]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[ffmpeg] Cache version data
[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,
ff91cf74 42 get_first,
dd27fd17 43 int_or_none,
641ad5d8 44 is_html,
34921b43 45 join_nonempty,
48416bc4 46 js_to_json,
94278f72 47 mimetype2ext,
9c0d7f49 48 network_exceptions,
a6213a49 49 NO_DEFAULT,
11f9be09 50 orderedSet,
6310acf5 51 parse_codecs,
49bd8c66 52 parse_count,
7c80519c 53 parse_duration,
7ea65411 54 parse_iso8601,
4dfbf869 55 parse_qs,
dca3ff4a 56 qualities,
c0ac49bc 57 remove_end,
3995d37d 58 remove_start,
cf7e015f 59 smuggle_url,
dbdaaa23 60 str_or_none,
c93d53f5 61 str_to_int,
f3aa3c3f 62 strftime_or_none,
7c365c21 63 traverse_obj,
556dbe7f 64 try_get,
c5e8d7af
PH
65 unescapeHTML,
66 unified_strdate,
f0d785d3 67 unified_timestamp,
cf7e015f 68 unsmuggle_url,
8bdd16b4 69 update_url_query,
21c340b8 70 url_or_none,
fe93e2c4 71 urljoin,
7c365c21 72 variadic,
c5e8d7af
PH
73)
74
5f6a1245 75
000c15a4 76# any clients starting with _ cannot be explicity requested by the user
77INNERTUBE_CLIENTS = {
78 'web': {
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
81 'client': {
82 'clientName': 'WEB',
18c7683d 83 'clientVersion': '2.20211221.00.00',
000c15a4 84 }
85 },
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
87 },
88 'web_embedded': {
89 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 93 'clientVersion': '1.20211215.00.01',
000c15a4 94 },
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
97 },
98 'web_music': {
99 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
100 'INNERTUBE_HOST': 'music.youtube.com',
101 'INNERTUBE_CONTEXT': {
102 'client': {
103 'clientName': 'WEB_REMIX',
18c7683d 104 'clientVersion': '1.20211213.00.00',
000c15a4 105 }
106 },
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
108 },
e7e94f2a 109 'web_creator': {
18c7683d 110 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
111 'INNERTUBE_CONTEXT': {
112 'client': {
113 'clientName': 'WEB_CREATOR',
18c7683d 114 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
115 }
116 },
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
118 },
000c15a4 119 'android': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID',
18c7683d 124 'clientVersion': '16.49',
000c15a4 125 }
126 },
127 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 128 'REQUIRE_JS_PLAYER': False
000c15a4 129 },
130 'android_embedded': {
18c7683d 131 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 132 'INNERTUBE_CONTEXT': {
133 'client': {
134 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 135 'clientVersion': '16.49',
000c15a4 136 },
137 },
b6de707d 138 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
139 'REQUIRE_JS_PLAYER': False
000c15a4 140 },
141 'android_music': {
18c7683d 142 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_MUSIC',
18c7683d 146 'clientVersion': '4.57',
000c15a4 147 }
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 150 'REQUIRE_JS_PLAYER': False
000c15a4 151 },
e7e94f2a 152 'android_creator': {
18c7683d 153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
154 'INNERTUBE_CONTEXT': {
155 'client': {
156 'clientName': 'ANDROID_CREATOR',
18c7683d 157 'clientVersion': '21.47',
e7e94f2a
D
158 },
159 },
b6de707d 160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
e7e94f2a 162 },
18c7683d 163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 165 'ios': {
18c7683d 166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS',
18c7683d 170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
000c15a4 172 }
173 },
b6de707d 174 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
175 'REQUIRE_JS_PLAYER': False
000c15a4 176 },
177 'ios_embedded': {
000c15a4 178 'INNERTUBE_CONTEXT': {
179 'client': {
180 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 181 'clientVersion': '16.46',
182 'deviceModel': 'iPhone14,3',
000c15a4 183 },
184 },
b6de707d 185 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
186 'REQUIRE_JS_PLAYER': False
000c15a4 187 },
188 'ios_music': {
18c7683d 189 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 190 'INNERTUBE_CONTEXT': {
191 'client': {
192 'clientName': 'IOS_MUSIC',
18c7683d 193 'clientVersion': '4.57',
000c15a4 194 },
195 },
b6de707d 196 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
197 'REQUIRE_JS_PLAYER': False
000c15a4 198 },
e7e94f2a
D
199 'ios_creator': {
200 'INNERTUBE_CONTEXT': {
201 'client': {
202 'clientName': 'IOS_CREATOR',
18c7683d 203 'clientVersion': '21.47',
e7e94f2a
D
204 },
205 },
b6de707d 206 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
207 'REQUIRE_JS_PLAYER': False
e7e94f2a 208 },
3619f78d 209 # mweb has 'ultralow' formats
210 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 211 'mweb': {
18c7683d 212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 213 'INNERTUBE_CONTEXT': {
214 'client': {
215 'clientName': 'MWEB',
18c7683d 216 'clientVersion': '2.20211221.01.00',
000c15a4 217 }
218 },
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
18c7683d 220 }
000c15a4 221}
222
223
224def build_innertube_clients():
2e4cacd0 225 THIRD_PARTY = {
65c2fde2 226 'embedUrl': 'https://google.com', # Can be any valid URL
227 }
2e4cacd0 228 BASE_CLIENTS = ('android', 'web', 'ios', 'mweb')
229 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 230
231 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 232 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 233 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 234 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 235 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 236
2e4cacd0 237 base_client, *variant = client.split('_')
238 ytcfg['priority'] = 10 * priority(base_client)
239
e48b3875 240 if not variant:
241 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
000c15a4 242 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
e48b3875 243 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 244 agegate_ytcfg['priority'] -= 1
e48b3875 245 elif variant == ['embedded']:
246 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 247 ytcfg['priority'] -= 2
e48b3875 248 else:
000c15a4 249 ytcfg['priority'] -= 3
250
251
252build_innertube_clients()
253
254
de7f3446 255class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 256 """Provide base functions for Youtube extractors"""
e00eb564 257
3462ffa8 258 _RESERVED_NAMES = (
3cd786db 259 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 260 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 261 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 262 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 263
3619f78d 264 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
265
52efa4b3 266 # _NETRC_MACHINE = 'youtube'
3619f78d 267
b2e8bc1b
JMF
268 # If True it will raise an error if no login info is provided
269 _LOGIN_REQUIRED = False
270
d9190e44
RH
271 _INVIDIOUS_SITES = (
272 # invidious-redirect websites
273 r'(?:www\.)?redirect\.invidious\.io',
274 r'(?:(?:www|dev)\.)?invidio\.us',
275 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
276 r'(?:www\.)?invidious\.pussthecat\.org',
277 r'(?:www\.)?invidious\.zee\.li',
278 r'(?:www\.)?invidious\.ethibox\.fr',
279 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
280 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
281 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
282 # youtube-dl invidious instances list
283 r'(?:(?:www|no)\.)?invidiou\.sh',
284 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
285 r'(?:www\.)?invidious\.kabi\.tk',
286 r'(?:www\.)?invidious\.mastodon\.host',
287 r'(?:www\.)?invidious\.zapashcanon\.fr',
288 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
289 r'(?:www\.)?invidious\.tinfoil-hat\.net',
290 r'(?:www\.)?invidious\.himiko\.cloud',
291 r'(?:www\.)?invidious\.reallyancient\.tech',
292 r'(?:www\.)?invidious\.tube',
293 r'(?:www\.)?invidiou\.site',
294 r'(?:www\.)?invidious\.site',
295 r'(?:www\.)?invidious\.xyz',
296 r'(?:www\.)?invidious\.nixnet\.xyz',
297 r'(?:www\.)?invidious\.048596\.xyz',
298 r'(?:www\.)?invidious\.drycat\.fr',
299 r'(?:www\.)?inv\.skyn3t\.in',
300 r'(?:www\.)?tube\.poal\.co',
301 r'(?:www\.)?tube\.connect\.cafe',
302 r'(?:www\.)?vid\.wxzm\.sx',
303 r'(?:www\.)?vid\.mint\.lgbt',
304 r'(?:www\.)?vid\.puffyan\.us',
305 r'(?:www\.)?yewtu\.be',
306 r'(?:www\.)?yt\.elukerio\.org',
307 r'(?:www\.)?yt\.lelux\.fi',
308 r'(?:www\.)?invidious\.ggc-project\.de',
309 r'(?:www\.)?yt\.maisputain\.ovh',
310 r'(?:www\.)?ytprivate\.com',
311 r'(?:www\.)?invidious\.13ad\.de',
312 r'(?:www\.)?invidious\.toot\.koeln',
313 r'(?:www\.)?invidious\.fdn\.fr',
314 r'(?:www\.)?watch\.nettohikari\.com',
315 r'(?:www\.)?invidious\.namazso\.eu',
316 r'(?:www\.)?invidious\.silkky\.cloud',
317 r'(?:www\.)?invidious\.exonip\.de',
318 r'(?:www\.)?invidious\.riverside\.rocks',
319 r'(?:www\.)?invidious\.blamefran\.net',
320 r'(?:www\.)?invidious\.moomoo\.de',
321 r'(?:www\.)?ytb\.trom\.tf',
322 r'(?:www\.)?yt\.cyberhost\.uk',
323 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
324 r'(?:www\.)?qklhadlycap4cnod\.onion',
325 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
326 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
327 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
328 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
329 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
330 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
331 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
332 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
333 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
334 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
335 )
336
cce889b9 337 def _initialize_consent(self):
338 cookies = self._get_cookies('https://www.youtube.com/')
339 if cookies.get('__Secure-3PSID'):
340 return
341 consent_id = None
342 consent = cookies.get('CONSENT')
343 if consent:
344 if 'YES' in consent.value:
345 return
346 consent_id = self._search_regex(
347 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
348 if not consent_id:
349 consent_id = random.randint(100, 999)
350 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 351
f3aa3c3f 352 def _initialize_pref(self):
353 cookies = self._get_cookies('https://www.youtube.com/')
354 pref_cookie = cookies.get('PREF')
355 pref = {}
356 if pref_cookie:
357 try:
358 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
359 except ValueError:
360 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 361 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 362 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
363
b2e8bc1b 364 def _real_initialize(self):
f3aa3c3f 365 self._initialize_pref()
cce889b9 366 self._initialize_consent()
52efa4b3 367 if (self._LOGIN_REQUIRED
368 and self.get_param('cookiefile') is None
369 and self.get_param('cookiesfrombrowser') is None):
370 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 371
a0566bbf 372 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 373 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
374 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 375
000c15a4 376 def _get_default_ytcfg(self, client='web'):
377 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 378
000c15a4 379 def _get_innertube_host(self, client='web'):
380 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 381
000c15a4 382 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 383 # try_get but with fallback to default ytcfg client values when present
384 _func = lambda y: try_get(y, getter, expected_type)
385 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
386
000c15a4 387 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 388 return self._ytcfg_get_safe(
389 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
390 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 391
000c15a4 392 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 393 return self._ytcfg_get_safe(
394 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
395 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 396
000c15a4 397 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 398 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
399
000c15a4 400 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 401 context = get_first(
402 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 403 # Enforce language and tz for extraction
404 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
405 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 406 return context
407
cf87314d 408 _SAPISID = None
409
109dd3b2 410 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 411 time_now = round(time.time())
cf87314d 412 if self._SAPISID is None:
413 yt_cookies = self._get_cookies('https://www.youtube.com')
414 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
415 # See: https://github.com/yt-dlp/yt-dlp/issues/393
416 sapisid_cookie = dict_get(
417 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
418 if sapisid_cookie and sapisid_cookie.value:
419 self._SAPISID = sapisid_cookie.value
420 self.write_debug('Extracted SAPISID cookie')
421 # SAPISID cookie is required if not already present
422 if not yt_cookies.get('SAPISID'):
423 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
424 self._set_cookie(
425 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
426 else:
427 self._SAPISID = False
428 if not self._SAPISID:
429 return None
1974e99f 430 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
431 sapisidhash = hashlib.sha1(
cf87314d 432 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 433 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
434
435 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 436 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 437 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 438
109dd3b2 439 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 440 data.update(query)
11f9be09 441 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 442 real_headers.update({'content-type': 'application/json'})
443 if headers:
444 real_headers.update(headers)
545cc85d 445 return self._download_json(
109dd3b2 446 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 447 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 448 data=json.dumps(data).encode('utf8'), headers=real_headers,
5dbc77df 449 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
f4f751af 450
ac56cf38 451 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
452 data = self._search_regex(
453 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
454 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
455 if data:
456 return self._parse_json(data, item_id, fatal=fatal)
0c148415 457
99e9e001 458 @staticmethod
459 def _extract_session_index(*data):
460 """
461 Index of current account in account list.
462 See: https://github.com/yt-dlp/yt-dlp/pull/519
463 """
464 for ytcfg in data:
465 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
466 if session_index is not None:
467 return session_index
468
469 # Deprecated?
470 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
471 if ytcfg:
472 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
473 if token:
474 return token
99e9e001 475 if webpage:
476 return self._search_regex(
477 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
478 'identity token', default=None, fatal=False)
a1c5d2ca
M
479
480 @staticmethod
fe93e2c4 481 def _extract_account_syncid(*args):
8ea3f7b9 482 """
483 Extract syncId required to download private playlists of secondary channels
fe93e2c4 484 @params response and/or ytcfg
8ea3f7b9 485 """
fe93e2c4 486 for data in args:
487 # ytcfg includes channel_syncid if on secondary channel
488 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
489 if delegated_sid:
490 return delegated_sid
491 sync_ids = (try_get(
492 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 493 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 494 if len(sync_ids) >= 2 and sync_ids[1]:
495 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
496 # and just "user_syncid||" for primary channel. We only want the channel_syncid
497 return sync_ids[0]
a1c5d2ca 498
ac56cf38 499 @staticmethod
500 def _extract_visitor_data(*args):
501 """
502 Extracts visitorData from an API response or ytcfg
503 Appears to be used to track session state
504 """
9222c381 505 return get_first(
6c73052c 506 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 507 expected_type=str)
ac56cf38 508
99e9e001 509 @property
510 def is_authenticated(self):
511 return bool(self._generate_sapisidhash_header())
512
11f9be09 513 def extract_ytcfg(self, video_id, webpage):
8c54a305 514 if not webpage:
515 return {}
29f7c58a 516 return self._parse_json(
517 self._search_regex(
518 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 519 default='{}'), video_id, fatal=False) or {}
520
11f9be09 521 def generate_api_headers(
99e9e001 522 self, *, ytcfg=None, account_syncid=None, session_index=None,
523 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
524
11f9be09 525 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 526 headers = {
109dd3b2 527 'X-YouTube-Client-Name': compat_str(
11f9be09 528 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
529 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 530 'Origin': origin,
531 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
532 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 533 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 534 }
535 if session_index is None:
314ee305 536 session_index = self._extract_session_index(ytcfg)
537 if account_syncid or session_index is not None:
538 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 539
109dd3b2 540 auth = self._generate_sapisidhash_header(origin)
f4f751af 541 if auth is not None:
542 headers['Authorization'] = auth
109dd3b2 543 headers['X-Origin'] = origin
99e9e001 544 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 545
2d6659b9 546 @staticmethod
547 def _build_api_continuation_query(continuation, ctp=None):
548 query = {
549 'continuation': continuation
550 }
551 # TODO: Inconsistency with clickTrackingParams.
552 # Currently we have a fixed ctp contained within context (from ytcfg)
553 # and a ctp in root query for continuation.
554 if ctp:
555 query['clickTracking'] = {'clickTrackingParams': ctp}
556 return query
557
2d6659b9 558 @classmethod
559 def _extract_next_continuation_data(cls, renderer):
560 next_continuation = try_get(
561 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
562 lambda x: x['continuation']['reloadContinuationData']), dict)
563 if not next_continuation:
564 return
565 continuation = next_continuation.get('continuation')
566 if not continuation:
567 return
568 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 569 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 570
571 @classmethod
572 def _extract_continuation_ep_data(cls, continuation_ep: dict):
573 if isinstance(continuation_ep, dict):
574 continuation = try_get(
575 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
576 if not continuation:
577 return
578 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 579 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 580
581 @classmethod
582 def _extract_continuation(cls, renderer):
583 next_continuation = cls._extract_next_continuation_data(renderer)
584 if next_continuation:
585 return next_continuation
fe93e2c4 586
2d6659b9 587 contents = []
588 for key in ('contents', 'items'):
589 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 590
2d6659b9 591 for content in contents:
592 if not isinstance(content, dict):
593 continue
594 continuation_ep = try_get(
595 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
596 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
597 dict)
598 continuation = cls._extract_continuation_ep_data(continuation_ep)
599 if continuation:
600 return continuation
601
fe93e2c4 602 @classmethod
603 def _extract_alerts(cls, data):
109dd3b2 604 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
605 if not isinstance(alert_dict, dict):
606 continue
607 for alert in alert_dict.values():
608 alert_type = alert.get('type')
609 if not alert_type:
610 continue
052e1350 611 message = cls._get_text(alert, 'text')
109dd3b2 612 if message:
613 yield alert_type, message
614
c0ac49bc 615 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 616 errors = []
617 warnings = []
618 for alert_type, alert_message in alerts:
641ad5d8 619 if alert_type.lower() == 'error' and fatal:
109dd3b2 620 errors.append([alert_type, alert_message])
621 else:
622 warnings.append([alert_type, alert_message])
623
624 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 625 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 626 if errors:
627 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
628
629 def _extract_and_report_alerts(self, data, *args, **kwargs):
630 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
631
47193e02 632 def _extract_badges(self, renderer: dict):
633 badges = set()
634 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
635 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
636 if label:
637 badges.add(label.lower())
638 return badges
639
640 @staticmethod
052e1350 641 def _get_text(data, *path_list, max_runs=None):
642 for path in path_list or [None]:
643 if path is None:
644 obj = [data]
645 else:
646 obj = traverse_obj(data, path, default=[])
647 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
648 obj = [obj]
649 for item in obj:
650 text = try_get(item, lambda x: x['simpleText'], compat_str)
651 if text:
652 return text
653 runs = try_get(item, lambda x: x['runs'], list) or []
654 if not runs and isinstance(item, list):
655 runs = item
656
657 runs = runs[:min(len(runs), max_runs or len(runs))]
658 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
659 if text:
660 return text
47193e02 661
f0d785d3 662 def _get_count(self, data, *path_list):
663 count_text = self._get_text(data, *path_list) or ''
664 count = parse_count(count_text)
665 if count is None:
666 count = str_to_int(
667 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
668 return count
669
a709d873 670 @staticmethod
671 def _extract_thumbnails(data, *path_list):
672 """
673 Extract thumbnails from thumbnails dict
674 @param path_list: path list to level that contains 'thumbnails' key
675 """
676 thumbnails = []
677 for path in path_list or [()]:
678 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
679 thumbnail_url = url_or_none(thumbnail.get('url'))
680 if not thumbnail_url:
681 continue
682 # Sometimes youtube gives a wrong thumbnail URL. See:
683 # https://github.com/yt-dlp/yt-dlp/issues/233
684 # https://github.com/ytdl-org/youtube-dl/issues/28023
685 if 'maxresdefault' in thumbnail_url:
686 thumbnail_url = thumbnail_url.split('?')[0]
687 thumbnails.append({
688 'url': thumbnail_url,
689 'height': int_or_none(thumbnail.get('height')),
690 'width': int_or_none(thumbnail.get('width')),
691 })
692 return thumbnails
693
f3aa3c3f 694 @staticmethod
695 def extract_relative_time(relative_time_text):
696 """
697 Extracts a relative time from string and converts to dt object
f0d785d3 698 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 699 """
f0d785d3 700 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
f3aa3c3f 701 if mobj:
f0d785d3 702 start = mobj.group('start')
703 if start:
704 return datetime_from_str(start)
f3aa3c3f 705 try:
f0d785d3 706 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 707 except ValueError:
708 return None
709
710 def _extract_time_text(self, renderer, *path_list):
711 text = self._get_text(renderer, *path_list) or ''
712 dt = self.extract_relative_time(text)
713 timestamp = None
714 if isinstance(dt, datetime.datetime):
715 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 716
717 if timestamp is None:
718 timestamp = (
719 unified_timestamp(text) or unified_timestamp(
720 self._search_regex(
17322130 721 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 722 text.lower(), 'time text', default=None)))
f0d785d3 723
f3aa3c3f 724 if text and timestamp is None:
17322130 725 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 726 return timestamp, text
727
109dd3b2 728 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
729 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 730 default_client='web'):
109dd3b2 731 response = None
732 last_error = None
733 count = -1
734 retries = self.get_param('extractor_retries', 3)
735 if check_get_keys is None:
736 check_get_keys = []
737 while count < retries:
738 count += 1
739 if last_error:
c0ac49bc 740 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 741 try:
742 response = self._call_api(
743 ep=ep, fatal=True, headers=headers,
744 video_id=item_id, query=query,
745 context=self._extract_context(ytcfg, default_client),
746 api_key=self._extract_api_key(ytcfg, default_client),
747 api_hostname=api_hostname, default_client=default_client,
748 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
749 except ExtractorError as e:
9c0d7f49 750 if isinstance(e.cause, network_exceptions):
87e8e8a7 751 if isinstance(e.cause, compat_HTTPError):
752 first_bytes = e.cause.read(512)
753 if not is_html(first_bytes):
754 yt_error = try_get(
755 self._parse_json(
756 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
757 lambda x: x['error']['message'], compat_str)
758 if yt_error:
759 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 760 # Downloading page may result in intermittent 5xx HTTP error
761 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 762 # We also want to catch all other network exceptions since errors in later pages can be troublesome
763 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
764 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 765 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 766 if count < retries:
767 continue
109dd3b2 768 if fatal:
769 raise
770 else:
771 self.report_warning(error_to_compat_str(e))
772 return
773
774 else:
109dd3b2 775 try:
ac56cf38 776 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 777 except ExtractorError as e:
c0ac49bc 778 # YouTube servers may return errors we want to retry on in a 200 OK response
779 # See: https://github.com/yt-dlp/yt-dlp/issues/839
780 if 'unknown error' in e.msg.lower():
781 last_error = e.msg
782 continue
109dd3b2 783 if fatal:
784 raise
785 self.report_warning(error_to_compat_str(e))
786 return
787 if not check_get_keys or dict_get(response, check_get_keys):
788 break
789 # Youtube sometimes sends incomplete data
790 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
791 last_error = 'Incomplete data received'
792 if count >= retries:
793 if fatal:
794 raise ExtractorError(last_error)
795 else:
796 self.report_warning(last_error)
797 return
798 return response
799
9297939e 800 @staticmethod
801 def is_music_url(url):
802 return re.match(r'https?://music\.youtube\.com/', url) is not None
803
30a074c2 804 def _extract_video(self, renderer):
805 video_id = renderer.get('videoId')
052e1350 806 title = self._get_text(renderer, 'title')
807 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 808 duration = parse_duration(self._get_text(
809 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 810 if duration is None:
811 duration = parse_duration(self._search_regex(
812 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
813 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
814 video_id, default=None, group='duration'))
815
f0d785d3 816 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 817
052e1350 818 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 819 channel_id = traverse_obj(
820 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
821 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
822 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
823 overlay_style = traverse_obj(
824 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
825 badges = self._extract_badges(renderer)
a709d873 826 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 827 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
828 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'), expected_type=str))
829 url = f'https://www.youtube.com/watch?v={video_id}'
830 if overlay_style == 'SHORTS' or (navigation_url and '/shorts/' in navigation_url):
831 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 832
30a074c2 833 return {
39ed931e 834 '_type': 'url',
30a074c2 835 'ie_key': YoutubeIE.ie_key(),
836 'id': video_id,
fd2ad7cb 837 'url': url,
30a074c2 838 'title': title,
839 'description': description,
840 'duration': duration,
841 'view_count': view_count,
842 'uploader': uploader,
f3aa3c3f 843 'channel_id': channel_id,
a709d873 844 'thumbnails': thumbnails,
a30a6ed3 845 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 846 'live_status': ('is_upcoming' if scheduled_timestamp is not None
847 else 'was_live' if 'streamed' in time_text.lower()
848 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
849 else None),
850 'release_timestamp': scheduled_timestamp,
851 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 852 }
853
0c148415 854
360e1ca5 855class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 856 IE_DESC = 'YouTube'
cb7dfeea 857 _VALID_URL = r"""(?x)^
c5e8d7af 858 (
edb53e2d 859 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 860 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
861 (?:www\.)?deturl\.com/www\.youtube\.com|
862 (?:www\.)?pwnyoutube\.com|
863 (?:www\.)?hooktube\.com|
864 (?:www\.)?yourepeat\.com|
865 tube\.majestyc\.net|
866 %(invidious)s|
867 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
868 (?:.*?\#/)? # handle anchor (#/) redirect urls
869 (?: # the various things that can precede the ID:
b6ce9bb0 870 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 871 |(?: # or the v= param in all its forms
f7000f3a 872 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 873 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 874 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
875 v=
876 )
f4b05232 877 ))
cbaed4bb
S
878 |(?:
879 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
880 vid\.plus| # or vid.plus/xxxx
881 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 882 %(invidious)s
cbaed4bb 883 )/
edb53e2d 884 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 885 )
c5e8d7af 886 )? # all until now is optional -> you can pass the naked ID
201c1459 887 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 888 (?(1).+)? # if we found the ID, everything can follow
9297939e 889 (?:\#|$)""" % {
d9190e44 890 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 891 }
e40c758c 892 _PLAYER_INFO_RE = (
cc2db878 893 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
894 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$',
545cc85d 895 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 896 )
2c62dc26 897 _formats = {
c2d3cb4c 898 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
899 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
900 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
901 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
902 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
903 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
904 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
905 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 906 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 907 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
908 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
909 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
910 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
911 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
912 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 913 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 914 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
915 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 916
917
918 # 3D videos
c2d3cb4c 919 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
920 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
921 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
922 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 923 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
924 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
925 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 926
96fb5605 927 # Apple HTTP Live Streaming
11f12195 928 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 929 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
930 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
931 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
932 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
933 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 934 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
935 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
936
937 # DASH mp4 video
d23028a8
S
938 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
939 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
940 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
942 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 943 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
944 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
945 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
946 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
947 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
948 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
949 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 950
f6f1fc92 951 # Dash mp4 audio
d23028a8
S
952 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
953 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
954 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
955 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
956 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
957 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
958 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
959
960 # Dash webm
d23028a8
S
961 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
962 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
963 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
967 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
968 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
969 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
970 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 976 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
977 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
978 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
979 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
980 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
981 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
982 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
983
984 # Dash webm audio
d23028a8
S
985 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
986 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 987
0857baad 988 # Dash webm audio with opus inside
d23028a8
S
989 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
990 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
991 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 992
ce6b9a2d
PH
993 # RTMP (unnamed)
994 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
995
996 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
997 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
998 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
999 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1000 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1001 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1002 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1003 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1004 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1005 }
29f7c58a 1006 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1007
fd5c4aab
S
1008 _GEO_BYPASS = False
1009
78caa52a 1010 IE_NAME = 'youtube'
2eb88d95
PH
1011 _TESTS = [
1012 {
2d3d2997 1013 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1014 'info_dict': {
1015 'id': 'BaW_jenozKc',
1016 'ext': 'mp4',
3867038a 1017 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1018 'uploader': 'Philipp Hagemeister',
1019 'uploader_id': 'phihag',
ec85ded8 1020 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1021 'channel': 'Philipp Hagemeister',
dd4c4492
S
1022 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1023 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1024 'upload_date': '20121002',
ff9f925b 1025 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1026 'categories': ['Science & Technology'],
3867038a 1027 'tags': ['youtube-dl'],
556dbe7f 1028 'duration': 10,
dbdaaa23 1029 'view_count': int,
3e7c1224 1030 'like_count': int,
ff9f925b 1031 'availability': 'public',
1032 'playable_in_embed': True,
1033 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1034 'live_status': 'not_live',
1035 'age_limit': 0,
7c80519c 1036 'start_time': 1,
297a564b 1037 'end_time': 9,
6c73052c 1038 'channel_follower_count': int
2eb88d95 1039 }
0e853ca4 1040 },
fccd3771 1041 {
4bc3a23e
PH
1042 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1043 'note': 'Embed-only video (#1746)',
1044 'info_dict': {
1045 'id': 'yZIXLfi8CZQ',
1046 'ext': 'mp4',
1047 'upload_date': '20120608',
1048 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1049 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1050 'uploader': 'SET India',
94bfcd23 1051 'uploader_id': 'setindia',
ec85ded8 1052 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1053 'age_limit': 18,
545cc85d 1054 },
1055 'skip': 'Private video',
fccd3771 1056 },
11b56058 1057 {
8bdd16b4 1058 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1059 'note': 'Use the first video ID in the URL',
1060 'info_dict': {
1061 'id': 'BaW_jenozKc',
1062 'ext': 'mp4',
3867038a 1063 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1064 'uploader': 'Philipp Hagemeister',
1065 'uploader_id': 'phihag',
ec85ded8 1066 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1067 'channel': 'Philipp Hagemeister',
1068 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1069 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1070 'upload_date': '20121002',
976ae3ea 1071 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1072 'categories': ['Science & Technology'],
3867038a 1073 'tags': ['youtube-dl'],
556dbe7f 1074 'duration': 10,
dbdaaa23 1075 'view_count': int,
11b56058 1076 'like_count': int,
976ae3ea 1077 'availability': 'public',
1078 'playable_in_embed': True,
1079 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1080 'live_status': 'not_live',
1081 'age_limit': 0,
6c73052c 1082 'channel_follower_count': int
34a7de29
S
1083 },
1084 'params': {
1085 'skip_download': True,
1086 },
11b56058 1087 },
dd27fd17 1088 {
2d3d2997 1089 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1090 'note': '256k DASH audio (format 141) via DASH manifest',
1091 'info_dict': {
1092 'id': 'a9LDPn-MO4I',
1093 'ext': 'm4a',
1094 'upload_date': '20121002',
1095 'uploader_id': '8KVIDEO',
ec85ded8 1096 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1097 'description': '',
1098 'uploader': '8KVIDEO',
1099 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1100 },
4bc3a23e
PH
1101 'params': {
1102 'youtube_include_dash_manifest': True,
1103 'format': '141',
4919603f 1104 },
de3c7fe0 1105 'skip': 'format 141 not served anymore',
dd27fd17 1106 },
8bdd16b4 1107 # DASH manifest with encrypted signature
1108 {
1109 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1110 'info_dict': {
1111 'id': 'IB3lcPjvWLA',
1112 'ext': 'm4a',
1113 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1114 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1115 'duration': 244,
1116 'uploader': 'AfrojackVEVO',
1117 'uploader_id': 'AfrojackVEVO',
1118 'upload_date': '20131011',
cc2db878 1119 'abr': 129.495,
976ae3ea 1120 'like_count': int,
1121 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1122 'playable_in_embed': True,
1123 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1124 'view_count': int,
1125 'track': 'The Spark',
1126 'live_status': 'not_live',
1127 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1128 'channel': 'Afrojack',
1129 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1130 'tags': 'count:19',
1131 'availability': 'public',
1132 'categories': ['Music'],
1133 'age_limit': 0,
1134 'alt_title': 'The Spark',
6c73052c 1135 'channel_follower_count': int
8bdd16b4 1136 },
1137 'params': {
1138 'youtube_include_dash_manifest': True,
1139 'format': '141/bestaudio[ext=m4a]',
1140 },
1141 },
65c2fde2 1142 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1143 {
65c2fde2 1144 'note': 'Embed allowed age-gate video',
2d3d2997 1145 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1146 'info_dict': {
1147 'id': 'HtVdAasjOgU',
1148 'ext': 'mp4',
1149 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1150 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1151 'duration': 142,
c522adb1
JMF
1152 'uploader': 'The Witcher',
1153 'uploader_id': 'WitcherGame',
ec85ded8 1154 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1155 'upload_date': '20140605',
34952f09 1156 'age_limit': 18,
976ae3ea 1157 'categories': ['Gaming'],
1158 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1159 'availability': 'needs_auth',
1160 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1161 'like_count': int,
1162 'channel': 'The Witcher',
1163 'live_status': 'not_live',
1164 'tags': 'count:17',
1165 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1166 'playable_in_embed': True,
1167 'view_count': int,
6c73052c 1168 'channel_follower_count': int
c522adb1
JMF
1169 },
1170 },
65c2fde2 1171 {
1172 'note': 'Age-gate video with embed allowed in public site',
1173 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1174 'info_dict': {
1175 'id': 'HsUATh_Nc2U',
1176 'ext': 'mp4',
1177 'title': 'Godzilla 2 (Official Video)',
1178 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1179 'upload_date': '20200408',
1180 'uploader_id': 'FlyingKitty900',
1181 'uploader': 'FlyingKitty',
1182 'age_limit': 18,
976ae3ea 1183 'availability': 'needs_auth',
1184 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1185 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1186 'channel': 'FlyingKitty',
1187 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1188 'view_count': int,
1189 'categories': ['Entertainment'],
1190 'live_status': 'not_live',
1191 'tags': ['Flyingkitty', 'godzilla 2'],
1192 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1193 'like_count': int,
1194 'duration': 177,
1195 'playable_in_embed': True,
6c73052c 1196 'channel_follower_count': int
65c2fde2 1197 },
1198 },
1199 {
1200 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1201 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1202 'info_dict': {
1203 'id': 'Tq92D6wQ1mg',
1204 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1205 'ext': 'mp4',
17322130 1206 'upload_date': '20191228',
65c2fde2 1207 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1208 'uploader': 'Projekt Melody',
1209 'description': 'md5:17eccca93a786d51bc67646756894066',
1210 'age_limit': 18,
976ae3ea 1211 'like_count': int,
1212 'availability': 'needs_auth',
1213 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1214 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1215 'view_count': int,
1216 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1217 'channel': 'Projekt Melody',
1218 'live_status': 'not_live',
1219 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1220 'playable_in_embed': True,
1221 'categories': ['Entertainment'],
1222 'duration': 106,
1223 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1224 'channel_follower_count': int
65c2fde2 1225 },
1226 },
1227 {
1228 'note': 'Non-Agegated non-embeddable video',
1229 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1230 'info_dict': {
1231 'id': 'MeJVWBSsPAY',
1232 'ext': 'mp4',
1233 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1234 'uploader': 'Herr Lurik',
1235 'uploader_id': 'st3in234',
1236 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1237 'upload_date': '20130730',
976ae3ea 1238 'track': 'Such mich find mich',
1239 'age_limit': 0,
1240 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1241 'like_count': int,
1242 'playable_in_embed': False,
1243 'creator': 'OOMPH!',
1244 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1245 'view_count': int,
1246 'alt_title': 'Such mich find mich',
1247 'duration': 210,
1248 'channel': 'Herr Lurik',
1249 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1250 'categories': ['Music'],
1251 'availability': 'public',
1252 'uploader_url': 'http://www.youtube.com/user/st3in234',
1253 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1254 'live_status': 'not_live',
1255 'artist': 'OOMPH!',
6c73052c 1256 'channel_follower_count': int
65c2fde2 1257 },
1258 },
1259 {
1260 'note': 'Non-bypassable age-gated video',
1261 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1262 'only_matching': True,
1263 },
8bdd16b4 1264 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1265 # YouTube Red ad is not captured for creator
1266 {
1267 'url': '__2ABJjxzNo',
1268 'info_dict': {
1269 'id': '__2ABJjxzNo',
1270 'ext': 'mp4',
1271 'duration': 266,
1272 'upload_date': '20100430',
1273 'uploader_id': 'deadmau5',
1274 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1275 'creator': 'deadmau5',
1276 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1277 'uploader': 'deadmau5',
1278 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1279 'alt_title': 'Some Chords',
976ae3ea 1280 'availability': 'public',
1281 'tags': 'count:14',
1282 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1283 'view_count': int,
1284 'live_status': 'not_live',
1285 'channel': 'deadmau5',
1286 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1287 'like_count': int,
1288 'track': 'Some Chords',
1289 'artist': 'deadmau5',
1290 'playable_in_embed': True,
1291 'age_limit': 0,
1292 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1293 'categories': ['Music'],
1294 'album': 'Some Chords',
6c73052c 1295 'channel_follower_count': int
8bdd16b4 1296 },
1297 'expected_warnings': [
1298 'DASH manifest missing',
1299 ]
1300 },
067aa17e 1301 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1302 {
1303 'url': 'lqQg6PlCWgI',
1304 'info_dict': {
1305 'id': 'lqQg6PlCWgI',
1306 'ext': 'mp4',
556dbe7f 1307 'duration': 6085,
90227264 1308 'upload_date': '20150827',
cbe2bd91 1309 'uploader_id': 'olympic',
ec85ded8 1310 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1311 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1312 'uploader': 'Olympics',
cbe2bd91 1313 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1314 'like_count': int,
1315 'release_timestamp': 1343767800,
1316 'playable_in_embed': True,
1317 'categories': ['Sports'],
1318 'release_date': '20120731',
1319 'channel': 'Olympics',
1320 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1321 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1322 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1323 'age_limit': 0,
1324 'availability': 'public',
1325 'live_status': 'was_live',
1326 'view_count': int,
1327 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1328 'channel_follower_count': int
cbe2bd91
PH
1329 },
1330 'params': {
1331 'skip_download': 'requires avconv',
e52a40ab 1332 }
cbe2bd91 1333 },
6271f1ca
PH
1334 # Non-square pixels
1335 {
1336 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1337 'info_dict': {
1338 'id': '_b-2C3KPAM0',
1339 'ext': 'mp4',
1340 'stretched_ratio': 16 / 9.,
556dbe7f 1341 'duration': 85,
6271f1ca
PH
1342 'upload_date': '20110310',
1343 'uploader_id': 'AllenMeow',
ec85ded8 1344 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1345 '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 1346 'uploader': '孫ᄋᄅ',
6271f1ca 1347 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1348 'playable_in_embed': True,
1349 'channel': '孫ᄋᄅ',
1350 'age_limit': 0,
1351 'tags': 'count:11',
1352 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1353 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1354 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1355 'view_count': int,
1356 'categories': ['People & Blogs'],
1357 'like_count': int,
1358 'live_status': 'not_live',
1359 'availability': 'unlisted',
6c73052c 1360 'channel_follower_count': int
6271f1ca 1361 },
06b491eb
S
1362 },
1363 # url_encoded_fmt_stream_map is empty string
1364 {
1365 'url': 'qEJwOuvDf7I',
1366 'info_dict': {
1367 'id': 'qEJwOuvDf7I',
f57b7835 1368 'ext': 'webm',
06b491eb
S
1369 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1370 'description': '',
1371 'upload_date': '20150404',
1372 'uploader_id': 'spbelect',
1373 'uploader': 'Наблюдатели Петербурга',
1374 },
1375 'params': {
1376 'skip_download': 'requires avconv',
e323cf3f
S
1377 },
1378 'skip': 'This live event has ended.',
06b491eb 1379 },
067aa17e 1380 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1381 {
1382 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1383 'info_dict': {
1384 'id': 'FIl7x6_3R5Y',
eb6793ba 1385 'ext': 'webm',
da77d856
S
1386 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1387 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1388 'duration': 220,
da77d856
S
1389 'upload_date': '20150625',
1390 'uploader_id': 'dorappi2000',
ec85ded8 1391 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1392 'uploader': 'dorappi2000',
eb6793ba 1393 'formats': 'mincount:31',
da77d856 1394 },
eb6793ba 1395 'skip': 'not actual anymore',
2ee8f5d8 1396 },
8a1a26ce
YCH
1397 # DASH manifest with segment_list
1398 {
1399 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1400 'md5': '8ce563a1d667b599d21064e982ab9e31',
1401 'info_dict': {
1402 'id': 'CsmdDsKjzN8',
1403 'ext': 'mp4',
17ee98e1 1404 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1405 'uploader': 'Airtek',
1406 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1407 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1408 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1409 },
1410 'params': {
1411 'youtube_include_dash_manifest': True,
1412 'format': '135', # bestvideo
be49068d
S
1413 },
1414 'skip': 'This live event has ended.',
2ee8f5d8 1415 },
cf7e015f
S
1416 {
1417 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1418 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1419 'info_dict': {
545cc85d 1420 'id': 'jvGDaLqkpTg',
1421 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1422 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1423 },
1424 'playlist': [{
1425 'info_dict': {
545cc85d 1426 'id': 'jvGDaLqkpTg',
cf7e015f 1427 'ext': 'mp4',
545cc85d 1428 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1429 'description': 'md5:e03b909557865076822aa169218d6a5d',
1430 'duration': 10643,
1431 'upload_date': '20161111',
1432 'uploader': 'Team PGP',
1433 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1434 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1435 },
1436 }, {
1437 'info_dict': {
545cc85d 1438 'id': '3AKt1R1aDnw',
cf7e015f 1439 'ext': 'mp4',
545cc85d 1440 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1441 'description': 'md5:e03b909557865076822aa169218d6a5d',
1442 'duration': 10991,
1443 'upload_date': '20161111',
1444 'uploader': 'Team PGP',
1445 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1446 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1447 },
1448 }, {
1449 'info_dict': {
545cc85d 1450 'id': 'RtAMM00gpVc',
cf7e015f 1451 'ext': 'mp4',
545cc85d 1452 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1453 'description': 'md5:e03b909557865076822aa169218d6a5d',
1454 'duration': 10995,
1455 'upload_date': '20161111',
1456 'uploader': 'Team PGP',
1457 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1458 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1459 },
1460 }, {
1461 'info_dict': {
545cc85d 1462 'id': '6N2fdlP3C5U',
cf7e015f 1463 'ext': 'mp4',
545cc85d 1464 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1465 'description': 'md5:e03b909557865076822aa169218d6a5d',
1466 'duration': 10990,
1467 'upload_date': '20161111',
1468 'uploader': 'Team PGP',
1469 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1470 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1471 },
1472 }],
1473 'params': {
1474 'skip_download': True,
1475 },
65c2fde2 1476 'skip': 'Not multifeed anymore',
cbaed4bb 1477 },
f9f49d87 1478 {
067aa17e 1479 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1480 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1481 'info_dict': {
1482 'id': 'gVfLd0zydlo',
1483 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1484 },
1485 'playlist_count': 2,
be49068d 1486 'skip': 'Not multifeed anymore',
f9f49d87 1487 },
cbaed4bb 1488 {
2d3d2997 1489 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1490 'only_matching': True,
0e49d9a6 1491 },
6d4fc66b 1492 {
2d3d2997 1493 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1494 'only_matching': True,
1495 },
0e49d9a6 1496 {
067aa17e 1497 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1498 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1499 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1500 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1501 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1502 'info_dict': {
1503 'id': 'lsguqyKfVQg',
1504 'ext': 'mp4',
1505 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1506 'alt_title': 'Dark Walk',
0e49d9a6 1507 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1508 'duration': 133,
0e49d9a6
LL
1509 'upload_date': '20151119',
1510 'uploader_id': 'IronSoulElf',
ec85ded8 1511 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1512 'uploader': 'IronSoulElf',
11f9be09 1513 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1514 'track': 'Dark Walk',
1515 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1516 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1517 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1518 'categories': ['Film & Animation'],
1519 'view_count': int,
1520 'live_status': 'not_live',
1521 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1522 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1523 'tags': 'count:13',
1524 'availability': 'public',
1525 'channel': 'IronSoulElf',
1526 'playable_in_embed': True,
1527 'like_count': int,
1528 'age_limit': 0,
6c73052c 1529 'channel_follower_count': int
0e49d9a6
LL
1530 },
1531 'params': {
1532 'skip_download': True,
1533 },
1534 },
61f92af1 1535 {
067aa17e 1536 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1537 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1538 'only_matching': True,
1539 },
313dfc45
LL
1540 {
1541 # Video with yt:stretch=17:0
1542 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1543 'info_dict': {
1544 'id': 'Q39EVAstoRM',
1545 'ext': 'mp4',
1546 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1547 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1548 'upload_date': '20151107',
1549 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1550 'uploader': 'CH GAMER DROID',
1551 },
1552 'params': {
1553 'skip_download': True,
1554 },
be49068d 1555 'skip': 'This video does not exist.',
313dfc45 1556 },
201c1459 1557 {
1558 # Video with incomplete 'yt:stretch=16:'
1559 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1560 'only_matching': True,
1561 },
7caf9830
S
1562 {
1563 # Video licensed under Creative Commons
1564 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1565 'info_dict': {
1566 'id': 'M4gD1WSo5mA',
1567 'ext': 'mp4',
1568 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1569 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1570 'duration': 721,
17322130 1571 'upload_date': '20150128',
7caf9830 1572 'uploader_id': 'BerkmanCenter',
ec85ded8 1573 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1574 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1575 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1576 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1577 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1578 'like_count': int,
1579 'age_limit': 0,
1580 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1581 'channel': 'The Berkman Klein Center for Internet & Society',
1582 'availability': 'public',
1583 'view_count': int,
1584 'categories': ['Education'],
1585 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1586 'live_status': 'not_live',
1587 'playable_in_embed': True,
6c73052c 1588 'channel_follower_count': int
7caf9830
S
1589 },
1590 'params': {
1591 'skip_download': True,
1592 },
1593 },
fd050249
S
1594 {
1595 # Channel-like uploader_url
1596 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1597 'info_dict': {
1598 'id': 'eQcmzGIKrzg',
1599 'ext': 'mp4',
1600 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1601 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1602 'duration': 4060,
17322130 1603 'upload_date': '20151120',
eb6793ba 1604 'uploader': 'Bernie Sanders',
fd050249 1605 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1606 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1607 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1608 'playable_in_embed': True,
1609 'tags': 'count:12',
1610 'like_count': int,
1611 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1612 'age_limit': 0,
1613 'availability': 'public',
1614 'categories': ['News & Politics'],
1615 'channel': 'Bernie Sanders',
1616 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1617 'view_count': int,
1618 'live_status': 'not_live',
1619 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1620 'channel_follower_count': int
fd050249
S
1621 },
1622 'params': {
1623 'skip_download': True,
1624 },
1625 },
040ac686
S
1626 {
1627 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1628 'only_matching': True,
7f29cf54
S
1629 },
1630 {
067aa17e 1631 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1632 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1633 'only_matching': True,
6496ccb4
S
1634 },
1635 {
1636 # Rental video preview
1637 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1638 'info_dict': {
1639 'id': 'uGpuVWrhIzE',
1640 'ext': 'mp4',
1641 'title': 'Piku - Trailer',
1642 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1643 'upload_date': '20150811',
1644 'uploader': 'FlixMatrix',
1645 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1647 'license': 'Standard YouTube License',
1648 },
1649 'params': {
1650 'skip_download': True,
1651 },
eb6793ba 1652 'skip': 'This video is not available.',
022a5d66 1653 },
12afdc2a
S
1654 {
1655 # YouTube Red video with episode data
1656 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1657 'info_dict': {
1658 'id': 'iqKdEhx-dD4',
1659 'ext': 'mp4',
1660 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1661 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1662 'duration': 2085,
12afdc2a
S
1663 'upload_date': '20170118',
1664 'uploader': 'Vsauce',
1665 'uploader_id': 'Vsauce',
1666 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1667 'series': 'Mind Field',
1668 'season_number': 1,
1669 'episode_number': 1,
976ae3ea 1670 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1671 'tags': 'count:12',
1672 'view_count': int,
1673 'availability': 'public',
1674 'age_limit': 0,
1675 'channel': 'Vsauce',
1676 'episode': 'Episode 1',
1677 'categories': ['Entertainment'],
1678 'season': 'Season 1',
1679 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1680 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1681 'like_count': int,
1682 'playable_in_embed': True,
1683 'live_status': 'not_live',
6c73052c 1684 'channel_follower_count': int
12afdc2a
S
1685 },
1686 'params': {
1687 'skip_download': True,
1688 },
1689 'expected_warnings': [
1690 'Skipping DASH manifest',
1691 ],
1692 },
c7121fa7
S
1693 {
1694 # The following content has been identified by the YouTube community
1695 # as inappropriate or offensive to some audiences.
1696 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1697 'info_dict': {
1698 'id': '6SJNVb0GnPI',
1699 'ext': 'mp4',
1700 'title': 'Race Differences in Intelligence',
1701 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1702 'duration': 965,
1703 'upload_date': '20140124',
1704 'uploader': 'New Century Foundation',
1705 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1706 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1707 },
1708 'params': {
1709 'skip_download': True,
1710 },
545cc85d 1711 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1712 },
022a5d66
S
1713 {
1714 # itag 212
1715 'url': '1t24XAntNCY',
1716 'only_matching': True,
fd5c4aab
S
1717 },
1718 {
1719 # geo restricted to JP
1720 'url': 'sJL6WA-aGkQ',
1721 'only_matching': True,
1722 },
cd5a74a2
S
1723 {
1724 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1725 'only_matching': True,
1726 },
bc2ca1bb 1727 {
1728 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1729 'only_matching': True,
1730 },
1731 {
1732 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1733 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1734 'only_matching': True,
1735 },
825cd268
RA
1736 {
1737 # DRM protected
1738 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1739 'only_matching': True,
4fe54c12
S
1740 },
1741 {
1742 # Video with unsupported adaptive stream type formats
1743 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1744 'info_dict': {
1745 'id': 'Z4Vy8R84T1U',
1746 'ext': 'mp4',
1747 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1748 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1749 'duration': 433,
1750 'upload_date': '20130923',
1751 'uploader': 'Amelia Putri Harwita',
1752 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1753 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1754 'formats': 'maxcount:10',
1755 },
1756 'params': {
1757 'skip_download': True,
1758 'youtube_include_dash_manifest': False,
1759 },
5429d6a9 1760 'skip': 'not actual anymore',
5caabd3c 1761 },
1762 {
822b9d9c 1763 # Youtube Music Auto-generated description
5caabd3c 1764 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1765 'info_dict': {
1766 'id': 'MgNrAu2pzNs',
1767 'ext': 'mp4',
1768 'title': 'Voyeur Girl',
1769 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1770 'upload_date': '20190312',
5429d6a9
S
1771 'uploader': 'Stephen - Topic',
1772 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1773 'artist': 'Stephen',
1774 'track': 'Voyeur Girl',
1775 'album': 'it\'s too much love to know my dear',
1776 'release_date': '20190313',
1777 'release_year': 2019,
976ae3ea 1778 'alt_title': 'Voyeur Girl',
1779 'view_count': int,
1780 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1781 'playable_in_embed': True,
1782 'like_count': int,
1783 'categories': ['Music'],
1784 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1785 'channel': 'Stephen',
1786 'availability': 'public',
1787 'creator': 'Stephen',
1788 'duration': 169,
1789 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1790 'age_limit': 0,
1791 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1792 'tags': 'count:11',
1793 'live_status': 'not_live',
6c73052c 1794 'channel_follower_count': int
5caabd3c 1795 },
1796 'params': {
1797 'skip_download': True,
1798 },
1799 },
66b48727
RA
1800 {
1801 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1802 'only_matching': True,
1803 },
011e75e6
S
1804 {
1805 # invalid -> valid video id redirection
1806 'url': 'DJztXj2GPfl',
1807 'info_dict': {
1808 'id': 'DJztXj2GPfk',
1809 'ext': 'mp4',
1810 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1811 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1812 'upload_date': '20090125',
1813 'uploader': 'Prochorowka',
1814 'uploader_id': 'Prochorowka',
1815 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1816 'artist': 'Panjabi MC',
1817 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1818 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1819 },
1820 'params': {
1821 'skip_download': True,
1822 },
545cc85d 1823 'skip': 'Video unavailable',
ea74e00b
DP
1824 },
1825 {
1826 # empty description results in an empty string
1827 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1828 'info_dict': {
1829 'id': 'x41yOUIvK2k',
1830 'ext': 'mp4',
1831 'title': 'IMG 3456',
1832 'description': '',
1833 'upload_date': '20170613',
1834 'uploader_id': 'ElevageOrVert',
1835 'uploader': 'ElevageOrVert',
976ae3ea 1836 'view_count': int,
1837 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1838 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1839 'like_count': int,
1840 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1841 'tags': [],
1842 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1843 'availability': 'public',
1844 'age_limit': 0,
1845 'categories': ['Pets & Animals'],
1846 'duration': 7,
1847 'playable_in_embed': True,
1848 'live_status': 'not_live',
1849 'channel': 'ElevageOrVert',
6c73052c 1850 'channel_follower_count': int
ea74e00b
DP
1851 },
1852 'params': {
1853 'skip_download': True,
1854 },
1855 },
a0566bbf 1856 {
29f7c58a 1857 # with '};' inside yt initial data (see [1])
1858 # see [2] for an example with '};' inside ytInitialPlayerResponse
1859 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1860 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1861 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1862 'info_dict': {
1863 'id': 'CHqg6qOn4no',
1864 'ext': 'mp4',
1865 'title': 'Part 77 Sort a list of simple types in c#',
1866 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1867 'upload_date': '20130831',
1868 'uploader_id': 'kudvenkat',
1869 'uploader': 'kudvenkat',
976ae3ea 1870 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1871 'like_count': int,
1872 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1873 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1874 'live_status': 'not_live',
1875 'categories': ['Education'],
1876 'availability': 'public',
1877 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1878 'tags': 'count:12',
1879 'playable_in_embed': True,
1880 'age_limit': 0,
1881 'view_count': int,
1882 'duration': 522,
1883 'channel': 'kudvenkat',
6c73052c 1884 'channel_follower_count': int
a0566bbf 1885 },
1886 'params': {
1887 'skip_download': True,
1888 },
1889 },
29f7c58a 1890 {
1891 # another example of '};' in ytInitialData
1892 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1893 'only_matching': True,
1894 },
1895 {
1896 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1897 'only_matching': True,
1898 },
545cc85d 1899 {
cc2db878 1900 # https://github.com/ytdl-org/youtube-dl/pull/28094
1901 'url': 'OtqTfy26tG0',
1902 'info_dict': {
1903 'id': 'OtqTfy26tG0',
1904 'ext': 'mp4',
1905 'title': 'Burn Out',
1906 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1907 'upload_date': '20141120',
1908 'uploader': 'The Cinematic Orchestra - Topic',
1909 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1910 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1911 'artist': 'The Cinematic Orchestra',
1912 'track': 'Burn Out',
1913 'album': 'Every Day',
976ae3ea 1914 'like_count': int,
1915 'live_status': 'not_live',
1916 'alt_title': 'Burn Out',
1917 'duration': 614,
1918 'age_limit': 0,
1919 'view_count': int,
1920 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1921 'creator': 'The Cinematic Orchestra',
1922 'channel': 'The Cinematic Orchestra',
1923 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1924 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1925 'availability': 'public',
1926 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1927 'categories': ['Music'],
1928 'playable_in_embed': True,
6c73052c 1929 'channel_follower_count': int
cc2db878 1930 },
1931 'params': {
1932 'skip_download': True,
1933 },
545cc85d 1934 },
bc2ca1bb 1935 {
1936 # controversial video, only works with bpctr when authenticated with cookies
1937 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1938 'only_matching': True,
1939 },
a1a7907b 1940 {
1941 # controversial video, requires bpctr/contentCheckOk
1942 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1943 'info_dict': {
1944 'id': 'SZJvDhaSDnc',
1945 'ext': 'mp4',
1946 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1947 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1948 'uploader': 'CBS Mornings',
11f9be09 1949 'uploader_id': 'CBSThisMorning',
a1a7907b 1950 'upload_date': '20140716',
976ae3ea 1951 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1952 'duration': 170,
1953 'categories': ['News & Politics'],
1954 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1955 'view_count': int,
1956 'channel': 'CBS Mornings',
1957 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1958 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1959 'age_limit': 18,
1960 'availability': 'needs_auth',
1961 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1962 'like_count': int,
1963 'live_status': 'not_live',
1964 'playable_in_embed': True,
6c73052c 1965 'channel_follower_count': int
a1a7907b 1966 }
1967 },
f7ad7160 1968 {
1969 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1970 'url': 'cBvYw8_A0vQ',
1971 'info_dict': {
1972 'id': 'cBvYw8_A0vQ',
1973 'ext': 'mp4',
1974 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1975 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1976 'upload_date': '20201120',
1977 'uploader': 'Walk around Japan',
1978 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1979 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1980 'duration': 1456,
1981 'categories': ['Travel & Events'],
1982 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1983 'view_count': int,
1984 'channel': 'Walk around Japan',
1985 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1986 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1987 'age_limit': 0,
1988 'availability': 'public',
1989 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1990 'live_status': 'not_live',
1991 'playable_in_embed': True,
6c73052c 1992 'channel_follower_count': int
f7ad7160 1993 },
1994 'params': {
1995 'skip_download': True,
1996 },
0fb983f6 1997 }, {
1998 # Has multiple audio streams
1999 'url': 'WaOKSUlf4TM',
2000 'only_matching': True
9297939e 2001 }, {
2002 # Requires Premium: has format 141 when requested using YTM url
2003 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2004 'only_matching': True
2005 }, {
120916da 2006 # multiple subtitles with same lang_code
2007 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2008 'only_matching': True,
109dd3b2 2009 }, {
2010 # Force use android client fallback
2011 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2012 'info_dict': {
2013 'id': 'YOelRv7fMxY',
11f9be09 2014 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2015 'ext': '3gp',
2016 'upload_date': '20210624',
2017 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2018 'uploader': 'colinfurze',
11f9be09 2019 'uploader_id': 'colinfurze',
109dd3b2 2020 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2021 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2022 'duration': 596,
2023 'categories': ['Entertainment'],
2024 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2025 'view_count': int,
2026 'channel': 'colinfurze',
2027 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2028 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2029 'age_limit': 0,
2030 'availability': 'public',
2031 'like_count': int,
2032 'live_status': 'not_live',
2033 'playable_in_embed': True,
6c73052c 2034 'channel_follower_count': int
109dd3b2 2035 },
2036 'params': {
2037 'format': '17', # 3gp format available on android
2038 'extractor_args': {'youtube': {'player_client': ['android']}},
2039 },
120916da 2040 },
109dd3b2 2041 {
2042 # Skip download of additional client configs (remix client config in this case)
2043 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2044 'only_matching': True,
2045 'params': {
2046 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2047 },
8fc54b12 2048 }, {
2049 # shorts
2050 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2051 'only_matching': True,
9222c381 2052 }, {
2053 'note': 'Storyboards',
2054 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2055 'info_dict': {
2056 'id': '5KLPxDtMqe8',
2057 'ext': 'mhtml',
2058 'format_id': 'sb0',
2059 'title': 'Your Brain is Plastic',
2060 'uploader_id': 'scishow',
2061 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2062 'upload_date': '20140324',
2063 'uploader': 'SciShow',
976ae3ea 2064 'like_count': int,
2065 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2066 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2067 'view_count': int,
2068 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2069 'playable_in_embed': True,
2070 'tags': 'count:12',
2071 'uploader_url': 'http://www.youtube.com/user/scishow',
2072 'availability': 'public',
2073 'channel': 'SciShow',
2074 'live_status': 'not_live',
2075 'duration': 248,
2076 'categories': ['Education'],
2077 'age_limit': 0,
6c73052c 2078 'channel_follower_count': int
9222c381 2079 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2080 }, {
2081 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2082 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2083 'info_dict': {
2084 'id': '2NUZ8W2llS4',
2085 'ext': 'mp4',
2086 'title': 'The NP that test your phone performance 🙂',
2087 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2088 'uploader': 'Leon Nguyen',
2089 'uploader_id': 'VNSXIII',
2090 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2091 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2092 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2093 'duration': 21,
2094 'view_count': int,
2095 'age_limit': 0,
2096 'categories': ['Gaming'],
2097 'tags': 'count:23',
2098 'playable_in_embed': True,
2099 'live_status': 'not_live',
2100 'upload_date': '20220103',
2101 'like_count': int,
2102 'availability': 'public',
2103 'channel': 'Leon Nguyen',
2104 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2105 'channel_follower_count': int
2106 }
2107 }, {
2108 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2109 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2110 'info_dict': {
2111 'id': 'mzZzzBU6lrM',
2112 'ext': 'mp4',
2113 'title': 'I Met GeorgeNotFound In Real Life...',
2114 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2115 'uploader': 'Quackity',
2116 'uploader_id': 'QuackityHQ',
2117 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2118 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2119 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2120 'duration': 955,
2121 'view_count': int,
2122 'age_limit': 0,
2123 'categories': ['Entertainment'],
2124 'tags': 'count:26',
2125 'playable_in_embed': True,
2126 'live_status': 'not_live',
2127 'release_timestamp': 1641172509,
2128 'release_date': '20220103',
2129 'upload_date': '20220103',
2130 'like_count': int,
2131 'availability': 'public',
2132 'channel': 'Quackity',
2133 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2134 'channel_follower_count': int
2135 }
2136 },
2137 { # continuous livestream. Microformat upload date should be preferred.
2138 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2139 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2140 'info_dict': {
2141 'id': 'kgx4WGK0oNU',
2142 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2143 'ext': 'mp4',
2144 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2145 'availability': 'public',
2146 'age_limit': 0,
2147 'release_timestamp': 1637975704,
2148 'upload_date': '20210619',
2149 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2150 'live_status': 'is_live',
2151 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2152 'uploader': '阿鲍Abao',
2153 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2154 'channel': 'Abao in Tokyo',
2155 'channel_follower_count': int,
2156 'release_date': '20211127',
2157 'tags': 'count:39',
2158 'categories': ['People & Blogs'],
2159 'like_count': int,
2160 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2161 'view_count': int,
2162 'playable_in_embed': True,
2163 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2164 },
2165 'params': {'skip_download': True}
2166 },
2eb88d95
PH
2167 ]
2168
201c1459 2169 @classmethod
2170 def suitable(cls, url):
4dfbf869 2171 from ..utils import parse_qs
2172
201c1459 2173 qs = parse_qs(url)
2174 if qs.get('list', [None])[0]:
2175 return False
2176 return super(YoutubeIE, cls).suitable(url)
2177
e0df6211
PH
2178 def __init__(self, *args, **kwargs):
2179 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2180 self._code_cache = {}
83799698 2181 self._player_cache = {}
e0df6211 2182
adbc4ec4 2183 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2184 lock = threading.Lock()
2185
2186 is_live = True
185bf310 2187 start_time = time.time()
adbc4ec4
THD
2188 formats = [f for f in formats if f.get('is_from_start')]
2189
185bf310 2190 def refetch_manifest(format_id, delay):
2191 nonlocal formats, start_time, is_live
2192 if time.time() <= start_time + delay:
adbc4ec4
THD
2193 return
2194
2195 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2196 video_details = traverse_obj(
2197 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2198 microformats = traverse_obj(
2199 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2200 expected_type=dict, default=[])
2201 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2202 start_time = time.time()
adbc4ec4 2203
185bf310 2204 def mpd_feed(format_id, delay):
adbc4ec4
THD
2205 """
2206 @returns (manifest_url, manifest_stream_number, is_live) or None
2207 """
2208 with lock:
185bf310 2209 refetch_manifest(format_id, delay)
adbc4ec4
THD
2210
2211 f = next((f for f in formats if f['format_id'] == format_id), None)
2212 if not f:
185bf310 2213 if not is_live:
2214 self.to_screen(f'{video_id}: Video is no longer live')
2215 else:
2216 self.report_warning(
2217 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2218 return None
2219 return f['manifest_url'], f['manifest_stream_number'], is_live
2220
2221 for f in formats:
a539f065 2222 f['is_live'] = True
adbc4ec4
THD
2223 f['protocol'] = 'http_dash_segments_generator'
2224 f['fragments'] = functools.partial(
2225 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2226
2227 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2228 FETCH_SPAN, MAX_DURATION = 5, 432000
2229
2230 mpd_url, stream_number, is_live = None, None, True
2231
2232 begin_index = 0
2233 download_start_time = ctx.get('start') or time.time()
2234
2235 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2236 if lack_early_segments:
2237 self.report_warning(bug_reports_message(
2238 'Starting download from the last 120 hours of the live stream since '
2239 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2240 lack_early_segments = True
2241
2242 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2243 fragments, fragment_base_url = None, None
2244
a539f065 2245 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2246 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2247 # Obtain from MPD's maximum seq value
2248 old_mpd_url = mpd_url
185bf310 2249 last_error = ctx.pop('last_error', None)
a539f065 2250 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2251 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2252 or (mpd_url, stream_number, False))
2253 if not refresh_sequence:
2254 if expire_fast and not is_live:
2255 return False, last_seq
2256 elif old_mpd_url == mpd_url:
2257 return True, last_seq
adbc4ec4
THD
2258 try:
2259 fmts, _ = self._extract_mpd_formats_and_subtitles(
2260 mpd_url, None, note=False, errnote=False, fatal=False)
2261 except ExtractorError:
2262 fmts = None
2263 if not fmts:
a539f065 2264 no_fragment_score += 2
adbc4ec4
THD
2265 return False, last_seq
2266 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2267 fragments = fmt_info['fragments']
2268 fragment_base_url = fmt_info['fragment_base_url']
2269 assert fragment_base_url
2270
2271 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2272 return True, _last_seq
2273
2274 while is_live:
2275 fetch_time = time.time()
2276 if no_fragment_score > 30:
2277 return
2278 if last_segment_url:
2279 # Obtain from "X-Head-Seqnum" header value from each segment
2280 try:
2281 urlh = self._request_webpage(
2282 last_segment_url, None, note=False, errnote=False, fatal=False)
2283 except ExtractorError:
2284 urlh = None
2285 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2286 if last_seq is None:
a539f065 2287 no_fragment_score += 2
adbc4ec4
THD
2288 last_segment_url = None
2289 continue
2290 else:
a539f065
LNO
2291 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2292 no_fragment_score += 2
185bf310 2293 if not should_continue:
adbc4ec4
THD
2294 continue
2295
2296 if known_idx > last_seq:
2297 last_segment_url = None
2298 continue
2299
2300 last_seq += 1
2301
2302 if begin_index < 0 and known_idx < 0:
2303 # skip from the start when it's negative value
2304 known_idx = last_seq + begin_index
2305 if lack_early_segments:
2306 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2307 try:
2308 for idx in range(known_idx, last_seq):
2309 # do not update sequence here or you'll get skipped some part of it
a539f065 2310 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2311 if not should_continue:
adbc4ec4
THD
2312 known_idx = idx - 1
2313 raise ExtractorError('breaking out of outer loop')
2314 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2315 yield {
2316 'url': last_segment_url,
2317 }
2318 if known_idx == last_seq:
2319 no_fragment_score += 5
2320 else:
2321 no_fragment_score = 0
2322 known_idx = last_seq
2323 except ExtractorError:
2324 continue
2325
2326 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2327
b6de707d 2328 def _extract_player_url(self, *ytcfgs, webpage=None):
2329 player_url = traverse_obj(
2330 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2331 get_all=False, expected_type=compat_str)
11f9be09 2332 if not player_url:
b6de707d 2333 return
60f393e4 2334 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2335
b6de707d 2336 def _download_player_url(self, video_id, fatal=False):
2337 res = self._download_webpage(
2338 'https://www.youtube.com/iframe_api',
2339 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2340 if res:
2341 player_version = self._search_regex(
2342 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2343 if player_version:
2344 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2345
60064c53
PH
2346 def _signature_cache_id(self, example_sig):
2347 """ Return a string representation of a signature """
78caa52a 2348 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2349
e40c758c
S
2350 @classmethod
2351 def _extract_player_info(cls, player_url):
2352 for player_re in cls._PLAYER_INFO_RE:
2353 id_m = re.search(player_re, player_url)
2354 if id_m:
2355 break
2356 else:
c081b35c 2357 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2358 return id_m.group('id')
e40c758c 2359
404f611f 2360 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2361 player_id = self._extract_player_info(player_url)
2362 if player_id not in self._code_cache:
1276a43a 2363 code = self._download_webpage(
109dd3b2 2364 player_url, video_id, fatal=fatal,
2365 note='Downloading player ' + player_id,
2366 errnote='Download of %s failed' % player_url)
1276a43a 2367 if code:
2368 self._code_cache[player_id] = code
404f611f 2369 return self._code_cache.get(player_id)
109dd3b2 2370
e40c758c 2371 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2372 player_id = self._extract_player_info(player_url)
e0df6211 2373
c4417ddb 2374 # Read from filesystem cache
545cc85d 2375 func_id = 'js_%s_%s' % (
2376 player_id, self._signature_cache_id(example_sig))
c4417ddb 2377 assert os.path.basename(func_id) == func_id
a0e07d31 2378
69ea8ca4 2379 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2380 if cache_spec is not None:
78caa52a 2381 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2382
404f611f 2383 code = self._load_player(video_id, player_url)
2384 if code:
109dd3b2 2385 res = self._parse_sig_js(code)
e0df6211 2386
109dd3b2 2387 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2388 cache_res = res(test_string)
2389 cache_spec = [ord(c) for c in cache_res]
83799698 2390
109dd3b2 2391 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2392 return res
83799698 2393
60064c53 2394 def _print_sig_code(self, func, example_sig):
404f611f 2395 if not self.get_param('youtube_print_sig_code'):
2396 return
2397
edf3e38e
PH
2398 def gen_sig_code(idxs):
2399 def _genslice(start, end, step):
78caa52a 2400 starts = '' if start == 0 else str(start)
8bcc8756 2401 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2402 steps = '' if step == 1 else (':%d' % step)
78caa52a 2403 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2404
2405 step = None
7af808a5
PH
2406 # Quelch pyflakes warnings - start will be set when step is set
2407 start = '(Never used)'
edf3e38e
PH
2408 for i, prev in zip(idxs[1:], idxs[:-1]):
2409 if step is not None:
2410 if i - prev == step:
2411 continue
2412 yield _genslice(start, prev, step)
2413 step = None
2414 continue
2415 if i - prev in [-1, 1]:
2416 step = i - prev
2417 start = prev
2418 continue
2419 else:
78caa52a 2420 yield 's[%d]' % prev
edf3e38e 2421 if step is None:
78caa52a 2422 yield 's[%d]' % i
edf3e38e
PH
2423 else:
2424 yield _genslice(start, i, step)
2425
78caa52a 2426 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2427 cache_res = func(test_string)
edf3e38e 2428 cache_spec = [ord(c) for c in cache_res]
78caa52a 2429 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2430 signature_id_tuple = '(%s)' % (
2431 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2432 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2433 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2434 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2435
e0df6211
PH
2436 def _parse_sig_js(self, jscode):
2437 funcname = self._search_regex(
abefc03f
S
2438 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2439 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
2440 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2441 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2442 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}\(a,\d+\)',
2443 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 2444 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2445 # Obsolete patterns
2446 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2447 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2448 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2449 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2450 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2451 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2452 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2453 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2454 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2455
2456 jsi = JSInterpreter(jscode)
2457 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2458 return lambda s: initial_function([s])
2459
545cc85d 2460 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2461 """Turn the encrypted s field into a working signature"""
6b37f0be 2462
c8bf86d5 2463 if player_url is None:
69ea8ca4 2464 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2465
c8bf86d5 2466 try:
62af3a0e 2467 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2468 if player_id not in self._player_cache:
2469 func = self._extract_signature_function(
60064c53 2470 video_id, player_url, s
c8bf86d5
PH
2471 )
2472 self._player_cache[player_id] = func
2473 func = self._player_cache[player_id]
404f611f 2474 self._print_sig_code(func, s)
c8bf86d5
PH
2475 return func(s)
2476 except Exception as e:
404f611f 2477 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2478
2479 def _decrypt_nsig(self, s, video_id, player_url):
2480 """Turn the encrypted n field into a working signature"""
2481 if player_url is None:
2482 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2483 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2484
2485 sig_id = ('nsig_value', s)
2486 if sig_id in self._player_cache:
2487 return self._player_cache[sig_id]
2488
2489 try:
2490 player_id = ('nsig', player_url)
2491 if player_id not in self._player_cache:
2492 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2493 func = self._player_cache[player_id]
2494 self._player_cache[sig_id] = func(s)
2495 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2496 return self._player_cache[sig_id]
2497 except Exception as e:
aa9369a2 2498 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2499
2500 def _extract_n_function_name(self, jscode):
48416bc4 2501 nfunc, idx = self._search_regex(
c571b3a6 2502 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2503 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2504 if not idx:
2505 return nfunc
2506 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2507 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2508 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2509
2510 def _extract_n_function(self, video_id, player_url):
2511 player_id = self._extract_player_info(player_url)
2512 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2513
2514 if func_code:
2515 jsi = JSInterpreter(func_code)
2516 else:
2517 jscode = self._load_player(video_id, player_url)
2518 funcname = self._extract_n_function_name(jscode)
2519 jsi = JSInterpreter(jscode)
2520 func_code = jsi.extract_function_code(funcname)
2521 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2522
2523 if self.get_param('youtube_print_sig_code'):
2524 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2525
2526 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2527
109dd3b2 2528 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2529 """
2530 Extract signatureTimestamp (sts)
2531 Required to tell API what sig/player version is in use.
2532 """
2533 sts = None
2534 if isinstance(ytcfg, dict):
2535 sts = int_or_none(ytcfg.get('STS'))
2536
2537 if not sts:
2538 # Attempt to extract from player
2539 if player_url is None:
2540 error_msg = 'Cannot extract signature timestamp without player_url.'
2541 if fatal:
2542 raise ExtractorError(error_msg)
2543 self.report_warning(error_msg)
2544 return
404f611f 2545 code = self._load_player(video_id, player_url, fatal=fatal)
2546 if code:
109dd3b2 2547 sts = int_or_none(self._search_regex(
2548 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2549 'JS player signature timestamp', group='sts', fatal=fatal))
2550 return sts
2551
11f9be09 2552 def _mark_watched(self, video_id, player_responses):
9222c381 2553 playback_url = get_first(
2554 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2555 expected_type=url_or_none)
d77ab8e2 2556 if not playback_url:
352d63fd 2557 self.report_warning('Unable to mark watched')
d77ab8e2
S
2558 return
2559 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2560 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2561
2562 # cpn generation algorithm is reverse engineered from base.js.
2563 # In fact it works even with dummy cpn.
2564 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2565 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2566
2567 qs.update({
2568 'ver': ['2'],
2569 'cpn': [cpn],
2570 })
2571 playback_url = compat_urlparse.urlunparse(
15707c7e 2572 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2573
2574 self._download_webpage(
2575 playback_url, video_id, 'Marking watched',
2576 'Unable to mark watched', fatal=False)
2577
66c9fa36
S
2578 @staticmethod
2579 def _extract_urls(webpage):
2580 # Embedded YouTube player
2581 entries = [
2582 unescapeHTML(mobj.group('url'))
2583 for mobj in re.finditer(r'''(?x)
2584 (?:
2585 <iframe[^>]+?src=|
2586 data-video-url=|
2587 <embed[^>]+?src=|
2588 embedSWF\(?:\s*|
2589 <object[^>]+data=|
2590 new\s+SWFObject\(
2591 )
2592 (["\'])
2593 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2594 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2595 \1''', webpage)]
2596
2597 # lazyYT YouTube embed
2598 entries.extend(list(map(
2599 unescapeHTML,
2600 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2601
2602 # Wordpress "YouTube Video Importer" plugin
2603 matches = re.findall(r'''(?x)<div[^>]+
2604 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2605 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2606 entries.extend(m[-1] for m in matches)
2607
2608 return entries
2609
2610 @staticmethod
2611 def _extract_url(webpage):
2612 urls = YoutubeIE._extract_urls(webpage)
2613 return urls[0] if urls else None
2614
97665381
PH
2615 @classmethod
2616 def extract_id(cls, url):
2617 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2618 if mobj is None:
69ea8ca4 2619 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2620 return mobj.group('id')
c5e8d7af 2621
7c365c21 2622 def _extract_chapters_from_json(self, data, duration):
2623 chapter_list = traverse_obj(
2624 data, (
2625 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2626 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2627 ), expected_type=list)
2628
2629 return self._extract_chapters(
2630 chapter_list,
2631 chapter_time=lambda chapter: float_or_none(
2632 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2633 chapter_title=lambda chapter: traverse_obj(
2634 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2635 duration=duration)
2636
2637 def _extract_chapters_from_engagement_panel(self, data, duration):
2638 content_list = traverse_obj(
8bdd16b4 2639 data,
7c365c21 2640 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2641 expected_type=list, default=[])
052e1350 2642 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2643 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2644
2645 return next((
2646 filter(None, (
2647 self._extract_chapters(
2648 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2649 chapter_time, chapter_title, duration)
2650 for contents in content_list
2651 ))), [])
2652
2653 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2654 chapters = []
7c365c21 2655 last_chapter = {'start_time': 0}
2656 for idx, chapter in enumerate(chapter_list or []):
2657 title = chapter_title(chapter)
84213ea8
S
2658 start_time = chapter_time(chapter)
2659 if start_time is None:
2660 continue
7c365c21 2661 last_chapter['end_time'] = start_time
2662 if start_time < last_chapter['start_time']:
2663 if idx == 1:
2664 chapters.pop()
2665 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2666 else:
2667 self.report_warning(f'Invalid start time for chapter "{title}"')
2668 continue
2669 last_chapter = {'start_time': start_time, 'title': title}
2670 chapters.append(last_chapter)
2671 last_chapter['end_time'] = duration
84213ea8
S
2672 return chapters
2673
545cc85d 2674 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2675 return self._parse_json(self._search_regex(
2676 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2677 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2678
a1c5d2ca
M
2679 def _extract_comment(self, comment_renderer, parent=None):
2680 comment_id = comment_renderer.get('commentId')
2681 if not comment_id:
2682 return
fe93e2c4 2683
052e1350 2684 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2685
49bd8c66 2686 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2687 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2688 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2689 author_id = try_get(comment_renderer,
2690 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2691
49bd8c66 2692 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2693 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2694 author_thumbnail = try_get(comment_renderer,
2695 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2696
2697 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2698 is_favorited = 'creatorHeart' in (try_get(
2699 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2700 return {
2701 'id': comment_id,
2702 'text': text,
d92f5d5a 2703 'timestamp': timestamp,
a1c5d2ca
M
2704 'time_text': time_text,
2705 'like_count': votes,
97524332 2706 'is_favorited': is_favorited,
a1c5d2ca
M
2707 'author': author,
2708 'author_id': author_id,
2709 'author_thumbnail': author_thumbnail,
2710 'author_is_uploader': author_is_uploader,
2711 'parent': parent or 'root'
2712 }
2713
46383212 2714 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2715
2716 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2717
2718 def extract_header(contents):
2d6659b9 2719 _continuation = None
2720 for content in contents:
46383212 2721 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2722 expected_comment_count = self._get_count(
2723 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2724
2d6659b9 2725 if expected_comment_count:
46383212 2726 tracker['est_total'] = expected_comment_count
2727 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2728 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2729
2730 sort_menu_item = try_get(
2731 comments_header_renderer,
2732 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2733 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2734
2735 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2736 if not _continuation:
2737 continue
2738
46383212 2739 sort_text = str_or_none(sort_menu_item.get('title'))
2740 if not sort_text:
2d6659b9 2741 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2742 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2743 break
a2160aa4 2744 return _continuation
a1c5d2ca 2745
2d6659b9 2746 def extract_thread(contents):
a1c5d2ca 2747 if not parent:
46383212 2748 tracker['current_page_thread'] = 0
a1c5d2ca 2749 for content in contents:
46383212 2750 if not parent and tracker['total_parent_comments'] >= max_parents:
2751 yield
a1c5d2ca 2752 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2753 comment_renderer = get_first(
2754 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2755 expected_type=dict, default={})
a1c5d2ca 2756
a1c5d2ca
M
2757 comment = self._extract_comment(comment_renderer, parent)
2758 if not comment:
2759 continue
46383212 2760
2761 tracker['running_total'] += 1
2762 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2763 yield comment
46383212 2764
a1c5d2ca
M
2765 # Attempt to get the replies
2766 comment_replies_renderer = try_get(
2767 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2768
2769 if comment_replies_renderer:
46383212 2770 tracker['current_page_thread'] += 1
a1c5d2ca 2771 comment_entries_iter = self._comment_entries(
99e9e001 2772 comment_replies_renderer, ytcfg, video_id,
46383212 2773 parent=comment.get('id'), tracker=tracker)
2774 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2775 yield reply_comment
2776
46383212 2777 # Keeps track of counts across recursive calls
2778 if not tracker:
2779 tracker = dict(
2780 running_total=0,
2781 est_total=0,
2782 current_page_thread=0,
2783 total_parent_comments=0,
2784 total_reply_comments=0)
2785
2786 # TODO: Deprecated
2d6659b9 2787 # YouTube comments have a max depth of 2
46383212 2788 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2789 if max_depth:
2790 self._downloader.deprecation_warning(
2791 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2792 if max_depth == 1 and parent:
2793 return
a1c5d2ca 2794
46383212 2795 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2796 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2797
46383212 2798 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2799 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2800 if message and not parent:
2801 self.report_warning(message, video_id=video_id)
2802
46383212 2803 response = None
2d6659b9 2804 is_first_continuation = parent is None
a1c5d2ca
M
2805
2806 for page_num in itertools.count(0):
2807 if not continuation:
2808 break
46383212 2809 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2810 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2811 if page_num == 0:
2812 if is_first_continuation:
2813 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2814 else:
2d6659b9 2815 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2816 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2817 else:
2818 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2819 ' ' if parent else '', ' replies' if parent else '',
2820 page_num, comment_prog_str)
2821
2822 response = self._extract_response(
fe93e2c4 2823 item_id=None, query=continuation,
2d6659b9 2824 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2825 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2826
46383212 2827 continuation_contents = traverse_obj(
2828 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2829
2d6659b9 2830 continuation = None
46383212 2831 for continuation_section in continuation_contents:
2832 continuation_items = traverse_obj(
2833 continuation_section,
2834 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2835 get_all=False, expected_type=list) or []
2836 if is_first_continuation:
2837 continuation = extract_header(continuation_items)
2838 is_first_continuation = False
2d6659b9 2839 if continuation:
a1c5d2ca 2840 break
46383212 2841 continue
a1c5d2ca 2842
46383212 2843 for entry in extract_thread(continuation_items):
2844 if not entry:
2845 return
2846 yield entry
2847 continuation = self._extract_continuation({'contents': continuation_items})
2848 if continuation:
2d6659b9 2849 break
a1c5d2ca 2850
a2160aa4 2851 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2852 """Entry for comment extraction"""
2d6659b9 2853 def _real_comment_extract(contents):
aae16f6e 2854 renderer = next((
2855 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2856 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2857 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2858
a2160aa4 2859 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2860 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2861
109dd3b2 2862 @staticmethod
99e9e001 2863 def _get_checkok_params():
2864 return {'contentCheckOk': True, 'racyCheckOk': True}
2865
2866 @classmethod
2867 def _generate_player_context(cls, sts=None):
109dd3b2 2868 context = {
2869 'html5Preference': 'HTML5_PREF_WANTS',
2870 }
2871 if sts is not None:
2872 context['signatureTimestamp'] = sts
2873 return {
2874 'playbackContext': {
2875 'contentPlaybackContext': context
a1a7907b 2876 },
99e9e001 2877 **cls._get_checkok_params()
109dd3b2 2878 }
2879
e7e94f2a
D
2880 @staticmethod
2881 def _is_agegated(player_response):
2882 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2883 return True
e7e94f2a
D
2884
2885 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2886 AGE_GATE_REASONS = (
2887 'confirm your age', 'age-restricted', 'inappropriate', # reason
2888 'age_verification_required', 'age_check_required', # status
2889 )
2890 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2891
2892 @staticmethod
2893 def _is_unplayable(player_response):
2894 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2895
99e9e001 2896 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2897
11f9be09 2898 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2899 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2900 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2901 headers = self.generate_api_headers(
99e9e001 2902 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2903
11f9be09 2904 yt_query = {'videoId': video_id}
2905 yt_query.update(self._generate_player_context(sts))
2906 return self._extract_response(
2907 item_id=video_id, ep='player', query=yt_query,
379e44ed 2908 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2909 default_client=client,
11f9be09 2910 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2911 ) or None
2912
11f9be09 2913 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2914 requested_clients = []
d0d012d4 2915 default = ['android', 'web']
000c15a4 2916 allowed_clients = sorted(
2917 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2918 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2919 for client in self._configuration_arg('player_client'):
2920 if client in allowed_clients:
2921 requested_clients.append(client)
d0d012d4 2922 elif client == 'default':
2923 requested_clients.extend(default)
b4c055ba 2924 elif client == 'all':
2925 requested_clients.extend(allowed_clients)
2926 else:
2927 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2928 if not requested_clients:
d0d012d4 2929 requested_clients = default
cf7e015f 2930
11f9be09 2931 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2932 requested_clients.extend(
e7e94f2a 2933 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2934
11f9be09 2935 return orderedSet(requested_clients)
cf7e015f 2936
c0bc527b
M
2937 def _extract_player_ytcfg(self, client, video_id):
2938 url = {
2939 'web_music': 'https://music.youtube.com',
2940 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2941 }.get(client)
2942 if not url:
2943 return {}
18c7683d 2944 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2945 return self.extract_ytcfg(video_id, webpage) or {}
2946
99e9e001 2947 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2948 initial_pr = None
2949 if webpage:
2950 initial_pr = self._extract_yt_initial_variable(
2951 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2952 video_id, 'initial player response')
6b09401b 2953
ae729626 2954 all_clients = set(clients)
c0bc527b 2955 clients = clients[::-1]
b6de707d 2956 prs = []
e7e94f2a 2957
ae729626 2958 def append_client(*client_names):
2959 """ Append the first client name that exists """
2960 for client_name in client_names:
2961 if client_name in INNERTUBE_CLIENTS:
2962 if client_name not in all_clients:
2963 clients.append(client_name)
2964 all_clients.add(client_name)
2965 return
e7e94f2a 2966
379e44ed 2967 # Android player_response does not have microFormats which are needed for
2968 # extraction of some data. So we return the initial_pr with formats
2969 # stripped out even if not requested by the user
2970 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2971 if initial_pr:
2972 pr = dict(initial_pr)
2973 pr['streamingData'] = None
b6de707d 2974 prs.append(pr)
379e44ed 2975
2976 last_error = None
b6de707d 2977 tried_iframe_fallback = False
2978 player_url = None
c0bc527b
M
2979 while clients:
2980 client = clients.pop()
11f9be09 2981 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2982 if 'configs' not in self._configuration_arg('player_skip'):
2983 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2984
b6de707d 2985 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2986 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2987 if 'js' in self._configuration_arg('player_skip'):
2988 require_js_player = False
2989 player_url = None
2990
2991 if not player_url and not tried_iframe_fallback and require_js_player:
2992 player_url = self._download_player_url(video_id)
2993 tried_iframe_fallback = True
2994
379e44ed 2995 try:
2996 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2997 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2998 except ExtractorError as e:
2999 if last_error:
3000 self.report_warning(last_error)
3001 last_error = e
3002 continue
3003
11f9be09 3004 if pr:
b6de707d 3005 prs.append(pr)
c0bc527b 3006
e7e94f2a 3007 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 3008 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
3009 append_client(client.replace('_agegate', '_creator'))
3010 elif self._is_agegated(pr):
ae729626 3011 append_client(f'{client}_embedded', f'{client.replace("_embedded", "")}_agegate')
c0bc527b 3012
379e44ed 3013 if last_error:
b6de707d 3014 if not len(prs):
379e44ed 3015 raise last_error
3016 self.report_warning(last_error)
b6de707d 3017 return prs, player_url
11f9be09 3018
a1b2d843 3019 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3020 itags, stream_ids = {}, []
2a9c6dcd 3021 itag_qualities, res_qualities = {}, {}
d3fc8074 3022 q = qualities([
2a9c6dcd 3023 # Normally tiny is the smallest video-only formats. But
3024 # audio-only formats with unknown quality may get tagged as tiny
3025 'tiny',
3026 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3027 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3028 ])
11f9be09 3029 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3030
545cc85d 3031 for fmt in streaming_formats:
727029c5 3032 if fmt.get('targetDurationSec'):
545cc85d 3033 continue
321bf820 3034
cc2db878 3035 itag = str_or_none(fmt.get('itag'))
9297939e 3036 audio_track = fmt.get('audioTrack') or {}
3037 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3038 if stream_id in stream_ids:
3039 continue
3040
cc2db878 3041 quality = fmt.get('quality')
2a9c6dcd 3042 height = int_or_none(fmt.get('height'))
d3fc8074 3043 if quality == 'tiny' or not quality:
3044 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3045 # The 3gp format (17) in android client has a quality of "small",
3046 # but is actually worse than other formats
3047 if itag == '17':
3048 quality = 'tiny'
3049 if quality:
3050 if itag:
3051 itag_qualities[itag] = quality
3052 if height:
3053 res_qualities[height] = quality
cc2db878 3054 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3055 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3056 # number of fragment that would subsequently requested with (`&sq=N`)
3057 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3058 continue
3059
545cc85d 3060 fmt_url = fmt.get('url')
3061 if not fmt_url:
3062 sc = compat_parse_qs(fmt.get('signatureCipher'))
3063 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3064 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3065 if not (sc and fmt_url and encrypted_sig):
3066 continue
545cc85d 3067 if not player_url:
201e9eaa 3068 continue
545cc85d 3069 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3070 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3071 fmt_url += '&' + sp + '=' + signature
3072
404f611f 3073 query = parse_qs(fmt_url)
3074 throttled = False
b2916526 3075 if query.get('n'):
404f611f 3076 try:
3077 fmt_url = update_url_query(fmt_url, {
3078 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3079 except ExtractorError as e:
aa9369a2 3080 self.report_warning(
3081 f'nsig extraction failed: You may experience throttling for some formats\n'
3082 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3083 throttled = True
3084
545cc85d 3085 if itag:
a0bb6ce5 3086 itags[itag] = 'https'
9297939e 3087 stream_ids.append(stream_id)
3088
0ad92dfb 3089 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3090 language_preference = (
3091 10 if audio_track.get('audioIsDefault') and 10
3092 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3093 else -1)
0ad92dfb 3094 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3095 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3096 # Make sure to avoid false positives with small duration differences.
3097 # Eg: __2ABJjxzNo, ySuUZEjARPY
3098 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3099 if is_damaged:
3100 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3101 dct = {
3102 'asr': int_or_none(fmt.get('audioSampleRate')),
3103 'filesize': int_or_none(fmt.get('contentLength')),
3104 'format_id': itag,
34921b43 3105 'format_note': join_nonempty(
26e8e044 3106 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3107 ' (default)' if language_preference > 0 else ''),
404f611f 3108 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3109 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3110 'source_preference': -10 if throttled else -1,
a4211baf 3111 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3112 'height': height,
dca3ff4a 3113 'quality': q(quality),
727029c5 3114 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3115 'tbr': tbr,
545cc85d 3116 'url': fmt_url,
2a9c6dcd 3117 'width': int_or_none(fmt.get('width')),
ab6df717 3118 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3119 'desc' if language_preference < -1 else ''),
3120 'language_preference': language_preference,
a405b38f 3121 # Strictly de-prioritize damaged and 3gp formats
3122 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3123 }
60bdb7bd 3124 mime_mobj = re.match(
3125 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3126 if mime_mobj:
3127 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3128 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3129 no_audio = dct.get('acodec') == 'none'
3130 no_video = dct.get('vcodec') == 'none'
3131 if no_audio:
3132 dct['vbr'] = tbr
3133 if no_video:
3134 dct['abr'] = tbr
3135 if no_audio or no_video:
545cc85d 3136 dct['downloader_options'] = {
3137 # Youtube throttles chunks >~10M
3138 'http_chunk_size': 10485760,
bf1317d2 3139 }
7c60c33e 3140 if dct.get('ext'):
3141 dct['container'] = dct['ext'] + '_dash'
11f9be09 3142 yield dct
545cc85d 3143
adbc4ec4 3144 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3145 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3146 if not self.get_param('youtube_include_hls_manifest', True):
3147 skip_manifests.append('hls')
3148 get_dash = 'dash' not in skip_manifests and (
3149 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3150 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3151
a0bb6ce5 3152 def process_manifest_format(f, proto, itag):
3153 if itag in itags:
3154 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3155 return False
3156 itag = f'{itag}-{proto}'
3157 if itag:
3158 f['format_id'] = itag
3159 itags[itag] = proto
3160
3161 f['quality'] = next((
3162 q(qdict[val])
e339d25a 3163 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3164 if val in qdict), -1)
3165 return True
2a9c6dcd 3166
11f9be09 3167 for sd in streaming_data:
5d3a0e79 3168 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3169 if hls_manifest_url:
2a9c6dcd 3170 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3171 if process_manifest_format(f, 'hls', self._search_regex(
3172 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3173 yield f
545cc85d 3174
5d3a0e79 3175 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3176 if dash_manifest_url:
2a9c6dcd 3177 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3178 if process_manifest_format(f, 'dash', f['format_id']):
3179 f['filesize'] = int_or_none(self._search_regex(
3180 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3181 if live_from_start:
3182 f['is_from_start'] = True
3183
a0bb6ce5 3184 yield f
11f9be09 3185
720c3099 3186 def _extract_storyboard(self, player_responses, duration):
3187 spec = get_first(
3188 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3189 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3190 if not base_url:
720c3099 3191 return
720c3099 3192 L = len(spec) - 1
3193 for i, args in enumerate(spec):
3194 args = args.split('#')
3195 counts = list(map(int_or_none, args[:5]))
3196 if len(args) != 8 or not all(counts):
3197 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3198 continue
3199 width, height, frame_count, cols, rows = counts
3200 N, sigh = args[6:]
3201
3202 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3203 fragment_count = frame_count / (cols * rows)
3204 fragment_duration = duration / fragment_count
3205 yield {
3206 'format_id': f'sb{i}',
3207 'format_note': 'storyboard',
3208 'ext': 'mhtml',
3209 'protocol': 'mhtml',
3210 'acodec': 'none',
3211 'vcodec': 'none',
3212 'url': url,
3213 'width': width,
3214 'height': height,
3215 'fragments': [{
b3edc806 3216 'url': url.replace('$M', str(j)),
720c3099 3217 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3218 } for j in range(math.ceil(fragment_count))],
3219 }
3220
adbc4ec4 3221 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3222 webpage = None
3223 if 'webpage' not in self._configuration_arg('player_skip'):
3224 webpage = self._download_webpage(
3225 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3226
3227 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3228
b6de707d 3229 player_responses, player_url = self._extract_player_responses(
11f9be09 3230 self._get_requested_clients(url, smuggled_data),
99e9e001 3231 video_id, webpage, master_ytcfg)
11f9be09 3232
adbc4ec4
THD
3233 return webpage, master_ytcfg, player_responses, player_url
3234
a1b2d843 3235 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3236 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3237 is_live = get_first(video_details, 'isLive')
3238 if is_live is None:
3239 is_live = get_first(live_broadcast_details, 'isLiveNow')
3240
3241 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3242 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3243
3244 return live_broadcast_details, is_live, streaming_data, formats
3245
3246 def _real_extract(self, url):
3247 url, smuggled_data = unsmuggle_url(url, {})
3248 video_id = self._match_id(url)
3249
3250 base_url = self.http_scheme() + '//www.youtube.com/'
3251 webpage_url = base_url + 'watch?v=' + video_id
3252
3253 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3254
11f9be09 3255 playability_statuses = traverse_obj(
3256 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3257
3258 trailer_video_id = get_first(
3259 playability_statuses,
3260 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3261 expected_type=str)
3262 if trailer_video_id:
3263 return self.url_result(
3264 trailer_video_id, self.ie_key(), trailer_video_id)
3265
3266 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3267 if webpage else (lambda x: None))
3268
3269 video_details = traverse_obj(
3270 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3271 microformats = traverse_obj(
3272 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3273 expected_type=dict, default=[])
3274 video_title = (
3275 get_first(video_details, 'title')
3276 or self._get_text(microformats, (..., 'title'))
3277 or search_meta(['og:title', 'twitter:title', 'title']))
3278 video_description = get_first(video_details, 'shortDescription')
3279
d89257f3 3280 multifeed_metadata_list = get_first(
3281 player_responses,
3282 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3283 expected_type=str)
3284 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3285 if self.get_param('noplaylist'):
11f9be09 3286 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3287 else:
3288 entries = []
3289 feed_ids = []
3290 for feed in multifeed_metadata_list.split(','):
3291 # Unquote should take place before split on comma (,) since textual
3292 # fields may contain comma as well (see
3293 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3294 feed_data = compat_parse_qs(
3295 compat_urllib_parse_unquote_plus(feed))
3296
3297 def feed_entry(name):
3298 return try_get(
3299 feed_data, lambda x: x[name][0], compat_str)
3300
3301 feed_id = feed_entry('id')
3302 if not feed_id:
3303 continue
3304 feed_title = feed_entry('title')
3305 title = video_title
3306 if feed_title:
3307 title += ' (%s)' % feed_title
3308 entries.append({
3309 '_type': 'url_transparent',
3310 'ie_key': 'Youtube',
3311 'url': smuggle_url(
3312 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3313 {'force_singlefeed': True}),
3314 'title': title,
3315 })
3316 feed_ids.append(feed_id)
3317 self.to_screen(
3318 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3319 % (', '.join(feed_ids), video_id))
3320 return self.playlist_result(
3321 entries, video_id, video_title, video_description)
11f9be09 3322
a1b2d843 3323 duration = int_or_none(
3324 get_first(video_details, 'lengthSeconds')
3325 or get_first(microformats, 'lengthSeconds')
3326 or parse_duration(search_meta('duration'))) or None
3327
3328 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3329 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3330
545cc85d 3331 if not formats:
11f9be09 3332 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3333 self.report_drm(video_id)
11f9be09 3334 pemr = get_first(
3335 playability_statuses,
3336 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3337 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3338 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3339 if subreason:
545cc85d 3340 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3341 countries = get_first(microformats, 'availableCountries')
545cc85d 3342 if not countries:
3343 regions_allowed = search_meta('regionsAllowed')
3344 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3345 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3346 reason += f'. {subreason}'
545cc85d 3347 if reason:
b7da73eb 3348 self.raise_no_formats(reason, expected=True)
bf1317d2 3349
11f9be09 3350 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3351 if not keywords and webpage:
3352 keywords = [
3353 unescapeHTML(m.group('content'))
3354 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3355 for keyword in keywords:
3356 if keyword.startswith('yt:stretch='):
201c1459 3357 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3358 if mobj:
3359 # NB: float is intentional for forcing float division
3360 w, h = (float(v) for v in mobj.groups())
3361 if w > 0 and h > 0:
3362 ratio = w / h
3363 for f in formats:
3364 if f.get('vcodec') != 'none':
3365 f['stretched_ratio'] = ratio
3366 break
a709d873 3367 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3368 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3369 if thumbnail_url:
3370 thumbnails.append({
3371 'url': thumbnail_url,
ff2751ac 3372 })
fccf5021 3373 original_thumbnails = thumbnails.copy()
3374
0ba692ac 3375 # The best resolution thumbnails sometimes does not appear in the webpage
3376 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3377 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3378 thumbnail_names = [
3379 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3380 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3381 'mqdefault', 'mq1', 'mq2', 'mq3',
3382 'default', '1', '2', '3'
3383 ]
cca80fe6 3384 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3385 thumbnails.extend({
3386 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3387 video_id=video_id, name=name, ext=ext,
3388 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3389 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3390 for thumb in thumbnails:
cca80fe6 3391 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3392 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3393 self._remove_duplicate_formats(thumbnails)
fccf5021 3394 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3395
7ea65411 3396 category = get_first(microformats, 'category') or search_meta('genre')
3397 channel_id = str_or_none(
3398 get_first(video_details, 'channelId')
3399 or get_first(microformats, 'externalChannelId')
3400 or search_meta('channelId'))
7ea65411 3401 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3402
3403 live_content = get_first(video_details, 'isLiveContent')
3404 is_upcoming = get_first(video_details, 'isUpcoming')
3405 if is_live is None:
3406 if is_upcoming or live_content is False:
3407 is_live = False
3408 if is_upcoming is None and (live_content or is_live):
3409 is_upcoming = False
adbc4ec4
THD
3410 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3411 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3412 if not duration and live_end_time and live_start_time:
3413 duration = live_end_time - live_start_time
3414
3415 if is_live and self.get_param('live_from_start'):
3416 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3417
720c3099 3418 formats.extend(self._extract_storyboard(player_responses, duration))
3419
3420 # Source is given priority since formats that throttle are given lower source_preference
3421 # When throttling issue is fully fixed, remove this
3422 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3423
545cc85d 3424 info = {
3425 'id': video_id,
39ca3b5c 3426 'title': video_title,
545cc85d 3427 'formats': formats,
3428 'thumbnails': thumbnails,
fccf5021 3429 # The best thumbnail that we are sure exists. Prevents unnecessary
3430 # URL checking if user don't care about getting the best possible thumbnail
3431 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3432 'description': video_description,
11f9be09 3433 'uploader': get_first(video_details, 'author'),
545cc85d 3434 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3435 'uploader_url': owner_profile_url,
3436 'channel_id': channel_id,
e0ddbd02 3437 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3438 'duration': duration,
3439 'view_count': int_or_none(
11f9be09 3440 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3441 or search_meta('interactionCount')),
11f9be09 3442 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3443 'age_limit': 18 if (
11f9be09 3444 get_first(microformats, 'isFamilySafe') is False
545cc85d 3445 or search_meta('isFamilyFriendly') == 'false'
3446 or search_meta('og:restrictions:age') == '18+') else 0,
3447 'webpage_url': webpage_url,
3448 'categories': [category] if category else None,
3449 'tags': keywords,
11f9be09 3450 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3451 'is_live': is_live,
3452 'was_live': (False if is_live or is_upcoming or live_content is False
3453 else None if is_live is None or is_upcoming is None
3454 else live_content),
3455 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3456 'release_timestamp': live_start_time,
545cc85d 3457 }
b477fc13 3458
3944e7af 3459 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3460 if pctr:
ecdc9049 3461 def get_lang_code(track):
3462 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3463 or track.get('languageCode'))
3464
3465 # Converted into dicts to remove duplicates
3466 captions = {
3467 get_lang_code(sub): sub
3468 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3469 translation_languages = {
3470 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3471 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3472
774d79cc 3473 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3474 lang_subs = container.setdefault(lang_code, [])
545cc85d 3475 for fmt in self._SUBTITLE_FORMATS:
3476 query.update({
3477 'fmt': fmt,
3478 })
3479 lang_subs.append({
3480 'ext': fmt,
60f393e4 3481 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3482 'name': sub_name,
545cc85d 3483 })
7e72694b 3484
ecdc9049 3485 subtitles, automatic_captions = {}, {}
3486 for lang_code, caption_track in captions.items():
3487 base_url = caption_track.get('baseUrl')
1235d333 3488 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3489 if not base_url:
3490 continue
ecdc9049 3491 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3492 if caption_track.get('kind') != 'asr':
545cc85d 3493 if not lang_code:
3494 continue
3495 process_language(
ecdc9049 3496 subtitles, base_url, lang_code, lang_name, {})
3497 if not caption_track.get('isTranslatable'):
3498 continue
3944e7af 3499 for trans_code, trans_name in translation_languages.items():
3500 if not trans_code:
545cc85d 3501 continue
1235d333 3502 orig_trans_code = trans_code
ecdc9049 3503 if caption_track.get('kind') != 'asr':
18e49408 3504 if 'translated_subs' in self._configuration_arg('skip'):
3505 continue
ecdc9049 3506 trans_code += f'-{lang_code}'
3507 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3508 # Add an "-orig" label to the original language so that it can be distinguished.
3509 # The subs are returned without "-orig" as well for compatibility
1235d333 3510 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3511 process_language(
d49669ac 3512 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3513 # Setting tlang=lang returns damaged subtitles.
d49669ac 3514 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3515 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3516 info['automatic_captions'] = automatic_captions
3517 info['subtitles'] = subtitles
7e72694b 3518
545cc85d 3519 parsed_url = compat_urllib_parse_urlparse(url)
3520 for component in [parsed_url.fragment, parsed_url.query]:
3521 query = compat_parse_qs(component)
3522 for k, v in query.items():
3523 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3524 d_k += '_time'
3525 if d_k not in info and k in s_ks:
3526 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3527
3528 # Youtube Music Auto-generated description
822b9d9c 3529 if video_description:
38d70284 3530 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 3531 if mobj:
822b9d9c
RA
3532 release_year = mobj.group('release_year')
3533 release_date = mobj.group('release_date')
3534 if release_date:
3535 release_date = release_date.replace('-', '')
3536 if not release_year:
545cc85d 3537 release_year = release_date[:4]
3538 info.update({
3539 'album': mobj.group('album'.strip()),
3540 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3541 'track': mobj.group('track').strip(),
3542 'release_date': release_date,
cc2db878 3543 'release_year': int_or_none(release_year),
545cc85d 3544 })
7e72694b 3545
545cc85d 3546 initial_data = None
3547 if webpage:
3548 initial_data = self._extract_yt_initial_variable(
3549 webpage, self._YT_INITIAL_DATA_RE, video_id,
3550 'yt initial data')
3551 if not initial_data:
99e9e001 3552 query = {'videoId': video_id}
3553 query.update(self._get_checkok_params())
109dd3b2 3554 initial_data = self._extract_response(
3555 item_id=video_id, ep='next', fatal=False,
99e9e001 3556 ytcfg=master_ytcfg, query=query,
3557 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3558 note='Downloading initial data API JSON')
545cc85d 3559
c60ee3a2 3560 try:
3561 # This will error if there is no livechat
3562 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3563 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3564 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3565 'video_id': video_id,
3566 'ext': 'json',
f6745c49 3567 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3568 }]
3569 except (KeyError, IndexError, TypeError):
3570 pass
545cc85d 3571
3572 if initial_data:
7c365c21 3573 info['chapters'] = (
3574 self._extract_chapters_from_json(initial_data, duration)
3575 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3576 or None)
545cc85d 3577
17322130 3578 contents = traverse_obj(
3579 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3580 expected_type=list, default=[])
3581
3582 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3583 if vpir:
3584 stl = vpir.get('superTitleLink')
3585 if stl:
3586 stl = self._get_text(stl)
3587 if try_get(
3588 vpir,
3589 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3590 info['location'] = stl
3591 else:
3592 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3593 if mobj:
545cc85d 3594 info.update({
17322130 3595 'series': mobj.group(1),
3596 'season_number': int(mobj.group(2)),
3597 'episode_number': int(mobj.group(3)),
545cc85d 3598 })
17322130 3599 for tlb in (try_get(
3600 vpir,
3601 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3602 list) or []):
3603 tbr = tlb.get('toggleButtonRenderer') or {}
3604 for getter, regex in [(
3605 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3606 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3607 lambda x: x['accessibility'],
3608 lambda x: x['accessibilityData']['accessibilityData'],
3609 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3610 label = (try_get(tbr, getter, dict) or {}).get('label')
3611 if label:
3612 mobj = re.match(regex, label)
3613 if mobj:
3614 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3615 break
17322130 3616 sbr_tooltip = try_get(
3617 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3618 if sbr_tooltip:
3619 like_count, dislike_count = sbr_tooltip.split(' / ')
3620 info.update({
3621 'like_count': str_to_int(like_count),
3622 'dislike_count': str_to_int(dislike_count),
3623 })
3624 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3625 if vsir:
3626 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3627 info.update({
3628 'channel': self._get_text(vor, 'title'),
3629 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3630
3631 rows = try_get(
3632 vsir,
3633 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3634 list) or []
3635 multiple_songs = False
3636 for row in rows:
3637 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3638 multiple_songs = True
3639 break
3640 for row in rows:
3641 mrr = row.get('metadataRowRenderer') or {}
3642 mrr_title = mrr.get('title')
3643 if not mrr_title:
3644 continue
3645 mrr_title = self._get_text(mrr, 'title')
3646 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3647 if mrr_title == 'License':
3648 info['license'] = mrr_contents_text
3649 elif not multiple_songs:
3650 if mrr_title == 'Album':
3651 info['album'] = mrr_contents_text
3652 elif mrr_title == 'Artist':
3653 info['artist'] = mrr_contents_text
3654 elif mrr_title == 'Song':
3655 info['track'] = mrr_contents_text
545cc85d 3656
3657 fallbacks = {
3658 'channel': 'uploader',
3659 'channel_id': 'uploader_id',
3660 'channel_url': 'uploader_url',
3661 }
992f9a73 3662
17322130 3663 # The upload date for scheduled, live and past live streams / premieres in microformats
3664 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3665 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3666 upload_date = (
3667 unified_strdate(get_first(microformats, 'uploadDate'))
3668 or unified_strdate(search_meta('uploadDate')))
3669 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3670 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3671 info['upload_date'] = upload_date
992f9a73 3672
545cc85d 3673 for to, frm in fallbacks.items():
3674 if not info.get(to):
3675 info[to] = info.get(frm)
3676
3677 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3678 v = info.get(s_k)
3679 if v:
3680 info[d_k] = v
b84071c0 3681
11f9be09 3682 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3683 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3684 is_membersonly = None
b28f8d24 3685 is_premium = None
c224251a
M
3686 if initial_data and is_private is not None:
3687 is_membersonly = False
b28f8d24 3688 is_premium = False
47193e02 3689 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3690 badge_labels = set()
3691 for content in contents:
3692 if not isinstance(content, dict):
3693 continue
3694 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3695 for badge_label in badge_labels:
3696 if badge_label.lower() == 'members only':
3697 is_membersonly = True
3698 elif badge_label.lower() == 'premium':
3699 is_premium = True
3700 elif badge_label.lower() == 'unlisted':
3701 is_unlisted = True
c224251a 3702
c224251a
M
3703 info['availability'] = self._availability(
3704 is_private=is_private,
b28f8d24 3705 needs_premium=is_premium,
c224251a
M
3706 needs_subscription=is_membersonly,
3707 needs_auth=info['age_limit'] >= 18,
3708 is_unlisted=None if is_private is None else is_unlisted)
3709
a2160aa4 3710 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3711
11f9be09 3712 self.mark_watched(video_id, player_responses)
d77ab8e2 3713
545cc85d 3714 return info
c5e8d7af 3715
a61fd4cf 3716
a6213a49 3717class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3718
182bda88 3719 @staticmethod
3720 def passthrough_smuggled_data(func):
3721 def _smuggle(entries, smuggled_data):
3722 for entry in entries:
3723 # TODO: Convert URL to music.youtube instead.
3724 # Do we need to passthrough any other smuggled_data?
3725 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3726 yield entry
3727
3728 @functools.wraps(func)
3729 def wrapper(self, url):
3730 url, smuggled_data = unsmuggle_url(url, {})
3731 if self.is_music_url(url):
3732 smuggled_data['is_music_url'] = True
3733 info_dict = func(self, url, smuggled_data)
3734 if smuggled_data and info_dict.get('entries'):
3735 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3736 return info_dict
3737 return wrapper
3738
a6213a49 3739 def _extract_channel_id(self, webpage):
3740 channel_id = self._html_search_meta(
3741 'channelId', webpage, 'channel id', default=None)
3742 if channel_id:
3743 return channel_id
3744 channel_url = self._html_search_meta(
3745 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3746 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3747 'twitter:app:url:googleplay'), webpage, 'channel url')
3748 return self._search_regex(
3749 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3750 channel_url, 'channel id')
15f6397c 3751
8bdd16b4 3752 @staticmethod
cd7c66cf 3753 def _extract_basic_item_renderer(item):
3754 # Modified from _extract_grid_item_renderer
201c1459 3755 known_basic_renderers = (
3756 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3757 )
3758 for key, renderer in item.items():
201c1459 3759 if not isinstance(renderer, dict):
cd7c66cf 3760 continue
201c1459 3761 elif key in known_basic_renderers:
3762 return renderer
3763 elif key.startswith('grid') and key.endswith('Renderer'):
3764 return renderer
8bdd16b4 3765
8bdd16b4 3766 def _grid_entries(self, grid_renderer):
3767 for item in grid_renderer['items']:
3768 if not isinstance(item, dict):
39b62db1 3769 continue
cd7c66cf 3770 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3771 if not isinstance(renderer, dict):
3772 continue
052e1350 3773 title = self._get_text(renderer, 'title')
fe93e2c4 3774
8bdd16b4 3775 # playlist
3776 playlist_id = renderer.get('playlistId')
3777 if playlist_id:
3778 yield self.url_result(
3779 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3780 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3781 video_title=title)
201c1459 3782 continue
8bdd16b4 3783 # video
3784 video_id = renderer.get('videoId')
3785 if video_id:
3786 yield self._extract_video(renderer)
201c1459 3787 continue
8bdd16b4 3788 # channel
3789 channel_id = renderer.get('channelId')
3790 if channel_id:
8bdd16b4 3791 yield self.url_result(
3792 'https://www.youtube.com/channel/%s' % channel_id,
3793 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3794 continue
3795 # generic endpoint URL support
3796 ep_url = urljoin('https://www.youtube.com/', try_get(
3797 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3798 compat_str))
3799 if ep_url:
3800 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3801 if ie.suitable(ep_url):
3802 yield self.url_result(
3803 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3804 break
8bdd16b4 3805
16aa9ea4 3806 def _music_reponsive_list_entry(self, renderer):
3807 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3808 if video_id:
3809 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3810 ie=YoutubeIE.ie_key(), video_id=video_id)
3811 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3812 if playlist_id:
3813 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3814 if video_id:
3815 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3816 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3817 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3818 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3819 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3820 if browse_id:
3821 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3822 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3823
3d3dddc9 3824 def _shelf_entries_from_content(self, shelf_renderer):
3825 content = shelf_renderer.get('content')
3826 if not isinstance(content, dict):
8bdd16b4 3827 return
cd7c66cf 3828 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3829 if renderer:
3830 # TODO: add support for nested playlists so each shelf is processed
3831 # as separate playlist
3832 # TODO: this includes only first N items
3833 for entry in self._grid_entries(renderer):
3834 yield entry
3835 renderer = content.get('horizontalListRenderer')
3836 if renderer:
3837 # TODO
3838 pass
8bdd16b4 3839
29f7c58a 3840 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3841 ep = try_get(
3842 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3843 compat_str)
3844 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3845 if shelf_url:
29f7c58a 3846 # Skipping links to another channels, note that checking for
3847 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3848 # will not work
3849 if skip_channels and '/channels?' in shelf_url:
3850 return
052e1350 3851 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3852 yield self.url_result(shelf_url, video_title=title)
3853 # Shelf may not contain shelf URL, fallback to extraction from content
3854 for entry in self._shelf_entries_from_content(shelf_renderer):
3855 yield entry
c5e8d7af 3856
8bdd16b4 3857 def _playlist_entries(self, video_list_renderer):
3858 for content in video_list_renderer['contents']:
3859 if not isinstance(content, dict):
3860 continue
3861 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3862 if not isinstance(renderer, dict):
3863 continue
3864 video_id = renderer.get('videoId')
3865 if not video_id:
3866 continue
3867 yield self._extract_video(renderer)
07aeced6 3868
3462ffa8 3869 def _rich_entries(self, rich_grid_renderer):
3870 renderer = try_get(
70d5c17b 3871 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3872 video_id = renderer.get('videoId')
3873 if not video_id:
3874 return
3875 yield self._extract_video(renderer)
3876
8bdd16b4 3877 def _video_entry(self, video_renderer):
3878 video_id = video_renderer.get('videoId')
3879 if video_id:
3880 return self._extract_video(video_renderer)
dacb3a86 3881
8bdd16b4 3882 def _post_thread_entries(self, post_thread_renderer):
3883 post_renderer = try_get(
3884 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3885 if not post_renderer:
3886 return
3887 # video attachment
3888 video_renderer = try_get(
895b0931 3889 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3890 video_id = video_renderer.get('videoId')
3891 if video_id:
3892 entry = self._extract_video(video_renderer)
8bdd16b4 3893 if entry:
3894 yield entry
895b0931 3895 # playlist attachment
3896 playlist_id = try_get(
3897 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3898 if playlist_id:
3899 yield self.url_result(
e28f1c0a 3900 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3901 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3902 # inline video links
3903 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3904 for run in runs:
3905 if not isinstance(run, dict):
3906 continue
3907 ep_url = try_get(
3908 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3909 if not ep_url:
3910 continue
3911 if not YoutubeIE.suitable(ep_url):
3912 continue
3913 ep_video_id = YoutubeIE._match_id(ep_url)
3914 if video_id == ep_video_id:
3915 continue
895b0931 3916 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3917
8bdd16b4 3918 def _post_thread_continuation_entries(self, post_thread_continuation):
3919 contents = post_thread_continuation.get('contents')
3920 if not isinstance(contents, list):
3921 return
3922 for content in contents:
3923 renderer = content.get('backstagePostThreadRenderer')
3924 if not isinstance(renderer, dict):
3925 continue
3926 for entry in self._post_thread_entries(renderer):
3927 yield entry
07aeced6 3928
39ed931e 3929 r''' # unused
3930 def _rich_grid_entries(self, contents):
3931 for content in contents:
3932 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3933 if video_renderer:
3934 entry = self._video_entry(video_renderer)
3935 if entry:
3936 yield entry
3937 '''
52efa4b3 3938
a6213a49 3939 def _extract_entries(self, parent_renderer, continuation_list):
3940 # continuation_list is modified in-place with continuation_list = [continuation_token]
3941 continuation_list[:] = [None]
3942 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3943 for content in contents:
3944 if not isinstance(content, dict):
3945 continue
16aa9ea4 3946 is_renderer = traverse_obj(
3947 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3948 expected_type=dict)
a6213a49 3949 if not is_renderer:
3950 renderer = content.get('richItemRenderer')
3951 if renderer:
3952 for entry in self._rich_entries(renderer):
3953 yield entry
3954 continuation_list[0] = self._extract_continuation(parent_renderer)
3955 continue
3956 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3957 for isr_content in isr_contents:
3958 if not isinstance(isr_content, dict):
8bdd16b4 3959 continue
69184e41 3960
a6213a49 3961 known_renderers = {
3962 'playlistVideoListRenderer': self._playlist_entries,
3963 'gridRenderer': self._grid_entries,
3964 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3965 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3966 'backstagePostThreadRenderer': self._post_thread_entries,
3967 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3968 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3969 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3970 }
3971 for key, renderer in isr_content.items():
3972 if key not in known_renderers:
3973 continue
3974 for entry in known_renderers[key](renderer):
3975 if entry:
3976 yield entry
3977 continuation_list[0] = self._extract_continuation(renderer)
3978 break
70d5c17b 3979
3980 if not continuation_list[0]:
a6213a49 3981 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3982
a6213a49 3983 if not continuation_list[0]:
3984 continuation_list[0] = self._extract_continuation(parent_renderer)
3985
3986 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3987 continuation_list = [None]
3988 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3989 tab_content = try_get(tab, lambda x: x['content'], dict)
3990 if not tab_content:
3991 return
3462ffa8 3992 parent_renderer = (
29f7c58a 3993 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3994 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3995 for entry in extract_entries(parent_renderer):
3996 yield entry
3462ffa8 3997 continuation = continuation_list[0]
d069eca7 3998
8bdd16b4 3999 for page_num in itertools.count(1):
4000 if not continuation:
4001 break
99e9e001 4002 headers = self.generate_api_headers(
4003 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4004 response = self._extract_response(
4005 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 4006 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4007 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4008
4009 if not response:
8bdd16b4 4010 break
ac56cf38 4011 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4012 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4013 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4014
69184e41 4015 known_continuation_renderers = {
4016 'playlistVideoListContinuation': self._playlist_entries,
4017 'gridContinuation': self._grid_entries,
4018 'itemSectionContinuation': self._post_thread_continuation_entries,
4019 'sectionListContinuation': extract_entries, # for feeds
4020 }
8bdd16b4 4021 continuation_contents = try_get(
69184e41 4022 response, lambda x: x['continuationContents'], dict) or {}
4023 continuation_renderer = None
4024 for key, value in continuation_contents.items():
4025 if key not in known_continuation_renderers:
3462ffa8 4026 continue
69184e41 4027 continuation_renderer = value
4028 continuation_list = [None]
4029 for entry in known_continuation_renderers[key](continuation_renderer):
4030 yield entry
4031 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4032 break
4033 if continuation_renderer:
4034 continue
c5e8d7af 4035
a1b535bd 4036 known_renderers = {
e4b98809 4037 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4038 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4039 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4040 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4041 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4042 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4043 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4044 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4045 }
cce889b9 4046 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4047 continuation_items = try_get(
cce889b9 4048 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4049 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4050 video_items_renderer = None
4051 for key, value in continuation_item.items():
4052 if key not in known_renderers:
8bdd16b4 4053 continue
a1b535bd 4054 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4055 continuation_list = [None]
a1b535bd 4056 for entry in known_renderers[key][0](video_items_renderer):
4057 yield entry
9ba5705a 4058 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4059 break
4060 if video_items_renderer:
4061 continue
8bdd16b4 4062 break
9558dcec 4063
8bdd16b4 4064 @staticmethod
7c219ea6 4065 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4066 for tab in tabs:
cd684175 4067 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4068 if renderer.get('selected') is True:
4069 return renderer
2b3c2546 4070 else:
7c219ea6 4071 if fatal:
4072 raise ExtractorError('Unable to find selected tab')
b82f815f 4073
47193e02 4074 @classmethod
4075 def _extract_uploader(cls, data):
8bdd16b4 4076 uploader = {}
47193e02 4077 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4078 owner = try_get(
4079 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4080 if owner:
4081 uploader['uploader'] = owner.get('text')
4082 uploader['uploader_id'] = try_get(
4083 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4084 uploader['uploader_url'] = urljoin(
4085 'https://www.youtube.com/',
4086 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4087 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4088
ac56cf38 4089 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4090 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4091 tags = []
b60419c5 4092
8bdd16b4 4093 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4094 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4095 renderer = try_get(
4096 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4097 if renderer:
b60419c5 4098 channel_name = renderer.get('title')
4099 channel_url = renderer.get('channelUrl')
4100 channel_id = renderer.get('externalId')
39ed931e 4101 else:
64c0d954 4102 renderer = try_get(
4103 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4104
8bdd16b4 4105 if renderer:
4106 title = renderer.get('title')
ecc97af3 4107 description = renderer.get('description', '')
b60419c5 4108 playlist_id = channel_id
4109 tags = renderer.get('keywords', '').split()
b60419c5 4110
301d07fc 4111 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4112 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4113 def _get_uncropped(url):
4114 return url_or_none((url or '').split('=')[0] + '=s0')
4115
4116 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4117 if avatar_thumbnails:
4118 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4119 if uncropped_avatar:
4120 avatar_thumbnails.append({
4121 'url': uncropped_avatar,
4122 'id': 'avatar_uncropped',
4123 'preference': 1
4124 })
4125
4126 channel_banners = self._extract_thumbnails(
4127 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4128 for banner in channel_banners:
4129 banner['preference'] = -10
4130
4131 if channel_banners:
4132 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4133 if uncropped_banner:
4134 channel_banners.append({
4135 'url': uncropped_banner,
4136 'id': 'banner_uncropped',
4137 'preference': -5
4138 })
4139
4140 primary_thumbnails = self._extract_thumbnails(
4141 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4142
3462ffa8 4143 if playlist_id is None:
70d5c17b 4144 playlist_id = item_id
f0d785d3 4145
4146 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4147 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4148 if title is None:
f0d785d3 4149 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4150 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4151 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4152
b60419c5 4153 metadata = {
4154 'playlist_id': playlist_id,
4155 'playlist_title': title,
4156 'playlist_description': description,
4157 'uploader': channel_name,
4158 'uploader_id': channel_id,
4159 'uploader_url': channel_url,
301d07fc 4160 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4161 'tags': tags,
f0d785d3 4162 'view_count': self._get_count(playlist_stats, 1),
4163 'availability': self._extract_availability(data),
4164 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4165 'playlist_count': self._get_count(playlist_stats, 0),
4166 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4167 }
4168 if not channel_id:
4169 metadata.update(self._extract_uploader(data))
4170 metadata.update({
4171 'channel': metadata['uploader'],
4172 'channel_id': metadata['uploader_id'],
4173 'channel_url': metadata['uploader_url']})
4174 return self.playlist_result(
d069eca7 4175 self._entries(
ac56cf38 4176 selected_tab, playlist_id, ytcfg,
4177 self._extract_account_syncid(ytcfg, data),
4178 self._extract_visitor_data(data, ytcfg)),
b60419c5 4179 **metadata)
73c4ac2c 4180
ac56cf38 4181 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4182 first_id = last_id = response = None
2be71994 4183 for page_num in itertools.count(1):
cd7c66cf 4184 videos = list(self._playlist_entries(playlist))
4185 if not videos:
4186 return
2be71994 4187 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4188 if start >= len(videos):
4189 return
4190 for video in videos[start:]:
4191 if video['id'] == first_id:
4192 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4193 return
4194 yield video
4195 first_id = first_id or videos[0]['id']
4196 last_id = videos[-1]['id']
79360d99 4197 watch_endpoint = try_get(
4198 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4199 headers = self.generate_api_headers(
4200 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4201 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4202 query = {
4203 'playlistId': playlist_id,
4204 'videoId': watch_endpoint.get('videoId') or last_id,
4205 'index': watch_endpoint.get('index') or len(videos),
4206 'params': watch_endpoint.get('params') or 'OAE%3D'
4207 }
4208 response = self._extract_response(
4209 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4210 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4211 check_get_keys='contents'
4212 )
cd7c66cf 4213 playlist = try_get(
79360d99 4214 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4215
ac56cf38 4216 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4217 title = playlist.get('title') or try_get(
4218 data, lambda x: x['titleText']['simpleText'], compat_str)
4219 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4220
4221 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4222 playlist_url = urljoin(url, try_get(
4223 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4224 compat_str))
4225 if playlist_url and playlist_url != url:
4226 return self.url_result(
4227 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4228 video_title=title)
cd7c66cf 4229
8bdd16b4 4230 return self.playlist_result(
ac56cf38 4231 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4232 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4233
47193e02 4234 def _extract_availability(self, data):
4235 """
4236 Gets the availability of a given playlist/tab.
4237 Note: Unless YouTube tells us explicitly, we do not assume it is public
4238 @param data: response
4239 """
4240 is_private = is_unlisted = None
4241 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4242 badge_labels = self._extract_badges(renderer)
4243
4244 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4245 privacy_dropdown_entries = try_get(
4246 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4247 for renderer_dict in privacy_dropdown_entries:
4248 is_selected = try_get(
4249 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4250 if not is_selected:
4251 continue
052e1350 4252 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4253 if label:
4254 badge_labels.add(label.lower())
4255 break
4256
4257 for badge_label in badge_labels:
4258 if badge_label == 'unlisted':
4259 is_unlisted = True
4260 elif badge_label == 'private':
4261 is_private = True
4262 elif badge_label == 'public':
4263 is_unlisted = is_private = False
4264 return self._availability(is_private, False, False, False, is_unlisted)
4265
4266 @staticmethod
4267 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4268 sidebar_renderer = try_get(
4269 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4270 for item in sidebar_renderer:
4271 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4272 if renderer:
4273 return renderer
4274
ac56cf38 4275 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4276 """
4277 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4278 """
5d342002 4279 browse_id = params = None
47193e02 4280 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4281 if not renderer:
4282 return
4283 menu_renderer = try_get(
4284 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4285 for menu_item in menu_renderer:
4286 if not isinstance(menu_item, dict):
358de58c 4287 continue
47193e02 4288 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4289 text = try_get(
4290 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4291 if not text or text.lower() != 'show unavailable videos':
4292 continue
4293 browse_endpoint = try_get(
4294 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4295 browse_id = browse_endpoint.get('browseId')
4296 params = browse_endpoint.get('params')
4297 break
5d342002 4298
11f9be09 4299 headers = self.generate_api_headers(
99e9e001 4300 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4301 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4302 query = {
4303 'params': params or 'wgYCCAA=',
4304 'browseId': browse_id or 'VL%s' % item_id
4305 }
4306 return self._extract_response(
4307 item_id=item_id, headers=headers, query=query,
fe93e2c4 4308 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4309 note='Downloading API JSON with unavailable videos')
358de58c 4310
ac56cf38 4311 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4312 retries = self.get_param('extractor_retries', 3)
62bff2c1 4313 count = -1
ac56cf38 4314 webpage = data = last_error = None
14fdfea9 4315 while count < retries:
62bff2c1 4316 count += 1
14fdfea9 4317 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4318 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4319 if last_error:
c705177d 4320 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4321 try:
4322 webpage = self._download_webpage(
4323 url, item_id,
4324 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4325 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4326 except ExtractorError as e:
4327 if isinstance(e.cause, network_exceptions):
4328 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4329 last_error = error_to_compat_str(e.cause or e.msg)
4330 if count < retries:
4331 continue
4332 if fatal:
4333 raise
4334 self.report_warning(error_to_compat_str(e))
14fdfea9 4335 break
ac56cf38 4336 else:
4337 try:
4338 self._extract_and_report_alerts(data)
4339 except ExtractorError as e:
4340 if fatal:
4341 raise
4342 self.report_warning(error_to_compat_str(e))
4343 break
4344
7c219ea6 4345 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4346 break
4347
4348 last_error = 'Incomplete yt initial data received'
4349 if count >= retries:
4350 if fatal:
4351 raise ExtractorError(last_error)
4352 self.report_warning(last_error)
4353 break
4354
cd7c66cf 4355 return webpage, data
4356
ac56cf38 4357 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4358 data = None
4359 if 'webpage' not in self._configuration_arg('skip'):
4360 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4361 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4362 # Reject webpage data if redirected to home page without explicitly requesting
4363 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4364 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4365 if (url != 'https://www.youtube.com/feed/recommended'
4366 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4367 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4368 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4369 if fatal:
4370 raise ExtractorError(msg, expected=True)
4371 self.report_warning(msg, only_once=True)
ac56cf38 4372 if not data:
4373 if not ytcfg and self.is_authenticated:
4374 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4375 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4376 raise ExtractorError(
4377 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4378 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4379 expected=True)
4380 self.report_warning(msg, only_once=True)
4381 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4382 return data, ytcfg
4383
4384 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4385 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4386 resolve_response = self._extract_response(
4387 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4388 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4389 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4390 for ep_key, ep in endpoints.items():
4391 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4392 if params:
4393 return self._extract_response(
4394 item_id=item_id, query=params, ep=ep, headers=headers,
4395 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4396 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4397 err_note = 'Failed to resolve url (does the playlist exist?)'
4398 if fatal:
4399 raise ExtractorError(err_note, expected=True)
4400 self.report_warning(err_note, item_id)
4401
a6213a49 4402 _SEARCH_PARAMS = None
4403
af5c1c55 4404 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4405 data = {'query': query}
4406 if params is NO_DEFAULT:
4407 params = self._SEARCH_PARAMS
4408 if params:
4409 data['params'] = params
16aa9ea4 4410
4411 content_keys = (
4412 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4413 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4414 # ytmusic search
4415 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4416 ('continuationContents', ),
4417 )
4418 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4419
a61fd4cf 4420 continuation_list = [None]
a6213a49 4421 for page_num in itertools.count(1):
a61fd4cf 4422 data.update(continuation_list[0] or {})
a6213a49 4423 search = self._extract_response(
4424 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4425 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4426 slr_contents = traverse_obj(search, *content_keys)
4427 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4428 if not continuation_list[0]:
a6213a49 4429 break
4430
4431
4432class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4433 IE_DESC = 'YouTube Tabs'
4434 _VALID_URL = r'''(?x:
4435 https?://
4436 (?:\w+\.)?
4437 (?:
4438 youtube(?:kids)?\.com|
4439 %(invidious)s
4440 )/
4441 (?:
4442 (?P<channel_type>channel|c|user|browse)/|
4443 (?P<not_channel>
4444 feed/|hashtag/|
4445 (?:playlist|watch)\?.*?\blist=
4446 )|
4447 (?!(?:%(reserved_names)s)\b) # Direct URLs
4448 )
4449 (?P<id>[^/?\#&]+)
4450 )''' % {
4451 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4452 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4453 }
4454 IE_NAME = 'youtube:tab'
4455
4456 _TESTS = [{
4457 'note': 'playlists, multipage',
4458 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4459 'playlist_mincount': 94,
4460 'info_dict': {
4461 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4462 'title': 'Igor Kleiner - Playlists',
a6213a49 4463 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4464 'uploader': 'Igor Kleiner',
a6213a49 4465 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4466 'channel': 'Igor Kleiner',
4467 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4468 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4469 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4470 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4471 'channel_follower_count': int
a6213a49 4472 },
4473 }, {
4474 'note': 'playlists, multipage, different order',
4475 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4476 'playlist_mincount': 94,
4477 'info_dict': {
4478 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4479 'title': 'Igor Kleiner - Playlists',
a6213a49 4480 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4481 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4482 'uploader': 'Igor Kleiner',
4483 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4484 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4485 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4486 'channel': 'Igor Kleiner',
4487 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4488 'channel_follower_count': int
a6213a49 4489 },
4490 }, {
4491 'note': 'playlists, series',
4492 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4493 'playlist_mincount': 5,
4494 'info_dict': {
4495 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4496 'title': '3Blue1Brown - Playlists',
4497 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4498 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4499 'uploader': '3Blue1Brown',
976ae3ea 4500 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4501 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4502 'channel': '3Blue1Brown',
4503 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4504 'tags': ['Mathematics'],
6c73052c 4505 'channel_follower_count': int
a6213a49 4506 },
4507 }, {
4508 'note': 'playlists, singlepage',
4509 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4510 'playlist_mincount': 4,
4511 'info_dict': {
4512 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4513 'title': 'ThirstForScience - Playlists',
4514 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4515 'uploader': 'ThirstForScience',
4516 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4517 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4518 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4519 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4520 'tags': 'count:13',
4521 'channel': 'ThirstForScience',
6c73052c 4522 'channel_follower_count': int
a6213a49 4523 }
4524 }, {
4525 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4526 'only_matching': True,
4527 }, {
4528 'note': 'basic, single video playlist',
4529 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4530 'info_dict': {
4531 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4532 'uploader': 'Sergey M.',
4533 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4534 'title': 'youtube-dl public playlist',
976ae3ea 4535 'description': '',
4536 'tags': [],
4537 'view_count': int,
4538 'modified_date': '20201130',
4539 'channel': 'Sergey M.',
4540 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4541 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4542 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4543 },
4544 'playlist_count': 1,
4545 }, {
4546 'note': 'empty playlist',
4547 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4548 'info_dict': {
4549 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4550 'uploader': 'Sergey M.',
4551 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4552 'title': 'youtube-dl empty playlist',
976ae3ea 4553 'tags': [],
4554 'channel': 'Sergey M.',
4555 'description': '',
4556 'modified_date': '20160902',
4557 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4558 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4559 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4560 },
4561 'playlist_count': 0,
4562 }, {
4563 'note': 'Home tab',
4564 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4565 'info_dict': {
4566 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4567 'title': 'lex will - Home',
4568 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4569 'uploader': 'lex will',
4570 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4571 'channel': 'lex will',
4572 'tags': ['bible', 'history', 'prophesy'],
4573 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4574 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4575 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4576 'channel_follower_count': int
a6213a49 4577 },
4578 'playlist_mincount': 2,
4579 }, {
4580 'note': 'Videos tab',
4581 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4582 'info_dict': {
4583 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4584 'title': 'lex will - Videos',
4585 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4586 'uploader': 'lex will',
4587 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4588 'tags': ['bible', 'history', 'prophesy'],
4589 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4590 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4591 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4592 'channel': 'lex will',
6c73052c 4593 'channel_follower_count': int
a6213a49 4594 },
4595 'playlist_mincount': 975,
4596 }, {
4597 'note': 'Videos tab, sorted by popular',
4598 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4599 'info_dict': {
4600 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4601 'title': 'lex will - Videos',
4602 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4603 'uploader': 'lex will',
4604 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4605 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4606 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4607 'channel': 'lex will',
4608 'tags': ['bible', 'history', 'prophesy'],
4609 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4610 'channel_follower_count': int
a6213a49 4611 },
4612 'playlist_mincount': 199,
4613 }, {
4614 'note': 'Playlists tab',
4615 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4616 'info_dict': {
4617 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4618 'title': 'lex will - Playlists',
4619 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4620 'uploader': 'lex will',
4621 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4622 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4623 'channel': 'lex will',
4624 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4625 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4626 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4627 'channel_follower_count': int
a6213a49 4628 },
4629 'playlist_mincount': 17,
4630 }, {
4631 'note': 'Community tab',
4632 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4633 'info_dict': {
4634 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4635 'title': 'lex will - Community',
4636 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4637 'uploader': 'lex will',
4638 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4639 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4640 'channel': 'lex will',
4641 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4642 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4643 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4644 'channel_follower_count': int
a6213a49 4645 },
4646 'playlist_mincount': 18,
4647 }, {
4648 'note': 'Channels tab',
4649 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4650 'info_dict': {
4651 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4652 'title': 'lex will - Channels',
4653 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4654 'uploader': 'lex will',
4655 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4656 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4657 'channel': 'lex will',
4658 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4659 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4660 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4661 'channel_follower_count': int
a6213a49 4662 },
4663 'playlist_mincount': 12,
4664 }, {
4665 'note': 'Search tab',
4666 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4667 'playlist_mincount': 40,
4668 'info_dict': {
4669 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4670 'title': '3Blue1Brown - Search - linear algebra',
4671 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4672 'uploader': '3Blue1Brown',
4673 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4674 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4675 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4676 'tags': ['Mathematics'],
4677 'channel': '3Blue1Brown',
4678 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4679 'channel_follower_count': int
a6213a49 4680 },
4681 }, {
4682 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4683 'only_matching': True,
4684 }, {
4685 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4686 'only_matching': True,
4687 }, {
4688 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4689 'only_matching': True,
4690 }, {
4691 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4692 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4693 'info_dict': {
4694 'title': '29C3: Not my department',
4695 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4696 'uploader': 'Christiaan008',
4697 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4698 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4699 'tags': [],
4700 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4701 'view_count': int,
4702 'modified_date': '20150605',
4703 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4704 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4705 'channel': 'Christiaan008',
a6213a49 4706 },
4707 'playlist_count': 96,
4708 }, {
4709 'note': 'Large playlist',
4710 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4711 'info_dict': {
4712 'title': 'Uploads from Cauchemar',
4713 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4714 'uploader': 'Cauchemar',
4715 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4716 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4717 'tags': [],
4718 'modified_date': r're:\d{8}',
4719 'channel': 'Cauchemar',
4720 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4721 'view_count': int,
4722 'description': '',
4723 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4724 },
4725 'playlist_mincount': 1123,
976ae3ea 4726 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4727 }, {
4728 'note': 'even larger playlist, 8832 videos',
4729 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4730 'only_matching': True,
4731 }, {
4732 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4733 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4734 'info_dict': {
4735 'title': 'Uploads from Interstellar Movie',
4736 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4737 'uploader': 'Interstellar Movie',
4738 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4739 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4740 'tags': [],
4741 'view_count': int,
4742 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4743 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4744 'channel': 'Interstellar Movie',
4745 'description': '',
4746 'modified_date': r're:\d{8}',
a6213a49 4747 },
4748 'playlist_mincount': 21,
4749 }, {
4750 'note': 'Playlist with "show unavailable videos" button',
4751 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4752 'info_dict': {
4753 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4754 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4755 'uploader': 'Phim Siêu Nhân Nhật Bản',
4756 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4757 'view_count': int,
4758 'channel': 'Phim Siêu Nhân Nhật Bản',
4759 'tags': [],
4760 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4761 'description': '',
4762 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4763 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4764 'modified_date': r're:\d{8}',
a6213a49 4765 },
4766 'playlist_mincount': 200,
976ae3ea 4767 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4768 }, {
4769 'note': 'Playlist with unavailable videos in page 7',
4770 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4771 'info_dict': {
4772 'title': 'Uploads from BlankTV',
4773 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4774 'uploader': 'BlankTV',
4775 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4776 'channel': 'BlankTV',
4777 'channel_url': 'https://www.youtube.com/c/blanktv',
4778 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4779 'view_count': int,
4780 'tags': [],
4781 'uploader_url': 'https://www.youtube.com/c/blanktv',
4782 'modified_date': r're:\d{8}',
4783 'description': '',
a6213a49 4784 },
4785 'playlist_mincount': 1000,
976ae3ea 4786 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4787 }, {
4788 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4789 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4790 'info_dict': {
4791 'title': 'Data Analysis with Dr Mike Pound',
4792 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4793 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4794 'uploader': 'Computerphile',
4795 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4796 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4797 'tags': [],
4798 'view_count': int,
4799 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4800 'channel_url': 'https://www.youtube.com/user/Computerphile',
4801 'channel': 'Computerphile',
a6213a49 4802 },
4803 'playlist_mincount': 11,
4804 }, {
4805 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4806 'only_matching': True,
4807 }, {
4808 'note': 'Playlist URL that does not actually serve a playlist',
4809 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4810 'info_dict': {
4811 'id': 'FqZTN594JQw',
4812 'ext': 'webm',
4813 'title': "Smiley's People 01 detective, Adventure Series, Action",
4814 'uploader': 'STREEM',
4815 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4816 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4817 'upload_date': '20150526',
4818 'license': 'Standard YouTube License',
4819 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4820 'categories': ['People & Blogs'],
4821 'tags': list,
4822 'view_count': int,
4823 'like_count': int,
a6213a49 4824 },
4825 'params': {
4826 'skip_download': True,
4827 },
4828 'skip': 'This video is not available.',
4829 'add_ie': [YoutubeIE.ie_key()],
4830 }, {
4831 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4832 'only_matching': True,
4833 }, {
4834 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4835 'only_matching': True,
4836 }, {
4837 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4838 'info_dict': {
6c73052c 4839 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4840 'ext': 'mp4',
976ae3ea 4841 'title': str,
a6213a49 4842 'uploader': 'Sky News',
4843 'uploader_id': 'skynews',
4844 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4845 'upload_date': r're:\d{8}',
976ae3ea 4846 'description': str,
a6213a49 4847 'categories': ['News & Politics'],
4848 'tags': list,
4849 'like_count': int,
6c73052c 4850 'release_timestamp': 1642502819,
976ae3ea 4851 'channel': 'Sky News',
4852 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4853 'age_limit': 0,
4854 'view_count': int,
6c73052c 4855 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4856 'playable_in_embed': True,
6c73052c 4857 'release_date': '20220118',
976ae3ea 4858 'availability': 'public',
4859 'live_status': 'is_live',
4860 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4861 'channel_follower_count': int
a6213a49 4862 },
4863 'params': {
4864 'skip_download': True,
4865 },
976ae3ea 4866 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4867 }, {
4868 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4869 'info_dict': {
4870 'id': 'a48o2S1cPoo',
4871 'ext': 'mp4',
4872 'title': 'The Young Turks - Live Main Show',
4873 'uploader': 'The Young Turks',
4874 'uploader_id': 'TheYoungTurks',
4875 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4876 'upload_date': '20150715',
4877 'license': 'Standard YouTube License',
4878 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4879 'categories': ['News & Politics'],
4880 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4881 'like_count': int,
a6213a49 4882 },
4883 'params': {
4884 'skip_download': True,
4885 },
4886 'only_matching': True,
4887 }, {
4888 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4889 'only_matching': True,
4890 }, {
4891 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4892 'only_matching': True,
4893 }, {
4894 'note': 'A channel that is not live. Should raise error',
4895 'url': 'https://www.youtube.com/user/numberphile/live',
4896 'only_matching': True,
4897 }, {
4898 'url': 'https://www.youtube.com/feed/trending',
4899 'only_matching': True,
4900 }, {
4901 'url': 'https://www.youtube.com/feed/library',
4902 'only_matching': True,
4903 }, {
4904 'url': 'https://www.youtube.com/feed/history',
4905 'only_matching': True,
4906 }, {
4907 'url': 'https://www.youtube.com/feed/subscriptions',
4908 'only_matching': True,
4909 }, {
4910 'url': 'https://www.youtube.com/feed/watch_later',
4911 'only_matching': True,
4912 }, {
4913 'note': 'Recommended - redirects to home page.',
4914 'url': 'https://www.youtube.com/feed/recommended',
4915 'only_matching': True,
4916 }, {
4917 'note': 'inline playlist with not always working continuations',
4918 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4919 'only_matching': True,
4920 }, {
4921 'url': 'https://www.youtube.com/course',
4922 'only_matching': True,
4923 }, {
4924 'url': 'https://www.youtube.com/zsecurity',
4925 'only_matching': True,
4926 }, {
4927 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4928 'only_matching': True,
4929 }, {
4930 'url': 'https://www.youtube.com/TheYoungTurks/live',
4931 'only_matching': True,
4932 }, {
4933 'url': 'https://www.youtube.com/hashtag/cctv9',
4934 'info_dict': {
4935 'id': 'cctv9',
4936 'title': '#cctv9',
976ae3ea 4937 'tags': [],
a6213a49 4938 },
4939 'playlist_mincount': 350,
4940 }, {
4941 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4942 'only_matching': True,
4943 }, {
4944 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4945 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4946 'only_matching': True
4947 }, {
4948 'note': '/browse/ should redirect to /channel/',
4949 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4950 'only_matching': True
4951 }, {
4952 'note': 'VLPL, should redirect to playlist?list=PL...',
4953 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4954 'info_dict': {
4955 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4956 'uploader': 'NoCopyrightSounds',
4957 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4958 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4959 'title': 'NCS Releases',
976ae3ea 4960 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4961 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4962 'modified_date': r're:\d{8}',
4963 'view_count': int,
4964 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4965 'tags': [],
4966 'channel': 'NoCopyrightSounds',
a6213a49 4967 },
4968 'playlist_mincount': 166,
976ae3ea 4969 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4970 }, {
4971 'note': 'Topic, should redirect to playlist?list=UU...',
4972 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4973 'info_dict': {
4974 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4975 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4976 'title': 'Uploads from Royalty Free Music - Topic',
4977 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4978 'tags': [],
4979 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4980 'channel': 'Royalty Free Music - Topic',
4981 'view_count': int,
4982 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4983 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4984 'modified_date': r're:\d{8}',
4985 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4986 'description': '',
a6213a49 4987 },
4988 'expected_warnings': [
a6213a49 4989 'The URL does not have a videos tab',
976ae3ea 4990 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4991 ],
4992 'playlist_mincount': 101,
4993 }, {
4994 'note': 'Topic without a UU playlist',
4995 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4996 'info_dict': {
4997 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4998 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4999 'tags': [],
a6213a49 5000 },
5001 'expected_warnings': [
976ae3ea 5002 'the playlist redirect gave error',
a6213a49 5003 ],
5004 'playlist_mincount': 9,
5005 }, {
5006 'note': 'Youtube music Album',
5007 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5008 'info_dict': {
5009 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5010 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5011 'tags': [],
5012 'view_count': int,
5013 'description': '',
5014 'availability': 'unlisted',
5015 'modified_date': r're:\d{8}',
a6213a49 5016 },
5017 'playlist_count': 50,
5018 }, {
5019 'note': 'unlisted single video playlist',
5020 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5021 'info_dict': {
5022 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5023 'uploader': 'colethedj',
5024 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5025 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5026 'availability': 'unlisted',
5027 'tags': [],
5028 'modified_date': '20211208',
5029 'channel': 'colethedj',
5030 'view_count': int,
5031 'description': '',
5032 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5033 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5034 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5035 },
5036 'playlist_count': 1,
5037 }, {
5038 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5039 'url': 'https://www.youtube.com/feed/recommended',
5040 'info_dict': {
5041 'id': 'recommended',
5042 'title': 'recommended',
6c73052c 5043 'tags': [],
a6213a49 5044 },
5045 'playlist_mincount': 50,
5046 'params': {
5047 'skip_download': True,
5048 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5049 },
5050 }, {
5051 'note': 'API Fallback: /videos tab, sorted by oldest first',
5052 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5053 'info_dict': {
5054 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5055 'title': 'Cody\'sLab - Videos',
5056 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5057 'uploader': 'Cody\'sLab',
5058 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5059 'channel': 'Cody\'sLab',
5060 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5061 'tags': [],
5062 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5063 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5064 'channel_follower_count': int
a6213a49 5065 },
5066 'playlist_mincount': 650,
5067 'params': {
5068 'skip_download': True,
5069 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5070 },
5071 }, {
5072 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5073 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5074 'info_dict': {
5075 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5076 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5077 'title': 'Uploads from Royalty Free Music - Topic',
5078 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5079 'modified_date': r're:\d{8}',
5080 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5081 'description': '',
5082 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5083 'tags': [],
5084 'channel': 'Royalty Free Music - Topic',
5085 'view_count': int,
5086 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5087 },
5088 'expected_warnings': [
976ae3ea 5089 'does not have a videos tab',
5090 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5091 ],
5092 'playlist_mincount': 101,
5093 'params': {
5094 'skip_download': True,
5095 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5096 },
7c219ea6 5097 }, {
5098 'note': 'non-standard redirect to regional channel',
5099 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5100 'only_matching': True
a6213a49 5101 }]
5102
5103 @classmethod
5104 def suitable(cls, url):
5105 return False if YoutubeIE.suitable(url) else super(
5106 YoutubeTabIE, cls).suitable(url)
9297939e 5107
64f36541 5108 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5109
182bda88 5110 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5111 def _real_extract(self, url, smuggled_data):
cd7c66cf 5112 item_id = self._match_id(url)
5113 url = compat_urlparse.urlunparse(
5114 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5115 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5116
fe03a6cd 5117 def get_mobj(url):
37e57a9f 5118 mobj = self._URL_RE.match(url).groupdict()
07cce701 5119 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5120 return mobj
5121
37e57a9f 5122 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5123 # Youtube returns incomplete data if tabname is not lower case
5124 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5125 if is_channel:
5126 if smuggled_data.get('is_music_url'):
37e57a9f 5127 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5128 item_id = item_id[2:]
37e57a9f 5129 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5130 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5131 mdata = self._extract_tab_endpoint(
37e57a9f 5132 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5133 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5134 get_all=False, expected_type=compat_str)
ac56cf38 5135 if not murl:
37e57a9f 5136 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5137 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5138 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5139 pre = f'https://www.youtube.com/channel/{item_id}'
5140
64f36541 5141 original_tab_name = tab
fe03a6cd 5142 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5143 # Home URLs should redirect to /videos/
37e57a9f 5144 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5145 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5146 tab = '/videos'
5147
5148 url = ''.join((pre, tab, post))
5149 mobj = get_mobj(url)
cd7c66cf 5150
5151 # Handle both video/playlist URLs
201c1459 5152 qs = parse_qs(url)
37e57a9f 5153 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5154
fe03a6cd 5155 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5156 if not playlist_id:
fe03a6cd 5157 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5158 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5159 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5160 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5161 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5162 mobj = get_mobj(url)
cd7c66cf 5163
5164 if video_id and playlist_id:
a06916d9 5165 if self.get_param('noplaylist'):
37e57a9f 5166 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5167 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5168 ie=YoutubeIE.ie_key(), video_id=video_id)
5169 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5170
ac56cf38 5171 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5172
7c219ea6 5173 # YouTube may provide a non-standard redirect to the regional channel
5174 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5175 redirect_url = traverse_obj(
5176 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5177 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5178 redirect_url = ''.join((
5179 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5180 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5181 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5182
37e57a9f 5183 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5184 if tabs:
5185 selected_tab = self._extract_selected_tab(tabs)
64f36541 5186 selected_tab_name = selected_tab.get('title', '').lower()
5187 if selected_tab_name == 'home':
5188 selected_tab_name = 'featured'
5189 requested_tab_name = mobj['tab'][1:]
09f1580e 5190 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5191 if requested_tab_name == 'live':
09f1580e 5192 # Live tab should have redirected to the video
5193 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5194 if requested_tab_name not in ('', selected_tab_name):
5195 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5196 if not original_tab_name:
5197 if item_id[:2] == 'UC':
5198 # Topic channels don't have /videos. Use the equivalent playlist instead
5199 pl_id = f'UU{item_id[2:]}'
5200 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5201 try:
5202 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5203 except ExtractorError:
5204 redirect_warning += ' and the playlist redirect gave error'
5205 else:
5206 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5207 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5208 if selected_tab_name and selected_tab_name != requested_tab_name:
5209 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5210 else:
5211 raise ExtractorError(redirect_warning, expected=True)
18db7548 5212
37e57a9f 5213 if redirect_warning:
64f36541 5214 self.to_screen(redirect_warning)
37e57a9f 5215 self.write_debug(f'Final URL: {url}')
18db7548 5216
358de58c 5217 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5218 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5219 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5220 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5221 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5222 if tabs:
ac56cf38 5223 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5224
37e57a9f 5225 playlist = traverse_obj(
5226 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5227 if playlist:
ac56cf38 5228 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5229
37e57a9f 5230 video_id = traverse_obj(
5231 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5232 if video_id:
09f1580e 5233 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5234 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5235 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5236 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5237
8bdd16b4 5238 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5239
c5e8d7af 5240
8bdd16b4 5241class YoutubePlaylistIE(InfoExtractor):
96565c7e 5242 IE_DESC = 'YouTube playlists'
8bdd16b4 5243 _VALID_URL = r'''(?x)(?:
5244 (?:https?://)?
5245 (?:\w+\.)?
5246 (?:
5247 (?:
5248 youtube(?:kids)?\.com|
d9190e44 5249 %(invidious)s
8bdd16b4 5250 )
5251 /.*?\?.*?\blist=
5252 )?
5253 (?P<id>%(playlist_id)s)
d9190e44
RH
5254 )''' % {
5255 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5256 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5257 }
8bdd16b4 5258 IE_NAME = 'youtube:playlist'
cdc628a4 5259 _TESTS = [{
8bdd16b4 5260 'note': 'issue #673',
5261 'url': 'PLBB231211A4F62143',
cdc628a4 5262 'info_dict': {
8bdd16b4 5263 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5264 'id': 'PLBB231211A4F62143',
976ae3ea 5265 'uploader': 'Wickman',
8bdd16b4 5266 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5267 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5268 'view_count': int,
5269 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5270 'modified_date': r're:\d{8}',
5271 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5272 'channel': 'Wickman',
5273 'tags': [],
5274 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5275 },
5276 'playlist_mincount': 29,
5277 }, {
5278 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5279 'info_dict': {
5280 'title': 'YDL_safe_search',
5281 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5282 },
5283 'playlist_count': 2,
5284 'skip': 'This playlist is private',
9558dcec 5285 }, {
8bdd16b4 5286 'note': 'embedded',
5287 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5288 'playlist_count': 4,
9558dcec 5289 'info_dict': {
8bdd16b4 5290 'title': 'JODA15',
5291 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5292 'uploader': 'milan',
5293 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5294 'description': '',
5295 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5296 'tags': [],
5297 'modified_date': '20140919',
5298 'view_count': int,
5299 'channel': 'milan',
5300 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5301 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5302 },
5303 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5304 }, {
8bdd16b4 5305 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5306 'playlist_mincount': 654,
8bdd16b4 5307 'info_dict': {
5308 'title': '2018 Chinese New Singles (11/6 updated)',
5309 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5310 'uploader': 'LBK',
5311 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5312 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5313 'channel': 'LBK',
5314 'view_count': int,
5315 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5316 'tags': [],
5317 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5318 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5319 'modified_date': r're:\d{8}',
5320 },
5321 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5322 }, {
29f7c58a 5323 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5324 'only_matching': True,
5325 }, {
5326 # music album playlist
5327 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5328 'only_matching': True,
5329 }]
5330
5331 @classmethod
5332 def suitable(cls, url):
201c1459 5333 if YoutubeTabIE.suitable(url):
5334 return False
49a57e70 5335 from ..utils import parse_qs
201c1459 5336 qs = parse_qs(url)
5337 if qs.get('v', [None])[0]:
5338 return False
5339 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5340
5341 def _real_extract(self, url):
5342 playlist_id = self._match_id(url)
46953e7e 5343 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5344 url = update_url_query(
5345 'https://www.youtube.com/playlist',
5346 parse_qs(url) or {'list': playlist_id})
5347 if is_music_url:
5348 url = smuggle_url(url, {'is_music_url': True})
5349 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5350
5351
5352class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5353 IE_DESC = 'youtu.be'
29f7c58a 5354 _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}
5355 _TESTS = [{
8bdd16b4 5356 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5357 'info_dict': {
5358 'id': 'yeWKywCrFtk',
5359 'ext': 'mp4',
5360 'title': 'Small Scale Baler and Braiding Rugs',
5361 'uploader': 'Backus-Page House Museum',
5362 'uploader_id': 'backuspagemuseum',
5363 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5364 'upload_date': '20161008',
5365 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5366 'categories': ['Nonprofits & Activism'],
5367 'tags': list,
5368 'like_count': int,
976ae3ea 5369 'age_limit': 0,
5370 'playable_in_embed': True,
5371 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5372 'channel': 'Backus-Page House Museum',
5373 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5374 'live_status': 'not_live',
5375 'view_count': int,
5376 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5377 'availability': 'public',
5378 'duration': 59,
8bdd16b4 5379 },
5380 'params': {
5381 'noplaylist': True,
5382 'skip_download': True,
5383 },
39e7107d 5384 }, {
8bdd16b4 5385 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5386 'only_matching': True,
cdc628a4
PH
5387 }]
5388
8bdd16b4 5389 def _real_extract(self, url):
5ad28e7f 5390 mobj = self._match_valid_url(url)
29f7c58a 5391 video_id = mobj.group('id')
5392 playlist_id = mobj.group('playlist_id')
8bdd16b4 5393 return self.url_result(
29f7c58a 5394 update_url_query('https://www.youtube.com/watch', {
5395 'v': video_id,
5396 'list': playlist_id,
5397 'feature': 'youtu.be',
5398 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5399
5400
b6ce9bb0 5401class YoutubeLivestreamEmbedIE(InfoExtractor):
5402 IE_DESC = 'YouTube livestream embeds'
5403 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5404 _TESTS = [{
5405 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5406 'only_matching': True,
5407 }]
5408
5409 def _real_extract(self, url):
5410 channel_id = self._match_id(url)
5411 return self.url_result(
5412 f'https://www.youtube.com/channel/{channel_id}/live',
5413 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5414
5415
8bdd16b4 5416class YoutubeYtUserIE(InfoExtractor):
96565c7e 5417 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5418 IE_NAME = 'youtube:user'
8bdd16b4 5419 _VALID_URL = r'ytuser:(?P<id>.+)'
5420 _TESTS = [{
5421 'url': 'ytuser:phihag',
5422 'only_matching': True,
5423 }]
5424
5425 def _real_extract(self, url):
5426 user_id = self._match_id(url)
5427 return self.url_result(
c586f9e8 5428 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5429 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5430
b05654f0 5431
3d3dddc9 5432class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5433 IE_NAME = 'youtube:favorites'
96565c7e 5434 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5435 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5436 _LOGIN_REQUIRED = True
5437 _TESTS = [{
5438 'url': ':ytfav',
5439 'only_matching': True,
5440 }, {
5441 'url': ':ytfavorites',
5442 'only_matching': True,
5443 }]
5444
5445 def _real_extract(self, url):
5446 return self.url_result(
5447 'https://www.youtube.com/playlist?list=LL',
5448 ie=YoutubeTabIE.ie_key())
5449
5450
a6213a49 5451class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5452 IE_DESC = 'YouTube search'
78caa52a 5453 IE_NAME = 'youtube:search'
b05654f0 5454 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5455 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5456 _TESTS = [{
5457 'url': 'ytsearch5:youtube-dl test video',
5458 'playlist_count': 5,
5459 'info_dict': {
5460 'id': 'youtube-dl test video',
5461 'title': 'youtube-dl test video',
5462 }
5463 }]
b05654f0 5464
a61fd4cf 5465
5f7cb91a 5466class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5467 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5468 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5469 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5470 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5471 _TESTS = [{
5472 'url': 'ytsearchdate5:youtube-dl test video',
5473 'playlist_count': 5,
5474 'info_dict': {
5475 'id': 'youtube-dl test video',
5476 'title': 'youtube-dl test video',
5477 }
5478 }]
75dff0ee 5479
c9ae7b95 5480
a6213a49 5481class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5482 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5483 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5484 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5485 _TESTS = [{
5486 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5487 'playlist_mincount': 5,
5488 'info_dict': {
11f9be09 5489 'id': 'youtube-dl test video',
3462ffa8 5490 'title': 'youtube-dl test video',
5491 }
a61fd4cf 5492 }, {
5493 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5494 'playlist_mincount': 5,
5495 'info_dict': {
5496 'id': 'python',
5497 'title': 'python',
5498 }
5499
3462ffa8 5500 }, {
5501 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5502 'only_matching': True,
5503 }]
5504
5505 def _real_extract(self, url):
4dfbf869 5506 qs = parse_qs(url)
386e1dd9 5507 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5508 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5509
5510
16aa9ea4 5511class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5512 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5513 IE_NAME = 'youtube:music:search_url'
5514 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5515 _TESTS = [{
5516 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5517 'playlist_count': 16,
5518 'info_dict': {
5519 'id': 'royalty free music',
5520 'title': 'royalty free music',
5521 }
5522 }, {
5523 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5524 'playlist_mincount': 30,
5525 'info_dict': {
5526 'id': 'royalty free music - songs',
5527 'title': 'royalty free music - songs',
5528 },
5529 'params': {'extract_flat': 'in_playlist'}
5530 }, {
5531 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5532 'playlist_mincount': 30,
5533 'info_dict': {
5534 'id': 'royalty free music - community playlists',
5535 'title': 'royalty free music - community playlists',
5536 },
5537 'params': {'extract_flat': 'in_playlist'}
5538 }]
5539
5540 _SECTIONS = {
5541 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5542 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5543 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5544 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5545 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5546 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5547 }
5548
5549 def _real_extract(self, url):
5550 qs = parse_qs(url)
5551 query = (qs.get('search_query') or qs.get('q'))[0]
5552 params = qs.get('sp', (None,))[0]
5553 if params:
5554 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5555 else:
5556 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5557 params = self._SECTIONS.get(section)
5558 if not params:
5559 section = None
5560 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5561 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5562
5563
182bda88 5564class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5565 """
25f14e9f 5566 Base class for feed extractors
3d3dddc9 5567 Subclasses must define the _FEED_NAME property.
d7ae0639 5568 """
b2e8bc1b 5569 _LOGIN_REQUIRED = True
ef2f3c7f 5570 _TESTS = []
d7ae0639
JMF
5571
5572 @property
5573 def IE_NAME(self):
78caa52a 5574 return 'youtube:%s' % self._FEED_NAME
04cc9617 5575
3853309f 5576 def _real_extract(self, url):
3d3dddc9 5577 return self.url_result(
182bda88 5578 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5579
5580
ef2f3c7f 5581class YoutubeWatchLaterIE(InfoExtractor):
5582 IE_NAME = 'youtube:watchlater'
96565c7e 5583 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5584 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5585 _TESTS = [{
8bdd16b4 5586 'url': ':ytwatchlater',
bc7a9cd8
S
5587 'only_matching': True,
5588 }]
25f14e9f
S
5589
5590 def _real_extract(self, url):
ef2f3c7f 5591 return self.url_result(
5592 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5593
5594
25f14e9f 5595class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5596 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5597 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5598 _FEED_NAME = 'recommended'
45db527f 5599 _LOGIN_REQUIRED = False
3d3dddc9 5600 _TESTS = [{
5601 'url': ':ytrec',
5602 'only_matching': True,
5603 }, {
5604 'url': ':ytrecommended',
5605 'only_matching': True,
5606 }, {
5607 'url': 'https://youtube.com',
5608 'only_matching': True,
5609 }]
1ed5b5c9 5610
1ed5b5c9 5611
25f14e9f 5612class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5613 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5614 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5615 _FEED_NAME = 'subscriptions'
3d3dddc9 5616 _TESTS = [{
5617 'url': ':ytsubs',
5618 'only_matching': True,
5619 }, {
5620 'url': ':ytsubscriptions',
5621 'only_matching': True,
5622 }]
1ed5b5c9 5623
1ed5b5c9 5624
25f14e9f 5625class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5626 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5627 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5628 _FEED_NAME = 'history'
3d3dddc9 5629 _TESTS = [{
5630 'url': ':ythistory',
5631 'only_matching': True,
5632 }]
1ed5b5c9
JMF
5633
5634
15870e90
PH
5635class YoutubeTruncatedURLIE(InfoExtractor):
5636 IE_NAME = 'youtube:truncated_url'
5637 IE_DESC = False # Do not list
975d35db 5638 _VALID_URL = r'''(?x)
b95aab84
PH
5639 (?:https?://)?
5640 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5641 (?:watch\?(?:
c4808c60 5642 feature=[a-z_]+|
b95aab84
PH
5643 annotation_id=annotation_[^&]+|
5644 x-yt-cl=[0-9]+|
c1708b89 5645 hl=[^&]*|
287be8c6 5646 t=[0-9]+
b95aab84
PH
5647 )?
5648 |
5649 attribution_link\?a=[^&]+
5650 )
5651 $
975d35db 5652 '''
15870e90 5653
c4808c60 5654 _TESTS = [{
2d3d2997 5655 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5656 'only_matching': True,
dc2fc736 5657 }, {
2d3d2997 5658 'url': 'https://www.youtube.com/watch?',
dc2fc736 5659 'only_matching': True,
b95aab84
PH
5660 }, {
5661 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5662 'only_matching': True,
5663 }, {
5664 'url': 'https://www.youtube.com/watch?feature=foo',
5665 'only_matching': True,
c1708b89
PH
5666 }, {
5667 'url': 'https://www.youtube.com/watch?hl=en-GB',
5668 'only_matching': True,
287be8c6
PH
5669 }, {
5670 'url': 'https://www.youtube.com/watch?t=2372',
5671 'only_matching': True,
c4808c60
PH
5672 }]
5673
15870e90
PH
5674 def _real_extract(self, url):
5675 raise ExtractorError(
78caa52a
PH
5676 'Did you forget to quote the URL? Remember that & is a meta '
5677 'character in most shells, so you want to put the URL in quotes, '
3867038a 5678 'like youtube-dl '
2d3d2997 5679 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5680 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5681 expected=True)
772fd5cc
PH
5682
5683
3cd786db 5684class YoutubeClipIE(InfoExtractor):
5685 IE_NAME = 'youtube:clip'
5686 IE_DESC = False # Do not list
5687 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5688
5689 def _real_extract(self, url):
5690 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5691 return self.url_result(url, 'Generic')
5692
5693
772fd5cc
PH
5694class YoutubeTruncatedIDIE(InfoExtractor):
5695 IE_NAME = 'youtube:truncated_id'
5696 IE_DESC = False # Do not list
b95aab84 5697 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5698
5699 _TESTS = [{
5700 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5701 'only_matching': True,
5702 }]
5703
5704 def _real_extract(self, url):
5705 video_id = self._match_id(url)
5706 raise ExtractorError(
5707 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5708 expected=True)