not None
823
824 def _extract_video(self, renderer):
825 video_id = renderer.get('videoId')
826 title = self._get_text(renderer, 'title')
827 description = self._get_text(renderer, 'descriptionSnippet')
828 duration = parse_duration(self._get_text(
829 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
830 if duration is None:
831 duration = parse_duration(self._search_regex(
832 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
833 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
834 video_id, default=None, group='duration'))
835
836 view_count = self._get_count(renderer, 'viewCountText')
837
838 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
839 channel_id = traverse_obj(
840 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
841 expected_type=str, get_all=False)
842 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
843 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
844 overlay_style = traverse_obj(
845 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
846 get_all=False, expected_type=str)
847 badges = self._extract_badges(renderer)
848 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
849 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
850 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
851 expected_type=str)) or ''
852 url = f'https://www.youtube.com/watch?v={video_id}'
853 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
854 url = f'https://www.youtube.com/shorts/{video_id}'
855
856 return {
857 '_type': 'url',
858 'ie_key': YoutubeIE.ie_key(),
859 'id': video_id,
860 'url': url,
861 'title': title,
862 'description': description,
863 'duration': duration,
864 'view_count': view_count,
865 'uploader': uploader,
866 'channel_id': channel_id,
867 'thumbnails': thumbnails,
868 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
869 if self._configuration_arg('approximate_date', ie_key='youtubetab')
870 else None),
871 'live_status': ('is_upcoming' if scheduled_timestamp is not None
872 else 'was_live' if 'streamed' in time_text.lower()
873 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
874 else None),
875 'release_timestamp': scheduled_timestamp,
876 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
877 }
878
879
880class YoutubeIE(YoutubeBaseInfoExtractor):
881 IE_DESC = 'YouTube'
882 _VALID_URL = r"""(?x)^
883 (
884 (?:https?://|//) # http(s):// or protocol-independent URL
885 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
886 (?:www\.)?deturl\.com/www\.youtube\.com|
887 (?:www\.)?pwnyoutube\.com|
888 (?:www\.)?hooktube\.com|
889 (?:www\.)?yourepeat\.com|
890 tube\.majestyc\.net|
891 %(invidious)s|
892 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
893 (?:.*?\#/)? # handle anchor (#/) redirect urls
894 (?: # the various things that can precede the ID:
895 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
896 |(?: # or the v= param in all its forms
897 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
898 (?:\?|\#!?) # the params delimiter ? or # or #!
899 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
900 v=
901 )
902 ))
903 |(?:
904 youtu\.be| # just youtu.be/xxxx
905 vid\.plus| # or vid.plus/xxxx
906 zwearz\.com/watch| # or zwearz.com/watch/xxxx
907 %(invidious)s
908 )/
909 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
910 )
911 )? # all until now is optional -> you can pass the naked ID
912 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
913 (?(1).+)? # if we found the ID, everything can follow
914 (?:\#|$)""" % {
915 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
916 }
917 _PLAYER_INFO_RE = (
918 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
919 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$',
920 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
921 )
922 _formats = {
923 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
924 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
925 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
926 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
927 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
928 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
929 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
930 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
931 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
932 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
933 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
934 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
935 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
936 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
937 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
938 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
939 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
940 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
941
942
943 # 3D videos
944 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
945 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
946 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
947 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
948 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
949 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
950 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
951
952 # Apple HTTP Live Streaming
953 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
954 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
955 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
956 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
957 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
958 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
959 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
960 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
961
962 # DASH mp4 video
963 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
964 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
965 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
966 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
967 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
968 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
969 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
970 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
971 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
972 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
973 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
974 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
975
976 # Dash mp4 audio
977 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
978 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
979 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
980 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
981 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
982 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
983 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
984
985 # Dash webm
986 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
987 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
988 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
989 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
990 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
991 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
992 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
993 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
994 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
995 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
996 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
997 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
998 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
999 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1000 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1001 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1002 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1003 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1004 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1005 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1006 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1008
1009 # Dash webm audio
1010 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1011 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1012
1013 # Dash webm audio with opus inside
1014 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1015 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1016 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1017
1018 # RTMP (unnamed)
1019 '_rtmp': {'protocol': 'rtmp'},
1020
1021 # av01 video only formats sometimes served with "unknown" codecs
1022 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1023 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1024 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1025 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1026 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1027 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1028 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1029 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1030 }
1031 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1032
1033 _GEO_BYPASS = False
1034
1035 IE_NAME = 'youtube'
1036 _TESTS = [
1037 {
1038 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1039 'info_dict': {
1040 'id': 'BaW_jenozKc',
1041 'ext': 'mp4',
1042 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1043 'uploader': 'Philipp Hagemeister',
1044 'uploader_id': 'phihag',
1045 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1046 'channel': 'Philipp Hagemeister',
1047 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1048 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1049 'upload_date': '20121002',
1050 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1051 'categories': ['Science & Technology'],
1052 'tags': ['youtube-dl'],
1053 'duration': 10,
1054 'view_count': int,
1055 'like_count': int,
1056 'availability': 'public',
1057 'playable_in_embed': True,
1058 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1059 'live_status': 'not_live',
1060 'age_limit': 0,
1061 'start_time': 1,
1062 'end_time': 9,
1063 'channel_follower_count': int
1064 }
1065 },
1066 {
1067 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1068 'note': 'Embed-only video (#1746)',
1069 'info_dict': {
1070 'id': 'yZIXLfi8CZQ',
1071 'ext': 'mp4',
1072 'upload_date': '20120608',
1073 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1074 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1075 'uploader': 'SET India',
1076 'uploader_id': 'setindia',
1077 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1078 'age_limit': 18,
1079 },
1080 'skip': 'Private video',
1081 },
1082 {
1083 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1084 'note': 'Use the first video ID in the URL',
1085 'info_dict': {
1086 'id': 'BaW_jenozKc',
1087 'ext': 'mp4',
1088 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1089 'uploader': 'Philipp Hagemeister',
1090 'uploader_id': 'phihag',
1091 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1092 'channel': 'Philipp Hagemeister',
1093 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1094 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1095 'upload_date': '20121002',
1096 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1097 'categories': ['Science & Technology'],
1098 'tags': ['youtube-dl'],
1099 'duration': 10,
1100 'view_count': int,
1101 'like_count': int,
1102 'availability': 'public',
1103 'playable_in_embed': True,
1104 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1105 'live_status': 'not_live',
1106 'age_limit': 0,
1107 'channel_follower_count': int
1108 },
1109 'params': {
1110 'skip_download': True,
1111 },
1112 },
1113 {
1114 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1115 'note': '256k DASH audio (format 141) via DASH manifest',
1116 'info_dict': {
1117 'id': 'a9LDPn-MO4I',
1118 'ext': 'm4a',
1119 'upload_date': '20121002',
1120 'uploader_id': '8KVIDEO',
1121 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1122 'description': '',
1123 'uploader': '8KVIDEO',
1124 'title': 'UHDTV TEST 8K VIDEO.mp4'
1125 },
1126 'params': {
1127 'youtube_include_dash_manifest': True,
1128 'format': '141',
1129 },
1130 'skip': 'format 141 not served anymore',
1131 },
1132 # DASH manifest with encrypted signature
1133 {
1134 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1135 'info_dict': {
1136 'id': 'IB3lcPjvWLA',
1137 'ext': 'm4a',
1138 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1139 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1140 'duration': 244,
1141 'uploader': 'AfrojackVEVO',
1142 'uploader_id': 'AfrojackVEVO',
1143 'upload_date': '20131011',
1144 'abr': 129.495,
1145 'like_count': int,
1146 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1147 'playable_in_embed': True,
1148 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1149 'view_count': int,
1150 'track': 'The Spark',
1151 'live_status': 'not_live',
1152 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1153 'channel': 'Afrojack',
1154 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1155 'tags': 'count:19',
1156 'availability': 'public',
1157 'categories': ['Music'],
1158 'age_limit': 0,
1159 'alt_title': 'The Spark',
1160 'channel_follower_count': int
1161 },
1162 'params': {
1163 'youtube_include_dash_manifest': True,
1164 'format': '141/bestaudio[ext=m4a]',
1165 },
1166 },
1167 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1168 {
1169 'note': 'Embed allowed age-gate video',
1170 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1171 'info_dict': {
1172 'id': 'HtVdAasjOgU',
1173 'ext': 'mp4',
1174 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1175 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1176 'duration': 142,
1177 'uploader': 'The Witcher',
1178 'uploader_id': 'WitcherGame',
1179 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1180 'upload_date': '20140605',
1181 'age_limit': 18,
1182 'categories': ['Gaming'],
1183 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1184 'availability': 'needs_auth',
1185 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1186 'like_count': int,
1187 'channel': 'The Witcher',
1188 'live_status': 'not_live',
1189 'tags': 'count:17',
1190 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1191 'playable_in_embed': True,
1192 'view_count': int,
1193 'channel_follower_count': int
1194 },
1195 },
1196 {
1197 'note': 'Age-gate video with embed allowed in public site',
1198 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1199 'info_dict': {
1200 'id': 'HsUATh_Nc2U',
1201 'ext': 'mp4',
1202 'title': 'Godzilla 2 (Official Video)',
1203 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1204 'upload_date': '20200408',
1205 'uploader_id': 'FlyingKitty900',
1206 'uploader': 'FlyingKitty',
1207 'age_limit': 18,
1208 'availability': 'needs_auth',
1209 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1210 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1211 'channel': 'FlyingKitty',
1212 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1213 'view_count': int,
1214 'categories': ['Entertainment'],
1215 'live_status': 'not_live',
1216 'tags': ['Flyingkitty', 'godzilla 2'],
1217 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1218 'like_count': int,
1219 'duration': 177,
1220 'playable_in_embed': True,
1221 'channel_follower_count': int
1222 },
1223 },
1224 {
1225 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1226 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1227 'info_dict': {
1228 'id': 'Tq92D6wQ1mg',
1229 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1230 'ext': 'mp4',
1231 'upload_date': '20191228',
1232 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1233 'uploader': 'Projekt Melody',
1234 'description': 'md5:17eccca93a786d51bc67646756894066',
1235 'age_limit': 18,
1236 'like_count': int,
1237 'availability': 'needs_auth',
1238 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1239 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1240 'view_count': int,
1241 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1242 'channel': 'Projekt Melody',
1243 'live_status': 'not_live',
1244 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1245 'playable_in_embed': True,
1246 'categories': ['Entertainment'],
1247 'duration': 106,
1248 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1249 'channel_follower_count': int
1250 },
1251 },
1252 {
1253 'note': 'Non-Agegated non-embeddable video',
1254 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1255 'info_dict': {
1256 'id': 'MeJVWBSsPAY',
1257 'ext': 'mp4',
1258 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1259 'uploader': 'Herr Lurik',
1260 'uploader_id': 'st3in234',
1261 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1262 'upload_date': '20130730',
1263 'track': 'Such mich find mich',
1264 'age_limit': 0,
1265 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1266 'like_count': int,
1267 'playable_in_embed': False,
1268 'creator': 'OOMPH!',
1269 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1270 'view_count': int,
1271 'alt_title': 'Such mich find mich',
1272 'duration': 210,
1273 'channel': 'Herr Lurik',
1274 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1275 'categories': ['Music'],
1276 'availability': 'public',
1277 'uploader_url': 'http://www.youtube.com/user/st3in234',
1278 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1279 'live_status': 'not_live',
1280 'artist': 'OOMPH!',
1281 'channel_follower_count': int
1282 },
1283 },
1284 {
1285 'note': 'Non-bypassable age-gated video',
1286 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1287 'only_matching': True,
1288 },
1289 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1290 # YouTube Red ad is not captured for creator
1291 {
1292 'url': '__2ABJjxzNo',
1293 'info_dict': {
1294 'id': '__2ABJjxzNo',
1295 'ext': 'mp4',
1296 'duration': 266,
1297 'upload_date': '20100430',
1298 'uploader_id': 'deadmau5',
1299 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1300 'creator': 'deadmau5',
1301 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1302 'uploader': 'deadmau5',
1303 'title': 'Deadmau5 - Some Chords (HD)',
1304 'alt_title': 'Some Chords',
1305 'availability': 'public',
1306 'tags': 'count:14',
1307 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1308 'view_count': int,
1309 'live_status': 'not_live',
1310 'channel': 'deadmau5',
1311 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1312 'like_count': int,
1313 'track': 'Some Chords',
1314 'artist': 'deadmau5',
1315 'playable_in_embed': True,
1316 'age_limit': 0,
1317 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1318 'categories': ['Music'],
1319 'album': 'Some Chords',
1320 'channel_follower_count': int
1321 },
1322 'expected_warnings': [
1323 'DASH manifest missing',
1324 ]
1325 },
1326 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1327 {
1328 'url': 'lqQg6PlCWgI',
1329 'info_dict': {
1330 'id': 'lqQg6PlCWgI',
1331 'ext': 'mp4',
1332 'duration': 6085,
1333 'upload_date': '20150827',
1334 'uploader_id': 'olympic',
1335 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1336 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1337 'uploader': 'Olympics',
1338 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1339 'like_count': int,
1340 'release_timestamp': 1343767800,
1341 'playable_in_embed': True,
1342 'categories': ['Sports'],
1343 'release_date': '20120731',
1344 'channel': 'Olympics',
1345 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1346 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1347 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1348 'age_limit': 0,
1349 'availability': 'public',
1350 'live_status': 'was_live',
1351 'view_count': int,
1352 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1353 'channel_follower_count': int
1354 },
1355 'params': {
1356 'skip_download': 'requires avconv',
1357 }
1358 },
1359 # Non-square pixels
1360 {
1361 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1362 'info_dict': {
1363 'id': '_b-2C3KPAM0',
1364 'ext': 'mp4',
1365 'stretched_ratio': 16 / 9.,
1366 'duration': 85,
1367 'upload_date': '20110310',
1368 'uploader_id': 'AllenMeow',
1369 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1370 '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',
1371 'uploader': '孫ᄋᄅ',
1372 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1373 'playable_in_embed': True,
1374 'channel': '孫ᄋᄅ',
1375 'age_limit': 0,
1376 'tags': 'count:11',
1377 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1378 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1379 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1380 'view_count': int,
1381 'categories': ['People & Blogs'],
1382 'like_count': int,
1383 'live_status': 'not_live',
1384 'availability': 'unlisted',
1385 'channel_follower_count': int
1386 },
1387 },
1388 # url_encoded_fmt_stream_map is empty string
1389 {
1390 'url': 'qEJwOuvDf7I',
1391 'info_dict': {
1392 'id': 'qEJwOuvDf7I',
1393 'ext': 'webm',
1394 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1395 'description': '',
1396 'upload_date': '20150404',
1397 'uploader_id': 'spbelect',
1398 'uploader': 'Наблюдатели Петербурга',
1399 },
1400 'params': {
1401 'skip_download': 'requires avconv',
1402 },
1403 'skip': 'This live event has ended.',
1404 },
1405 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1406 {
1407 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1408 'info_dict': {
1409 'id': 'FIl7x6_3R5Y',
1410 'ext': 'webm',
1411 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1412 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1413 'duration': 220,
1414 'upload_date': '20150625',
1415 'uploader_id': 'dorappi2000',
1416 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1417 'uploader': 'dorappi2000',
1418 'formats': 'mincount:31',
1419 },
1420 'skip': 'not actual anymore',
1421 },
1422 # DASH manifest with segment_list
1423 {
1424 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1425 'md5': '8ce563a1d667b599d21064e982ab9e31',
1426 'info_dict': {
1427 'id': 'CsmdDsKjzN8',
1428 'ext': 'mp4',
1429 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1430 'uploader': 'Airtek',
1431 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1432 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1433 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1434 },
1435 'params': {
1436 'youtube_include_dash_manifest': True,
1437 'format': '135', # bestvideo
1438 },
1439 'skip': 'This live event has ended.',
1440 },
1441 {
1442 # Multifeed videos (multiple cameras), URL is for Main Camera
1443 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1444 'info_dict': {
1445 'id': 'jvGDaLqkpTg',
1446 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1447 'description': 'md5:e03b909557865076822aa169218d6a5d',
1448 },
1449 'playlist': [{
1450 'info_dict': {
1451 'id': 'jvGDaLqkpTg',
1452 'ext': 'mp4',
1453 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1454 'description': 'md5:e03b909557865076822aa169218d6a5d',
1455 'duration': 10643,
1456 'upload_date': '20161111',
1457 'uploader': 'Team PGP',
1458 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1460 },
1461 }, {
1462 'info_dict': {
1463 'id': '3AKt1R1aDnw',
1464 'ext': 'mp4',
1465 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1466 'description': 'md5:e03b909557865076822aa169218d6a5d',
1467 'duration': 10991,
1468 'upload_date': '20161111',
1469 'uploader': 'Team PGP',
1470 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1471 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1472 },
1473 }, {
1474 'info_dict': {
1475 'id': 'RtAMM00gpVc',
1476 'ext': 'mp4',
1477 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1478 'description': 'md5:e03b909557865076822aa169218d6a5d',
1479 'duration': 10995,
1480 'upload_date': '20161111',
1481 'uploader': 'Team PGP',
1482 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1483 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1484 },
1485 }, {
1486 'info_dict': {
1487 'id': '6N2fdlP3C5U',
1488 'ext': 'mp4',
1489 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1490 'description': 'md5:e03b909557865076822aa169218d6a5d',
1491 'duration': 10990,
1492 'upload_date': '20161111',
1493 'uploader': 'Team PGP',
1494 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1495 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1496 },
1497 }],
1498 'params': {
1499 'skip_download': True,
1500 },
1501 'skip': 'Not multifeed anymore',
1502 },
1503 {
1504 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1505 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1506 'info_dict': {
1507 'id': 'gVfLd0zydlo',
1508 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1509 },
1510 'playlist_count': 2,
1511 'skip': 'Not multifeed anymore',
1512 },
1513 {
1514 'url': 'https://vid.plus/FlRa-iH7PGw',
1515 'only_matching': True,
1516 },
1517 {
1518 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1519 'only_matching': True,
1520 },
1521 {
1522 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1523 # Also tests cut-off URL expansion in video description (see
1524 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1525 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1526 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1527 'info_dict': {
1528 'id': 'lsguqyKfVQg',
1529 'ext': 'mp4',
1530 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1531 'alt_title': 'Dark Walk',
1532 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1533 'duration': 133,
1534 'upload_date': '20151119',
1535 'uploader_id': 'IronSoulElf',
1536 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1537 'uploader': 'IronSoulElf',
1538 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1539 'track': 'Dark Walk',
1540 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1541 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1542 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1543 'categories': ['Film & Animation'],
1544 'view_count': int,
1545 'live_status': 'not_live',
1546 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1547 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1548 'tags': 'count:13',
1549 'availability': 'public',
1550 'channel': 'IronSoulElf',
1551 'playable_in_embed': True,
1552 'like_count': int,
1553 'age_limit': 0,
1554 'channel_follower_count': int
1555 },
1556 'params': {
1557 'skip_download': True,
1558 },
1559 },
1560 {
1561 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1562 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1563 'only_matching': True,
1564 },
1565 {
1566 # Video with yt:stretch=17:0
1567 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1568 'info_dict': {
1569 'id': 'Q39EVAstoRM',
1570 'ext': 'mp4',
1571 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1572 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1573 'upload_date': '20151107',
1574 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1575 'uploader': 'CH GAMER DROID',
1576 },
1577 'params': {
1578 'skip_download': True,
1579 },
1580 'skip': 'This video does not exist.',
1581 },
1582 {
1583 # Video with incomplete 'yt:stretch=16:'
1584 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1585 'only_matching': True,
1586 },
1587 {
1588 # Video licensed under Creative Commons
1589 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1590 'info_dict': {
1591 'id': 'M4gD1WSo5mA',
1592 'ext': 'mp4',
1593 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1594 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1595 'duration': 721,
1596 'upload_date': '20150128',
1597 'uploader_id': 'BerkmanCenter',
1598 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1599 'uploader': 'The Berkman Klein Center for Internet & Society',
1600 'license': 'Creative Commons Attribution license (reuse allowed)',
1601 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1602 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1603 'like_count': int,
1604 'age_limit': 0,
1605 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1606 'channel': 'The Berkman Klein Center for Internet & Society',
1607 'availability': 'public',
1608 'view_count': int,
1609 'categories': ['Education'],
1610 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1611 'live_status': 'not_live',
1612 'playable_in_embed': True,
1613 'channel_follower_count': int
1614 },
1615 'params': {
1616 'skip_download': True,
1617 },
1618 },
1619 {
1620 # Channel-like uploader_url
1621 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1622 'info_dict': {
1623 'id': 'eQcmzGIKrzg',
1624 'ext': 'mp4',
1625 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1626 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1627 'duration': 4060,
1628 'upload_date': '20151120',
1629 'uploader': 'Bernie Sanders',
1630 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1631 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1632 'license': 'Creative Commons Attribution license (reuse allowed)',
1633 'playable_in_embed': True,
1634 'tags': 'count:12',
1635 'like_count': int,
1636 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1637 'age_limit': 0,
1638 'availability': 'public',
1639 'categories': ['News & Politics'],
1640 'channel': 'Bernie Sanders',
1641 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1642 'view_count': int,
1643 'live_status': 'not_live',
1644 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1645 'channel_follower_count': int
1646 },
1647 'params': {
1648 'skip_download': True,
1649 },
1650 },
1651 {
1652 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1653 'only_matching': True,
1654 },
1655 {
1656 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1657 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1658 'only_matching': True,
1659 },
1660 {
1661 # Rental video preview
1662 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1663 'info_dict': {
1664 'id': 'uGpuVWrhIzE',
1665 'ext': 'mp4',
1666 'title': 'Piku - Trailer',
1667 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1668 'upload_date': '20150811',
1669 'uploader': 'FlixMatrix',
1670 'uploader_id': 'FlixMatrixKaravan',
1671 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1672 'license': 'Standard YouTube License',
1673 },
1674 'params': {
1675 'skip_download': True,
1676 },
1677 'skip': 'This video is not available.',
1678 },
1679 {
1680 # YouTube Red video with episode data
1681 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1682 'info_dict': {
1683 'id': 'iqKdEhx-dD4',
1684 'ext': 'mp4',
1685 'title': 'Isolation - Mind Field (Ep 1)',
1686 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1687 'duration': 2085,
1688 'upload_date': '20170118',
1689 'uploader': 'Vsauce',
1690 'uploader_id': 'Vsauce',
1691 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1692 'series': 'Mind Field',
1693 'season_number': 1,
1694 'episode_number': 1,
1695 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1696 'tags': 'count:12',
1697 'view_count': int,
1698 'availability': 'public',
1699 'age_limit': 0,
1700 'channel': 'Vsauce',
1701 'episode': 'Episode 1',
1702 'categories': ['Entertainment'],
1703 'season': 'Season 1',
1704 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1705 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1706 'like_count': int,
1707 'playable_in_embed': True,
1708 'live_status': 'not_live',
1709 'channel_follower_count': int
1710 },
1711 'params': {
1712 'skip_download': True,
1713 },
1714 'expected_warnings': [
1715 'Skipping DASH manifest',
1716 ],
1717 },
1718 {
1719 # The following content has been identified by the YouTube community
1720 # as inappropriate or offensive to some audiences.
1721 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1722 'info_dict': {
1723 'id': '6SJNVb0GnPI',
1724 'ext': 'mp4',
1725 'title': 'Race Differences in Intelligence',
1726 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1727 'duration': 965,
1728 'upload_date': '20140124',
1729 'uploader': 'New Century Foundation',
1730 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1731 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1732 },
1733 'params': {
1734 'skip_download': True,
1735 },
1736 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1737 },
1738 {
1739 # itag 212
1740 'url': '1t24XAntNCY',
1741 'only_matching': True,
1742 },
1743 {
1744 # geo restricted to JP
1745 'url': 'sJL6WA-aGkQ',
1746 'only_matching': True,
1747 },
1748 {
1749 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1750 'only_matching': True,
1751 },
1752 {
1753 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1754 'only_matching': True,
1755 },
1756 {
1757 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1758 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1759 'only_matching': True,
1760 },
1761 {
1762 # DRM protected
1763 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1764 'only_matching': True,
1765 },
1766 {
1767 # Video with unsupported adaptive stream type formats
1768 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1769 'info_dict': {
1770 'id': 'Z4Vy8R84T1U',
1771 'ext': 'mp4',
1772 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1773 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1774 'duration': 433,
1775 'upload_date': '20130923',
1776 'uploader': 'Amelia Putri Harwita',
1777 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1778 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1779 'formats': 'maxcount:10',
1780 },
1781 'params': {
1782 'skip_download': True,
1783 'youtube_include_dash_manifest': False,
1784 },
1785 'skip': 'not actual anymore',
1786 },
1787 {
1788 # Youtube Music Auto-generated description
1789 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1790 'info_dict': {
1791 'id': 'MgNrAu2pzNs',
1792 'ext': 'mp4',
1793 'title': 'Voyeur Girl',
1794 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1795 'upload_date': '20190312',
1796 'uploader': 'Stephen - Topic',
1797 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1798 'artist': 'Stephen',
1799 'track': 'Voyeur Girl',
1800 'album': 'it\'s too much love to know my dear',
1801 'release_date': '20190313',
1802 'release_year': 2019,
1803 'alt_title': 'Voyeur Girl',
1804 'view_count': int,
1805 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1806 'playable_in_embed': True,
1807 'like_count': int,
1808 'categories': ['Music'],
1809 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1810 'channel': 'Stephen',
1811 'availability': 'public',
1812 'creator': 'Stephen',
1813 'duration': 169,
1814 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1815 'age_limit': 0,
1816 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1817 'tags': 'count:11',
1818 'live_status': 'not_live',
1819 'channel_follower_count': int
1820 },
1821 'params': {
1822 'skip_download': True,
1823 },
1824 },
1825 {
1826 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1827 'only_matching': True,
1828 },
1829 {
1830 # invalid -> valid video id redirection
1831 'url': 'DJztXj2GPfl',
1832 'info_dict': {
1833 'id': 'DJztXj2GPfk',
1834 'ext': 'mp4',
1835 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1836 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1837 'upload_date': '20090125',
1838 'uploader': 'Prochorowka',
1839 'uploader_id': 'Prochorowka',
1840 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1841 'artist': 'Panjabi MC',
1842 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1843 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1844 },
1845 'params': {
1846 'skip_download': True,
1847 },
1848 'skip': 'Video unavailable',
1849 },
1850 {
1851 # empty description results in an empty string
1852 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1853 'info_dict': {
1854 'id': 'x41yOUIvK2k',
1855 'ext': 'mp4',
1856 'title': 'IMG 3456',
1857 'description': '',
1858 'upload_date': '20170613',
1859 'uploader_id': 'ElevageOrVert',
1860 'uploader': 'ElevageOrVert',
1861 'view_count': int,
1862 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1863 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1864 'like_count': int,
1865 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1866 'tags': [],
1867 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1868 'availability': 'public',
1869 'age_limit': 0,
1870 'categories': ['Pets & Animals'],
1871 'duration': 7,
1872 'playable_in_embed': True,
1873 'live_status': 'not_live',
1874 'channel': 'ElevageOrVert',
1875 'channel_follower_count': int
1876 },
1877 'params': {
1878 'skip_download': True,
1879 },
1880 },
1881 {
1882 # with '};' inside yt initial data (see [1])
1883 # see [2] for an example with '};' inside ytInitialPlayerResponse
1884 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1885 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1886 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1887 'info_dict': {
1888 'id': 'CHqg6qOn4no',
1889 'ext': 'mp4',
1890 'title': 'Part 77 Sort a list of simple types in c#',
1891 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1892 'upload_date': '20130831',
1893 'uploader_id': 'kudvenkat',
1894 'uploader': 'kudvenkat',
1895 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1896 'like_count': int,
1897 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1898 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1899 'live_status': 'not_live',
1900 'categories': ['Education'],
1901 'availability': 'public',
1902 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1903 'tags': 'count:12',
1904 'playable_in_embed': True,
1905 'age_limit': 0,
1906 'view_count': int,
1907 'duration': 522,
1908 'channel': 'kudvenkat',
1909 'channel_follower_count': int
1910 },
1911 'params': {
1912 'skip_download': True,
1913 },
1914 },
1915 {
1916 # another example of '};' in ytInitialData
1917 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1918 'only_matching': True,
1919 },
1920 {
1921 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1922 'only_matching': True,
1923 },
1924 {
1925 # https://github.com/ytdl-org/youtube-dl/pull/28094
1926 'url': 'OtqTfy26tG0',
1927 'info_dict': {
1928 'id': 'OtqTfy26tG0',
1929 'ext': 'mp4',
1930 'title': 'Burn Out',
1931 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1932 'upload_date': '20141120',
1933 'uploader': 'The Cinematic Orchestra - Topic',
1934 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1935 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1936 'artist': 'The Cinematic Orchestra',
1937 'track': 'Burn Out',
1938 'album': 'Every Day',
1939 'like_count': int,
1940 'live_status': 'not_live',
1941 'alt_title': 'Burn Out',
1942 'duration': 614,
1943 'age_limit': 0,
1944 'view_count': int,
1945 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1946 'creator': 'The Cinematic Orchestra',
1947 'channel': 'The Cinematic Orchestra',
1948 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1949 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1950 'availability': 'public',
1951 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1952 'categories': ['Music'],
1953 'playable_in_embed': True,
1954 'channel_follower_count': int
1955 },
1956 'params': {
1957 'skip_download': True,
1958 },
1959 },
1960 {
1961 # controversial video, only works with bpctr when authenticated with cookies
1962 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1963 'only_matching': True,
1964 },
1965 {
1966 # controversial video, requires bpctr/contentCheckOk
1967 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1968 'info_dict': {
1969 'id': 'SZJvDhaSDnc',
1970 'ext': 'mp4',
1971 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1972 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1973 'uploader': 'CBS Mornings',
1974 'uploader_id': 'CBSThisMorning',
1975 'upload_date': '20140716',
1976 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1977 'duration': 170,
1978 'categories': ['News & Politics'],
1979 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1980 'view_count': int,
1981 'channel': 'CBS Mornings',
1982 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1983 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1984 'age_limit': 18,
1985 'availability': 'needs_auth',
1986 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1987 'like_count': int,
1988 'live_status': 'not_live',
1989 'playable_in_embed': True,
1990 'channel_follower_count': int
1991 }
1992 },
1993 {
1994 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1995 'url': 'cBvYw8_A0vQ',
1996 'info_dict': {
1997 'id': 'cBvYw8_A0vQ',
1998 'ext': 'mp4',
1999 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2000 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2001 'upload_date': '20201120',
2002 'uploader': 'Walk around Japan',
2003 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2004 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2005 'duration': 1456,
2006 'categories': ['Travel & Events'],
2007 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2008 'view_count': int,
2009 'channel': 'Walk around Japan',
2010 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2011 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2012 'age_limit': 0,
2013 'availability': 'public',
2014 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2015 'live_status': 'not_live',
2016 'playable_in_embed': True,
2017 'channel_follower_count': int
2018 },
2019 'params': {
2020 'skip_download': True,
2021 },
2022 }, {
2023 # Has multiple audio streams
2024 'url': 'WaOKSUlf4TM',
2025 'only_matching': True
2026 }, {
2027 # Requires Premium: has format 141 when requested using YTM url
2028 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2029 'only_matching': True
2030 }, {
2031 # multiple subtitles with same lang_code
2032 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2033 'only_matching': True,
2034 }, {
2035 # Force use android client fallback
2036 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2037 'info_dict': {
2038 'id': 'YOelRv7fMxY',
2039 'title': 'DIGGING A SECRET TUNNEL Part 1',
2040 'ext': '3gp',
2041 'upload_date': '20210624',
2042 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2043 'uploader': 'colinfurze',
2044 'uploader_id': 'colinfurze',
2045 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2046 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2047 'duration': 596,
2048 'categories': ['Entertainment'],
2049 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2050 'view_count': int,
2051 'channel': 'colinfurze',
2052 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2053 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2054 'age_limit': 0,
2055 'availability': 'public',
2056 'like_count': int,
2057 'live_status': 'not_live',
2058 'playable_in_embed': True,
2059 'channel_follower_count': int
2060 },
2061 'params': {
2062 'format': '17', # 3gp format available on android
2063 'extractor_args': {'youtube': {'player_client': ['android']}},
2064 },
2065 },
2066 {
2067 # Skip download of additional client configs (remix client config in this case)
2068 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2069 'only_matching': True,
2070 'params': {
2071 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2072 },
2073 }, {
2074 # shorts
2075 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2076 'only_matching': True,
2077 }, {
2078 'note': 'Storyboards',
2079 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2080 'info_dict': {
2081 'id': '5KLPxDtMqe8',
2082 'ext': 'mhtml',
2083 'format_id': 'sb0',
2084 'title': 'Your Brain is Plastic',
2085 'uploader_id': 'scishow',
2086 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2087 'upload_date': '20140324',
2088 'uploader': 'SciShow',
2089 'like_count': int,
2090 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2091 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2092 'view_count': int,
2093 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2094 'playable_in_embed': True,
2095 'tags': 'count:12',
2096 'uploader_url': 'http://www.youtube.com/user/scishow',
2097 'availability': 'public',
2098 'channel': 'SciShow',
2099 'live_status': 'not_live',
2100 'duration': 248,
2101 'categories': ['Education'],
2102 'age_limit': 0,
2103 'channel_follower_count': int
2104 }, 'params': {'format': 'mhtml', 'skip_download': True}
2105 }, {
2106 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2107 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2108 'info_dict': {
2109 'id': '2NUZ8W2llS4',
2110 'ext': 'mp4',
2111 'title': 'The NP that test your phone performance 🙂',
2112 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2113 'uploader': 'Leon Nguyen',
2114 'uploader_id': 'VNSXIII',
2115 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2116 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2117 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2118 'duration': 21,
2119 'view_count': int,
2120 'age_limit': 0,
2121 'categories': ['Gaming'],
2122 'tags': 'count:23',
2123 'playable_in_embed': True,
2124 'live_status': 'not_live',
2125 'upload_date': '20220103',
2126 'like_count': int,
2127 'availability': 'public',
2128 'channel': 'Leon Nguyen',
2129 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2130 'channel_follower_count': int
2131 }
2132 }, {
2133 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2134 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2135 'info_dict': {
2136 'id': 'mzZzzBU6lrM',
2137 'ext': 'mp4',
2138 'title': 'I Met GeorgeNotFound In Real Life...',
2139 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2140 'uploader': 'Quackity',
2141 'uploader_id': 'QuackityHQ',
2142 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2143 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2144 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2145 'duration': 955,
2146 'view_count': int,
2147 'age_limit': 0,
2148 'categories': ['Entertainment'],
2149 'tags': 'count:26',
2150 'playable_in_embed': True,
2151 'live_status': 'not_live',
2152 'release_timestamp': 1641172509,
2153 'release_date': '20220103',
2154 'upload_date': '20220103',
2155 'like_count': int,
2156 'availability': 'public',
2157 'channel': 'Quackity',
2158 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2159 'channel_follower_count': int
2160 }
2161 },
2162 { # continuous livestream. Microformat upload date should be preferred.
2163 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2164 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2165 'info_dict': {
2166 'id': 'kgx4WGK0oNU',
2167 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2168 'ext': 'mp4',
2169 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2170 'availability': 'public',
2171 'age_limit': 0,
2172 'release_timestamp': 1637975704,
2173 'upload_date': '20210619',
2174 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2175 'live_status': 'is_live',
2176 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2177 'uploader': '阿鲍Abao',
2178 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2179 'channel': 'Abao in Tokyo',
2180 'channel_follower_count': int,
2181 'release_date': '20211127',
2182 'tags': 'count:39',
2183 'categories': ['People & Blogs'],
2184 'like_count': int,
2185 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2186 'view_count': int,
2187 'playable_in_embed': True,
2188 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2189 },
2190 'params': {'skip_download': True}
2191 },
2192 ]
2193
2194 @classmethod
2195 def suitable(cls, url):
2196 from ..utils import parse_qs
2197
2198 qs = parse_qs(url)
2199 if qs.get('list', [None])[0]:
2200 return False
2201 return super(YoutubeIE, cls).suitable(url)
2202
2203 def __init__(self, *args, **kwargs):
2204 super(YoutubeIE, self).__init__(*args, **kwargs)
2205 self._code_cache = {}
2206 self._player_cache = {}
2207
2208 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2209 lock = threading.Lock()
2210
2211 is_live = True
2212 start_time = time.time()
2213 formats = [f for f in formats if f.get('is_from_start')]
2214
2215 def refetch_manifest(format_id, delay):
2216 nonlocal formats, start_time, is_live
2217 if time.time() <= start_time + delay:
2218 return
2219
2220 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2221 video_details = traverse_obj(
2222 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2223 microformats = traverse_obj(
2224 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2225 expected_type=dict, default=[])
2226 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
2227 start_time = time.time()
2228
2229 def mpd_feed(format_id, delay):
2230 """
2231 @returns (manifest_url, manifest_stream_number, is_live) or None
2232 """
2233 with lock:
2234 refetch_manifest(format_id, delay)
2235
2236 f = next((f for f in formats if f['format_id'] == format_id), None)
2237 if not f:
2238 if not is_live:
2239 self.to_screen(f'{video_id}: Video is no longer live')
2240 else:
2241 self.report_warning(
2242 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2243 return None
2244 return f['manifest_url'], f['manifest_stream_number'], is_live
2245
2246 for f in formats:
2247 f['is_live'] = True
2248 f['protocol'] = 'http_dash_segments_generator'
2249 f['fragments'] = functools.partial(
2250 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2251
2252 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2253 FETCH_SPAN, MAX_DURATION = 5, 432000
2254
2255 mpd_url, stream_number, is_live = None, None, True
2256
2257 begin_index = 0
2258 download_start_time = ctx.get('start') or time.time()
2259
2260 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2261 if lack_early_segments:
2262 self.report_warning(bug_reports_message(
2263 'Starting download from the last 120 hours of the live stream since '
2264 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2265 lack_early_segments = True
2266
2267 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2268 fragments, fragment_base_url = None, None
2269
2270 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2271 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2272 # Obtain from MPD's maximum seq value
2273 old_mpd_url = mpd_url
2274 last_error = ctx.pop('last_error', None)
2275 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2276 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2277 or (mpd_url, stream_number, False))
2278 if not refresh_sequence:
2279 if expire_fast and not is_live:
2280 return False, last_seq
2281 elif old_mpd_url == mpd_url:
2282 return True, last_seq
2283 try:
2284 fmts, _ = self._extract_mpd_formats_and_subtitles(
2285 mpd_url, None, note=False, errnote=False, fatal=False)
2286 except ExtractorError:
2287 fmts = None
2288 if not fmts:
2289 no_fragment_score += 2
2290 return False, last_seq
2291 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2292 fragments = fmt_info['fragments']
2293 fragment_base_url = fmt_info['fragment_base_url']
2294 assert fragment_base_url
2295
2296 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2297 return True, _last_seq
2298
2299 while is_live:
2300 fetch_time = time.time()
2301 if no_fragment_score > 30:
2302 return
2303 if last_segment_url:
2304 # Obtain from "X-Head-Seqnum" header value from each segment
2305 try:
2306 urlh = self._request_webpage(
2307 last_segment_url, None, note=False, errnote=False, fatal=False)
2308 except ExtractorError:
2309 urlh = None
2310 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2311 if last_seq is None:
2312 no_fragment_score += 2
2313 last_segment_url = None
2314 continue
2315 else:
2316 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2317 no_fragment_score += 2
2318 if not should_continue:
2319 continue
2320
2321 if known_idx > last_seq:
2322 last_segment_url = None
2323 continue
2324
2325 last_seq += 1
2326
2327 if begin_index < 0 and known_idx < 0:
2328 # skip from the start when it's negative value
2329 known_idx = last_seq + begin_index
2330 if lack_early_segments:
2331 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2332 try:
2333 for idx in range(known_idx, last_seq):
2334 # do not update sequence here or you'll get skipped some part of it
2335 should_continue, _ = _extract_sequence_from_mpd(False, False)
2336 if not should_continue:
2337 known_idx = idx - 1
2338 raise ExtractorError('breaking out of outer loop')
2339 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2340 yield {
2341 'url': last_segment_url,
2342 }
2343 if known_idx == last_seq:
2344 no_fragment_score += 5
2345 else:
2346 no_fragment_score = 0
2347 known_idx = last_seq
2348 except ExtractorError:
2349 continue
2350
2351 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2352
2353 def _extract_player_url(self, *ytcfgs, webpage=None):
2354 player_url = traverse_obj(
2355 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2356 get_all=False, expected_type=compat_str)
2357 if not player_url:
2358 return
2359 return urljoin('https://www.youtube.com', player_url)
2360
2361 def _download_player_url(self, video_id, fatal=False):
2362 res = self._download_webpage(
2363 'https://www.youtube.com/iframe_api',
2364 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2365 if res:
2366 player_version = self._search_regex(
2367 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2368 if player_version:
2369 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2370
2371 def _signature_cache_id(self, example_sig):
2372 """ Return a string representation of a signature """
2373 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
2374
2375 @classmethod
2376 def _extract_player_info(cls, player_url):
2377 for player_re in cls._PLAYER_INFO_RE:
2378 id_m = re.search(player_re, player_url)
2379 if id_m:
2380 break
2381 else:
2382 raise ExtractorError('Cannot identify player %r' % player_url)
2383 return id_m.group('id')
2384
2385 def _load_player(self, video_id, player_url, fatal=True):
2386 player_id = self._extract_player_info(player_url)
2387 if player_id not in self._code_cache:
2388 code = self._download_webpage(
2389 player_url, video_id, fatal=fatal,
2390 note='Downloading player ' + player_id,
2391 errnote='Download of %s failed' % player_url)
2392 if code:
2393 self._code_cache[player_id] = code
2394 return self._code_cache.get(player_id)
2395
2396 def _extract_signature_function(self, video_id, player_url, example_sig):
2397 player_id = self._extract_player_info(player_url)
2398
2399 # Read from filesystem cache
2400 func_id = 'js_%s_%s' % (
2401 player_id, self._signature_cache_id(example_sig))
2402 assert os.path.basename(func_id) == func_id
2403
2404 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
2405 if cache_spec is not None:
2406 return lambda s: ''.join(s[i] for i in cache_spec)
2407
2408 code = self._load_player(video_id, player_url)
2409 if code:
2410 res = self._parse_sig_js(code)
2411
2412 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2413 cache_res = res(test_string)
2414 cache_spec = [ord(c) for c in cache_res]
2415
2416 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2417 return res
2418
2419 def _print_sig_code(self, func, example_sig):
2420 if not self.get_param('youtube_print_sig_code'):
2421 return
2422
2423 def gen_sig_code(idxs):
2424 def _genslice(start, end, step):
2425 starts = '' if start == 0 else str(start)
2426 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2427 steps = '' if step == 1 else (':%d' % step)
2428 return 's[%s%s%s]' % (starts, ends, steps)
2429
2430 step = None
2431 # Quelch pyflakes warnings - start will be set when step is set
2432 start = '(Never used)'
2433 for i, prev in zip(idxs[1:], idxs[:-1]):
2434 if step is not None:
2435 if i - prev == step:
2436 continue
2437 yield _genslice(start, prev, step)
2438 step = None
2439 continue
2440 if i - prev in [-1, 1]:
2441 step = i - prev
2442 start = prev
2443 continue
2444 else:
2445 yield 's[%d]' % prev
2446 if step is None:
2447 yield 's[%d]' % i
2448 else:
2449 yield _genslice(start, i, step)
2450
2451 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2452 cache_res = func(test_string)
2453 cache_spec = [ord(c) for c in cache_res]
2454 expr_code = ' + '.join(gen_sig_code(cache_spec))
2455 signature_id_tuple = '(%s)' % (
2456 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
2457 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2458 ' return %s\n') % (signature_id_tuple, expr_code)
2459 self.to_screen('Extracted signature function:\n' + code)
2460
2461 def _parse_sig_js(self, jscode):
2462 funcname = self._search_regex(
2463 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2464 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2465 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2466 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2467 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}\(a,\d+\)',
2468 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\(\s*""\s*\)',
2469 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2470 # Obsolete patterns
2471 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2472 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2473 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2474 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2475 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2476 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2477 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2478 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2479 jscode, 'Initial JS player signature function name', group='sig')
2480
2481 jsi = JSInterpreter(jscode)
2482 initial_function = jsi.extract_function(funcname)
2483 return lambda s: initial_function([s])
2484
2485 def _decrypt_signature(self, s, video_id, player_url):
2486 """Turn the encrypted s field into a working signature"""
2487
2488 if player_url is None:
2489 raise ExtractorError('Cannot decrypt signature without player_url')
2490
2491 try:
2492 player_id = (player_url, self._signature_cache_id(s))
2493 if player_id not in self._player_cache:
2494 func = self._extract_signature_function(
2495 video_id, player_url, s
2496 )
2497 self._player_cache[player_id] = func
2498 func = self._player_cache[player_id]
2499 self._print_sig_code(func, s)
2500 return func(s)
2501 except Exception as e:
2502 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2503
2504 def _decrypt_nsig(self, s, video_id, player_url):
2505 """Turn the encrypted n field into a working signature"""
2506 if player_url is None:
2507 raise ExtractorError('Cannot decrypt nsig without player_url')
2508 player_url = urljoin('https://www.youtube.com', player_url)
2509
2510 sig_id = ('nsig_value', s)
2511 if sig_id in self._player_cache:
2512 return self._player_cache[sig_id]
2513
2514 try:
2515 player_id = ('nsig', player_url)
2516 if player_id not in self._player_cache:
2517 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2518 func = self._player_cache[player_id]
2519 self._player_cache[sig_id] = func(s)
2520 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2521 return self._player_cache[sig_id]
2522 except Exception as e:
2523 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2524
2525 def _extract_n_function_name(self, jscode):
2526 nfunc, idx = self._search_regex(
2527 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2528 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2529 if not idx:
2530 return nfunc
2531 return json.loads(js_to_json(self._search_regex(
2532 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
2533 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
2534
2535 def _extract_n_function(self, video_id, player_url):
2536 player_id = self._extract_player_info(player_url)
2537 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2538
2539 if func_code:
2540 jsi = JSInterpreter(func_code)
2541 else:
2542 jscode = self._load_player(video_id, player_url)
2543 funcname = self._extract_n_function_name(jscode)
2544 jsi = JSInterpreter(jscode)
2545 func_code = jsi.extract_function_code(funcname)
2546 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2547
2548 if self.get_param('youtube_print_sig_code'):
2549 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2550
2551 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2552
2553 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2554 """
2555 Extract signatureTimestamp (sts)
2556 Required to tell API what sig/player version is in use.
2557 """
2558 sts = None
2559 if isinstance(ytcfg, dict):
2560 sts = int_or_none(ytcfg.get('STS'))
2561
2562 if not sts:
2563 # Attempt to extract from player
2564 if player_url is None:
2565 error_msg = 'Cannot extract signature timestamp without player_url.'
2566 if fatal:
2567 raise ExtractorError(error_msg)
2568 self.report_warning(error_msg)
2569 return
2570 code = self._load_player(video_id, player_url, fatal=fatal)
2571 if code:
2572 sts = int_or_none(self._search_regex(
2573 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2574 'JS player signature timestamp', group='sts', fatal=fatal))
2575 return sts
2576
2577 def _mark_watched(self, video_id, player_responses):
2578 playback_url = get_first(
2579 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2580 expected_type=url_or_none)
2581 if not playback_url:
2582 self.report_warning('Unable to mark watched')
2583 return
2584 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2585 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2586
2587 # cpn generation algorithm is reverse engineered from base.js.
2588 # In fact it works even with dummy cpn.
2589 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2590 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2591
2592 qs.update({
2593 'ver': ['2'],
2594 'cpn': [cpn],
2595 })
2596 playback_url = compat_urlparse.urlunparse(
2597 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2598
2599 self._download_webpage(
2600 playback_url, video_id, 'Marking watched',
2601 'Unable to mark watched', fatal=False)
2602
2603 @staticmethod
2604 def _extract_urls(webpage):
2605 # Embedded YouTube player
2606 entries = [
2607 unescapeHTML(mobj.group('url'))
2608 for mobj in re.finditer(r'''(?x)
2609 (?:
2610 <iframe[^>]+?src=|
2611 data-video-url=|
2612 <embed[^>]+?src=|
2613 embedSWF\(?:\s*|
2614 <object[^>]+data=|
2615 new\s+SWFObject\(
2616 )
2617 (["\'])
2618 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2619 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2620 \1''', webpage)]
2621
2622 # lazyYT YouTube embed
2623 entries.extend(list(map(
2624 unescapeHTML,
2625 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2626
2627 # Wordpress "YouTube Video Importer" plugin
2628 matches = re.findall(r'''(?x)<div[^>]+
2629 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2630 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2631 entries.extend(m[-1] for m in matches)
2632
2633 return entries
2634
2635 @staticmethod
2636 def _extract_url(webpage):
2637 urls = YoutubeIE._extract_urls(webpage)
2638 return urls[0] if urls else None
2639
2640 @classmethod
2641 def extract_id(cls, url):
2642 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2643 if mobj is None:
2644 raise ExtractorError('Invalid URL: %s' % url)
2645 return mobj.group('id')
2646
2647 def _extract_chapters_from_json(self, data, duration):
2648 chapter_list = traverse_obj(
2649 data, (
2650 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2651 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2652 ), expected_type=list)
2653
2654 return self._extract_chapters(
2655 chapter_list,
2656 chapter_time=lambda chapter: float_or_none(
2657 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2658 chapter_title=lambda chapter: traverse_obj(
2659 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2660 duration=duration)
2661
2662 def _extract_chapters_from_engagement_panel(self, data, duration):
2663 content_list = traverse_obj(
2664 data,
2665 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2666 expected_type=list, default=[])
2667 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2668 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2669
2670 return next((
2671 filter(None, (
2672 self._extract_chapters(
2673 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2674 chapter_time, chapter_title, duration)
2675 for contents in content_list
2676 ))), [])
2677
2678 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2679 chapters = []
2680 last_chapter = {'start_time': 0}
2681 for idx, chapter in enumerate(chapter_list or []):
2682 title = chapter_title(chapter)
2683 start_time = chapter_time(chapter)
2684 if start_time is None:
2685 continue
2686 last_chapter['end_time'] = start_time
2687 if start_time < last_chapter['start_time']:
2688 if idx == 1:
2689 chapters.pop()
2690 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2691 else:
2692 self.report_warning(f'Invalid start time for chapter "{title}"')
2693 continue
2694 last_chapter = {'start_time': start_time, 'title': title}
2695 chapters.append(last_chapter)
2696 last_chapter['end_time'] = duration
2697 return chapters
2698
2699 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2700 return self._parse_json(self._search_regex(
2701 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2702 regex), webpage, name, default='{}'), video_id, fatal=False)
2703
2704 def _extract_comment(self, comment_renderer, parent=None):
2705 comment_id = comment_renderer.get('commentId')
2706 if not comment_id:
2707 return
2708
2709 text = self._get_text(comment_renderer, 'contentText')
2710
2711 # note: timestamp is an estimate calculated from the current time and time_text
2712 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2713 author = self._get_text(comment_renderer, 'authorText')
2714 author_id = try_get(comment_renderer,
2715 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2716
2717 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2718 lambda x: x['likeCount']), compat_str)) or 0
2719 author_thumbnail = try_get(comment_renderer,
2720 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2721
2722 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2723 is_favorited = 'creatorHeart' in (try_get(
2724 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2725 return {
2726 'id': comment_id,
2727 'text': text,
2728 'timestamp': timestamp,
2729 'time_text': time_text,
2730 'like_count': votes,
2731 'is_favorited': is_favorited,
2732 'author': author,
2733 'author_id': author_id,
2734 'author_thumbnail': author_thumbnail,
2735 'author_is_uploader': author_is_uploader,
2736 'parent': parent or 'root'
2737 }
2738
2739 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2740
2741 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2742
2743 def extract_header(contents):
2744 _continuation = None
2745 for content in contents:
2746 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2747 expected_comment_count = self._get_count(
2748 comments_header_renderer, 'countText', 'commentsCount')
2749
2750 if expected_comment_count:
2751 tracker['est_total'] = expected_comment_count
2752 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2753 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2754
2755 sort_menu_item = try_get(
2756 comments_header_renderer,
2757 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2758 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2759
2760 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2761 if not _continuation:
2762 continue
2763
2764 sort_text = str_or_none(sort_menu_item.get('title'))
2765 if not sort_text:
2766 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2767 self.to_screen('Sorting comments by %s' % sort_text.lower())
2768 break
2769 return _continuation
2770
2771 def extract_thread(contents):
2772 if not parent:
2773 tracker['current_page_thread'] = 0
2774 for content in contents:
2775 if not parent and tracker['total_parent_comments'] >= max_parents:
2776 yield
2777 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2778 comment_renderer = get_first(
2779 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2780 expected_type=dict, default={})
2781
2782 comment = self._extract_comment(comment_renderer, parent)
2783 if not comment:
2784 continue
2785
2786 tracker['running_total'] += 1
2787 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2788 yield comment
2789
2790 # Attempt to get the replies
2791 comment_replies_renderer = try_get(
2792 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2793
2794 if comment_replies_renderer:
2795 tracker['current_page_thread'] += 1
2796 comment_entries_iter = self._comment_entries(
2797 comment_replies_renderer, ytcfg, video_id,
2798 parent=comment.get('id'), tracker=tracker)
2799 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2800 yield reply_comment
2801
2802 # Keeps track of counts across recursive calls
2803 if not tracker:
2804 tracker = dict(
2805 running_total=0,
2806 est_total=0,
2807 current_page_thread=0,
2808 total_parent_comments=0,
2809 total_reply_comments=0)
2810
2811 # TODO: Deprecated
2812 # YouTube comments have a max depth of 2
2813 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2814 if max_depth:
2815 self._downloader.deprecation_warning(
2816 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2817 if max_depth == 1 and parent:
2818 return
2819
2820 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2821 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2822
2823 continuation = self._extract_continuation(root_continuation_data)
2824 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2825 if message and not parent:
2826 self.report_warning(message, video_id=video_id)
2827
2828 response = None
2829 is_first_continuation = parent is None
2830
2831 for page_num in itertools.count(0):
2832 if not continuation:
2833 break
2834 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2835 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2836 if page_num == 0:
2837 if is_first_continuation:
2838 note_prefix = 'Downloading comment section API JSON'
2839 else:
2840 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2841 tracker['current_page_thread'], comment_prog_str)
2842 else:
2843 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2844 ' ' if parent else '', ' replies' if parent else '',
2845 page_num, comment_prog_str)
2846
2847 response = self._extract_response(
2848 item_id=None, query=continuation,
2849 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2850 check_get_keys='onResponseReceivedEndpoints')
2851
2852 continuation_contents = traverse_obj(
2853 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2854
2855 continuation = None
2856 for continuation_section in continuation_contents:
2857 continuation_items = traverse_obj(
2858 continuation_section,
2859 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2860 get_all=False, expected_type=list) or []
2861 if is_first_continuation:
2862 continuation = extract_header(continuation_items)
2863 is_first_continuation = False
2864 if continuation:
2865 break
2866 continue
2867
2868 for entry in extract_thread(continuation_items):
2869 if not entry:
2870 return
2871 yield entry
2872 continuation = self._extract_continuation({'contents': continuation_items})
2873 if continuation:
2874 break
2875
2876 def _get_comments(self, ytcfg, video_id, contents, webpage):
2877 """Entry for comment extraction"""
2878 def _real_comment_extract(contents):
2879 renderer = next((
2880 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2881 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2882 yield from self._comment_entries(renderer, ytcfg, video_id)
2883
2884 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2885 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2886
2887 @staticmethod
2888 def _get_checkok_params():
2889 return {'contentCheckOk': True, 'racyCheckOk': True}
2890
2891 @classmethod
2892 def _generate_player_context(cls, sts=None):
2893 context = {
2894 'html5Preference': 'HTML5_PREF_WANTS',
2895 }
2896 if sts is not None:
2897 context['signatureTimestamp'] = sts
2898 return {
2899 'playbackContext': {
2900 'contentPlaybackContext': context
2901 },
2902 **cls._get_checkok_params()
2903 }
2904
2905 @staticmethod
2906 def _is_agegated(player_response):
2907 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2908 return True
2909
2910 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2911 AGE_GATE_REASONS = (
2912 'confirm your age', 'age-restricted', 'inappropriate', # reason
2913 'age_verification_required', 'age_check_required', # status
2914 )
2915 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2916
2917 @staticmethod
2918 def _is_unplayable(player_response):
2919 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2920
2921 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2922
2923 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2924 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2925 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2926 headers = self.generate_api_headers(
2927 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2928
2929 yt_query = {'videoId': video_id}
2930 yt_query.update(self._generate_player_context(sts))
2931 return self._extract_response(
2932 item_id=video_id, ep='player', query=yt_query,
2933 ytcfg=player_ytcfg, headers=headers, fatal=True,
2934 default_client=client,
2935 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2936 ) or None
2937
2938 def _get_requested_clients(self, url, smuggled_data):
2939 requested_clients = []
2940 default = ['android', 'web']
2941 allowed_clients = sorted(
2942 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2943 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2944 for client in self._configuration_arg('player_client'):
2945 if client in allowed_clients:
2946 requested_clients.append(client)
2947 elif client == 'default':
2948 requested_clients.extend(default)
2949 elif client == 'all':
2950 requested_clients.extend(allowed_clients)
2951 else:
2952 self.report_warning(f'Skipping unsupported client {client}')
2953 if not requested_clients:
2954 requested_clients = default
2955
2956 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2957 requested_clients.extend(
2958 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2959
2960 return orderedSet(requested_clients)
2961
2962 def _extract_player_ytcfg(self, client, video_id):
2963 url = {
2964 'web_music': 'https://music.youtube.com',
2965 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2966 }.get(client)
2967 if not url:
2968 return {}
2969 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
2970 return self.extract_ytcfg(video_id, webpage) or {}
2971
2972 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2973 initial_pr = None
2974 if webpage:
2975 initial_pr = self._extract_yt_initial_variable(
2976 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2977 video_id, 'initial player response')
2978
2979 all_clients = set(clients)
2980 clients = clients[::-1]
2981 prs = []
2982
2983 def append_client(*client_names):
2984 """ Append the first client name that exists but not already used """
2985 for client_name in client_names:
2986 actual_client = _split_innertube_client(client_name)[0]
2987 if actual_client in INNERTUBE_CLIENTS:
2988 if actual_client not in all_clients:
2989 clients.append(client_name)
2990 all_clients.add(actual_client)
2991 return
2992
2993 # Android player_response does not have microFormats which are needed for
2994 # extraction of some data. So we return the initial_pr with formats
2995 # stripped out even if not requested by the user
2996 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2997 if initial_pr:
2998 pr = dict(initial_pr)
2999 pr['streamingData'] = None
3000 prs.append(pr)
3001
3002 last_error = None
3003 tried_iframe_fallback = False
3004 player_url = None
3005 while clients:
3006 client, base_client, variant = _split_innertube_client(clients.pop())
3007 player_ytcfg = master_ytcfg if client == 'web' else {}
3008 if 'configs' not in self._configuration_arg('player_skip'):
3009 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
3010
3011 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3012 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3013 if 'js' in self._configuration_arg('player_skip'):
3014 require_js_player = False
3015 player_url = None
3016
3017 if not player_url and not tried_iframe_fallback and require_js_player:
3018 player_url = self._download_player_url(video_id)
3019 tried_iframe_fallback = True
3020
3021 try:
3022 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3023 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3024 except ExtractorError as e:
3025 if last_error:
3026 self.report_warning(last_error)
3027 last_error = e
3028 continue
3029
3030 if pr:
3031 prs.append(pr)
3032
3033 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3034 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3035 append_client(f'{base_client}_creator')
3036 elif self._is_agegated(pr):
3037 if variant == 'tv_embedded':
3038 append_client(f'{base_client}_embedded')
3039 elif not variant:
3040 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3041
3042 if last_error:
3043 if not len(prs):
3044 raise last_error
3045 self.report_warning(last_error)
3046 return prs, player_url
3047
3048 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
3049 itags, stream_ids = {}, []
3050 itag_qualities, res_qualities = {}, {}
3051 q = qualities([
3052 # Normally tiny is the smallest video-only formats. But
3053 # audio-only formats with unknown quality may get tagged as tiny
3054 'tiny',
3055 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3056 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3057 ])
3058 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3059
3060 for fmt in streaming_formats:
3061 if fmt.get('targetDurationSec'):
3062 continue
3063
3064 itag = str_or_none(fmt.get('itag'))
3065 audio_track = fmt.get('audioTrack') or {}
3066 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3067 if stream_id in stream_ids:
3068 continue
3069
3070 quality = fmt.get('quality')
3071 height = int_or_none(fmt.get('height'))
3072 if quality == 'tiny' or not quality:
3073 quality = fmt.get('audioQuality', '').lower() or quality
3074 # The 3gp format (17) in android client has a quality of "small",
3075 # but is actually worse than other formats
3076 if itag == '17':
3077 quality = 'tiny'
3078 if quality:
3079 if itag:
3080 itag_qualities[itag] = quality
3081 if height:
3082 res_qualities[height] = quality
3083 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3084 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3085 # number of fragment that would subsequently requested with (`&sq=N`)
3086 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3087 continue
3088
3089 fmt_url = fmt.get('url')
3090 if not fmt_url:
3091 sc = compat_parse_qs(fmt.get('signatureCipher'))
3092 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3093 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3094 if not (sc and fmt_url and encrypted_sig):
3095 continue
3096 if not player_url:
3097 continue
3098 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3099 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3100 fmt_url += '&' + sp + '=' + signature
3101
3102 query = parse_qs(fmt_url)
3103 throttled = False
3104 if query.get('n'):
3105 try:
3106 fmt_url = update_url_query(fmt_url, {
3107 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3108 except ExtractorError as e:
3109 self.report_warning(
3110 f'nsig extraction failed: You may experience throttling for some formats\n'
3111 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
3112 throttled = True
3113
3114 if itag:
3115 itags[itag] = 'https'
3116 stream_ids.append(stream_id)
3117
3118 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3119 language_preference = (
3120 10 if audio_track.get('audioIsDefault') and 10
3121 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3122 else -1)
3123 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3124 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3125 # Make sure to avoid false positives with small duration differences.
3126 # Eg: __2ABJjxzNo, ySuUZEjARPY
3127 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3128 if is_damaged:
3129 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3130 dct = {
3131 'asr': int_or_none(fmt.get('audioSampleRate')),
3132 'filesize': int_or_none(fmt.get('contentLength')),
3133 'format_id': itag,
3134 'format_note': join_nonempty(
3135 '%s%s' % (audio_track.get('displayName') or '',
3136 ' (default)' if language_preference > 0 else ''),
3137 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3138 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3139 'source_preference': -10 if throttled else -1,
3140 'fps': int_or_none(fmt.get('fps')) or None,
3141 'height': height,
3142 'quality': q(quality),
3143 'has_drm': bool(fmt.get('drmFamilies')),
3144 'tbr': tbr,
3145 'url': fmt_url,
3146 'width': int_or_none(fmt.get('width')),
3147 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3148 'desc' if language_preference < -1 else ''),
3149 'language_preference': language_preference,
3150 # Strictly de-prioritize damaged and 3gp formats
3151 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3152 }
3153 mime_mobj = re.match(
3154 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3155 if mime_mobj:
3156 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3157 dct.update(parse_codecs(mime_mobj.group(2)))
3158 no_audio = dct.get('acodec') == 'none'
3159 no_video = dct.get('vcodec') == 'none'
3160 if no_audio:
3161 dct['vbr'] = tbr
3162 if no_video:
3163 dct['abr'] = tbr
3164 if no_audio or no_video:
3165 dct['downloader_options'] = {
3166 # Youtube throttles chunks >~10M
3167 'http_chunk_size': 10485760,
3168 }
3169 if dct.get('ext'):
3170 dct['container'] = dct['ext'] + '_dash'
3171 yield dct
3172
3173 live_from_start = is_live and self.get_param('live_from_start')
3174 skip_manifests = self._configuration_arg('skip')
3175 if not self.get_param('youtube_include_hls_manifest', True):
3176 skip_manifests.append('hls')
3177 get_dash = 'dash' not in skip_manifests and (
3178 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3179 get_hls = not live_from_start and 'hls' not in skip_manifests
3180
3181 def process_manifest_format(f, proto, itag):
3182 if itag in itags:
3183 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3184 return False
3185 itag = f'{itag}-{proto}'
3186 if itag:
3187 f['format_id'] = itag
3188 itags[itag] = proto
3189
3190 f['quality'] = next((
3191 q(qdict[val])
3192 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3193 if val in qdict), -1)
3194 return True
3195
3196 for sd in streaming_data:
3197 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3198 if hls_manifest_url:
3199 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3200 if process_manifest_format(f, 'hls', self._search_regex(
3201 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3202 yield f
3203
3204 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3205 if dash_manifest_url:
3206 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3207 if process_manifest_format(f, 'dash', f['format_id']):
3208 f['filesize'] = int_or_none(self._search_regex(
3209 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3210 if live_from_start:
3211 f['is_from_start'] = True
3212
3213 yield f
3214
3215 def _extract_storyboard(self, player_responses, duration):
3216 spec = get_first(
3217 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3218 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3219 if not base_url:
3220 return
3221 L = len(spec) - 1
3222 for i, args in enumerate(spec):
3223 args = args.split('#')
3224 counts = list(map(int_or_none, args[:5]))
3225 if len(args) != 8 or not all(counts):
3226 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3227 continue
3228 width, height, frame_count, cols, rows = counts
3229 N, sigh = args[6:]
3230
3231 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3232 fragment_count = frame_count / (cols * rows)
3233 fragment_duration = duration / fragment_count
3234 yield {
3235 'format_id': f'sb{i}',
3236 'format_note': 'storyboard',
3237 'ext': 'mhtml',
3238 'protocol': 'mhtml',
3239 'acodec': 'none',
3240 'vcodec': 'none',
3241 'url': url,
3242 'width': width,
3243 'height': height,
3244 'fragments': [{
3245 'url': url.replace('$M', str(j)),
3246 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3247 } for j in range(math.ceil(fragment_count))],
3248 }
3249
3250 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3251 webpage = None
3252 if 'webpage' not in self._configuration_arg('player_skip'):
3253 webpage = self._download_webpage(
3254 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3255
3256 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3257
3258 player_responses, player_url = self._extract_player_responses(
3259 self._get_requested_clients(url, smuggled_data),
3260 video_id, webpage, master_ytcfg)
3261
3262 return webpage, master_ytcfg, player_responses, player_url
3263
3264 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3265 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3266 is_live = get_first(video_details, 'isLive')
3267 if is_live is None:
3268 is_live = get_first(live_broadcast_details, 'isLiveNow')
3269
3270 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3271 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
3272
3273 return live_broadcast_details, is_live, streaming_data, formats
3274
3275 def _real_extract(self, url):
3276 url, smuggled_data = unsmuggle_url(url, {})
3277 video_id = self._match_id(url)
3278
3279 base_url = self.http_scheme() + '//www.youtube.com/'
3280 webpage_url = base_url + 'watch?v=' + video_id
3281
3282 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3283
3284 playability_statuses = traverse_obj(
3285 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3286
3287 trailer_video_id = get_first(
3288 playability_statuses,
3289 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3290 expected_type=str)
3291 if trailer_video_id:
3292 return self.url_result(
3293 trailer_video_id, self.ie_key(), trailer_video_id)
3294
3295 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3296 if webpage else (lambda x: None))
3297
3298 video_details = traverse_obj(
3299 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3300 microformats = traverse_obj(
3301 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3302 expected_type=dict, default=[])
3303 video_title = (
3304 get_first(video_details, 'title')
3305 or self._get_text(microformats, (..., 'title'))
3306 or search_meta(['og:title', 'twitter:title', 'title']))
3307 video_description = get_first(video_details, 'shortDescription')
3308
3309 multifeed_metadata_list = get_first(
3310 player_responses,
3311 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3312 expected_type=str)
3313 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3314 if self.get_param('noplaylist'):
3315 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3316 else:
3317 entries = []
3318 feed_ids = []
3319 for feed in multifeed_metadata_list.split(','):
3320 # Unquote should take place before split on comma (,) since textual
3321 # fields may contain comma as well (see
3322 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3323 feed_data = compat_parse_qs(
3324 compat_urllib_parse_unquote_plus(feed))
3325
3326 def feed_entry(name):
3327 return try_get(
3328 feed_data, lambda x: x[name][0], compat_str)
3329
3330 feed_id = feed_entry('id')
3331 if not feed_id:
3332 continue
3333 feed_title = feed_entry('title')
3334 title = video_title
3335 if feed_title:
3336 title += ' (%s)' % feed_title
3337 entries.append({
3338 '_type': 'url_transparent',
3339 'ie_key': 'Youtube',
3340 'url': smuggle_url(
3341 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3342 {'force_singlefeed': True}),
3343 'title': title,
3344 })
3345 feed_ids.append(feed_id)
3346 self.to_screen(
3347 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3348 % (', '.join(feed_ids), video_id))
3349 return self.playlist_result(
3350 entries, video_id, video_title, video_description)
3351
3352 duration = int_or_none(
3353 get_first(video_details, 'lengthSeconds')
3354 or get_first(microformats, 'lengthSeconds')
3355 or parse_duration(search_meta('duration'))) or None
3356
3357 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3358 video_id, microformats, video_details, player_responses, player_url, duration)
3359
3360 if not formats:
3361 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3362 self.report_drm(video_id)
3363 pemr = get_first(
3364 playability_statuses,
3365 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3366 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3367 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3368 if subreason:
3369 if subreason == 'The uploader has not made this video available in your country.':
3370 countries = get_first(microformats, 'availableCountries')
3371 if not countries:
3372 regions_allowed = search_meta('regionsAllowed')
3373 countries = regions_allowed.split(',') if regions_allowed else None
3374 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3375 reason += f'. {subreason}'
3376 if reason:
3377 self.raise_no_formats(reason, expected=True)
3378
3379 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3380 if not keywords and webpage:
3381 keywords = [
3382 unescapeHTML(m.group('content'))
3383 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3384 for keyword in keywords:
3385 if keyword.startswith('yt:stretch='):
3386 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3387 if mobj:
3388 # NB: float is intentional for forcing float division
3389 w, h = (float(v) for v in mobj.groups())
3390 if w > 0 and h > 0:
3391 ratio = w / h
3392 for f in formats:
3393 if f.get('vcodec') != 'none':
3394 f['stretched_ratio'] = ratio
3395 break
3396 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3397 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3398 if thumbnail_url:
3399 thumbnails.append({
3400 'url': thumbnail_url,
3401 })
3402 original_thumbnails = thumbnails.copy()
3403
3404 # The best resolution thumbnails sometimes does not appear in the webpage
3405 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3406 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3407 thumbnail_names = [
3408 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3409 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3410 'mqdefault', 'mq1', 'mq2', 'mq3',
3411 'default', '1', '2', '3'
3412 ]
3413 n_thumbnail_names = len(thumbnail_names)
3414 thumbnails.extend({
3415 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3416 video_id=video_id, name=name, ext=ext,
3417 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3418 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3419 for thumb in thumbnails:
3420 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3421 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3422 self._remove_duplicate_formats(thumbnails)
3423 self._downloader._sort_thumbnails(original_thumbnails)
3424
3425 category = get_first(microformats, 'category') or search_meta('genre')
3426 channel_id = str_or_none(
3427 get_first(video_details, 'channelId')
3428 or get_first(microformats, 'externalChannelId')
3429 or search_meta('channelId'))
3430 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3431
3432 live_content = get_first(video_details, 'isLiveContent')
3433 is_upcoming = get_first(video_details, 'isUpcoming')
3434 if is_live is None:
3435 if is_upcoming or live_content is False:
3436 is_live = False
3437 if is_upcoming is None and (live_content or is_live):
3438 is_upcoming = False
3439 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3440 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3441 if not duration and live_end_time and live_start_time:
3442 duration = live_end_time - live_start_time
3443
3444 if is_live and self.get_param('live_from_start'):
3445 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3446
3447 formats.extend(self._extract_storyboard(player_responses, duration))
3448
3449 # Source is given priority since formats that throttle are given lower source_preference
3450 # When throttling issue is fully fixed, remove this
3451 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3452
3453 info = {
3454 'id': video_id,
3455 'title': video_title,
3456 'formats': formats,
3457 'thumbnails': thumbnails,
3458 # The best thumbnail that we are sure exists. Prevents unnecessary
3459 # URL checking if user don't care about getting the best possible thumbnail
3460 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3461 'description': video_description,
3462 'uploader': get_first(video_details, 'author'),
3463 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3464 'uploader_url': owner_profile_url,
3465 'channel_id': channel_id,
3466 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3467 'duration': duration,
3468 'view_count': int_or_none(
3469 get_first((video_details, microformats), (..., 'viewCount'))
3470 or search_meta('interactionCount')),
3471 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3472 'age_limit': 18 if (
3473 get_first(microformats, 'isFamilySafe') is False
3474 or search_meta('isFamilyFriendly') == 'false'
3475 or search_meta('og:restrictions:age') == '18+') else 0,
3476 'webpage_url': webpage_url,
3477 'categories': [category] if category else None,
3478 'tags': keywords,
3479 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3480 'is_live': is_live,
3481 'was_live': (False if is_live or is_upcoming or live_content is False
3482 else None if is_live is None or is_upcoming is None
3483 else live_content),
3484 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3485 'release_timestamp': live_start_time,
3486 }
3487
3488 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3489 if pctr:
3490 def get_lang_code(track):
3491 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3492 or track.get('languageCode'))
3493
3494 # Converted into dicts to remove duplicates
3495 captions = {
3496 get_lang_code(sub): sub
3497 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3498 translation_languages = {
3499 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3500 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3501
3502 def process_language(container, base_url, lang_code, sub_name, query):
3503 lang_subs = container.setdefault(lang_code, [])
3504 for fmt in self._SUBTITLE_FORMATS:
3505 query.update({
3506 'fmt': fmt,
3507 })
3508 lang_subs.append({
3509 'ext': fmt,
3510 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3511 'name': sub_name,
3512 })
3513
3514 subtitles, automatic_captions = {}, {}
3515 for lang_code, caption_track in captions.items():
3516 base_url = caption_track.get('baseUrl')
3517 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3518 if not base_url:
3519 continue
3520 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3521 if caption_track.get('kind') != 'asr':
3522 if not lang_code:
3523 continue
3524 process_language(
3525 subtitles, base_url, lang_code, lang_name, {})
3526 if not caption_track.get('isTranslatable'):
3527 continue
3528 for trans_code, trans_name in translation_languages.items():
3529 if not trans_code:
3530 continue
3531 orig_trans_code = trans_code
3532 if caption_track.get('kind') != 'asr':
3533 if 'translated_subs' in self._configuration_arg('skip'):
3534 continue
3535 trans_code += f'-{lang_code}'
3536 trans_name += format_field(lang_name, template=' from %s')
3537 # Add an "-orig" label to the original language so that it can be distinguished.
3538 # The subs are returned without "-orig" as well for compatibility
3539 if lang_code == f'a-{orig_trans_code}':
3540 process_language(
3541 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3542 # Setting tlang=lang returns damaged subtitles.
3543 process_language(automatic_captions, base_url, trans_code, trans_name,
3544 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
3545 info['automatic_captions'] = automatic_captions
3546 info['subtitles'] = subtitles
3547
3548 parsed_url = compat_urllib_parse_urlparse(url)
3549 for component in [parsed_url.fragment, parsed_url.query]:
3550 query = compat_parse_qs(component)
3551 for k, v in query.items():
3552 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3553 d_k += '_time'
3554 if d_k not in info and k in s_ks:
3555 info[d_k] = parse_duration(query[k][0])
3556
3557 # Youtube Music Auto-generated description
3558 if video_description:
3559 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
3560 if mobj:
3561 release_year = mobj.group('release_year')
3562 release_date = mobj.group('release_date')
3563 if release_date:
3564 release_date = release_date.replace('-', '')
3565 if not release_year:
3566 release_year = release_date[:4]
3567 info.update({
3568 'album': mobj.group('album'.strip()),
3569 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3570 'track': mobj.group('track').strip(),
3571 'release_date': release_date,
3572 'release_year': int_or_none(release_year),
3573 })
3574
3575 initial_data = None
3576 if webpage:
3577 initial_data = self._extract_yt_initial_variable(
3578 webpage, self._YT_INITIAL_DATA_RE, video_id,
3579 'yt initial data')
3580 if not initial_data:
3581 query = {'videoId': video_id}
3582 query.update(self._get_checkok_params())
3583 initial_data = self._extract_response(
3584 item_id=video_id, ep='next', fatal=False,
3585 ytcfg=master_ytcfg, query=query,
3586 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3587 note='Downloading initial data API JSON')
3588
3589 try:
3590 # This will error if there is no livechat
3591 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3592 info.setdefault('subtitles', {})['live_chat'] = [{
3593 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3594 'video_id': video_id,
3595 'ext': 'json',
3596 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3597 }]
3598 except (KeyError, IndexError, TypeError):
3599 pass
3600
3601 if initial_data:
3602 info['chapters'] = (
3603 self._extract_chapters_from_json(initial_data, duration)
3604 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3605 or None)
3606
3607 contents = traverse_obj(
3608 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3609 expected_type=list, default=[])
3610
3611 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3612 if vpir:
3613 stl = vpir.get('superTitleLink')
3614 if stl:
3615 stl = self._get_text(stl)
3616 if try_get(
3617 vpir,
3618 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3619 info['location'] = stl
3620 else:
3621 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3622 if mobj:
3623 info.update({
3624 'series': mobj.group(1),
3625 'season_number': int(mobj.group(2)),
3626 'episode_number': int(mobj.group(3)),
3627 })
3628 for tlb in (try_get(
3629 vpir,
3630 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3631 list) or []):
3632 tbr = tlb.get('toggleButtonRenderer') or {}
3633 for getter, regex in [(
3634 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3635 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3636 lambda x: x['accessibility'],
3637 lambda x: x['accessibilityData']['accessibilityData'],
3638 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3639 label = (try_get(tbr, getter, dict) or {}).get('label')
3640 if label:
3641 mobj = re.match(regex, label)
3642 if mobj:
3643 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3644 break
3645 sbr_tooltip = try_get(
3646 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3647 if sbr_tooltip:
3648 like_count, dislike_count = sbr_tooltip.split(' / ')
3649 info.update({
3650 'like_count': str_to_int(like_count),
3651 'dislike_count': str_to_int(dislike_count),
3652 })
3653 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3654 if vsir:
3655 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3656 info.update({
3657 'channel': self._get_text(vor, 'title'),
3658 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3659
3660 rows = try_get(
3661 vsir,
3662 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3663 list) or []
3664 multiple_songs = False
3665 for row in rows:
3666 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3667 multiple_songs = True
3668 break
3669 for row in rows:
3670 mrr = row.get('metadataRowRenderer') or {}
3671 mrr_title = mrr.get('title')
3672 if not mrr_title:
3673 continue
3674 mrr_title = self._get_text(mrr, 'title')
3675 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3676 if mrr_title == 'License':
3677 info['license'] = mrr_contents_text
3678 elif not multiple_songs:
3679 if mrr_title == 'Album':
3680 info['album'] = mrr_contents_text
3681 elif mrr_title == 'Artist':
3682 info['artist'] = mrr_contents_text
3683 elif mrr_title == 'Song':
3684 info['track'] = mrr_contents_text
3685
3686 fallbacks = {
3687 'channel': 'uploader',
3688 'channel_id': 'uploader_id',
3689 'channel_url': 'uploader_url',
3690 }
3691
3692 # The upload date for scheduled, live and past live streams / premieres in microformats
3693 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3694 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3695 upload_date = (
3696 unified_strdate(get_first(microformats, 'uploadDate'))
3697 or unified_strdate(search_meta('uploadDate')))
3698 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3699 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3700 info['upload_date'] = upload_date
3701
3702 for to, frm in fallbacks.items():
3703 if not info.get(to):
3704 info[to] = info.get(frm)
3705
3706 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3707 v = info.get(s_k)
3708 if v:
3709 info[d_k] = v
3710
3711 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3712 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3713 is_membersonly = None
3714 is_premium = None
3715 if initial_data and is_private is not None:
3716 is_membersonly = False
3717 is_premium = False
3718 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3719 badge_labels = set()
3720 for content in contents:
3721 if not isinstance(content, dict):
3722 continue
3723 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3724 for badge_label in badge_labels:
3725 if badge_label.lower() == 'members only':
3726 is_membersonly = True
3727 elif badge_label.lower() == 'premium':
3728 is_premium = True
3729 elif badge_label.lower() == 'unlisted':
3730 is_unlisted = True
3731
3732 info['availability'] = self._availability(
3733 is_private=is_private,
3734 needs_premium=is_premium,
3735 needs_subscription=is_membersonly,
3736 needs_auth=info['age_limit'] >= 18,
3737 is_unlisted=None if is_private is None else is_unlisted)
3738
3739 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3740
3741 self.mark_watched(video_id, player_responses)
3742
3743 return info
3744
3745
3746class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3747
3748 @staticmethod
3749 def passthrough_smuggled_data(func):
3750 def _smuggle(entries, smuggled_data):
3751 for entry in entries:
3752 # TODO: Convert URL to music.youtube instead.
3753 # Do we need to passthrough any other smuggled_data?
3754 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3755 yield entry
3756
3757 @functools.wraps(func)
3758 def wrapper(self, url):
3759 url, smuggled_data = unsmuggle_url(url, {})
3760 if self.is_music_url(url):
3761 smuggled_data['is_music_url'] = True
3762 info_dict = func(self, url, smuggled_data)
3763 if smuggled_data and info_dict.get('entries'):
3764 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3765 return info_dict
3766 return wrapper
3767
3768 def _extract_channel_id(self, webpage):
3769 channel_id = self._html_search_meta(
3770 'channelId', webpage, 'channel id', default=None)
3771 if channel_id:
3772 return channel_id
3773 channel_url = self._html_search_meta(
3774 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3775 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3776 'twitter:app:url:googleplay'), webpage, 'channel url')
3777 return self._search_regex(
3778 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3779 channel_url, 'channel id')
3780
3781 @staticmethod
3782 def _extract_basic_item_renderer(item):
3783 # Modified from _extract_grid_item_renderer
3784 known_basic_renderers = (
3785 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3786 )
3787 for key, renderer in item.items():
3788 if not isinstance(renderer, dict):
3789 continue
3790 elif key in known_basic_renderers:
3791 return renderer
3792 elif key.startswith('grid') and key.endswith('Renderer'):
3793 return renderer
3794
3795 def _grid_entries(self, grid_renderer):
3796 for item in grid_renderer['items']:
3797 if not isinstance(item, dict):
3798 continue
3799 renderer = self._extract_basic_item_renderer(item)
3800 if not isinstance(renderer, dict):
3801 continue
3802 title = self._get_text(renderer, 'title')
3803
3804 # playlist
3805 playlist_id = renderer.get('playlistId')
3806 if playlist_id:
3807 yield self.url_result(
3808 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3809 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3810 video_title=title)
3811 continue
3812 # video
3813 video_id = renderer.get('videoId')
3814 if video_id:
3815 yield self._extract_video(renderer)
3816 continue
3817 # channel
3818 channel_id = renderer.get('channelId')
3819 if channel_id:
3820 yield self.url_result(
3821 'https://www.youtube.com/channel/%s' % channel_id,
3822 ie=YoutubeTabIE.ie_key(), video_title=title)
3823 continue
3824 # generic endpoint URL support
3825 ep_url = urljoin('https://www.youtube.com/', try_get(
3826 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3827 compat_str))
3828 if ep_url:
3829 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3830 if ie.suitable(ep_url):
3831 yield self.url_result(
3832 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3833 break
3834
3835 def _music_reponsive_list_entry(self, renderer):
3836 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3837 if video_id:
3838 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3839 ie=YoutubeIE.ie_key(), video_id=video_id)
3840 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3841 if playlist_id:
3842 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3843 if video_id:
3844 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3845 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3846 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3847 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3848 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3849 if browse_id:
3850 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3851 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3852
3853 def _shelf_entries_from_content(self, shelf_renderer):
3854 content = shelf_renderer.get('content')
3855 if not isinstance(content, dict):
3856 return
3857 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3858 if renderer:
3859 # TODO: add support for nested playlists so each shelf is processed
3860 # as separate playlist
3861 # TODO: this includes only first N items
3862 for entry in self._grid_entries(renderer):
3863 yield entry
3864 renderer = content.get('horizontalListRenderer')
3865 if renderer:
3866 # TODO
3867 pass
3868
3869 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3870 ep = try_get(
3871 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3872 compat_str)
3873 shelf_url = urljoin('https://www.youtube.com', ep)
3874 if shelf_url:
3875 # Skipping links to another channels, note that checking for
3876 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3877 # will not work
3878 if skip_channels and '/channels?' in shelf_url:
3879 return
3880 title = self._get_text(shelf_renderer, 'title')
3881 yield self.url_result(shelf_url, video_title=title)
3882 # Shelf may not contain shelf URL, fallback to extraction from content
3883 for entry in self._shelf_entries_from_content(shelf_renderer):
3884 yield entry
3885
3886 def _playlist_entries(self, video_list_renderer):
3887 for content in video_list_renderer['contents']:
3888 if not isinstance(content, dict):
3889 continue
3890 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3891 if not isinstance(renderer, dict):
3892 continue
3893 video_id = renderer.get('videoId')
3894 if not video_id:
3895 continue
3896 yield self._extract_video(renderer)
3897
3898 def _rich_entries(self, rich_grid_renderer):
3899 renderer = try_get(
3900 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3901 video_id = renderer.get('videoId')
3902 if not video_id:
3903 return
3904 yield self._extract_video(renderer)
3905
3906 def _video_entry(self, video_renderer):
3907 video_id = video_renderer.get('videoId')
3908 if video_id:
3909 return self._extract_video(video_renderer)
3910
3911 def _hashtag_tile_entry(self, hashtag_tile_renderer):
3912 url = urljoin('https://youtube.com', traverse_obj(
3913 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
3914 if url:
3915 return self.url_result(
3916 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
3917
3918 def _post_thread_entries(self, post_thread_renderer):
3919 post_renderer = try_get(
3920 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3921 if not post_renderer:
3922 return
3923 # video attachment
3924 video_renderer = try_get(
3925 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3926 video_id = video_renderer.get('videoId')
3927 if video_id:
3928 entry = self._extract_video(video_renderer)
3929 if entry:
3930 yield entry
3931 # playlist attachment
3932 playlist_id = try_get(
3933 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3934 if playlist_id:
3935 yield self.url_result(
3936 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3937 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3938 # inline video links
3939 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3940 for run in runs:
3941 if not isinstance(run, dict):
3942 continue
3943 ep_url = try_get(
3944 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3945 if not ep_url:
3946 continue
3947 if not YoutubeIE.suitable(ep_url):
3948 continue
3949 ep_video_id = YoutubeIE._match_id(ep_url)
3950 if video_id == ep_video_id:
3951 continue
3952 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3953
3954 def _post_thread_continuation_entries(self, post_thread_continuation):
3955 contents = post_thread_continuation.get('contents')
3956 if not isinstance(contents, list):
3957 return
3958 for content in contents:
3959 renderer = content.get('backstagePostThreadRenderer')
3960 if not isinstance(renderer, dict):
3961 continue
3962 for entry in self._post_thread_entries(renderer):
3963 yield entry
3964
3965 r''' # unused
3966 def _rich_grid_entries(self, contents):
3967 for content in contents:
3968 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3969 if video_renderer:
3970 entry = self._video_entry(video_renderer)
3971 if entry:
3972 yield entry
3973 '''
3974
3975 def _extract_entries(self, parent_renderer, continuation_list):
3976 # continuation_list is modified in-place with continuation_list = [continuation_token]
3977 continuation_list[:] = [None]
3978 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3979 for content in contents:
3980 if not isinstance(content, dict):
3981 continue
3982 is_renderer = traverse_obj(
3983 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3984 expected_type=dict)
3985 if not is_renderer:
3986 renderer = content.get('richItemRenderer')
3987 if renderer:
3988 for entry in self._rich_entries(renderer):
3989 yield entry
3990 continuation_list[0] = self._extract_continuation(parent_renderer)
3991 continue
3992 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3993 for isr_content in isr_contents:
3994 if not isinstance(isr_content, dict):
3995 continue
3996
3997 known_renderers = {
3998 'playlistVideoListRenderer': self._playlist_entries,
3999 'gridRenderer': self._grid_entries,
4000 'reelShelfRenderer': self._grid_entries,
4001 'shelfRenderer': self._shelf_entries,
4002 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4003 'backstagePostThreadRenderer': self._post_thread_entries,
4004 'videoRenderer': lambda x: [self._video_entry(x)],
4005 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4006 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4007 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4008 }
4009 for key, renderer in isr_content.items():
4010 if key not in known_renderers:
4011 continue
4012 for entry in known_renderers[key](renderer):
4013 if entry:
4014 yield entry
4015 continuation_list[0] = self._extract_continuation(renderer)
4016 break
4017
4018 if not continuation_list[0]:
4019 continuation_list[0] = self._extract_continuation(is_renderer)
4020
4021 if not continuation_list[0]:
4022 continuation_list[0] = self._extract_continuation(parent_renderer)
4023
4024 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4025 continuation_list = [None]
4026 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4027 tab_content = try_get(tab, lambda x: x['content'], dict)
4028 if not tab_content:
4029 return
4030 parent_renderer = (
4031 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4032 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4033 for entry in extract_entries(parent_renderer):
4034 yield entry
4035 continuation = continuation_list[0]
4036
4037 for page_num in itertools.count(1):
4038 if not continuation:
4039 break
4040 headers = self.generate_api_headers(
4041 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4042 response = self._extract_response(
4043 item_id='%s page %s' % (item_id, page_num),
4044 query=continuation, headers=headers, ytcfg=ytcfg,
4045 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4046
4047 if not response:
4048 break
4049 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4050 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4051 visitor_data = self._extract_visitor_data(response) or visitor_data
4052
4053 known_continuation_renderers = {
4054 'playlistVideoListContinuation': self._playlist_entries,
4055 'gridContinuation': self._grid_entries,
4056 'itemSectionContinuation': self._post_thread_continuation_entries,
4057 'sectionListContinuation': extract_entries, # for feeds
4058 }
4059 continuation_contents = try_get(
4060 response, lambda x: x['continuationContents'], dict) or {}
4061 continuation_renderer = None
4062 for key, value in continuation_contents.items():
4063 if key not in known_continuation_renderers:
4064 continue
4065 continuation_renderer = value
4066 continuation_list = [None]
4067 for entry in known_continuation_renderers[key](continuation_renderer):
4068 yield entry
4069 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4070 break
4071 if continuation_renderer:
4072 continue
4073
4074 known_renderers = {
4075 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4076 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4077 'gridVideoRenderer': (self._grid_entries, 'items'),
4078 'gridChannelRenderer': (self._grid_entries, 'items'),
4079 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4080 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4081 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4082 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
4083 }
4084 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4085 continuation_items = try_get(
4086 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
4087 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4088 video_items_renderer = None
4089 for key, value in continuation_item.items():
4090 if key not in known_renderers:
4091 continue
4092 video_items_renderer = {known_renderers[key][1]: continuation_items}
4093 continuation_list = [None]
4094 for entry in known_renderers[key][0](video_items_renderer):
4095 yield entry
4096 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4097 break
4098 if video_items_renderer:
4099 continue
4100 break
4101
4102 @staticmethod
4103 def _extract_selected_tab(tabs, fatal=True):
4104 for tab in tabs:
4105 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4106 if renderer.get('selected') is True:
4107 return renderer
4108 else:
4109 if fatal:
4110 raise ExtractorError('Unable to find selected tab')
4111
4112 def _extract_uploader(self, data):
4113 uploader = {}
4114 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4115 owner = try_get(
4116 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4117 if owner:
4118 owner_text = owner.get('text')
4119 uploader['uploader'] = self._search_regex(
4120 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
4121 uploader['uploader_id'] = try_get(
4122 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4123 uploader['uploader_url'] = urljoin(
4124 'https://www.youtube.com/',
4125 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
4126 return {k: v for k, v in uploader.items() if v is not None}
4127
4128 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4129 playlist_id = title = description = channel_url = channel_name = channel_id = None
4130 tags = []
4131
4132 selected_tab = self._extract_selected_tab(tabs)
4133 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4134 renderer = try_get(
4135 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4136 if renderer:
4137 channel_name = renderer.get('title')
4138 channel_url = renderer.get('channelUrl')
4139 channel_id = renderer.get('externalId')
4140 else:
4141 renderer = try_get(
4142 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
4143
4144 if renderer:
4145 title = renderer.get('title')
4146 description = renderer.get('description', '')
4147 playlist_id = channel_id
4148 tags = renderer.get('keywords', '').split()
4149
4150 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4151 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4152 def _get_uncropped(url):
4153 return url_or_none((url or '').split('=')[0] + '=s0')
4154
4155 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4156 if avatar_thumbnails:
4157 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4158 if uncropped_avatar:
4159 avatar_thumbnails.append({
4160 'url': uncropped_avatar,
4161 'id': 'avatar_uncropped',
4162 'preference': 1
4163 })
4164
4165 channel_banners = self._extract_thumbnails(
4166 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4167 for banner in channel_banners:
4168 banner['preference'] = -10
4169
4170 if channel_banners:
4171 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4172 if uncropped_banner:
4173 channel_banners.append({
4174 'url': uncropped_banner,
4175 'id': 'banner_uncropped',
4176 'preference': -5
4177 })
4178
4179 primary_thumbnails = self._extract_thumbnails(
4180 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4181
4182 if playlist_id is None:
4183 playlist_id = item_id
4184
4185 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4186 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
4187 if title is None:
4188 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4189 title += format_field(selected_tab, 'title', ' - %s')
4190 title += format_field(selected_tab, 'expandedText', ' - %s')
4191
4192 metadata = {
4193 'playlist_id': playlist_id,
4194 'playlist_title': title,
4195 'playlist_description': description,
4196 'uploader': channel_name,
4197 'uploader_id': channel_id,
4198 'uploader_url': channel_url,
4199 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4200 'tags': tags,
4201 'view_count': self._get_count(playlist_stats, 1),
4202 'availability': self._extract_availability(data),
4203 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4204 'playlist_count': self._get_count(playlist_stats, 0),
4205 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4206 }
4207 if not channel_id:
4208 metadata.update(self._extract_uploader(data))
4209 metadata.update({
4210 'channel': metadata['uploader'],
4211 'channel_id': metadata['uploader_id'],
4212 'channel_url': metadata['uploader_url']})
4213 return self.playlist_result(
4214 self._entries(
4215 selected_tab, playlist_id, ytcfg,
4216 self._extract_account_syncid(ytcfg, data),
4217 self._extract_visitor_data(data, ytcfg)),
4218 **metadata)
4219
4220 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4221 first_id = last_id = response = None
4222 for page_num in itertools.count(1):
4223 videos = list(self._playlist_entries(playlist))
4224 if not videos:
4225 return
4226 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4227 if start >= len(videos):
4228 return
4229 for video in videos[start:]:
4230 if video['id'] == first_id:
4231 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4232 return
4233 yield video
4234 first_id = first_id or videos[0]['id']
4235 last_id = videos[-1]['id']
4236 watch_endpoint = try_get(
4237 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4238 headers = self.generate_api_headers(
4239 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4240 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4241 query = {
4242 'playlistId': playlist_id,
4243 'videoId': watch_endpoint.get('videoId') or last_id,
4244 'index': watch_endpoint.get('index') or len(videos),
4245 'params': watch_endpoint.get('params') or 'OAE%3D'
4246 }
4247 response = self._extract_response(
4248 item_id='%s page %d' % (playlist_id, page_num),
4249 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4250 check_get_keys='contents'
4251 )
4252 playlist = try_get(
4253 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4254
4255 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4256 title = playlist.get('title') or try_get(
4257 data, lambda x: x['titleText']['simpleText'], compat_str)
4258 playlist_id = playlist.get('playlistId') or item_id
4259
4260 # Delegating everything except mix playlists to regular tab-based playlist URL
4261 playlist_url = urljoin(url, try_get(
4262 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4263 compat_str))
4264 if playlist_url and playlist_url != url:
4265 return self.url_result(
4266 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4267 video_title=title)
4268
4269 return self.playlist_result(
4270 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4271 playlist_id=playlist_id, playlist_title=title)
4272
4273 def _extract_availability(self, data):
4274 """
4275 Gets the availability of a given playlist/tab.
4276 Note: Unless YouTube tells us explicitly, we do not assume it is public
4277 @param data: response
4278 """
4279 is_private = is_unlisted = None
4280 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4281 badge_labels = self._extract_badges(renderer)
4282
4283 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4284 privacy_dropdown_entries = try_get(
4285 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4286 for renderer_dict in privacy_dropdown_entries:
4287 is_selected = try_get(
4288 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4289 if not is_selected:
4290 continue
4291 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4292 if label:
4293 badge_labels.add(label.lower())
4294 break
4295
4296 for badge_label in badge_labels:
4297 if badge_label == 'unlisted':
4298 is_unlisted = True
4299 elif badge_label == 'private':
4300 is_private = True
4301 elif badge_label == 'public':
4302 is_unlisted = is_private = False
4303 return self._availability(is_private, False, False, False, is_unlisted)
4304
4305 @staticmethod
4306 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4307 sidebar_renderer = try_get(
4308 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4309 for item in sidebar_renderer:
4310 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4311 if renderer:
4312 return renderer
4313
4314 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4315 """
4316 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4317 """
4318 browse_id = params = None
4319 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4320 if not renderer:
4321 return
4322 menu_renderer = try_get(
4323 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4324 for menu_item in menu_renderer:
4325 if not isinstance(menu_item, dict):
4326 continue
4327 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4328 text = try_get(
4329 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4330 if not text or text.lower() != 'show unavailable videos':
4331 continue
4332 browse_endpoint = try_get(
4333 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4334 browse_id = browse_endpoint.get('browseId')
4335 params = browse_endpoint.get('params')
4336 break
4337
4338 headers = self.generate_api_headers(
4339 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4340 visitor_data=self._extract_visitor_data(data, ytcfg))
4341 query = {
4342 'params': params or 'wgYCCAA=',
4343 'browseId': browse_id or 'VL%s' % item_id
4344 }
4345 return self._extract_response(
4346 item_id=item_id, headers=headers, query=query,
4347 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4348 note='Downloading API JSON with unavailable videos')
4349
4350 def _extract_webpage(self, url, item_id, fatal=True):
4351 retries = self.get_param('extractor_retries', 3)
4352 count = -1
4353 webpage = data = last_error = None
4354 while count < retries:
4355 count += 1
4356 # Sometimes youtube returns a webpage with incomplete ytInitialData
4357 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4358 if last_error:
4359 self.report_warning('%s. Retrying ...' % last_error)
4360 try:
4361 webpage = self._download_webpage(
4362 url, item_id,
4363 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4364 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4365 except ExtractorError as e:
4366 if isinstance(e.cause, network_exceptions):
4367 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4368 last_error = error_to_compat_str(e.cause or e.msg)
4369 if count < retries:
4370 continue
4371 if fatal:
4372 raise
4373 self.report_warning(error_to_compat_str(e))
4374 break
4375 else:
4376 try:
4377 self._extract_and_report_alerts(data)
4378 except ExtractorError as e:
4379 if fatal:
4380 raise
4381 self.report_warning(error_to_compat_str(e))
4382 break
4383
4384 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4385 break
4386
4387 last_error = 'Incomplete yt initial data received'
4388 if count >= retries:
4389 if fatal:
4390 raise ExtractorError(last_error)
4391 self.report_warning(last_error)
4392 break
4393
4394 return webpage, data
4395
4396 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4397 data = None
4398 if 'webpage' not in self._configuration_arg('skip'):
4399 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4400 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4401 # Reject webpage data if redirected to home page without explicitly requesting
4402 selected_tab = self._extract_selected_tab(traverse_obj(
4403 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4404 if (url != 'https://www.youtube.com/feed/recommended'
4405 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4406 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4407 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4408 if fatal:
4409 raise ExtractorError(msg, expected=True)
4410 self.report_warning(msg, only_once=True)
4411 if not data:
4412 if not ytcfg and self.is_authenticated:
4413 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4414 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4415 raise ExtractorError(
4416 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4417 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4418 expected=True)
4419 self.report_warning(msg, only_once=True)
4420 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4421 return data, ytcfg
4422
4423 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4424 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4425 resolve_response = self._extract_response(
4426 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4427 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4428 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4429 for ep_key, ep in endpoints.items():
4430 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4431 if params:
4432 return self._extract_response(
4433 item_id=item_id, query=params, ep=ep, headers=headers,
4434 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4435 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4436 err_note = 'Failed to resolve url (does the playlist exist?)'
4437 if fatal:
4438 raise ExtractorError(err_note, expected=True)
4439 self.report_warning(err_note, item_id)
4440
4441 _SEARCH_PARAMS = None
4442
4443 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4444 data = {'query': query}
4445 if params is NO_DEFAULT:
4446 params = self._SEARCH_PARAMS
4447 if params:
4448 data['params'] = params
4449
4450 content_keys = (
4451 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4452 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4453 # ytmusic search
4454 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4455 ('continuationContents', ),
4456 )
4457 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4458
4459 continuation_list = [None]
4460 for page_num in itertools.count(1):
4461 data.update(continuation_list[0] or {})
4462 search = self._extract_response(
4463 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4464 default_client=default_client, check_get_keys=check_get_keys)
4465 slr_contents = traverse_obj(search, *content_keys)
4466 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4467 if not continuation_list[0]:
4468 break
4469
4470
4471class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4472 IE_DESC = 'YouTube Tabs'
4473 _VALID_URL = r'''(?x:
4474 https?://
4475 (?:\w+\.)?
4476 (?:
4477 youtube(?:kids)?\.com|
4478 %(invidious)s
4479 )/
4480 (?:
4481 (?P<channel_type>channel|c|user|browse)/|
4482 (?P<not_channel>
4483 feed/|hashtag/|
4484 (?:playlist|watch)\?.*?\blist=
4485 )|
4486 (?!(?:%(reserved_names)s)\b) # Direct URLs
4487 )
4488 (?P<id>[^/?\#&]+)
4489 )''' % {
4490 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4491 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4492 }
4493 IE_NAME = 'youtube:tab'
4494
4495 _TESTS = [{
4496 'note': 'playlists, multipage',
4497 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4498 'playlist_mincount': 94,
4499 'info_dict': {
4500 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4501 'title': 'Igor Kleiner - Playlists',
4502 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4503 'uploader': 'Igor Kleiner',
4504 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4505 'channel': 'Igor Kleiner',
4506 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4507 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4508 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4509 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4510 'channel_follower_count': int
4511 },
4512 }, {
4513 'note': 'playlists, multipage, different order',
4514 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4515 'playlist_mincount': 94,
4516 'info_dict': {
4517 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4518 'title': 'Igor Kleiner - Playlists',
4519 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4520 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4521 'uploader': 'Igor Kleiner',
4522 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4523 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4524 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4525 'channel': 'Igor Kleiner',
4526 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4527 'channel_follower_count': int
4528 },
4529 }, {
4530 'note': 'playlists, series',
4531 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4532 'playlist_mincount': 5,
4533 'info_dict': {
4534 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4535 'title': '3Blue1Brown - Playlists',
4536 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4537 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4538 'uploader': '3Blue1Brown',
4539 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4540 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4541 'channel': '3Blue1Brown',
4542 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4543 'tags': ['Mathematics'],
4544 'channel_follower_count': int
4545 },
4546 }, {
4547 'note': 'playlists, singlepage',
4548 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4549 'playlist_mincount': 4,
4550 'info_dict': {
4551 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4552 'title': 'ThirstForScience - Playlists',
4553 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4554 'uploader': 'ThirstForScience',
4555 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4556 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4557 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4558 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4559 'tags': 'count:13',
4560 'channel': 'ThirstForScience',
4561 'channel_follower_count': int
4562 }
4563 }, {
4564 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4565 'only_matching': True,
4566 }, {
4567 'note': 'basic, single video playlist',
4568 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4569 'info_dict': {
4570 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4571 'uploader': 'Sergey M.',
4572 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4573 'title': 'youtube-dl public playlist',
4574 'description': '',
4575 'tags': [],
4576 'view_count': int,
4577 'modified_date': '20201130',
4578 'channel': 'Sergey M.',
4579 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4580 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4581 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4582 },
4583 'playlist_count': 1,
4584 }, {
4585 'note': 'empty playlist',
4586 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4587 'info_dict': {
4588 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4589 'uploader': 'Sergey M.',
4590 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4591 'title': 'youtube-dl empty playlist',
4592 'tags': [],
4593 'channel': 'Sergey M.',
4594 'description': '',
4595 'modified_date': '20160902',
4596 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4597 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4598 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4599 },
4600 'playlist_count': 0,
4601 }, {
4602 'note': 'Home tab',
4603 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4604 'info_dict': {
4605 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4606 'title': 'lex will - Home',
4607 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4608 'uploader': 'lex will',
4609 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4610 'channel': 'lex will',
4611 'tags': ['bible', 'history', 'prophesy'],
4612 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4613 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4614 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4615 'channel_follower_count': int
4616 },
4617 'playlist_mincount': 2,
4618 }, {
4619 'note': 'Videos tab',
4620 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4621 'info_dict': {
4622 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4623 'title': 'lex will - Videos',
4624 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4625 'uploader': 'lex will',
4626 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4627 'tags': ['bible', 'history', 'prophesy'],
4628 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4629 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4630 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4631 'channel': 'lex will',
4632 'channel_follower_count': int
4633 },
4634 'playlist_mincount': 975,
4635 }, {
4636 'note': 'Videos tab, sorted by popular',
4637 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4638 'info_dict': {
4639 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4640 'title': 'lex will - Videos',
4641 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4642 'uploader': 'lex will',
4643 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4644 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4645 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4646 'channel': 'lex will',
4647 'tags': ['bible', 'history', 'prophesy'],
4648 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4649 'channel_follower_count': int
4650 },
4651 'playlist_mincount': 199,
4652 }, {
4653 'note': 'Playlists tab',
4654 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4655 'info_dict': {
4656 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4657 'title': 'lex will - Playlists',
4658 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4659 'uploader': 'lex will',
4660 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4661 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4662 'channel': 'lex will',
4663 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4664 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4665 'tags': ['bible', 'history', 'prophesy'],
4666 'channel_follower_count': int
4667 },
4668 'playlist_mincount': 17,
4669 }, {
4670 'note': 'Community tab',
4671 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4672 'info_dict': {
4673 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4674 'title': 'lex will - Community',
4675 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4676 'uploader': 'lex will',
4677 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4678 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4679 'channel': 'lex will',
4680 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4681 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4682 'tags': ['bible', 'history', 'prophesy'],
4683 'channel_follower_count': int
4684 },
4685 'playlist_mincount': 18,
4686 }, {
4687 'note': 'Channels tab',
4688 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4689 'info_dict': {
4690 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4691 'title': 'lex will - Channels',
4692 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4693 'uploader': 'lex will',
4694 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4695 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4696 'channel': 'lex will',
4697 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4698 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4699 'tags': ['bible', 'history', 'prophesy'],
4700 'channel_follower_count': int
4701 },
4702 'playlist_mincount': 12,
4703 }, {
4704 'note': 'Search tab',
4705 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4706 'playlist_mincount': 40,
4707 'info_dict': {
4708 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4709 'title': '3Blue1Brown - Search - linear algebra',
4710 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4711 'uploader': '3Blue1Brown',
4712 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4713 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4714 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4715 'tags': ['Mathematics'],
4716 'channel': '3Blue1Brown',
4717 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4718 'channel_follower_count': int
4719 },
4720 }, {
4721 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4722 'only_matching': True,
4723 }, {
4724 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4725 'only_matching': True,
4726 }, {
4727 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4728 'only_matching': True,
4729 }, {
4730 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4731 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4732 'info_dict': {
4733 'title': '29C3: Not my department',
4734 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4735 'uploader': 'Christiaan008',
4736 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4737 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4738 'tags': [],
4739 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4740 'view_count': int,
4741 'modified_date': '20150605',
4742 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4743 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4744 'channel': 'Christiaan008',
4745 },
4746 'playlist_count': 96,
4747 }, {
4748 'note': 'Large playlist',
4749 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4750 'info_dict': {
4751 'title': 'Uploads from Cauchemar',
4752 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4753 'uploader': 'Cauchemar',
4754 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4755 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4756 'tags': [],
4757 'modified_date': r're:\d{8}',
4758 'channel': 'Cauchemar',
4759 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4760 'view_count': int,
4761 'description': '',
4762 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4763 },
4764 'playlist_mincount': 1123,
4765 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4766 }, {
4767 'note': 'even larger playlist, 8832 videos',
4768 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4769 'only_matching': True,
4770 }, {
4771 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4772 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4773 'info_dict': {
4774 'title': 'Uploads from Interstellar Movie',
4775 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4776 'uploader': 'Interstellar Movie',
4777 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4778 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4779 'tags': [],
4780 'view_count': int,
4781 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4782 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4783 'channel': 'Interstellar Movie',
4784 'description': '',
4785 'modified_date': r're:\d{8}',
4786 },
4787 'playlist_mincount': 21,
4788 }, {
4789 'note': 'Playlist with "show unavailable videos" button',
4790 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4791 'info_dict': {
4792 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4793 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4794 'uploader': 'Phim Siêu Nhân Nhật Bản',
4795 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4796 'view_count': int,
4797 'channel': 'Phim Siêu Nhân Nhật Bản',
4798 'tags': [],
4799 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4800 'description': '',
4801 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4802 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4803 'modified_date': r're:\d{8}',
4804 },
4805 'playlist_mincount': 200,
4806 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4807 }, {
4808 'note': 'Playlist with unavailable videos in page 7',
4809 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4810 'info_dict': {
4811 'title': 'Uploads from BlankTV',
4812 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4813 'uploader': 'BlankTV',
4814 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4815 'channel': 'BlankTV',
4816 'channel_url': 'https://www.youtube.com/c/blanktv',
4817 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4818 'view_count': int,
4819 'tags': [],
4820 'uploader_url': 'https://www.youtube.com/c/blanktv',
4821 'modified_date': r're:\d{8}',
4822 'description': '',
4823 },
4824 'playlist_mincount': 1000,
4825 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4826 }, {
4827 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4828 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4829 'info_dict': {
4830 'title': 'Data Analysis with Dr Mike Pound',
4831 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4832 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4833 'uploader': 'Computerphile',
4834 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4835 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4836 'tags': [],
4837 'view_count': int,
4838 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4839 'channel_url': 'https://www.youtube.com/user/Computerphile',
4840 'channel': 'Computerphile',
4841 },
4842 'playlist_mincount': 11,
4843 }, {
4844 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4845 'only_matching': True,
4846 }, {
4847 'note': 'Playlist URL that does not actually serve a playlist',
4848 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4849 'info_dict': {
4850 'id': 'FqZTN594JQw',
4851 'ext': 'webm',
4852 'title': "Smiley's People 01 detective, Adventure Series, Action",
4853 'uploader': 'STREEM',
4854 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4855 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4856 'upload_date': '20150526',
4857 'license': 'Standard YouTube License',
4858 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4859 'categories': ['People & Blogs'],
4860 'tags': list,
4861 'view_count': int,
4862 'like_count': int,
4863 },
4864 'params': {
4865 'skip_download': True,
4866 },
4867 'skip': 'This video is not available.',
4868 'add_ie': [YoutubeIE.ie_key()],
4869 }, {
4870 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4871 'only_matching': True,
4872 }, {
4873 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4874 'only_matching': True,
4875 }, {
4876 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4877 'info_dict': {
4878 'id': 'GgL890LIznQ', # This will keep changing
4879 'ext': 'mp4',
4880 'title': str,
4881 'uploader': 'Sky News',
4882 'uploader_id': 'skynews',
4883 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4884 'upload_date': r're:\d{8}',
4885 'description': str,
4886 'categories': ['News & Politics'],
4887 'tags': list,
4888 'like_count': int,
4889 'release_timestamp': 1642502819,
4890 'channel': 'Sky News',
4891 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4892 'age_limit': 0,
4893 'view_count': int,
4894 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4895 'playable_in_embed': True,
4896 'release_date': '20220118',
4897 'availability': 'public',
4898 'live_status': 'is_live',
4899 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4900 'channel_follower_count': int
4901 },
4902 'params': {
4903 'skip_download': True,
4904 },
4905 'expected_warnings': ['Ignoring subtitle tracks found in '],
4906 }, {
4907 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4908 'info_dict': {
4909 'id': 'a48o2S1cPoo',
4910 'ext': 'mp4',
4911 'title': 'The Young Turks - Live Main Show',
4912 'uploader': 'The Young Turks',
4913 'uploader_id': 'TheYoungTurks',
4914 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4915 'upload_date': '20150715',
4916 'license': 'Standard YouTube License',
4917 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4918 'categories': ['News & Politics'],
4919 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4920 'like_count': int,
4921 },
4922 'params': {
4923 'skip_download': True,
4924 },
4925 'only_matching': True,
4926 }, {
4927 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4928 'only_matching': True,
4929 }, {
4930 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4931 'only_matching': True,
4932 }, {
4933 'note': 'A channel that is not live. Should raise error',
4934 'url': 'https://www.youtube.com/user/numberphile/live',
4935 'only_matching': True,
4936 }, {
4937 'url': 'https://www.youtube.com/feed/trending',
4938 'only_matching': True,
4939 }, {
4940 'url': 'https://www.youtube.com/feed/library',
4941 'only_matching': True,
4942 }, {
4943 'url': 'https://www.youtube.com/feed/history',
4944 'only_matching': True,
4945 }, {
4946 'url': 'https://www.youtube.com/feed/subscriptions',
4947 'only_matching': True,
4948 }, {
4949 'url': 'https://www.youtube.com/feed/watch_later',
4950 'only_matching': True,
4951 }, {
4952 'note': 'Recommended - redirects to home page.',
4953 'url': 'https://www.youtube.com/feed/recommended',
4954 'only_matching': True,
4955 }, {
4956 'note': 'inline playlist with not always working continuations',
4957 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4958 'only_matching': True,
4959 }, {
4960 'url': 'https://www.youtube.com/course',
4961 'only_matching': True,
4962 }, {
4963 'url': 'https://www.youtube.com/zsecurity',
4964 'only_matching': True,
4965 }, {
4966 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4967 'only_matching': True,
4968 }, {
4969 'url': 'https://www.youtube.com/TheYoungTurks/live',
4970 'only_matching': True,
4971 }, {
4972 'url': 'https://www.youtube.com/hashtag/cctv9',
4973 'info_dict': {
4974 'id': 'cctv9',
4975 'title': '#cctv9',
4976 'tags': [],
4977 },
4978 'playlist_mincount': 350,
4979 }, {
4980 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4981 'only_matching': True,
4982 }, {
4983 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4984 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4985 'only_matching': True
4986 }, {
4987 'note': '/browse/ should redirect to /channel/',
4988 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4989 'only_matching': True
4990 }, {
4991 'note': 'VLPL, should redirect to playlist?list=PL...',
4992 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4993 'info_dict': {
4994 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4995 'uploader': 'NoCopyrightSounds',
4996 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4997 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4998 'title': 'NCS Releases',
4999 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5000 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5001 'modified_date': r're:\d{8}',
5002 'view_count': int,
5003 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5004 'tags': [],
5005 'channel': 'NoCopyrightSounds',
5006 },
5007 'playlist_mincount': 166,
5008 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5009 }, {
5010 'note': 'Topic, should redirect to playlist?list=UU...',
5011 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5012 'info_dict': {
5013 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5014 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5015 'title': 'Uploads from Royalty Free Music - Topic',
5016 'uploader': 'Royalty Free Music - Topic',
5017 'tags': [],
5018 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5019 'channel': 'Royalty Free Music - Topic',
5020 'view_count': int,
5021 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5022 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5023 'modified_date': r're:\d{8}',
5024 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5025 'description': '',
5026 },
5027 'expected_warnings': [
5028 'The URL does not have a videos tab',
5029 r'[Uu]navailable videos (are|will be) hidden',
5030 ],
5031 'playlist_mincount': 101,
5032 }, {
5033 'note': 'Topic without a UU playlist',
5034 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5035 'info_dict': {
5036 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5037 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5038 'tags': [],
5039 },
5040 'expected_warnings': [
5041 'the playlist redirect gave error',
5042 ],
5043 'playlist_mincount': 9,
5044 }, {
5045 'note': 'Youtube music Album',
5046 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5047 'info_dict': {
5048 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5049 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5050 'tags': [],
5051 'view_count': int,
5052 'description': '',
5053 'availability': 'unlisted',
5054 'modified_date': r're:\d{8}',
5055 },
5056 'playlist_count': 50,
5057 }, {
5058 'note': 'unlisted single video playlist',
5059 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5060 'info_dict': {
5061 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5062 'uploader': 'colethedj',
5063 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5064 'title': 'yt-dlp unlisted playlist test',
5065 'availability': 'unlisted',
5066 'tags': [],
5067 'modified_date': '20211208',
5068 'channel': 'colethedj',
5069 'view_count': int,
5070 'description': '',
5071 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5072 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5073 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5074 },
5075 'playlist_count': 1,
5076 }, {
5077 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5078 'url': 'https://www.youtube.com/feed/recommended',
5079 'info_dict': {
5080 'id': 'recommended',
5081 'title': 'recommended',
5082 'tags': [],
5083 },
5084 'playlist_mincount': 50,
5085 'params': {
5086 'skip_download': True,
5087 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5088 },
5089 }, {
5090 'note': 'API Fallback: /videos tab, sorted by oldest first',
5091 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5092 'info_dict': {
5093 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5094 'title': 'Cody\'sLab - Videos',
5095 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5096 'uploader': 'Cody\'sLab',
5097 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5098 'channel': 'Cody\'sLab',
5099 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5100 'tags': [],
5101 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5102 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5103 'channel_follower_count': int
5104 },
5105 'playlist_mincount': 650,
5106 'params': {
5107 'skip_download': True,
5108 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5109 },
5110 }, {
5111 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5112 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5113 'info_dict': {
5114 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5115 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5116 'title': 'Uploads from Royalty Free Music - Topic',
5117 'uploader': 'Royalty Free Music - Topic',
5118 'modified_date': r're:\d{8}',
5119 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5120 'description': '',
5121 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5122 'tags': [],
5123 'channel': 'Royalty Free Music - Topic',
5124 'view_count': int,
5125 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5126 },
5127 'expected_warnings': [
5128 'does not have a videos tab',
5129 r'[Uu]navailable videos (are|will be) hidden',
5130 ],
5131 'playlist_mincount': 101,
5132 'params': {
5133 'skip_download': True,
5134 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5135 },
5136 }, {
5137 'note': 'non-standard redirect to regional channel',
5138 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5139 'only_matching': True
5140 }, {
5141 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5142 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5143 'info_dict': {
5144 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5145 'modified_date': '20220407',
5146 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5147 'tags': [],
5148 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5149 'uploader': 'pukkandan',
5150 'availability': 'unlisted',
5151 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5152 'channel': 'pukkandan',
5153 'description': 'Test for collaborative playlist',
5154 'title': 'yt-dlp test - collaborative playlist',
5155 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5156 },
5157 'playlist_mincount': 2
5158 }]
5159
5160 @classmethod
5161 def suitable(cls, url):
5162 return False if YoutubeIE.suitable(url) else super(
5163 YoutubeTabIE, cls).suitable(url)
5164
5165 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5166
5167 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5168 def _real_extract(self, url, smuggled_data):
5169 item_id = self._match_id(url)
5170 url = compat_urlparse.urlunparse(
5171 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
5172 compat_opts = self.get_param('compat_opts', [])
5173
5174 def get_mobj(url):
5175 mobj = self._URL_RE.match(url).groupdict()
5176 mobj.update((k, '') for k, v in mobj.items() if v is None)
5177 return mobj
5178
5179 mobj, redirect_warning = get_mobj(url), None
5180 # Youtube returns incomplete data if tabname is not lower case
5181 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5182 if is_channel:
5183 if smuggled_data.get('is_music_url'):
5184 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5185 item_id = item_id[2:]
5186 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5187 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5188 mdata = self._extract_tab_endpoint(
5189 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5190 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5191 get_all=False, expected_type=compat_str)
5192 if not murl:
5193 raise ExtractorError('Failed to resolve album to playlist')
5194 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5195 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5196 pre = f'https://www.youtube.com/channel/{item_id}'
5197
5198 original_tab_name = tab
5199 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5200 # Home URLs should redirect to /videos/
5201 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5202 'To download only the videos in the home page, add a "/featured" to the URL')
5203 tab = '/videos'
5204
5205 url = ''.join((pre, tab, post))
5206 mobj = get_mobj(url)
5207
5208 # Handle both video/playlist URLs
5209 qs = parse_qs(url)
5210 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
5211
5212 if not video_id and mobj['not_channel'].startswith('watch'):
5213 if not playlist_id:
5214 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5215 raise ExtractorError('Unable to recognize tab page')
5216 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5217 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5218 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5219 mobj = get_mobj(url)
5220
5221 if video_id and playlist_id:
5222 if self.get_param('noplaylist'):
5223 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5224 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5225 ie=YoutubeIE.ie_key(), video_id=video_id)
5226 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5227
5228 data, ytcfg = self._extract_data(url, item_id)
5229
5230 # YouTube may provide a non-standard redirect to the regional channel
5231 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5232 redirect_url = traverse_obj(
5233 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5234 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5235 redirect_url = ''.join((
5236 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5237 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5238 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5239
5240 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5241 if tabs:
5242 selected_tab = self._extract_selected_tab(tabs)
5243 selected_tab_name = selected_tab.get('title', '').lower()
5244 if selected_tab_name == 'home':
5245 selected_tab_name = 'featured'
5246 requested_tab_name = mobj['tab'][1:]
5247 if 'no-youtube-channel-redirect' not in compat_opts:
5248 if requested_tab_name == 'live':
5249 # Live tab should have redirected to the video
5250 raise ExtractorError('The channel is not currently live', expected=True)
5251 if requested_tab_name not in ('', selected_tab_name):
5252 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5253 if not original_tab_name:
5254 if item_id[:2] == 'UC':
5255 # Topic channels don't have /videos. Use the equivalent playlist instead
5256 pl_id = f'UU{item_id[2:]}'
5257 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5258 try:
5259 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5260 except ExtractorError:
5261 redirect_warning += ' and the playlist redirect gave error'
5262 else:
5263 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5264 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5265 if selected_tab_name and selected_tab_name != requested_tab_name:
5266 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5267 else:
5268 raise ExtractorError(redirect_warning, expected=True)
5269
5270 if redirect_warning:
5271 self.to_screen(redirect_warning)
5272 self.write_debug(f'Final URL: {url}')
5273
5274 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5275 if 'no-youtube-unavailable-videos' not in compat_opts:
5276 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5277 self._extract_and_report_alerts(data, only_once=True)
5278 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5279 if tabs:
5280 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5281
5282 playlist = traverse_obj(
5283 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5284 if playlist:
5285 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5286
5287 video_id = traverse_obj(
5288 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5289 if video_id:
5290 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5291 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5292 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5293 ie=YoutubeIE.ie_key(), video_id=video_id)
5294
5295 raise ExtractorError('Unable to recognize tab page')
5296
5297
5298class YoutubePlaylistIE(InfoExtractor):
5299 IE_DESC = 'YouTube playlists'
5300 _VALID_URL = r'''(?x)(?:
5301 (?:https?://)?
5302 (?:\w+\.)?
5303 (?:
5304 (?:
5305 youtube(?:kids)?\.com|
5306 %(invidious)s
5307 )
5308 /.*?\?.*?\blist=
5309 )?
5310 (?P<id>%(playlist_id)s)
5311 )''' % {
5312 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5313 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5314 }
5315 IE_NAME = 'youtube:playlist'
5316 _TESTS = [{
5317 'note': 'issue #673',
5318 'url': 'PLBB231211A4F62143',
5319 'info_dict': {
5320 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5321 'id': 'PLBB231211A4F62143',
5322 'uploader': 'Wickman',
5323 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5324 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5325 'view_count': int,
5326 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5327 'modified_date': r're:\d{8}',
5328 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5329 'channel': 'Wickman',
5330 'tags': [],
5331 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5332 },
5333 'playlist_mincount': 29,
5334 }, {
5335 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5336 'info_dict': {
5337 'title': 'YDL_safe_search',
5338 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5339 },
5340 'playlist_count': 2,
5341 'skip': 'This playlist is private',
5342 }, {
5343 'note': 'embedded',
5344 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5345 'playlist_count': 4,
5346 'info_dict': {
5347 'title': 'JODA15',
5348 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5349 'uploader': 'milan',
5350 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5351 'description': '',
5352 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5353 'tags': [],
5354 'modified_date': '20140919',
5355 'view_count': int,
5356 'channel': 'milan',
5357 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5358 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5359 },
5360 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5361 }, {
5362 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5363 'playlist_mincount': 654,
5364 'info_dict': {
5365 'title': '2018 Chinese New Singles (11/6 updated)',
5366 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5367 'uploader': 'LBK',
5368 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5369 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5370 'channel': 'LBK',
5371 'view_count': int,
5372 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5373 'tags': [],
5374 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5375 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5376 'modified_date': r're:\d{8}',
5377 },
5378 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5379 }, {
5380 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5381 'only_matching': True,
5382 }, {
5383 # music album playlist
5384 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5385 'only_matching': True,
5386 }]
5387
5388 @classmethod
5389 def suitable(cls, url):
5390 if YoutubeTabIE.suitable(url):
5391 return False
5392 from ..utils import parse_qs
5393 qs = parse_qs(url)
5394 if qs.get('v', [None])[0]:
5395 return False
5396 return super(YoutubePlaylistIE, cls).suitable(url)
5397
5398 def _real_extract(self, url):
5399 playlist_id = self._match_id(url)
5400 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5401 url = update_url_query(
5402 'https://www.youtube.com/playlist',
5403 parse_qs(url) or {'list': playlist_id})
5404 if is_music_url:
5405 url = smuggle_url(url, {'is_music_url': True})
5406 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5407
5408
5409class YoutubeYtBeIE(InfoExtractor):
5410 IE_DESC = 'youtu.be'
5411 _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}
5412 _TESTS = [{
5413 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5414 'info_dict': {
5415 'id': 'yeWKywCrFtk',
5416 'ext': 'mp4',
5417 'title': 'Small Scale Baler and Braiding Rugs',
5418 'uploader': 'Backus-Page House Museum',
5419 'uploader_id': 'backuspagemuseum',
5420 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5421 'upload_date': '20161008',
5422 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5423 'categories': ['Nonprofits & Activism'],
5424 'tags': list,
5425 'like_count': int,
5426 'age_limit': 0,
5427 'playable_in_embed': True,
5428 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5429 'channel': 'Backus-Page House Museum',
5430 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5431 'live_status': 'not_live',
5432 'view_count': int,
5433 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5434 'availability': 'public',
5435 'duration': 59,
5436 },
5437 'params': {
5438 'noplaylist': True,
5439 'skip_download': True,
5440 },
5441 }, {
5442 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5443 'only_matching': True,
5444 }]
5445
5446 def _real_extract(self, url):
5447 mobj = self._match_valid_url(url)
5448 video_id = mobj.group('id')
5449 playlist_id = mobj.group('playlist_id')
5450 return self.url_result(
5451 update_url_query('https://www.youtube.com/watch', {
5452 'v': video_id,
5453 'list': playlist_id,
5454 'feature': 'youtu.be',
5455 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5456
5457
5458class YoutubeLivestreamEmbedIE(InfoExtractor):
5459 IE_DESC = 'YouTube livestream embeds'
5460 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5461 _TESTS = [{
5462 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5463 'only_matching': True,
5464 }]
5465
5466 def _real_extract(self, url):
5467 channel_id = self._match_id(url)
5468 return self.url_result(
5469 f'https://www.youtube.com/channel/{channel_id}/live',
5470 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5471
5472
5473class YoutubeYtUserIE(InfoExtractor):
5474 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5475 IE_NAME = 'youtube:user'
5476 _VALID_URL = r'ytuser:(?P<id>.+)'
5477 _TESTS = [{
5478 'url': 'ytuser:phihag',
5479 'only_matching': True,
5480 }]
5481
5482 def _real_extract(self, url):
5483 user_id = self._match_id(url)
5484 return self.url_result(
5485 'https://www.youtube.com/user/%s/videos' % user_id,
5486 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5487
5488
5489class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5490 IE_NAME = 'youtube:favorites'
5491 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5492 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5493 _LOGIN_REQUIRED = True
5494 _TESTS = [{
5495 'url': ':ytfav',
5496 'only_matching': True,
5497 }, {
5498 'url': ':ytfavorites',
5499 'only_matching': True,
5500 }]
5501
5502 def _real_extract(self, url):
5503 return self.url_result(
5504 'https://www.youtube.com/playlist?list=LL',
5505 ie=YoutubeTabIE.ie_key())
5506
5507
5508class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5509 IE_DESC = 'YouTube search'
5510 IE_NAME = 'youtube:search'
5511 _SEARCH_KEY = 'ytsearch'
5512 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5513 _TESTS = [{
5514 'url': 'ytsearch5:youtube-dl test video',
5515 'playlist_count': 5,
5516 'info_dict': {
5517 'id': 'youtube-dl test video',
5518 'title': 'youtube-dl test video',
5519 }
5520 }]
5521
5522
5523class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5524 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5525 _SEARCH_KEY = 'ytsearchdate'
5526 IE_DESC = 'YouTube search, newest videos first'
5527 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5528 _TESTS = [{
5529 'url': 'ytsearchdate5:youtube-dl test video',
5530 'playlist_count': 5,
5531 'info_dict': {
5532 'id': 'youtube-dl test video',
5533 'title': 'youtube-dl test video',
5534 }
5535 }]
5536
5537
5538class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5539 IE_DESC = 'YouTube search URLs with sorting and filter support'
5540 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5541 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5542 _TESTS = [{
5543 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5544 'playlist_mincount': 5,
5545 'info_dict': {
5546 'id': 'youtube-dl test video',
5547 'title': 'youtube-dl test video',
5548 }
5549 }, {
5550 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5551 'playlist_mincount': 5,
5552 'info_dict': {
5553 'id': 'python',
5554 'title': 'python',
5555 }
5556 }, {
5557 'url': 'https://www.youtube.com/results?search_query=%23cats',
5558 'playlist_mincount': 1,
5559 'info_dict': {
5560 'id': '#cats',
5561 'title': '#cats',
5562 'entries': [{
5563 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5564 'title': '#cats',
5565 }],
5566 },
5567 }, {
5568 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5569 'only_matching': True,
5570 }]
5571
5572 def _real_extract(self, url):
5573 qs = parse_qs(url)
5574 query = (qs.get('search_query') or qs.get('q'))[0]
5575 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5576
5577
5578class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5579 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
5580 IE_NAME = 'youtube:music:search_url'
5581 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5582 _TESTS = [{
5583 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5584 'playlist_count': 16,
5585 'info_dict': {
5586 'id': 'royalty free music',
5587 'title': 'royalty free music',
5588 }
5589 }, {
5590 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5591 'playlist_mincount': 30,
5592 'info_dict': {
5593 'id': 'royalty free music - songs',
5594 'title': 'royalty free music - songs',
5595 },
5596 'params': {'extract_flat': 'in_playlist'}
5597 }, {
5598 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5599 'playlist_mincount': 30,
5600 'info_dict': {
5601 'id': 'royalty free music - community playlists',
5602 'title': 'royalty free music - community playlists',
5603 },
5604 'params': {'extract_flat': 'in_playlist'}
5605 }]
5606
5607 _SECTIONS = {
5608 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5609 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5610 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5611 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5612 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5613 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5614 }
5615
5616 def _real_extract(self, url):
5617 qs = parse_qs(url)
5618 query = (qs.get('search_query') or qs.get('q'))[0]
5619 params = qs.get('sp', (None,))[0]
5620 if params:
5621 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5622 else:
5623 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5624 params = self._SECTIONS.get(section)
5625 if not params:
5626 section = None
5627 title = join_nonempty(query, section, delim=' - ')
5628 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
5629
5630
5631class YoutubeFeedsInfoExtractor(InfoExtractor):
5632 """
5633 Base class for feed extractors
5634 Subclasses must define the _FEED_NAME property.
5635 """
5636 _LOGIN_REQUIRED = True
5637 _TESTS = []
5638
5639 @property
5640 def IE_NAME(self):
5641 return 'youtube:%s' % self._FEED_NAME
5642
5643 def _real_extract(self, url):
5644 return self.url_result(
5645 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
5646
5647
5648class YoutubeWatchLaterIE(InfoExtractor):
5649 IE_NAME = 'youtube:watchlater'
5650 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5651 _VALID_URL = r':ytwatchlater'
5652 _TESTS = [{
5653 'url': ':ytwatchlater',
5654 'only_matching': True,
5655 }]
5656
5657 def _real_extract(self, url):
5658 return self.url_result(
5659 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5660
5661
5662class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5663 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5664 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5665 _FEED_NAME = 'recommended'
5666 _LOGIN_REQUIRED = False
5667 _TESTS = [{
5668 'url': ':ytrec',
5669 'only_matching': True,
5670 }, {
5671 'url': ':ytrecommended',
5672 'only_matching': True,
5673 }, {
5674 'url': 'https://youtube.com',
5675 'only_matching': True,
5676 }]
5677
5678
5679class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5680 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5681 _VALID_URL = r':ytsub(?:scription)?s?'
5682 _FEED_NAME = 'subscriptions'
5683 _TESTS = [{
5684 'url': ':ytsubs',
5685 'only_matching': True,
5686 }, {
5687 'url': ':ytsubscriptions',
5688 'only_matching': True,
5689 }]
5690
5691
5692class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5693 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5694 _VALID_URL = r':ythis(?:tory)?'
5695 _FEED_NAME = 'history'
5696 _TESTS = [{
5697 'url': ':ythistory',
5698 'only_matching': True,
5699 }]
5700
5701
5702class YoutubeTruncatedURLIE(InfoExtractor):
5703 IE_NAME = 'youtube:truncated_url'
5704 IE_DESC = False # Do not list
5705 _VALID_URL = r'''(?x)
5706 (?:https?://)?
5707 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5708 (?:watch\?(?:
5709 feature=[a-z_]+|
5710 annotation_id=annotation_[^&]+|
5711 x-yt-cl=[0-9]+|
5712 hl=[^&]*|
5713 t=[0-9]+
5714 )?
5715 |
5716 attribution_link\?a=[^&]+
5717 )
5718 $
5719 '''
5720
5721 _TESTS = [{
5722 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5723 'only_matching': True,
5724 }, {
5725 'url': 'https://www.youtube.com/watch?',
5726 'only_matching': True,
5727 }, {
5728 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5729 'only_matching': True,
5730 }, {
5731 'url': 'https://www.youtube.com/watch?feature=foo',
5732 'only_matching': True,
5733 }, {
5734 'url': 'https://www.youtube.com/watch?hl=en-GB',
5735 'only_matching': True,
5736 }, {
5737 'url': 'https://www.youtube.com/watch?t=2372',
5738 'only_matching': True,
5739 }]
5740
5741 def _real_extract(self, url):
5742 raise ExtractorError(
5743 'Did you forget to quote the URL? Remember that & is a meta '
5744 'character in most shells, so you want to put the URL in quotes, '
5745 'like youtube-dl '
5746 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5747 ' or simply youtube-dl BaW_jenozKc .',
5748 expected=True)
5749
5750
5751class YoutubeClipIE(InfoExtractor):
5752 IE_NAME = 'youtube:clip'
5753 IE_DESC = False # Do not list
5754 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5755
5756 def _real_extract(self, url):
5757 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5758 return self.url_result(url, 'Generic')
5759
5760
5761class YoutubeTruncatedIDIE(InfoExtractor):
5762 IE_NAME = 'youtube:truncated_id'
5763 IE_DESC = False # Do not list
5764 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5765
5766 _TESTS = [{
5767 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5768 'only_matching': True,
5769 }]
5770
5771 def _real_extract(self, url):
5772 video_id = self._match_id(url)
5773 raise ExtractorError(
5774 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5775 expected=True)