]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[utils] Better traceback for `ExtractorError`
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
d92f5d5a 5import calendar
109dd3b2 6import copy
fe93e2c4 7import datetime
adbc4ec4 8import functools
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
720c3099 12import math
c4417ddb 13import os.path
d77ab8e2 14import random
c5e8d7af 15import re
46383212 16import sys
8a784c74 17import time
e0df6211 18import traceback
adbc4ec4 19import threading
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 22from ..compat import (
edf3e38e 23 compat_chr,
29f7c58a 24 compat_HTTPError,
c5e8d7af 25 compat_parse_qs,
545cc85d 26 compat_str,
7fd002c0 27 compat_urllib_parse_unquote_plus,
15707c7e 28 compat_urllib_parse_urlencode,
7c80519c 29 compat_urllib_parse_urlparse,
7c61bd36 30 compat_urlparse,
4bb4a188 31)
545cc85d 32from ..jsinterp import JSInterpreter
4bb4a188 33from ..utils import (
720c3099 34 bug_reports_message,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
c5e8d7af 39 ExtractorError,
2d30521a 40 float_or_none,
11f9be09 41 format_field,
dd27fd17 42 int_or_none,
641ad5d8 43 is_html,
34921b43 44 join_nonempty,
48416bc4 45 js_to_json,
94278f72 46 mimetype2ext,
9c0d7f49 47 network_exceptions,
a6213a49 48 NO_DEFAULT,
11f9be09 49 orderedSet,
6310acf5 50 parse_codecs,
49bd8c66 51 parse_count,
7c80519c 52 parse_duration,
7ea65411 53 parse_iso8601,
4dfbf869 54 parse_qs,
dca3ff4a 55 qualities,
c0ac49bc 56 remove_end,
3995d37d 57 remove_start,
cf7e015f 58 smuggle_url,
dbdaaa23 59 str_or_none,
c93d53f5 60 str_to_int,
f3aa3c3f 61 strftime_or_none,
7c365c21 62 traverse_obj,
556dbe7f 63 try_get,
c5e8d7af
PH
64 unescapeHTML,
65 unified_strdate,
f0d785d3 66 unified_timestamp,
cf7e015f 67 unsmuggle_url,
8bdd16b4 68 update_url_query,
21c340b8 69 url_or_none,
fe93e2c4 70 urljoin,
7c365c21 71 variadic,
c5e8d7af
PH
72)
73
5f6a1245 74
720c3099 75def get_first(obj, keys, **kwargs):
76 return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
77
78
000c15a4 79# any clients starting with _ cannot be explicity requested by the user
80INNERTUBE_CLIENTS = {
81 'web': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB',
18c7683d 86 'clientVersion': '2.20211221.00.00',
000c15a4 87 }
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
90 },
91 'web_embedded': {
92 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
93 'INNERTUBE_CONTEXT': {
94 'client': {
95 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 96 'clientVersion': '1.20211215.00.01',
000c15a4 97 },
98 },
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
100 },
101 'web_music': {
102 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
103 'INNERTUBE_HOST': 'music.youtube.com',
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_REMIX',
18c7683d 107 'clientVersion': '1.20211213.00.00',
000c15a4 108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
111 },
e7e94f2a 112 'web_creator': {
18c7683d 113 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'WEB_CREATOR',
18c7683d 117 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
118 }
119 },
120 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
121 },
000c15a4 122 'android': {
18c7683d 123 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 124 'INNERTUBE_CONTEXT': {
125 'client': {
126 'clientName': 'ANDROID',
18c7683d 127 'clientVersion': '16.49',
000c15a4 128 }
129 },
130 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 131 'REQUIRE_JS_PLAYER': False
000c15a4 132 },
133 'android_embedded': {
18c7683d 134 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 135 'INNERTUBE_CONTEXT': {
136 'client': {
137 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 138 'clientVersion': '16.49',
000c15a4 139 },
140 },
b6de707d 141 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
142 'REQUIRE_JS_PLAYER': False
000c15a4 143 },
144 'android_music': {
18c7683d 145 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 146 'INNERTUBE_CONTEXT': {
147 'client': {
148 'clientName': 'ANDROID_MUSIC',
18c7683d 149 'clientVersion': '4.57',
000c15a4 150 }
151 },
152 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 153 'REQUIRE_JS_PLAYER': False
000c15a4 154 },
e7e94f2a 155 'android_creator': {
18c7683d 156 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
157 'INNERTUBE_CONTEXT': {
158 'client': {
159 'clientName': 'ANDROID_CREATOR',
18c7683d 160 'clientVersion': '21.47',
e7e94f2a
D
161 },
162 },
b6de707d 163 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
164 'REQUIRE_JS_PLAYER': False
e7e94f2a 165 },
18c7683d 166 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
167 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 168 'ios': {
18c7683d 169 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS',
18c7683d 173 'clientVersion': '16.46',
174 'deviceModel': 'iPhone14,3',
000c15a4 175 }
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_embedded': {
000c15a4 181 'INNERTUBE_CONTEXT': {
182 'client': {
183 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 184 'clientVersion': '16.46',
185 'deviceModel': 'iPhone14,3',
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
191 'ios_music': {
18c7683d 192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
18c7683d 196 'clientVersion': '4.57',
000c15a4 197 },
198 },
b6de707d 199 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
200 'REQUIRE_JS_PLAYER': False
000c15a4 201 },
e7e94f2a
D
202 'ios_creator': {
203 'INNERTUBE_CONTEXT': {
204 'client': {
205 'clientName': 'IOS_CREATOR',
18c7683d 206 'clientVersion': '21.47',
e7e94f2a
D
207 },
208 },
b6de707d 209 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
210 'REQUIRE_JS_PLAYER': False
e7e94f2a 211 },
3619f78d 212 # mweb has 'ultralow' formats
213 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 214 'mweb': {
18c7683d 215 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 216 'INNERTUBE_CONTEXT': {
217 'client': {
218 'clientName': 'MWEB',
18c7683d 219 'clientVersion': '2.20211221.01.00',
000c15a4 220 }
221 },
222 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
18c7683d 223 }
000c15a4 224}
225
226
227def build_innertube_clients():
2e4cacd0 228 THIRD_PARTY = {
65c2fde2 229 'embedUrl': 'https://google.com', # Can be any valid URL
230 }
2e4cacd0 231 BASE_CLIENTS = ('android', 'web', 'ios', 'mweb')
232 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 233
234 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 235 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 236 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 237 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 238 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 239
2e4cacd0 240 base_client, *variant = client.split('_')
241 ytcfg['priority'] = 10 * priority(base_client)
242
e48b3875 243 if not variant:
244 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
000c15a4 245 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
e48b3875 246 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 247 agegate_ytcfg['priority'] -= 1
e48b3875 248 elif variant == ['embedded']:
249 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 250 ytcfg['priority'] -= 2
e48b3875 251 else:
000c15a4 252 ytcfg['priority'] -= 3
253
254
255build_innertube_clients()
256
257
de7f3446 258class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 259 """Provide base functions for Youtube extractors"""
e00eb564 260
3462ffa8 261 _RESERVED_NAMES = (
3cd786db 262 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 263 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 264 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 265 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 266
3619f78d 267 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
268
b2e8bc1b 269 _NETRC_MACHINE = 'youtube'
3619f78d 270
b2e8bc1b
JMF
271 # If True it will raise an error if no login info is provided
272 _LOGIN_REQUIRED = False
273
d9190e44
RH
274 _INVIDIOUS_SITES = (
275 # invidious-redirect websites
276 r'(?:www\.)?redirect\.invidious\.io',
277 r'(?:(?:www|dev)\.)?invidio\.us',
278 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
279 r'(?:www\.)?invidious\.pussthecat\.org',
280 r'(?:www\.)?invidious\.zee\.li',
281 r'(?:www\.)?invidious\.ethibox\.fr',
282 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
283 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
284 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
285 # youtube-dl invidious instances list
286 r'(?:(?:www|no)\.)?invidiou\.sh',
287 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
288 r'(?:www\.)?invidious\.kabi\.tk',
289 r'(?:www\.)?invidious\.mastodon\.host',
290 r'(?:www\.)?invidious\.zapashcanon\.fr',
291 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
292 r'(?:www\.)?invidious\.tinfoil-hat\.net',
293 r'(?:www\.)?invidious\.himiko\.cloud',
294 r'(?:www\.)?invidious\.reallyancient\.tech',
295 r'(?:www\.)?invidious\.tube',
296 r'(?:www\.)?invidiou\.site',
297 r'(?:www\.)?invidious\.site',
298 r'(?:www\.)?invidious\.xyz',
299 r'(?:www\.)?invidious\.nixnet\.xyz',
300 r'(?:www\.)?invidious\.048596\.xyz',
301 r'(?:www\.)?invidious\.drycat\.fr',
302 r'(?:www\.)?inv\.skyn3t\.in',
303 r'(?:www\.)?tube\.poal\.co',
304 r'(?:www\.)?tube\.connect\.cafe',
305 r'(?:www\.)?vid\.wxzm\.sx',
306 r'(?:www\.)?vid\.mint\.lgbt',
307 r'(?:www\.)?vid\.puffyan\.us',
308 r'(?:www\.)?yewtu\.be',
309 r'(?:www\.)?yt\.elukerio\.org',
310 r'(?:www\.)?yt\.lelux\.fi',
311 r'(?:www\.)?invidious\.ggc-project\.de',
312 r'(?:www\.)?yt\.maisputain\.ovh',
313 r'(?:www\.)?ytprivate\.com',
314 r'(?:www\.)?invidious\.13ad\.de',
315 r'(?:www\.)?invidious\.toot\.koeln',
316 r'(?:www\.)?invidious\.fdn\.fr',
317 r'(?:www\.)?watch\.nettohikari\.com',
318 r'(?:www\.)?invidious\.namazso\.eu',
319 r'(?:www\.)?invidious\.silkky\.cloud',
320 r'(?:www\.)?invidious\.exonip\.de',
321 r'(?:www\.)?invidious\.riverside\.rocks',
322 r'(?:www\.)?invidious\.blamefran\.net',
323 r'(?:www\.)?invidious\.moomoo\.de',
324 r'(?:www\.)?ytb\.trom\.tf',
325 r'(?:www\.)?yt\.cyberhost\.uk',
326 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
327 r'(?:www\.)?qklhadlycap4cnod\.onion',
328 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
329 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
330 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
331 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
332 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
333 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
334 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
335 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
336 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
337 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
338 )
339
b2e8bc1b 340 def _login(self):
83317f69 341 """
342 Attempt to log in to YouTube.
83317f69 343 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
344 """
9d5d4d64 345
982ee69a
MB
346 if (self._LOGIN_REQUIRED
347 and self.get_param('cookiefile') is None
348 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 349 self.raise_login_required(
350 'Login details are needed to download this content', method='cookies')
68217024 351 username, password = self._get_login_info()
9d5d4d64 352 if username:
24b0a72b 353 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
b2e8bc1b 354
cce889b9 355 def _initialize_consent(self):
356 cookies = self._get_cookies('https://www.youtube.com/')
357 if cookies.get('__Secure-3PSID'):
358 return
359 consent_id = None
360 consent = cookies.get('CONSENT')
361 if consent:
362 if 'YES' in consent.value:
363 return
364 consent_id = self._search_regex(
365 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
366 if not consent_id:
367 consent_id = random.randint(100, 999)
368 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 369
f3aa3c3f 370 def _initialize_pref(self):
371 cookies = self._get_cookies('https://www.youtube.com/')
372 pref_cookie = cookies.get('PREF')
373 pref = {}
374 if pref_cookie:
375 try:
376 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
377 except ValueError:
378 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 379 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 380 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
381
b2e8bc1b 382 def _real_initialize(self):
f3aa3c3f 383 self._initialize_pref()
cce889b9 384 self._initialize_consent()
24b0a72b 385 self._login()
c5e8d7af 386
a0566bbf 387 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 388 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
389 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 390
000c15a4 391 def _get_default_ytcfg(self, client='web'):
392 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 393
000c15a4 394 def _get_innertube_host(self, client='web'):
395 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 396
000c15a4 397 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 398 # try_get but with fallback to default ytcfg client values when present
399 _func = lambda y: try_get(y, getter, expected_type)
400 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
401
000c15a4 402 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 403 return self._ytcfg_get_safe(
404 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
405 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 406
000c15a4 407 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 411
000c15a4 412 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 413 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
414
000c15a4 415 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 416 context = get_first(
417 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 418 # Enforce language and tz for extraction
419 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
420 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 421 return context
422
cf87314d 423 _SAPISID = None
424
109dd3b2 425 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 426 time_now = round(time.time())
cf87314d 427 if self._SAPISID is None:
428 yt_cookies = self._get_cookies('https://www.youtube.com')
429 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
430 # See: https://github.com/yt-dlp/yt-dlp/issues/393
431 sapisid_cookie = dict_get(
432 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
433 if sapisid_cookie and sapisid_cookie.value:
434 self._SAPISID = sapisid_cookie.value
435 self.write_debug('Extracted SAPISID cookie')
436 # SAPISID cookie is required if not already present
437 if not yt_cookies.get('SAPISID'):
438 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
439 self._set_cookie(
440 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
441 else:
442 self._SAPISID = False
443 if not self._SAPISID:
444 return None
1974e99f 445 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
446 sapisidhash = hashlib.sha1(
cf87314d 447 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 448 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
449
450 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 451 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 452 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 453
109dd3b2 454 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 455 data.update(query)
11f9be09 456 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 457 real_headers.update({'content-type': 'application/json'})
458 if headers:
459 real_headers.update(headers)
545cc85d 460 return self._download_json(
109dd3b2 461 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 462 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 463 data=json.dumps(data).encode('utf8'), headers=real_headers,
464 query={'key': api_key or self._extract_api_key()})
465
ac56cf38 466 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
467 data = self._search_regex(
468 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
469 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
470 if data:
471 return self._parse_json(data, item_id, fatal=fatal)
0c148415 472
99e9e001 473 @staticmethod
474 def _extract_session_index(*data):
475 """
476 Index of current account in account list.
477 See: https://github.com/yt-dlp/yt-dlp/pull/519
478 """
479 for ytcfg in data:
480 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
481 if session_index is not None:
482 return session_index
483
484 # Deprecated?
485 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
486 if ytcfg:
487 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
488 if token:
489 return token
99e9e001 490 if webpage:
491 return self._search_regex(
492 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
493 'identity token', default=None, fatal=False)
a1c5d2ca
M
494
495 @staticmethod
fe93e2c4 496 def _extract_account_syncid(*args):
8ea3f7b9 497 """
498 Extract syncId required to download private playlists of secondary channels
fe93e2c4 499 @params response and/or ytcfg
8ea3f7b9 500 """
fe93e2c4 501 for data in args:
502 # ytcfg includes channel_syncid if on secondary channel
503 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
504 if delegated_sid:
505 return delegated_sid
506 sync_ids = (try_get(
507 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 508 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 509 if len(sync_ids) >= 2 and sync_ids[1]:
510 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
511 # and just "user_syncid||" for primary channel. We only want the channel_syncid
512 return sync_ids[0]
a1c5d2ca 513
ac56cf38 514 @staticmethod
515 def _extract_visitor_data(*args):
516 """
517 Extracts visitorData from an API response or ytcfg
518 Appears to be used to track session state
519 """
9222c381 520 return get_first(
6c73052c 521 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 522 expected_type=str)
ac56cf38 523
99e9e001 524 @property
525 def is_authenticated(self):
526 return bool(self._generate_sapisidhash_header())
527
11f9be09 528 def extract_ytcfg(self, video_id, webpage):
8c54a305 529 if not webpage:
530 return {}
29f7c58a 531 return self._parse_json(
532 self._search_regex(
533 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 534 default='{}'), video_id, fatal=False) or {}
535
11f9be09 536 def generate_api_headers(
99e9e001 537 self, *, ytcfg=None, account_syncid=None, session_index=None,
538 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
539
11f9be09 540 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 541 headers = {
109dd3b2 542 'X-YouTube-Client-Name': compat_str(
11f9be09 543 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
544 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 545 'Origin': origin,
546 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
547 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 548 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 549 }
550 if session_index is None:
314ee305 551 session_index = self._extract_session_index(ytcfg)
552 if account_syncid or session_index is not None:
553 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 554
109dd3b2 555 auth = self._generate_sapisidhash_header(origin)
f4f751af 556 if auth is not None:
557 headers['Authorization'] = auth
109dd3b2 558 headers['X-Origin'] = origin
99e9e001 559 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 560
2d6659b9 561 @staticmethod
562 def _build_api_continuation_query(continuation, ctp=None):
563 query = {
564 'continuation': continuation
565 }
566 # TODO: Inconsistency with clickTrackingParams.
567 # Currently we have a fixed ctp contained within context (from ytcfg)
568 # and a ctp in root query for continuation.
569 if ctp:
570 query['clickTracking'] = {'clickTrackingParams': ctp}
571 return query
572
2d6659b9 573 @classmethod
574 def _extract_next_continuation_data(cls, renderer):
575 next_continuation = try_get(
576 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
577 lambda x: x['continuation']['reloadContinuationData']), dict)
578 if not next_continuation:
579 return
580 continuation = next_continuation.get('continuation')
581 if not continuation:
582 return
583 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 584 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 585
586 @classmethod
587 def _extract_continuation_ep_data(cls, continuation_ep: dict):
588 if isinstance(continuation_ep, dict):
589 continuation = try_get(
590 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
591 if not continuation:
592 return
593 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 594 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 595
596 @classmethod
597 def _extract_continuation(cls, renderer):
598 next_continuation = cls._extract_next_continuation_data(renderer)
599 if next_continuation:
600 return next_continuation
fe93e2c4 601
2d6659b9 602 contents = []
603 for key in ('contents', 'items'):
604 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 605
2d6659b9 606 for content in contents:
607 if not isinstance(content, dict):
608 continue
609 continuation_ep = try_get(
610 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
611 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
612 dict)
613 continuation = cls._extract_continuation_ep_data(continuation_ep)
614 if continuation:
615 return continuation
616
fe93e2c4 617 @classmethod
618 def _extract_alerts(cls, data):
109dd3b2 619 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
620 if not isinstance(alert_dict, dict):
621 continue
622 for alert in alert_dict.values():
623 alert_type = alert.get('type')
624 if not alert_type:
625 continue
052e1350 626 message = cls._get_text(alert, 'text')
109dd3b2 627 if message:
628 yield alert_type, message
629
c0ac49bc 630 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 631 errors = []
632 warnings = []
633 for alert_type, alert_message in alerts:
641ad5d8 634 if alert_type.lower() == 'error' and fatal:
109dd3b2 635 errors.append([alert_type, alert_message])
636 else:
637 warnings.append([alert_type, alert_message])
638
639 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 640 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 641 if errors:
642 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
643
644 def _extract_and_report_alerts(self, data, *args, **kwargs):
645 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
646
47193e02 647 def _extract_badges(self, renderer: dict):
648 badges = set()
649 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
650 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
651 if label:
652 badges.add(label.lower())
653 return badges
654
655 @staticmethod
052e1350 656 def _get_text(data, *path_list, max_runs=None):
657 for path in path_list or [None]:
658 if path is None:
659 obj = [data]
660 else:
661 obj = traverse_obj(data, path, default=[])
662 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
663 obj = [obj]
664 for item in obj:
665 text = try_get(item, lambda x: x['simpleText'], compat_str)
666 if text:
667 return text
668 runs = try_get(item, lambda x: x['runs'], list) or []
669 if not runs and isinstance(item, list):
670 runs = item
671
672 runs = runs[:min(len(runs), max_runs or len(runs))]
673 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
674 if text:
675 return text
47193e02 676
f0d785d3 677 def _get_count(self, data, *path_list):
678 count_text = self._get_text(data, *path_list) or ''
679 count = parse_count(count_text)
680 if count is None:
681 count = str_to_int(
682 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
683 return count
684
a709d873 685 @staticmethod
686 def _extract_thumbnails(data, *path_list):
687 """
688 Extract thumbnails from thumbnails dict
689 @param path_list: path list to level that contains 'thumbnails' key
690 """
691 thumbnails = []
692 for path in path_list or [()]:
693 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
694 thumbnail_url = url_or_none(thumbnail.get('url'))
695 if not thumbnail_url:
696 continue
697 # Sometimes youtube gives a wrong thumbnail URL. See:
698 # https://github.com/yt-dlp/yt-dlp/issues/233
699 # https://github.com/ytdl-org/youtube-dl/issues/28023
700 if 'maxresdefault' in thumbnail_url:
701 thumbnail_url = thumbnail_url.split('?')[0]
702 thumbnails.append({
703 'url': thumbnail_url,
704 'height': int_or_none(thumbnail.get('height')),
705 'width': int_or_none(thumbnail.get('width')),
706 })
707 return thumbnails
708
f3aa3c3f 709 @staticmethod
710 def extract_relative_time(relative_time_text):
711 """
712 Extracts a relative time from string and converts to dt object
f0d785d3 713 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 714 """
f0d785d3 715 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)
f3aa3c3f 716 if mobj:
f0d785d3 717 start = mobj.group('start')
718 if start:
719 return datetime_from_str(start)
f3aa3c3f 720 try:
f0d785d3 721 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 722 except ValueError:
723 return None
724
725 def _extract_time_text(self, renderer, *path_list):
726 text = self._get_text(renderer, *path_list) or ''
727 dt = self.extract_relative_time(text)
728 timestamp = None
729 if isinstance(dt, datetime.datetime):
730 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 731
732 if timestamp is None:
733 timestamp = (
734 unified_timestamp(text) or unified_timestamp(
735 self._search_regex(
396a76f7 736 (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
737 text.lower(), 'time text', default=None)))
f0d785d3 738
f3aa3c3f 739 if text and timestamp is None:
740 self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
741 return timestamp, text
742
109dd3b2 743 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
744 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 745 default_client='web'):
109dd3b2 746 response = None
747 last_error = None
748 count = -1
749 retries = self.get_param('extractor_retries', 3)
750 if check_get_keys is None:
751 check_get_keys = []
752 while count < retries:
753 count += 1
754 if last_error:
c0ac49bc 755 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 756 try:
757 response = self._call_api(
758 ep=ep, fatal=True, headers=headers,
759 video_id=item_id, query=query,
760 context=self._extract_context(ytcfg, default_client),
761 api_key=self._extract_api_key(ytcfg, default_client),
762 api_hostname=api_hostname, default_client=default_client,
763 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
764 except ExtractorError as e:
9c0d7f49 765 if isinstance(e.cause, network_exceptions):
87e8e8a7 766 if isinstance(e.cause, compat_HTTPError):
767 first_bytes = e.cause.read(512)
768 if not is_html(first_bytes):
769 yt_error = try_get(
770 self._parse_json(
771 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
772 lambda x: x['error']['message'], compat_str)
773 if yt_error:
774 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 775 # Downloading page may result in intermittent 5xx HTTP error
776 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 777 # We also want to catch all other network exceptions since errors in later pages can be troublesome
778 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
779 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 780 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 781 if count < retries:
782 continue
109dd3b2 783 if fatal:
784 raise
785 else:
786 self.report_warning(error_to_compat_str(e))
787 return
788
789 else:
109dd3b2 790 try:
ac56cf38 791 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 792 except ExtractorError as e:
c0ac49bc 793 # YouTube servers may return errors we want to retry on in a 200 OK response
794 # See: https://github.com/yt-dlp/yt-dlp/issues/839
795 if 'unknown error' in e.msg.lower():
796 last_error = e.msg
797 continue
109dd3b2 798 if fatal:
799 raise
800 self.report_warning(error_to_compat_str(e))
801 return
802 if not check_get_keys or dict_get(response, check_get_keys):
803 break
804 # Youtube sometimes sends incomplete data
805 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
806 last_error = 'Incomplete data received'
807 if count >= retries:
808 if fatal:
809 raise ExtractorError(last_error)
810 else:
811 self.report_warning(last_error)
812 return
813 return response
814
9297939e 815 @staticmethod
816 def is_music_url(url):
817 return re.match(r'https?://music\.youtube\.com/', url) is not None
818
30a074c2 819 def _extract_video(self, renderer):
820 video_id = renderer.get('videoId')
052e1350 821 title = self._get_text(renderer, 'title')
822 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 823 duration = parse_duration(self._get_text(
824 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
f0d785d3 825 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 826
052e1350 827 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 828 channel_id = traverse_obj(
829 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
830 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
831 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
832 overlay_style = traverse_obj(
833 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
834 badges = self._extract_badges(renderer)
a709d873 835 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
836
30a074c2 837 return {
39ed931e 838 '_type': 'url',
30a074c2 839 'ie_key': YoutubeIE.ie_key(),
840 'id': video_id,
5e3f2f8f 841 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 842 'title': title,
843 'description': description,
844 'duration': duration,
845 'view_count': view_count,
846 'uploader': uploader,
f3aa3c3f 847 'channel_id': channel_id,
a709d873 848 'thumbnails': thumbnails,
a30a6ed3 849 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 850 'live_status': ('is_upcoming' if scheduled_timestamp is not None
851 else 'was_live' if 'streamed' in time_text.lower()
852 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
853 else None),
854 'release_timestamp': scheduled_timestamp,
855 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 856 }
857
0c148415 858
360e1ca5 859class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 860 IE_DESC = 'YouTube'
cb7dfeea 861 _VALID_URL = r"""(?x)^
c5e8d7af 862 (
edb53e2d 863 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 864 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
865 (?:www\.)?deturl\.com/www\.youtube\.com|
866 (?:www\.)?pwnyoutube\.com|
867 (?:www\.)?hooktube\.com|
868 (?:www\.)?yourepeat\.com|
869 tube\.majestyc\.net|
870 %(invidious)s|
871 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
872 (?:.*?\#/)? # handle anchor (#/) redirect urls
873 (?: # the various things that can precede the ID:
b6ce9bb0 874 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 875 |(?: # or the v= param in all its forms
f7000f3a 876 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 877 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 878 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
879 v=
880 )
f4b05232 881 ))
cbaed4bb
S
882 |(?:
883 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
884 vid\.plus| # or vid.plus/xxxx
885 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 886 %(invidious)s
cbaed4bb 887 )/
edb53e2d 888 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 889 )
c5e8d7af 890 )? # all until now is optional -> you can pass the naked ID
201c1459 891 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 892 (?(1).+)? # if we found the ID, everything can follow
9297939e 893 (?:\#|$)""" % {
d9190e44 894 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 895 }
e40c758c 896 _PLAYER_INFO_RE = (
cc2db878 897 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
898 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 899 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 900 )
2c62dc26 901 _formats = {
c2d3cb4c 902 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
903 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
904 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
905 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
906 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
907 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
908 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
909 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 910 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 911 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
912 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
913 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
914 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
915 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
916 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 917 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 918 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
919 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 920
921
922 # 3D videos
c2d3cb4c 923 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
924 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
925 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
926 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 927 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
928 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
929 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 930
96fb5605 931 # Apple HTTP Live Streaming
11f12195 932 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 933 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
934 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
935 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
936 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
937 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 938 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
939 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
940
941 # DASH mp4 video
d23028a8
S
942 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
943 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
944 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
945 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
946 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 947 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
948 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
949 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
950 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
951 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
952 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
953 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 954
f6f1fc92 955 # Dash mp4 audio
d23028a8
S
956 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
957 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
958 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
959 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
960 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
961 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
962 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
963
964 # Dash webm
d23028a8
S
965 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
967 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
968 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
969 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
970 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
971 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
972 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
976 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
977 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
978 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
979 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 980 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
981 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
982 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
983 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
984 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
985 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
986 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
987
988 # Dash webm audio
d23028a8
S
989 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
990 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 991
0857baad 992 # Dash webm audio with opus inside
d23028a8
S
993 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
994 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
995 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 996
ce6b9a2d
PH
997 # RTMP (unnamed)
998 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
999
1000 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1001 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1002 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1003 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1004 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1005 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1006 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1007 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1008 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1009 }
29f7c58a 1010 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1011
fd5c4aab
S
1012 _GEO_BYPASS = False
1013
78caa52a 1014 IE_NAME = 'youtube'
2eb88d95
PH
1015 _TESTS = [
1016 {
2d3d2997 1017 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1018 'info_dict': {
1019 'id': 'BaW_jenozKc',
1020 'ext': 'mp4',
3867038a 1021 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1022 'uploader': 'Philipp Hagemeister',
1023 'uploader_id': 'phihag',
ec85ded8 1024 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1025 'channel': 'Philipp Hagemeister',
dd4c4492
S
1026 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1027 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1028 'upload_date': '20121002',
ff9f925b 1029 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1030 'categories': ['Science & Technology'],
3867038a 1031 'tags': ['youtube-dl'],
556dbe7f 1032 'duration': 10,
dbdaaa23 1033 'view_count': int,
3e7c1224 1034 'like_count': int,
ff9f925b 1035 'availability': 'public',
1036 'playable_in_embed': True,
1037 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1038 'live_status': 'not_live',
1039 'age_limit': 0,
7c80519c 1040 'start_time': 1,
297a564b 1041 'end_time': 9,
6c73052c 1042 'channel_follower_count': int
2eb88d95 1043 }
0e853ca4 1044 },
fccd3771 1045 {
4bc3a23e
PH
1046 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1047 'note': 'Embed-only video (#1746)',
1048 'info_dict': {
1049 'id': 'yZIXLfi8CZQ',
1050 'ext': 'mp4',
1051 'upload_date': '20120608',
1052 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1053 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1054 'uploader': 'SET India',
94bfcd23 1055 'uploader_id': 'setindia',
ec85ded8 1056 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1057 'age_limit': 18,
545cc85d 1058 },
1059 'skip': 'Private video',
fccd3771 1060 },
11b56058 1061 {
8bdd16b4 1062 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1063 'note': 'Use the first video ID in the URL',
1064 'info_dict': {
1065 'id': 'BaW_jenozKc',
1066 'ext': 'mp4',
3867038a 1067 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1068 'uploader': 'Philipp Hagemeister',
1069 'uploader_id': 'phihag',
ec85ded8 1070 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1071 'channel': 'Philipp Hagemeister',
1072 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1073 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1074 'upload_date': '20121002',
976ae3ea 1075 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1076 'categories': ['Science & Technology'],
3867038a 1077 'tags': ['youtube-dl'],
556dbe7f 1078 'duration': 10,
dbdaaa23 1079 'view_count': int,
11b56058 1080 'like_count': int,
976ae3ea 1081 'availability': 'public',
1082 'playable_in_embed': True,
1083 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1084 'live_status': 'not_live',
1085 'age_limit': 0,
6c73052c 1086 'channel_follower_count': int
34a7de29
S
1087 },
1088 'params': {
1089 'skip_download': True,
1090 },
11b56058 1091 },
dd27fd17 1092 {
2d3d2997 1093 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1094 'note': '256k DASH audio (format 141) via DASH manifest',
1095 'info_dict': {
1096 'id': 'a9LDPn-MO4I',
1097 'ext': 'm4a',
1098 'upload_date': '20121002',
1099 'uploader_id': '8KVIDEO',
ec85ded8 1100 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1101 'description': '',
1102 'uploader': '8KVIDEO',
1103 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1104 },
4bc3a23e
PH
1105 'params': {
1106 'youtube_include_dash_manifest': True,
1107 'format': '141',
4919603f 1108 },
de3c7fe0 1109 'skip': 'format 141 not served anymore',
dd27fd17 1110 },
8bdd16b4 1111 # DASH manifest with encrypted signature
1112 {
1113 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1114 'info_dict': {
1115 'id': 'IB3lcPjvWLA',
1116 'ext': 'm4a',
1117 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1118 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1119 'duration': 244,
1120 'uploader': 'AfrojackVEVO',
1121 'uploader_id': 'AfrojackVEVO',
1122 'upload_date': '20131011',
cc2db878 1123 'abr': 129.495,
976ae3ea 1124 'like_count': int,
1125 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1126 'playable_in_embed': True,
1127 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1128 'view_count': int,
1129 'track': 'The Spark',
1130 'live_status': 'not_live',
1131 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1132 'channel': 'Afrojack',
1133 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1134 'tags': 'count:19',
1135 'availability': 'public',
1136 'categories': ['Music'],
1137 'age_limit': 0,
1138 'alt_title': 'The Spark',
6c73052c 1139 'channel_follower_count': int
8bdd16b4 1140 },
1141 'params': {
1142 'youtube_include_dash_manifest': True,
1143 'format': '141/bestaudio[ext=m4a]',
1144 },
1145 },
65c2fde2 1146 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1147 {
65c2fde2 1148 'note': 'Embed allowed age-gate video',
2d3d2997 1149 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1150 'info_dict': {
1151 'id': 'HtVdAasjOgU',
1152 'ext': 'mp4',
1153 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1154 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1155 'duration': 142,
c522adb1
JMF
1156 'uploader': 'The Witcher',
1157 'uploader_id': 'WitcherGame',
ec85ded8 1158 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1159 'upload_date': '20140605',
34952f09 1160 'age_limit': 18,
976ae3ea 1161 'categories': ['Gaming'],
1162 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1163 'availability': 'needs_auth',
1164 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1165 'like_count': int,
1166 'channel': 'The Witcher',
1167 'live_status': 'not_live',
1168 'tags': 'count:17',
1169 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1170 'playable_in_embed': True,
1171 'view_count': int,
6c73052c 1172 'channel_follower_count': int
c522adb1
JMF
1173 },
1174 },
65c2fde2 1175 {
1176 'note': 'Age-gate video with embed allowed in public site',
1177 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1178 'info_dict': {
1179 'id': 'HsUATh_Nc2U',
1180 'ext': 'mp4',
1181 'title': 'Godzilla 2 (Official Video)',
1182 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1183 'upload_date': '20200408',
1184 'uploader_id': 'FlyingKitty900',
1185 'uploader': 'FlyingKitty',
1186 'age_limit': 18,
976ae3ea 1187 'availability': 'needs_auth',
1188 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1189 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1190 'channel': 'FlyingKitty',
1191 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1192 'view_count': int,
1193 'categories': ['Entertainment'],
1194 'live_status': 'not_live',
1195 'tags': ['Flyingkitty', 'godzilla 2'],
1196 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1197 'like_count': int,
1198 'duration': 177,
1199 'playable_in_embed': True,
6c73052c 1200 'channel_follower_count': int
65c2fde2 1201 },
1202 },
1203 {
1204 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1205 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1206 'info_dict': {
1207 'id': 'Tq92D6wQ1mg',
1208 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1209 'ext': 'mp4',
1210 'upload_date': '20191227',
65c2fde2 1211 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1212 'uploader': 'Projekt Melody',
1213 'description': 'md5:17eccca93a786d51bc67646756894066',
1214 'age_limit': 18,
976ae3ea 1215 'like_count': int,
1216 'availability': 'needs_auth',
1217 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1218 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1219 'view_count': int,
1220 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1221 'channel': 'Projekt Melody',
1222 'live_status': 'not_live',
1223 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1224 'playable_in_embed': True,
1225 'categories': ['Entertainment'],
1226 'duration': 106,
1227 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1228 'channel_follower_count': int
65c2fde2 1229 },
1230 },
1231 {
1232 'note': 'Non-Agegated non-embeddable video',
1233 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1234 'info_dict': {
1235 'id': 'MeJVWBSsPAY',
1236 'ext': 'mp4',
1237 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1238 'uploader': 'Herr Lurik',
1239 'uploader_id': 'st3in234',
1240 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1241 'upload_date': '20130730',
976ae3ea 1242 'track': 'Such mich find mich',
1243 'age_limit': 0,
1244 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1245 'like_count': int,
1246 'playable_in_embed': False,
1247 'creator': 'OOMPH!',
1248 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1249 'view_count': int,
1250 'alt_title': 'Such mich find mich',
1251 'duration': 210,
1252 'channel': 'Herr Lurik',
1253 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1254 'categories': ['Music'],
1255 'availability': 'public',
1256 'uploader_url': 'http://www.youtube.com/user/st3in234',
1257 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1258 'live_status': 'not_live',
1259 'artist': 'OOMPH!',
6c73052c 1260 'channel_follower_count': int
65c2fde2 1261 },
1262 },
1263 {
1264 'note': 'Non-bypassable age-gated video',
1265 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1266 'only_matching': True,
1267 },
8bdd16b4 1268 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1269 # YouTube Red ad is not captured for creator
1270 {
1271 'url': '__2ABJjxzNo',
1272 'info_dict': {
1273 'id': '__2ABJjxzNo',
1274 'ext': 'mp4',
1275 'duration': 266,
1276 'upload_date': '20100430',
1277 'uploader_id': 'deadmau5',
1278 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1279 'creator': 'deadmau5',
1280 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1281 'uploader': 'deadmau5',
1282 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1283 'alt_title': 'Some Chords',
976ae3ea 1284 'availability': 'public',
1285 'tags': 'count:14',
1286 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1287 'view_count': int,
1288 'live_status': 'not_live',
1289 'channel': 'deadmau5',
1290 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1291 'like_count': int,
1292 'track': 'Some Chords',
1293 'artist': 'deadmau5',
1294 'playable_in_embed': True,
1295 'age_limit': 0,
1296 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1297 'categories': ['Music'],
1298 'album': 'Some Chords',
6c73052c 1299 'channel_follower_count': int
8bdd16b4 1300 },
1301 'expected_warnings': [
1302 'DASH manifest missing',
1303 ]
1304 },
067aa17e 1305 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1306 {
1307 'url': 'lqQg6PlCWgI',
1308 'info_dict': {
1309 'id': 'lqQg6PlCWgI',
1310 'ext': 'mp4',
556dbe7f 1311 'duration': 6085,
90227264 1312 'upload_date': '20150827',
cbe2bd91 1313 'uploader_id': 'olympic',
ec85ded8 1314 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1315 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1316 'uploader': 'Olympics',
cbe2bd91 1317 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1318 'like_count': int,
1319 'release_timestamp': 1343767800,
1320 'playable_in_embed': True,
1321 'categories': ['Sports'],
1322 'release_date': '20120731',
1323 'channel': 'Olympics',
1324 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1325 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1326 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1327 'age_limit': 0,
1328 'availability': 'public',
1329 'live_status': 'was_live',
1330 'view_count': int,
1331 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1332 'channel_follower_count': int
cbe2bd91
PH
1333 },
1334 'params': {
1335 'skip_download': 'requires avconv',
e52a40ab 1336 }
cbe2bd91 1337 },
6271f1ca
PH
1338 # Non-square pixels
1339 {
1340 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1341 'info_dict': {
1342 'id': '_b-2C3KPAM0',
1343 'ext': 'mp4',
1344 'stretched_ratio': 16 / 9.,
556dbe7f 1345 'duration': 85,
6271f1ca
PH
1346 'upload_date': '20110310',
1347 'uploader_id': 'AllenMeow',
ec85ded8 1348 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1349 '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',
eb6793ba 1350 'uploader': '孫ᄋᄅ',
6271f1ca 1351 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1352 'playable_in_embed': True,
1353 'channel': '孫ᄋᄅ',
1354 'age_limit': 0,
1355 'tags': 'count:11',
1356 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1357 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1358 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1359 'view_count': int,
1360 'categories': ['People & Blogs'],
1361 'like_count': int,
1362 'live_status': 'not_live',
1363 'availability': 'unlisted',
6c73052c 1364 'channel_follower_count': int
6271f1ca 1365 },
06b491eb
S
1366 },
1367 # url_encoded_fmt_stream_map is empty string
1368 {
1369 'url': 'qEJwOuvDf7I',
1370 'info_dict': {
1371 'id': 'qEJwOuvDf7I',
f57b7835 1372 'ext': 'webm',
06b491eb
S
1373 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1374 'description': '',
1375 'upload_date': '20150404',
1376 'uploader_id': 'spbelect',
1377 'uploader': 'Наблюдатели Петербурга',
1378 },
1379 'params': {
1380 'skip_download': 'requires avconv',
e323cf3f
S
1381 },
1382 'skip': 'This live event has ended.',
06b491eb 1383 },
067aa17e 1384 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1385 {
1386 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1387 'info_dict': {
1388 'id': 'FIl7x6_3R5Y',
eb6793ba 1389 'ext': 'webm',
da77d856
S
1390 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1391 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1392 'duration': 220,
da77d856
S
1393 'upload_date': '20150625',
1394 'uploader_id': 'dorappi2000',
ec85ded8 1395 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1396 'uploader': 'dorappi2000',
eb6793ba 1397 'formats': 'mincount:31',
da77d856 1398 },
eb6793ba 1399 'skip': 'not actual anymore',
2ee8f5d8 1400 },
8a1a26ce
YCH
1401 # DASH manifest with segment_list
1402 {
1403 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1404 'md5': '8ce563a1d667b599d21064e982ab9e31',
1405 'info_dict': {
1406 'id': 'CsmdDsKjzN8',
1407 'ext': 'mp4',
17ee98e1 1408 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1409 'uploader': 'Airtek',
1410 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1411 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1412 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1413 },
1414 'params': {
1415 'youtube_include_dash_manifest': True,
1416 'format': '135', # bestvideo
be49068d
S
1417 },
1418 'skip': 'This live event has ended.',
2ee8f5d8 1419 },
cf7e015f
S
1420 {
1421 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1422 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1423 'info_dict': {
545cc85d 1424 'id': 'jvGDaLqkpTg',
1425 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1426 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1427 },
1428 'playlist': [{
1429 'info_dict': {
545cc85d 1430 'id': 'jvGDaLqkpTg',
cf7e015f 1431 'ext': 'mp4',
545cc85d 1432 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1433 'description': 'md5:e03b909557865076822aa169218d6a5d',
1434 'duration': 10643,
1435 'upload_date': '20161111',
1436 'uploader': 'Team PGP',
1437 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1438 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1439 },
1440 }, {
1441 'info_dict': {
545cc85d 1442 'id': '3AKt1R1aDnw',
cf7e015f 1443 'ext': 'mp4',
545cc85d 1444 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1445 'description': 'md5:e03b909557865076822aa169218d6a5d',
1446 'duration': 10991,
1447 'upload_date': '20161111',
1448 'uploader': 'Team PGP',
1449 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1450 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1451 },
1452 }, {
1453 'info_dict': {
545cc85d 1454 'id': 'RtAMM00gpVc',
cf7e015f 1455 'ext': 'mp4',
545cc85d 1456 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1457 'description': 'md5:e03b909557865076822aa169218d6a5d',
1458 'duration': 10995,
1459 'upload_date': '20161111',
1460 'uploader': 'Team PGP',
1461 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1462 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1463 },
1464 }, {
1465 'info_dict': {
545cc85d 1466 'id': '6N2fdlP3C5U',
cf7e015f 1467 'ext': 'mp4',
545cc85d 1468 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1469 'description': 'md5:e03b909557865076822aa169218d6a5d',
1470 'duration': 10990,
1471 'upload_date': '20161111',
1472 'uploader': 'Team PGP',
1473 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1474 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1475 },
1476 }],
1477 'params': {
1478 'skip_download': True,
1479 },
65c2fde2 1480 'skip': 'Not multifeed anymore',
cbaed4bb 1481 },
f9f49d87 1482 {
067aa17e 1483 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1484 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1485 'info_dict': {
1486 'id': 'gVfLd0zydlo',
1487 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1488 },
1489 'playlist_count': 2,
be49068d 1490 'skip': 'Not multifeed anymore',
f9f49d87 1491 },
cbaed4bb 1492 {
2d3d2997 1493 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1494 'only_matching': True,
0e49d9a6 1495 },
6d4fc66b 1496 {
2d3d2997 1497 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1498 'only_matching': True,
1499 },
0e49d9a6 1500 {
067aa17e 1501 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1502 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1503 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1504 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1505 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1506 'info_dict': {
1507 'id': 'lsguqyKfVQg',
1508 'ext': 'mp4',
1509 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1510 'alt_title': 'Dark Walk',
0e49d9a6 1511 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1512 'duration': 133,
0e49d9a6
LL
1513 'upload_date': '20151119',
1514 'uploader_id': 'IronSoulElf',
ec85ded8 1515 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1516 'uploader': 'IronSoulElf',
11f9be09 1517 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1518 'track': 'Dark Walk',
1519 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1520 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1521 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1522 'categories': ['Film & Animation'],
1523 'view_count': int,
1524 'live_status': 'not_live',
1525 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1526 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1527 'tags': 'count:13',
1528 'availability': 'public',
1529 'channel': 'IronSoulElf',
1530 'playable_in_embed': True,
1531 'like_count': int,
1532 'age_limit': 0,
6c73052c 1533 'channel_follower_count': int
0e49d9a6
LL
1534 },
1535 'params': {
1536 'skip_download': True,
1537 },
1538 },
61f92af1 1539 {
067aa17e 1540 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1541 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1542 'only_matching': True,
1543 },
313dfc45
LL
1544 {
1545 # Video with yt:stretch=17:0
1546 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1547 'info_dict': {
1548 'id': 'Q39EVAstoRM',
1549 'ext': 'mp4',
1550 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1551 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1552 'upload_date': '20151107',
1553 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1554 'uploader': 'CH GAMER DROID',
1555 },
1556 'params': {
1557 'skip_download': True,
1558 },
be49068d 1559 'skip': 'This video does not exist.',
313dfc45 1560 },
201c1459 1561 {
1562 # Video with incomplete 'yt:stretch=16:'
1563 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1564 'only_matching': True,
1565 },
7caf9830
S
1566 {
1567 # Video licensed under Creative Commons
1568 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1569 'info_dict': {
1570 'id': 'M4gD1WSo5mA',
1571 'ext': 'mp4',
1572 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1573 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1574 'duration': 721,
7caf9830
S
1575 'upload_date': '20150127',
1576 'uploader_id': 'BerkmanCenter',
ec85ded8 1577 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1578 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1579 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1580 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1581 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1582 'like_count': int,
1583 'age_limit': 0,
1584 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1585 'channel': 'The Berkman Klein Center for Internet & Society',
1586 'availability': 'public',
1587 'view_count': int,
1588 'categories': ['Education'],
1589 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1590 'live_status': 'not_live',
1591 'playable_in_embed': True,
6c73052c 1592 'channel_follower_count': int
7caf9830
S
1593 },
1594 'params': {
1595 'skip_download': True,
1596 },
1597 },
fd050249
S
1598 {
1599 # Channel-like uploader_url
1600 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1601 'info_dict': {
1602 'id': 'eQcmzGIKrzg',
1603 'ext': 'mp4',
1604 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1605 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1606 'duration': 4060,
fd050249 1607 'upload_date': '20151119',
eb6793ba 1608 'uploader': 'Bernie Sanders',
fd050249 1609 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1610 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1611 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1612 'playable_in_embed': True,
1613 'tags': 'count:12',
1614 'like_count': int,
1615 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1616 'age_limit': 0,
1617 'availability': 'public',
1618 'categories': ['News & Politics'],
1619 'channel': 'Bernie Sanders',
1620 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1621 'view_count': int,
1622 'live_status': 'not_live',
1623 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1624 'channel_follower_count': int
fd050249
S
1625 },
1626 'params': {
1627 'skip_download': True,
1628 },
1629 },
040ac686
S
1630 {
1631 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1632 'only_matching': True,
7f29cf54
S
1633 },
1634 {
067aa17e 1635 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1636 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1637 'only_matching': True,
6496ccb4
S
1638 },
1639 {
1640 # Rental video preview
1641 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1642 'info_dict': {
1643 'id': 'uGpuVWrhIzE',
1644 'ext': 'mp4',
1645 'title': 'Piku - Trailer',
1646 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1647 'upload_date': '20150811',
1648 'uploader': 'FlixMatrix',
1649 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1650 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1651 'license': 'Standard YouTube License',
1652 },
1653 'params': {
1654 'skip_download': True,
1655 },
eb6793ba 1656 'skip': 'This video is not available.',
022a5d66 1657 },
12afdc2a
S
1658 {
1659 # YouTube Red video with episode data
1660 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1661 'info_dict': {
1662 'id': 'iqKdEhx-dD4',
1663 'ext': 'mp4',
1664 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1665 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1666 'duration': 2085,
12afdc2a
S
1667 'upload_date': '20170118',
1668 'uploader': 'Vsauce',
1669 'uploader_id': 'Vsauce',
1670 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1671 'series': 'Mind Field',
1672 'season_number': 1,
1673 'episode_number': 1,
976ae3ea 1674 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1675 'tags': 'count:12',
1676 'view_count': int,
1677 'availability': 'public',
1678 'age_limit': 0,
1679 'channel': 'Vsauce',
1680 'episode': 'Episode 1',
1681 'categories': ['Entertainment'],
1682 'season': 'Season 1',
1683 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1684 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1685 'like_count': int,
1686 'playable_in_embed': True,
1687 'live_status': 'not_live',
6c73052c 1688 'channel_follower_count': int
12afdc2a
S
1689 },
1690 'params': {
1691 'skip_download': True,
1692 },
1693 'expected_warnings': [
1694 'Skipping DASH manifest',
1695 ],
1696 },
c7121fa7
S
1697 {
1698 # The following content has been identified by the YouTube community
1699 # as inappropriate or offensive to some audiences.
1700 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1701 'info_dict': {
1702 'id': '6SJNVb0GnPI',
1703 'ext': 'mp4',
1704 'title': 'Race Differences in Intelligence',
1705 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1706 'duration': 965,
1707 'upload_date': '20140124',
1708 'uploader': 'New Century Foundation',
1709 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1710 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1711 },
1712 'params': {
1713 'skip_download': True,
1714 },
545cc85d 1715 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1716 },
022a5d66
S
1717 {
1718 # itag 212
1719 'url': '1t24XAntNCY',
1720 'only_matching': True,
fd5c4aab
S
1721 },
1722 {
1723 # geo restricted to JP
1724 'url': 'sJL6WA-aGkQ',
1725 'only_matching': True,
1726 },
cd5a74a2
S
1727 {
1728 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1729 'only_matching': True,
1730 },
bc2ca1bb 1731 {
1732 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1733 'only_matching': True,
1734 },
1735 {
1736 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1737 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1738 'only_matching': True,
1739 },
825cd268
RA
1740 {
1741 # DRM protected
1742 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1743 'only_matching': True,
4fe54c12
S
1744 },
1745 {
1746 # Video with unsupported adaptive stream type formats
1747 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1748 'info_dict': {
1749 'id': 'Z4Vy8R84T1U',
1750 'ext': 'mp4',
1751 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1752 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1753 'duration': 433,
1754 'upload_date': '20130923',
1755 'uploader': 'Amelia Putri Harwita',
1756 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1757 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1758 'formats': 'maxcount:10',
1759 },
1760 'params': {
1761 'skip_download': True,
1762 'youtube_include_dash_manifest': False,
1763 },
5429d6a9 1764 'skip': 'not actual anymore',
5caabd3c 1765 },
1766 {
822b9d9c 1767 # Youtube Music Auto-generated description
5caabd3c 1768 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1769 'info_dict': {
1770 'id': 'MgNrAu2pzNs',
1771 'ext': 'mp4',
1772 'title': 'Voyeur Girl',
1773 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1774 'upload_date': '20190312',
5429d6a9
S
1775 'uploader': 'Stephen - Topic',
1776 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1777 'artist': 'Stephen',
1778 'track': 'Voyeur Girl',
1779 'album': 'it\'s too much love to know my dear',
1780 'release_date': '20190313',
1781 'release_year': 2019,
976ae3ea 1782 'alt_title': 'Voyeur Girl',
1783 'view_count': int,
1784 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1785 'playable_in_embed': True,
1786 'like_count': int,
1787 'categories': ['Music'],
1788 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1789 'channel': 'Stephen',
1790 'availability': 'public',
1791 'creator': 'Stephen',
1792 'duration': 169,
1793 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1794 'age_limit': 0,
1795 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1796 'tags': 'count:11',
1797 'live_status': 'not_live',
6c73052c 1798 'channel_follower_count': int
5caabd3c 1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 },
66b48727
RA
1804 {
1805 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1806 'only_matching': True,
1807 },
011e75e6
S
1808 {
1809 # invalid -> valid video id redirection
1810 'url': 'DJztXj2GPfl',
1811 'info_dict': {
1812 'id': 'DJztXj2GPfk',
1813 'ext': 'mp4',
1814 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1815 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1816 'upload_date': '20090125',
1817 'uploader': 'Prochorowka',
1818 'uploader_id': 'Prochorowka',
1819 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1820 'artist': 'Panjabi MC',
1821 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1822 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1823 },
1824 'params': {
1825 'skip_download': True,
1826 },
545cc85d 1827 'skip': 'Video unavailable',
ea74e00b
DP
1828 },
1829 {
1830 # empty description results in an empty string
1831 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1832 'info_dict': {
1833 'id': 'x41yOUIvK2k',
1834 'ext': 'mp4',
1835 'title': 'IMG 3456',
1836 'description': '',
1837 'upload_date': '20170613',
1838 'uploader_id': 'ElevageOrVert',
1839 'uploader': 'ElevageOrVert',
976ae3ea 1840 'view_count': int,
1841 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1842 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1843 'like_count': int,
1844 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1845 'tags': [],
1846 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1847 'availability': 'public',
1848 'age_limit': 0,
1849 'categories': ['Pets & Animals'],
1850 'duration': 7,
1851 'playable_in_embed': True,
1852 'live_status': 'not_live',
1853 'channel': 'ElevageOrVert',
6c73052c 1854 'channel_follower_count': int
ea74e00b
DP
1855 },
1856 'params': {
1857 'skip_download': True,
1858 },
1859 },
a0566bbf 1860 {
29f7c58a 1861 # with '};' inside yt initial data (see [1])
1862 # see [2] for an example with '};' inside ytInitialPlayerResponse
1863 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1864 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1865 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1866 'info_dict': {
1867 'id': 'CHqg6qOn4no',
1868 'ext': 'mp4',
1869 'title': 'Part 77 Sort a list of simple types in c#',
1870 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1871 'upload_date': '20130831',
1872 'uploader_id': 'kudvenkat',
1873 'uploader': 'kudvenkat',
976ae3ea 1874 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1875 'like_count': int,
1876 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1877 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1878 'live_status': 'not_live',
1879 'categories': ['Education'],
1880 'availability': 'public',
1881 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1882 'tags': 'count:12',
1883 'playable_in_embed': True,
1884 'age_limit': 0,
1885 'view_count': int,
1886 'duration': 522,
1887 'channel': 'kudvenkat',
6c73052c 1888 'channel_follower_count': int
a0566bbf 1889 },
1890 'params': {
1891 'skip_download': True,
1892 },
1893 },
29f7c58a 1894 {
1895 # another example of '};' in ytInitialData
1896 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1897 'only_matching': True,
1898 },
1899 {
1900 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1901 'only_matching': True,
1902 },
545cc85d 1903 {
cc2db878 1904 # https://github.com/ytdl-org/youtube-dl/pull/28094
1905 'url': 'OtqTfy26tG0',
1906 'info_dict': {
1907 'id': 'OtqTfy26tG0',
1908 'ext': 'mp4',
1909 'title': 'Burn Out',
1910 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1911 'upload_date': '20141120',
1912 'uploader': 'The Cinematic Orchestra - Topic',
1913 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1914 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1915 'artist': 'The Cinematic Orchestra',
1916 'track': 'Burn Out',
1917 'album': 'Every Day',
976ae3ea 1918 'like_count': int,
1919 'live_status': 'not_live',
1920 'alt_title': 'Burn Out',
1921 'duration': 614,
1922 'age_limit': 0,
1923 'view_count': int,
1924 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1925 'creator': 'The Cinematic Orchestra',
1926 'channel': 'The Cinematic Orchestra',
1927 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1928 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1929 'availability': 'public',
1930 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1931 'categories': ['Music'],
1932 'playable_in_embed': True,
6c73052c 1933 'channel_follower_count': int
cc2db878 1934 },
1935 'params': {
1936 'skip_download': True,
1937 },
545cc85d 1938 },
bc2ca1bb 1939 {
1940 # controversial video, only works with bpctr when authenticated with cookies
1941 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1942 'only_matching': True,
1943 },
a1a7907b 1944 {
1945 # controversial video, requires bpctr/contentCheckOk
1946 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1947 'info_dict': {
1948 'id': 'SZJvDhaSDnc',
1949 'ext': 'mp4',
1950 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1951 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1952 'uploader': 'CBS Mornings',
11f9be09 1953 'uploader_id': 'CBSThisMorning',
a1a7907b 1954 'upload_date': '20140716',
976ae3ea 1955 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1956 'duration': 170,
1957 'categories': ['News & Politics'],
1958 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1959 'view_count': int,
1960 'channel': 'CBS Mornings',
1961 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1962 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1963 'age_limit': 18,
1964 'availability': 'needs_auth',
1965 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1966 'like_count': int,
1967 'live_status': 'not_live',
1968 'playable_in_embed': True,
6c73052c 1969 'channel_follower_count': int
a1a7907b 1970 }
1971 },
f7ad7160 1972 {
1973 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1974 'url': 'cBvYw8_A0vQ',
1975 'info_dict': {
1976 'id': 'cBvYw8_A0vQ',
1977 'ext': 'mp4',
1978 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1979 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1980 'upload_date': '20201120',
1981 'uploader': 'Walk around Japan',
1982 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1983 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1984 'duration': 1456,
1985 'categories': ['Travel & Events'],
1986 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1987 'view_count': int,
1988 'channel': 'Walk around Japan',
1989 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1990 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1991 'age_limit': 0,
1992 'availability': 'public',
1993 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1994 'live_status': 'not_live',
1995 'playable_in_embed': True,
6c73052c 1996 'channel_follower_count': int
f7ad7160 1997 },
1998 'params': {
1999 'skip_download': True,
2000 },
0fb983f6 2001 }, {
2002 # Has multiple audio streams
2003 'url': 'WaOKSUlf4TM',
2004 'only_matching': True
9297939e 2005 }, {
2006 # Requires Premium: has format 141 when requested using YTM url
2007 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2008 'only_matching': True
2009 }, {
120916da 2010 # multiple subtitles with same lang_code
2011 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2012 'only_matching': True,
109dd3b2 2013 }, {
2014 # Force use android client fallback
2015 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2016 'info_dict': {
2017 'id': 'YOelRv7fMxY',
11f9be09 2018 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2019 'ext': '3gp',
2020 'upload_date': '20210624',
2021 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2022 'uploader': 'colinfurze',
11f9be09 2023 'uploader_id': 'colinfurze',
109dd3b2 2024 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2025 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2026 'duration': 596,
2027 'categories': ['Entertainment'],
2028 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2029 'view_count': int,
2030 'channel': 'colinfurze',
2031 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2032 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2033 'age_limit': 0,
2034 'availability': 'public',
2035 'like_count': int,
2036 'live_status': 'not_live',
2037 'playable_in_embed': True,
6c73052c 2038 'channel_follower_count': int
109dd3b2 2039 },
2040 'params': {
2041 'format': '17', # 3gp format available on android
2042 'extractor_args': {'youtube': {'player_client': ['android']}},
2043 },
120916da 2044 },
109dd3b2 2045 {
2046 # Skip download of additional client configs (remix client config in this case)
2047 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2048 'only_matching': True,
2049 'params': {
2050 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2051 },
8fc54b12 2052 }, {
2053 # shorts
2054 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2055 'only_matching': True,
9222c381 2056 }, {
2057 'note': 'Storyboards',
2058 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2059 'info_dict': {
2060 'id': '5KLPxDtMqe8',
2061 'ext': 'mhtml',
2062 'format_id': 'sb0',
2063 'title': 'Your Brain is Plastic',
2064 'uploader_id': 'scishow',
2065 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2066 'upload_date': '20140324',
2067 'uploader': 'SciShow',
976ae3ea 2068 'like_count': int,
2069 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2070 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2071 'view_count': int,
2072 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2073 'playable_in_embed': True,
2074 'tags': 'count:12',
2075 'uploader_url': 'http://www.youtube.com/user/scishow',
2076 'availability': 'public',
2077 'channel': 'SciShow',
2078 'live_status': 'not_live',
2079 'duration': 248,
2080 'categories': ['Education'],
2081 'age_limit': 0,
6c73052c 2082 'channel_follower_count': int
9222c381 2083 }, 'params': {'format': 'mhtml', 'skip_download': True}
2084 }
2eb88d95
PH
2085 ]
2086
201c1459 2087 @classmethod
2088 def suitable(cls, url):
4dfbf869 2089 from ..utils import parse_qs
2090
201c1459 2091 qs = parse_qs(url)
2092 if qs.get('list', [None])[0]:
2093 return False
2094 return super(YoutubeIE, cls).suitable(url)
2095
e0df6211
PH
2096 def __init__(self, *args, **kwargs):
2097 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2098 self._code_cache = {}
83799698 2099 self._player_cache = {}
e0df6211 2100
adbc4ec4 2101 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2102 lock = threading.Lock()
2103
2104 is_live = True
185bf310 2105 start_time = time.time()
adbc4ec4
THD
2106 formats = [f for f in formats if f.get('is_from_start')]
2107
185bf310 2108 def refetch_manifest(format_id, delay):
2109 nonlocal formats, start_time, is_live
2110 if time.time() <= start_time + delay:
adbc4ec4
THD
2111 return
2112
2113 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2114 video_details = traverse_obj(
2115 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2116 microformats = traverse_obj(
2117 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2118 expected_type=dict, default=[])
2119 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2120 start_time = time.time()
adbc4ec4 2121
185bf310 2122 def mpd_feed(format_id, delay):
adbc4ec4
THD
2123 """
2124 @returns (manifest_url, manifest_stream_number, is_live) or None
2125 """
2126 with lock:
185bf310 2127 refetch_manifest(format_id, delay)
adbc4ec4
THD
2128
2129 f = next((f for f in formats if f['format_id'] == format_id), None)
2130 if not f:
185bf310 2131 if not is_live:
2132 self.to_screen(f'{video_id}: Video is no longer live')
2133 else:
2134 self.report_warning(
2135 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2136 return None
2137 return f['manifest_url'], f['manifest_stream_number'], is_live
2138
2139 for f in formats:
a539f065 2140 f['is_live'] = True
adbc4ec4
THD
2141 f['protocol'] = 'http_dash_segments_generator'
2142 f['fragments'] = functools.partial(
2143 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2144
2145 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2146 FETCH_SPAN, MAX_DURATION = 5, 432000
2147
2148 mpd_url, stream_number, is_live = None, None, True
2149
2150 begin_index = 0
2151 download_start_time = ctx.get('start') or time.time()
2152
2153 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2154 if lack_early_segments:
2155 self.report_warning(bug_reports_message(
2156 'Starting download from the last 120 hours of the live stream since '
2157 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2158 lack_early_segments = True
2159
2160 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2161 fragments, fragment_base_url = None, None
2162
a539f065 2163 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2164 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2165 # Obtain from MPD's maximum seq value
2166 old_mpd_url = mpd_url
185bf310 2167 last_error = ctx.pop('last_error', None)
a539f065 2168 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2169 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2170 or (mpd_url, stream_number, False))
2171 if not refresh_sequence:
2172 if expire_fast and not is_live:
2173 return False, last_seq
2174 elif old_mpd_url == mpd_url:
2175 return True, last_seq
adbc4ec4
THD
2176 try:
2177 fmts, _ = self._extract_mpd_formats_and_subtitles(
2178 mpd_url, None, note=False, errnote=False, fatal=False)
2179 except ExtractorError:
2180 fmts = None
2181 if not fmts:
a539f065 2182 no_fragment_score += 2
adbc4ec4
THD
2183 return False, last_seq
2184 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2185 fragments = fmt_info['fragments']
2186 fragment_base_url = fmt_info['fragment_base_url']
2187 assert fragment_base_url
2188
2189 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2190 return True, _last_seq
2191
2192 while is_live:
2193 fetch_time = time.time()
2194 if no_fragment_score > 30:
2195 return
2196 if last_segment_url:
2197 # Obtain from "X-Head-Seqnum" header value from each segment
2198 try:
2199 urlh = self._request_webpage(
2200 last_segment_url, None, note=False, errnote=False, fatal=False)
2201 except ExtractorError:
2202 urlh = None
2203 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2204 if last_seq is None:
a539f065 2205 no_fragment_score += 2
adbc4ec4
THD
2206 last_segment_url = None
2207 continue
2208 else:
a539f065
LNO
2209 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2210 no_fragment_score += 2
185bf310 2211 if not should_continue:
adbc4ec4
THD
2212 continue
2213
2214 if known_idx > last_seq:
2215 last_segment_url = None
2216 continue
2217
2218 last_seq += 1
2219
2220 if begin_index < 0 and known_idx < 0:
2221 # skip from the start when it's negative value
2222 known_idx = last_seq + begin_index
2223 if lack_early_segments:
2224 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2225 try:
2226 for idx in range(known_idx, last_seq):
2227 # do not update sequence here or you'll get skipped some part of it
a539f065 2228 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2229 if not should_continue:
adbc4ec4
THD
2230 known_idx = idx - 1
2231 raise ExtractorError('breaking out of outer loop')
2232 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2233 yield {
2234 'url': last_segment_url,
2235 }
2236 if known_idx == last_seq:
2237 no_fragment_score += 5
2238 else:
2239 no_fragment_score = 0
2240 known_idx = last_seq
2241 except ExtractorError:
2242 continue
2243
2244 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2245
b6de707d 2246 def _extract_player_url(self, *ytcfgs, webpage=None):
2247 player_url = traverse_obj(
2248 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2249 get_all=False, expected_type=compat_str)
11f9be09 2250 if not player_url:
b6de707d 2251 return
60f393e4 2252 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2253
b6de707d 2254 def _download_player_url(self, video_id, fatal=False):
2255 res = self._download_webpage(
2256 'https://www.youtube.com/iframe_api',
2257 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2258 if res:
2259 player_version = self._search_regex(
2260 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2261 if player_version:
2262 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2263
60064c53
PH
2264 def _signature_cache_id(self, example_sig):
2265 """ Return a string representation of a signature """
78caa52a 2266 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2267
e40c758c
S
2268 @classmethod
2269 def _extract_player_info(cls, player_url):
2270 for player_re in cls._PLAYER_INFO_RE:
2271 id_m = re.search(player_re, player_url)
2272 if id_m:
2273 break
2274 else:
c081b35c 2275 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2276 return id_m.group('id')
e40c758c 2277
404f611f 2278 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2279 player_id = self._extract_player_info(player_url)
2280 if player_id not in self._code_cache:
1276a43a 2281 code = self._download_webpage(
109dd3b2 2282 player_url, video_id, fatal=fatal,
2283 note='Downloading player ' + player_id,
2284 errnote='Download of %s failed' % player_url)
1276a43a 2285 if code:
2286 self._code_cache[player_id] = code
404f611f 2287 return self._code_cache.get(player_id)
109dd3b2 2288
e40c758c 2289 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2290 player_id = self._extract_player_info(player_url)
e0df6211 2291
c4417ddb 2292 # Read from filesystem cache
545cc85d 2293 func_id = 'js_%s_%s' % (
2294 player_id, self._signature_cache_id(example_sig))
c4417ddb 2295 assert os.path.basename(func_id) == func_id
a0e07d31 2296
69ea8ca4 2297 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2298 if cache_spec is not None:
78caa52a 2299 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2300
404f611f 2301 code = self._load_player(video_id, player_url)
2302 if code:
109dd3b2 2303 res = self._parse_sig_js(code)
e0df6211 2304
109dd3b2 2305 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2306 cache_res = res(test_string)
2307 cache_spec = [ord(c) for c in cache_res]
83799698 2308
109dd3b2 2309 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2310 return res
83799698 2311
60064c53 2312 def _print_sig_code(self, func, example_sig):
404f611f 2313 if not self.get_param('youtube_print_sig_code'):
2314 return
2315
edf3e38e
PH
2316 def gen_sig_code(idxs):
2317 def _genslice(start, end, step):
78caa52a 2318 starts = '' if start == 0 else str(start)
8bcc8756 2319 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2320 steps = '' if step == 1 else (':%d' % step)
78caa52a 2321 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2322
2323 step = None
7af808a5
PH
2324 # Quelch pyflakes warnings - start will be set when step is set
2325 start = '(Never used)'
edf3e38e
PH
2326 for i, prev in zip(idxs[1:], idxs[:-1]):
2327 if step is not None:
2328 if i - prev == step:
2329 continue
2330 yield _genslice(start, prev, step)
2331 step = None
2332 continue
2333 if i - prev in [-1, 1]:
2334 step = i - prev
2335 start = prev
2336 continue
2337 else:
78caa52a 2338 yield 's[%d]' % prev
edf3e38e 2339 if step is None:
78caa52a 2340 yield 's[%d]' % i
edf3e38e
PH
2341 else:
2342 yield _genslice(start, i, step)
2343
78caa52a 2344 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2345 cache_res = func(test_string)
edf3e38e 2346 cache_spec = [ord(c) for c in cache_res]
78caa52a 2347 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2348 signature_id_tuple = '(%s)' % (
2349 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2350 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2351 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2352 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2353
e0df6211
PH
2354 def _parse_sig_js(self, jscode):
2355 funcname = self._search_regex(
abefc03f
S
2356 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2357 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
858a65ec
P
2358 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2359 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2360 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}\(a,\d+\)',
2361 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\(\s*""\s*\)',
31ce6e99 2362 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2363 # Obsolete patterns
2364 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2365 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2366 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2367 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2368 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2369 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2370 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2371 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2372 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2373
2374 jsi = JSInterpreter(jscode)
2375 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2376 return lambda s: initial_function([s])
2377
545cc85d 2378 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2379 """Turn the encrypted s field into a working signature"""
6b37f0be 2380
c8bf86d5 2381 if player_url is None:
69ea8ca4 2382 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2383
c8bf86d5 2384 try:
62af3a0e 2385 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2386 if player_id not in self._player_cache:
2387 func = self._extract_signature_function(
60064c53 2388 video_id, player_url, s
c8bf86d5
PH
2389 )
2390 self._player_cache[player_id] = func
2391 func = self._player_cache[player_id]
404f611f 2392 self._print_sig_code(func, s)
c8bf86d5
PH
2393 return func(s)
2394 except Exception as e:
404f611f 2395 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2396
2397 def _decrypt_nsig(self, s, video_id, player_url):
2398 """Turn the encrypted n field into a working signature"""
2399 if player_url is None:
2400 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2401 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2402
2403 sig_id = ('nsig_value', s)
2404 if sig_id in self._player_cache:
2405 return self._player_cache[sig_id]
2406
2407 try:
2408 player_id = ('nsig', player_url)
2409 if player_id not in self._player_cache:
2410 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2411 func = self._player_cache[player_id]
2412 self._player_cache[sig_id] = func(s)
2413 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2414 return self._player_cache[sig_id]
2415 except Exception as e:
aa9369a2 2416 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2417
2418 def _extract_n_function_name(self, jscode):
48416bc4 2419 nfunc, idx = self._search_regex(
c571b3a6 2420 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2421 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2422 if not idx:
2423 return nfunc
2424 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2425 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2426 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2427
2428 def _extract_n_function(self, video_id, player_url):
2429 player_id = self._extract_player_info(player_url)
2430 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2431
2432 if func_code:
2433 jsi = JSInterpreter(func_code)
2434 else:
2435 jscode = self._load_player(video_id, player_url)
2436 funcname = self._extract_n_function_name(jscode)
2437 jsi = JSInterpreter(jscode)
2438 func_code = jsi.extract_function_code(funcname)
2439 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2440
2441 if self.get_param('youtube_print_sig_code'):
2442 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2443
2444 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2445
109dd3b2 2446 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2447 """
2448 Extract signatureTimestamp (sts)
2449 Required to tell API what sig/player version is in use.
2450 """
2451 sts = None
2452 if isinstance(ytcfg, dict):
2453 sts = int_or_none(ytcfg.get('STS'))
2454
2455 if not sts:
2456 # Attempt to extract from player
2457 if player_url is None:
2458 error_msg = 'Cannot extract signature timestamp without player_url.'
2459 if fatal:
2460 raise ExtractorError(error_msg)
2461 self.report_warning(error_msg)
2462 return
404f611f 2463 code = self._load_player(video_id, player_url, fatal=fatal)
2464 if code:
109dd3b2 2465 sts = int_or_none(self._search_regex(
2466 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2467 'JS player signature timestamp', group='sts', fatal=fatal))
2468 return sts
2469
11f9be09 2470 def _mark_watched(self, video_id, player_responses):
9222c381 2471 playback_url = get_first(
2472 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2473 expected_type=url_or_none)
d77ab8e2 2474 if not playback_url:
352d63fd 2475 self.report_warning('Unable to mark watched')
d77ab8e2
S
2476 return
2477 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2478 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2479
2480 # cpn generation algorithm is reverse engineered from base.js.
2481 # In fact it works even with dummy cpn.
2482 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2483 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2484
2485 qs.update({
2486 'ver': ['2'],
2487 'cpn': [cpn],
2488 })
2489 playback_url = compat_urlparse.urlunparse(
15707c7e 2490 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2491
2492 self._download_webpage(
2493 playback_url, video_id, 'Marking watched',
2494 'Unable to mark watched', fatal=False)
2495
66c9fa36
S
2496 @staticmethod
2497 def _extract_urls(webpage):
2498 # Embedded YouTube player
2499 entries = [
2500 unescapeHTML(mobj.group('url'))
2501 for mobj in re.finditer(r'''(?x)
2502 (?:
2503 <iframe[^>]+?src=|
2504 data-video-url=|
2505 <embed[^>]+?src=|
2506 embedSWF\(?:\s*|
2507 <object[^>]+data=|
2508 new\s+SWFObject\(
2509 )
2510 (["\'])
2511 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2512 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2513 \1''', webpage)]
2514
2515 # lazyYT YouTube embed
2516 entries.extend(list(map(
2517 unescapeHTML,
2518 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2519
2520 # Wordpress "YouTube Video Importer" plugin
2521 matches = re.findall(r'''(?x)<div[^>]+
2522 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2523 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2524 entries.extend(m[-1] for m in matches)
2525
2526 return entries
2527
2528 @staticmethod
2529 def _extract_url(webpage):
2530 urls = YoutubeIE._extract_urls(webpage)
2531 return urls[0] if urls else None
2532
97665381
PH
2533 @classmethod
2534 def extract_id(cls, url):
2535 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2536 if mobj is None:
69ea8ca4 2537 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2538 return mobj.group('id')
c5e8d7af 2539
7c365c21 2540 def _extract_chapters_from_json(self, data, duration):
2541 chapter_list = traverse_obj(
2542 data, (
2543 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2544 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2545 ), expected_type=list)
2546
2547 return self._extract_chapters(
2548 chapter_list,
2549 chapter_time=lambda chapter: float_or_none(
2550 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2551 chapter_title=lambda chapter: traverse_obj(
2552 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2553 duration=duration)
2554
2555 def _extract_chapters_from_engagement_panel(self, data, duration):
2556 content_list = traverse_obj(
8bdd16b4 2557 data,
7c365c21 2558 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2559 expected_type=list, default=[])
052e1350 2560 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2561 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2562
2563 return next((
2564 filter(None, (
2565 self._extract_chapters(
2566 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2567 chapter_time, chapter_title, duration)
2568 for contents in content_list
2569 ))), [])
2570
2571 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2572 chapters = []
7c365c21 2573 last_chapter = {'start_time': 0}
2574 for idx, chapter in enumerate(chapter_list or []):
2575 title = chapter_title(chapter)
84213ea8
S
2576 start_time = chapter_time(chapter)
2577 if start_time is None:
2578 continue
7c365c21 2579 last_chapter['end_time'] = start_time
2580 if start_time < last_chapter['start_time']:
2581 if idx == 1:
2582 chapters.pop()
2583 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2584 else:
2585 self.report_warning(f'Invalid start time for chapter "{title}"')
2586 continue
2587 last_chapter = {'start_time': start_time, 'title': title}
2588 chapters.append(last_chapter)
2589 last_chapter['end_time'] = duration
84213ea8
S
2590 return chapters
2591
545cc85d 2592 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2593 return self._parse_json(self._search_regex(
2594 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2595 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2596
a1c5d2ca
M
2597 def _extract_comment(self, comment_renderer, parent=None):
2598 comment_id = comment_renderer.get('commentId')
2599 if not comment_id:
2600 return
fe93e2c4 2601
052e1350 2602 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2603
49bd8c66 2604 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2605 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2606 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2607 author_id = try_get(comment_renderer,
2608 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2609
49bd8c66 2610 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2611 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2612 author_thumbnail = try_get(comment_renderer,
2613 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2614
2615 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2616 is_favorited = 'creatorHeart' in (try_get(
2617 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2618 return {
2619 'id': comment_id,
2620 'text': text,
d92f5d5a 2621 'timestamp': timestamp,
a1c5d2ca
M
2622 'time_text': time_text,
2623 'like_count': votes,
97524332 2624 'is_favorited': is_favorited,
a1c5d2ca
M
2625 'author': author,
2626 'author_id': author_id,
2627 'author_thumbnail': author_thumbnail,
2628 'author_is_uploader': author_is_uploader,
2629 'parent': parent or 'root'
2630 }
2631
46383212 2632 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2633
2634 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2635
2636 def extract_header(contents):
2d6659b9 2637 _continuation = None
2638 for content in contents:
46383212 2639 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2640 expected_comment_count = self._get_count(
2641 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2642
2d6659b9 2643 if expected_comment_count:
46383212 2644 tracker['est_total'] = expected_comment_count
2645 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2646 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2647
2648 sort_menu_item = try_get(
2649 comments_header_renderer,
2650 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2651 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2652
2653 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2654 if not _continuation:
2655 continue
2656
46383212 2657 sort_text = str_or_none(sort_menu_item.get('title'))
2658 if not sort_text:
2d6659b9 2659 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2660 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2661 break
a2160aa4 2662 return _continuation
a1c5d2ca 2663
2d6659b9 2664 def extract_thread(contents):
a1c5d2ca 2665 if not parent:
46383212 2666 tracker['current_page_thread'] = 0
a1c5d2ca 2667 for content in contents:
46383212 2668 if not parent and tracker['total_parent_comments'] >= max_parents:
2669 yield
a1c5d2ca 2670 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2671 comment_renderer = get_first(
2672 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2673 expected_type=dict, default={})
a1c5d2ca 2674
a1c5d2ca
M
2675 comment = self._extract_comment(comment_renderer, parent)
2676 if not comment:
2677 continue
46383212 2678
2679 tracker['running_total'] += 1
2680 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2681 yield comment
46383212 2682
a1c5d2ca
M
2683 # Attempt to get the replies
2684 comment_replies_renderer = try_get(
2685 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2686
2687 if comment_replies_renderer:
46383212 2688 tracker['current_page_thread'] += 1
a1c5d2ca 2689 comment_entries_iter = self._comment_entries(
99e9e001 2690 comment_replies_renderer, ytcfg, video_id,
46383212 2691 parent=comment.get('id'), tracker=tracker)
2692 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2693 yield reply_comment
2694
46383212 2695 # Keeps track of counts across recursive calls
2696 if not tracker:
2697 tracker = dict(
2698 running_total=0,
2699 est_total=0,
2700 current_page_thread=0,
2701 total_parent_comments=0,
2702 total_reply_comments=0)
2703
2704 # TODO: Deprecated
2d6659b9 2705 # YouTube comments have a max depth of 2
46383212 2706 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2707 if max_depth:
2708 self._downloader.deprecation_warning(
2709 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2710 if max_depth == 1 and parent:
2711 return
a1c5d2ca 2712
46383212 2713 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2714 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2715
46383212 2716 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2717 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2718 if message and not parent:
2719 self.report_warning(message, video_id=video_id)
2720
46383212 2721 response = None
2d6659b9 2722 is_first_continuation = parent is None
a1c5d2ca
M
2723
2724 for page_num in itertools.count(0):
2725 if not continuation:
2726 break
46383212 2727 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2728 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2729 if page_num == 0:
2730 if is_first_continuation:
2731 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2732 else:
2d6659b9 2733 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2734 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2735 else:
2736 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2737 ' ' if parent else '', ' replies' if parent else '',
2738 page_num, comment_prog_str)
2739
2740 response = self._extract_response(
fe93e2c4 2741 item_id=None, query=continuation,
2d6659b9 2742 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2743 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2744
46383212 2745 continuation_contents = traverse_obj(
2746 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2747
2d6659b9 2748 continuation = None
46383212 2749 for continuation_section in continuation_contents:
2750 continuation_items = traverse_obj(
2751 continuation_section,
2752 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2753 get_all=False, expected_type=list) or []
2754 if is_first_continuation:
2755 continuation = extract_header(continuation_items)
2756 is_first_continuation = False
2d6659b9 2757 if continuation:
a1c5d2ca 2758 break
46383212 2759 continue
a1c5d2ca 2760
46383212 2761 for entry in extract_thread(continuation_items):
2762 if not entry:
2763 return
2764 yield entry
2765 continuation = self._extract_continuation({'contents': continuation_items})
2766 if continuation:
2d6659b9 2767 break
a1c5d2ca 2768
a2160aa4 2769 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2770 """Entry for comment extraction"""
2d6659b9 2771 def _real_comment_extract(contents):
aae16f6e 2772 renderer = next((
2773 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2774 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2775 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2776
a2160aa4 2777 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2778 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2779
109dd3b2 2780 @staticmethod
99e9e001 2781 def _get_checkok_params():
2782 return {'contentCheckOk': True, 'racyCheckOk': True}
2783
2784 @classmethod
2785 def _generate_player_context(cls, sts=None):
109dd3b2 2786 context = {
2787 'html5Preference': 'HTML5_PREF_WANTS',
2788 }
2789 if sts is not None:
2790 context['signatureTimestamp'] = sts
2791 return {
2792 'playbackContext': {
2793 'contentPlaybackContext': context
a1a7907b 2794 },
99e9e001 2795 **cls._get_checkok_params()
109dd3b2 2796 }
2797
e7e94f2a
D
2798 @staticmethod
2799 def _is_agegated(player_response):
2800 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2801 return True
e7e94f2a
D
2802
2803 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2804 AGE_GATE_REASONS = (
2805 'confirm your age', 'age-restricted', 'inappropriate', # reason
2806 'age_verification_required', 'age_check_required', # status
2807 )
2808 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2809
2810 @staticmethod
2811 def _is_unplayable(player_response):
2812 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2813
99e9e001 2814 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2815
11f9be09 2816 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2817 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2818 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2819 headers = self.generate_api_headers(
99e9e001 2820 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2821
11f9be09 2822 yt_query = {'videoId': video_id}
2823 yt_query.update(self._generate_player_context(sts))
2824 return self._extract_response(
2825 item_id=video_id, ep='player', query=yt_query,
379e44ed 2826 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2827 default_client=client,
11f9be09 2828 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2829 ) or None
2830
11f9be09 2831 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2832 requested_clients = []
d0d012d4 2833 default = ['android', 'web']
000c15a4 2834 allowed_clients = sorted(
2835 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2836 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2837 for client in self._configuration_arg('player_client'):
2838 if client in allowed_clients:
2839 requested_clients.append(client)
d0d012d4 2840 elif client == 'default':
2841 requested_clients.extend(default)
b4c055ba 2842 elif client == 'all':
2843 requested_clients.extend(allowed_clients)
2844 else:
2845 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2846 if not requested_clients:
d0d012d4 2847 requested_clients = default
cf7e015f 2848
11f9be09 2849 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2850 requested_clients.extend(
e7e94f2a 2851 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2852
11f9be09 2853 return orderedSet(requested_clients)
cf7e015f 2854
c0bc527b
M
2855 def _extract_player_ytcfg(self, client, video_id):
2856 url = {
2857 'web_music': 'https://music.youtube.com',
2858 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2859 }.get(client)
2860 if not url:
2861 return {}
18c7683d 2862 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2863 return self.extract_ytcfg(video_id, webpage) or {}
2864
99e9e001 2865 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2866 initial_pr = None
2867 if webpage:
2868 initial_pr = self._extract_yt_initial_variable(
2869 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2870 video_id, 'initial player response')
6b09401b 2871
c0bc527b
M
2872 original_clients = clients
2873 clients = clients[::-1]
b6de707d 2874 prs = []
e7e94f2a
D
2875
2876 def append_client(client_name):
2877 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2878 clients.append(client_name)
2879
379e44ed 2880 # Android player_response does not have microFormats which are needed for
2881 # extraction of some data. So we return the initial_pr with formats
2882 # stripped out even if not requested by the user
2883 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2884 if initial_pr:
2885 pr = dict(initial_pr)
2886 pr['streamingData'] = None
b6de707d 2887 prs.append(pr)
379e44ed 2888
2889 last_error = None
b6de707d 2890 tried_iframe_fallback = False
2891 player_url = None
c0bc527b
M
2892 while clients:
2893 client = clients.pop()
11f9be09 2894 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2895 if 'configs' not in self._configuration_arg('player_skip'):
2896 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2897
b6de707d 2898 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2899 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2900 if 'js' in self._configuration_arg('player_skip'):
2901 require_js_player = False
2902 player_url = None
2903
2904 if not player_url and not tried_iframe_fallback and require_js_player:
2905 player_url = self._download_player_url(video_id)
2906 tried_iframe_fallback = True
2907
379e44ed 2908 try:
2909 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2910 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2911 except ExtractorError as e:
2912 if last_error:
2913 self.report_warning(last_error)
2914 last_error = e
2915 continue
2916
11f9be09 2917 if pr:
b6de707d 2918 prs.append(pr)
c0bc527b 2919
e7e94f2a 2920 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 2921 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
2922 append_client(client.replace('_agegate', '_creator'))
2923 elif self._is_agegated(pr):
2924 append_client(f'{client}_agegate')
c0bc527b 2925
379e44ed 2926 if last_error:
b6de707d 2927 if not len(prs):
379e44ed 2928 raise last_error
2929 self.report_warning(last_error)
b6de707d 2930 return prs, player_url
11f9be09 2931
2932 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
a0bb6ce5 2933 itags, stream_ids = {}, []
2a9c6dcd 2934 itag_qualities, res_qualities = {}, {}
d3fc8074 2935 q = qualities([
2a9c6dcd 2936 # Normally tiny is the smallest video-only formats. But
2937 # audio-only formats with unknown quality may get tagged as tiny
2938 'tiny',
2939 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 2940 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2941 ])
11f9be09 2942 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
0ad92dfb 2943 approx_duration = max(traverse_obj(streaming_formats, (..., 'approxDurationMs'), expected_type=float_or_none) or [0]) or None
9297939e 2944
545cc85d 2945 for fmt in streaming_formats:
2946 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2947 continue
321bf820 2948
cc2db878 2949 itag = str_or_none(fmt.get('itag'))
9297939e 2950 audio_track = fmt.get('audioTrack') or {}
2951 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2952 if stream_id in stream_ids:
2953 continue
2954
cc2db878 2955 quality = fmt.get('quality')
2a9c6dcd 2956 height = int_or_none(fmt.get('height'))
d3fc8074 2957 if quality == 'tiny' or not quality:
2958 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 2959 # The 3gp format (17) in android client has a quality of "small",
2960 # but is actually worse than other formats
2961 if itag == '17':
2962 quality = 'tiny'
2963 if quality:
2964 if itag:
2965 itag_qualities[itag] = quality
2966 if height:
2967 res_qualities[height] = quality
cc2db878 2968 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2969 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2970 # number of fragment that would subsequently requested with (`&sq=N`)
2971 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2972 continue
2973
545cc85d 2974 fmt_url = fmt.get('url')
2975 if not fmt_url:
2976 sc = compat_parse_qs(fmt.get('signatureCipher'))
2977 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2978 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2979 if not (sc and fmt_url and encrypted_sig):
2980 continue
545cc85d 2981 if not player_url:
201e9eaa 2982 continue
545cc85d 2983 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2984 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2985 fmt_url += '&' + sp + '=' + signature
2986
404f611f 2987 query = parse_qs(fmt_url)
2988 throttled = False
b2916526 2989 if query.get('n'):
404f611f 2990 try:
2991 fmt_url = update_url_query(fmt_url, {
2992 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2993 except ExtractorError as e:
aa9369a2 2994 self.report_warning(
2995 f'nsig extraction failed: You may experience throttling for some formats\n'
2996 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 2997 throttled = True
2998
545cc85d 2999 if itag:
a0bb6ce5 3000 itags[itag] = 'https'
9297939e 3001 stream_ids.append(stream_id)
3002
0ad92dfb 3003 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3004 language_preference = (
3005 10 if audio_track.get('audioIsDefault') and 10
3006 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3007 else -1)
0ad92dfb 3008 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3009 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3010 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) < approx_duration - 10000)
545cc85d 3011 dct = {
3012 'asr': int_or_none(fmt.get('audioSampleRate')),
3013 'filesize': int_or_none(fmt.get('contentLength')),
3014 'format_id': itag,
34921b43 3015 'format_note': join_nonempty(
26e8e044 3016 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3017 ' (default)' if language_preference > 0 else ''),
404f611f 3018 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3019 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3020 'source_preference': -10 if throttled else -1,
a4211baf 3021 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3022 'height': height,
dca3ff4a 3023 'quality': q(quality),
cc2db878 3024 'tbr': tbr,
545cc85d 3025 'url': fmt_url,
2a9c6dcd 3026 'width': int_or_none(fmt.get('width')),
ab6df717 3027 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3028 'desc' if language_preference < -1 else ''),
3029 'language_preference': language_preference,
0ad92dfb 3030 'preference': -10 if is_damaged else None,
545cc85d 3031 }
60bdb7bd 3032 mime_mobj = re.match(
3033 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3034 if mime_mobj:
3035 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3036 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3037 no_audio = dct.get('acodec') == 'none'
3038 no_video = dct.get('vcodec') == 'none'
3039 if no_audio:
3040 dct['vbr'] = tbr
3041 if no_video:
3042 dct['abr'] = tbr
3043 if no_audio or no_video:
545cc85d 3044 dct['downloader_options'] = {
3045 # Youtube throttles chunks >~10M
3046 'http_chunk_size': 10485760,
bf1317d2 3047 }
7c60c33e 3048 if dct.get('ext'):
3049 dct['container'] = dct['ext'] + '_dash'
11f9be09 3050 yield dct
545cc85d 3051
adbc4ec4 3052 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3053 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3054 if not self.get_param('youtube_include_hls_manifest', True):
3055 skip_manifests.append('hls')
3056 get_dash = 'dash' not in skip_manifests and (
3057 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3058 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3059
a0bb6ce5 3060 def process_manifest_format(f, proto, itag):
3061 if itag in itags:
3062 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3063 return False
3064 itag = f'{itag}-{proto}'
3065 if itag:
3066 f['format_id'] = itag
3067 itags[itag] = proto
3068
3069 f['quality'] = next((
3070 q(qdict[val])
e339d25a 3071 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3072 if val in qdict), -1)
3073 return True
2a9c6dcd 3074
11f9be09 3075 for sd in streaming_data:
5d3a0e79 3076 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3077 if hls_manifest_url:
2a9c6dcd 3078 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3079 if process_manifest_format(f, 'hls', self._search_regex(
3080 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3081 yield f
545cc85d 3082
5d3a0e79 3083 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3084 if dash_manifest_url:
2a9c6dcd 3085 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3086 if process_manifest_format(f, 'dash', f['format_id']):
3087 f['filesize'] = int_or_none(self._search_regex(
3088 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3089 if live_from_start:
3090 f['is_from_start'] = True
3091
a0bb6ce5 3092 yield f
11f9be09 3093
720c3099 3094 def _extract_storyboard(self, player_responses, duration):
3095 spec = get_first(
3096 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3097 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3098 if not base_url:
720c3099 3099 return
720c3099 3100 L = len(spec) - 1
3101 for i, args in enumerate(spec):
3102 args = args.split('#')
3103 counts = list(map(int_or_none, args[:5]))
3104 if len(args) != 8 or not all(counts):
3105 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3106 continue
3107 width, height, frame_count, cols, rows = counts
3108 N, sigh = args[6:]
3109
3110 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3111 fragment_count = frame_count / (cols * rows)
3112 fragment_duration = duration / fragment_count
3113 yield {
3114 'format_id': f'sb{i}',
3115 'format_note': 'storyboard',
3116 'ext': 'mhtml',
3117 'protocol': 'mhtml',
3118 'acodec': 'none',
3119 'vcodec': 'none',
3120 'url': url,
3121 'width': width,
3122 'height': height,
3123 'fragments': [{
3124 'path': url.replace('$M', str(j)),
3125 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3126 } for j in range(math.ceil(fragment_count))],
3127 }
3128
adbc4ec4 3129 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3130 webpage = None
3131 if 'webpage' not in self._configuration_arg('player_skip'):
3132 webpage = self._download_webpage(
3133 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3134
3135 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3136
b6de707d 3137 player_responses, player_url = self._extract_player_responses(
11f9be09 3138 self._get_requested_clients(url, smuggled_data),
99e9e001 3139 video_id, webpage, master_ytcfg)
11f9be09 3140
adbc4ec4
THD
3141 return webpage, master_ytcfg, player_responses, player_url
3142
3143 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3144 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3145 is_live = get_first(video_details, 'isLive')
3146 if is_live is None:
3147 is_live = get_first(live_broadcast_details, 'isLiveNow')
3148
3149 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3150 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3151
3152 return live_broadcast_details, is_live, streaming_data, formats
3153
3154 def _real_extract(self, url):
3155 url, smuggled_data = unsmuggle_url(url, {})
3156 video_id = self._match_id(url)
3157
3158 base_url = self.http_scheme() + '//www.youtube.com/'
3159 webpage_url = base_url + 'watch?v=' + video_id
3160
3161 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3162
11f9be09 3163 playability_statuses = traverse_obj(
3164 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3165
3166 trailer_video_id = get_first(
3167 playability_statuses,
3168 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3169 expected_type=str)
3170 if trailer_video_id:
3171 return self.url_result(
3172 trailer_video_id, self.ie_key(), trailer_video_id)
3173
3174 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3175 if webpage else (lambda x: None))
3176
3177 video_details = traverse_obj(
3178 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3179 microformats = traverse_obj(
3180 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3181 expected_type=dict, default=[])
3182 video_title = (
3183 get_first(video_details, 'title')
3184 or self._get_text(microformats, (..., 'title'))
3185 or search_meta(['og:title', 'twitter:title', 'title']))
3186 video_description = get_first(video_details, 'shortDescription')
3187
d89257f3 3188 multifeed_metadata_list = get_first(
3189 player_responses,
3190 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3191 expected_type=str)
3192 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3193 if self.get_param('noplaylist'):
11f9be09 3194 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3195 else:
3196 entries = []
3197 feed_ids = []
3198 for feed in multifeed_metadata_list.split(','):
3199 # Unquote should take place before split on comma (,) since textual
3200 # fields may contain comma as well (see
3201 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3202 feed_data = compat_parse_qs(
3203 compat_urllib_parse_unquote_plus(feed))
3204
3205 def feed_entry(name):
3206 return try_get(
3207 feed_data, lambda x: x[name][0], compat_str)
3208
3209 feed_id = feed_entry('id')
3210 if not feed_id:
3211 continue
3212 feed_title = feed_entry('title')
3213 title = video_title
3214 if feed_title:
3215 title += ' (%s)' % feed_title
3216 entries.append({
3217 '_type': 'url_transparent',
3218 'ie_key': 'Youtube',
3219 'url': smuggle_url(
3220 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3221 {'force_singlefeed': True}),
3222 'title': title,
3223 })
3224 feed_ids.append(feed_id)
3225 self.to_screen(
3226 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3227 % (', '.join(feed_ids), video_id))
3228 return self.playlist_result(
3229 entries, video_id, video_title, video_description)
11f9be09 3230
adbc4ec4 3231 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3232
545cc85d 3233 if not formats:
11f9be09 3234 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3235 self.report_drm(video_id)
11f9be09 3236 pemr = get_first(
3237 playability_statuses,
3238 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3239 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3240 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3241 if subreason:
545cc85d 3242 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3243 countries = get_first(microformats, 'availableCountries')
545cc85d 3244 if not countries:
3245 regions_allowed = search_meta('regionsAllowed')
3246 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3247 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3248 reason += f'. {subreason}'
545cc85d 3249 if reason:
b7da73eb 3250 self.raise_no_formats(reason, expected=True)
bf1317d2 3251
11f9be09 3252 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3253 if not keywords and webpage:
3254 keywords = [
3255 unescapeHTML(m.group('content'))
3256 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3257 for keyword in keywords:
3258 if keyword.startswith('yt:stretch='):
201c1459 3259 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3260 if mobj:
3261 # NB: float is intentional for forcing float division
3262 w, h = (float(v) for v in mobj.groups())
3263 if w > 0 and h > 0:
3264 ratio = w / h
3265 for f in formats:
3266 if f.get('vcodec') != 'none':
3267 f['stretched_ratio'] = ratio
3268 break
a709d873 3269 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3270 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3271 if thumbnail_url:
3272 thumbnails.append({
3273 'url': thumbnail_url,
ff2751ac 3274 })
fccf5021 3275 original_thumbnails = thumbnails.copy()
3276
0ba692ac 3277 # The best resolution thumbnails sometimes does not appear in the webpage
3278 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3279 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3280 thumbnail_names = [
3281 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3282 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3283 'mqdefault', 'mq1', 'mq2', 'mq3',
3284 'default', '1', '2', '3'
3285 ]
cca80fe6 3286 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3287 thumbnails.extend({
3288 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3289 video_id=video_id, name=name, ext=ext,
3290 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3291 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3292 for thumb in thumbnails:
cca80fe6 3293 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3294 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3295 self._remove_duplicate_formats(thumbnails)
fccf5021 3296 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3297
7ea65411 3298 category = get_first(microformats, 'category') or search_meta('genre')
3299 channel_id = str_or_none(
3300 get_first(video_details, 'channelId')
3301 or get_first(microformats, 'externalChannelId')
3302 or search_meta('channelId'))
3303 duration = int_or_none(
3304 get_first(video_details, 'lengthSeconds')
3305 or get_first(microformats, 'lengthSeconds')
3306 or parse_duration(search_meta('duration'))) or None
3307 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3308
3309 live_content = get_first(video_details, 'isLiveContent')
3310 is_upcoming = get_first(video_details, 'isUpcoming')
3311 if is_live is None:
3312 if is_upcoming or live_content is False:
3313 is_live = False
3314 if is_upcoming is None and (live_content or is_live):
3315 is_upcoming = False
adbc4ec4
THD
3316 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3317 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3318 if not duration and live_end_time and live_start_time:
3319 duration = live_end_time - live_start_time
3320
3321 if is_live and self.get_param('live_from_start'):
3322 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3323
720c3099 3324 formats.extend(self._extract_storyboard(player_responses, duration))
3325
3326 # Source is given priority since formats that throttle are given lower source_preference
3327 # When throttling issue is fully fixed, remove this
3328 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3329
545cc85d 3330 info = {
3331 'id': video_id,
39ca3b5c 3332 'title': video_title,
545cc85d 3333 'formats': formats,
3334 'thumbnails': thumbnails,
fccf5021 3335 # The best thumbnail that we are sure exists. Prevents unnecessary
3336 # URL checking if user don't care about getting the best possible thumbnail
3337 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3338 'description': video_description,
3339 'upload_date': unified_strdate(
11f9be09 3340 get_first(microformats, 'uploadDate')
545cc85d 3341 or search_meta('uploadDate')),
11f9be09 3342 'uploader': get_first(video_details, 'author'),
545cc85d 3343 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3344 'uploader_url': owner_profile_url,
3345 'channel_id': channel_id,
e0ddbd02 3346 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3347 'duration': duration,
3348 'view_count': int_or_none(
11f9be09 3349 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3350 or search_meta('interactionCount')),
11f9be09 3351 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3352 'age_limit': 18 if (
11f9be09 3353 get_first(microformats, 'isFamilySafe') is False
545cc85d 3354 or search_meta('isFamilyFriendly') == 'false'
3355 or search_meta('og:restrictions:age') == '18+') else 0,
3356 'webpage_url': webpage_url,
3357 'categories': [category] if category else None,
3358 'tags': keywords,
11f9be09 3359 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3360 'is_live': is_live,
3361 'was_live': (False if is_live or is_upcoming or live_content is False
3362 else None if is_live is None or is_upcoming is None
3363 else live_content),
3364 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3365 'release_timestamp': live_start_time,
545cc85d 3366 }
b477fc13 3367
3944e7af 3368 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3369 if pctr:
ecdc9049 3370 def get_lang_code(track):
3371 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3372 or track.get('languageCode'))
3373
3374 # Converted into dicts to remove duplicates
3375 captions = {
3376 get_lang_code(sub): sub
3377 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3378 translation_languages = {
3379 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3380 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3381
774d79cc 3382 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3383 lang_subs = container.setdefault(lang_code, [])
545cc85d 3384 for fmt in self._SUBTITLE_FORMATS:
3385 query.update({
3386 'fmt': fmt,
3387 })
3388 lang_subs.append({
3389 'ext': fmt,
60f393e4 3390 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3391 'name': sub_name,
545cc85d 3392 })
7e72694b 3393
ecdc9049 3394 subtitles, automatic_captions = {}, {}
3395 for lang_code, caption_track in captions.items():
3396 base_url = caption_track.get('baseUrl')
545cc85d 3397 if not base_url:
3398 continue
ecdc9049 3399 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3400 if caption_track.get('kind') != 'asr':
545cc85d 3401 if not lang_code:
3402 continue
3403 process_language(
ecdc9049 3404 subtitles, base_url, lang_code, lang_name, {})
3405 if not caption_track.get('isTranslatable'):
3406 continue
3944e7af 3407 for trans_code, trans_name in translation_languages.items():
3408 if not trans_code:
545cc85d 3409 continue
ecdc9049 3410 if caption_track.get('kind') != 'asr':
3411 trans_code += f'-{lang_code}'
3412 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3413 # Add an "-orig" label to the original language so that it can be distinguished.
3414 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 3415 if lang_code == f'a-{trans_code}':
3416 process_language(
d49669ac 3417 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3418 # Setting tlang=lang returns damaged subtitles.
3419 # Not using lang_code == f'a-{trans_code}' here for future-proofing
3420 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3421 process_language(automatic_captions, base_url, trans_code, trans_name,
3422 {} if orig_lang == trans_code else {'tlang': trans_code})
ecdc9049 3423 info['automatic_captions'] = automatic_captions
3424 info['subtitles'] = subtitles
7e72694b 3425
545cc85d 3426 parsed_url = compat_urllib_parse_urlparse(url)
3427 for component in [parsed_url.fragment, parsed_url.query]:
3428 query = compat_parse_qs(component)
3429 for k, v in query.items():
3430 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3431 d_k += '_time'
3432 if d_k not in info and k in s_ks:
3433 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3434
3435 # Youtube Music Auto-generated description
822b9d9c 3436 if video_description:
38d70284 3437 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)
822b9d9c 3438 if mobj:
822b9d9c
RA
3439 release_year = mobj.group('release_year')
3440 release_date = mobj.group('release_date')
3441 if release_date:
3442 release_date = release_date.replace('-', '')
3443 if not release_year:
545cc85d 3444 release_year = release_date[:4]
3445 info.update({
3446 'album': mobj.group('album'.strip()),
3447 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3448 'track': mobj.group('track').strip(),
3449 'release_date': release_date,
cc2db878 3450 'release_year': int_or_none(release_year),
545cc85d 3451 })
7e72694b 3452
545cc85d 3453 initial_data = None
3454 if webpage:
3455 initial_data = self._extract_yt_initial_variable(
3456 webpage, self._YT_INITIAL_DATA_RE, video_id,
3457 'yt initial data')
3458 if not initial_data:
99e9e001 3459 query = {'videoId': video_id}
3460 query.update(self._get_checkok_params())
109dd3b2 3461 initial_data = self._extract_response(
3462 item_id=video_id, ep='next', fatal=False,
99e9e001 3463 ytcfg=master_ytcfg, query=query,
3464 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3465 note='Downloading initial data API JSON')
545cc85d 3466
c60ee3a2 3467 try:
3468 # This will error if there is no livechat
3469 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3470 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3471 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3472 'video_id': video_id,
3473 'ext': 'json',
f6745c49 3474 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3475 }]
3476 except (KeyError, IndexError, TypeError):
3477 pass
545cc85d 3478
3479 if initial_data:
7c365c21 3480 info['chapters'] = (
3481 self._extract_chapters_from_json(initial_data, duration)
3482 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3483 or None)
545cc85d 3484
3485 contents = try_get(
3486 initial_data,
3487 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3488 list) or []
3489 for content in contents:
3490 vpir = content.get('videoPrimaryInfoRenderer')
3491 if vpir:
3492 stl = vpir.get('superTitleLink')
3493 if stl:
fe93e2c4 3494 stl = self._get_text(stl)
545cc85d 3495 if try_get(
3496 vpir,
3497 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3498 info['location'] = stl
3499 else:
3500 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3501 if mobj:
3502 info.update({
3503 'series': mobj.group(1),
3504 'season_number': int(mobj.group(2)),
3505 'episode_number': int(mobj.group(3)),
3506 })
3507 for tlb in (try_get(
3508 vpir,
3509 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3510 list) or []):
3511 tbr = tlb.get('toggleButtonRenderer') or {}
3512 for getter, regex in [(
3513 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3514 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3515 lambda x: x['accessibility'],
3516 lambda x: x['accessibilityData']['accessibilityData'],
3517 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3518 label = (try_get(tbr, getter, dict) or {}).get('label')
3519 if label:
3520 mobj = re.match(regex, label)
3521 if mobj:
3522 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3523 break
3524 sbr_tooltip = try_get(
3525 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3526 if sbr_tooltip:
3527 like_count, dislike_count = sbr_tooltip.split(' / ')
3528 info.update({
3529 'like_count': str_to_int(like_count),
3530 'dislike_count': str_to_int(dislike_count),
3531 })
3532 vsir = content.get('videoSecondaryInfoRenderer')
3533 if vsir:
6c73052c 3534 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3535 info.update({
3536 'channel': self._get_text(vor, 'title'),
3537 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3538
545cc85d 3539 rows = try_get(
3540 vsir,
3541 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3542 list) or []
3543 multiple_songs = False
3544 for row in rows:
3545 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3546 multiple_songs = True
3547 break
3548 for row in rows:
3549 mrr = row.get('metadataRowRenderer') or {}
3550 mrr_title = mrr.get('title')
3551 if not mrr_title:
3552 continue
052e1350 3553 mrr_title = self._get_text(mrr, 'title')
3554 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3555 if mrr_title == 'License':
3556 info['license'] = mrr_contents_text
3557 elif not multiple_songs:
3558 if mrr_title == 'Album':
3559 info['album'] = mrr_contents_text
3560 elif mrr_title == 'Artist':
3561 info['artist'] = mrr_contents_text
3562 elif mrr_title == 'Song':
3563 info['track'] = mrr_contents_text
3564
3565 fallbacks = {
3566 'channel': 'uploader',
3567 'channel_id': 'uploader_id',
3568 'channel_url': 'uploader_url',
3569 }
3570 for to, frm in fallbacks.items():
3571 if not info.get(to):
3572 info[to] = info.get(frm)
3573
3574 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3575 v = info.get(s_k)
3576 if v:
3577 info[d_k] = v
b84071c0 3578
11f9be09 3579 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3580 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3581 is_membersonly = None
b28f8d24 3582 is_premium = None
c224251a
M
3583 if initial_data and is_private is not None:
3584 is_membersonly = False
b28f8d24 3585 is_premium = False
47193e02 3586 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3587 badge_labels = set()
3588 for content in contents:
3589 if not isinstance(content, dict):
3590 continue
3591 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3592 for badge_label in badge_labels:
3593 if badge_label.lower() == 'members only':
3594 is_membersonly = True
3595 elif badge_label.lower() == 'premium':
3596 is_premium = True
3597 elif badge_label.lower() == 'unlisted':
3598 is_unlisted = True
c224251a 3599
c224251a
M
3600 info['availability'] = self._availability(
3601 is_private=is_private,
b28f8d24 3602 needs_premium=is_premium,
c224251a
M
3603 needs_subscription=is_membersonly,
3604 needs_auth=info['age_limit'] >= 18,
3605 is_unlisted=None if is_private is None else is_unlisted)
3606
a2160aa4 3607 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3608
11f9be09 3609 self.mark_watched(video_id, player_responses)
d77ab8e2 3610
545cc85d 3611 return info
c5e8d7af 3612
a61fd4cf 3613
a6213a49 3614class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3615
182bda88 3616 @staticmethod
3617 def passthrough_smuggled_data(func):
3618 def _smuggle(entries, smuggled_data):
3619 for entry in entries:
3620 # TODO: Convert URL to music.youtube instead.
3621 # Do we need to passthrough any other smuggled_data?
3622 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3623 yield entry
3624
3625 @functools.wraps(func)
3626 def wrapper(self, url):
3627 url, smuggled_data = unsmuggle_url(url, {})
3628 if self.is_music_url(url):
3629 smuggled_data['is_music_url'] = True
3630 info_dict = func(self, url, smuggled_data)
3631 if smuggled_data and info_dict.get('entries'):
3632 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3633 return info_dict
3634 return wrapper
3635
a6213a49 3636 def _extract_channel_id(self, webpage):
3637 channel_id = self._html_search_meta(
3638 'channelId', webpage, 'channel id', default=None)
3639 if channel_id:
3640 return channel_id
3641 channel_url = self._html_search_meta(
3642 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3643 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3644 'twitter:app:url:googleplay'), webpage, 'channel url')
3645 return self._search_regex(
3646 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3647 channel_url, 'channel id')
15f6397c 3648
8bdd16b4 3649 @staticmethod
cd7c66cf 3650 def _extract_basic_item_renderer(item):
3651 # Modified from _extract_grid_item_renderer
201c1459 3652 known_basic_renderers = (
3653 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3654 )
3655 for key, renderer in item.items():
201c1459 3656 if not isinstance(renderer, dict):
cd7c66cf 3657 continue
201c1459 3658 elif key in known_basic_renderers:
3659 return renderer
3660 elif key.startswith('grid') and key.endswith('Renderer'):
3661 return renderer
8bdd16b4 3662
8bdd16b4 3663 def _grid_entries(self, grid_renderer):
3664 for item in grid_renderer['items']:
3665 if not isinstance(item, dict):
39b62db1 3666 continue
cd7c66cf 3667 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3668 if not isinstance(renderer, dict):
3669 continue
052e1350 3670 title = self._get_text(renderer, 'title')
fe93e2c4 3671
8bdd16b4 3672 # playlist
3673 playlist_id = renderer.get('playlistId')
3674 if playlist_id:
3675 yield self.url_result(
3676 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3677 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3678 video_title=title)
201c1459 3679 continue
8bdd16b4 3680 # video
3681 video_id = renderer.get('videoId')
3682 if video_id:
3683 yield self._extract_video(renderer)
201c1459 3684 continue
8bdd16b4 3685 # channel
3686 channel_id = renderer.get('channelId')
3687 if channel_id:
8bdd16b4 3688 yield self.url_result(
3689 'https://www.youtube.com/channel/%s' % channel_id,
3690 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3691 continue
3692 # generic endpoint URL support
3693 ep_url = urljoin('https://www.youtube.com/', try_get(
3694 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3695 compat_str))
3696 if ep_url:
3697 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3698 if ie.suitable(ep_url):
3699 yield self.url_result(
3700 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3701 break
8bdd16b4 3702
16aa9ea4 3703 def _music_reponsive_list_entry(self, renderer):
3704 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3705 if video_id:
3706 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3707 ie=YoutubeIE.ie_key(), video_id=video_id)
3708 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3709 if playlist_id:
3710 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3711 if video_id:
3712 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3713 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3714 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3715 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3716 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3717 if browse_id:
3718 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3719 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3720
3d3dddc9 3721 def _shelf_entries_from_content(self, shelf_renderer):
3722 content = shelf_renderer.get('content')
3723 if not isinstance(content, dict):
8bdd16b4 3724 return
cd7c66cf 3725 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3726 if renderer:
3727 # TODO: add support for nested playlists so each shelf is processed
3728 # as separate playlist
3729 # TODO: this includes only first N items
3730 for entry in self._grid_entries(renderer):
3731 yield entry
3732 renderer = content.get('horizontalListRenderer')
3733 if renderer:
3734 # TODO
3735 pass
8bdd16b4 3736
29f7c58a 3737 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3738 ep = try_get(
3739 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3740 compat_str)
3741 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3742 if shelf_url:
29f7c58a 3743 # Skipping links to another channels, note that checking for
3744 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3745 # will not work
3746 if skip_channels and '/channels?' in shelf_url:
3747 return
052e1350 3748 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3749 yield self.url_result(shelf_url, video_title=title)
3750 # Shelf may not contain shelf URL, fallback to extraction from content
3751 for entry in self._shelf_entries_from_content(shelf_renderer):
3752 yield entry
c5e8d7af 3753
8bdd16b4 3754 def _playlist_entries(self, video_list_renderer):
3755 for content in video_list_renderer['contents']:
3756 if not isinstance(content, dict):
3757 continue
3758 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3759 if not isinstance(renderer, dict):
3760 continue
3761 video_id = renderer.get('videoId')
3762 if not video_id:
3763 continue
3764 yield self._extract_video(renderer)
07aeced6 3765
3462ffa8 3766 def _rich_entries(self, rich_grid_renderer):
3767 renderer = try_get(
70d5c17b 3768 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3769 video_id = renderer.get('videoId')
3770 if not video_id:
3771 return
3772 yield self._extract_video(renderer)
3773
8bdd16b4 3774 def _video_entry(self, video_renderer):
3775 video_id = video_renderer.get('videoId')
3776 if video_id:
3777 return self._extract_video(video_renderer)
dacb3a86 3778
8bdd16b4 3779 def _post_thread_entries(self, post_thread_renderer):
3780 post_renderer = try_get(
3781 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3782 if not post_renderer:
3783 return
3784 # video attachment
3785 video_renderer = try_get(
895b0931 3786 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3787 video_id = video_renderer.get('videoId')
3788 if video_id:
3789 entry = self._extract_video(video_renderer)
8bdd16b4 3790 if entry:
3791 yield entry
895b0931 3792 # playlist attachment
3793 playlist_id = try_get(
3794 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3795 if playlist_id:
3796 yield self.url_result(
e28f1c0a 3797 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3798 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3799 # inline video links
3800 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3801 for run in runs:
3802 if not isinstance(run, dict):
3803 continue
3804 ep_url = try_get(
3805 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3806 if not ep_url:
3807 continue
3808 if not YoutubeIE.suitable(ep_url):
3809 continue
3810 ep_video_id = YoutubeIE._match_id(ep_url)
3811 if video_id == ep_video_id:
3812 continue
895b0931 3813 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3814
8bdd16b4 3815 def _post_thread_continuation_entries(self, post_thread_continuation):
3816 contents = post_thread_continuation.get('contents')
3817 if not isinstance(contents, list):
3818 return
3819 for content in contents:
3820 renderer = content.get('backstagePostThreadRenderer')
3821 if not isinstance(renderer, dict):
3822 continue
3823 for entry in self._post_thread_entries(renderer):
3824 yield entry
07aeced6 3825
39ed931e 3826 r''' # unused
3827 def _rich_grid_entries(self, contents):
3828 for content in contents:
3829 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3830 if video_renderer:
3831 entry = self._video_entry(video_renderer)
3832 if entry:
3833 yield entry
3834 '''
a6213a49 3835 def _extract_entries(self, parent_renderer, continuation_list):
3836 # continuation_list is modified in-place with continuation_list = [continuation_token]
3837 continuation_list[:] = [None]
3838 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3839 for content in contents:
3840 if not isinstance(content, dict):
3841 continue
16aa9ea4 3842 is_renderer = traverse_obj(
3843 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3844 expected_type=dict)
a6213a49 3845 if not is_renderer:
3846 renderer = content.get('richItemRenderer')
3847 if renderer:
3848 for entry in self._rich_entries(renderer):
3849 yield entry
3850 continuation_list[0] = self._extract_continuation(parent_renderer)
3851 continue
3852 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3853 for isr_content in isr_contents:
3854 if not isinstance(isr_content, dict):
8bdd16b4 3855 continue
69184e41 3856
a6213a49 3857 known_renderers = {
3858 'playlistVideoListRenderer': self._playlist_entries,
3859 'gridRenderer': self._grid_entries,
3860 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3861 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3862 'backstagePostThreadRenderer': self._post_thread_entries,
3863 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3864 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3865 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3866 }
3867 for key, renderer in isr_content.items():
3868 if key not in known_renderers:
3869 continue
3870 for entry in known_renderers[key](renderer):
3871 if entry:
3872 yield entry
3873 continuation_list[0] = self._extract_continuation(renderer)
3874 break
70d5c17b 3875
3876 if not continuation_list[0]:
a6213a49 3877 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3878
a6213a49 3879 if not continuation_list[0]:
3880 continuation_list[0] = self._extract_continuation(parent_renderer)
3881
3882 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3883 continuation_list = [None]
3884 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3885 tab_content = try_get(tab, lambda x: x['content'], dict)
3886 if not tab_content:
3887 return
3462ffa8 3888 parent_renderer = (
29f7c58a 3889 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3890 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3891 for entry in extract_entries(parent_renderer):
3892 yield entry
3462ffa8 3893 continuation = continuation_list[0]
d069eca7 3894
8bdd16b4 3895 for page_num in itertools.count(1):
3896 if not continuation:
3897 break
99e9e001 3898 headers = self.generate_api_headers(
3899 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3900 response = self._extract_response(
3901 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3902 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3903 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3904
3905 if not response:
8bdd16b4 3906 break
ac56cf38 3907 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3908 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3909 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 3910
69184e41 3911 known_continuation_renderers = {
3912 'playlistVideoListContinuation': self._playlist_entries,
3913 'gridContinuation': self._grid_entries,
3914 'itemSectionContinuation': self._post_thread_continuation_entries,
3915 'sectionListContinuation': extract_entries, # for feeds
3916 }
8bdd16b4 3917 continuation_contents = try_get(
69184e41 3918 response, lambda x: x['continuationContents'], dict) or {}
3919 continuation_renderer = None
3920 for key, value in continuation_contents.items():
3921 if key not in known_continuation_renderers:
3462ffa8 3922 continue
69184e41 3923 continuation_renderer = value
3924 continuation_list = [None]
3925 for entry in known_continuation_renderers[key](continuation_renderer):
3926 yield entry
3927 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3928 break
3929 if continuation_renderer:
3930 continue
c5e8d7af 3931
a1b535bd 3932 known_renderers = {
3933 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3934 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3935 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3936 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3937 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3938 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3939 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3940 }
cce889b9 3941 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3942 continuation_items = try_get(
cce889b9 3943 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3944 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3945 video_items_renderer = None
3946 for key, value in continuation_item.items():
3947 if key not in known_renderers:
8bdd16b4 3948 continue
a1b535bd 3949 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3950 continuation_list = [None]
a1b535bd 3951 for entry in known_renderers[key][0](video_items_renderer):
3952 yield entry
9ba5705a 3953 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3954 break
3955 if video_items_renderer:
3956 continue
8bdd16b4 3957 break
9558dcec 3958
8bdd16b4 3959 @staticmethod
7c219ea6 3960 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 3961 for tab in tabs:
cd684175 3962 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3963 if renderer.get('selected') is True:
3964 return renderer
2b3c2546 3965 else:
7c219ea6 3966 if fatal:
3967 raise ExtractorError('Unable to find selected tab')
b82f815f 3968
47193e02 3969 @classmethod
3970 def _extract_uploader(cls, data):
8bdd16b4 3971 uploader = {}
47193e02 3972 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3973 owner = try_get(
3974 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3975 if owner:
3976 uploader['uploader'] = owner.get('text')
3977 uploader['uploader_id'] = try_get(
3978 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3979 uploader['uploader_url'] = urljoin(
3980 'https://www.youtube.com/',
3981 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3982 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3983
ac56cf38 3984 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 3985 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 3986 tags = []
b60419c5 3987
8bdd16b4 3988 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 3989 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 3990 renderer = try_get(
3991 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3992 if renderer:
b60419c5 3993 channel_name = renderer.get('title')
3994 channel_url = renderer.get('channelUrl')
3995 channel_id = renderer.get('externalId')
39ed931e 3996 else:
64c0d954 3997 renderer = try_get(
3998 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3999
8bdd16b4 4000 if renderer:
4001 title = renderer.get('title')
ecc97af3 4002 description = renderer.get('description', '')
b60419c5 4003 playlist_id = channel_id
4004 tags = renderer.get('keywords', '').split()
b60419c5 4005
301d07fc 4006 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4007 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4008 def _get_uncropped(url):
4009 return url_or_none((url or '').split('=')[0] + '=s0')
4010
4011 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4012 if avatar_thumbnails:
4013 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4014 if uncropped_avatar:
4015 avatar_thumbnails.append({
4016 'url': uncropped_avatar,
4017 'id': 'avatar_uncropped',
4018 'preference': 1
4019 })
4020
4021 channel_banners = self._extract_thumbnails(
4022 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4023 for banner in channel_banners:
4024 banner['preference'] = -10
4025
4026 if channel_banners:
4027 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4028 if uncropped_banner:
4029 channel_banners.append({
4030 'url': uncropped_banner,
4031 'id': 'banner_uncropped',
4032 'preference': -5
4033 })
4034
4035 primary_thumbnails = self._extract_thumbnails(
4036 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4037
3462ffa8 4038 if playlist_id is None:
70d5c17b 4039 playlist_id = item_id
f0d785d3 4040
4041 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4042 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4043 if title is None:
f0d785d3 4044 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4045 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4046 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4047
b60419c5 4048 metadata = {
4049 'playlist_id': playlist_id,
4050 'playlist_title': title,
4051 'playlist_description': description,
4052 'uploader': channel_name,
4053 'uploader_id': channel_id,
4054 'uploader_url': channel_url,
301d07fc 4055 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4056 'tags': tags,
f0d785d3 4057 'view_count': self._get_count(playlist_stats, 1),
4058 'availability': self._extract_availability(data),
4059 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4060 'playlist_count': self._get_count(playlist_stats, 0),
4061 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4062 }
4063 if not channel_id:
4064 metadata.update(self._extract_uploader(data))
4065 metadata.update({
4066 'channel': metadata['uploader'],
4067 'channel_id': metadata['uploader_id'],
4068 'channel_url': metadata['uploader_url']})
4069 return self.playlist_result(
d069eca7 4070 self._entries(
ac56cf38 4071 selected_tab, playlist_id, ytcfg,
4072 self._extract_account_syncid(ytcfg, data),
4073 self._extract_visitor_data(data, ytcfg)),
b60419c5 4074 **metadata)
73c4ac2c 4075
ac56cf38 4076 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4077 first_id = last_id = response = None
2be71994 4078 for page_num in itertools.count(1):
cd7c66cf 4079 videos = list(self._playlist_entries(playlist))
4080 if not videos:
4081 return
2be71994 4082 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4083 if start >= len(videos):
4084 return
4085 for video in videos[start:]:
4086 if video['id'] == first_id:
4087 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4088 return
4089 yield video
4090 first_id = first_id or videos[0]['id']
4091 last_id = videos[-1]['id']
79360d99 4092 watch_endpoint = try_get(
4093 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4094 headers = self.generate_api_headers(
4095 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4096 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4097 query = {
4098 'playlistId': playlist_id,
4099 'videoId': watch_endpoint.get('videoId') or last_id,
4100 'index': watch_endpoint.get('index') or len(videos),
4101 'params': watch_endpoint.get('params') or 'OAE%3D'
4102 }
4103 response = self._extract_response(
4104 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4105 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4106 check_get_keys='contents'
4107 )
cd7c66cf 4108 playlist = try_get(
79360d99 4109 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4110
ac56cf38 4111 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4112 title = playlist.get('title') or try_get(
4113 data, lambda x: x['titleText']['simpleText'], compat_str)
4114 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4115
4116 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4117 playlist_url = urljoin(url, try_get(
4118 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4119 compat_str))
4120 if playlist_url and playlist_url != url:
4121 return self.url_result(
4122 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4123 video_title=title)
cd7c66cf 4124
8bdd16b4 4125 return self.playlist_result(
ac56cf38 4126 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4127 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4128
47193e02 4129 def _extract_availability(self, data):
4130 """
4131 Gets the availability of a given playlist/tab.
4132 Note: Unless YouTube tells us explicitly, we do not assume it is public
4133 @param data: response
4134 """
4135 is_private = is_unlisted = None
4136 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4137 badge_labels = self._extract_badges(renderer)
4138
4139 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4140 privacy_dropdown_entries = try_get(
4141 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4142 for renderer_dict in privacy_dropdown_entries:
4143 is_selected = try_get(
4144 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4145 if not is_selected:
4146 continue
052e1350 4147 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4148 if label:
4149 badge_labels.add(label.lower())
4150 break
4151
4152 for badge_label in badge_labels:
4153 if badge_label == 'unlisted':
4154 is_unlisted = True
4155 elif badge_label == 'private':
4156 is_private = True
4157 elif badge_label == 'public':
4158 is_unlisted = is_private = False
4159 return self._availability(is_private, False, False, False, is_unlisted)
4160
4161 @staticmethod
4162 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4163 sidebar_renderer = try_get(
4164 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4165 for item in sidebar_renderer:
4166 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4167 if renderer:
4168 return renderer
4169
ac56cf38 4170 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4171 """
4172 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4173 """
5d342002 4174 browse_id = params = None
47193e02 4175 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4176 if not renderer:
4177 return
4178 menu_renderer = try_get(
4179 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4180 for menu_item in menu_renderer:
4181 if not isinstance(menu_item, dict):
358de58c 4182 continue
47193e02 4183 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4184 text = try_get(
4185 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4186 if not text or text.lower() != 'show unavailable videos':
4187 continue
4188 browse_endpoint = try_get(
4189 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4190 browse_id = browse_endpoint.get('browseId')
4191 params = browse_endpoint.get('params')
4192 break
5d342002 4193
11f9be09 4194 headers = self.generate_api_headers(
99e9e001 4195 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4196 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4197 query = {
4198 'params': params or 'wgYCCAA=',
4199 'browseId': browse_id or 'VL%s' % item_id
4200 }
4201 return self._extract_response(
4202 item_id=item_id, headers=headers, query=query,
fe93e2c4 4203 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4204 note='Downloading API JSON with unavailable videos')
358de58c 4205
ac56cf38 4206 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4207 retries = self.get_param('extractor_retries', 3)
62bff2c1 4208 count = -1
ac56cf38 4209 webpage = data = last_error = None
14fdfea9 4210 while count < retries:
62bff2c1 4211 count += 1
14fdfea9 4212 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4213 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4214 if last_error:
c705177d 4215 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4216 try:
4217 webpage = self._download_webpage(
4218 url, item_id,
4219 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4220 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4221 except ExtractorError as e:
4222 if isinstance(e.cause, network_exceptions):
4223 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4224 last_error = error_to_compat_str(e.cause or e.msg)
4225 if count < retries:
4226 continue
4227 if fatal:
4228 raise
4229 self.report_warning(error_to_compat_str(e))
14fdfea9 4230 break
ac56cf38 4231 else:
4232 try:
4233 self._extract_and_report_alerts(data)
4234 except ExtractorError as e:
4235 if fatal:
4236 raise
4237 self.report_warning(error_to_compat_str(e))
4238 break
4239
7c219ea6 4240 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4241 break
4242
4243 last_error = 'Incomplete yt initial data received'
4244 if count >= retries:
4245 if fatal:
4246 raise ExtractorError(last_error)
4247 self.report_warning(last_error)
4248 break
4249
cd7c66cf 4250 return webpage, data
4251
ac56cf38 4252 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4253 data = None
4254 if 'webpage' not in self._configuration_arg('skip'):
4255 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4256 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4257 # Reject webpage data if redirected to home page without explicitly requesting
4258 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4259 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4260 if (url != 'https://www.youtube.com/feed/recommended'
4261 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4262 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4263 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4264 if fatal:
4265 raise ExtractorError(msg, expected=True)
4266 self.report_warning(msg, only_once=True)
ac56cf38 4267 if not data:
4268 if not ytcfg and self.is_authenticated:
4269 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4270 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4271 raise ExtractorError(
4272 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4273 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4274 expected=True)
4275 self.report_warning(msg, only_once=True)
4276 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4277 return data, ytcfg
4278
4279 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4280 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4281 resolve_response = self._extract_response(
4282 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4283 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4284 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4285 for ep_key, ep in endpoints.items():
4286 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4287 if params:
4288 return self._extract_response(
4289 item_id=item_id, query=params, ep=ep, headers=headers,
4290 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4291 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4292 err_note = 'Failed to resolve url (does the playlist exist?)'
4293 if fatal:
4294 raise ExtractorError(err_note, expected=True)
4295 self.report_warning(err_note, item_id)
4296
a6213a49 4297 _SEARCH_PARAMS = None
4298
af5c1c55 4299 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4300 data = {'query': query}
4301 if params is NO_DEFAULT:
4302 params = self._SEARCH_PARAMS
4303 if params:
4304 data['params'] = params
16aa9ea4 4305
4306 content_keys = (
4307 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4308 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4309 # ytmusic search
4310 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4311 ('continuationContents', ),
4312 )
4313 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4314
a61fd4cf 4315 continuation_list = [None]
a6213a49 4316 for page_num in itertools.count(1):
a61fd4cf 4317 data.update(continuation_list[0] or {})
a6213a49 4318 search = self._extract_response(
4319 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4320 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4321 slr_contents = traverse_obj(search, *content_keys)
4322 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4323 if not continuation_list[0]:
a6213a49 4324 break
4325
4326
4327class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4328 IE_DESC = 'YouTube Tabs'
4329 _VALID_URL = r'''(?x:
4330 https?://
4331 (?:\w+\.)?
4332 (?:
4333 youtube(?:kids)?\.com|
4334 %(invidious)s
4335 )/
4336 (?:
4337 (?P<channel_type>channel|c|user|browse)/|
4338 (?P<not_channel>
4339 feed/|hashtag/|
4340 (?:playlist|watch)\?.*?\blist=
4341 )|
4342 (?!(?:%(reserved_names)s)\b) # Direct URLs
4343 )
4344 (?P<id>[^/?\#&]+)
4345 )''' % {
4346 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4347 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4348 }
4349 IE_NAME = 'youtube:tab'
4350
4351 _TESTS = [{
4352 'note': 'playlists, multipage',
4353 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4354 'playlist_mincount': 94,
4355 'info_dict': {
4356 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4357 'title': 'Igor Kleiner - Playlists',
a6213a49 4358 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4359 'uploader': 'Igor Kleiner',
a6213a49 4360 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4361 'channel': 'Igor Kleiner',
4362 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4363 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4364 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4365 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4366 'channel_follower_count': int
a6213a49 4367 },
4368 }, {
4369 'note': 'playlists, multipage, different order',
4370 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4371 'playlist_mincount': 94,
4372 'info_dict': {
4373 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4374 'title': 'Igor Kleiner - Playlists',
a6213a49 4375 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4376 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4377 'uploader': 'Igor Kleiner',
4378 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4379 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4380 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4381 'channel': 'Igor Kleiner',
4382 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4383 'channel_follower_count': int
a6213a49 4384 },
4385 }, {
4386 'note': 'playlists, series',
4387 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4388 'playlist_mincount': 5,
4389 'info_dict': {
4390 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4391 'title': '3Blue1Brown - Playlists',
4392 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4393 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4394 'uploader': '3Blue1Brown',
976ae3ea 4395 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4396 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4397 'channel': '3Blue1Brown',
4398 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4399 'tags': ['Mathematics'],
6c73052c 4400 'channel_follower_count': int
a6213a49 4401 },
4402 }, {
4403 'note': 'playlists, singlepage',
4404 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4405 'playlist_mincount': 4,
4406 'info_dict': {
4407 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4408 'title': 'ThirstForScience - Playlists',
4409 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4410 'uploader': 'ThirstForScience',
4411 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4412 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4413 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4414 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4415 'tags': 'count:13',
4416 'channel': 'ThirstForScience',
6c73052c 4417 'channel_follower_count': int
a6213a49 4418 }
4419 }, {
4420 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4421 'only_matching': True,
4422 }, {
4423 'note': 'basic, single video playlist',
4424 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4425 'info_dict': {
4426 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4427 'uploader': 'Sergey M.',
4428 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4429 'title': 'youtube-dl public playlist',
976ae3ea 4430 'description': '',
4431 'tags': [],
4432 'view_count': int,
4433 'modified_date': '20201130',
4434 'channel': 'Sergey M.',
4435 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4436 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4437 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4438 },
4439 'playlist_count': 1,
4440 }, {
4441 'note': 'empty playlist',
4442 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4443 'info_dict': {
4444 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4445 'uploader': 'Sergey M.',
4446 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4447 'title': 'youtube-dl empty playlist',
976ae3ea 4448 'tags': [],
4449 'channel': 'Sergey M.',
4450 'description': '',
4451 'modified_date': '20160902',
4452 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4453 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4454 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4455 },
4456 'playlist_count': 0,
4457 }, {
4458 'note': 'Home tab',
4459 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4460 'info_dict': {
4461 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4462 'title': 'lex will - Home',
4463 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4464 'uploader': 'lex will',
4465 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4466 'channel': 'lex will',
4467 'tags': ['bible', 'history', 'prophesy'],
4468 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4469 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4470 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4471 'channel_follower_count': int
a6213a49 4472 },
4473 'playlist_mincount': 2,
4474 }, {
4475 'note': 'Videos tab',
4476 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4477 'info_dict': {
4478 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4479 'title': 'lex will - Videos',
4480 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4481 'uploader': 'lex will',
4482 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4483 'tags': ['bible', 'history', 'prophesy'],
4484 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4485 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4486 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4487 'channel': 'lex will',
6c73052c 4488 'channel_follower_count': int
a6213a49 4489 },
4490 'playlist_mincount': 975,
4491 }, {
4492 'note': 'Videos tab, sorted by popular',
4493 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4494 'info_dict': {
4495 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4496 'title': 'lex will - Videos',
4497 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4498 'uploader': 'lex will',
4499 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4500 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4501 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4502 'channel': 'lex will',
4503 'tags': ['bible', 'history', 'prophesy'],
4504 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4505 'channel_follower_count': int
a6213a49 4506 },
4507 'playlist_mincount': 199,
4508 }, {
4509 'note': 'Playlists tab',
4510 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4511 'info_dict': {
4512 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4513 'title': 'lex will - Playlists',
4514 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4515 'uploader': 'lex will',
4516 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4517 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4518 'channel': 'lex will',
4519 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4520 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4521 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4522 'channel_follower_count': int
a6213a49 4523 },
4524 'playlist_mincount': 17,
4525 }, {
4526 'note': 'Community tab',
4527 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4528 'info_dict': {
4529 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4530 'title': 'lex will - Community',
4531 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4532 'uploader': 'lex will',
4533 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4534 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4535 'channel': 'lex will',
4536 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4537 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4538 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4539 'channel_follower_count': int
a6213a49 4540 },
4541 'playlist_mincount': 18,
4542 }, {
4543 'note': 'Channels tab',
4544 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4545 'info_dict': {
4546 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4547 'title': 'lex will - Channels',
4548 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4549 'uploader': 'lex will',
4550 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4551 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4552 'channel': 'lex will',
4553 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4554 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4555 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4556 'channel_follower_count': int
a6213a49 4557 },
4558 'playlist_mincount': 12,
4559 }, {
4560 'note': 'Search tab',
4561 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4562 'playlist_mincount': 40,
4563 'info_dict': {
4564 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4565 'title': '3Blue1Brown - Search - linear algebra',
4566 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4567 'uploader': '3Blue1Brown',
4568 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4569 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4570 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4571 'tags': ['Mathematics'],
4572 'channel': '3Blue1Brown',
4573 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4574 'channel_follower_count': int
a6213a49 4575 },
4576 }, {
4577 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4578 'only_matching': True,
4579 }, {
4580 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4581 'only_matching': True,
4582 }, {
4583 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4584 'only_matching': True,
4585 }, {
4586 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4587 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4588 'info_dict': {
4589 'title': '29C3: Not my department',
4590 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4591 'uploader': 'Christiaan008',
4592 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4593 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4594 'tags': [],
4595 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4596 'view_count': int,
4597 'modified_date': '20150605',
4598 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4599 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4600 'channel': 'Christiaan008',
a6213a49 4601 },
4602 'playlist_count': 96,
4603 }, {
4604 'note': 'Large playlist',
4605 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4606 'info_dict': {
4607 'title': 'Uploads from Cauchemar',
4608 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4609 'uploader': 'Cauchemar',
4610 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4611 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4612 'tags': [],
4613 'modified_date': r're:\d{8}',
4614 'channel': 'Cauchemar',
4615 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4616 'view_count': int,
4617 'description': '',
4618 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4619 },
4620 'playlist_mincount': 1123,
976ae3ea 4621 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4622 }, {
4623 'note': 'even larger playlist, 8832 videos',
4624 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4625 'only_matching': True,
4626 }, {
4627 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4628 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4629 'info_dict': {
4630 'title': 'Uploads from Interstellar Movie',
4631 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4632 'uploader': 'Interstellar Movie',
4633 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4634 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4635 'tags': [],
4636 'view_count': int,
4637 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4638 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4639 'channel': 'Interstellar Movie',
4640 'description': '',
4641 'modified_date': r're:\d{8}',
a6213a49 4642 },
4643 'playlist_mincount': 21,
4644 }, {
4645 'note': 'Playlist with "show unavailable videos" button',
4646 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4647 'info_dict': {
4648 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4649 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4650 'uploader': 'Phim Siêu Nhân Nhật Bản',
4651 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4652 'view_count': int,
4653 'channel': 'Phim Siêu Nhân Nhật Bản',
4654 'tags': [],
4655 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4656 'description': '',
4657 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4658 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4659 'modified_date': r're:\d{8}',
a6213a49 4660 },
4661 'playlist_mincount': 200,
976ae3ea 4662 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4663 }, {
4664 'note': 'Playlist with unavailable videos in page 7',
4665 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4666 'info_dict': {
4667 'title': 'Uploads from BlankTV',
4668 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4669 'uploader': 'BlankTV',
4670 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4671 'channel': 'BlankTV',
4672 'channel_url': 'https://www.youtube.com/c/blanktv',
4673 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4674 'view_count': int,
4675 'tags': [],
4676 'uploader_url': 'https://www.youtube.com/c/blanktv',
4677 'modified_date': r're:\d{8}',
4678 'description': '',
a6213a49 4679 },
4680 'playlist_mincount': 1000,
976ae3ea 4681 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4682 }, {
4683 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4684 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4685 'info_dict': {
4686 'title': 'Data Analysis with Dr Mike Pound',
4687 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4688 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4689 'uploader': 'Computerphile',
4690 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4691 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4692 'tags': [],
4693 'view_count': int,
4694 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4695 'channel_url': 'https://www.youtube.com/user/Computerphile',
4696 'channel': 'Computerphile',
a6213a49 4697 },
4698 'playlist_mincount': 11,
4699 }, {
4700 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4701 'only_matching': True,
4702 }, {
4703 'note': 'Playlist URL that does not actually serve a playlist',
4704 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4705 'info_dict': {
4706 'id': 'FqZTN594JQw',
4707 'ext': 'webm',
4708 'title': "Smiley's People 01 detective, Adventure Series, Action",
4709 'uploader': 'STREEM',
4710 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4711 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4712 'upload_date': '20150526',
4713 'license': 'Standard YouTube License',
4714 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4715 'categories': ['People & Blogs'],
4716 'tags': list,
4717 'view_count': int,
4718 'like_count': int,
a6213a49 4719 },
4720 'params': {
4721 'skip_download': True,
4722 },
4723 'skip': 'This video is not available.',
4724 'add_ie': [YoutubeIE.ie_key()],
4725 }, {
4726 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4727 'only_matching': True,
4728 }, {
4729 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4730 'only_matching': True,
4731 }, {
4732 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4733 'info_dict': {
6c73052c 4734 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4735 'ext': 'mp4',
976ae3ea 4736 'title': str,
a6213a49 4737 'uploader': 'Sky News',
4738 'uploader_id': 'skynews',
4739 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4740 'upload_date': r're:\d{8}',
976ae3ea 4741 'description': str,
a6213a49 4742 'categories': ['News & Politics'],
4743 'tags': list,
4744 'like_count': int,
6c73052c 4745 'release_timestamp': 1642502819,
976ae3ea 4746 'channel': 'Sky News',
4747 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4748 'age_limit': 0,
4749 'view_count': int,
6c73052c 4750 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4751 'playable_in_embed': True,
6c73052c 4752 'release_date': '20220118',
976ae3ea 4753 'availability': 'public',
4754 'live_status': 'is_live',
4755 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4756 'channel_follower_count': int
a6213a49 4757 },
4758 'params': {
4759 'skip_download': True,
4760 },
976ae3ea 4761 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4762 }, {
4763 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4764 'info_dict': {
4765 'id': 'a48o2S1cPoo',
4766 'ext': 'mp4',
4767 'title': 'The Young Turks - Live Main Show',
4768 'uploader': 'The Young Turks',
4769 'uploader_id': 'TheYoungTurks',
4770 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4771 'upload_date': '20150715',
4772 'license': 'Standard YouTube License',
4773 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4774 'categories': ['News & Politics'],
4775 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4776 'like_count': int,
a6213a49 4777 },
4778 'params': {
4779 'skip_download': True,
4780 },
4781 'only_matching': True,
4782 }, {
4783 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4784 'only_matching': True,
4785 }, {
4786 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4787 'only_matching': True,
4788 }, {
4789 'note': 'A channel that is not live. Should raise error',
4790 'url': 'https://www.youtube.com/user/numberphile/live',
4791 'only_matching': True,
4792 }, {
4793 'url': 'https://www.youtube.com/feed/trending',
4794 'only_matching': True,
4795 }, {
4796 'url': 'https://www.youtube.com/feed/library',
4797 'only_matching': True,
4798 }, {
4799 'url': 'https://www.youtube.com/feed/history',
4800 'only_matching': True,
4801 }, {
4802 'url': 'https://www.youtube.com/feed/subscriptions',
4803 'only_matching': True,
4804 }, {
4805 'url': 'https://www.youtube.com/feed/watch_later',
4806 'only_matching': True,
4807 }, {
4808 'note': 'Recommended - redirects to home page.',
4809 'url': 'https://www.youtube.com/feed/recommended',
4810 'only_matching': True,
4811 }, {
4812 'note': 'inline playlist with not always working continuations',
4813 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4814 'only_matching': True,
4815 }, {
4816 'url': 'https://www.youtube.com/course',
4817 'only_matching': True,
4818 }, {
4819 'url': 'https://www.youtube.com/zsecurity',
4820 'only_matching': True,
4821 }, {
4822 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4823 'only_matching': True,
4824 }, {
4825 'url': 'https://www.youtube.com/TheYoungTurks/live',
4826 'only_matching': True,
4827 }, {
4828 'url': 'https://www.youtube.com/hashtag/cctv9',
4829 'info_dict': {
4830 'id': 'cctv9',
4831 'title': '#cctv9',
976ae3ea 4832 'tags': [],
a6213a49 4833 },
4834 'playlist_mincount': 350,
4835 }, {
4836 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4837 'only_matching': True,
4838 }, {
4839 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4840 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4841 'only_matching': True
4842 }, {
4843 'note': '/browse/ should redirect to /channel/',
4844 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4845 'only_matching': True
4846 }, {
4847 'note': 'VLPL, should redirect to playlist?list=PL...',
4848 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4849 'info_dict': {
4850 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4851 'uploader': 'NoCopyrightSounds',
4852 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4853 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4854 'title': 'NCS Releases',
976ae3ea 4855 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4856 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4857 'modified_date': r're:\d{8}',
4858 'view_count': int,
4859 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4860 'tags': [],
4861 'channel': 'NoCopyrightSounds',
a6213a49 4862 },
4863 'playlist_mincount': 166,
976ae3ea 4864 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4865 }, {
4866 'note': 'Topic, should redirect to playlist?list=UU...',
4867 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4868 'info_dict': {
4869 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4870 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4871 'title': 'Uploads from Royalty Free Music - Topic',
4872 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4873 'tags': [],
4874 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4875 'channel': 'Royalty Free Music - Topic',
4876 'view_count': int,
4877 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4878 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4879 'modified_date': r're:\d{8}',
4880 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4881 'description': '',
a6213a49 4882 },
4883 'expected_warnings': [
a6213a49 4884 'The URL does not have a videos tab',
976ae3ea 4885 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4886 ],
4887 'playlist_mincount': 101,
4888 }, {
4889 'note': 'Topic without a UU playlist',
4890 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4891 'info_dict': {
4892 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4893 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4894 'tags': [],
a6213a49 4895 },
4896 'expected_warnings': [
976ae3ea 4897 'the playlist redirect gave error',
a6213a49 4898 ],
4899 'playlist_mincount': 9,
4900 }, {
4901 'note': 'Youtube music Album',
4902 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4903 'info_dict': {
4904 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4905 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 4906 'tags': [],
4907 'view_count': int,
4908 'description': '',
4909 'availability': 'unlisted',
4910 'modified_date': r're:\d{8}',
a6213a49 4911 },
4912 'playlist_count': 50,
4913 }, {
4914 'note': 'unlisted single video playlist',
4915 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4916 'info_dict': {
4917 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4918 'uploader': 'colethedj',
4919 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4920 'title': 'yt-dlp unlisted playlist test',
976ae3ea 4921 'availability': 'unlisted',
4922 'tags': [],
4923 'modified_date': '20211208',
4924 'channel': 'colethedj',
4925 'view_count': int,
4926 'description': '',
4927 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4928 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4929 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 4930 },
4931 'playlist_count': 1,
4932 }, {
4933 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4934 'url': 'https://www.youtube.com/feed/recommended',
4935 'info_dict': {
4936 'id': 'recommended',
4937 'title': 'recommended',
6c73052c 4938 'tags': [],
a6213a49 4939 },
4940 'playlist_mincount': 50,
4941 'params': {
4942 'skip_download': True,
4943 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4944 },
4945 }, {
4946 'note': 'API Fallback: /videos tab, sorted by oldest first',
4947 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4948 'info_dict': {
4949 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4950 'title': 'Cody\'sLab - Videos',
4951 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4952 'uploader': 'Cody\'sLab',
4953 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 4954 'channel': 'Cody\'sLab',
4955 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4956 'tags': [],
4957 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4958 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 4959 'channel_follower_count': int
a6213a49 4960 },
4961 'playlist_mincount': 650,
4962 'params': {
4963 'skip_download': True,
4964 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4965 },
4966 }, {
4967 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4968 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4969 'info_dict': {
4970 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4971 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4972 'title': 'Uploads from Royalty Free Music - Topic',
4973 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4974 'modified_date': r're:\d{8}',
4975 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4976 'description': '',
4977 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4978 'tags': [],
4979 'channel': 'Royalty Free Music - Topic',
4980 'view_count': int,
4981 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 4982 },
4983 'expected_warnings': [
976ae3ea 4984 'does not have a videos tab',
4985 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4986 ],
4987 'playlist_mincount': 101,
4988 'params': {
4989 'skip_download': True,
4990 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4991 },
7c219ea6 4992 }, {
4993 'note': 'non-standard redirect to regional channel',
4994 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
4995 'only_matching': True
a6213a49 4996 }]
4997
4998 @classmethod
4999 def suitable(cls, url):
5000 return False if YoutubeIE.suitable(url) else super(
5001 YoutubeTabIE, cls).suitable(url)
9297939e 5002
64f36541 5003 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5004
182bda88 5005 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5006 def _real_extract(self, url, smuggled_data):
cd7c66cf 5007 item_id = self._match_id(url)
5008 url = compat_urlparse.urlunparse(
5009 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5010 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5011
fe03a6cd 5012 def get_mobj(url):
37e57a9f 5013 mobj = self._URL_RE.match(url).groupdict()
07cce701 5014 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5015 return mobj
5016
37e57a9f 5017 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5018 # Youtube returns incomplete data if tabname is not lower case
5019 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5020 if is_channel:
5021 if smuggled_data.get('is_music_url'):
37e57a9f 5022 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5023 item_id = item_id[2:]
37e57a9f 5024 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5025 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5026 mdata = self._extract_tab_endpoint(
37e57a9f 5027 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5028 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5029 get_all=False, expected_type=compat_str)
ac56cf38 5030 if not murl:
37e57a9f 5031 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5032 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5033 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5034 pre = f'https://www.youtube.com/channel/{item_id}'
5035
64f36541 5036 original_tab_name = tab
fe03a6cd 5037 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5038 # Home URLs should redirect to /videos/
37e57a9f 5039 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5040 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5041 tab = '/videos'
5042
5043 url = ''.join((pre, tab, post))
5044 mobj = get_mobj(url)
cd7c66cf 5045
5046 # Handle both video/playlist URLs
201c1459 5047 qs = parse_qs(url)
37e57a9f 5048 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5049
fe03a6cd 5050 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5051 if not playlist_id:
fe03a6cd 5052 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5053 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5054 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5055 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5056 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5057 mobj = get_mobj(url)
cd7c66cf 5058
5059 if video_id and playlist_id:
a06916d9 5060 if self.get_param('noplaylist'):
37e57a9f 5061 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5062 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5063 ie=YoutubeIE.ie_key(), video_id=video_id)
5064 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5065
ac56cf38 5066 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5067
7c219ea6 5068 # YouTube may provide a non-standard redirect to the regional channel
5069 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5070 redirect_url = traverse_obj(
5071 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5072 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5073 redirect_url = ''.join((
5074 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5075 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5076 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5077
37e57a9f 5078 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5079 if tabs:
5080 selected_tab = self._extract_selected_tab(tabs)
64f36541 5081 selected_tab_name = selected_tab.get('title', '').lower()
5082 if selected_tab_name == 'home':
5083 selected_tab_name = 'featured'
5084 requested_tab_name = mobj['tab'][1:]
09f1580e 5085 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5086 if requested_tab_name == 'live':
09f1580e 5087 # Live tab should have redirected to the video
5088 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5089 if requested_tab_name not in ('', selected_tab_name):
5090 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5091 if not original_tab_name:
5092 if item_id[:2] == 'UC':
5093 # Topic channels don't have /videos. Use the equivalent playlist instead
5094 pl_id = f'UU{item_id[2:]}'
5095 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5096 try:
5097 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5098 except ExtractorError:
5099 redirect_warning += ' and the playlist redirect gave error'
5100 else:
5101 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5102 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5103 if selected_tab_name and selected_tab_name != requested_tab_name:
5104 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5105 else:
5106 raise ExtractorError(redirect_warning, expected=True)
18db7548 5107
37e57a9f 5108 if redirect_warning:
64f36541 5109 self.to_screen(redirect_warning)
37e57a9f 5110 self.write_debug(f'Final URL: {url}')
18db7548 5111
358de58c 5112 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5113 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5114 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5115 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5116 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5117 if tabs:
ac56cf38 5118 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5119
37e57a9f 5120 playlist = traverse_obj(
5121 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5122 if playlist:
ac56cf38 5123 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5124
37e57a9f 5125 video_id = traverse_obj(
5126 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5127 if video_id:
09f1580e 5128 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5129 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5130 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5131 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5132
8bdd16b4 5133 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5134
c5e8d7af 5135
8bdd16b4 5136class YoutubePlaylistIE(InfoExtractor):
96565c7e 5137 IE_DESC = 'YouTube playlists'
8bdd16b4 5138 _VALID_URL = r'''(?x)(?:
5139 (?:https?://)?
5140 (?:\w+\.)?
5141 (?:
5142 (?:
5143 youtube(?:kids)?\.com|
d9190e44 5144 %(invidious)s
8bdd16b4 5145 )
5146 /.*?\?.*?\blist=
5147 )?
5148 (?P<id>%(playlist_id)s)
d9190e44
RH
5149 )''' % {
5150 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5151 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5152 }
8bdd16b4 5153 IE_NAME = 'youtube:playlist'
cdc628a4 5154 _TESTS = [{
8bdd16b4 5155 'note': 'issue #673',
5156 'url': 'PLBB231211A4F62143',
cdc628a4 5157 'info_dict': {
8bdd16b4 5158 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5159 'id': 'PLBB231211A4F62143',
976ae3ea 5160 'uploader': 'Wickman',
8bdd16b4 5161 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5162 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5163 'view_count': int,
5164 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5165 'modified_date': r're:\d{8}',
5166 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5167 'channel': 'Wickman',
5168 'tags': [],
5169 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5170 },
5171 'playlist_mincount': 29,
5172 }, {
5173 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5174 'info_dict': {
5175 'title': 'YDL_safe_search',
5176 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5177 },
5178 'playlist_count': 2,
5179 'skip': 'This playlist is private',
9558dcec 5180 }, {
8bdd16b4 5181 'note': 'embedded',
5182 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5183 'playlist_count': 4,
9558dcec 5184 'info_dict': {
8bdd16b4 5185 'title': 'JODA15',
5186 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5187 'uploader': 'milan',
5188 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5189 'description': '',
5190 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5191 'tags': [],
5192 'modified_date': '20140919',
5193 'view_count': int,
5194 'channel': 'milan',
5195 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5196 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5197 },
5198 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5199 }, {
8bdd16b4 5200 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5201 'playlist_mincount': 654,
8bdd16b4 5202 'info_dict': {
5203 'title': '2018 Chinese New Singles (11/6 updated)',
5204 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5205 'uploader': 'LBK',
5206 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5207 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5208 'channel': 'LBK',
5209 'view_count': int,
5210 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5211 'tags': [],
5212 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5213 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5214 'modified_date': r're:\d{8}',
5215 },
5216 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5217 }, {
29f7c58a 5218 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5219 'only_matching': True,
5220 }, {
5221 # music album playlist
5222 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5223 'only_matching': True,
5224 }]
5225
5226 @classmethod
5227 def suitable(cls, url):
201c1459 5228 if YoutubeTabIE.suitable(url):
5229 return False
49a57e70 5230 from ..utils import parse_qs
201c1459 5231 qs = parse_qs(url)
5232 if qs.get('v', [None])[0]:
5233 return False
5234 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5235
5236 def _real_extract(self, url):
5237 playlist_id = self._match_id(url)
46953e7e 5238 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5239 url = update_url_query(
5240 'https://www.youtube.com/playlist',
5241 parse_qs(url) or {'list': playlist_id})
5242 if is_music_url:
5243 url = smuggle_url(url, {'is_music_url': True})
5244 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5245
5246
5247class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5248 IE_DESC = 'youtu.be'
29f7c58a 5249 _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}
5250 _TESTS = [{
8bdd16b4 5251 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5252 'info_dict': {
5253 'id': 'yeWKywCrFtk',
5254 'ext': 'mp4',
5255 'title': 'Small Scale Baler and Braiding Rugs',
5256 'uploader': 'Backus-Page House Museum',
5257 'uploader_id': 'backuspagemuseum',
5258 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5259 'upload_date': '20161008',
5260 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5261 'categories': ['Nonprofits & Activism'],
5262 'tags': list,
5263 'like_count': int,
976ae3ea 5264 'age_limit': 0,
5265 'playable_in_embed': True,
5266 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5267 'channel': 'Backus-Page House Museum',
5268 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5269 'live_status': 'not_live',
5270 'view_count': int,
5271 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5272 'availability': 'public',
5273 'duration': 59,
8bdd16b4 5274 },
5275 'params': {
5276 'noplaylist': True,
5277 'skip_download': True,
5278 },
39e7107d 5279 }, {
8bdd16b4 5280 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5281 'only_matching': True,
cdc628a4
PH
5282 }]
5283
8bdd16b4 5284 def _real_extract(self, url):
5ad28e7f 5285 mobj = self._match_valid_url(url)
29f7c58a 5286 video_id = mobj.group('id')
5287 playlist_id = mobj.group('playlist_id')
8bdd16b4 5288 return self.url_result(
29f7c58a 5289 update_url_query('https://www.youtube.com/watch', {
5290 'v': video_id,
5291 'list': playlist_id,
5292 'feature': 'youtu.be',
5293 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5294
5295
b6ce9bb0 5296class YoutubeLivestreamEmbedIE(InfoExtractor):
5297 IE_DESC = 'YouTube livestream embeds'
5298 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5299 _TESTS = [{
5300 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5301 'only_matching': True,
5302 }]
5303
5304 def _real_extract(self, url):
5305 channel_id = self._match_id(url)
5306 return self.url_result(
5307 f'https://www.youtube.com/channel/{channel_id}/live',
5308 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5309
5310
8bdd16b4 5311class YoutubeYtUserIE(InfoExtractor):
96565c7e 5312 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5313 IE_NAME = 'youtube:user'
8bdd16b4 5314 _VALID_URL = r'ytuser:(?P<id>.+)'
5315 _TESTS = [{
5316 'url': 'ytuser:phihag',
5317 'only_matching': True,
5318 }]
5319
5320 def _real_extract(self, url):
5321 user_id = self._match_id(url)
5322 return self.url_result(
c586f9e8 5323 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5324 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5325
b05654f0 5326
3d3dddc9 5327class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5328 IE_NAME = 'youtube:favorites'
96565c7e 5329 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5330 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5331 _LOGIN_REQUIRED = True
5332 _TESTS = [{
5333 'url': ':ytfav',
5334 'only_matching': True,
5335 }, {
5336 'url': ':ytfavorites',
5337 'only_matching': True,
5338 }]
5339
5340 def _real_extract(self, url):
5341 return self.url_result(
5342 'https://www.youtube.com/playlist?list=LL',
5343 ie=YoutubeTabIE.ie_key())
5344
5345
a6213a49 5346class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5347 IE_DESC = 'YouTube search'
78caa52a 5348 IE_NAME = 'youtube:search'
b05654f0 5349 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5350 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5351 _TESTS = [{
5352 'url': 'ytsearch5:youtube-dl test video',
5353 'playlist_count': 5,
5354 'info_dict': {
5355 'id': 'youtube-dl test video',
5356 'title': 'youtube-dl test video',
5357 }
5358 }]
b05654f0 5359
a61fd4cf 5360
5f7cb91a 5361class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5362 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5363 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5364 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5365 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5366 _TESTS = [{
5367 'url': 'ytsearchdate5:youtube-dl test video',
5368 'playlist_count': 5,
5369 'info_dict': {
5370 'id': 'youtube-dl test video',
5371 'title': 'youtube-dl test video',
5372 }
5373 }]
75dff0ee 5374
c9ae7b95 5375
a6213a49 5376class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5377 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5378 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5379 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5380 _TESTS = [{
5381 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5382 'playlist_mincount': 5,
5383 'info_dict': {
11f9be09 5384 'id': 'youtube-dl test video',
3462ffa8 5385 'title': 'youtube-dl test video',
5386 }
a61fd4cf 5387 }, {
5388 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5389 'playlist_mincount': 5,
5390 'info_dict': {
5391 'id': 'python',
5392 'title': 'python',
5393 }
5394
3462ffa8 5395 }, {
5396 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5397 'only_matching': True,
5398 }]
5399
5400 def _real_extract(self, url):
4dfbf869 5401 qs = parse_qs(url)
386e1dd9 5402 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5403 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5404
5405
16aa9ea4 5406class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5407 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5408 IE_NAME = 'youtube:music:search_url'
5409 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5410 _TESTS = [{
5411 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5412 'playlist_count': 16,
5413 'info_dict': {
5414 'id': 'royalty free music',
5415 'title': 'royalty free music',
5416 }
5417 }, {
5418 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5419 'playlist_mincount': 30,
5420 'info_dict': {
5421 'id': 'royalty free music - songs',
5422 'title': 'royalty free music - songs',
5423 },
5424 'params': {'extract_flat': 'in_playlist'}
5425 }, {
5426 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5427 'playlist_mincount': 30,
5428 'info_dict': {
5429 'id': 'royalty free music - community playlists',
5430 'title': 'royalty free music - community playlists',
5431 },
5432 'params': {'extract_flat': 'in_playlist'}
5433 }]
5434
5435 _SECTIONS = {
5436 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5437 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5438 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5439 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5440 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5441 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5442 }
5443
5444 def _real_extract(self, url):
5445 qs = parse_qs(url)
5446 query = (qs.get('search_query') or qs.get('q'))[0]
5447 params = qs.get('sp', (None,))[0]
5448 if params:
5449 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5450 else:
5451 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5452 params = self._SECTIONS.get(section)
5453 if not params:
5454 section = None
5455 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5456 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5457
5458
182bda88 5459class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5460 """
25f14e9f 5461 Base class for feed extractors
3d3dddc9 5462 Subclasses must define the _FEED_NAME property.
d7ae0639 5463 """
b2e8bc1b 5464 _LOGIN_REQUIRED = True
ef2f3c7f 5465 _TESTS = []
d7ae0639
JMF
5466
5467 @property
5468 def IE_NAME(self):
78caa52a 5469 return 'youtube:%s' % self._FEED_NAME
04cc9617 5470
3853309f 5471 def _real_extract(self, url):
3d3dddc9 5472 return self.url_result(
182bda88 5473 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5474
5475
ef2f3c7f 5476class YoutubeWatchLaterIE(InfoExtractor):
5477 IE_NAME = 'youtube:watchlater'
96565c7e 5478 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5479 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5480 _TESTS = [{
8bdd16b4 5481 'url': ':ytwatchlater',
bc7a9cd8
S
5482 'only_matching': True,
5483 }]
25f14e9f
S
5484
5485 def _real_extract(self, url):
ef2f3c7f 5486 return self.url_result(
5487 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5488
5489
25f14e9f 5490class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5491 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5492 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5493 _FEED_NAME = 'recommended'
45db527f 5494 _LOGIN_REQUIRED = False
3d3dddc9 5495 _TESTS = [{
5496 'url': ':ytrec',
5497 'only_matching': True,
5498 }, {
5499 'url': ':ytrecommended',
5500 'only_matching': True,
5501 }, {
5502 'url': 'https://youtube.com',
5503 'only_matching': True,
5504 }]
1ed5b5c9 5505
1ed5b5c9 5506
25f14e9f 5507class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5508 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5509 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5510 _FEED_NAME = 'subscriptions'
3d3dddc9 5511 _TESTS = [{
5512 'url': ':ytsubs',
5513 'only_matching': True,
5514 }, {
5515 'url': ':ytsubscriptions',
5516 'only_matching': True,
5517 }]
1ed5b5c9 5518
1ed5b5c9 5519
25f14e9f 5520class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5521 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5522 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5523 _FEED_NAME = 'history'
3d3dddc9 5524 _TESTS = [{
5525 'url': ':ythistory',
5526 'only_matching': True,
5527 }]
1ed5b5c9
JMF
5528
5529
15870e90
PH
5530class YoutubeTruncatedURLIE(InfoExtractor):
5531 IE_NAME = 'youtube:truncated_url'
5532 IE_DESC = False # Do not list
975d35db 5533 _VALID_URL = r'''(?x)
b95aab84
PH
5534 (?:https?://)?
5535 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5536 (?:watch\?(?:
c4808c60 5537 feature=[a-z_]+|
b95aab84
PH
5538 annotation_id=annotation_[^&]+|
5539 x-yt-cl=[0-9]+|
c1708b89 5540 hl=[^&]*|
287be8c6 5541 t=[0-9]+
b95aab84
PH
5542 )?
5543 |
5544 attribution_link\?a=[^&]+
5545 )
5546 $
975d35db 5547 '''
15870e90 5548
c4808c60 5549 _TESTS = [{
2d3d2997 5550 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5551 'only_matching': True,
dc2fc736 5552 }, {
2d3d2997 5553 'url': 'https://www.youtube.com/watch?',
dc2fc736 5554 'only_matching': True,
b95aab84
PH
5555 }, {
5556 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5557 'only_matching': True,
5558 }, {
5559 'url': 'https://www.youtube.com/watch?feature=foo',
5560 'only_matching': True,
c1708b89
PH
5561 }, {
5562 'url': 'https://www.youtube.com/watch?hl=en-GB',
5563 'only_matching': True,
287be8c6
PH
5564 }, {
5565 'url': 'https://www.youtube.com/watch?t=2372',
5566 'only_matching': True,
c4808c60
PH
5567 }]
5568
15870e90
PH
5569 def _real_extract(self, url):
5570 raise ExtractorError(
78caa52a
PH
5571 'Did you forget to quote the URL? Remember that & is a meta '
5572 'character in most shells, so you want to put the URL in quotes, '
3867038a 5573 'like youtube-dl '
2d3d2997 5574 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5575 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5576 expected=True)
772fd5cc
PH
5577
5578
3cd786db 5579class YoutubeClipIE(InfoExtractor):
5580 IE_NAME = 'youtube:clip'
5581 IE_DESC = False # Do not list
5582 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5583
5584 def _real_extract(self, url):
5585 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5586 return self.url_result(url, 'Generic')
5587
5588
772fd5cc
PH
5589class YoutubeTruncatedIDIE(InfoExtractor):
5590 IE_NAME = 'youtube:truncated_id'
5591 IE_DESC = False # Do not list
b95aab84 5592 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5593
5594 _TESTS = [{
5595 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5596 'only_matching': True,
5597 }]
5598
5599 def _real_extract(self, url):
5600 video_id = self._match_id(url)
5601 raise ExtractorError(
5602 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5603 expected=True)