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