]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[docs] Minor improvements
[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')))
f0d785d3 810 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 811
052e1350 812 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 813 channel_id = traverse_obj(
814 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
815 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
816 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
817 overlay_style = traverse_obj(
818 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
819 badges = self._extract_badges(renderer)
a709d873 820 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
821
30a074c2 822 return {
39ed931e 823 '_type': 'url',
30a074c2 824 'ie_key': YoutubeIE.ie_key(),
825 'id': video_id,
5e3f2f8f 826 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 827 'title': title,
828 'description': description,
829 'duration': duration,
830 'view_count': view_count,
831 'uploader': uploader,
f3aa3c3f 832 'channel_id': channel_id,
a709d873 833 'thumbnails': thumbnails,
a30a6ed3 834 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 835 'live_status': ('is_upcoming' if scheduled_timestamp is not None
836 else 'was_live' if 'streamed' in time_text.lower()
837 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
838 else None),
839 'release_timestamp': scheduled_timestamp,
840 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 841 }
842
0c148415 843
360e1ca5 844class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 845 IE_DESC = 'YouTube'
cb7dfeea 846 _VALID_URL = r"""(?x)^
c5e8d7af 847 (
edb53e2d 848 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 849 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
850 (?:www\.)?deturl\.com/www\.youtube\.com|
851 (?:www\.)?pwnyoutube\.com|
852 (?:www\.)?hooktube\.com|
853 (?:www\.)?yourepeat\.com|
854 tube\.majestyc\.net|
855 %(invidious)s|
856 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
857 (?:.*?\#/)? # handle anchor (#/) redirect urls
858 (?: # the various things that can precede the ID:
b6ce9bb0 859 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 860 |(?: # or the v= param in all its forms
f7000f3a 861 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 862 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 863 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
864 v=
865 )
f4b05232 866 ))
cbaed4bb
S
867 |(?:
868 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
869 vid\.plus| # or vid.plus/xxxx
870 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 871 %(invidious)s
cbaed4bb 872 )/
edb53e2d 873 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 874 )
c5e8d7af 875 )? # all until now is optional -> you can pass the naked ID
201c1459 876 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 877 (?(1).+)? # if we found the ID, everything can follow
9297939e 878 (?:\#|$)""" % {
d9190e44 879 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 880 }
e40c758c 881 _PLAYER_INFO_RE = (
cc2db878 882 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
883 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 884 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 885 )
2c62dc26 886 _formats = {
c2d3cb4c 887 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
888 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
889 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
890 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
891 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
892 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
893 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
894 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 895 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 896 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
897 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
898 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
899 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
900 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
901 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 902 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 903 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
904 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 905
906
907 # 3D videos
c2d3cb4c 908 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
909 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
910 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
911 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 912 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
913 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
914 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 915
96fb5605 916 # Apple HTTP Live Streaming
11f12195 917 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 918 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
919 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
920 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
921 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
922 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 923 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
924 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
925
926 # DASH mp4 video
d23028a8
S
927 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
928 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
929 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
930 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
931 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 932 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
933 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
934 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
935 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
936 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
937 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
938 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 939
f6f1fc92 940 # Dash mp4 audio
d23028a8
S
941 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
942 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
943 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
944 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
945 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
946 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
947 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
948
949 # Dash webm
d23028a8
S
950 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
951 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
952 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
953 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
954 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
955 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
956 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
957 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
958 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
959 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
960 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
961 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
962 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
963 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
964 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 965 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
966 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
967 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
968 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
969 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
970 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
972
973 # Dash webm audio
d23028a8
S
974 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
975 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 976
0857baad 977 # Dash webm audio with opus inside
d23028a8
S
978 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
979 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
980 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 981
ce6b9a2d
PH
982 # RTMP (unnamed)
983 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
984
985 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
986 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
987 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
988 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
989 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
990 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
991 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
992 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
993 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 994 }
29f7c58a 995 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 996
fd5c4aab
S
997 _GEO_BYPASS = False
998
78caa52a 999 IE_NAME = 'youtube'
2eb88d95
PH
1000 _TESTS = [
1001 {
2d3d2997 1002 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1003 'info_dict': {
1004 'id': 'BaW_jenozKc',
1005 'ext': 'mp4',
3867038a 1006 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1007 'uploader': 'Philipp Hagemeister',
1008 'uploader_id': 'phihag',
ec85ded8 1009 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1010 'channel': 'Philipp Hagemeister',
dd4c4492
S
1011 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1012 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1013 'upload_date': '20121002',
ff9f925b 1014 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1015 'categories': ['Science & Technology'],
3867038a 1016 'tags': ['youtube-dl'],
556dbe7f 1017 'duration': 10,
dbdaaa23 1018 'view_count': int,
3e7c1224 1019 'like_count': int,
ff9f925b 1020 'availability': 'public',
1021 'playable_in_embed': True,
1022 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1023 'live_status': 'not_live',
1024 'age_limit': 0,
7c80519c 1025 'start_time': 1,
297a564b 1026 'end_time': 9,
6c73052c 1027 'channel_follower_count': int
2eb88d95 1028 }
0e853ca4 1029 },
fccd3771 1030 {
4bc3a23e
PH
1031 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1032 'note': 'Embed-only video (#1746)',
1033 'info_dict': {
1034 'id': 'yZIXLfi8CZQ',
1035 'ext': 'mp4',
1036 'upload_date': '20120608',
1037 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1038 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1039 'uploader': 'SET India',
94bfcd23 1040 'uploader_id': 'setindia',
ec85ded8 1041 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1042 'age_limit': 18,
545cc85d 1043 },
1044 'skip': 'Private video',
fccd3771 1045 },
11b56058 1046 {
8bdd16b4 1047 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1048 'note': 'Use the first video ID in the URL',
1049 'info_dict': {
1050 'id': 'BaW_jenozKc',
1051 'ext': 'mp4',
3867038a 1052 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1053 'uploader': 'Philipp Hagemeister',
1054 'uploader_id': 'phihag',
ec85ded8 1055 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1056 'channel': 'Philipp Hagemeister',
1057 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1058 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1059 'upload_date': '20121002',
976ae3ea 1060 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1061 'categories': ['Science & Technology'],
3867038a 1062 'tags': ['youtube-dl'],
556dbe7f 1063 'duration': 10,
dbdaaa23 1064 'view_count': int,
11b56058 1065 'like_count': int,
976ae3ea 1066 'availability': 'public',
1067 'playable_in_embed': True,
1068 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1069 'live_status': 'not_live',
1070 'age_limit': 0,
6c73052c 1071 'channel_follower_count': int
34a7de29
S
1072 },
1073 'params': {
1074 'skip_download': True,
1075 },
11b56058 1076 },
dd27fd17 1077 {
2d3d2997 1078 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1079 'note': '256k DASH audio (format 141) via DASH manifest',
1080 'info_dict': {
1081 'id': 'a9LDPn-MO4I',
1082 'ext': 'm4a',
1083 'upload_date': '20121002',
1084 'uploader_id': '8KVIDEO',
ec85ded8 1085 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1086 'description': '',
1087 'uploader': '8KVIDEO',
1088 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1089 },
4bc3a23e
PH
1090 'params': {
1091 'youtube_include_dash_manifest': True,
1092 'format': '141',
4919603f 1093 },
de3c7fe0 1094 'skip': 'format 141 not served anymore',
dd27fd17 1095 },
8bdd16b4 1096 # DASH manifest with encrypted signature
1097 {
1098 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1099 'info_dict': {
1100 'id': 'IB3lcPjvWLA',
1101 'ext': 'm4a',
1102 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1103 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1104 'duration': 244,
1105 'uploader': 'AfrojackVEVO',
1106 'uploader_id': 'AfrojackVEVO',
1107 'upload_date': '20131011',
cc2db878 1108 'abr': 129.495,
976ae3ea 1109 'like_count': int,
1110 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1111 'playable_in_embed': True,
1112 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1113 'view_count': int,
1114 'track': 'The Spark',
1115 'live_status': 'not_live',
1116 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1117 'channel': 'Afrojack',
1118 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1119 'tags': 'count:19',
1120 'availability': 'public',
1121 'categories': ['Music'],
1122 'age_limit': 0,
1123 'alt_title': 'The Spark',
6c73052c 1124 'channel_follower_count': int
8bdd16b4 1125 },
1126 'params': {
1127 'youtube_include_dash_manifest': True,
1128 'format': '141/bestaudio[ext=m4a]',
1129 },
1130 },
65c2fde2 1131 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1132 {
65c2fde2 1133 'note': 'Embed allowed age-gate video',
2d3d2997 1134 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1135 'info_dict': {
1136 'id': 'HtVdAasjOgU',
1137 'ext': 'mp4',
1138 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1139 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1140 'duration': 142,
c522adb1
JMF
1141 'uploader': 'The Witcher',
1142 'uploader_id': 'WitcherGame',
ec85ded8 1143 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1144 'upload_date': '20140605',
34952f09 1145 'age_limit': 18,
976ae3ea 1146 'categories': ['Gaming'],
1147 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1148 'availability': 'needs_auth',
1149 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1150 'like_count': int,
1151 'channel': 'The Witcher',
1152 'live_status': 'not_live',
1153 'tags': 'count:17',
1154 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1155 'playable_in_embed': True,
1156 'view_count': int,
6c73052c 1157 'channel_follower_count': int
c522adb1
JMF
1158 },
1159 },
65c2fde2 1160 {
1161 'note': 'Age-gate video with embed allowed in public site',
1162 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1163 'info_dict': {
1164 'id': 'HsUATh_Nc2U',
1165 'ext': 'mp4',
1166 'title': 'Godzilla 2 (Official Video)',
1167 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1168 'upload_date': '20200408',
1169 'uploader_id': 'FlyingKitty900',
1170 'uploader': 'FlyingKitty',
1171 'age_limit': 18,
976ae3ea 1172 'availability': 'needs_auth',
1173 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1174 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1175 'channel': 'FlyingKitty',
1176 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1177 'view_count': int,
1178 'categories': ['Entertainment'],
1179 'live_status': 'not_live',
1180 'tags': ['Flyingkitty', 'godzilla 2'],
1181 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1182 'like_count': int,
1183 'duration': 177,
1184 'playable_in_embed': True,
6c73052c 1185 'channel_follower_count': int
65c2fde2 1186 },
1187 },
1188 {
1189 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1190 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1191 'info_dict': {
1192 'id': 'Tq92D6wQ1mg',
1193 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1194 'ext': 'mp4',
17322130 1195 'upload_date': '20191228',
65c2fde2 1196 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1197 'uploader': 'Projekt Melody',
1198 'description': 'md5:17eccca93a786d51bc67646756894066',
1199 'age_limit': 18,
976ae3ea 1200 'like_count': int,
1201 'availability': 'needs_auth',
1202 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1203 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1204 'view_count': int,
1205 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1206 'channel': 'Projekt Melody',
1207 'live_status': 'not_live',
1208 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1209 'playable_in_embed': True,
1210 'categories': ['Entertainment'],
1211 'duration': 106,
1212 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1213 'channel_follower_count': int
65c2fde2 1214 },
1215 },
1216 {
1217 'note': 'Non-Agegated non-embeddable video',
1218 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1219 'info_dict': {
1220 'id': 'MeJVWBSsPAY',
1221 'ext': 'mp4',
1222 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1223 'uploader': 'Herr Lurik',
1224 'uploader_id': 'st3in234',
1225 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1226 'upload_date': '20130730',
976ae3ea 1227 'track': 'Such mich find mich',
1228 'age_limit': 0,
1229 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1230 'like_count': int,
1231 'playable_in_embed': False,
1232 'creator': 'OOMPH!',
1233 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1234 'view_count': int,
1235 'alt_title': 'Such mich find mich',
1236 'duration': 210,
1237 'channel': 'Herr Lurik',
1238 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1239 'categories': ['Music'],
1240 'availability': 'public',
1241 'uploader_url': 'http://www.youtube.com/user/st3in234',
1242 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1243 'live_status': 'not_live',
1244 'artist': 'OOMPH!',
6c73052c 1245 'channel_follower_count': int
65c2fde2 1246 },
1247 },
1248 {
1249 'note': 'Non-bypassable age-gated video',
1250 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1251 'only_matching': True,
1252 },
8bdd16b4 1253 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1254 # YouTube Red ad is not captured for creator
1255 {
1256 'url': '__2ABJjxzNo',
1257 'info_dict': {
1258 'id': '__2ABJjxzNo',
1259 'ext': 'mp4',
1260 'duration': 266,
1261 'upload_date': '20100430',
1262 'uploader_id': 'deadmau5',
1263 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1264 'creator': 'deadmau5',
1265 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1266 'uploader': 'deadmau5',
1267 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1268 'alt_title': 'Some Chords',
976ae3ea 1269 'availability': 'public',
1270 'tags': 'count:14',
1271 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1272 'view_count': int,
1273 'live_status': 'not_live',
1274 'channel': 'deadmau5',
1275 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1276 'like_count': int,
1277 'track': 'Some Chords',
1278 'artist': 'deadmau5',
1279 'playable_in_embed': True,
1280 'age_limit': 0,
1281 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1282 'categories': ['Music'],
1283 'album': 'Some Chords',
6c73052c 1284 'channel_follower_count': int
8bdd16b4 1285 },
1286 'expected_warnings': [
1287 'DASH manifest missing',
1288 ]
1289 },
067aa17e 1290 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1291 {
1292 'url': 'lqQg6PlCWgI',
1293 'info_dict': {
1294 'id': 'lqQg6PlCWgI',
1295 'ext': 'mp4',
556dbe7f 1296 'duration': 6085,
90227264 1297 'upload_date': '20150827',
cbe2bd91 1298 'uploader_id': 'olympic',
ec85ded8 1299 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1300 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1301 'uploader': 'Olympics',
cbe2bd91 1302 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1303 'like_count': int,
1304 'release_timestamp': 1343767800,
1305 'playable_in_embed': True,
1306 'categories': ['Sports'],
1307 'release_date': '20120731',
1308 'channel': 'Olympics',
1309 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1310 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1311 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1312 'age_limit': 0,
1313 'availability': 'public',
1314 'live_status': 'was_live',
1315 'view_count': int,
1316 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1317 'channel_follower_count': int
cbe2bd91
PH
1318 },
1319 'params': {
1320 'skip_download': 'requires avconv',
e52a40ab 1321 }
cbe2bd91 1322 },
6271f1ca
PH
1323 # Non-square pixels
1324 {
1325 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1326 'info_dict': {
1327 'id': '_b-2C3KPAM0',
1328 'ext': 'mp4',
1329 'stretched_ratio': 16 / 9.,
556dbe7f 1330 'duration': 85,
6271f1ca
PH
1331 'upload_date': '20110310',
1332 'uploader_id': 'AllenMeow',
ec85ded8 1333 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1334 '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 1335 'uploader': '孫ᄋᄅ',
6271f1ca 1336 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1337 'playable_in_embed': True,
1338 'channel': '孫ᄋᄅ',
1339 'age_limit': 0,
1340 'tags': 'count:11',
1341 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1342 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1343 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1344 'view_count': int,
1345 'categories': ['People & Blogs'],
1346 'like_count': int,
1347 'live_status': 'not_live',
1348 'availability': 'unlisted',
6c73052c 1349 'channel_follower_count': int
6271f1ca 1350 },
06b491eb
S
1351 },
1352 # url_encoded_fmt_stream_map is empty string
1353 {
1354 'url': 'qEJwOuvDf7I',
1355 'info_dict': {
1356 'id': 'qEJwOuvDf7I',
f57b7835 1357 'ext': 'webm',
06b491eb
S
1358 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1359 'description': '',
1360 'upload_date': '20150404',
1361 'uploader_id': 'spbelect',
1362 'uploader': 'Наблюдатели Петербурга',
1363 },
1364 'params': {
1365 'skip_download': 'requires avconv',
e323cf3f
S
1366 },
1367 'skip': 'This live event has ended.',
06b491eb 1368 },
067aa17e 1369 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1370 {
1371 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1372 'info_dict': {
1373 'id': 'FIl7x6_3R5Y',
eb6793ba 1374 'ext': 'webm',
da77d856
S
1375 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1376 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1377 'duration': 220,
da77d856
S
1378 'upload_date': '20150625',
1379 'uploader_id': 'dorappi2000',
ec85ded8 1380 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1381 'uploader': 'dorappi2000',
eb6793ba 1382 'formats': 'mincount:31',
da77d856 1383 },
eb6793ba 1384 'skip': 'not actual anymore',
2ee8f5d8 1385 },
8a1a26ce
YCH
1386 # DASH manifest with segment_list
1387 {
1388 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1389 'md5': '8ce563a1d667b599d21064e982ab9e31',
1390 'info_dict': {
1391 'id': 'CsmdDsKjzN8',
1392 'ext': 'mp4',
17ee98e1 1393 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1394 'uploader': 'Airtek',
1395 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1396 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1397 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1398 },
1399 'params': {
1400 'youtube_include_dash_manifest': True,
1401 'format': '135', # bestvideo
be49068d
S
1402 },
1403 'skip': 'This live event has ended.',
2ee8f5d8 1404 },
cf7e015f
S
1405 {
1406 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1407 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1408 'info_dict': {
545cc85d 1409 'id': 'jvGDaLqkpTg',
1410 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1411 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1412 },
1413 'playlist': [{
1414 'info_dict': {
545cc85d 1415 'id': 'jvGDaLqkpTg',
cf7e015f 1416 'ext': 'mp4',
545cc85d 1417 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1418 'description': 'md5:e03b909557865076822aa169218d6a5d',
1419 'duration': 10643,
1420 'upload_date': '20161111',
1421 'uploader': 'Team PGP',
1422 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1423 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1424 },
1425 }, {
1426 'info_dict': {
545cc85d 1427 'id': '3AKt1R1aDnw',
cf7e015f 1428 'ext': 'mp4',
545cc85d 1429 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1430 'description': 'md5:e03b909557865076822aa169218d6a5d',
1431 'duration': 10991,
1432 'upload_date': '20161111',
1433 'uploader': 'Team PGP',
1434 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1435 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1436 },
1437 }, {
1438 'info_dict': {
545cc85d 1439 'id': 'RtAMM00gpVc',
cf7e015f 1440 'ext': 'mp4',
545cc85d 1441 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1442 'description': 'md5:e03b909557865076822aa169218d6a5d',
1443 'duration': 10995,
1444 'upload_date': '20161111',
1445 'uploader': 'Team PGP',
1446 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1447 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1448 },
1449 }, {
1450 'info_dict': {
545cc85d 1451 'id': '6N2fdlP3C5U',
cf7e015f 1452 'ext': 'mp4',
545cc85d 1453 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1454 'description': 'md5:e03b909557865076822aa169218d6a5d',
1455 'duration': 10990,
1456 'upload_date': '20161111',
1457 'uploader': 'Team PGP',
1458 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1460 },
1461 }],
1462 'params': {
1463 'skip_download': True,
1464 },
65c2fde2 1465 'skip': 'Not multifeed anymore',
cbaed4bb 1466 },
f9f49d87 1467 {
067aa17e 1468 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1469 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1470 'info_dict': {
1471 'id': 'gVfLd0zydlo',
1472 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1473 },
1474 'playlist_count': 2,
be49068d 1475 'skip': 'Not multifeed anymore',
f9f49d87 1476 },
cbaed4bb 1477 {
2d3d2997 1478 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1479 'only_matching': True,
0e49d9a6 1480 },
6d4fc66b 1481 {
2d3d2997 1482 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1483 'only_matching': True,
1484 },
0e49d9a6 1485 {
067aa17e 1486 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1487 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1488 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1489 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1490 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1491 'info_dict': {
1492 'id': 'lsguqyKfVQg',
1493 'ext': 'mp4',
1494 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1495 'alt_title': 'Dark Walk',
0e49d9a6 1496 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1497 'duration': 133,
0e49d9a6
LL
1498 'upload_date': '20151119',
1499 'uploader_id': 'IronSoulElf',
ec85ded8 1500 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1501 'uploader': 'IronSoulElf',
11f9be09 1502 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1503 'track': 'Dark Walk',
1504 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1505 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1506 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1507 'categories': ['Film & Animation'],
1508 'view_count': int,
1509 'live_status': 'not_live',
1510 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1511 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1512 'tags': 'count:13',
1513 'availability': 'public',
1514 'channel': 'IronSoulElf',
1515 'playable_in_embed': True,
1516 'like_count': int,
1517 'age_limit': 0,
6c73052c 1518 'channel_follower_count': int
0e49d9a6
LL
1519 },
1520 'params': {
1521 'skip_download': True,
1522 },
1523 },
61f92af1 1524 {
067aa17e 1525 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1526 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1527 'only_matching': True,
1528 },
313dfc45
LL
1529 {
1530 # Video with yt:stretch=17:0
1531 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1532 'info_dict': {
1533 'id': 'Q39EVAstoRM',
1534 'ext': 'mp4',
1535 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1536 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1537 'upload_date': '20151107',
1538 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1539 'uploader': 'CH GAMER DROID',
1540 },
1541 'params': {
1542 'skip_download': True,
1543 },
be49068d 1544 'skip': 'This video does not exist.',
313dfc45 1545 },
201c1459 1546 {
1547 # Video with incomplete 'yt:stretch=16:'
1548 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1549 'only_matching': True,
1550 },
7caf9830
S
1551 {
1552 # Video licensed under Creative Commons
1553 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1554 'info_dict': {
1555 'id': 'M4gD1WSo5mA',
1556 'ext': 'mp4',
1557 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1558 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1559 'duration': 721,
17322130 1560 'upload_date': '20150128',
7caf9830 1561 'uploader_id': 'BerkmanCenter',
ec85ded8 1562 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1563 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1564 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1565 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1566 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1567 'like_count': int,
1568 'age_limit': 0,
1569 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1570 'channel': 'The Berkman Klein Center for Internet & Society',
1571 'availability': 'public',
1572 'view_count': int,
1573 'categories': ['Education'],
1574 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1575 'live_status': 'not_live',
1576 'playable_in_embed': True,
6c73052c 1577 'channel_follower_count': int
7caf9830
S
1578 },
1579 'params': {
1580 'skip_download': True,
1581 },
1582 },
fd050249
S
1583 {
1584 # Channel-like uploader_url
1585 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1586 'info_dict': {
1587 'id': 'eQcmzGIKrzg',
1588 'ext': 'mp4',
1589 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1590 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1591 'duration': 4060,
17322130 1592 'upload_date': '20151120',
eb6793ba 1593 'uploader': 'Bernie Sanders',
fd050249 1594 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1595 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1596 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1597 'playable_in_embed': True,
1598 'tags': 'count:12',
1599 'like_count': int,
1600 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1601 'age_limit': 0,
1602 'availability': 'public',
1603 'categories': ['News & Politics'],
1604 'channel': 'Bernie Sanders',
1605 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1606 'view_count': int,
1607 'live_status': 'not_live',
1608 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1609 'channel_follower_count': int
fd050249
S
1610 },
1611 'params': {
1612 'skip_download': True,
1613 },
1614 },
040ac686
S
1615 {
1616 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1617 'only_matching': True,
7f29cf54
S
1618 },
1619 {
067aa17e 1620 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1621 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1622 'only_matching': True,
6496ccb4
S
1623 },
1624 {
1625 # Rental video preview
1626 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1627 'info_dict': {
1628 'id': 'uGpuVWrhIzE',
1629 'ext': 'mp4',
1630 'title': 'Piku - Trailer',
1631 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1632 'upload_date': '20150811',
1633 'uploader': 'FlixMatrix',
1634 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1635 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1636 'license': 'Standard YouTube License',
1637 },
1638 'params': {
1639 'skip_download': True,
1640 },
eb6793ba 1641 'skip': 'This video is not available.',
022a5d66 1642 },
12afdc2a
S
1643 {
1644 # YouTube Red video with episode data
1645 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1646 'info_dict': {
1647 'id': 'iqKdEhx-dD4',
1648 'ext': 'mp4',
1649 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1650 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1651 'duration': 2085,
12afdc2a
S
1652 'upload_date': '20170118',
1653 'uploader': 'Vsauce',
1654 'uploader_id': 'Vsauce',
1655 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1656 'series': 'Mind Field',
1657 'season_number': 1,
1658 'episode_number': 1,
976ae3ea 1659 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1660 'tags': 'count:12',
1661 'view_count': int,
1662 'availability': 'public',
1663 'age_limit': 0,
1664 'channel': 'Vsauce',
1665 'episode': 'Episode 1',
1666 'categories': ['Entertainment'],
1667 'season': 'Season 1',
1668 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1669 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1670 'like_count': int,
1671 'playable_in_embed': True,
1672 'live_status': 'not_live',
6c73052c 1673 'channel_follower_count': int
12afdc2a
S
1674 },
1675 'params': {
1676 'skip_download': True,
1677 },
1678 'expected_warnings': [
1679 'Skipping DASH manifest',
1680 ],
1681 },
c7121fa7
S
1682 {
1683 # The following content has been identified by the YouTube community
1684 # as inappropriate or offensive to some audiences.
1685 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1686 'info_dict': {
1687 'id': '6SJNVb0GnPI',
1688 'ext': 'mp4',
1689 'title': 'Race Differences in Intelligence',
1690 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1691 'duration': 965,
1692 'upload_date': '20140124',
1693 'uploader': 'New Century Foundation',
1694 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1695 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1696 },
1697 'params': {
1698 'skip_download': True,
1699 },
545cc85d 1700 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1701 },
022a5d66
S
1702 {
1703 # itag 212
1704 'url': '1t24XAntNCY',
1705 'only_matching': True,
fd5c4aab
S
1706 },
1707 {
1708 # geo restricted to JP
1709 'url': 'sJL6WA-aGkQ',
1710 'only_matching': True,
1711 },
cd5a74a2
S
1712 {
1713 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1714 'only_matching': True,
1715 },
bc2ca1bb 1716 {
1717 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1718 'only_matching': True,
1719 },
1720 {
1721 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1722 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1723 'only_matching': True,
1724 },
825cd268
RA
1725 {
1726 # DRM protected
1727 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1728 'only_matching': True,
4fe54c12
S
1729 },
1730 {
1731 # Video with unsupported adaptive stream type formats
1732 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1733 'info_dict': {
1734 'id': 'Z4Vy8R84T1U',
1735 'ext': 'mp4',
1736 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1737 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1738 'duration': 433,
1739 'upload_date': '20130923',
1740 'uploader': 'Amelia Putri Harwita',
1741 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1742 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1743 'formats': 'maxcount:10',
1744 },
1745 'params': {
1746 'skip_download': True,
1747 'youtube_include_dash_manifest': False,
1748 },
5429d6a9 1749 'skip': 'not actual anymore',
5caabd3c 1750 },
1751 {
822b9d9c 1752 # Youtube Music Auto-generated description
5caabd3c 1753 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1754 'info_dict': {
1755 'id': 'MgNrAu2pzNs',
1756 'ext': 'mp4',
1757 'title': 'Voyeur Girl',
1758 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1759 'upload_date': '20190312',
5429d6a9
S
1760 'uploader': 'Stephen - Topic',
1761 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1762 'artist': 'Stephen',
1763 'track': 'Voyeur Girl',
1764 'album': 'it\'s too much love to know my dear',
1765 'release_date': '20190313',
1766 'release_year': 2019,
976ae3ea 1767 'alt_title': 'Voyeur Girl',
1768 'view_count': int,
1769 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1770 'playable_in_embed': True,
1771 'like_count': int,
1772 'categories': ['Music'],
1773 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1774 'channel': 'Stephen',
1775 'availability': 'public',
1776 'creator': 'Stephen',
1777 'duration': 169,
1778 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1779 'age_limit': 0,
1780 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1781 'tags': 'count:11',
1782 'live_status': 'not_live',
6c73052c 1783 'channel_follower_count': int
5caabd3c 1784 },
1785 'params': {
1786 'skip_download': True,
1787 },
1788 },
66b48727
RA
1789 {
1790 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1791 'only_matching': True,
1792 },
011e75e6
S
1793 {
1794 # invalid -> valid video id redirection
1795 'url': 'DJztXj2GPfl',
1796 'info_dict': {
1797 'id': 'DJztXj2GPfk',
1798 'ext': 'mp4',
1799 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1800 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1801 'upload_date': '20090125',
1802 'uploader': 'Prochorowka',
1803 'uploader_id': 'Prochorowka',
1804 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1805 'artist': 'Panjabi MC',
1806 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1807 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1808 },
1809 'params': {
1810 'skip_download': True,
1811 },
545cc85d 1812 'skip': 'Video unavailable',
ea74e00b
DP
1813 },
1814 {
1815 # empty description results in an empty string
1816 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1817 'info_dict': {
1818 'id': 'x41yOUIvK2k',
1819 'ext': 'mp4',
1820 'title': 'IMG 3456',
1821 'description': '',
1822 'upload_date': '20170613',
1823 'uploader_id': 'ElevageOrVert',
1824 'uploader': 'ElevageOrVert',
976ae3ea 1825 'view_count': int,
1826 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1827 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1828 'like_count': int,
1829 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1830 'tags': [],
1831 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1832 'availability': 'public',
1833 'age_limit': 0,
1834 'categories': ['Pets & Animals'],
1835 'duration': 7,
1836 'playable_in_embed': True,
1837 'live_status': 'not_live',
1838 'channel': 'ElevageOrVert',
6c73052c 1839 'channel_follower_count': int
ea74e00b
DP
1840 },
1841 'params': {
1842 'skip_download': True,
1843 },
1844 },
a0566bbf 1845 {
29f7c58a 1846 # with '};' inside yt initial data (see [1])
1847 # see [2] for an example with '};' inside ytInitialPlayerResponse
1848 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1849 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1850 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1851 'info_dict': {
1852 'id': 'CHqg6qOn4no',
1853 'ext': 'mp4',
1854 'title': 'Part 77 Sort a list of simple types in c#',
1855 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1856 'upload_date': '20130831',
1857 'uploader_id': 'kudvenkat',
1858 'uploader': 'kudvenkat',
976ae3ea 1859 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1860 'like_count': int,
1861 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1862 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1863 'live_status': 'not_live',
1864 'categories': ['Education'],
1865 'availability': 'public',
1866 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1867 'tags': 'count:12',
1868 'playable_in_embed': True,
1869 'age_limit': 0,
1870 'view_count': int,
1871 'duration': 522,
1872 'channel': 'kudvenkat',
6c73052c 1873 'channel_follower_count': int
a0566bbf 1874 },
1875 'params': {
1876 'skip_download': True,
1877 },
1878 },
29f7c58a 1879 {
1880 # another example of '};' in ytInitialData
1881 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1882 'only_matching': True,
1883 },
1884 {
1885 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1886 'only_matching': True,
1887 },
545cc85d 1888 {
cc2db878 1889 # https://github.com/ytdl-org/youtube-dl/pull/28094
1890 'url': 'OtqTfy26tG0',
1891 'info_dict': {
1892 'id': 'OtqTfy26tG0',
1893 'ext': 'mp4',
1894 'title': 'Burn Out',
1895 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1896 'upload_date': '20141120',
1897 'uploader': 'The Cinematic Orchestra - Topic',
1898 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1899 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1900 'artist': 'The Cinematic Orchestra',
1901 'track': 'Burn Out',
1902 'album': 'Every Day',
976ae3ea 1903 'like_count': int,
1904 'live_status': 'not_live',
1905 'alt_title': 'Burn Out',
1906 'duration': 614,
1907 'age_limit': 0,
1908 'view_count': int,
1909 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1910 'creator': 'The Cinematic Orchestra',
1911 'channel': 'The Cinematic Orchestra',
1912 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1913 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1914 'availability': 'public',
1915 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1916 'categories': ['Music'],
1917 'playable_in_embed': True,
6c73052c 1918 'channel_follower_count': int
cc2db878 1919 },
1920 'params': {
1921 'skip_download': True,
1922 },
545cc85d 1923 },
bc2ca1bb 1924 {
1925 # controversial video, only works with bpctr when authenticated with cookies
1926 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1927 'only_matching': True,
1928 },
a1a7907b 1929 {
1930 # controversial video, requires bpctr/contentCheckOk
1931 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1932 'info_dict': {
1933 'id': 'SZJvDhaSDnc',
1934 'ext': 'mp4',
1935 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1936 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1937 'uploader': 'CBS Mornings',
11f9be09 1938 'uploader_id': 'CBSThisMorning',
a1a7907b 1939 'upload_date': '20140716',
976ae3ea 1940 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1941 'duration': 170,
1942 'categories': ['News & Politics'],
1943 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1944 'view_count': int,
1945 'channel': 'CBS Mornings',
1946 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1947 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1948 'age_limit': 18,
1949 'availability': 'needs_auth',
1950 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1951 'like_count': int,
1952 'live_status': 'not_live',
1953 'playable_in_embed': True,
6c73052c 1954 'channel_follower_count': int
a1a7907b 1955 }
1956 },
f7ad7160 1957 {
1958 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1959 'url': 'cBvYw8_A0vQ',
1960 'info_dict': {
1961 'id': 'cBvYw8_A0vQ',
1962 'ext': 'mp4',
1963 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1964 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1965 'upload_date': '20201120',
1966 'uploader': 'Walk around Japan',
1967 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1968 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1969 'duration': 1456,
1970 'categories': ['Travel & Events'],
1971 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1972 'view_count': int,
1973 'channel': 'Walk around Japan',
1974 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1975 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1976 'age_limit': 0,
1977 'availability': 'public',
1978 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1979 'live_status': 'not_live',
1980 'playable_in_embed': True,
6c73052c 1981 'channel_follower_count': int
f7ad7160 1982 },
1983 'params': {
1984 'skip_download': True,
1985 },
0fb983f6 1986 }, {
1987 # Has multiple audio streams
1988 'url': 'WaOKSUlf4TM',
1989 'only_matching': True
9297939e 1990 }, {
1991 # Requires Premium: has format 141 when requested using YTM url
1992 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1993 'only_matching': True
1994 }, {
120916da 1995 # multiple subtitles with same lang_code
1996 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1997 'only_matching': True,
109dd3b2 1998 }, {
1999 # Force use android client fallback
2000 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2001 'info_dict': {
2002 'id': 'YOelRv7fMxY',
11f9be09 2003 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2004 'ext': '3gp',
2005 'upload_date': '20210624',
2006 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2007 'uploader': 'colinfurze',
11f9be09 2008 'uploader_id': 'colinfurze',
109dd3b2 2009 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2010 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2011 'duration': 596,
2012 'categories': ['Entertainment'],
2013 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2014 'view_count': int,
2015 'channel': 'colinfurze',
2016 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2017 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2018 'age_limit': 0,
2019 'availability': 'public',
2020 'like_count': int,
2021 'live_status': 'not_live',
2022 'playable_in_embed': True,
6c73052c 2023 'channel_follower_count': int
109dd3b2 2024 },
2025 'params': {
2026 'format': '17', # 3gp format available on android
2027 'extractor_args': {'youtube': {'player_client': ['android']}},
2028 },
120916da 2029 },
109dd3b2 2030 {
2031 # Skip download of additional client configs (remix client config in this case)
2032 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2033 'only_matching': True,
2034 'params': {
2035 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2036 },
8fc54b12 2037 }, {
2038 # shorts
2039 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2040 'only_matching': True,
9222c381 2041 }, {
2042 'note': 'Storyboards',
2043 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2044 'info_dict': {
2045 'id': '5KLPxDtMqe8',
2046 'ext': 'mhtml',
2047 'format_id': 'sb0',
2048 'title': 'Your Brain is Plastic',
2049 'uploader_id': 'scishow',
2050 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2051 'upload_date': '20140324',
2052 'uploader': 'SciShow',
976ae3ea 2053 'like_count': int,
2054 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2055 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2056 'view_count': int,
2057 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2058 'playable_in_embed': True,
2059 'tags': 'count:12',
2060 'uploader_url': 'http://www.youtube.com/user/scishow',
2061 'availability': 'public',
2062 'channel': 'SciShow',
2063 'live_status': 'not_live',
2064 'duration': 248,
2065 'categories': ['Education'],
2066 'age_limit': 0,
6c73052c 2067 'channel_follower_count': int
9222c381 2068 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2069 }, {
2070 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2071 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2072 'info_dict': {
2073 'id': '2NUZ8W2llS4',
2074 'ext': 'mp4',
2075 'title': 'The NP that test your phone performance 🙂',
2076 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2077 'uploader': 'Leon Nguyen',
2078 'uploader_id': 'VNSXIII',
2079 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2080 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2081 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2082 'duration': 21,
2083 'view_count': int,
2084 'age_limit': 0,
2085 'categories': ['Gaming'],
2086 'tags': 'count:23',
2087 'playable_in_embed': True,
2088 'live_status': 'not_live',
2089 'upload_date': '20220103',
2090 'like_count': int,
2091 'availability': 'public',
2092 'channel': 'Leon Nguyen',
2093 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2094 'channel_follower_count': int
2095 }
2096 }, {
2097 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2098 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2099 'info_dict': {
2100 'id': 'mzZzzBU6lrM',
2101 'ext': 'mp4',
2102 'title': 'I Met GeorgeNotFound In Real Life...',
2103 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2104 'uploader': 'Quackity',
2105 'uploader_id': 'QuackityHQ',
2106 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2107 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2108 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2109 'duration': 955,
2110 'view_count': int,
2111 'age_limit': 0,
2112 'categories': ['Entertainment'],
2113 'tags': 'count:26',
2114 'playable_in_embed': True,
2115 'live_status': 'not_live',
2116 'release_timestamp': 1641172509,
2117 'release_date': '20220103',
2118 'upload_date': '20220103',
2119 'like_count': int,
2120 'availability': 'public',
2121 'channel': 'Quackity',
2122 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2123 'channel_follower_count': int
2124 }
2125 },
2126 { # continuous livestream. Microformat upload date should be preferred.
2127 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2128 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2129 'info_dict': {
2130 'id': 'kgx4WGK0oNU',
2131 '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}',
2132 'ext': 'mp4',
2133 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2134 'availability': 'public',
2135 'age_limit': 0,
2136 'release_timestamp': 1637975704,
2137 'upload_date': '20210619',
2138 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2139 'live_status': 'is_live',
2140 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2141 'uploader': '阿鲍Abao',
2142 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2143 'channel': 'Abao in Tokyo',
2144 'channel_follower_count': int,
2145 'release_date': '20211127',
2146 'tags': 'count:39',
2147 'categories': ['People & Blogs'],
2148 'like_count': int,
2149 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2150 'view_count': int,
2151 'playable_in_embed': True,
2152 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2153 },
2154 'params': {'skip_download': True}
2155 },
2eb88d95
PH
2156 ]
2157
201c1459 2158 @classmethod
2159 def suitable(cls, url):
4dfbf869 2160 from ..utils import parse_qs
2161
201c1459 2162 qs = parse_qs(url)
2163 if qs.get('list', [None])[0]:
2164 return False
2165 return super(YoutubeIE, cls).suitable(url)
2166
e0df6211
PH
2167 def __init__(self, *args, **kwargs):
2168 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2169 self._code_cache = {}
83799698 2170 self._player_cache = {}
e0df6211 2171
adbc4ec4 2172 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2173 lock = threading.Lock()
2174
2175 is_live = True
185bf310 2176 start_time = time.time()
adbc4ec4
THD
2177 formats = [f for f in formats if f.get('is_from_start')]
2178
185bf310 2179 def refetch_manifest(format_id, delay):
2180 nonlocal formats, start_time, is_live
2181 if time.time() <= start_time + delay:
adbc4ec4
THD
2182 return
2183
2184 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2185 video_details = traverse_obj(
2186 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2187 microformats = traverse_obj(
2188 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2189 expected_type=dict, default=[])
2190 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2191 start_time = time.time()
adbc4ec4 2192
185bf310 2193 def mpd_feed(format_id, delay):
adbc4ec4
THD
2194 """
2195 @returns (manifest_url, manifest_stream_number, is_live) or None
2196 """
2197 with lock:
185bf310 2198 refetch_manifest(format_id, delay)
adbc4ec4
THD
2199
2200 f = next((f for f in formats if f['format_id'] == format_id), None)
2201 if not f:
185bf310 2202 if not is_live:
2203 self.to_screen(f'{video_id}: Video is no longer live')
2204 else:
2205 self.report_warning(
2206 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2207 return None
2208 return f['manifest_url'], f['manifest_stream_number'], is_live
2209
2210 for f in formats:
a539f065 2211 f['is_live'] = True
adbc4ec4
THD
2212 f['protocol'] = 'http_dash_segments_generator'
2213 f['fragments'] = functools.partial(
2214 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2215
2216 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2217 FETCH_SPAN, MAX_DURATION = 5, 432000
2218
2219 mpd_url, stream_number, is_live = None, None, True
2220
2221 begin_index = 0
2222 download_start_time = ctx.get('start') or time.time()
2223
2224 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2225 if lack_early_segments:
2226 self.report_warning(bug_reports_message(
2227 'Starting download from the last 120 hours of the live stream since '
2228 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2229 lack_early_segments = True
2230
2231 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2232 fragments, fragment_base_url = None, None
2233
a539f065 2234 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2235 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2236 # Obtain from MPD's maximum seq value
2237 old_mpd_url = mpd_url
185bf310 2238 last_error = ctx.pop('last_error', None)
a539f065 2239 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2240 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2241 or (mpd_url, stream_number, False))
2242 if not refresh_sequence:
2243 if expire_fast and not is_live:
2244 return False, last_seq
2245 elif old_mpd_url == mpd_url:
2246 return True, last_seq
adbc4ec4
THD
2247 try:
2248 fmts, _ = self._extract_mpd_formats_and_subtitles(
2249 mpd_url, None, note=False, errnote=False, fatal=False)
2250 except ExtractorError:
2251 fmts = None
2252 if not fmts:
a539f065 2253 no_fragment_score += 2
adbc4ec4
THD
2254 return False, last_seq
2255 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2256 fragments = fmt_info['fragments']
2257 fragment_base_url = fmt_info['fragment_base_url']
2258 assert fragment_base_url
2259
2260 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2261 return True, _last_seq
2262
2263 while is_live:
2264 fetch_time = time.time()
2265 if no_fragment_score > 30:
2266 return
2267 if last_segment_url:
2268 # Obtain from "X-Head-Seqnum" header value from each segment
2269 try:
2270 urlh = self._request_webpage(
2271 last_segment_url, None, note=False, errnote=False, fatal=False)
2272 except ExtractorError:
2273 urlh = None
2274 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2275 if last_seq is None:
a539f065 2276 no_fragment_score += 2
adbc4ec4
THD
2277 last_segment_url = None
2278 continue
2279 else:
a539f065
LNO
2280 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2281 no_fragment_score += 2
185bf310 2282 if not should_continue:
adbc4ec4
THD
2283 continue
2284
2285 if known_idx > last_seq:
2286 last_segment_url = None
2287 continue
2288
2289 last_seq += 1
2290
2291 if begin_index < 0 and known_idx < 0:
2292 # skip from the start when it's negative value
2293 known_idx = last_seq + begin_index
2294 if lack_early_segments:
2295 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2296 try:
2297 for idx in range(known_idx, last_seq):
2298 # do not update sequence here or you'll get skipped some part of it
a539f065 2299 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2300 if not should_continue:
adbc4ec4
THD
2301 known_idx = idx - 1
2302 raise ExtractorError('breaking out of outer loop')
2303 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2304 yield {
2305 'url': last_segment_url,
2306 }
2307 if known_idx == last_seq:
2308 no_fragment_score += 5
2309 else:
2310 no_fragment_score = 0
2311 known_idx = last_seq
2312 except ExtractorError:
2313 continue
2314
2315 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2316
b6de707d 2317 def _extract_player_url(self, *ytcfgs, webpage=None):
2318 player_url = traverse_obj(
2319 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2320 get_all=False, expected_type=compat_str)
11f9be09 2321 if not player_url:
b6de707d 2322 return
60f393e4 2323 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2324
b6de707d 2325 def _download_player_url(self, video_id, fatal=False):
2326 res = self._download_webpage(
2327 'https://www.youtube.com/iframe_api',
2328 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2329 if res:
2330 player_version = self._search_regex(
2331 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2332 if player_version:
2333 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2334
60064c53
PH
2335 def _signature_cache_id(self, example_sig):
2336 """ Return a string representation of a signature """
78caa52a 2337 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2338
e40c758c
S
2339 @classmethod
2340 def _extract_player_info(cls, player_url):
2341 for player_re in cls._PLAYER_INFO_RE:
2342 id_m = re.search(player_re, player_url)
2343 if id_m:
2344 break
2345 else:
c081b35c 2346 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2347 return id_m.group('id')
e40c758c 2348
404f611f 2349 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2350 player_id = self._extract_player_info(player_url)
2351 if player_id not in self._code_cache:
1276a43a 2352 code = self._download_webpage(
109dd3b2 2353 player_url, video_id, fatal=fatal,
2354 note='Downloading player ' + player_id,
2355 errnote='Download of %s failed' % player_url)
1276a43a 2356 if code:
2357 self._code_cache[player_id] = code
404f611f 2358 return self._code_cache.get(player_id)
109dd3b2 2359
e40c758c 2360 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2361 player_id = self._extract_player_info(player_url)
e0df6211 2362
c4417ddb 2363 # Read from filesystem cache
545cc85d 2364 func_id = 'js_%s_%s' % (
2365 player_id, self._signature_cache_id(example_sig))
c4417ddb 2366 assert os.path.basename(func_id) == func_id
a0e07d31 2367
69ea8ca4 2368 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2369 if cache_spec is not None:
78caa52a 2370 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2371
404f611f 2372 code = self._load_player(video_id, player_url)
2373 if code:
109dd3b2 2374 res = self._parse_sig_js(code)
e0df6211 2375
109dd3b2 2376 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2377 cache_res = res(test_string)
2378 cache_spec = [ord(c) for c in cache_res]
83799698 2379
109dd3b2 2380 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2381 return res
83799698 2382
60064c53 2383 def _print_sig_code(self, func, example_sig):
404f611f 2384 if not self.get_param('youtube_print_sig_code'):
2385 return
2386
edf3e38e
PH
2387 def gen_sig_code(idxs):
2388 def _genslice(start, end, step):
78caa52a 2389 starts = '' if start == 0 else str(start)
8bcc8756 2390 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2391 steps = '' if step == 1 else (':%d' % step)
78caa52a 2392 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2393
2394 step = None
7af808a5
PH
2395 # Quelch pyflakes warnings - start will be set when step is set
2396 start = '(Never used)'
edf3e38e
PH
2397 for i, prev in zip(idxs[1:], idxs[:-1]):
2398 if step is not None:
2399 if i - prev == step:
2400 continue
2401 yield _genslice(start, prev, step)
2402 step = None
2403 continue
2404 if i - prev in [-1, 1]:
2405 step = i - prev
2406 start = prev
2407 continue
2408 else:
78caa52a 2409 yield 's[%d]' % prev
edf3e38e 2410 if step is None:
78caa52a 2411 yield 's[%d]' % i
edf3e38e
PH
2412 else:
2413 yield _genslice(start, i, step)
2414
78caa52a 2415 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2416 cache_res = func(test_string)
edf3e38e 2417 cache_spec = [ord(c) for c in cache_res]
78caa52a 2418 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2419 signature_id_tuple = '(%s)' % (
2420 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2421 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2422 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2423 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2424
e0df6211
PH
2425 def _parse_sig_js(self, jscode):
2426 funcname = self._search_regex(
abefc03f
S
2427 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2428 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
2429 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2430 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2431 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}\(a,\d+\)',
2432 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 2433 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2434 # Obsolete patterns
2435 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2436 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2437 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2438 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2439 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2440 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2441 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2442 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2443 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2444
2445 jsi = JSInterpreter(jscode)
2446 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2447 return lambda s: initial_function([s])
2448
545cc85d 2449 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2450 """Turn the encrypted s field into a working signature"""
6b37f0be 2451
c8bf86d5 2452 if player_url is None:
69ea8ca4 2453 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2454
c8bf86d5 2455 try:
62af3a0e 2456 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2457 if player_id not in self._player_cache:
2458 func = self._extract_signature_function(
60064c53 2459 video_id, player_url, s
c8bf86d5
PH
2460 )
2461 self._player_cache[player_id] = func
2462 func = self._player_cache[player_id]
404f611f 2463 self._print_sig_code(func, s)
c8bf86d5
PH
2464 return func(s)
2465 except Exception as e:
404f611f 2466 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2467
2468 def _decrypt_nsig(self, s, video_id, player_url):
2469 """Turn the encrypted n field into a working signature"""
2470 if player_url is None:
2471 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2472 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2473
2474 sig_id = ('nsig_value', s)
2475 if sig_id in self._player_cache:
2476 return self._player_cache[sig_id]
2477
2478 try:
2479 player_id = ('nsig', player_url)
2480 if player_id not in self._player_cache:
2481 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2482 func = self._player_cache[player_id]
2483 self._player_cache[sig_id] = func(s)
2484 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2485 return self._player_cache[sig_id]
2486 except Exception as e:
aa9369a2 2487 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2488
2489 def _extract_n_function_name(self, jscode):
48416bc4 2490 nfunc, idx = self._search_regex(
c571b3a6 2491 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2492 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2493 if not idx:
2494 return nfunc
2495 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2496 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2497 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2498
2499 def _extract_n_function(self, video_id, player_url):
2500 player_id = self._extract_player_info(player_url)
2501 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2502
2503 if func_code:
2504 jsi = JSInterpreter(func_code)
2505 else:
2506 jscode = self._load_player(video_id, player_url)
2507 funcname = self._extract_n_function_name(jscode)
2508 jsi = JSInterpreter(jscode)
2509 func_code = jsi.extract_function_code(funcname)
2510 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2511
2512 if self.get_param('youtube_print_sig_code'):
2513 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2514
2515 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2516
109dd3b2 2517 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2518 """
2519 Extract signatureTimestamp (sts)
2520 Required to tell API what sig/player version is in use.
2521 """
2522 sts = None
2523 if isinstance(ytcfg, dict):
2524 sts = int_or_none(ytcfg.get('STS'))
2525
2526 if not sts:
2527 # Attempt to extract from player
2528 if player_url is None:
2529 error_msg = 'Cannot extract signature timestamp without player_url.'
2530 if fatal:
2531 raise ExtractorError(error_msg)
2532 self.report_warning(error_msg)
2533 return
404f611f 2534 code = self._load_player(video_id, player_url, fatal=fatal)
2535 if code:
109dd3b2 2536 sts = int_or_none(self._search_regex(
2537 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2538 'JS player signature timestamp', group='sts', fatal=fatal))
2539 return sts
2540
11f9be09 2541 def _mark_watched(self, video_id, player_responses):
9222c381 2542 playback_url = get_first(
2543 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2544 expected_type=url_or_none)
d77ab8e2 2545 if not playback_url:
352d63fd 2546 self.report_warning('Unable to mark watched')
d77ab8e2
S
2547 return
2548 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2549 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2550
2551 # cpn generation algorithm is reverse engineered from base.js.
2552 # In fact it works even with dummy cpn.
2553 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2554 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2555
2556 qs.update({
2557 'ver': ['2'],
2558 'cpn': [cpn],
2559 })
2560 playback_url = compat_urlparse.urlunparse(
15707c7e 2561 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2562
2563 self._download_webpage(
2564 playback_url, video_id, 'Marking watched',
2565 'Unable to mark watched', fatal=False)
2566
66c9fa36
S
2567 @staticmethod
2568 def _extract_urls(webpage):
2569 # Embedded YouTube player
2570 entries = [
2571 unescapeHTML(mobj.group('url'))
2572 for mobj in re.finditer(r'''(?x)
2573 (?:
2574 <iframe[^>]+?src=|
2575 data-video-url=|
2576 <embed[^>]+?src=|
2577 embedSWF\(?:\s*|
2578 <object[^>]+data=|
2579 new\s+SWFObject\(
2580 )
2581 (["\'])
2582 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2583 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2584 \1''', webpage)]
2585
2586 # lazyYT YouTube embed
2587 entries.extend(list(map(
2588 unescapeHTML,
2589 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2590
2591 # Wordpress "YouTube Video Importer" plugin
2592 matches = re.findall(r'''(?x)<div[^>]+
2593 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2594 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2595 entries.extend(m[-1] for m in matches)
2596
2597 return entries
2598
2599 @staticmethod
2600 def _extract_url(webpage):
2601 urls = YoutubeIE._extract_urls(webpage)
2602 return urls[0] if urls else None
2603
97665381
PH
2604 @classmethod
2605 def extract_id(cls, url):
2606 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2607 if mobj is None:
69ea8ca4 2608 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2609 return mobj.group('id')
c5e8d7af 2610
7c365c21 2611 def _extract_chapters_from_json(self, data, duration):
2612 chapter_list = traverse_obj(
2613 data, (
2614 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2615 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2616 ), expected_type=list)
2617
2618 return self._extract_chapters(
2619 chapter_list,
2620 chapter_time=lambda chapter: float_or_none(
2621 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2622 chapter_title=lambda chapter: traverse_obj(
2623 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2624 duration=duration)
2625
2626 def _extract_chapters_from_engagement_panel(self, data, duration):
2627 content_list = traverse_obj(
8bdd16b4 2628 data,
7c365c21 2629 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2630 expected_type=list, default=[])
052e1350 2631 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2632 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2633
2634 return next((
2635 filter(None, (
2636 self._extract_chapters(
2637 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2638 chapter_time, chapter_title, duration)
2639 for contents in content_list
2640 ))), [])
2641
2642 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2643 chapters = []
7c365c21 2644 last_chapter = {'start_time': 0}
2645 for idx, chapter in enumerate(chapter_list or []):
2646 title = chapter_title(chapter)
84213ea8
S
2647 start_time = chapter_time(chapter)
2648 if start_time is None:
2649 continue
7c365c21 2650 last_chapter['end_time'] = start_time
2651 if start_time < last_chapter['start_time']:
2652 if idx == 1:
2653 chapters.pop()
2654 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2655 else:
2656 self.report_warning(f'Invalid start time for chapter "{title}"')
2657 continue
2658 last_chapter = {'start_time': start_time, 'title': title}
2659 chapters.append(last_chapter)
2660 last_chapter['end_time'] = duration
84213ea8
S
2661 return chapters
2662
545cc85d 2663 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2664 return self._parse_json(self._search_regex(
2665 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2666 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2667
a1c5d2ca
M
2668 def _extract_comment(self, comment_renderer, parent=None):
2669 comment_id = comment_renderer.get('commentId')
2670 if not comment_id:
2671 return
fe93e2c4 2672
052e1350 2673 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2674
49bd8c66 2675 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2676 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2677 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2678 author_id = try_get(comment_renderer,
2679 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2680
49bd8c66 2681 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2682 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2683 author_thumbnail = try_get(comment_renderer,
2684 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2685
2686 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2687 is_favorited = 'creatorHeart' in (try_get(
2688 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2689 return {
2690 'id': comment_id,
2691 'text': text,
d92f5d5a 2692 'timestamp': timestamp,
a1c5d2ca
M
2693 'time_text': time_text,
2694 'like_count': votes,
97524332 2695 'is_favorited': is_favorited,
a1c5d2ca
M
2696 'author': author,
2697 'author_id': author_id,
2698 'author_thumbnail': author_thumbnail,
2699 'author_is_uploader': author_is_uploader,
2700 'parent': parent or 'root'
2701 }
2702
46383212 2703 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2704
2705 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2706
2707 def extract_header(contents):
2d6659b9 2708 _continuation = None
2709 for content in contents:
46383212 2710 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2711 expected_comment_count = self._get_count(
2712 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2713
2d6659b9 2714 if expected_comment_count:
46383212 2715 tracker['est_total'] = expected_comment_count
2716 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2717 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2718
2719 sort_menu_item = try_get(
2720 comments_header_renderer,
2721 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2722 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2723
2724 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2725 if not _continuation:
2726 continue
2727
46383212 2728 sort_text = str_or_none(sort_menu_item.get('title'))
2729 if not sort_text:
2d6659b9 2730 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2731 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2732 break
a2160aa4 2733 return _continuation
a1c5d2ca 2734
2d6659b9 2735 def extract_thread(contents):
a1c5d2ca 2736 if not parent:
46383212 2737 tracker['current_page_thread'] = 0
a1c5d2ca 2738 for content in contents:
46383212 2739 if not parent and tracker['total_parent_comments'] >= max_parents:
2740 yield
a1c5d2ca 2741 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2742 comment_renderer = get_first(
2743 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2744 expected_type=dict, default={})
a1c5d2ca 2745
a1c5d2ca
M
2746 comment = self._extract_comment(comment_renderer, parent)
2747 if not comment:
2748 continue
46383212 2749
2750 tracker['running_total'] += 1
2751 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2752 yield comment
46383212 2753
a1c5d2ca
M
2754 # Attempt to get the replies
2755 comment_replies_renderer = try_get(
2756 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2757
2758 if comment_replies_renderer:
46383212 2759 tracker['current_page_thread'] += 1
a1c5d2ca 2760 comment_entries_iter = self._comment_entries(
99e9e001 2761 comment_replies_renderer, ytcfg, video_id,
46383212 2762 parent=comment.get('id'), tracker=tracker)
2763 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2764 yield reply_comment
2765
46383212 2766 # Keeps track of counts across recursive calls
2767 if not tracker:
2768 tracker = dict(
2769 running_total=0,
2770 est_total=0,
2771 current_page_thread=0,
2772 total_parent_comments=0,
2773 total_reply_comments=0)
2774
2775 # TODO: Deprecated
2d6659b9 2776 # YouTube comments have a max depth of 2
46383212 2777 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2778 if max_depth:
2779 self._downloader.deprecation_warning(
2780 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2781 if max_depth == 1 and parent:
2782 return
a1c5d2ca 2783
46383212 2784 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2785 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2786
46383212 2787 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2788 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2789 if message and not parent:
2790 self.report_warning(message, video_id=video_id)
2791
46383212 2792 response = None
2d6659b9 2793 is_first_continuation = parent is None
a1c5d2ca
M
2794
2795 for page_num in itertools.count(0):
2796 if not continuation:
2797 break
46383212 2798 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2799 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2800 if page_num == 0:
2801 if is_first_continuation:
2802 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2803 else:
2d6659b9 2804 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2805 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2806 else:
2807 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2808 ' ' if parent else '', ' replies' if parent else '',
2809 page_num, comment_prog_str)
2810
2811 response = self._extract_response(
fe93e2c4 2812 item_id=None, query=continuation,
2d6659b9 2813 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2814 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2815
46383212 2816 continuation_contents = traverse_obj(
2817 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2818
2d6659b9 2819 continuation = None
46383212 2820 for continuation_section in continuation_contents:
2821 continuation_items = traverse_obj(
2822 continuation_section,
2823 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2824 get_all=False, expected_type=list) or []
2825 if is_first_continuation:
2826 continuation = extract_header(continuation_items)
2827 is_first_continuation = False
2d6659b9 2828 if continuation:
a1c5d2ca 2829 break
46383212 2830 continue
a1c5d2ca 2831
46383212 2832 for entry in extract_thread(continuation_items):
2833 if not entry:
2834 return
2835 yield entry
2836 continuation = self._extract_continuation({'contents': continuation_items})
2837 if continuation:
2d6659b9 2838 break
a1c5d2ca 2839
a2160aa4 2840 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2841 """Entry for comment extraction"""
2d6659b9 2842 def _real_comment_extract(contents):
aae16f6e 2843 renderer = next((
2844 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2845 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2846 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2847
a2160aa4 2848 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2849 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2850
109dd3b2 2851 @staticmethod
99e9e001 2852 def _get_checkok_params():
2853 return {'contentCheckOk': True, 'racyCheckOk': True}
2854
2855 @classmethod
2856 def _generate_player_context(cls, sts=None):
109dd3b2 2857 context = {
2858 'html5Preference': 'HTML5_PREF_WANTS',
2859 }
2860 if sts is not None:
2861 context['signatureTimestamp'] = sts
2862 return {
2863 'playbackContext': {
2864 'contentPlaybackContext': context
a1a7907b 2865 },
99e9e001 2866 **cls._get_checkok_params()
109dd3b2 2867 }
2868
e7e94f2a
D
2869 @staticmethod
2870 def _is_agegated(player_response):
2871 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2872 return True
e7e94f2a
D
2873
2874 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2875 AGE_GATE_REASONS = (
2876 'confirm your age', 'age-restricted', 'inappropriate', # reason
2877 'age_verification_required', 'age_check_required', # status
2878 )
2879 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2880
2881 @staticmethod
2882 def _is_unplayable(player_response):
2883 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2884
99e9e001 2885 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2886
11f9be09 2887 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2888 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2889 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2890 headers = self.generate_api_headers(
99e9e001 2891 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2892
11f9be09 2893 yt_query = {'videoId': video_id}
2894 yt_query.update(self._generate_player_context(sts))
2895 return self._extract_response(
2896 item_id=video_id, ep='player', query=yt_query,
379e44ed 2897 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2898 default_client=client,
11f9be09 2899 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2900 ) or None
2901
11f9be09 2902 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2903 requested_clients = []
d0d012d4 2904 default = ['android', 'web']
000c15a4 2905 allowed_clients = sorted(
2906 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2907 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2908 for client in self._configuration_arg('player_client'):
2909 if client in allowed_clients:
2910 requested_clients.append(client)
d0d012d4 2911 elif client == 'default':
2912 requested_clients.extend(default)
b4c055ba 2913 elif client == 'all':
2914 requested_clients.extend(allowed_clients)
2915 else:
2916 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2917 if not requested_clients:
d0d012d4 2918 requested_clients = default
cf7e015f 2919
11f9be09 2920 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2921 requested_clients.extend(
e7e94f2a 2922 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2923
11f9be09 2924 return orderedSet(requested_clients)
cf7e015f 2925
c0bc527b
M
2926 def _extract_player_ytcfg(self, client, video_id):
2927 url = {
2928 'web_music': 'https://music.youtube.com',
2929 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2930 }.get(client)
2931 if not url:
2932 return {}
18c7683d 2933 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2934 return self.extract_ytcfg(video_id, webpage) or {}
2935
99e9e001 2936 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2937 initial_pr = None
2938 if webpage:
2939 initial_pr = self._extract_yt_initial_variable(
2940 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2941 video_id, 'initial player response')
6b09401b 2942
c0bc527b
M
2943 original_clients = clients
2944 clients = clients[::-1]
b6de707d 2945 prs = []
e7e94f2a
D
2946
2947 def append_client(client_name):
2948 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2949 clients.append(client_name)
2950
379e44ed 2951 # Android player_response does not have microFormats which are needed for
2952 # extraction of some data. So we return the initial_pr with formats
2953 # stripped out even if not requested by the user
2954 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2955 if initial_pr:
2956 pr = dict(initial_pr)
2957 pr['streamingData'] = None
b6de707d 2958 prs.append(pr)
379e44ed 2959
2960 last_error = None
b6de707d 2961 tried_iframe_fallback = False
2962 player_url = None
c0bc527b
M
2963 while clients:
2964 client = clients.pop()
11f9be09 2965 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2966 if 'configs' not in self._configuration_arg('player_skip'):
2967 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2968
b6de707d 2969 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2970 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2971 if 'js' in self._configuration_arg('player_skip'):
2972 require_js_player = False
2973 player_url = None
2974
2975 if not player_url and not tried_iframe_fallback and require_js_player:
2976 player_url = self._download_player_url(video_id)
2977 tried_iframe_fallback = True
2978
379e44ed 2979 try:
2980 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2981 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2982 except ExtractorError as e:
2983 if last_error:
2984 self.report_warning(last_error)
2985 last_error = e
2986 continue
2987
11f9be09 2988 if pr:
b6de707d 2989 prs.append(pr)
c0bc527b 2990
e7e94f2a 2991 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 2992 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
2993 append_client(client.replace('_agegate', '_creator'))
2994 elif self._is_agegated(pr):
2995 append_client(f'{client}_agegate')
c0bc527b 2996
379e44ed 2997 if last_error:
b6de707d 2998 if not len(prs):
379e44ed 2999 raise last_error
3000 self.report_warning(last_error)
b6de707d 3001 return prs, player_url
11f9be09 3002
a1b2d843 3003 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3004 itags, stream_ids = {}, []
2a9c6dcd 3005 itag_qualities, res_qualities = {}, {}
d3fc8074 3006 q = qualities([
2a9c6dcd 3007 # Normally tiny is the smallest video-only formats. But
3008 # audio-only formats with unknown quality may get tagged as tiny
3009 'tiny',
3010 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3011 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3012 ])
11f9be09 3013 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3014
545cc85d 3015 for fmt in streaming_formats:
3016 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
3017 continue
321bf820 3018
cc2db878 3019 itag = str_or_none(fmt.get('itag'))
9297939e 3020 audio_track = fmt.get('audioTrack') or {}
3021 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3022 if stream_id in stream_ids:
3023 continue
3024
cc2db878 3025 quality = fmt.get('quality')
2a9c6dcd 3026 height = int_or_none(fmt.get('height'))
d3fc8074 3027 if quality == 'tiny' or not quality:
3028 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3029 # The 3gp format (17) in android client has a quality of "small",
3030 # but is actually worse than other formats
3031 if itag == '17':
3032 quality = 'tiny'
3033 if quality:
3034 if itag:
3035 itag_qualities[itag] = quality
3036 if height:
3037 res_qualities[height] = quality
cc2db878 3038 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3039 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3040 # number of fragment that would subsequently requested with (`&sq=N`)
3041 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3042 continue
3043
545cc85d 3044 fmt_url = fmt.get('url')
3045 if not fmt_url:
3046 sc = compat_parse_qs(fmt.get('signatureCipher'))
3047 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3048 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3049 if not (sc and fmt_url and encrypted_sig):
3050 continue
545cc85d 3051 if not player_url:
201e9eaa 3052 continue
545cc85d 3053 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3054 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3055 fmt_url += '&' + sp + '=' + signature
3056
404f611f 3057 query = parse_qs(fmt_url)
3058 throttled = False
b2916526 3059 if query.get('n'):
404f611f 3060 try:
3061 fmt_url = update_url_query(fmt_url, {
3062 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3063 except ExtractorError as e:
aa9369a2 3064 self.report_warning(
3065 f'nsig extraction failed: You may experience throttling for some formats\n'
3066 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3067 throttled = True
3068
545cc85d 3069 if itag:
a0bb6ce5 3070 itags[itag] = 'https'
9297939e 3071 stream_ids.append(stream_id)
3072
0ad92dfb 3073 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3074 language_preference = (
3075 10 if audio_track.get('audioIsDefault') and 10
3076 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3077 else -1)
0ad92dfb 3078 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3079 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3080 # Make sure to avoid false positives with small duration differences.
3081 # Eg: __2ABJjxzNo, ySuUZEjARPY
3082 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3083 if is_damaged:
3084 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3085 dct = {
3086 'asr': int_or_none(fmt.get('audioSampleRate')),
3087 'filesize': int_or_none(fmt.get('contentLength')),
3088 'format_id': itag,
34921b43 3089 'format_note': join_nonempty(
26e8e044 3090 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3091 ' (default)' if language_preference > 0 else ''),
404f611f 3092 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3093 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3094 'source_preference': -10 if throttled else -1,
a4211baf 3095 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3096 'height': height,
dca3ff4a 3097 'quality': q(quality),
cc2db878 3098 'tbr': tbr,
545cc85d 3099 'url': fmt_url,
2a9c6dcd 3100 'width': int_or_none(fmt.get('width')),
ab6df717 3101 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3102 'desc' if language_preference < -1 else ''),
3103 'language_preference': language_preference,
a405b38f 3104 # Strictly de-prioritize damaged and 3gp formats
3105 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3106 }
60bdb7bd 3107 mime_mobj = re.match(
3108 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3109 if mime_mobj:
3110 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3111 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3112 no_audio = dct.get('acodec') == 'none'
3113 no_video = dct.get('vcodec') == 'none'
3114 if no_audio:
3115 dct['vbr'] = tbr
3116 if no_video:
3117 dct['abr'] = tbr
3118 if no_audio or no_video:
545cc85d 3119 dct['downloader_options'] = {
3120 # Youtube throttles chunks >~10M
3121 'http_chunk_size': 10485760,
bf1317d2 3122 }
7c60c33e 3123 if dct.get('ext'):
3124 dct['container'] = dct['ext'] + '_dash'
11f9be09 3125 yield dct
545cc85d 3126
adbc4ec4 3127 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3128 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3129 if not self.get_param('youtube_include_hls_manifest', True):
3130 skip_manifests.append('hls')
3131 get_dash = 'dash' not in skip_manifests and (
3132 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3133 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3134
a0bb6ce5 3135 def process_manifest_format(f, proto, itag):
3136 if itag in itags:
3137 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3138 return False
3139 itag = f'{itag}-{proto}'
3140 if itag:
3141 f['format_id'] = itag
3142 itags[itag] = proto
3143
3144 f['quality'] = next((
3145 q(qdict[val])
e339d25a 3146 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3147 if val in qdict), -1)
3148 return True
2a9c6dcd 3149
11f9be09 3150 for sd in streaming_data:
5d3a0e79 3151 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3152 if hls_manifest_url:
2a9c6dcd 3153 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3154 if process_manifest_format(f, 'hls', self._search_regex(
3155 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3156 yield f
545cc85d 3157
5d3a0e79 3158 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3159 if dash_manifest_url:
2a9c6dcd 3160 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3161 if process_manifest_format(f, 'dash', f['format_id']):
3162 f['filesize'] = int_or_none(self._search_regex(
3163 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3164 if live_from_start:
3165 f['is_from_start'] = True
3166
a0bb6ce5 3167 yield f
11f9be09 3168
720c3099 3169 def _extract_storyboard(self, player_responses, duration):
3170 spec = get_first(
3171 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3172 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3173 if not base_url:
720c3099 3174 return
720c3099 3175 L = len(spec) - 1
3176 for i, args in enumerate(spec):
3177 args = args.split('#')
3178 counts = list(map(int_or_none, args[:5]))
3179 if len(args) != 8 or not all(counts):
3180 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3181 continue
3182 width, height, frame_count, cols, rows = counts
3183 N, sigh = args[6:]
3184
3185 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3186 fragment_count = frame_count / (cols * rows)
3187 fragment_duration = duration / fragment_count
3188 yield {
3189 'format_id': f'sb{i}',
3190 'format_note': 'storyboard',
3191 'ext': 'mhtml',
3192 'protocol': 'mhtml',
3193 'acodec': 'none',
3194 'vcodec': 'none',
3195 'url': url,
3196 'width': width,
3197 'height': height,
3198 'fragments': [{
b3edc806 3199 'url': url.replace('$M', str(j)),
720c3099 3200 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3201 } for j in range(math.ceil(fragment_count))],
3202 }
3203
adbc4ec4 3204 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3205 webpage = None
3206 if 'webpage' not in self._configuration_arg('player_skip'):
3207 webpage = self._download_webpage(
3208 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3209
3210 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3211
b6de707d 3212 player_responses, player_url = self._extract_player_responses(
11f9be09 3213 self._get_requested_clients(url, smuggled_data),
99e9e001 3214 video_id, webpage, master_ytcfg)
11f9be09 3215
adbc4ec4
THD
3216 return webpage, master_ytcfg, player_responses, player_url
3217
a1b2d843 3218 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3219 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3220 is_live = get_first(video_details, 'isLive')
3221 if is_live is None:
3222 is_live = get_first(live_broadcast_details, 'isLiveNow')
3223
3224 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3225 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3226
3227 return live_broadcast_details, is_live, streaming_data, formats
3228
3229 def _real_extract(self, url):
3230 url, smuggled_data = unsmuggle_url(url, {})
3231 video_id = self._match_id(url)
3232
3233 base_url = self.http_scheme() + '//www.youtube.com/'
3234 webpage_url = base_url + 'watch?v=' + video_id
3235
3236 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3237
11f9be09 3238 playability_statuses = traverse_obj(
3239 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3240
3241 trailer_video_id = get_first(
3242 playability_statuses,
3243 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3244 expected_type=str)
3245 if trailer_video_id:
3246 return self.url_result(
3247 trailer_video_id, self.ie_key(), trailer_video_id)
3248
3249 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3250 if webpage else (lambda x: None))
3251
3252 video_details = traverse_obj(
3253 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3254 microformats = traverse_obj(
3255 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3256 expected_type=dict, default=[])
3257 video_title = (
3258 get_first(video_details, 'title')
3259 or self._get_text(microformats, (..., 'title'))
3260 or search_meta(['og:title', 'twitter:title', 'title']))
3261 video_description = get_first(video_details, 'shortDescription')
3262
d89257f3 3263 multifeed_metadata_list = get_first(
3264 player_responses,
3265 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3266 expected_type=str)
3267 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3268 if self.get_param('noplaylist'):
11f9be09 3269 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3270 else:
3271 entries = []
3272 feed_ids = []
3273 for feed in multifeed_metadata_list.split(','):
3274 # Unquote should take place before split on comma (,) since textual
3275 # fields may contain comma as well (see
3276 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3277 feed_data = compat_parse_qs(
3278 compat_urllib_parse_unquote_plus(feed))
3279
3280 def feed_entry(name):
3281 return try_get(
3282 feed_data, lambda x: x[name][0], compat_str)
3283
3284 feed_id = feed_entry('id')
3285 if not feed_id:
3286 continue
3287 feed_title = feed_entry('title')
3288 title = video_title
3289 if feed_title:
3290 title += ' (%s)' % feed_title
3291 entries.append({
3292 '_type': 'url_transparent',
3293 'ie_key': 'Youtube',
3294 'url': smuggle_url(
3295 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3296 {'force_singlefeed': True}),
3297 'title': title,
3298 })
3299 feed_ids.append(feed_id)
3300 self.to_screen(
3301 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3302 % (', '.join(feed_ids), video_id))
3303 return self.playlist_result(
3304 entries, video_id, video_title, video_description)
11f9be09 3305
a1b2d843 3306 duration = int_or_none(
3307 get_first(video_details, 'lengthSeconds')
3308 or get_first(microformats, 'lengthSeconds')
3309 or parse_duration(search_meta('duration'))) or None
3310
3311 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3312 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3313
545cc85d 3314 if not formats:
11f9be09 3315 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3316 self.report_drm(video_id)
11f9be09 3317 pemr = get_first(
3318 playability_statuses,
3319 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3320 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3321 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3322 if subreason:
545cc85d 3323 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3324 countries = get_first(microformats, 'availableCountries')
545cc85d 3325 if not countries:
3326 regions_allowed = search_meta('regionsAllowed')
3327 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3328 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3329 reason += f'. {subreason}'
545cc85d 3330 if reason:
b7da73eb 3331 self.raise_no_formats(reason, expected=True)
bf1317d2 3332
11f9be09 3333 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3334 if not keywords and webpage:
3335 keywords = [
3336 unescapeHTML(m.group('content'))
3337 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3338 for keyword in keywords:
3339 if keyword.startswith('yt:stretch='):
201c1459 3340 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3341 if mobj:
3342 # NB: float is intentional for forcing float division
3343 w, h = (float(v) for v in mobj.groups())
3344 if w > 0 and h > 0:
3345 ratio = w / h
3346 for f in formats:
3347 if f.get('vcodec') != 'none':
3348 f['stretched_ratio'] = ratio
3349 break
a709d873 3350 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3351 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3352 if thumbnail_url:
3353 thumbnails.append({
3354 'url': thumbnail_url,
ff2751ac 3355 })
fccf5021 3356 original_thumbnails = thumbnails.copy()
3357
0ba692ac 3358 # The best resolution thumbnails sometimes does not appear in the webpage
3359 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3360 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3361 thumbnail_names = [
3362 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3363 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3364 'mqdefault', 'mq1', 'mq2', 'mq3',
3365 'default', '1', '2', '3'
3366 ]
cca80fe6 3367 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3368 thumbnails.extend({
3369 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3370 video_id=video_id, name=name, ext=ext,
3371 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3372 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3373 for thumb in thumbnails:
cca80fe6 3374 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3375 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3376 self._remove_duplicate_formats(thumbnails)
fccf5021 3377 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3378
7ea65411 3379 category = get_first(microformats, 'category') or search_meta('genre')
3380 channel_id = str_or_none(
3381 get_first(video_details, 'channelId')
3382 or get_first(microformats, 'externalChannelId')
3383 or search_meta('channelId'))
7ea65411 3384 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3385
3386 live_content = get_first(video_details, 'isLiveContent')
3387 is_upcoming = get_first(video_details, 'isUpcoming')
3388 if is_live is None:
3389 if is_upcoming or live_content is False:
3390 is_live = False
3391 if is_upcoming is None and (live_content or is_live):
3392 is_upcoming = False
adbc4ec4
THD
3393 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3394 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3395 if not duration and live_end_time and live_start_time:
3396 duration = live_end_time - live_start_time
3397
3398 if is_live and self.get_param('live_from_start'):
3399 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3400
720c3099 3401 formats.extend(self._extract_storyboard(player_responses, duration))
3402
3403 # Source is given priority since formats that throttle are given lower source_preference
3404 # When throttling issue is fully fixed, remove this
3405 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3406
545cc85d 3407 info = {
3408 'id': video_id,
39ca3b5c 3409 'title': video_title,
545cc85d 3410 'formats': formats,
3411 'thumbnails': thumbnails,
fccf5021 3412 # The best thumbnail that we are sure exists. Prevents unnecessary
3413 # URL checking if user don't care about getting the best possible thumbnail
3414 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3415 'description': video_description,
11f9be09 3416 'uploader': get_first(video_details, 'author'),
545cc85d 3417 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3418 'uploader_url': owner_profile_url,
3419 'channel_id': channel_id,
e0ddbd02 3420 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3421 'duration': duration,
3422 'view_count': int_or_none(
11f9be09 3423 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3424 or search_meta('interactionCount')),
11f9be09 3425 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3426 'age_limit': 18 if (
11f9be09 3427 get_first(microformats, 'isFamilySafe') is False
545cc85d 3428 or search_meta('isFamilyFriendly') == 'false'
3429 or search_meta('og:restrictions:age') == '18+') else 0,
3430 'webpage_url': webpage_url,
3431 'categories': [category] if category else None,
3432 'tags': keywords,
11f9be09 3433 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3434 'is_live': is_live,
3435 'was_live': (False if is_live or is_upcoming or live_content is False
3436 else None if is_live is None or is_upcoming is None
3437 else live_content),
3438 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3439 'release_timestamp': live_start_time,
545cc85d 3440 }
b477fc13 3441
3944e7af 3442 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3443 if pctr:
ecdc9049 3444 def get_lang_code(track):
3445 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3446 or track.get('languageCode'))
3447
3448 # Converted into dicts to remove duplicates
3449 captions = {
3450 get_lang_code(sub): sub
3451 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3452 translation_languages = {
3453 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3454 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3455
774d79cc 3456 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3457 lang_subs = container.setdefault(lang_code, [])
545cc85d 3458 for fmt in self._SUBTITLE_FORMATS:
3459 query.update({
3460 'fmt': fmt,
3461 })
3462 lang_subs.append({
3463 'ext': fmt,
60f393e4 3464 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3465 'name': sub_name,
545cc85d 3466 })
7e72694b 3467
ecdc9049 3468 subtitles, automatic_captions = {}, {}
3469 for lang_code, caption_track in captions.items():
3470 base_url = caption_track.get('baseUrl')
545cc85d 3471 if not base_url:
3472 continue
ecdc9049 3473 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3474 if caption_track.get('kind') != 'asr':
545cc85d 3475 if not lang_code:
3476 continue
3477 process_language(
ecdc9049 3478 subtitles, base_url, lang_code, lang_name, {})
3479 if not caption_track.get('isTranslatable'):
3480 continue
3944e7af 3481 for trans_code, trans_name in translation_languages.items():
3482 if not trans_code:
545cc85d 3483 continue
ecdc9049 3484 if caption_track.get('kind') != 'asr':
3485 trans_code += f'-{lang_code}'
3486 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3487 # Add an "-orig" label to the original language so that it can be distinguished.
3488 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 3489 if lang_code == f'a-{trans_code}':
3490 process_language(
d49669ac 3491 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3492 # Setting tlang=lang returns damaged subtitles.
3493 # Not using lang_code == f'a-{trans_code}' here for future-proofing
3494 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3495 process_language(automatic_captions, base_url, trans_code, trans_name,
3496 {} if orig_lang == trans_code else {'tlang': trans_code})
ecdc9049 3497 info['automatic_captions'] = automatic_captions
3498 info['subtitles'] = subtitles
7e72694b 3499
545cc85d 3500 parsed_url = compat_urllib_parse_urlparse(url)
3501 for component in [parsed_url.fragment, parsed_url.query]:
3502 query = compat_parse_qs(component)
3503 for k, v in query.items():
3504 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3505 d_k += '_time'
3506 if d_k not in info and k in s_ks:
3507 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3508
3509 # Youtube Music Auto-generated description
822b9d9c 3510 if video_description:
38d70284 3511 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 3512 if mobj:
822b9d9c
RA
3513 release_year = mobj.group('release_year')
3514 release_date = mobj.group('release_date')
3515 if release_date:
3516 release_date = release_date.replace('-', '')
3517 if not release_year:
545cc85d 3518 release_year = release_date[:4]
3519 info.update({
3520 'album': mobj.group('album'.strip()),
3521 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3522 'track': mobj.group('track').strip(),
3523 'release_date': release_date,
cc2db878 3524 'release_year': int_or_none(release_year),
545cc85d 3525 })
7e72694b 3526
545cc85d 3527 initial_data = None
3528 if webpage:
3529 initial_data = self._extract_yt_initial_variable(
3530 webpage, self._YT_INITIAL_DATA_RE, video_id,
3531 'yt initial data')
3532 if not initial_data:
99e9e001 3533 query = {'videoId': video_id}
3534 query.update(self._get_checkok_params())
109dd3b2 3535 initial_data = self._extract_response(
3536 item_id=video_id, ep='next', fatal=False,
99e9e001 3537 ytcfg=master_ytcfg, query=query,
3538 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3539 note='Downloading initial data API JSON')
545cc85d 3540
c60ee3a2 3541 try:
3542 # This will error if there is no livechat
3543 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3544 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3545 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3546 'video_id': video_id,
3547 'ext': 'json',
f6745c49 3548 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3549 }]
3550 except (KeyError, IndexError, TypeError):
3551 pass
545cc85d 3552
3553 if initial_data:
7c365c21 3554 info['chapters'] = (
3555 self._extract_chapters_from_json(initial_data, duration)
3556 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3557 or None)
545cc85d 3558
17322130 3559 contents = traverse_obj(
3560 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3561 expected_type=list, default=[])
3562
3563 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3564 if vpir:
3565 stl = vpir.get('superTitleLink')
3566 if stl:
3567 stl = self._get_text(stl)
3568 if try_get(
3569 vpir,
3570 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3571 info['location'] = stl
3572 else:
3573 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3574 if mobj:
545cc85d 3575 info.update({
17322130 3576 'series': mobj.group(1),
3577 'season_number': int(mobj.group(2)),
3578 'episode_number': int(mobj.group(3)),
545cc85d 3579 })
17322130 3580 for tlb in (try_get(
3581 vpir,
3582 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3583 list) or []):
3584 tbr = tlb.get('toggleButtonRenderer') or {}
3585 for getter, regex in [(
3586 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3587 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3588 lambda x: x['accessibility'],
3589 lambda x: x['accessibilityData']['accessibilityData'],
3590 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3591 label = (try_get(tbr, getter, dict) or {}).get('label')
3592 if label:
3593 mobj = re.match(regex, label)
3594 if mobj:
3595 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3596 break
17322130 3597 sbr_tooltip = try_get(
3598 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3599 if sbr_tooltip:
3600 like_count, dislike_count = sbr_tooltip.split(' / ')
3601 info.update({
3602 'like_count': str_to_int(like_count),
3603 'dislike_count': str_to_int(dislike_count),
3604 })
3605 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3606 if vsir:
3607 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3608 info.update({
3609 'channel': self._get_text(vor, 'title'),
3610 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3611
3612 rows = try_get(
3613 vsir,
3614 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3615 list) or []
3616 multiple_songs = False
3617 for row in rows:
3618 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3619 multiple_songs = True
3620 break
3621 for row in rows:
3622 mrr = row.get('metadataRowRenderer') or {}
3623 mrr_title = mrr.get('title')
3624 if not mrr_title:
3625 continue
3626 mrr_title = self._get_text(mrr, 'title')
3627 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3628 if mrr_title == 'License':
3629 info['license'] = mrr_contents_text
3630 elif not multiple_songs:
3631 if mrr_title == 'Album':
3632 info['album'] = mrr_contents_text
3633 elif mrr_title == 'Artist':
3634 info['artist'] = mrr_contents_text
3635 elif mrr_title == 'Song':
3636 info['track'] = mrr_contents_text
545cc85d 3637
3638 fallbacks = {
3639 'channel': 'uploader',
3640 'channel_id': 'uploader_id',
3641 'channel_url': 'uploader_url',
3642 }
992f9a73 3643
17322130 3644 # The upload date for scheduled, live and past live streams / premieres in microformats
3645 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3646 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3647 upload_date = (
3648 unified_strdate(get_first(microformats, 'uploadDate'))
3649 or unified_strdate(search_meta('uploadDate')))
3650 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3651 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3652 info['upload_date'] = upload_date
992f9a73 3653
545cc85d 3654 for to, frm in fallbacks.items():
3655 if not info.get(to):
3656 info[to] = info.get(frm)
3657
3658 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3659 v = info.get(s_k)
3660 if v:
3661 info[d_k] = v
b84071c0 3662
11f9be09 3663 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3664 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3665 is_membersonly = None
b28f8d24 3666 is_premium = None
c224251a
M
3667 if initial_data and is_private is not None:
3668 is_membersonly = False
b28f8d24 3669 is_premium = False
47193e02 3670 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3671 badge_labels = set()
3672 for content in contents:
3673 if not isinstance(content, dict):
3674 continue
3675 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3676 for badge_label in badge_labels:
3677 if badge_label.lower() == 'members only':
3678 is_membersonly = True
3679 elif badge_label.lower() == 'premium':
3680 is_premium = True
3681 elif badge_label.lower() == 'unlisted':
3682 is_unlisted = True
c224251a 3683
c224251a
M
3684 info['availability'] = self._availability(
3685 is_private=is_private,
b28f8d24 3686 needs_premium=is_premium,
c224251a
M
3687 needs_subscription=is_membersonly,
3688 needs_auth=info['age_limit'] >= 18,
3689 is_unlisted=None if is_private is None else is_unlisted)
3690
a2160aa4 3691 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3692
11f9be09 3693 self.mark_watched(video_id, player_responses)
d77ab8e2 3694
545cc85d 3695 return info
c5e8d7af 3696
a61fd4cf 3697
a6213a49 3698class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3699
182bda88 3700 @staticmethod
3701 def passthrough_smuggled_data(func):
3702 def _smuggle(entries, smuggled_data):
3703 for entry in entries:
3704 # TODO: Convert URL to music.youtube instead.
3705 # Do we need to passthrough any other smuggled_data?
3706 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3707 yield entry
3708
3709 @functools.wraps(func)
3710 def wrapper(self, url):
3711 url, smuggled_data = unsmuggle_url(url, {})
3712 if self.is_music_url(url):
3713 smuggled_data['is_music_url'] = True
3714 info_dict = func(self, url, smuggled_data)
3715 if smuggled_data and info_dict.get('entries'):
3716 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3717 return info_dict
3718 return wrapper
3719
a6213a49 3720 def _extract_channel_id(self, webpage):
3721 channel_id = self._html_search_meta(
3722 'channelId', webpage, 'channel id', default=None)
3723 if channel_id:
3724 return channel_id
3725 channel_url = self._html_search_meta(
3726 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3727 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3728 'twitter:app:url:googleplay'), webpage, 'channel url')
3729 return self._search_regex(
3730 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3731 channel_url, 'channel id')
15f6397c 3732
8bdd16b4 3733 @staticmethod
cd7c66cf 3734 def _extract_basic_item_renderer(item):
3735 # Modified from _extract_grid_item_renderer
201c1459 3736 known_basic_renderers = (
3737 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3738 )
3739 for key, renderer in item.items():
201c1459 3740 if not isinstance(renderer, dict):
cd7c66cf 3741 continue
201c1459 3742 elif key in known_basic_renderers:
3743 return renderer
3744 elif key.startswith('grid') and key.endswith('Renderer'):
3745 return renderer
8bdd16b4 3746
8bdd16b4 3747 def _grid_entries(self, grid_renderer):
3748 for item in grid_renderer['items']:
3749 if not isinstance(item, dict):
39b62db1 3750 continue
cd7c66cf 3751 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3752 if not isinstance(renderer, dict):
3753 continue
052e1350 3754 title = self._get_text(renderer, 'title')
fe93e2c4 3755
8bdd16b4 3756 # playlist
3757 playlist_id = renderer.get('playlistId')
3758 if playlist_id:
3759 yield self.url_result(
3760 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3761 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3762 video_title=title)
201c1459 3763 continue
8bdd16b4 3764 # video
3765 video_id = renderer.get('videoId')
3766 if video_id:
3767 yield self._extract_video(renderer)
201c1459 3768 continue
8bdd16b4 3769 # channel
3770 channel_id = renderer.get('channelId')
3771 if channel_id:
8bdd16b4 3772 yield self.url_result(
3773 'https://www.youtube.com/channel/%s' % channel_id,
3774 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3775 continue
3776 # generic endpoint URL support
3777 ep_url = urljoin('https://www.youtube.com/', try_get(
3778 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3779 compat_str))
3780 if ep_url:
3781 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3782 if ie.suitable(ep_url):
3783 yield self.url_result(
3784 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3785 break
8bdd16b4 3786
16aa9ea4 3787 def _music_reponsive_list_entry(self, renderer):
3788 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3789 if video_id:
3790 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3791 ie=YoutubeIE.ie_key(), video_id=video_id)
3792 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3793 if playlist_id:
3794 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3795 if video_id:
3796 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3797 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3798 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3799 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3800 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3801 if browse_id:
3802 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3803 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3804
3d3dddc9 3805 def _shelf_entries_from_content(self, shelf_renderer):
3806 content = shelf_renderer.get('content')
3807 if not isinstance(content, dict):
8bdd16b4 3808 return
cd7c66cf 3809 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3810 if renderer:
3811 # TODO: add support for nested playlists so each shelf is processed
3812 # as separate playlist
3813 # TODO: this includes only first N items
3814 for entry in self._grid_entries(renderer):
3815 yield entry
3816 renderer = content.get('horizontalListRenderer')
3817 if renderer:
3818 # TODO
3819 pass
8bdd16b4 3820
29f7c58a 3821 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3822 ep = try_get(
3823 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3824 compat_str)
3825 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3826 if shelf_url:
29f7c58a 3827 # Skipping links to another channels, note that checking for
3828 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3829 # will not work
3830 if skip_channels and '/channels?' in shelf_url:
3831 return
052e1350 3832 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3833 yield self.url_result(shelf_url, video_title=title)
3834 # Shelf may not contain shelf URL, fallback to extraction from content
3835 for entry in self._shelf_entries_from_content(shelf_renderer):
3836 yield entry
c5e8d7af 3837
8bdd16b4 3838 def _playlist_entries(self, video_list_renderer):
3839 for content in video_list_renderer['contents']:
3840 if not isinstance(content, dict):
3841 continue
3842 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3843 if not isinstance(renderer, dict):
3844 continue
3845 video_id = renderer.get('videoId')
3846 if not video_id:
3847 continue
3848 yield self._extract_video(renderer)
07aeced6 3849
3462ffa8 3850 def _rich_entries(self, rich_grid_renderer):
3851 renderer = try_get(
70d5c17b 3852 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3853 video_id = renderer.get('videoId')
3854 if not video_id:
3855 return
3856 yield self._extract_video(renderer)
3857
8bdd16b4 3858 def _video_entry(self, video_renderer):
3859 video_id = video_renderer.get('videoId')
3860 if video_id:
3861 return self._extract_video(video_renderer)
dacb3a86 3862
8bdd16b4 3863 def _post_thread_entries(self, post_thread_renderer):
3864 post_renderer = try_get(
3865 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3866 if not post_renderer:
3867 return
3868 # video attachment
3869 video_renderer = try_get(
895b0931 3870 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3871 video_id = video_renderer.get('videoId')
3872 if video_id:
3873 entry = self._extract_video(video_renderer)
8bdd16b4 3874 if entry:
3875 yield entry
895b0931 3876 # playlist attachment
3877 playlist_id = try_get(
3878 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3879 if playlist_id:
3880 yield self.url_result(
e28f1c0a 3881 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3882 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3883 # inline video links
3884 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3885 for run in runs:
3886 if not isinstance(run, dict):
3887 continue
3888 ep_url = try_get(
3889 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3890 if not ep_url:
3891 continue
3892 if not YoutubeIE.suitable(ep_url):
3893 continue
3894 ep_video_id = YoutubeIE._match_id(ep_url)
3895 if video_id == ep_video_id:
3896 continue
895b0931 3897 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3898
8bdd16b4 3899 def _post_thread_continuation_entries(self, post_thread_continuation):
3900 contents = post_thread_continuation.get('contents')
3901 if not isinstance(contents, list):
3902 return
3903 for content in contents:
3904 renderer = content.get('backstagePostThreadRenderer')
3905 if not isinstance(renderer, dict):
3906 continue
3907 for entry in self._post_thread_entries(renderer):
3908 yield entry
07aeced6 3909
39ed931e 3910 r''' # unused
3911 def _rich_grid_entries(self, contents):
3912 for content in contents:
3913 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3914 if video_renderer:
3915 entry = self._video_entry(video_renderer)
3916 if entry:
3917 yield entry
3918 '''
52efa4b3 3919
a6213a49 3920 def _extract_entries(self, parent_renderer, continuation_list):
3921 # continuation_list is modified in-place with continuation_list = [continuation_token]
3922 continuation_list[:] = [None]
3923 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3924 for content in contents:
3925 if not isinstance(content, dict):
3926 continue
16aa9ea4 3927 is_renderer = traverse_obj(
3928 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3929 expected_type=dict)
a6213a49 3930 if not is_renderer:
3931 renderer = content.get('richItemRenderer')
3932 if renderer:
3933 for entry in self._rich_entries(renderer):
3934 yield entry
3935 continuation_list[0] = self._extract_continuation(parent_renderer)
3936 continue
3937 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3938 for isr_content in isr_contents:
3939 if not isinstance(isr_content, dict):
8bdd16b4 3940 continue
69184e41 3941
a6213a49 3942 known_renderers = {
3943 'playlistVideoListRenderer': self._playlist_entries,
3944 'gridRenderer': self._grid_entries,
3945 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3946 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3947 'backstagePostThreadRenderer': self._post_thread_entries,
3948 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3949 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3950 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3951 }
3952 for key, renderer in isr_content.items():
3953 if key not in known_renderers:
3954 continue
3955 for entry in known_renderers[key](renderer):
3956 if entry:
3957 yield entry
3958 continuation_list[0] = self._extract_continuation(renderer)
3959 break
70d5c17b 3960
3961 if not continuation_list[0]:
a6213a49 3962 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3963
a6213a49 3964 if not continuation_list[0]:
3965 continuation_list[0] = self._extract_continuation(parent_renderer)
3966
3967 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3968 continuation_list = [None]
3969 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3970 tab_content = try_get(tab, lambda x: x['content'], dict)
3971 if not tab_content:
3972 return
3462ffa8 3973 parent_renderer = (
29f7c58a 3974 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3975 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3976 for entry in extract_entries(parent_renderer):
3977 yield entry
3462ffa8 3978 continuation = continuation_list[0]
d069eca7 3979
8bdd16b4 3980 for page_num in itertools.count(1):
3981 if not continuation:
3982 break
99e9e001 3983 headers = self.generate_api_headers(
3984 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3985 response = self._extract_response(
3986 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3987 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3988 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3989
3990 if not response:
8bdd16b4 3991 break
ac56cf38 3992 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3993 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3994 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 3995
69184e41 3996 known_continuation_renderers = {
3997 'playlistVideoListContinuation': self._playlist_entries,
3998 'gridContinuation': self._grid_entries,
3999 'itemSectionContinuation': self._post_thread_continuation_entries,
4000 'sectionListContinuation': extract_entries, # for feeds
4001 }
8bdd16b4 4002 continuation_contents = try_get(
69184e41 4003 response, lambda x: x['continuationContents'], dict) or {}
4004 continuation_renderer = None
4005 for key, value in continuation_contents.items():
4006 if key not in known_continuation_renderers:
3462ffa8 4007 continue
69184e41 4008 continuation_renderer = value
4009 continuation_list = [None]
4010 for entry in known_continuation_renderers[key](continuation_renderer):
4011 yield entry
4012 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4013 break
4014 if continuation_renderer:
4015 continue
c5e8d7af 4016
a1b535bd 4017 known_renderers = {
e4b98809 4018 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4019 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4020 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4021 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4022 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4023 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4024 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4025 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4026 }
cce889b9 4027 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4028 continuation_items = try_get(
cce889b9 4029 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4030 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4031 video_items_renderer = None
4032 for key, value in continuation_item.items():
4033 if key not in known_renderers:
8bdd16b4 4034 continue
a1b535bd 4035 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4036 continuation_list = [None]
a1b535bd 4037 for entry in known_renderers[key][0](video_items_renderer):
4038 yield entry
9ba5705a 4039 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4040 break
4041 if video_items_renderer:
4042 continue
8bdd16b4 4043 break
9558dcec 4044
8bdd16b4 4045 @staticmethod
7c219ea6 4046 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4047 for tab in tabs:
cd684175 4048 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4049 if renderer.get('selected') is True:
4050 return renderer
2b3c2546 4051 else:
7c219ea6 4052 if fatal:
4053 raise ExtractorError('Unable to find selected tab')
b82f815f 4054
47193e02 4055 @classmethod
4056 def _extract_uploader(cls, data):
8bdd16b4 4057 uploader = {}
47193e02 4058 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4059 owner = try_get(
4060 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4061 if owner:
4062 uploader['uploader'] = owner.get('text')
4063 uploader['uploader_id'] = try_get(
4064 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4065 uploader['uploader_url'] = urljoin(
4066 'https://www.youtube.com/',
4067 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4068 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4069
ac56cf38 4070 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4071 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4072 tags = []
b60419c5 4073
8bdd16b4 4074 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4075 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4076 renderer = try_get(
4077 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4078 if renderer:
b60419c5 4079 channel_name = renderer.get('title')
4080 channel_url = renderer.get('channelUrl')
4081 channel_id = renderer.get('externalId')
39ed931e 4082 else:
64c0d954 4083 renderer = try_get(
4084 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4085
8bdd16b4 4086 if renderer:
4087 title = renderer.get('title')
ecc97af3 4088 description = renderer.get('description', '')
b60419c5 4089 playlist_id = channel_id
4090 tags = renderer.get('keywords', '').split()
b60419c5 4091
301d07fc 4092 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4093 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4094 def _get_uncropped(url):
4095 return url_or_none((url or '').split('=')[0] + '=s0')
4096
4097 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4098 if avatar_thumbnails:
4099 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4100 if uncropped_avatar:
4101 avatar_thumbnails.append({
4102 'url': uncropped_avatar,
4103 'id': 'avatar_uncropped',
4104 'preference': 1
4105 })
4106
4107 channel_banners = self._extract_thumbnails(
4108 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4109 for banner in channel_banners:
4110 banner['preference'] = -10
4111
4112 if channel_banners:
4113 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4114 if uncropped_banner:
4115 channel_banners.append({
4116 'url': uncropped_banner,
4117 'id': 'banner_uncropped',
4118 'preference': -5
4119 })
4120
4121 primary_thumbnails = self._extract_thumbnails(
4122 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4123
3462ffa8 4124 if playlist_id is None:
70d5c17b 4125 playlist_id = item_id
f0d785d3 4126
4127 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4128 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4129 if title is None:
f0d785d3 4130 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4131 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4132 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4133
b60419c5 4134 metadata = {
4135 'playlist_id': playlist_id,
4136 'playlist_title': title,
4137 'playlist_description': description,
4138 'uploader': channel_name,
4139 'uploader_id': channel_id,
4140 'uploader_url': channel_url,
301d07fc 4141 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4142 'tags': tags,
f0d785d3 4143 'view_count': self._get_count(playlist_stats, 1),
4144 'availability': self._extract_availability(data),
4145 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4146 'playlist_count': self._get_count(playlist_stats, 0),
4147 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4148 }
4149 if not channel_id:
4150 metadata.update(self._extract_uploader(data))
4151 metadata.update({
4152 'channel': metadata['uploader'],
4153 'channel_id': metadata['uploader_id'],
4154 'channel_url': metadata['uploader_url']})
4155 return self.playlist_result(
d069eca7 4156 self._entries(
ac56cf38 4157 selected_tab, playlist_id, ytcfg,
4158 self._extract_account_syncid(ytcfg, data),
4159 self._extract_visitor_data(data, ytcfg)),
b60419c5 4160 **metadata)
73c4ac2c 4161
ac56cf38 4162 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4163 first_id = last_id = response = None
2be71994 4164 for page_num in itertools.count(1):
cd7c66cf 4165 videos = list(self._playlist_entries(playlist))
4166 if not videos:
4167 return
2be71994 4168 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4169 if start >= len(videos):
4170 return
4171 for video in videos[start:]:
4172 if video['id'] == first_id:
4173 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4174 return
4175 yield video
4176 first_id = first_id or videos[0]['id']
4177 last_id = videos[-1]['id']
79360d99 4178 watch_endpoint = try_get(
4179 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4180 headers = self.generate_api_headers(
4181 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4182 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4183 query = {
4184 'playlistId': playlist_id,
4185 'videoId': watch_endpoint.get('videoId') or last_id,
4186 'index': watch_endpoint.get('index') or len(videos),
4187 'params': watch_endpoint.get('params') or 'OAE%3D'
4188 }
4189 response = self._extract_response(
4190 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4191 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4192 check_get_keys='contents'
4193 )
cd7c66cf 4194 playlist = try_get(
79360d99 4195 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4196
ac56cf38 4197 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4198 title = playlist.get('title') or try_get(
4199 data, lambda x: x['titleText']['simpleText'], compat_str)
4200 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4201
4202 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4203 playlist_url = urljoin(url, try_get(
4204 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4205 compat_str))
4206 if playlist_url and playlist_url != url:
4207 return self.url_result(
4208 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4209 video_title=title)
cd7c66cf 4210
8bdd16b4 4211 return self.playlist_result(
ac56cf38 4212 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4213 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4214
47193e02 4215 def _extract_availability(self, data):
4216 """
4217 Gets the availability of a given playlist/tab.
4218 Note: Unless YouTube tells us explicitly, we do not assume it is public
4219 @param data: response
4220 """
4221 is_private = is_unlisted = None
4222 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4223 badge_labels = self._extract_badges(renderer)
4224
4225 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4226 privacy_dropdown_entries = try_get(
4227 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4228 for renderer_dict in privacy_dropdown_entries:
4229 is_selected = try_get(
4230 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4231 if not is_selected:
4232 continue
052e1350 4233 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4234 if label:
4235 badge_labels.add(label.lower())
4236 break
4237
4238 for badge_label in badge_labels:
4239 if badge_label == 'unlisted':
4240 is_unlisted = True
4241 elif badge_label == 'private':
4242 is_private = True
4243 elif badge_label == 'public':
4244 is_unlisted = is_private = False
4245 return self._availability(is_private, False, False, False, is_unlisted)
4246
4247 @staticmethod
4248 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4249 sidebar_renderer = try_get(
4250 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4251 for item in sidebar_renderer:
4252 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4253 if renderer:
4254 return renderer
4255
ac56cf38 4256 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4257 """
4258 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4259 """
5d342002 4260 browse_id = params = None
47193e02 4261 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4262 if not renderer:
4263 return
4264 menu_renderer = try_get(
4265 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4266 for menu_item in menu_renderer:
4267 if not isinstance(menu_item, dict):
358de58c 4268 continue
47193e02 4269 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4270 text = try_get(
4271 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4272 if not text or text.lower() != 'show unavailable videos':
4273 continue
4274 browse_endpoint = try_get(
4275 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4276 browse_id = browse_endpoint.get('browseId')
4277 params = browse_endpoint.get('params')
4278 break
5d342002 4279
11f9be09 4280 headers = self.generate_api_headers(
99e9e001 4281 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4282 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4283 query = {
4284 'params': params or 'wgYCCAA=',
4285 'browseId': browse_id or 'VL%s' % item_id
4286 }
4287 return self._extract_response(
4288 item_id=item_id, headers=headers, query=query,
fe93e2c4 4289 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4290 note='Downloading API JSON with unavailable videos')
358de58c 4291
ac56cf38 4292 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4293 retries = self.get_param('extractor_retries', 3)
62bff2c1 4294 count = -1
ac56cf38 4295 webpage = data = last_error = None
14fdfea9 4296 while count < retries:
62bff2c1 4297 count += 1
14fdfea9 4298 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4299 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4300 if last_error:
c705177d 4301 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4302 try:
4303 webpage = self._download_webpage(
4304 url, item_id,
4305 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4306 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4307 except ExtractorError as e:
4308 if isinstance(e.cause, network_exceptions):
4309 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4310 last_error = error_to_compat_str(e.cause or e.msg)
4311 if count < retries:
4312 continue
4313 if fatal:
4314 raise
4315 self.report_warning(error_to_compat_str(e))
14fdfea9 4316 break
ac56cf38 4317 else:
4318 try:
4319 self._extract_and_report_alerts(data)
4320 except ExtractorError as e:
4321 if fatal:
4322 raise
4323 self.report_warning(error_to_compat_str(e))
4324 break
4325
7c219ea6 4326 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4327 break
4328
4329 last_error = 'Incomplete yt initial data received'
4330 if count >= retries:
4331 if fatal:
4332 raise ExtractorError(last_error)
4333 self.report_warning(last_error)
4334 break
4335
cd7c66cf 4336 return webpage, data
4337
ac56cf38 4338 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4339 data = None
4340 if 'webpage' not in self._configuration_arg('skip'):
4341 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4342 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4343 # Reject webpage data if redirected to home page without explicitly requesting
4344 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4345 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4346 if (url != 'https://www.youtube.com/feed/recommended'
4347 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4348 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4349 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4350 if fatal:
4351 raise ExtractorError(msg, expected=True)
4352 self.report_warning(msg, only_once=True)
ac56cf38 4353 if not data:
4354 if not ytcfg and self.is_authenticated:
4355 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4356 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4357 raise ExtractorError(
4358 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4359 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4360 expected=True)
4361 self.report_warning(msg, only_once=True)
4362 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4363 return data, ytcfg
4364
4365 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4366 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4367 resolve_response = self._extract_response(
4368 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4369 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4370 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4371 for ep_key, ep in endpoints.items():
4372 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4373 if params:
4374 return self._extract_response(
4375 item_id=item_id, query=params, ep=ep, headers=headers,
4376 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4377 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4378 err_note = 'Failed to resolve url (does the playlist exist?)'
4379 if fatal:
4380 raise ExtractorError(err_note, expected=True)
4381 self.report_warning(err_note, item_id)
4382
a6213a49 4383 _SEARCH_PARAMS = None
4384
af5c1c55 4385 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4386 data = {'query': query}
4387 if params is NO_DEFAULT:
4388 params = self._SEARCH_PARAMS
4389 if params:
4390 data['params'] = params
16aa9ea4 4391
4392 content_keys = (
4393 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4394 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4395 # ytmusic search
4396 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4397 ('continuationContents', ),
4398 )
4399 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4400
a61fd4cf 4401 continuation_list = [None]
a6213a49 4402 for page_num in itertools.count(1):
a61fd4cf 4403 data.update(continuation_list[0] or {})
a6213a49 4404 search = self._extract_response(
4405 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4406 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4407 slr_contents = traverse_obj(search, *content_keys)
4408 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4409 if not continuation_list[0]:
a6213a49 4410 break
4411
4412
4413class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4414 IE_DESC = 'YouTube Tabs'
4415 _VALID_URL = r'''(?x:
4416 https?://
4417 (?:\w+\.)?
4418 (?:
4419 youtube(?:kids)?\.com|
4420 %(invidious)s
4421 )/
4422 (?:
4423 (?P<channel_type>channel|c|user|browse)/|
4424 (?P<not_channel>
4425 feed/|hashtag/|
4426 (?:playlist|watch)\?.*?\blist=
4427 )|
4428 (?!(?:%(reserved_names)s)\b) # Direct URLs
4429 )
4430 (?P<id>[^/?\#&]+)
4431 )''' % {
4432 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4433 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4434 }
4435 IE_NAME = 'youtube:tab'
4436
4437 _TESTS = [{
4438 'note': 'playlists, multipage',
4439 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4440 'playlist_mincount': 94,
4441 'info_dict': {
4442 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4443 'title': 'Igor Kleiner - Playlists',
a6213a49 4444 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4445 'uploader': 'Igor Kleiner',
a6213a49 4446 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4447 'channel': 'Igor Kleiner',
4448 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4449 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4450 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4451 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4452 'channel_follower_count': int
a6213a49 4453 },
4454 }, {
4455 'note': 'playlists, multipage, different order',
4456 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4457 'playlist_mincount': 94,
4458 'info_dict': {
4459 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4460 'title': 'Igor Kleiner - Playlists',
a6213a49 4461 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4462 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4463 'uploader': 'Igor Kleiner',
4464 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4465 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4466 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4467 'channel': 'Igor Kleiner',
4468 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4469 'channel_follower_count': int
a6213a49 4470 },
4471 }, {
4472 'note': 'playlists, series',
4473 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4474 'playlist_mincount': 5,
4475 'info_dict': {
4476 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4477 'title': '3Blue1Brown - Playlists',
4478 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4479 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4480 'uploader': '3Blue1Brown',
976ae3ea 4481 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4482 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4483 'channel': '3Blue1Brown',
4484 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4485 'tags': ['Mathematics'],
6c73052c 4486 'channel_follower_count': int
a6213a49 4487 },
4488 }, {
4489 'note': 'playlists, singlepage',
4490 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4491 'playlist_mincount': 4,
4492 'info_dict': {
4493 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4494 'title': 'ThirstForScience - Playlists',
4495 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4496 'uploader': 'ThirstForScience',
4497 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4498 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4499 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4500 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4501 'tags': 'count:13',
4502 'channel': 'ThirstForScience',
6c73052c 4503 'channel_follower_count': int
a6213a49 4504 }
4505 }, {
4506 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4507 'only_matching': True,
4508 }, {
4509 'note': 'basic, single video playlist',
4510 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4511 'info_dict': {
4512 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4513 'uploader': 'Sergey M.',
4514 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4515 'title': 'youtube-dl public playlist',
976ae3ea 4516 'description': '',
4517 'tags': [],
4518 'view_count': int,
4519 'modified_date': '20201130',
4520 'channel': 'Sergey M.',
4521 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4522 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4523 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4524 },
4525 'playlist_count': 1,
4526 }, {
4527 'note': 'empty playlist',
4528 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4529 'info_dict': {
4530 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4531 'uploader': 'Sergey M.',
4532 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4533 'title': 'youtube-dl empty playlist',
976ae3ea 4534 'tags': [],
4535 'channel': 'Sergey M.',
4536 'description': '',
4537 'modified_date': '20160902',
4538 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4539 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4540 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4541 },
4542 'playlist_count': 0,
4543 }, {
4544 'note': 'Home tab',
4545 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4546 'info_dict': {
4547 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4548 'title': 'lex will - Home',
4549 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4550 'uploader': 'lex will',
4551 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4552 'channel': 'lex will',
4553 'tags': ['bible', 'history', 'prophesy'],
4554 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4555 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4556 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4557 'channel_follower_count': int
a6213a49 4558 },
4559 'playlist_mincount': 2,
4560 }, {
4561 'note': 'Videos tab',
4562 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4563 'info_dict': {
4564 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4565 'title': 'lex will - Videos',
4566 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4567 'uploader': 'lex will',
4568 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4569 'tags': ['bible', 'history', 'prophesy'],
4570 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4571 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4572 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4573 'channel': 'lex will',
6c73052c 4574 'channel_follower_count': int
a6213a49 4575 },
4576 'playlist_mincount': 975,
4577 }, {
4578 'note': 'Videos tab, sorted by popular',
4579 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4580 'info_dict': {
4581 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4582 'title': 'lex will - Videos',
4583 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4584 'uploader': 'lex will',
4585 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4586 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4587 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4588 'channel': 'lex will',
4589 'tags': ['bible', 'history', 'prophesy'],
4590 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4591 'channel_follower_count': int
a6213a49 4592 },
4593 'playlist_mincount': 199,
4594 }, {
4595 'note': 'Playlists tab',
4596 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4597 'info_dict': {
4598 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4599 'title': 'lex will - Playlists',
4600 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4601 'uploader': 'lex will',
4602 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4603 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4604 'channel': 'lex will',
4605 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4606 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4607 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4608 'channel_follower_count': int
a6213a49 4609 },
4610 'playlist_mincount': 17,
4611 }, {
4612 'note': 'Community tab',
4613 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4614 'info_dict': {
4615 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4616 'title': 'lex will - Community',
4617 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4618 'uploader': 'lex will',
4619 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4620 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4621 'channel': 'lex will',
4622 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4623 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4624 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4625 'channel_follower_count': int
a6213a49 4626 },
4627 'playlist_mincount': 18,
4628 }, {
4629 'note': 'Channels tab',
4630 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4631 'info_dict': {
4632 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4633 'title': 'lex will - Channels',
4634 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4635 'uploader': 'lex will',
4636 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4637 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4638 'channel': 'lex will',
4639 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4640 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4641 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4642 'channel_follower_count': int
a6213a49 4643 },
4644 'playlist_mincount': 12,
4645 }, {
4646 'note': 'Search tab',
4647 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4648 'playlist_mincount': 40,
4649 'info_dict': {
4650 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4651 'title': '3Blue1Brown - Search - linear algebra',
4652 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4653 'uploader': '3Blue1Brown',
4654 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4655 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4656 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4657 'tags': ['Mathematics'],
4658 'channel': '3Blue1Brown',
4659 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4660 'channel_follower_count': int
a6213a49 4661 },
4662 }, {
4663 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4664 'only_matching': True,
4665 }, {
4666 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4667 'only_matching': True,
4668 }, {
4669 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4670 'only_matching': True,
4671 }, {
4672 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4673 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4674 'info_dict': {
4675 'title': '29C3: Not my department',
4676 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4677 'uploader': 'Christiaan008',
4678 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4679 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4680 'tags': [],
4681 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4682 'view_count': int,
4683 'modified_date': '20150605',
4684 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4685 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4686 'channel': 'Christiaan008',
a6213a49 4687 },
4688 'playlist_count': 96,
4689 }, {
4690 'note': 'Large playlist',
4691 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4692 'info_dict': {
4693 'title': 'Uploads from Cauchemar',
4694 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4695 'uploader': 'Cauchemar',
4696 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4697 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4698 'tags': [],
4699 'modified_date': r're:\d{8}',
4700 'channel': 'Cauchemar',
4701 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4702 'view_count': int,
4703 'description': '',
4704 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4705 },
4706 'playlist_mincount': 1123,
976ae3ea 4707 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4708 }, {
4709 'note': 'even larger playlist, 8832 videos',
4710 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4711 'only_matching': True,
4712 }, {
4713 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4714 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4715 'info_dict': {
4716 'title': 'Uploads from Interstellar Movie',
4717 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4718 'uploader': 'Interstellar Movie',
4719 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4720 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4721 'tags': [],
4722 'view_count': int,
4723 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4724 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4725 'channel': 'Interstellar Movie',
4726 'description': '',
4727 'modified_date': r're:\d{8}',
a6213a49 4728 },
4729 'playlist_mincount': 21,
4730 }, {
4731 'note': 'Playlist with "show unavailable videos" button',
4732 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4733 'info_dict': {
4734 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4735 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4736 'uploader': 'Phim Siêu Nhân Nhật Bản',
4737 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4738 'view_count': int,
4739 'channel': 'Phim Siêu Nhân Nhật Bản',
4740 'tags': [],
4741 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4742 'description': '',
4743 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4744 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4745 'modified_date': r're:\d{8}',
a6213a49 4746 },
4747 'playlist_mincount': 200,
976ae3ea 4748 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4749 }, {
4750 'note': 'Playlist with unavailable videos in page 7',
4751 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4752 'info_dict': {
4753 'title': 'Uploads from BlankTV',
4754 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4755 'uploader': 'BlankTV',
4756 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4757 'channel': 'BlankTV',
4758 'channel_url': 'https://www.youtube.com/c/blanktv',
4759 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4760 'view_count': int,
4761 'tags': [],
4762 'uploader_url': 'https://www.youtube.com/c/blanktv',
4763 'modified_date': r're:\d{8}',
4764 'description': '',
a6213a49 4765 },
4766 'playlist_mincount': 1000,
976ae3ea 4767 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4768 }, {
4769 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4770 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4771 'info_dict': {
4772 'title': 'Data Analysis with Dr Mike Pound',
4773 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4774 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4775 'uploader': 'Computerphile',
4776 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4777 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4778 'tags': [],
4779 'view_count': int,
4780 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4781 'channel_url': 'https://www.youtube.com/user/Computerphile',
4782 'channel': 'Computerphile',
a6213a49 4783 },
4784 'playlist_mincount': 11,
4785 }, {
4786 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4787 'only_matching': True,
4788 }, {
4789 'note': 'Playlist URL that does not actually serve a playlist',
4790 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4791 'info_dict': {
4792 'id': 'FqZTN594JQw',
4793 'ext': 'webm',
4794 'title': "Smiley's People 01 detective, Adventure Series, Action",
4795 'uploader': 'STREEM',
4796 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4797 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4798 'upload_date': '20150526',
4799 'license': 'Standard YouTube License',
4800 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4801 'categories': ['People & Blogs'],
4802 'tags': list,
4803 'view_count': int,
4804 'like_count': int,
a6213a49 4805 },
4806 'params': {
4807 'skip_download': True,
4808 },
4809 'skip': 'This video is not available.',
4810 'add_ie': [YoutubeIE.ie_key()],
4811 }, {
4812 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4813 'only_matching': True,
4814 }, {
4815 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4816 'only_matching': True,
4817 }, {
4818 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4819 'info_dict': {
6c73052c 4820 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4821 'ext': 'mp4',
976ae3ea 4822 'title': str,
a6213a49 4823 'uploader': 'Sky News',
4824 'uploader_id': 'skynews',
4825 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4826 'upload_date': r're:\d{8}',
976ae3ea 4827 'description': str,
a6213a49 4828 'categories': ['News & Politics'],
4829 'tags': list,
4830 'like_count': int,
6c73052c 4831 'release_timestamp': 1642502819,
976ae3ea 4832 'channel': 'Sky News',
4833 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4834 'age_limit': 0,
4835 'view_count': int,
6c73052c 4836 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4837 'playable_in_embed': True,
6c73052c 4838 'release_date': '20220118',
976ae3ea 4839 'availability': 'public',
4840 'live_status': 'is_live',
4841 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4842 'channel_follower_count': int
a6213a49 4843 },
4844 'params': {
4845 'skip_download': True,
4846 },
976ae3ea 4847 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4848 }, {
4849 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4850 'info_dict': {
4851 'id': 'a48o2S1cPoo',
4852 'ext': 'mp4',
4853 'title': 'The Young Turks - Live Main Show',
4854 'uploader': 'The Young Turks',
4855 'uploader_id': 'TheYoungTurks',
4856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4857 'upload_date': '20150715',
4858 'license': 'Standard YouTube License',
4859 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4860 'categories': ['News & Politics'],
4861 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4862 'like_count': int,
a6213a49 4863 },
4864 'params': {
4865 'skip_download': True,
4866 },
4867 'only_matching': True,
4868 }, {
4869 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4870 'only_matching': True,
4871 }, {
4872 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4873 'only_matching': True,
4874 }, {
4875 'note': 'A channel that is not live. Should raise error',
4876 'url': 'https://www.youtube.com/user/numberphile/live',
4877 'only_matching': True,
4878 }, {
4879 'url': 'https://www.youtube.com/feed/trending',
4880 'only_matching': True,
4881 }, {
4882 'url': 'https://www.youtube.com/feed/library',
4883 'only_matching': True,
4884 }, {
4885 'url': 'https://www.youtube.com/feed/history',
4886 'only_matching': True,
4887 }, {
4888 'url': 'https://www.youtube.com/feed/subscriptions',
4889 'only_matching': True,
4890 }, {
4891 'url': 'https://www.youtube.com/feed/watch_later',
4892 'only_matching': True,
4893 }, {
4894 'note': 'Recommended - redirects to home page.',
4895 'url': 'https://www.youtube.com/feed/recommended',
4896 'only_matching': True,
4897 }, {
4898 'note': 'inline playlist with not always working continuations',
4899 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4900 'only_matching': True,
4901 }, {
4902 'url': 'https://www.youtube.com/course',
4903 'only_matching': True,
4904 }, {
4905 'url': 'https://www.youtube.com/zsecurity',
4906 'only_matching': True,
4907 }, {
4908 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4909 'only_matching': True,
4910 }, {
4911 'url': 'https://www.youtube.com/TheYoungTurks/live',
4912 'only_matching': True,
4913 }, {
4914 'url': 'https://www.youtube.com/hashtag/cctv9',
4915 'info_dict': {
4916 'id': 'cctv9',
4917 'title': '#cctv9',
976ae3ea 4918 'tags': [],
a6213a49 4919 },
4920 'playlist_mincount': 350,
4921 }, {
4922 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4923 'only_matching': True,
4924 }, {
4925 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4926 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4927 'only_matching': True
4928 }, {
4929 'note': '/browse/ should redirect to /channel/',
4930 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4931 'only_matching': True
4932 }, {
4933 'note': 'VLPL, should redirect to playlist?list=PL...',
4934 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4935 'info_dict': {
4936 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4937 'uploader': 'NoCopyrightSounds',
4938 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4939 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4940 'title': 'NCS Releases',
976ae3ea 4941 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4942 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4943 'modified_date': r're:\d{8}',
4944 'view_count': int,
4945 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4946 'tags': [],
4947 'channel': 'NoCopyrightSounds',
a6213a49 4948 },
4949 'playlist_mincount': 166,
976ae3ea 4950 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4951 }, {
4952 'note': 'Topic, should redirect to playlist?list=UU...',
4953 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4954 'info_dict': {
4955 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4956 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4957 'title': 'Uploads from Royalty Free Music - Topic',
4958 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4959 'tags': [],
4960 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4961 'channel': 'Royalty Free Music - Topic',
4962 'view_count': int,
4963 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4964 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4965 'modified_date': r're:\d{8}',
4966 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4967 'description': '',
a6213a49 4968 },
4969 'expected_warnings': [
a6213a49 4970 'The URL does not have a videos tab',
976ae3ea 4971 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4972 ],
4973 'playlist_mincount': 101,
4974 }, {
4975 'note': 'Topic without a UU playlist',
4976 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4977 'info_dict': {
4978 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4979 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4980 'tags': [],
a6213a49 4981 },
4982 'expected_warnings': [
976ae3ea 4983 'the playlist redirect gave error',
a6213a49 4984 ],
4985 'playlist_mincount': 9,
4986 }, {
4987 'note': 'Youtube music Album',
4988 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4989 'info_dict': {
4990 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4991 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 4992 'tags': [],
4993 'view_count': int,
4994 'description': '',
4995 'availability': 'unlisted',
4996 'modified_date': r're:\d{8}',
a6213a49 4997 },
4998 'playlist_count': 50,
4999 }, {
5000 'note': 'unlisted single video playlist',
5001 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5002 'info_dict': {
5003 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5004 'uploader': 'colethedj',
5005 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5006 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5007 'availability': 'unlisted',
5008 'tags': [],
5009 'modified_date': '20211208',
5010 'channel': 'colethedj',
5011 'view_count': int,
5012 'description': '',
5013 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5014 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5015 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5016 },
5017 'playlist_count': 1,
5018 }, {
5019 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5020 'url': 'https://www.youtube.com/feed/recommended',
5021 'info_dict': {
5022 'id': 'recommended',
5023 'title': 'recommended',
6c73052c 5024 'tags': [],
a6213a49 5025 },
5026 'playlist_mincount': 50,
5027 'params': {
5028 'skip_download': True,
5029 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5030 },
5031 }, {
5032 'note': 'API Fallback: /videos tab, sorted by oldest first',
5033 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5034 'info_dict': {
5035 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5036 'title': 'Cody\'sLab - Videos',
5037 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5038 'uploader': 'Cody\'sLab',
5039 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5040 'channel': 'Cody\'sLab',
5041 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5042 'tags': [],
5043 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5044 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5045 'channel_follower_count': int
a6213a49 5046 },
5047 'playlist_mincount': 650,
5048 'params': {
5049 'skip_download': True,
5050 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5051 },
5052 }, {
5053 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5054 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5055 'info_dict': {
5056 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5057 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5058 'title': 'Uploads from Royalty Free Music - Topic',
5059 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5060 'modified_date': r're:\d{8}',
5061 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5062 'description': '',
5063 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5064 'tags': [],
5065 'channel': 'Royalty Free Music - Topic',
5066 'view_count': int,
5067 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5068 },
5069 'expected_warnings': [
976ae3ea 5070 'does not have a videos tab',
5071 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5072 ],
5073 'playlist_mincount': 101,
5074 'params': {
5075 'skip_download': True,
5076 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5077 },
7c219ea6 5078 }, {
5079 'note': 'non-standard redirect to regional channel',
5080 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5081 'only_matching': True
a6213a49 5082 }]
5083
5084 @classmethod
5085 def suitable(cls, url):
5086 return False if YoutubeIE.suitable(url) else super(
5087 YoutubeTabIE, cls).suitable(url)
9297939e 5088
64f36541 5089 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5090
182bda88 5091 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5092 def _real_extract(self, url, smuggled_data):
cd7c66cf 5093 item_id = self._match_id(url)
5094 url = compat_urlparse.urlunparse(
5095 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5096 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5097
fe03a6cd 5098 def get_mobj(url):
37e57a9f 5099 mobj = self._URL_RE.match(url).groupdict()
07cce701 5100 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5101 return mobj
5102
37e57a9f 5103 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5104 # Youtube returns incomplete data if tabname is not lower case
5105 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5106 if is_channel:
5107 if smuggled_data.get('is_music_url'):
37e57a9f 5108 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5109 item_id = item_id[2:]
37e57a9f 5110 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5111 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5112 mdata = self._extract_tab_endpoint(
37e57a9f 5113 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5114 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5115 get_all=False, expected_type=compat_str)
ac56cf38 5116 if not murl:
37e57a9f 5117 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5118 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5119 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5120 pre = f'https://www.youtube.com/channel/{item_id}'
5121
64f36541 5122 original_tab_name = tab
fe03a6cd 5123 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5124 # Home URLs should redirect to /videos/
37e57a9f 5125 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5126 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5127 tab = '/videos'
5128
5129 url = ''.join((pre, tab, post))
5130 mobj = get_mobj(url)
cd7c66cf 5131
5132 # Handle both video/playlist URLs
201c1459 5133 qs = parse_qs(url)
37e57a9f 5134 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5135
fe03a6cd 5136 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5137 if not playlist_id:
fe03a6cd 5138 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5139 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5140 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5141 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5142 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5143 mobj = get_mobj(url)
cd7c66cf 5144
5145 if video_id and playlist_id:
a06916d9 5146 if self.get_param('noplaylist'):
37e57a9f 5147 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5148 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5149 ie=YoutubeIE.ie_key(), video_id=video_id)
5150 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5151
ac56cf38 5152 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5153
7c219ea6 5154 # YouTube may provide a non-standard redirect to the regional channel
5155 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5156 redirect_url = traverse_obj(
5157 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5158 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5159 redirect_url = ''.join((
5160 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5161 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5162 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5163
37e57a9f 5164 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5165 if tabs:
5166 selected_tab = self._extract_selected_tab(tabs)
64f36541 5167 selected_tab_name = selected_tab.get('title', '').lower()
5168 if selected_tab_name == 'home':
5169 selected_tab_name = 'featured'
5170 requested_tab_name = mobj['tab'][1:]
09f1580e 5171 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5172 if requested_tab_name == 'live':
09f1580e 5173 # Live tab should have redirected to the video
5174 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5175 if requested_tab_name not in ('', selected_tab_name):
5176 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5177 if not original_tab_name:
5178 if item_id[:2] == 'UC':
5179 # Topic channels don't have /videos. Use the equivalent playlist instead
5180 pl_id = f'UU{item_id[2:]}'
5181 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5182 try:
5183 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5184 except ExtractorError:
5185 redirect_warning += ' and the playlist redirect gave error'
5186 else:
5187 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5188 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5189 if selected_tab_name and selected_tab_name != requested_tab_name:
5190 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5191 else:
5192 raise ExtractorError(redirect_warning, expected=True)
18db7548 5193
37e57a9f 5194 if redirect_warning:
64f36541 5195 self.to_screen(redirect_warning)
37e57a9f 5196 self.write_debug(f'Final URL: {url}')
18db7548 5197
358de58c 5198 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5199 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5200 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5201 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5202 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5203 if tabs:
ac56cf38 5204 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5205
37e57a9f 5206 playlist = traverse_obj(
5207 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5208 if playlist:
ac56cf38 5209 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5210
37e57a9f 5211 video_id = traverse_obj(
5212 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5213 if video_id:
09f1580e 5214 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5215 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5216 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5217 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5218
8bdd16b4 5219 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5220
c5e8d7af 5221
8bdd16b4 5222class YoutubePlaylistIE(InfoExtractor):
96565c7e 5223 IE_DESC = 'YouTube playlists'
8bdd16b4 5224 _VALID_URL = r'''(?x)(?:
5225 (?:https?://)?
5226 (?:\w+\.)?
5227 (?:
5228 (?:
5229 youtube(?:kids)?\.com|
d9190e44 5230 %(invidious)s
8bdd16b4 5231 )
5232 /.*?\?.*?\blist=
5233 )?
5234 (?P<id>%(playlist_id)s)
d9190e44
RH
5235 )''' % {
5236 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5237 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5238 }
8bdd16b4 5239 IE_NAME = 'youtube:playlist'
cdc628a4 5240 _TESTS = [{
8bdd16b4 5241 'note': 'issue #673',
5242 'url': 'PLBB231211A4F62143',
cdc628a4 5243 'info_dict': {
8bdd16b4 5244 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5245 'id': 'PLBB231211A4F62143',
976ae3ea 5246 'uploader': 'Wickman',
8bdd16b4 5247 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5248 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5249 'view_count': int,
5250 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5251 'modified_date': r're:\d{8}',
5252 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5253 'channel': 'Wickman',
5254 'tags': [],
5255 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5256 },
5257 'playlist_mincount': 29,
5258 }, {
5259 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5260 'info_dict': {
5261 'title': 'YDL_safe_search',
5262 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5263 },
5264 'playlist_count': 2,
5265 'skip': 'This playlist is private',
9558dcec 5266 }, {
8bdd16b4 5267 'note': 'embedded',
5268 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5269 'playlist_count': 4,
9558dcec 5270 'info_dict': {
8bdd16b4 5271 'title': 'JODA15',
5272 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5273 'uploader': 'milan',
5274 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5275 'description': '',
5276 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5277 'tags': [],
5278 'modified_date': '20140919',
5279 'view_count': int,
5280 'channel': 'milan',
5281 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5282 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5283 },
5284 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5285 }, {
8bdd16b4 5286 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5287 'playlist_mincount': 654,
8bdd16b4 5288 'info_dict': {
5289 'title': '2018 Chinese New Singles (11/6 updated)',
5290 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5291 'uploader': 'LBK',
5292 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5293 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5294 'channel': 'LBK',
5295 'view_count': int,
5296 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5297 'tags': [],
5298 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5299 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5300 'modified_date': r're:\d{8}',
5301 },
5302 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5303 }, {
29f7c58a 5304 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5305 'only_matching': True,
5306 }, {
5307 # music album playlist
5308 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5309 'only_matching': True,
5310 }]
5311
5312 @classmethod
5313 def suitable(cls, url):
201c1459 5314 if YoutubeTabIE.suitable(url):
5315 return False
49a57e70 5316 from ..utils import parse_qs
201c1459 5317 qs = parse_qs(url)
5318 if qs.get('v', [None])[0]:
5319 return False
5320 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5321
5322 def _real_extract(self, url):
5323 playlist_id = self._match_id(url)
46953e7e 5324 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5325 url = update_url_query(
5326 'https://www.youtube.com/playlist',
5327 parse_qs(url) or {'list': playlist_id})
5328 if is_music_url:
5329 url = smuggle_url(url, {'is_music_url': True})
5330 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5331
5332
5333class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5334 IE_DESC = 'youtu.be'
29f7c58a 5335 _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}
5336 _TESTS = [{
8bdd16b4 5337 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5338 'info_dict': {
5339 'id': 'yeWKywCrFtk',
5340 'ext': 'mp4',
5341 'title': 'Small Scale Baler and Braiding Rugs',
5342 'uploader': 'Backus-Page House Museum',
5343 'uploader_id': 'backuspagemuseum',
5344 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5345 'upload_date': '20161008',
5346 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5347 'categories': ['Nonprofits & Activism'],
5348 'tags': list,
5349 'like_count': int,
976ae3ea 5350 'age_limit': 0,
5351 'playable_in_embed': True,
5352 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5353 'channel': 'Backus-Page House Museum',
5354 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5355 'live_status': 'not_live',
5356 'view_count': int,
5357 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5358 'availability': 'public',
5359 'duration': 59,
8bdd16b4 5360 },
5361 'params': {
5362 'noplaylist': True,
5363 'skip_download': True,
5364 },
39e7107d 5365 }, {
8bdd16b4 5366 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5367 'only_matching': True,
cdc628a4
PH
5368 }]
5369
8bdd16b4 5370 def _real_extract(self, url):
5ad28e7f 5371 mobj = self._match_valid_url(url)
29f7c58a 5372 video_id = mobj.group('id')
5373 playlist_id = mobj.group('playlist_id')
8bdd16b4 5374 return self.url_result(
29f7c58a 5375 update_url_query('https://www.youtube.com/watch', {
5376 'v': video_id,
5377 'list': playlist_id,
5378 'feature': 'youtu.be',
5379 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5380
5381
b6ce9bb0 5382class YoutubeLivestreamEmbedIE(InfoExtractor):
5383 IE_DESC = 'YouTube livestream embeds'
5384 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5385 _TESTS = [{
5386 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5387 'only_matching': True,
5388 }]
5389
5390 def _real_extract(self, url):
5391 channel_id = self._match_id(url)
5392 return self.url_result(
5393 f'https://www.youtube.com/channel/{channel_id}/live',
5394 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5395
5396
8bdd16b4 5397class YoutubeYtUserIE(InfoExtractor):
96565c7e 5398 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5399 IE_NAME = 'youtube:user'
8bdd16b4 5400 _VALID_URL = r'ytuser:(?P<id>.+)'
5401 _TESTS = [{
5402 'url': 'ytuser:phihag',
5403 'only_matching': True,
5404 }]
5405
5406 def _real_extract(self, url):
5407 user_id = self._match_id(url)
5408 return self.url_result(
c586f9e8 5409 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5410 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5411
b05654f0 5412
3d3dddc9 5413class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5414 IE_NAME = 'youtube:favorites'
96565c7e 5415 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5416 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5417 _LOGIN_REQUIRED = True
5418 _TESTS = [{
5419 'url': ':ytfav',
5420 'only_matching': True,
5421 }, {
5422 'url': ':ytfavorites',
5423 'only_matching': True,
5424 }]
5425
5426 def _real_extract(self, url):
5427 return self.url_result(
5428 'https://www.youtube.com/playlist?list=LL',
5429 ie=YoutubeTabIE.ie_key())
5430
5431
a6213a49 5432class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5433 IE_DESC = 'YouTube search'
78caa52a 5434 IE_NAME = 'youtube:search'
b05654f0 5435 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5436 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5437 _TESTS = [{
5438 'url': 'ytsearch5:youtube-dl test video',
5439 'playlist_count': 5,
5440 'info_dict': {
5441 'id': 'youtube-dl test video',
5442 'title': 'youtube-dl test video',
5443 }
5444 }]
b05654f0 5445
a61fd4cf 5446
5f7cb91a 5447class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5448 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5449 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5450 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5451 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5452 _TESTS = [{
5453 'url': 'ytsearchdate5:youtube-dl test video',
5454 'playlist_count': 5,
5455 'info_dict': {
5456 'id': 'youtube-dl test video',
5457 'title': 'youtube-dl test video',
5458 }
5459 }]
75dff0ee 5460
c9ae7b95 5461
a6213a49 5462class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5463 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5464 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5465 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5466 _TESTS = [{
5467 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5468 'playlist_mincount': 5,
5469 'info_dict': {
11f9be09 5470 'id': 'youtube-dl test video',
3462ffa8 5471 'title': 'youtube-dl test video',
5472 }
a61fd4cf 5473 }, {
5474 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5475 'playlist_mincount': 5,
5476 'info_dict': {
5477 'id': 'python',
5478 'title': 'python',
5479 }
5480
3462ffa8 5481 }, {
5482 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5483 'only_matching': True,
5484 }]
5485
5486 def _real_extract(self, url):
4dfbf869 5487 qs = parse_qs(url)
386e1dd9 5488 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5489 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5490
5491
16aa9ea4 5492class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5493 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5494 IE_NAME = 'youtube:music:search_url'
5495 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5496 _TESTS = [{
5497 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5498 'playlist_count': 16,
5499 'info_dict': {
5500 'id': 'royalty free music',
5501 'title': 'royalty free music',
5502 }
5503 }, {
5504 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5505 'playlist_mincount': 30,
5506 'info_dict': {
5507 'id': 'royalty free music - songs',
5508 'title': 'royalty free music - songs',
5509 },
5510 'params': {'extract_flat': 'in_playlist'}
5511 }, {
5512 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5513 'playlist_mincount': 30,
5514 'info_dict': {
5515 'id': 'royalty free music - community playlists',
5516 'title': 'royalty free music - community playlists',
5517 },
5518 'params': {'extract_flat': 'in_playlist'}
5519 }]
5520
5521 _SECTIONS = {
5522 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5523 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5524 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5525 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5526 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5527 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5528 }
5529
5530 def _real_extract(self, url):
5531 qs = parse_qs(url)
5532 query = (qs.get('search_query') or qs.get('q'))[0]
5533 params = qs.get('sp', (None,))[0]
5534 if params:
5535 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5536 else:
5537 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5538 params = self._SECTIONS.get(section)
5539 if not params:
5540 section = None
5541 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5542 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5543
5544
182bda88 5545class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5546 """
25f14e9f 5547 Base class for feed extractors
3d3dddc9 5548 Subclasses must define the _FEED_NAME property.
d7ae0639 5549 """
b2e8bc1b 5550 _LOGIN_REQUIRED = True
ef2f3c7f 5551 _TESTS = []
d7ae0639
JMF
5552
5553 @property
5554 def IE_NAME(self):
78caa52a 5555 return 'youtube:%s' % self._FEED_NAME
04cc9617 5556
3853309f 5557 def _real_extract(self, url):
3d3dddc9 5558 return self.url_result(
182bda88 5559 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5560
5561
ef2f3c7f 5562class YoutubeWatchLaterIE(InfoExtractor):
5563 IE_NAME = 'youtube:watchlater'
96565c7e 5564 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5565 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5566 _TESTS = [{
8bdd16b4 5567 'url': ':ytwatchlater',
bc7a9cd8
S
5568 'only_matching': True,
5569 }]
25f14e9f
S
5570
5571 def _real_extract(self, url):
ef2f3c7f 5572 return self.url_result(
5573 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5574
5575
25f14e9f 5576class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5577 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5578 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5579 _FEED_NAME = 'recommended'
45db527f 5580 _LOGIN_REQUIRED = False
3d3dddc9 5581 _TESTS = [{
5582 'url': ':ytrec',
5583 'only_matching': True,
5584 }, {
5585 'url': ':ytrecommended',
5586 'only_matching': True,
5587 }, {
5588 'url': 'https://youtube.com',
5589 'only_matching': True,
5590 }]
1ed5b5c9 5591
1ed5b5c9 5592
25f14e9f 5593class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5594 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5595 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5596 _FEED_NAME = 'subscriptions'
3d3dddc9 5597 _TESTS = [{
5598 'url': ':ytsubs',
5599 'only_matching': True,
5600 }, {
5601 'url': ':ytsubscriptions',
5602 'only_matching': True,
5603 }]
1ed5b5c9 5604
1ed5b5c9 5605
25f14e9f 5606class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5607 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5608 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5609 _FEED_NAME = 'history'
3d3dddc9 5610 _TESTS = [{
5611 'url': ':ythistory',
5612 'only_matching': True,
5613 }]
1ed5b5c9
JMF
5614
5615
15870e90
PH
5616class YoutubeTruncatedURLIE(InfoExtractor):
5617 IE_NAME = 'youtube:truncated_url'
5618 IE_DESC = False # Do not list
975d35db 5619 _VALID_URL = r'''(?x)
b95aab84
PH
5620 (?:https?://)?
5621 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5622 (?:watch\?(?:
c4808c60 5623 feature=[a-z_]+|
b95aab84
PH
5624 annotation_id=annotation_[^&]+|
5625 x-yt-cl=[0-9]+|
c1708b89 5626 hl=[^&]*|
287be8c6 5627 t=[0-9]+
b95aab84
PH
5628 )?
5629 |
5630 attribution_link\?a=[^&]+
5631 )
5632 $
975d35db 5633 '''
15870e90 5634
c4808c60 5635 _TESTS = [{
2d3d2997 5636 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5637 'only_matching': True,
dc2fc736 5638 }, {
2d3d2997 5639 'url': 'https://www.youtube.com/watch?',
dc2fc736 5640 'only_matching': True,
b95aab84
PH
5641 }, {
5642 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5643 'only_matching': True,
5644 }, {
5645 'url': 'https://www.youtube.com/watch?feature=foo',
5646 'only_matching': True,
c1708b89
PH
5647 }, {
5648 'url': 'https://www.youtube.com/watch?hl=en-GB',
5649 'only_matching': True,
287be8c6
PH
5650 }, {
5651 'url': 'https://www.youtube.com/watch?t=2372',
5652 'only_matching': True,
c4808c60
PH
5653 }]
5654
15870e90
PH
5655 def _real_extract(self, url):
5656 raise ExtractorError(
78caa52a
PH
5657 'Did you forget to quote the URL? Remember that & is a meta '
5658 'character in most shells, so you want to put the URL in quotes, '
3867038a 5659 'like youtube-dl '
2d3d2997 5660 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5661 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5662 expected=True)
772fd5cc
PH
5663
5664
3cd786db 5665class YoutubeClipIE(InfoExtractor):
5666 IE_NAME = 'youtube:clip'
5667 IE_DESC = False # Do not list
5668 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5669
5670 def _real_extract(self, url):
5671 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5672 return self.url_result(url, 'Generic')
5673
5674
772fd5cc
PH
5675class YoutubeTruncatedIDIE(InfoExtractor):
5676 IE_NAME = 'youtube:truncated_id'
5677 IE_DESC = False # Do not list
b95aab84 5678 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5679
5680 _TESTS = [{
5681 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5682 'only_matching': True,
5683 }]
5684
5685 def _real_extract(self, url):
5686 video_id = self._match_id(url)
5687 raise ExtractorError(
5688 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5689 expected=True)