]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[go,viu] Extract subtitles from the m3u8 manifest (#3219)
[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')
fd2ad7cb 821 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
822 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'), expected_type=str))
823 url = f'https://www.youtube.com/watch?v={video_id}'
824 if overlay_style == 'SHORTS' or (navigation_url and '/shorts/' in navigation_url):
825 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 826
30a074c2 827 return {
39ed931e 828 '_type': 'url',
30a074c2 829 'ie_key': YoutubeIE.ie_key(),
830 'id': video_id,
fd2ad7cb 831 'url': url,
30a074c2 832 'title': title,
833 'description': description,
834 'duration': duration,
835 'view_count': view_count,
836 'uploader': uploader,
f3aa3c3f 837 'channel_id': channel_id,
a709d873 838 'thumbnails': thumbnails,
a30a6ed3 839 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 840 'live_status': ('is_upcoming' if scheduled_timestamp is not None
841 else 'was_live' if 'streamed' in time_text.lower()
842 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
843 else None),
844 'release_timestamp': scheduled_timestamp,
845 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 846 }
847
0c148415 848
360e1ca5 849class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 850 IE_DESC = 'YouTube'
cb7dfeea 851 _VALID_URL = r"""(?x)^
c5e8d7af 852 (
edb53e2d 853 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 854 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
855 (?:www\.)?deturl\.com/www\.youtube\.com|
856 (?:www\.)?pwnyoutube\.com|
857 (?:www\.)?hooktube\.com|
858 (?:www\.)?yourepeat\.com|
859 tube\.majestyc\.net|
860 %(invidious)s|
861 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
862 (?:.*?\#/)? # handle anchor (#/) redirect urls
863 (?: # the various things that can precede the ID:
b6ce9bb0 864 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 865 |(?: # or the v= param in all its forms
f7000f3a 866 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 867 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 868 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
869 v=
870 )
f4b05232 871 ))
cbaed4bb
S
872 |(?:
873 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
874 vid\.plus| # or vid.plus/xxxx
875 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 876 %(invidious)s
cbaed4bb 877 )/
edb53e2d 878 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 879 )
c5e8d7af 880 )? # all until now is optional -> you can pass the naked ID
201c1459 881 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 882 (?(1).+)? # if we found the ID, everything can follow
9297939e 883 (?:\#|$)""" % {
d9190e44 884 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 885 }
e40c758c 886 _PLAYER_INFO_RE = (
cc2db878 887 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
888 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 889 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 890 )
2c62dc26 891 _formats = {
c2d3cb4c 892 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
893 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
894 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
895 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
896 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
897 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
898 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
899 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 900 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 901 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
902 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
903 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
904 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
905 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
906 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 907 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 908 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
909 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 910
911
912 # 3D videos
c2d3cb4c 913 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
914 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
915 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
916 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 917 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
918 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
919 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 920
96fb5605 921 # Apple HTTP Live Streaming
11f12195 922 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 923 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
924 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
925 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
926 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
927 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 928 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
929 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
930
931 # DASH mp4 video
d23028a8
S
932 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
933 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
934 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
935 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
936 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 937 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
938 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
939 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
940 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
942 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
943 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 944
f6f1fc92 945 # Dash mp4 audio
d23028a8
S
946 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
947 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
948 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
949 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
950 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
951 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
952 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
953
954 # Dash webm
d23028a8
S
955 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
956 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
957 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
958 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
959 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
960 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
961 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
962 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
963 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
964 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
965 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
966 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
967 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
968 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
969 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 970 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
971 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
973 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
974 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
975 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
976 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
977
978 # Dash webm audio
d23028a8
S
979 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
980 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 981
0857baad 982 # Dash webm audio with opus inside
d23028a8
S
983 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
984 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
985 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 986
ce6b9a2d
PH
987 # RTMP (unnamed)
988 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
989
990 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
991 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
992 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
993 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
994 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
995 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
996 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
997 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
998 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 999 }
29f7c58a 1000 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1001
fd5c4aab
S
1002 _GEO_BYPASS = False
1003
78caa52a 1004 IE_NAME = 'youtube'
2eb88d95
PH
1005 _TESTS = [
1006 {
2d3d2997 1007 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1008 'info_dict': {
1009 'id': 'BaW_jenozKc',
1010 'ext': 'mp4',
3867038a 1011 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1012 'uploader': 'Philipp Hagemeister',
1013 'uploader_id': 'phihag',
ec85ded8 1014 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1015 'channel': 'Philipp Hagemeister',
dd4c4492
S
1016 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1017 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1018 'upload_date': '20121002',
ff9f925b 1019 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1020 'categories': ['Science & Technology'],
3867038a 1021 'tags': ['youtube-dl'],
556dbe7f 1022 'duration': 10,
dbdaaa23 1023 'view_count': int,
3e7c1224 1024 'like_count': int,
ff9f925b 1025 'availability': 'public',
1026 'playable_in_embed': True,
1027 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1028 'live_status': 'not_live',
1029 'age_limit': 0,
7c80519c 1030 'start_time': 1,
297a564b 1031 'end_time': 9,
6c73052c 1032 'channel_follower_count': int
2eb88d95 1033 }
0e853ca4 1034 },
fccd3771 1035 {
4bc3a23e
PH
1036 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1037 'note': 'Embed-only video (#1746)',
1038 'info_dict': {
1039 'id': 'yZIXLfi8CZQ',
1040 'ext': 'mp4',
1041 'upload_date': '20120608',
1042 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1043 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1044 'uploader': 'SET India',
94bfcd23 1045 'uploader_id': 'setindia',
ec85ded8 1046 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1047 'age_limit': 18,
545cc85d 1048 },
1049 'skip': 'Private video',
fccd3771 1050 },
11b56058 1051 {
8bdd16b4 1052 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1053 'note': 'Use the first video ID in the URL',
1054 'info_dict': {
1055 'id': 'BaW_jenozKc',
1056 'ext': 'mp4',
3867038a 1057 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1058 'uploader': 'Philipp Hagemeister',
1059 'uploader_id': 'phihag',
ec85ded8 1060 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1061 'channel': 'Philipp Hagemeister',
1062 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1063 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1064 'upload_date': '20121002',
976ae3ea 1065 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1066 'categories': ['Science & Technology'],
3867038a 1067 'tags': ['youtube-dl'],
556dbe7f 1068 'duration': 10,
dbdaaa23 1069 'view_count': int,
11b56058 1070 'like_count': int,
976ae3ea 1071 'availability': 'public',
1072 'playable_in_embed': True,
1073 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1074 'live_status': 'not_live',
1075 'age_limit': 0,
6c73052c 1076 'channel_follower_count': int
34a7de29
S
1077 },
1078 'params': {
1079 'skip_download': True,
1080 },
11b56058 1081 },
dd27fd17 1082 {
2d3d2997 1083 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1084 'note': '256k DASH audio (format 141) via DASH manifest',
1085 'info_dict': {
1086 'id': 'a9LDPn-MO4I',
1087 'ext': 'm4a',
1088 'upload_date': '20121002',
1089 'uploader_id': '8KVIDEO',
ec85ded8 1090 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1091 'description': '',
1092 'uploader': '8KVIDEO',
1093 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1094 },
4bc3a23e
PH
1095 'params': {
1096 'youtube_include_dash_manifest': True,
1097 'format': '141',
4919603f 1098 },
de3c7fe0 1099 'skip': 'format 141 not served anymore',
dd27fd17 1100 },
8bdd16b4 1101 # DASH manifest with encrypted signature
1102 {
1103 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1104 'info_dict': {
1105 'id': 'IB3lcPjvWLA',
1106 'ext': 'm4a',
1107 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1108 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1109 'duration': 244,
1110 'uploader': 'AfrojackVEVO',
1111 'uploader_id': 'AfrojackVEVO',
1112 'upload_date': '20131011',
cc2db878 1113 'abr': 129.495,
976ae3ea 1114 'like_count': int,
1115 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1116 'playable_in_embed': True,
1117 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1118 'view_count': int,
1119 'track': 'The Spark',
1120 'live_status': 'not_live',
1121 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1122 'channel': 'Afrojack',
1123 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1124 'tags': 'count:19',
1125 'availability': 'public',
1126 'categories': ['Music'],
1127 'age_limit': 0,
1128 'alt_title': 'The Spark',
6c73052c 1129 'channel_follower_count': int
8bdd16b4 1130 },
1131 'params': {
1132 'youtube_include_dash_manifest': True,
1133 'format': '141/bestaudio[ext=m4a]',
1134 },
1135 },
65c2fde2 1136 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1137 {
65c2fde2 1138 'note': 'Embed allowed age-gate video',
2d3d2997 1139 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1140 'info_dict': {
1141 'id': 'HtVdAasjOgU',
1142 'ext': 'mp4',
1143 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1144 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1145 'duration': 142,
c522adb1
JMF
1146 'uploader': 'The Witcher',
1147 'uploader_id': 'WitcherGame',
ec85ded8 1148 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1149 'upload_date': '20140605',
34952f09 1150 'age_limit': 18,
976ae3ea 1151 'categories': ['Gaming'],
1152 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1153 'availability': 'needs_auth',
1154 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1155 'like_count': int,
1156 'channel': 'The Witcher',
1157 'live_status': 'not_live',
1158 'tags': 'count:17',
1159 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1160 'playable_in_embed': True,
1161 'view_count': int,
6c73052c 1162 'channel_follower_count': int
c522adb1
JMF
1163 },
1164 },
65c2fde2 1165 {
1166 'note': 'Age-gate video with embed allowed in public site',
1167 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1168 'info_dict': {
1169 'id': 'HsUATh_Nc2U',
1170 'ext': 'mp4',
1171 'title': 'Godzilla 2 (Official Video)',
1172 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1173 'upload_date': '20200408',
1174 'uploader_id': 'FlyingKitty900',
1175 'uploader': 'FlyingKitty',
1176 'age_limit': 18,
976ae3ea 1177 'availability': 'needs_auth',
1178 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1179 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1180 'channel': 'FlyingKitty',
1181 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1182 'view_count': int,
1183 'categories': ['Entertainment'],
1184 'live_status': 'not_live',
1185 'tags': ['Flyingkitty', 'godzilla 2'],
1186 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1187 'like_count': int,
1188 'duration': 177,
1189 'playable_in_embed': True,
6c73052c 1190 'channel_follower_count': int
65c2fde2 1191 },
1192 },
1193 {
1194 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1195 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1196 'info_dict': {
1197 'id': 'Tq92D6wQ1mg',
1198 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1199 'ext': 'mp4',
17322130 1200 'upload_date': '20191228',
65c2fde2 1201 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1202 'uploader': 'Projekt Melody',
1203 'description': 'md5:17eccca93a786d51bc67646756894066',
1204 'age_limit': 18,
976ae3ea 1205 'like_count': int,
1206 'availability': 'needs_auth',
1207 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1208 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1209 'view_count': int,
1210 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1211 'channel': 'Projekt Melody',
1212 'live_status': 'not_live',
1213 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1214 'playable_in_embed': True,
1215 'categories': ['Entertainment'],
1216 'duration': 106,
1217 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1218 'channel_follower_count': int
65c2fde2 1219 },
1220 },
1221 {
1222 'note': 'Non-Agegated non-embeddable video',
1223 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1224 'info_dict': {
1225 'id': 'MeJVWBSsPAY',
1226 'ext': 'mp4',
1227 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1228 'uploader': 'Herr Lurik',
1229 'uploader_id': 'st3in234',
1230 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1231 'upload_date': '20130730',
976ae3ea 1232 'track': 'Such mich find mich',
1233 'age_limit': 0,
1234 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1235 'like_count': int,
1236 'playable_in_embed': False,
1237 'creator': 'OOMPH!',
1238 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1239 'view_count': int,
1240 'alt_title': 'Such mich find mich',
1241 'duration': 210,
1242 'channel': 'Herr Lurik',
1243 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1244 'categories': ['Music'],
1245 'availability': 'public',
1246 'uploader_url': 'http://www.youtube.com/user/st3in234',
1247 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1248 'live_status': 'not_live',
1249 'artist': 'OOMPH!',
6c73052c 1250 'channel_follower_count': int
65c2fde2 1251 },
1252 },
1253 {
1254 'note': 'Non-bypassable age-gated video',
1255 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1256 'only_matching': True,
1257 },
8bdd16b4 1258 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1259 # YouTube Red ad is not captured for creator
1260 {
1261 'url': '__2ABJjxzNo',
1262 'info_dict': {
1263 'id': '__2ABJjxzNo',
1264 'ext': 'mp4',
1265 'duration': 266,
1266 'upload_date': '20100430',
1267 'uploader_id': 'deadmau5',
1268 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1269 'creator': 'deadmau5',
1270 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1271 'uploader': 'deadmau5',
1272 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1273 'alt_title': 'Some Chords',
976ae3ea 1274 'availability': 'public',
1275 'tags': 'count:14',
1276 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1277 'view_count': int,
1278 'live_status': 'not_live',
1279 'channel': 'deadmau5',
1280 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1281 'like_count': int,
1282 'track': 'Some Chords',
1283 'artist': 'deadmau5',
1284 'playable_in_embed': True,
1285 'age_limit': 0,
1286 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1287 'categories': ['Music'],
1288 'album': 'Some Chords',
6c73052c 1289 'channel_follower_count': int
8bdd16b4 1290 },
1291 'expected_warnings': [
1292 'DASH manifest missing',
1293 ]
1294 },
067aa17e 1295 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1296 {
1297 'url': 'lqQg6PlCWgI',
1298 'info_dict': {
1299 'id': 'lqQg6PlCWgI',
1300 'ext': 'mp4',
556dbe7f 1301 'duration': 6085,
90227264 1302 'upload_date': '20150827',
cbe2bd91 1303 'uploader_id': 'olympic',
ec85ded8 1304 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1305 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1306 'uploader': 'Olympics',
cbe2bd91 1307 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1308 'like_count': int,
1309 'release_timestamp': 1343767800,
1310 'playable_in_embed': True,
1311 'categories': ['Sports'],
1312 'release_date': '20120731',
1313 'channel': 'Olympics',
1314 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1315 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1316 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1317 'age_limit': 0,
1318 'availability': 'public',
1319 'live_status': 'was_live',
1320 'view_count': int,
1321 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1322 'channel_follower_count': int
cbe2bd91
PH
1323 },
1324 'params': {
1325 'skip_download': 'requires avconv',
e52a40ab 1326 }
cbe2bd91 1327 },
6271f1ca
PH
1328 # Non-square pixels
1329 {
1330 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1331 'info_dict': {
1332 'id': '_b-2C3KPAM0',
1333 'ext': 'mp4',
1334 'stretched_ratio': 16 / 9.,
556dbe7f 1335 'duration': 85,
6271f1ca
PH
1336 'upload_date': '20110310',
1337 'uploader_id': 'AllenMeow',
ec85ded8 1338 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1339 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
eb6793ba 1340 'uploader': '孫ᄋᄅ',
6271f1ca 1341 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1342 'playable_in_embed': True,
1343 'channel': '孫ᄋᄅ',
1344 'age_limit': 0,
1345 'tags': 'count:11',
1346 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1347 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1348 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1349 'view_count': int,
1350 'categories': ['People & Blogs'],
1351 'like_count': int,
1352 'live_status': 'not_live',
1353 'availability': 'unlisted',
6c73052c 1354 'channel_follower_count': int
6271f1ca 1355 },
06b491eb
S
1356 },
1357 # url_encoded_fmt_stream_map is empty string
1358 {
1359 'url': 'qEJwOuvDf7I',
1360 'info_dict': {
1361 'id': 'qEJwOuvDf7I',
f57b7835 1362 'ext': 'webm',
06b491eb
S
1363 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1364 'description': '',
1365 'upload_date': '20150404',
1366 'uploader_id': 'spbelect',
1367 'uploader': 'Наблюдатели Петербурга',
1368 },
1369 'params': {
1370 'skip_download': 'requires avconv',
e323cf3f
S
1371 },
1372 'skip': 'This live event has ended.',
06b491eb 1373 },
067aa17e 1374 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1375 {
1376 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1377 'info_dict': {
1378 'id': 'FIl7x6_3R5Y',
eb6793ba 1379 'ext': 'webm',
da77d856
S
1380 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1381 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1382 'duration': 220,
da77d856
S
1383 'upload_date': '20150625',
1384 'uploader_id': 'dorappi2000',
ec85ded8 1385 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1386 'uploader': 'dorappi2000',
eb6793ba 1387 'formats': 'mincount:31',
da77d856 1388 },
eb6793ba 1389 'skip': 'not actual anymore',
2ee8f5d8 1390 },
8a1a26ce
YCH
1391 # DASH manifest with segment_list
1392 {
1393 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1394 'md5': '8ce563a1d667b599d21064e982ab9e31',
1395 'info_dict': {
1396 'id': 'CsmdDsKjzN8',
1397 'ext': 'mp4',
17ee98e1 1398 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1399 'uploader': 'Airtek',
1400 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1401 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1402 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1403 },
1404 'params': {
1405 'youtube_include_dash_manifest': True,
1406 'format': '135', # bestvideo
be49068d
S
1407 },
1408 'skip': 'This live event has ended.',
2ee8f5d8 1409 },
cf7e015f
S
1410 {
1411 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1412 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1413 'info_dict': {
545cc85d 1414 'id': 'jvGDaLqkpTg',
1415 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1416 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1417 },
1418 'playlist': [{
1419 'info_dict': {
545cc85d 1420 'id': 'jvGDaLqkpTg',
cf7e015f 1421 'ext': 'mp4',
545cc85d 1422 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1423 'description': 'md5:e03b909557865076822aa169218d6a5d',
1424 'duration': 10643,
1425 'upload_date': '20161111',
1426 'uploader': 'Team PGP',
1427 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1428 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1429 },
1430 }, {
1431 'info_dict': {
545cc85d 1432 'id': '3AKt1R1aDnw',
cf7e015f 1433 'ext': 'mp4',
545cc85d 1434 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1435 'description': 'md5:e03b909557865076822aa169218d6a5d',
1436 'duration': 10991,
1437 'upload_date': '20161111',
1438 'uploader': 'Team PGP',
1439 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1440 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1441 },
1442 }, {
1443 'info_dict': {
545cc85d 1444 'id': 'RtAMM00gpVc',
cf7e015f 1445 'ext': 'mp4',
545cc85d 1446 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1447 'description': 'md5:e03b909557865076822aa169218d6a5d',
1448 'duration': 10995,
1449 'upload_date': '20161111',
1450 'uploader': 'Team PGP',
1451 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1452 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1453 },
1454 }, {
1455 'info_dict': {
545cc85d 1456 'id': '6N2fdlP3C5U',
cf7e015f 1457 'ext': 'mp4',
545cc85d 1458 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1459 'description': 'md5:e03b909557865076822aa169218d6a5d',
1460 'duration': 10990,
1461 'upload_date': '20161111',
1462 'uploader': 'Team PGP',
1463 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1464 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1465 },
1466 }],
1467 'params': {
1468 'skip_download': True,
1469 },
65c2fde2 1470 'skip': 'Not multifeed anymore',
cbaed4bb 1471 },
f9f49d87 1472 {
067aa17e 1473 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1474 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1475 'info_dict': {
1476 'id': 'gVfLd0zydlo',
1477 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1478 },
1479 'playlist_count': 2,
be49068d 1480 'skip': 'Not multifeed anymore',
f9f49d87 1481 },
cbaed4bb 1482 {
2d3d2997 1483 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1484 'only_matching': True,
0e49d9a6 1485 },
6d4fc66b 1486 {
2d3d2997 1487 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1488 'only_matching': True,
1489 },
0e49d9a6 1490 {
067aa17e 1491 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1492 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1493 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1494 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1495 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1496 'info_dict': {
1497 'id': 'lsguqyKfVQg',
1498 'ext': 'mp4',
1499 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1500 'alt_title': 'Dark Walk',
0e49d9a6 1501 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1502 'duration': 133,
0e49d9a6
LL
1503 'upload_date': '20151119',
1504 'uploader_id': 'IronSoulElf',
ec85ded8 1505 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1506 'uploader': 'IronSoulElf',
11f9be09 1507 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1508 'track': 'Dark Walk',
1509 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1510 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1511 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1512 'categories': ['Film & Animation'],
1513 'view_count': int,
1514 'live_status': 'not_live',
1515 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1516 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1517 'tags': 'count:13',
1518 'availability': 'public',
1519 'channel': 'IronSoulElf',
1520 'playable_in_embed': True,
1521 'like_count': int,
1522 'age_limit': 0,
6c73052c 1523 'channel_follower_count': int
0e49d9a6
LL
1524 },
1525 'params': {
1526 'skip_download': True,
1527 },
1528 },
61f92af1 1529 {
067aa17e 1530 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1531 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1532 'only_matching': True,
1533 },
313dfc45
LL
1534 {
1535 # Video with yt:stretch=17:0
1536 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1537 'info_dict': {
1538 'id': 'Q39EVAstoRM',
1539 'ext': 'mp4',
1540 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1541 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1542 'upload_date': '20151107',
1543 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1544 'uploader': 'CH GAMER DROID',
1545 },
1546 'params': {
1547 'skip_download': True,
1548 },
be49068d 1549 'skip': 'This video does not exist.',
313dfc45 1550 },
201c1459 1551 {
1552 # Video with incomplete 'yt:stretch=16:'
1553 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1554 'only_matching': True,
1555 },
7caf9830
S
1556 {
1557 # Video licensed under Creative Commons
1558 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1559 'info_dict': {
1560 'id': 'M4gD1WSo5mA',
1561 'ext': 'mp4',
1562 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1563 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1564 'duration': 721,
17322130 1565 'upload_date': '20150128',
7caf9830 1566 'uploader_id': 'BerkmanCenter',
ec85ded8 1567 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1568 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1569 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1570 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1571 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1572 'like_count': int,
1573 'age_limit': 0,
1574 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1575 'channel': 'The Berkman Klein Center for Internet & Society',
1576 'availability': 'public',
1577 'view_count': int,
1578 'categories': ['Education'],
1579 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1580 'live_status': 'not_live',
1581 'playable_in_embed': True,
6c73052c 1582 'channel_follower_count': int
7caf9830
S
1583 },
1584 'params': {
1585 'skip_download': True,
1586 },
1587 },
fd050249
S
1588 {
1589 # Channel-like uploader_url
1590 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1591 'info_dict': {
1592 'id': 'eQcmzGIKrzg',
1593 'ext': 'mp4',
1594 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1595 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1596 'duration': 4060,
17322130 1597 'upload_date': '20151120',
eb6793ba 1598 'uploader': 'Bernie Sanders',
fd050249 1599 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1600 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1601 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1602 'playable_in_embed': True,
1603 'tags': 'count:12',
1604 'like_count': int,
1605 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1606 'age_limit': 0,
1607 'availability': 'public',
1608 'categories': ['News & Politics'],
1609 'channel': 'Bernie Sanders',
1610 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1611 'view_count': int,
1612 'live_status': 'not_live',
1613 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1614 'channel_follower_count': int
fd050249
S
1615 },
1616 'params': {
1617 'skip_download': True,
1618 },
1619 },
040ac686
S
1620 {
1621 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1622 'only_matching': True,
7f29cf54
S
1623 },
1624 {
067aa17e 1625 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1626 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1627 'only_matching': True,
6496ccb4
S
1628 },
1629 {
1630 # Rental video preview
1631 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1632 'info_dict': {
1633 'id': 'uGpuVWrhIzE',
1634 'ext': 'mp4',
1635 'title': 'Piku - Trailer',
1636 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1637 'upload_date': '20150811',
1638 'uploader': 'FlixMatrix',
1639 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1640 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1641 'license': 'Standard YouTube License',
1642 },
1643 'params': {
1644 'skip_download': True,
1645 },
eb6793ba 1646 'skip': 'This video is not available.',
022a5d66 1647 },
12afdc2a
S
1648 {
1649 # YouTube Red video with episode data
1650 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1651 'info_dict': {
1652 'id': 'iqKdEhx-dD4',
1653 'ext': 'mp4',
1654 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1655 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1656 'duration': 2085,
12afdc2a
S
1657 'upload_date': '20170118',
1658 'uploader': 'Vsauce',
1659 'uploader_id': 'Vsauce',
1660 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1661 'series': 'Mind Field',
1662 'season_number': 1,
1663 'episode_number': 1,
976ae3ea 1664 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1665 'tags': 'count:12',
1666 'view_count': int,
1667 'availability': 'public',
1668 'age_limit': 0,
1669 'channel': 'Vsauce',
1670 'episode': 'Episode 1',
1671 'categories': ['Entertainment'],
1672 'season': 'Season 1',
1673 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1674 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1675 'like_count': int,
1676 'playable_in_embed': True,
1677 'live_status': 'not_live',
6c73052c 1678 'channel_follower_count': int
12afdc2a
S
1679 },
1680 'params': {
1681 'skip_download': True,
1682 },
1683 'expected_warnings': [
1684 'Skipping DASH manifest',
1685 ],
1686 },
c7121fa7
S
1687 {
1688 # The following content has been identified by the YouTube community
1689 # as inappropriate or offensive to some audiences.
1690 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1691 'info_dict': {
1692 'id': '6SJNVb0GnPI',
1693 'ext': 'mp4',
1694 'title': 'Race Differences in Intelligence',
1695 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1696 'duration': 965,
1697 'upload_date': '20140124',
1698 'uploader': 'New Century Foundation',
1699 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1700 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1701 },
1702 'params': {
1703 'skip_download': True,
1704 },
545cc85d 1705 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1706 },
022a5d66
S
1707 {
1708 # itag 212
1709 'url': '1t24XAntNCY',
1710 'only_matching': True,
fd5c4aab
S
1711 },
1712 {
1713 # geo restricted to JP
1714 'url': 'sJL6WA-aGkQ',
1715 'only_matching': True,
1716 },
cd5a74a2
S
1717 {
1718 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1719 'only_matching': True,
1720 },
bc2ca1bb 1721 {
1722 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1723 'only_matching': True,
1724 },
1725 {
1726 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1727 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1728 'only_matching': True,
1729 },
825cd268
RA
1730 {
1731 # DRM protected
1732 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1733 'only_matching': True,
4fe54c12
S
1734 },
1735 {
1736 # Video with unsupported adaptive stream type formats
1737 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1738 'info_dict': {
1739 'id': 'Z4Vy8R84T1U',
1740 'ext': 'mp4',
1741 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1742 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1743 'duration': 433,
1744 'upload_date': '20130923',
1745 'uploader': 'Amelia Putri Harwita',
1746 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1747 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1748 'formats': 'maxcount:10',
1749 },
1750 'params': {
1751 'skip_download': True,
1752 'youtube_include_dash_manifest': False,
1753 },
5429d6a9 1754 'skip': 'not actual anymore',
5caabd3c 1755 },
1756 {
822b9d9c 1757 # Youtube Music Auto-generated description
5caabd3c 1758 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1759 'info_dict': {
1760 'id': 'MgNrAu2pzNs',
1761 'ext': 'mp4',
1762 'title': 'Voyeur Girl',
1763 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1764 'upload_date': '20190312',
5429d6a9
S
1765 'uploader': 'Stephen - Topic',
1766 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1767 'artist': 'Stephen',
1768 'track': 'Voyeur Girl',
1769 'album': 'it\'s too much love to know my dear',
1770 'release_date': '20190313',
1771 'release_year': 2019,
976ae3ea 1772 'alt_title': 'Voyeur Girl',
1773 'view_count': int,
1774 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1775 'playable_in_embed': True,
1776 'like_count': int,
1777 'categories': ['Music'],
1778 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1779 'channel': 'Stephen',
1780 'availability': 'public',
1781 'creator': 'Stephen',
1782 'duration': 169,
1783 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1784 'age_limit': 0,
1785 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1786 'tags': 'count:11',
1787 'live_status': 'not_live',
6c73052c 1788 'channel_follower_count': int
5caabd3c 1789 },
1790 'params': {
1791 'skip_download': True,
1792 },
1793 },
66b48727
RA
1794 {
1795 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1796 'only_matching': True,
1797 },
011e75e6
S
1798 {
1799 # invalid -> valid video id redirection
1800 'url': 'DJztXj2GPfl',
1801 'info_dict': {
1802 'id': 'DJztXj2GPfk',
1803 'ext': 'mp4',
1804 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1805 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1806 'upload_date': '20090125',
1807 'uploader': 'Prochorowka',
1808 'uploader_id': 'Prochorowka',
1809 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1810 'artist': 'Panjabi MC',
1811 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1812 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1813 },
1814 'params': {
1815 'skip_download': True,
1816 },
545cc85d 1817 'skip': 'Video unavailable',
ea74e00b
DP
1818 },
1819 {
1820 # empty description results in an empty string
1821 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1822 'info_dict': {
1823 'id': 'x41yOUIvK2k',
1824 'ext': 'mp4',
1825 'title': 'IMG 3456',
1826 'description': '',
1827 'upload_date': '20170613',
1828 'uploader_id': 'ElevageOrVert',
1829 'uploader': 'ElevageOrVert',
976ae3ea 1830 'view_count': int,
1831 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1832 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1833 'like_count': int,
1834 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1835 'tags': [],
1836 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1837 'availability': 'public',
1838 'age_limit': 0,
1839 'categories': ['Pets & Animals'],
1840 'duration': 7,
1841 'playable_in_embed': True,
1842 'live_status': 'not_live',
1843 'channel': 'ElevageOrVert',
6c73052c 1844 'channel_follower_count': int
ea74e00b
DP
1845 },
1846 'params': {
1847 'skip_download': True,
1848 },
1849 },
a0566bbf 1850 {
29f7c58a 1851 # with '};' inside yt initial data (see [1])
1852 # see [2] for an example with '};' inside ytInitialPlayerResponse
1853 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1854 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1855 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1856 'info_dict': {
1857 'id': 'CHqg6qOn4no',
1858 'ext': 'mp4',
1859 'title': 'Part 77 Sort a list of simple types in c#',
1860 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1861 'upload_date': '20130831',
1862 'uploader_id': 'kudvenkat',
1863 'uploader': 'kudvenkat',
976ae3ea 1864 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1865 'like_count': int,
1866 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1867 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1868 'live_status': 'not_live',
1869 'categories': ['Education'],
1870 'availability': 'public',
1871 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1872 'tags': 'count:12',
1873 'playable_in_embed': True,
1874 'age_limit': 0,
1875 'view_count': int,
1876 'duration': 522,
1877 'channel': 'kudvenkat',
6c73052c 1878 'channel_follower_count': int
a0566bbf 1879 },
1880 'params': {
1881 'skip_download': True,
1882 },
1883 },
29f7c58a 1884 {
1885 # another example of '};' in ytInitialData
1886 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1887 'only_matching': True,
1888 },
1889 {
1890 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1891 'only_matching': True,
1892 },
545cc85d 1893 {
cc2db878 1894 # https://github.com/ytdl-org/youtube-dl/pull/28094
1895 'url': 'OtqTfy26tG0',
1896 'info_dict': {
1897 'id': 'OtqTfy26tG0',
1898 'ext': 'mp4',
1899 'title': 'Burn Out',
1900 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1901 'upload_date': '20141120',
1902 'uploader': 'The Cinematic Orchestra - Topic',
1903 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1904 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1905 'artist': 'The Cinematic Orchestra',
1906 'track': 'Burn Out',
1907 'album': 'Every Day',
976ae3ea 1908 'like_count': int,
1909 'live_status': 'not_live',
1910 'alt_title': 'Burn Out',
1911 'duration': 614,
1912 'age_limit': 0,
1913 'view_count': int,
1914 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1915 'creator': 'The Cinematic Orchestra',
1916 'channel': 'The Cinematic Orchestra',
1917 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1918 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1919 'availability': 'public',
1920 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1921 'categories': ['Music'],
1922 'playable_in_embed': True,
6c73052c 1923 'channel_follower_count': int
cc2db878 1924 },
1925 'params': {
1926 'skip_download': True,
1927 },
545cc85d 1928 },
bc2ca1bb 1929 {
1930 # controversial video, only works with bpctr when authenticated with cookies
1931 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1932 'only_matching': True,
1933 },
a1a7907b 1934 {
1935 # controversial video, requires bpctr/contentCheckOk
1936 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1937 'info_dict': {
1938 'id': 'SZJvDhaSDnc',
1939 'ext': 'mp4',
1940 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1941 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1942 'uploader': 'CBS Mornings',
11f9be09 1943 'uploader_id': 'CBSThisMorning',
a1a7907b 1944 'upload_date': '20140716',
976ae3ea 1945 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1946 'duration': 170,
1947 'categories': ['News & Politics'],
1948 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1949 'view_count': int,
1950 'channel': 'CBS Mornings',
1951 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1952 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1953 'age_limit': 18,
1954 'availability': 'needs_auth',
1955 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1956 'like_count': int,
1957 'live_status': 'not_live',
1958 'playable_in_embed': True,
6c73052c 1959 'channel_follower_count': int
a1a7907b 1960 }
1961 },
f7ad7160 1962 {
1963 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1964 'url': 'cBvYw8_A0vQ',
1965 'info_dict': {
1966 'id': 'cBvYw8_A0vQ',
1967 'ext': 'mp4',
1968 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1969 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1970 'upload_date': '20201120',
1971 'uploader': 'Walk around Japan',
1972 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1973 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1974 'duration': 1456,
1975 'categories': ['Travel & Events'],
1976 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1977 'view_count': int,
1978 'channel': 'Walk around Japan',
1979 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1980 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1981 'age_limit': 0,
1982 'availability': 'public',
1983 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1984 'live_status': 'not_live',
1985 'playable_in_embed': True,
6c73052c 1986 'channel_follower_count': int
f7ad7160 1987 },
1988 'params': {
1989 'skip_download': True,
1990 },
0fb983f6 1991 }, {
1992 # Has multiple audio streams
1993 'url': 'WaOKSUlf4TM',
1994 'only_matching': True
9297939e 1995 }, {
1996 # Requires Premium: has format 141 when requested using YTM url
1997 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1998 'only_matching': True
1999 }, {
120916da 2000 # multiple subtitles with same lang_code
2001 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2002 'only_matching': True,
109dd3b2 2003 }, {
2004 # Force use android client fallback
2005 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2006 'info_dict': {
2007 'id': 'YOelRv7fMxY',
11f9be09 2008 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2009 'ext': '3gp',
2010 'upload_date': '20210624',
2011 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2012 'uploader': 'colinfurze',
11f9be09 2013 'uploader_id': 'colinfurze',
109dd3b2 2014 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2015 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2016 'duration': 596,
2017 'categories': ['Entertainment'],
2018 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2019 'view_count': int,
2020 'channel': 'colinfurze',
2021 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2022 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2023 'age_limit': 0,
2024 'availability': 'public',
2025 'like_count': int,
2026 'live_status': 'not_live',
2027 'playable_in_embed': True,
6c73052c 2028 'channel_follower_count': int
109dd3b2 2029 },
2030 'params': {
2031 'format': '17', # 3gp format available on android
2032 'extractor_args': {'youtube': {'player_client': ['android']}},
2033 },
120916da 2034 },
109dd3b2 2035 {
2036 # Skip download of additional client configs (remix client config in this case)
2037 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2038 'only_matching': True,
2039 'params': {
2040 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2041 },
8fc54b12 2042 }, {
2043 # shorts
2044 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2045 'only_matching': True,
9222c381 2046 }, {
2047 'note': 'Storyboards',
2048 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2049 'info_dict': {
2050 'id': '5KLPxDtMqe8',
2051 'ext': 'mhtml',
2052 'format_id': 'sb0',
2053 'title': 'Your Brain is Plastic',
2054 'uploader_id': 'scishow',
2055 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2056 'upload_date': '20140324',
2057 'uploader': 'SciShow',
976ae3ea 2058 'like_count': int,
2059 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2060 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2061 'view_count': int,
2062 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2063 'playable_in_embed': True,
2064 'tags': 'count:12',
2065 'uploader_url': 'http://www.youtube.com/user/scishow',
2066 'availability': 'public',
2067 'channel': 'SciShow',
2068 'live_status': 'not_live',
2069 'duration': 248,
2070 'categories': ['Education'],
2071 'age_limit': 0,
6c73052c 2072 'channel_follower_count': int
9222c381 2073 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2074 }, {
2075 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2076 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2077 'info_dict': {
2078 'id': '2NUZ8W2llS4',
2079 'ext': 'mp4',
2080 'title': 'The NP that test your phone performance 🙂',
2081 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2082 'uploader': 'Leon Nguyen',
2083 'uploader_id': 'VNSXIII',
2084 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2085 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2086 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2087 'duration': 21,
2088 'view_count': int,
2089 'age_limit': 0,
2090 'categories': ['Gaming'],
2091 'tags': 'count:23',
2092 'playable_in_embed': True,
2093 'live_status': 'not_live',
2094 'upload_date': '20220103',
2095 'like_count': int,
2096 'availability': 'public',
2097 'channel': 'Leon Nguyen',
2098 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2099 'channel_follower_count': int
2100 }
2101 }, {
2102 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2103 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2104 'info_dict': {
2105 'id': 'mzZzzBU6lrM',
2106 'ext': 'mp4',
2107 'title': 'I Met GeorgeNotFound In Real Life...',
2108 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2109 'uploader': 'Quackity',
2110 'uploader_id': 'QuackityHQ',
2111 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2112 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2113 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2114 'duration': 955,
2115 'view_count': int,
2116 'age_limit': 0,
2117 'categories': ['Entertainment'],
2118 'tags': 'count:26',
2119 'playable_in_embed': True,
2120 'live_status': 'not_live',
2121 'release_timestamp': 1641172509,
2122 'release_date': '20220103',
2123 'upload_date': '20220103',
2124 'like_count': int,
2125 'availability': 'public',
2126 'channel': 'Quackity',
2127 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2128 'channel_follower_count': int
2129 }
2130 },
2131 { # continuous livestream. Microformat upload date should be preferred.
2132 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2133 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2134 'info_dict': {
2135 'id': 'kgx4WGK0oNU',
2136 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2137 'ext': 'mp4',
2138 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2139 'availability': 'public',
2140 'age_limit': 0,
2141 'release_timestamp': 1637975704,
2142 'upload_date': '20210619',
2143 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2144 'live_status': 'is_live',
2145 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2146 'uploader': '阿鲍Abao',
2147 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2148 'channel': 'Abao in Tokyo',
2149 'channel_follower_count': int,
2150 'release_date': '20211127',
2151 'tags': 'count:39',
2152 'categories': ['People & Blogs'],
2153 'like_count': int,
2154 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2155 'view_count': int,
2156 'playable_in_embed': True,
2157 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2158 },
2159 'params': {'skip_download': True}
2160 },
2eb88d95
PH
2161 ]
2162
201c1459 2163 @classmethod
2164 def suitable(cls, url):
4dfbf869 2165 from ..utils import parse_qs
2166
201c1459 2167 qs = parse_qs(url)
2168 if qs.get('list', [None])[0]:
2169 return False
2170 return super(YoutubeIE, cls).suitable(url)
2171
e0df6211
PH
2172 def __init__(self, *args, **kwargs):
2173 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2174 self._code_cache = {}
83799698 2175 self._player_cache = {}
e0df6211 2176
adbc4ec4 2177 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2178 lock = threading.Lock()
2179
2180 is_live = True
185bf310 2181 start_time = time.time()
adbc4ec4
THD
2182 formats = [f for f in formats if f.get('is_from_start')]
2183
185bf310 2184 def refetch_manifest(format_id, delay):
2185 nonlocal formats, start_time, is_live
2186 if time.time() <= start_time + delay:
adbc4ec4
THD
2187 return
2188
2189 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2190 video_details = traverse_obj(
2191 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2192 microformats = traverse_obj(
2193 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2194 expected_type=dict, default=[])
2195 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2196 start_time = time.time()
adbc4ec4 2197
185bf310 2198 def mpd_feed(format_id, delay):
adbc4ec4
THD
2199 """
2200 @returns (manifest_url, manifest_stream_number, is_live) or None
2201 """
2202 with lock:
185bf310 2203 refetch_manifest(format_id, delay)
adbc4ec4
THD
2204
2205 f = next((f for f in formats if f['format_id'] == format_id), None)
2206 if not f:
185bf310 2207 if not is_live:
2208 self.to_screen(f'{video_id}: Video is no longer live')
2209 else:
2210 self.report_warning(
2211 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2212 return None
2213 return f['manifest_url'], f['manifest_stream_number'], is_live
2214
2215 for f in formats:
a539f065 2216 f['is_live'] = True
adbc4ec4
THD
2217 f['protocol'] = 'http_dash_segments_generator'
2218 f['fragments'] = functools.partial(
2219 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2220
2221 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2222 FETCH_SPAN, MAX_DURATION = 5, 432000
2223
2224 mpd_url, stream_number, is_live = None, None, True
2225
2226 begin_index = 0
2227 download_start_time = ctx.get('start') or time.time()
2228
2229 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2230 if lack_early_segments:
2231 self.report_warning(bug_reports_message(
2232 'Starting download from the last 120 hours of the live stream since '
2233 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2234 lack_early_segments = True
2235
2236 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2237 fragments, fragment_base_url = None, None
2238
a539f065 2239 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2240 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2241 # Obtain from MPD's maximum seq value
2242 old_mpd_url = mpd_url
185bf310 2243 last_error = ctx.pop('last_error', None)
a539f065 2244 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2245 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2246 or (mpd_url, stream_number, False))
2247 if not refresh_sequence:
2248 if expire_fast and not is_live:
2249 return False, last_seq
2250 elif old_mpd_url == mpd_url:
2251 return True, last_seq
adbc4ec4
THD
2252 try:
2253 fmts, _ = self._extract_mpd_formats_and_subtitles(
2254 mpd_url, None, note=False, errnote=False, fatal=False)
2255 except ExtractorError:
2256 fmts = None
2257 if not fmts:
a539f065 2258 no_fragment_score += 2
adbc4ec4
THD
2259 return False, last_seq
2260 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2261 fragments = fmt_info['fragments']
2262 fragment_base_url = fmt_info['fragment_base_url']
2263 assert fragment_base_url
2264
2265 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2266 return True, _last_seq
2267
2268 while is_live:
2269 fetch_time = time.time()
2270 if no_fragment_score > 30:
2271 return
2272 if last_segment_url:
2273 # Obtain from "X-Head-Seqnum" header value from each segment
2274 try:
2275 urlh = self._request_webpage(
2276 last_segment_url, None, note=False, errnote=False, fatal=False)
2277 except ExtractorError:
2278 urlh = None
2279 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2280 if last_seq is None:
a539f065 2281 no_fragment_score += 2
adbc4ec4
THD
2282 last_segment_url = None
2283 continue
2284 else:
a539f065
LNO
2285 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2286 no_fragment_score += 2
185bf310 2287 if not should_continue:
adbc4ec4
THD
2288 continue
2289
2290 if known_idx > last_seq:
2291 last_segment_url = None
2292 continue
2293
2294 last_seq += 1
2295
2296 if begin_index < 0 and known_idx < 0:
2297 # skip from the start when it's negative value
2298 known_idx = last_seq + begin_index
2299 if lack_early_segments:
2300 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2301 try:
2302 for idx in range(known_idx, last_seq):
2303 # do not update sequence here or you'll get skipped some part of it
a539f065 2304 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2305 if not should_continue:
adbc4ec4
THD
2306 known_idx = idx - 1
2307 raise ExtractorError('breaking out of outer loop')
2308 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2309 yield {
2310 'url': last_segment_url,
2311 }
2312 if known_idx == last_seq:
2313 no_fragment_score += 5
2314 else:
2315 no_fragment_score = 0
2316 known_idx = last_seq
2317 except ExtractorError:
2318 continue
2319
2320 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2321
b6de707d 2322 def _extract_player_url(self, *ytcfgs, webpage=None):
2323 player_url = traverse_obj(
2324 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2325 get_all=False, expected_type=compat_str)
11f9be09 2326 if not player_url:
b6de707d 2327 return
60f393e4 2328 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2329
b6de707d 2330 def _download_player_url(self, video_id, fatal=False):
2331 res = self._download_webpage(
2332 'https://www.youtube.com/iframe_api',
2333 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2334 if res:
2335 player_version = self._search_regex(
2336 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2337 if player_version:
2338 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2339
60064c53
PH
2340 def _signature_cache_id(self, example_sig):
2341 """ Return a string representation of a signature """
78caa52a 2342 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2343
e40c758c
S
2344 @classmethod
2345 def _extract_player_info(cls, player_url):
2346 for player_re in cls._PLAYER_INFO_RE:
2347 id_m = re.search(player_re, player_url)
2348 if id_m:
2349 break
2350 else:
c081b35c 2351 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2352 return id_m.group('id')
e40c758c 2353
404f611f 2354 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2355 player_id = self._extract_player_info(player_url)
2356 if player_id not in self._code_cache:
1276a43a 2357 code = self._download_webpage(
109dd3b2 2358 player_url, video_id, fatal=fatal,
2359 note='Downloading player ' + player_id,
2360 errnote='Download of %s failed' % player_url)
1276a43a 2361 if code:
2362 self._code_cache[player_id] = code
404f611f 2363 return self._code_cache.get(player_id)
109dd3b2 2364
e40c758c 2365 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2366 player_id = self._extract_player_info(player_url)
e0df6211 2367
c4417ddb 2368 # Read from filesystem cache
545cc85d 2369 func_id = 'js_%s_%s' % (
2370 player_id, self._signature_cache_id(example_sig))
c4417ddb 2371 assert os.path.basename(func_id) == func_id
a0e07d31 2372
69ea8ca4 2373 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2374 if cache_spec is not None:
78caa52a 2375 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2376
404f611f 2377 code = self._load_player(video_id, player_url)
2378 if code:
109dd3b2 2379 res = self._parse_sig_js(code)
e0df6211 2380
109dd3b2 2381 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2382 cache_res = res(test_string)
2383 cache_spec = [ord(c) for c in cache_res]
83799698 2384
109dd3b2 2385 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2386 return res
83799698 2387
60064c53 2388 def _print_sig_code(self, func, example_sig):
404f611f 2389 if not self.get_param('youtube_print_sig_code'):
2390 return
2391
edf3e38e
PH
2392 def gen_sig_code(idxs):
2393 def _genslice(start, end, step):
78caa52a 2394 starts = '' if start == 0 else str(start)
8bcc8756 2395 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2396 steps = '' if step == 1 else (':%d' % step)
78caa52a 2397 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2398
2399 step = None
7af808a5
PH
2400 # Quelch pyflakes warnings - start will be set when step is set
2401 start = '(Never used)'
edf3e38e
PH
2402 for i, prev in zip(idxs[1:], idxs[:-1]):
2403 if step is not None:
2404 if i - prev == step:
2405 continue
2406 yield _genslice(start, prev, step)
2407 step = None
2408 continue
2409 if i - prev in [-1, 1]:
2410 step = i - prev
2411 start = prev
2412 continue
2413 else:
78caa52a 2414 yield 's[%d]' % prev
edf3e38e 2415 if step is None:
78caa52a 2416 yield 's[%d]' % i
edf3e38e
PH
2417 else:
2418 yield _genslice(start, i, step)
2419
78caa52a 2420 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2421 cache_res = func(test_string)
edf3e38e 2422 cache_spec = [ord(c) for c in cache_res]
78caa52a 2423 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2424 signature_id_tuple = '(%s)' % (
2425 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2426 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2427 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2428 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2429
e0df6211
PH
2430 def _parse_sig_js(self, jscode):
2431 funcname = self._search_regex(
abefc03f
S
2432 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2433 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
858a65ec
P
2434 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2435 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2436 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
2437 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 2438 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2439 # Obsolete patterns
2440 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2441 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2442 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2443 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2444 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2445 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2446 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2447 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2448 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2449
2450 jsi = JSInterpreter(jscode)
2451 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2452 return lambda s: initial_function([s])
2453
545cc85d 2454 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2455 """Turn the encrypted s field into a working signature"""
6b37f0be 2456
c8bf86d5 2457 if player_url is None:
69ea8ca4 2458 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2459
c8bf86d5 2460 try:
62af3a0e 2461 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2462 if player_id not in self._player_cache:
2463 func = self._extract_signature_function(
60064c53 2464 video_id, player_url, s
c8bf86d5
PH
2465 )
2466 self._player_cache[player_id] = func
2467 func = self._player_cache[player_id]
404f611f 2468 self._print_sig_code(func, s)
c8bf86d5
PH
2469 return func(s)
2470 except Exception as e:
404f611f 2471 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2472
2473 def _decrypt_nsig(self, s, video_id, player_url):
2474 """Turn the encrypted n field into a working signature"""
2475 if player_url is None:
2476 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2477 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2478
2479 sig_id = ('nsig_value', s)
2480 if sig_id in self._player_cache:
2481 return self._player_cache[sig_id]
2482
2483 try:
2484 player_id = ('nsig', player_url)
2485 if player_id not in self._player_cache:
2486 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2487 func = self._player_cache[player_id]
2488 self._player_cache[sig_id] = func(s)
2489 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2490 return self._player_cache[sig_id]
2491 except Exception as e:
aa9369a2 2492 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2493
2494 def _extract_n_function_name(self, jscode):
48416bc4 2495 nfunc, idx = self._search_regex(
c571b3a6 2496 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2497 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2498 if not idx:
2499 return nfunc
2500 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2501 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2502 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2503
2504 def _extract_n_function(self, video_id, player_url):
2505 player_id = self._extract_player_info(player_url)
2506 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2507
2508 if func_code:
2509 jsi = JSInterpreter(func_code)
2510 else:
2511 jscode = self._load_player(video_id, player_url)
2512 funcname = self._extract_n_function_name(jscode)
2513 jsi = JSInterpreter(jscode)
2514 func_code = jsi.extract_function_code(funcname)
2515 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2516
2517 if self.get_param('youtube_print_sig_code'):
2518 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2519
2520 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2521
109dd3b2 2522 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2523 """
2524 Extract signatureTimestamp (sts)
2525 Required to tell API what sig/player version is in use.
2526 """
2527 sts = None
2528 if isinstance(ytcfg, dict):
2529 sts = int_or_none(ytcfg.get('STS'))
2530
2531 if not sts:
2532 # Attempt to extract from player
2533 if player_url is None:
2534 error_msg = 'Cannot extract signature timestamp without player_url.'
2535 if fatal:
2536 raise ExtractorError(error_msg)
2537 self.report_warning(error_msg)
2538 return
404f611f 2539 code = self._load_player(video_id, player_url, fatal=fatal)
2540 if code:
109dd3b2 2541 sts = int_or_none(self._search_regex(
2542 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2543 'JS player signature timestamp', group='sts', fatal=fatal))
2544 return sts
2545
11f9be09 2546 def _mark_watched(self, video_id, player_responses):
9222c381 2547 playback_url = get_first(
2548 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2549 expected_type=url_or_none)
d77ab8e2 2550 if not playback_url:
352d63fd 2551 self.report_warning('Unable to mark watched')
d77ab8e2
S
2552 return
2553 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2554 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2555
2556 # cpn generation algorithm is reverse engineered from base.js.
2557 # In fact it works even with dummy cpn.
2558 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2559 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2560
2561 qs.update({
2562 'ver': ['2'],
2563 'cpn': [cpn],
2564 })
2565 playback_url = compat_urlparse.urlunparse(
15707c7e 2566 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2567
2568 self._download_webpage(
2569 playback_url, video_id, 'Marking watched',
2570 'Unable to mark watched', fatal=False)
2571
66c9fa36
S
2572 @staticmethod
2573 def _extract_urls(webpage):
2574 # Embedded YouTube player
2575 entries = [
2576 unescapeHTML(mobj.group('url'))
2577 for mobj in re.finditer(r'''(?x)
2578 (?:
2579 <iframe[^>]+?src=|
2580 data-video-url=|
2581 <embed[^>]+?src=|
2582 embedSWF\(?:\s*|
2583 <object[^>]+data=|
2584 new\s+SWFObject\(
2585 )
2586 (["\'])
2587 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2588 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2589 \1''', webpage)]
2590
2591 # lazyYT YouTube embed
2592 entries.extend(list(map(
2593 unescapeHTML,
2594 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2595
2596 # Wordpress "YouTube Video Importer" plugin
2597 matches = re.findall(r'''(?x)<div[^>]+
2598 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2599 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2600 entries.extend(m[-1] for m in matches)
2601
2602 return entries
2603
2604 @staticmethod
2605 def _extract_url(webpage):
2606 urls = YoutubeIE._extract_urls(webpage)
2607 return urls[0] if urls else None
2608
97665381
PH
2609 @classmethod
2610 def extract_id(cls, url):
2611 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2612 if mobj is None:
69ea8ca4 2613 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2614 return mobj.group('id')
c5e8d7af 2615
7c365c21 2616 def _extract_chapters_from_json(self, data, duration):
2617 chapter_list = traverse_obj(
2618 data, (
2619 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2620 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2621 ), expected_type=list)
2622
2623 return self._extract_chapters(
2624 chapter_list,
2625 chapter_time=lambda chapter: float_or_none(
2626 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2627 chapter_title=lambda chapter: traverse_obj(
2628 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2629 duration=duration)
2630
2631 def _extract_chapters_from_engagement_panel(self, data, duration):
2632 content_list = traverse_obj(
8bdd16b4 2633 data,
7c365c21 2634 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2635 expected_type=list, default=[])
052e1350 2636 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2637 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2638
2639 return next((
2640 filter(None, (
2641 self._extract_chapters(
2642 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2643 chapter_time, chapter_title, duration)
2644 for contents in content_list
2645 ))), [])
2646
2647 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2648 chapters = []
7c365c21 2649 last_chapter = {'start_time': 0}
2650 for idx, chapter in enumerate(chapter_list or []):
2651 title = chapter_title(chapter)
84213ea8
S
2652 start_time = chapter_time(chapter)
2653 if start_time is None:
2654 continue
7c365c21 2655 last_chapter['end_time'] = start_time
2656 if start_time < last_chapter['start_time']:
2657 if idx == 1:
2658 chapters.pop()
2659 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2660 else:
2661 self.report_warning(f'Invalid start time for chapter "{title}"')
2662 continue
2663 last_chapter = {'start_time': start_time, 'title': title}
2664 chapters.append(last_chapter)
2665 last_chapter['end_time'] = duration
84213ea8
S
2666 return chapters
2667
545cc85d 2668 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2669 return self._parse_json(self._search_regex(
2670 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2671 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2672
a1c5d2ca
M
2673 def _extract_comment(self, comment_renderer, parent=None):
2674 comment_id = comment_renderer.get('commentId')
2675 if not comment_id:
2676 return
fe93e2c4 2677
052e1350 2678 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2679
49bd8c66 2680 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2681 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2682 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2683 author_id = try_get(comment_renderer,
2684 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2685
49bd8c66 2686 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2687 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2688 author_thumbnail = try_get(comment_renderer,
2689 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2690
2691 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2692 is_favorited = 'creatorHeart' in (try_get(
2693 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2694 return {
2695 'id': comment_id,
2696 'text': text,
d92f5d5a 2697 'timestamp': timestamp,
a1c5d2ca
M
2698 'time_text': time_text,
2699 'like_count': votes,
97524332 2700 'is_favorited': is_favorited,
a1c5d2ca
M
2701 'author': author,
2702 'author_id': author_id,
2703 'author_thumbnail': author_thumbnail,
2704 'author_is_uploader': author_is_uploader,
2705 'parent': parent or 'root'
2706 }
2707
46383212 2708 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2709
2710 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2711
2712 def extract_header(contents):
2d6659b9 2713 _continuation = None
2714 for content in contents:
46383212 2715 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2716 expected_comment_count = self._get_count(
2717 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2718
2d6659b9 2719 if expected_comment_count:
46383212 2720 tracker['est_total'] = expected_comment_count
2721 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2722 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2723
2724 sort_menu_item = try_get(
2725 comments_header_renderer,
2726 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2727 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2728
2729 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2730 if not _continuation:
2731 continue
2732
46383212 2733 sort_text = str_or_none(sort_menu_item.get('title'))
2734 if not sort_text:
2d6659b9 2735 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2736 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2737 break
a2160aa4 2738 return _continuation
a1c5d2ca 2739
2d6659b9 2740 def extract_thread(contents):
a1c5d2ca 2741 if not parent:
46383212 2742 tracker['current_page_thread'] = 0
a1c5d2ca 2743 for content in contents:
46383212 2744 if not parent and tracker['total_parent_comments'] >= max_parents:
2745 yield
a1c5d2ca 2746 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2747 comment_renderer = get_first(
2748 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2749 expected_type=dict, default={})
a1c5d2ca 2750
a1c5d2ca
M
2751 comment = self._extract_comment(comment_renderer, parent)
2752 if not comment:
2753 continue
46383212 2754
2755 tracker['running_total'] += 1
2756 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2757 yield comment
46383212 2758
a1c5d2ca
M
2759 # Attempt to get the replies
2760 comment_replies_renderer = try_get(
2761 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2762
2763 if comment_replies_renderer:
46383212 2764 tracker['current_page_thread'] += 1
a1c5d2ca 2765 comment_entries_iter = self._comment_entries(
99e9e001 2766 comment_replies_renderer, ytcfg, video_id,
46383212 2767 parent=comment.get('id'), tracker=tracker)
2768 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2769 yield reply_comment
2770
46383212 2771 # Keeps track of counts across recursive calls
2772 if not tracker:
2773 tracker = dict(
2774 running_total=0,
2775 est_total=0,
2776 current_page_thread=0,
2777 total_parent_comments=0,
2778 total_reply_comments=0)
2779
2780 # TODO: Deprecated
2d6659b9 2781 # YouTube comments have a max depth of 2
46383212 2782 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2783 if max_depth:
2784 self._downloader.deprecation_warning(
2785 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2786 if max_depth == 1 and parent:
2787 return
a1c5d2ca 2788
46383212 2789 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2790 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2791
46383212 2792 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2793 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2794 if message and not parent:
2795 self.report_warning(message, video_id=video_id)
2796
46383212 2797 response = None
2d6659b9 2798 is_first_continuation = parent is None
a1c5d2ca
M
2799
2800 for page_num in itertools.count(0):
2801 if not continuation:
2802 break
46383212 2803 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2804 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2805 if page_num == 0:
2806 if is_first_continuation:
2807 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2808 else:
2d6659b9 2809 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2810 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2811 else:
2812 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2813 ' ' if parent else '', ' replies' if parent else '',
2814 page_num, comment_prog_str)
2815
2816 response = self._extract_response(
fe93e2c4 2817 item_id=None, query=continuation,
2d6659b9 2818 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2819 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2820
46383212 2821 continuation_contents = traverse_obj(
2822 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2823
2d6659b9 2824 continuation = None
46383212 2825 for continuation_section in continuation_contents:
2826 continuation_items = traverse_obj(
2827 continuation_section,
2828 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2829 get_all=False, expected_type=list) or []
2830 if is_first_continuation:
2831 continuation = extract_header(continuation_items)
2832 is_first_continuation = False
2d6659b9 2833 if continuation:
a1c5d2ca 2834 break
46383212 2835 continue
a1c5d2ca 2836
46383212 2837 for entry in extract_thread(continuation_items):
2838 if not entry:
2839 return
2840 yield entry
2841 continuation = self._extract_continuation({'contents': continuation_items})
2842 if continuation:
2d6659b9 2843 break
a1c5d2ca 2844
a2160aa4 2845 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2846 """Entry for comment extraction"""
2d6659b9 2847 def _real_comment_extract(contents):
aae16f6e 2848 renderer = next((
2849 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2850 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2851 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2852
a2160aa4 2853 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2854 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2855
109dd3b2 2856 @staticmethod
99e9e001 2857 def _get_checkok_params():
2858 return {'contentCheckOk': True, 'racyCheckOk': True}
2859
2860 @classmethod
2861 def _generate_player_context(cls, sts=None):
109dd3b2 2862 context = {
2863 'html5Preference': 'HTML5_PREF_WANTS',
2864 }
2865 if sts is not None:
2866 context['signatureTimestamp'] = sts
2867 return {
2868 'playbackContext': {
2869 'contentPlaybackContext': context
a1a7907b 2870 },
99e9e001 2871 **cls._get_checkok_params()
109dd3b2 2872 }
2873
e7e94f2a
D
2874 @staticmethod
2875 def _is_agegated(player_response):
2876 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2877 return True
e7e94f2a
D
2878
2879 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2880 AGE_GATE_REASONS = (
2881 'confirm your age', 'age-restricted', 'inappropriate', # reason
2882 'age_verification_required', 'age_check_required', # status
2883 )
2884 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2885
2886 @staticmethod
2887 def _is_unplayable(player_response):
2888 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2889
99e9e001 2890 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2891
11f9be09 2892 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2893 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2894 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2895 headers = self.generate_api_headers(
99e9e001 2896 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2897
11f9be09 2898 yt_query = {'videoId': video_id}
2899 yt_query.update(self._generate_player_context(sts))
2900 return self._extract_response(
2901 item_id=video_id, ep='player', query=yt_query,
379e44ed 2902 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2903 default_client=client,
11f9be09 2904 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2905 ) or None
2906
11f9be09 2907 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2908 requested_clients = []
d0d012d4 2909 default = ['android', 'web']
000c15a4 2910 allowed_clients = sorted(
2911 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2912 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2913 for client in self._configuration_arg('player_client'):
2914 if client in allowed_clients:
2915 requested_clients.append(client)
d0d012d4 2916 elif client == 'default':
2917 requested_clients.extend(default)
b4c055ba 2918 elif client == 'all':
2919 requested_clients.extend(allowed_clients)
2920 else:
2921 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2922 if not requested_clients:
d0d012d4 2923 requested_clients = default
cf7e015f 2924
11f9be09 2925 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2926 requested_clients.extend(
e7e94f2a 2927 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2928
11f9be09 2929 return orderedSet(requested_clients)
cf7e015f 2930
c0bc527b
M
2931 def _extract_player_ytcfg(self, client, video_id):
2932 url = {
2933 'web_music': 'https://music.youtube.com',
2934 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2935 }.get(client)
2936 if not url:
2937 return {}
18c7683d 2938 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2939 return self.extract_ytcfg(video_id, webpage) or {}
2940
99e9e001 2941 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2942 initial_pr = None
2943 if webpage:
2944 initial_pr = self._extract_yt_initial_variable(
2945 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2946 video_id, 'initial player response')
6b09401b 2947
ae729626 2948 all_clients = set(clients)
c0bc527b 2949 clients = clients[::-1]
b6de707d 2950 prs = []
e7e94f2a 2951
ae729626 2952 def append_client(*client_names):
2953 """ Append the first client name that exists """
2954 for client_name in client_names:
2955 if client_name in INNERTUBE_CLIENTS:
2956 if client_name not in all_clients:
2957 clients.append(client_name)
2958 all_clients.add(client_name)
2959 return
e7e94f2a 2960
379e44ed 2961 # Android player_response does not have microFormats which are needed for
2962 # extraction of some data. So we return the initial_pr with formats
2963 # stripped out even if not requested by the user
2964 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2965 if initial_pr:
2966 pr = dict(initial_pr)
2967 pr['streamingData'] = None
b6de707d 2968 prs.append(pr)
379e44ed 2969
2970 last_error = None
b6de707d 2971 tried_iframe_fallback = False
2972 player_url = None
c0bc527b
M
2973 while clients:
2974 client = clients.pop()
11f9be09 2975 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2976 if 'configs' not in self._configuration_arg('player_skip'):
2977 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2978
b6de707d 2979 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2980 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2981 if 'js' in self._configuration_arg('player_skip'):
2982 require_js_player = False
2983 player_url = None
2984
2985 if not player_url and not tried_iframe_fallback and require_js_player:
2986 player_url = self._download_player_url(video_id)
2987 tried_iframe_fallback = True
2988
379e44ed 2989 try:
2990 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2991 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2992 except ExtractorError as e:
2993 if last_error:
2994 self.report_warning(last_error)
2995 last_error = e
2996 continue
2997
11f9be09 2998 if pr:
b6de707d 2999 prs.append(pr)
c0bc527b 3000
e7e94f2a 3001 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 3002 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
3003 append_client(client.replace('_agegate', '_creator'))
3004 elif self._is_agegated(pr):
ae729626 3005 append_client(f'{client}_embedded', f'{client.replace("_embedded", "")}_agegate')
c0bc527b 3006
379e44ed 3007 if last_error:
b6de707d 3008 if not len(prs):
379e44ed 3009 raise last_error
3010 self.report_warning(last_error)
b6de707d 3011 return prs, player_url
11f9be09 3012
a1b2d843 3013 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3014 itags, stream_ids = {}, []
2a9c6dcd 3015 itag_qualities, res_qualities = {}, {}
d3fc8074 3016 q = qualities([
2a9c6dcd 3017 # Normally tiny is the smallest video-only formats. But
3018 # audio-only formats with unknown quality may get tagged as tiny
3019 'tiny',
3020 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3021 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3022 ])
11f9be09 3023 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3024
545cc85d 3025 for fmt in streaming_formats:
727029c5 3026 if fmt.get('targetDurationSec'):
545cc85d 3027 continue
321bf820 3028
cc2db878 3029 itag = str_or_none(fmt.get('itag'))
9297939e 3030 audio_track = fmt.get('audioTrack') or {}
3031 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3032 if stream_id in stream_ids:
3033 continue
3034
cc2db878 3035 quality = fmt.get('quality')
2a9c6dcd 3036 height = int_or_none(fmt.get('height'))
d3fc8074 3037 if quality == 'tiny' or not quality:
3038 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3039 # The 3gp format (17) in android client has a quality of "small",
3040 # but is actually worse than other formats
3041 if itag == '17':
3042 quality = 'tiny'
3043 if quality:
3044 if itag:
3045 itag_qualities[itag] = quality
3046 if height:
3047 res_qualities[height] = quality
cc2db878 3048 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3049 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3050 # number of fragment that would subsequently requested with (`&sq=N`)
3051 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3052 continue
3053
545cc85d 3054 fmt_url = fmt.get('url')
3055 if not fmt_url:
3056 sc = compat_parse_qs(fmt.get('signatureCipher'))
3057 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3058 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3059 if not (sc and fmt_url and encrypted_sig):
3060 continue
545cc85d 3061 if not player_url:
201e9eaa 3062 continue
545cc85d 3063 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3064 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3065 fmt_url += '&' + sp + '=' + signature
3066
404f611f 3067 query = parse_qs(fmt_url)
3068 throttled = False
b2916526 3069 if query.get('n'):
404f611f 3070 try:
3071 fmt_url = update_url_query(fmt_url, {
3072 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3073 except ExtractorError as e:
aa9369a2 3074 self.report_warning(
3075 f'nsig extraction failed: You may experience throttling for some formats\n'
3076 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3077 throttled = True
3078
545cc85d 3079 if itag:
a0bb6ce5 3080 itags[itag] = 'https'
9297939e 3081 stream_ids.append(stream_id)
3082
0ad92dfb 3083 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3084 language_preference = (
3085 10 if audio_track.get('audioIsDefault') and 10
3086 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3087 else -1)
0ad92dfb 3088 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3089 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3090 # Make sure to avoid false positives with small duration differences.
3091 # Eg: __2ABJjxzNo, ySuUZEjARPY
3092 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3093 if is_damaged:
3094 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3095 dct = {
3096 'asr': int_or_none(fmt.get('audioSampleRate')),
3097 'filesize': int_or_none(fmt.get('contentLength')),
3098 'format_id': itag,
34921b43 3099 'format_note': join_nonempty(
26e8e044 3100 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3101 ' (default)' if language_preference > 0 else ''),
404f611f 3102 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3103 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3104 'source_preference': -10 if throttled else -1,
a4211baf 3105 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3106 'height': height,
dca3ff4a 3107 'quality': q(quality),
727029c5 3108 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3109 'tbr': tbr,
545cc85d 3110 'url': fmt_url,
2a9c6dcd 3111 'width': int_or_none(fmt.get('width')),
ab6df717 3112 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3113 'desc' if language_preference < -1 else ''),
3114 'language_preference': language_preference,
a405b38f 3115 # Strictly de-prioritize damaged and 3gp formats
3116 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3117 }
60bdb7bd 3118 mime_mobj = re.match(
3119 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3120 if mime_mobj:
3121 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3122 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3123 no_audio = dct.get('acodec') == 'none'
3124 no_video = dct.get('vcodec') == 'none'
3125 if no_audio:
3126 dct['vbr'] = tbr
3127 if no_video:
3128 dct['abr'] = tbr
3129 if no_audio or no_video:
545cc85d 3130 dct['downloader_options'] = {
3131 # Youtube throttles chunks >~10M
3132 'http_chunk_size': 10485760,
bf1317d2 3133 }
7c60c33e 3134 if dct.get('ext'):
3135 dct['container'] = dct['ext'] + '_dash'
11f9be09 3136 yield dct
545cc85d 3137
adbc4ec4 3138 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3139 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3140 if not self.get_param('youtube_include_hls_manifest', True):
3141 skip_manifests.append('hls')
3142 get_dash = 'dash' not in skip_manifests and (
3143 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3144 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3145
a0bb6ce5 3146 def process_manifest_format(f, proto, itag):
3147 if itag in itags:
3148 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3149 return False
3150 itag = f'{itag}-{proto}'
3151 if itag:
3152 f['format_id'] = itag
3153 itags[itag] = proto
3154
3155 f['quality'] = next((
3156 q(qdict[val])
e339d25a 3157 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3158 if val in qdict), -1)
3159 return True
2a9c6dcd 3160
11f9be09 3161 for sd in streaming_data:
5d3a0e79 3162 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3163 if hls_manifest_url:
2a9c6dcd 3164 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3165 if process_manifest_format(f, 'hls', self._search_regex(
3166 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3167 yield f
545cc85d 3168
5d3a0e79 3169 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3170 if dash_manifest_url:
2a9c6dcd 3171 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3172 if process_manifest_format(f, 'dash', f['format_id']):
3173 f['filesize'] = int_or_none(self._search_regex(
3174 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3175 if live_from_start:
3176 f['is_from_start'] = True
3177
a0bb6ce5 3178 yield f
11f9be09 3179
720c3099 3180 def _extract_storyboard(self, player_responses, duration):
3181 spec = get_first(
3182 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3183 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3184 if not base_url:
720c3099 3185 return
720c3099 3186 L = len(spec) - 1
3187 for i, args in enumerate(spec):
3188 args = args.split('#')
3189 counts = list(map(int_or_none, args[:5]))
3190 if len(args) != 8 or not all(counts):
3191 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3192 continue
3193 width, height, frame_count, cols, rows = counts
3194 N, sigh = args[6:]
3195
3196 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3197 fragment_count = frame_count / (cols * rows)
3198 fragment_duration = duration / fragment_count
3199 yield {
3200 'format_id': f'sb{i}',
3201 'format_note': 'storyboard',
3202 'ext': 'mhtml',
3203 'protocol': 'mhtml',
3204 'acodec': 'none',
3205 'vcodec': 'none',
3206 'url': url,
3207 'width': width,
3208 'height': height,
3209 'fragments': [{
b3edc806 3210 'url': url.replace('$M', str(j)),
720c3099 3211 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3212 } for j in range(math.ceil(fragment_count))],
3213 }
3214
adbc4ec4 3215 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3216 webpage = None
3217 if 'webpage' not in self._configuration_arg('player_skip'):
3218 webpage = self._download_webpage(
3219 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3220
3221 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3222
b6de707d 3223 player_responses, player_url = self._extract_player_responses(
11f9be09 3224 self._get_requested_clients(url, smuggled_data),
99e9e001 3225 video_id, webpage, master_ytcfg)
11f9be09 3226
adbc4ec4
THD
3227 return webpage, master_ytcfg, player_responses, player_url
3228
a1b2d843 3229 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3230 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3231 is_live = get_first(video_details, 'isLive')
3232 if is_live is None:
3233 is_live = get_first(live_broadcast_details, 'isLiveNow')
3234
3235 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3236 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3237
3238 return live_broadcast_details, is_live, streaming_data, formats
3239
3240 def _real_extract(self, url):
3241 url, smuggled_data = unsmuggle_url(url, {})
3242 video_id = self._match_id(url)
3243
3244 base_url = self.http_scheme() + '//www.youtube.com/'
3245 webpage_url = base_url + 'watch?v=' + video_id
3246
3247 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3248
11f9be09 3249 playability_statuses = traverse_obj(
3250 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3251
3252 trailer_video_id = get_first(
3253 playability_statuses,
3254 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3255 expected_type=str)
3256 if trailer_video_id:
3257 return self.url_result(
3258 trailer_video_id, self.ie_key(), trailer_video_id)
3259
3260 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3261 if webpage else (lambda x: None))
3262
3263 video_details = traverse_obj(
3264 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3265 microformats = traverse_obj(
3266 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3267 expected_type=dict, default=[])
3268 video_title = (
3269 get_first(video_details, 'title')
3270 or self._get_text(microformats, (..., 'title'))
3271 or search_meta(['og:title', 'twitter:title', 'title']))
3272 video_description = get_first(video_details, 'shortDescription')
3273
d89257f3 3274 multifeed_metadata_list = get_first(
3275 player_responses,
3276 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3277 expected_type=str)
3278 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3279 if self.get_param('noplaylist'):
11f9be09 3280 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3281 else:
3282 entries = []
3283 feed_ids = []
3284 for feed in multifeed_metadata_list.split(','):
3285 # Unquote should take place before split on comma (,) since textual
3286 # fields may contain comma as well (see
3287 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3288 feed_data = compat_parse_qs(
3289 compat_urllib_parse_unquote_plus(feed))
3290
3291 def feed_entry(name):
3292 return try_get(
3293 feed_data, lambda x: x[name][0], compat_str)
3294
3295 feed_id = feed_entry('id')
3296 if not feed_id:
3297 continue
3298 feed_title = feed_entry('title')
3299 title = video_title
3300 if feed_title:
3301 title += ' (%s)' % feed_title
3302 entries.append({
3303 '_type': 'url_transparent',
3304 'ie_key': 'Youtube',
3305 'url': smuggle_url(
3306 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3307 {'force_singlefeed': True}),
3308 'title': title,
3309 })
3310 feed_ids.append(feed_id)
3311 self.to_screen(
3312 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3313 % (', '.join(feed_ids), video_id))
3314 return self.playlist_result(
3315 entries, video_id, video_title, video_description)
11f9be09 3316
a1b2d843 3317 duration = int_or_none(
3318 get_first(video_details, 'lengthSeconds')
3319 or get_first(microformats, 'lengthSeconds')
3320 or parse_duration(search_meta('duration'))) or None
3321
3322 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3323 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3324
545cc85d 3325 if not formats:
11f9be09 3326 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3327 self.report_drm(video_id)
11f9be09 3328 pemr = get_first(
3329 playability_statuses,
3330 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3331 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3332 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3333 if subreason:
545cc85d 3334 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3335 countries = get_first(microformats, 'availableCountries')
545cc85d 3336 if not countries:
3337 regions_allowed = search_meta('regionsAllowed')
3338 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3339 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3340 reason += f'. {subreason}'
545cc85d 3341 if reason:
b7da73eb 3342 self.raise_no_formats(reason, expected=True)
bf1317d2 3343
11f9be09 3344 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3345 if not keywords and webpage:
3346 keywords = [
3347 unescapeHTML(m.group('content'))
3348 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3349 for keyword in keywords:
3350 if keyword.startswith('yt:stretch='):
201c1459 3351 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3352 if mobj:
3353 # NB: float is intentional for forcing float division
3354 w, h = (float(v) for v in mobj.groups())
3355 if w > 0 and h > 0:
3356 ratio = w / h
3357 for f in formats:
3358 if f.get('vcodec') != 'none':
3359 f['stretched_ratio'] = ratio
3360 break
a709d873 3361 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3362 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3363 if thumbnail_url:
3364 thumbnails.append({
3365 'url': thumbnail_url,
ff2751ac 3366 })
fccf5021 3367 original_thumbnails = thumbnails.copy()
3368
0ba692ac 3369 # The best resolution thumbnails sometimes does not appear in the webpage
3370 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3371 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3372 thumbnail_names = [
3373 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3374 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3375 'mqdefault', 'mq1', 'mq2', 'mq3',
3376 'default', '1', '2', '3'
3377 ]
cca80fe6 3378 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3379 thumbnails.extend({
3380 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3381 video_id=video_id, name=name, ext=ext,
3382 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3383 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3384 for thumb in thumbnails:
cca80fe6 3385 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3386 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3387 self._remove_duplicate_formats(thumbnails)
fccf5021 3388 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3389
7ea65411 3390 category = get_first(microformats, 'category') or search_meta('genre')
3391 channel_id = str_or_none(
3392 get_first(video_details, 'channelId')
3393 or get_first(microformats, 'externalChannelId')
3394 or search_meta('channelId'))
7ea65411 3395 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3396
3397 live_content = get_first(video_details, 'isLiveContent')
3398 is_upcoming = get_first(video_details, 'isUpcoming')
3399 if is_live is None:
3400 if is_upcoming or live_content is False:
3401 is_live = False
3402 if is_upcoming is None and (live_content or is_live):
3403 is_upcoming = False
adbc4ec4
THD
3404 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3405 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3406 if not duration and live_end_time and live_start_time:
3407 duration = live_end_time - live_start_time
3408
3409 if is_live and self.get_param('live_from_start'):
3410 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3411
720c3099 3412 formats.extend(self._extract_storyboard(player_responses, duration))
3413
3414 # Source is given priority since formats that throttle are given lower source_preference
3415 # When throttling issue is fully fixed, remove this
3416 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3417
545cc85d 3418 info = {
3419 'id': video_id,
39ca3b5c 3420 'title': video_title,
545cc85d 3421 'formats': formats,
3422 'thumbnails': thumbnails,
fccf5021 3423 # The best thumbnail that we are sure exists. Prevents unnecessary
3424 # URL checking if user don't care about getting the best possible thumbnail
3425 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3426 'description': video_description,
11f9be09 3427 'uploader': get_first(video_details, 'author'),
545cc85d 3428 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3429 'uploader_url': owner_profile_url,
3430 'channel_id': channel_id,
e0ddbd02 3431 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3432 'duration': duration,
3433 'view_count': int_or_none(
11f9be09 3434 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3435 or search_meta('interactionCount')),
11f9be09 3436 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3437 'age_limit': 18 if (
11f9be09 3438 get_first(microformats, 'isFamilySafe') is False
545cc85d 3439 or search_meta('isFamilyFriendly') == 'false'
3440 or search_meta('og:restrictions:age') == '18+') else 0,
3441 'webpage_url': webpage_url,
3442 'categories': [category] if category else None,
3443 'tags': keywords,
11f9be09 3444 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3445 'is_live': is_live,
3446 'was_live': (False if is_live or is_upcoming or live_content is False
3447 else None if is_live is None or is_upcoming is None
3448 else live_content),
3449 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3450 'release_timestamp': live_start_time,
545cc85d 3451 }
b477fc13 3452
3944e7af 3453 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3454 if pctr:
ecdc9049 3455 def get_lang_code(track):
3456 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3457 or track.get('languageCode'))
3458
3459 # Converted into dicts to remove duplicates
3460 captions = {
3461 get_lang_code(sub): sub
3462 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3463 translation_languages = {
3464 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3465 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3466
774d79cc 3467 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3468 lang_subs = container.setdefault(lang_code, [])
545cc85d 3469 for fmt in self._SUBTITLE_FORMATS:
3470 query.update({
3471 'fmt': fmt,
3472 })
3473 lang_subs.append({
3474 'ext': fmt,
60f393e4 3475 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3476 'name': sub_name,
545cc85d 3477 })
7e72694b 3478
ecdc9049 3479 subtitles, automatic_captions = {}, {}
3480 for lang_code, caption_track in captions.items():
3481 base_url = caption_track.get('baseUrl')
1235d333 3482 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3483 if not base_url:
3484 continue
ecdc9049 3485 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3486 if caption_track.get('kind') != 'asr':
545cc85d 3487 if not lang_code:
3488 continue
3489 process_language(
ecdc9049 3490 subtitles, base_url, lang_code, lang_name, {})
3491 if not caption_track.get('isTranslatable'):
3492 continue
3944e7af 3493 for trans_code, trans_name in translation_languages.items():
3494 if not trans_code:
545cc85d 3495 continue
1235d333 3496 orig_trans_code = trans_code
ecdc9049 3497 if caption_track.get('kind') != 'asr':
18e49408 3498 if 'translated_subs' in self._configuration_arg('skip'):
3499 continue
ecdc9049 3500 trans_code += f'-{lang_code}'
3501 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3502 # Add an "-orig" label to the original language so that it can be distinguished.
3503 # The subs are returned without "-orig" as well for compatibility
1235d333 3504 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3505 process_language(
d49669ac 3506 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3507 # Setting tlang=lang returns damaged subtitles.
d49669ac 3508 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3509 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3510 info['automatic_captions'] = automatic_captions
3511 info['subtitles'] = subtitles
7e72694b 3512
545cc85d 3513 parsed_url = compat_urllib_parse_urlparse(url)
3514 for component in [parsed_url.fragment, parsed_url.query]:
3515 query = compat_parse_qs(component)
3516 for k, v in query.items():
3517 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3518 d_k += '_time'
3519 if d_k not in info and k in s_ks:
3520 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3521
3522 # Youtube Music Auto-generated description
822b9d9c 3523 if video_description:
38d70284 3524 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 3525 if mobj:
822b9d9c
RA
3526 release_year = mobj.group('release_year')
3527 release_date = mobj.group('release_date')
3528 if release_date:
3529 release_date = release_date.replace('-', '')
3530 if not release_year:
545cc85d 3531 release_year = release_date[:4]
3532 info.update({
3533 'album': mobj.group('album'.strip()),
3534 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3535 'track': mobj.group('track').strip(),
3536 'release_date': release_date,
cc2db878 3537 'release_year': int_or_none(release_year),
545cc85d 3538 })
7e72694b 3539
545cc85d 3540 initial_data = None
3541 if webpage:
3542 initial_data = self._extract_yt_initial_variable(
3543 webpage, self._YT_INITIAL_DATA_RE, video_id,
3544 'yt initial data')
3545 if not initial_data:
99e9e001 3546 query = {'videoId': video_id}
3547 query.update(self._get_checkok_params())
109dd3b2 3548 initial_data = self._extract_response(
3549 item_id=video_id, ep='next', fatal=False,
99e9e001 3550 ytcfg=master_ytcfg, query=query,
3551 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3552 note='Downloading initial data API JSON')
545cc85d 3553
c60ee3a2 3554 try:
3555 # This will error if there is no livechat
3556 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3557 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3558 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3559 'video_id': video_id,
3560 'ext': 'json',
f6745c49 3561 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3562 }]
3563 except (KeyError, IndexError, TypeError):
3564 pass
545cc85d 3565
3566 if initial_data:
7c365c21 3567 info['chapters'] = (
3568 self._extract_chapters_from_json(initial_data, duration)
3569 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3570 or None)
545cc85d 3571
17322130 3572 contents = traverse_obj(
3573 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3574 expected_type=list, default=[])
3575
3576 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3577 if vpir:
3578 stl = vpir.get('superTitleLink')
3579 if stl:
3580 stl = self._get_text(stl)
3581 if try_get(
3582 vpir,
3583 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3584 info['location'] = stl
3585 else:
3586 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3587 if mobj:
545cc85d 3588 info.update({
17322130 3589 'series': mobj.group(1),
3590 'season_number': int(mobj.group(2)),
3591 'episode_number': int(mobj.group(3)),
545cc85d 3592 })
17322130 3593 for tlb in (try_get(
3594 vpir,
3595 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3596 list) or []):
3597 tbr = tlb.get('toggleButtonRenderer') or {}
3598 for getter, regex in [(
3599 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3600 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3601 lambda x: x['accessibility'],
3602 lambda x: x['accessibilityData']['accessibilityData'],
3603 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3604 label = (try_get(tbr, getter, dict) or {}).get('label')
3605 if label:
3606 mobj = re.match(regex, label)
3607 if mobj:
3608 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3609 break
17322130 3610 sbr_tooltip = try_get(
3611 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3612 if sbr_tooltip:
3613 like_count, dislike_count = sbr_tooltip.split(' / ')
3614 info.update({
3615 'like_count': str_to_int(like_count),
3616 'dislike_count': str_to_int(dislike_count),
3617 })
3618 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3619 if vsir:
3620 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3621 info.update({
3622 'channel': self._get_text(vor, 'title'),
3623 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3624
3625 rows = try_get(
3626 vsir,
3627 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3628 list) or []
3629 multiple_songs = False
3630 for row in rows:
3631 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3632 multiple_songs = True
3633 break
3634 for row in rows:
3635 mrr = row.get('metadataRowRenderer') or {}
3636 mrr_title = mrr.get('title')
3637 if not mrr_title:
3638 continue
3639 mrr_title = self._get_text(mrr, 'title')
3640 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3641 if mrr_title == 'License':
3642 info['license'] = mrr_contents_text
3643 elif not multiple_songs:
3644 if mrr_title == 'Album':
3645 info['album'] = mrr_contents_text
3646 elif mrr_title == 'Artist':
3647 info['artist'] = mrr_contents_text
3648 elif mrr_title == 'Song':
3649 info['track'] = mrr_contents_text
545cc85d 3650
3651 fallbacks = {
3652 'channel': 'uploader',
3653 'channel_id': 'uploader_id',
3654 'channel_url': 'uploader_url',
3655 }
992f9a73 3656
17322130 3657 # The upload date for scheduled, live and past live streams / premieres in microformats
3658 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3659 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3660 upload_date = (
3661 unified_strdate(get_first(microformats, 'uploadDate'))
3662 or unified_strdate(search_meta('uploadDate')))
3663 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3664 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3665 info['upload_date'] = upload_date
992f9a73 3666
545cc85d 3667 for to, frm in fallbacks.items():
3668 if not info.get(to):
3669 info[to] = info.get(frm)
3670
3671 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3672 v = info.get(s_k)
3673 if v:
3674 info[d_k] = v
b84071c0 3675
11f9be09 3676 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3677 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3678 is_membersonly = None
b28f8d24 3679 is_premium = None
c224251a
M
3680 if initial_data and is_private is not None:
3681 is_membersonly = False
b28f8d24 3682 is_premium = False
47193e02 3683 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3684 badge_labels = set()
3685 for content in contents:
3686 if not isinstance(content, dict):
3687 continue
3688 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3689 for badge_label in badge_labels:
3690 if badge_label.lower() == 'members only':
3691 is_membersonly = True
3692 elif badge_label.lower() == 'premium':
3693 is_premium = True
3694 elif badge_label.lower() == 'unlisted':
3695 is_unlisted = True
c224251a 3696
c224251a
M
3697 info['availability'] = self._availability(
3698 is_private=is_private,
b28f8d24 3699 needs_premium=is_premium,
c224251a
M
3700 needs_subscription=is_membersonly,
3701 needs_auth=info['age_limit'] >= 18,
3702 is_unlisted=None if is_private is None else is_unlisted)
3703
a2160aa4 3704 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3705
11f9be09 3706 self.mark_watched(video_id, player_responses)
d77ab8e2 3707
545cc85d 3708 return info
c5e8d7af 3709
a61fd4cf 3710
a6213a49 3711class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3712
182bda88 3713 @staticmethod
3714 def passthrough_smuggled_data(func):
3715 def _smuggle(entries, smuggled_data):
3716 for entry in entries:
3717 # TODO: Convert URL to music.youtube instead.
3718 # Do we need to passthrough any other smuggled_data?
3719 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3720 yield entry
3721
3722 @functools.wraps(func)
3723 def wrapper(self, url):
3724 url, smuggled_data = unsmuggle_url(url, {})
3725 if self.is_music_url(url):
3726 smuggled_data['is_music_url'] = True
3727 info_dict = func(self, url, smuggled_data)
3728 if smuggled_data and info_dict.get('entries'):
3729 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3730 return info_dict
3731 return wrapper
3732
a6213a49 3733 def _extract_channel_id(self, webpage):
3734 channel_id = self._html_search_meta(
3735 'channelId', webpage, 'channel id', default=None)
3736 if channel_id:
3737 return channel_id
3738 channel_url = self._html_search_meta(
3739 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3740 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3741 'twitter:app:url:googleplay'), webpage, 'channel url')
3742 return self._search_regex(
3743 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3744 channel_url, 'channel id')
15f6397c 3745
8bdd16b4 3746 @staticmethod
cd7c66cf 3747 def _extract_basic_item_renderer(item):
3748 # Modified from _extract_grid_item_renderer
201c1459 3749 known_basic_renderers = (
3750 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3751 )
3752 for key, renderer in item.items():
201c1459 3753 if not isinstance(renderer, dict):
cd7c66cf 3754 continue
201c1459 3755 elif key in known_basic_renderers:
3756 return renderer
3757 elif key.startswith('grid') and key.endswith('Renderer'):
3758 return renderer
8bdd16b4 3759
8bdd16b4 3760 def _grid_entries(self, grid_renderer):
3761 for item in grid_renderer['items']:
3762 if not isinstance(item, dict):
39b62db1 3763 continue
cd7c66cf 3764 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3765 if not isinstance(renderer, dict):
3766 continue
052e1350 3767 title = self._get_text(renderer, 'title')
fe93e2c4 3768
8bdd16b4 3769 # playlist
3770 playlist_id = renderer.get('playlistId')
3771 if playlist_id:
3772 yield self.url_result(
3773 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3774 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3775 video_title=title)
201c1459 3776 continue
8bdd16b4 3777 # video
3778 video_id = renderer.get('videoId')
3779 if video_id:
3780 yield self._extract_video(renderer)
201c1459 3781 continue
8bdd16b4 3782 # channel
3783 channel_id = renderer.get('channelId')
3784 if channel_id:
8bdd16b4 3785 yield self.url_result(
3786 'https://www.youtube.com/channel/%s' % channel_id,
3787 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3788 continue
3789 # generic endpoint URL support
3790 ep_url = urljoin('https://www.youtube.com/', try_get(
3791 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3792 compat_str))
3793 if ep_url:
3794 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3795 if ie.suitable(ep_url):
3796 yield self.url_result(
3797 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3798 break
8bdd16b4 3799
16aa9ea4 3800 def _music_reponsive_list_entry(self, renderer):
3801 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3802 if video_id:
3803 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3804 ie=YoutubeIE.ie_key(), video_id=video_id)
3805 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3806 if playlist_id:
3807 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3808 if video_id:
3809 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3810 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3811 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3812 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3813 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3814 if browse_id:
3815 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3816 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3817
3d3dddc9 3818 def _shelf_entries_from_content(self, shelf_renderer):
3819 content = shelf_renderer.get('content')
3820 if not isinstance(content, dict):
8bdd16b4 3821 return
cd7c66cf 3822 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3823 if renderer:
3824 # TODO: add support for nested playlists so each shelf is processed
3825 # as separate playlist
3826 # TODO: this includes only first N items
3827 for entry in self._grid_entries(renderer):
3828 yield entry
3829 renderer = content.get('horizontalListRenderer')
3830 if renderer:
3831 # TODO
3832 pass
8bdd16b4 3833
29f7c58a 3834 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3835 ep = try_get(
3836 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3837 compat_str)
3838 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3839 if shelf_url:
29f7c58a 3840 # Skipping links to another channels, note that checking for
3841 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3842 # will not work
3843 if skip_channels and '/channels?' in shelf_url:
3844 return
052e1350 3845 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3846 yield self.url_result(shelf_url, video_title=title)
3847 # Shelf may not contain shelf URL, fallback to extraction from content
3848 for entry in self._shelf_entries_from_content(shelf_renderer):
3849 yield entry
c5e8d7af 3850
8bdd16b4 3851 def _playlist_entries(self, video_list_renderer):
3852 for content in video_list_renderer['contents']:
3853 if not isinstance(content, dict):
3854 continue
3855 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3856 if not isinstance(renderer, dict):
3857 continue
3858 video_id = renderer.get('videoId')
3859 if not video_id:
3860 continue
3861 yield self._extract_video(renderer)
07aeced6 3862
3462ffa8 3863 def _rich_entries(self, rich_grid_renderer):
3864 renderer = try_get(
70d5c17b 3865 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3866 video_id = renderer.get('videoId')
3867 if not video_id:
3868 return
3869 yield self._extract_video(renderer)
3870
8bdd16b4 3871 def _video_entry(self, video_renderer):
3872 video_id = video_renderer.get('videoId')
3873 if video_id:
3874 return self._extract_video(video_renderer)
dacb3a86 3875
8bdd16b4 3876 def _post_thread_entries(self, post_thread_renderer):
3877 post_renderer = try_get(
3878 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3879 if not post_renderer:
3880 return
3881 # video attachment
3882 video_renderer = try_get(
895b0931 3883 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3884 video_id = video_renderer.get('videoId')
3885 if video_id:
3886 entry = self._extract_video(video_renderer)
8bdd16b4 3887 if entry:
3888 yield entry
895b0931 3889 # playlist attachment
3890 playlist_id = try_get(
3891 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3892 if playlist_id:
3893 yield self.url_result(
e28f1c0a 3894 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3895 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3896 # inline video links
3897 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3898 for run in runs:
3899 if not isinstance(run, dict):
3900 continue
3901 ep_url = try_get(
3902 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3903 if not ep_url:
3904 continue
3905 if not YoutubeIE.suitable(ep_url):
3906 continue
3907 ep_video_id = YoutubeIE._match_id(ep_url)
3908 if video_id == ep_video_id:
3909 continue
895b0931 3910 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3911
8bdd16b4 3912 def _post_thread_continuation_entries(self, post_thread_continuation):
3913 contents = post_thread_continuation.get('contents')
3914 if not isinstance(contents, list):
3915 return
3916 for content in contents:
3917 renderer = content.get('backstagePostThreadRenderer')
3918 if not isinstance(renderer, dict):
3919 continue
3920 for entry in self._post_thread_entries(renderer):
3921 yield entry
07aeced6 3922
39ed931e 3923 r''' # unused
3924 def _rich_grid_entries(self, contents):
3925 for content in contents:
3926 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3927 if video_renderer:
3928 entry = self._video_entry(video_renderer)
3929 if entry:
3930 yield entry
3931 '''
52efa4b3 3932
a6213a49 3933 def _extract_entries(self, parent_renderer, continuation_list):
3934 # continuation_list is modified in-place with continuation_list = [continuation_token]
3935 continuation_list[:] = [None]
3936 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3937 for content in contents:
3938 if not isinstance(content, dict):
3939 continue
16aa9ea4 3940 is_renderer = traverse_obj(
3941 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3942 expected_type=dict)
a6213a49 3943 if not is_renderer:
3944 renderer = content.get('richItemRenderer')
3945 if renderer:
3946 for entry in self._rich_entries(renderer):
3947 yield entry
3948 continuation_list[0] = self._extract_continuation(parent_renderer)
3949 continue
3950 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3951 for isr_content in isr_contents:
3952 if not isinstance(isr_content, dict):
8bdd16b4 3953 continue
69184e41 3954
a6213a49 3955 known_renderers = {
3956 'playlistVideoListRenderer': self._playlist_entries,
3957 'gridRenderer': self._grid_entries,
3958 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3959 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3960 'backstagePostThreadRenderer': self._post_thread_entries,
3961 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3962 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3963 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3964 }
3965 for key, renderer in isr_content.items():
3966 if key not in known_renderers:
3967 continue
3968 for entry in known_renderers[key](renderer):
3969 if entry:
3970 yield entry
3971 continuation_list[0] = self._extract_continuation(renderer)
3972 break
70d5c17b 3973
3974 if not continuation_list[0]:
a6213a49 3975 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3976
a6213a49 3977 if not continuation_list[0]:
3978 continuation_list[0] = self._extract_continuation(parent_renderer)
3979
3980 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3981 continuation_list = [None]
3982 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3983 tab_content = try_get(tab, lambda x: x['content'], dict)
3984 if not tab_content:
3985 return
3462ffa8 3986 parent_renderer = (
29f7c58a 3987 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3988 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3989 for entry in extract_entries(parent_renderer):
3990 yield entry
3462ffa8 3991 continuation = continuation_list[0]
d069eca7 3992
8bdd16b4 3993 for page_num in itertools.count(1):
3994 if not continuation:
3995 break
99e9e001 3996 headers = self.generate_api_headers(
3997 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3998 response = self._extract_response(
3999 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 4000 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4001 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4002
4003 if not response:
8bdd16b4 4004 break
ac56cf38 4005 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4006 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4007 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4008
69184e41 4009 known_continuation_renderers = {
4010 'playlistVideoListContinuation': self._playlist_entries,
4011 'gridContinuation': self._grid_entries,
4012 'itemSectionContinuation': self._post_thread_continuation_entries,
4013 'sectionListContinuation': extract_entries, # for feeds
4014 }
8bdd16b4 4015 continuation_contents = try_get(
69184e41 4016 response, lambda x: x['continuationContents'], dict) or {}
4017 continuation_renderer = None
4018 for key, value in continuation_contents.items():
4019 if key not in known_continuation_renderers:
3462ffa8 4020 continue
69184e41 4021 continuation_renderer = value
4022 continuation_list = [None]
4023 for entry in known_continuation_renderers[key](continuation_renderer):
4024 yield entry
4025 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4026 break
4027 if continuation_renderer:
4028 continue
c5e8d7af 4029
a1b535bd 4030 known_renderers = {
e4b98809 4031 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4032 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4033 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4034 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4035 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4036 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4037 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4038 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4039 }
cce889b9 4040 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4041 continuation_items = try_get(
cce889b9 4042 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4043 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4044 video_items_renderer = None
4045 for key, value in continuation_item.items():
4046 if key not in known_renderers:
8bdd16b4 4047 continue
a1b535bd 4048 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4049 continuation_list = [None]
a1b535bd 4050 for entry in known_renderers[key][0](video_items_renderer):
4051 yield entry
9ba5705a 4052 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4053 break
4054 if video_items_renderer:
4055 continue
8bdd16b4 4056 break
9558dcec 4057
8bdd16b4 4058 @staticmethod
7c219ea6 4059 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4060 for tab in tabs:
cd684175 4061 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4062 if renderer.get('selected') is True:
4063 return renderer
2b3c2546 4064 else:
7c219ea6 4065 if fatal:
4066 raise ExtractorError('Unable to find selected tab')
b82f815f 4067
47193e02 4068 @classmethod
4069 def _extract_uploader(cls, data):
8bdd16b4 4070 uploader = {}
47193e02 4071 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4072 owner = try_get(
4073 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4074 if owner:
4075 uploader['uploader'] = owner.get('text')
4076 uploader['uploader_id'] = try_get(
4077 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4078 uploader['uploader_url'] = urljoin(
4079 'https://www.youtube.com/',
4080 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4081 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4082
ac56cf38 4083 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4084 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4085 tags = []
b60419c5 4086
8bdd16b4 4087 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4088 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4089 renderer = try_get(
4090 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4091 if renderer:
b60419c5 4092 channel_name = renderer.get('title')
4093 channel_url = renderer.get('channelUrl')
4094 channel_id = renderer.get('externalId')
39ed931e 4095 else:
64c0d954 4096 renderer = try_get(
4097 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4098
8bdd16b4 4099 if renderer:
4100 title = renderer.get('title')
ecc97af3 4101 description = renderer.get('description', '')
b60419c5 4102 playlist_id = channel_id
4103 tags = renderer.get('keywords', '').split()
b60419c5 4104
301d07fc 4105 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4106 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4107 def _get_uncropped(url):
4108 return url_or_none((url or '').split('=')[0] + '=s0')
4109
4110 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4111 if avatar_thumbnails:
4112 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4113 if uncropped_avatar:
4114 avatar_thumbnails.append({
4115 'url': uncropped_avatar,
4116 'id': 'avatar_uncropped',
4117 'preference': 1
4118 })
4119
4120 channel_banners = self._extract_thumbnails(
4121 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4122 for banner in channel_banners:
4123 banner['preference'] = -10
4124
4125 if channel_banners:
4126 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4127 if uncropped_banner:
4128 channel_banners.append({
4129 'url': uncropped_banner,
4130 'id': 'banner_uncropped',
4131 'preference': -5
4132 })
4133
4134 primary_thumbnails = self._extract_thumbnails(
4135 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4136
3462ffa8 4137 if playlist_id is None:
70d5c17b 4138 playlist_id = item_id
f0d785d3 4139
4140 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4141 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4142 if title is None:
f0d785d3 4143 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4144 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4145 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4146
b60419c5 4147 metadata = {
4148 'playlist_id': playlist_id,
4149 'playlist_title': title,
4150 'playlist_description': description,
4151 'uploader': channel_name,
4152 'uploader_id': channel_id,
4153 'uploader_url': channel_url,
301d07fc 4154 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4155 'tags': tags,
f0d785d3 4156 'view_count': self._get_count(playlist_stats, 1),
4157 'availability': self._extract_availability(data),
4158 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4159 'playlist_count': self._get_count(playlist_stats, 0),
4160 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4161 }
4162 if not channel_id:
4163 metadata.update(self._extract_uploader(data))
4164 metadata.update({
4165 'channel': metadata['uploader'],
4166 'channel_id': metadata['uploader_id'],
4167 'channel_url': metadata['uploader_url']})
4168 return self.playlist_result(
d069eca7 4169 self._entries(
ac56cf38 4170 selected_tab, playlist_id, ytcfg,
4171 self._extract_account_syncid(ytcfg, data),
4172 self._extract_visitor_data(data, ytcfg)),
b60419c5 4173 **metadata)
73c4ac2c 4174
ac56cf38 4175 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4176 first_id = last_id = response = None
2be71994 4177 for page_num in itertools.count(1):
cd7c66cf 4178 videos = list(self._playlist_entries(playlist))
4179 if not videos:
4180 return
2be71994 4181 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4182 if start >= len(videos):
4183 return
4184 for video in videos[start:]:
4185 if video['id'] == first_id:
4186 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4187 return
4188 yield video
4189 first_id = first_id or videos[0]['id']
4190 last_id = videos[-1]['id']
79360d99 4191 watch_endpoint = try_get(
4192 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4193 headers = self.generate_api_headers(
4194 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4195 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4196 query = {
4197 'playlistId': playlist_id,
4198 'videoId': watch_endpoint.get('videoId') or last_id,
4199 'index': watch_endpoint.get('index') or len(videos),
4200 'params': watch_endpoint.get('params') or 'OAE%3D'
4201 }
4202 response = self._extract_response(
4203 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4204 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4205 check_get_keys='contents'
4206 )
cd7c66cf 4207 playlist = try_get(
79360d99 4208 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4209
ac56cf38 4210 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4211 title = playlist.get('title') or try_get(
4212 data, lambda x: x['titleText']['simpleText'], compat_str)
4213 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4214
4215 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4216 playlist_url = urljoin(url, try_get(
4217 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4218 compat_str))
4219 if playlist_url and playlist_url != url:
4220 return self.url_result(
4221 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4222 video_title=title)
cd7c66cf 4223
8bdd16b4 4224 return self.playlist_result(
ac56cf38 4225 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4226 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4227
47193e02 4228 def _extract_availability(self, data):
4229 """
4230 Gets the availability of a given playlist/tab.
4231 Note: Unless YouTube tells us explicitly, we do not assume it is public
4232 @param data: response
4233 """
4234 is_private = is_unlisted = None
4235 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4236 badge_labels = self._extract_badges(renderer)
4237
4238 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4239 privacy_dropdown_entries = try_get(
4240 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4241 for renderer_dict in privacy_dropdown_entries:
4242 is_selected = try_get(
4243 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4244 if not is_selected:
4245 continue
052e1350 4246 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4247 if label:
4248 badge_labels.add(label.lower())
4249 break
4250
4251 for badge_label in badge_labels:
4252 if badge_label == 'unlisted':
4253 is_unlisted = True
4254 elif badge_label == 'private':
4255 is_private = True
4256 elif badge_label == 'public':
4257 is_unlisted = is_private = False
4258 return self._availability(is_private, False, False, False, is_unlisted)
4259
4260 @staticmethod
4261 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4262 sidebar_renderer = try_get(
4263 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4264 for item in sidebar_renderer:
4265 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4266 if renderer:
4267 return renderer
4268
ac56cf38 4269 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4270 """
4271 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4272 """
5d342002 4273 browse_id = params = None
47193e02 4274 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4275 if not renderer:
4276 return
4277 menu_renderer = try_get(
4278 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4279 for menu_item in menu_renderer:
4280 if not isinstance(menu_item, dict):
358de58c 4281 continue
47193e02 4282 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4283 text = try_get(
4284 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4285 if not text or text.lower() != 'show unavailable videos':
4286 continue
4287 browse_endpoint = try_get(
4288 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4289 browse_id = browse_endpoint.get('browseId')
4290 params = browse_endpoint.get('params')
4291 break
5d342002 4292
11f9be09 4293 headers = self.generate_api_headers(
99e9e001 4294 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4295 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4296 query = {
4297 'params': params or 'wgYCCAA=',
4298 'browseId': browse_id or 'VL%s' % item_id
4299 }
4300 return self._extract_response(
4301 item_id=item_id, headers=headers, query=query,
fe93e2c4 4302 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4303 note='Downloading API JSON with unavailable videos')
358de58c 4304
ac56cf38 4305 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4306 retries = self.get_param('extractor_retries', 3)
62bff2c1 4307 count = -1
ac56cf38 4308 webpage = data = last_error = None
14fdfea9 4309 while count < retries:
62bff2c1 4310 count += 1
14fdfea9 4311 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4312 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4313 if last_error:
c705177d 4314 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4315 try:
4316 webpage = self._download_webpage(
4317 url, item_id,
4318 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4319 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4320 except ExtractorError as e:
4321 if isinstance(e.cause, network_exceptions):
4322 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4323 last_error = error_to_compat_str(e.cause or e.msg)
4324 if count < retries:
4325 continue
4326 if fatal:
4327 raise
4328 self.report_warning(error_to_compat_str(e))
14fdfea9 4329 break
ac56cf38 4330 else:
4331 try:
4332 self._extract_and_report_alerts(data)
4333 except ExtractorError as e:
4334 if fatal:
4335 raise
4336 self.report_warning(error_to_compat_str(e))
4337 break
4338
7c219ea6 4339 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4340 break
4341
4342 last_error = 'Incomplete yt initial data received'
4343 if count >= retries:
4344 if fatal:
4345 raise ExtractorError(last_error)
4346 self.report_warning(last_error)
4347 break
4348
cd7c66cf 4349 return webpage, data
4350
ac56cf38 4351 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4352 data = None
4353 if 'webpage' not in self._configuration_arg('skip'):
4354 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4355 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4356 # Reject webpage data if redirected to home page without explicitly requesting
4357 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4358 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4359 if (url != 'https://www.youtube.com/feed/recommended'
4360 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4361 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4362 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4363 if fatal:
4364 raise ExtractorError(msg, expected=True)
4365 self.report_warning(msg, only_once=True)
ac56cf38 4366 if not data:
4367 if not ytcfg and self.is_authenticated:
4368 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4369 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4370 raise ExtractorError(
4371 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4372 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4373 expected=True)
4374 self.report_warning(msg, only_once=True)
4375 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4376 return data, ytcfg
4377
4378 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4379 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4380 resolve_response = self._extract_response(
4381 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4382 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4383 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4384 for ep_key, ep in endpoints.items():
4385 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4386 if params:
4387 return self._extract_response(
4388 item_id=item_id, query=params, ep=ep, headers=headers,
4389 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4390 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4391 err_note = 'Failed to resolve url (does the playlist exist?)'
4392 if fatal:
4393 raise ExtractorError(err_note, expected=True)
4394 self.report_warning(err_note, item_id)
4395
a6213a49 4396 _SEARCH_PARAMS = None
4397
af5c1c55 4398 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4399 data = {'query': query}
4400 if params is NO_DEFAULT:
4401 params = self._SEARCH_PARAMS
4402 if params:
4403 data['params'] = params
16aa9ea4 4404
4405 content_keys = (
4406 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4407 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4408 # ytmusic search
4409 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4410 ('continuationContents', ),
4411 )
4412 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4413
a61fd4cf 4414 continuation_list = [None]
a6213a49 4415 for page_num in itertools.count(1):
a61fd4cf 4416 data.update(continuation_list[0] or {})
a6213a49 4417 search = self._extract_response(
4418 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4419 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4420 slr_contents = traverse_obj(search, *content_keys)
4421 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4422 if not continuation_list[0]:
a6213a49 4423 break
4424
4425
4426class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4427 IE_DESC = 'YouTube Tabs'
4428 _VALID_URL = r'''(?x:
4429 https?://
4430 (?:\w+\.)?
4431 (?:
4432 youtube(?:kids)?\.com|
4433 %(invidious)s
4434 )/
4435 (?:
4436 (?P<channel_type>channel|c|user|browse)/|
4437 (?P<not_channel>
4438 feed/|hashtag/|
4439 (?:playlist|watch)\?.*?\blist=
4440 )|
4441 (?!(?:%(reserved_names)s)\b) # Direct URLs
4442 )
4443 (?P<id>[^/?\#&]+)
4444 )''' % {
4445 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4446 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4447 }
4448 IE_NAME = 'youtube:tab'
4449
4450 _TESTS = [{
4451 'note': 'playlists, multipage',
4452 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4453 'playlist_mincount': 94,
4454 'info_dict': {
4455 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4456 'title': 'Igor Kleiner - Playlists',
a6213a49 4457 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4458 'uploader': 'Igor Kleiner',
a6213a49 4459 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4460 'channel': 'Igor Kleiner',
4461 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4462 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4463 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4464 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4465 'channel_follower_count': int
a6213a49 4466 },
4467 }, {
4468 'note': 'playlists, multipage, different order',
4469 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4470 'playlist_mincount': 94,
4471 'info_dict': {
4472 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4473 'title': 'Igor Kleiner - Playlists',
a6213a49 4474 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4475 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4476 'uploader': 'Igor Kleiner',
4477 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4478 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4479 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4480 'channel': 'Igor Kleiner',
4481 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4482 'channel_follower_count': int
a6213a49 4483 },
4484 }, {
4485 'note': 'playlists, series',
4486 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4487 'playlist_mincount': 5,
4488 'info_dict': {
4489 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4490 'title': '3Blue1Brown - Playlists',
4491 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4492 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4493 'uploader': '3Blue1Brown',
976ae3ea 4494 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4495 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4496 'channel': '3Blue1Brown',
4497 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4498 'tags': ['Mathematics'],
6c73052c 4499 'channel_follower_count': int
a6213a49 4500 },
4501 }, {
4502 'note': 'playlists, singlepage',
4503 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4504 'playlist_mincount': 4,
4505 'info_dict': {
4506 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4507 'title': 'ThirstForScience - Playlists',
4508 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4509 'uploader': 'ThirstForScience',
4510 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4511 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4512 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4513 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4514 'tags': 'count:13',
4515 'channel': 'ThirstForScience',
6c73052c 4516 'channel_follower_count': int
a6213a49 4517 }
4518 }, {
4519 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4520 'only_matching': True,
4521 }, {
4522 'note': 'basic, single video playlist',
4523 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4524 'info_dict': {
4525 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4526 'uploader': 'Sergey M.',
4527 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4528 'title': 'youtube-dl public playlist',
976ae3ea 4529 'description': '',
4530 'tags': [],
4531 'view_count': int,
4532 'modified_date': '20201130',
4533 'channel': 'Sergey M.',
4534 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4535 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4536 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4537 },
4538 'playlist_count': 1,
4539 }, {
4540 'note': 'empty playlist',
4541 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4542 'info_dict': {
4543 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4544 'uploader': 'Sergey M.',
4545 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4546 'title': 'youtube-dl empty playlist',
976ae3ea 4547 'tags': [],
4548 'channel': 'Sergey M.',
4549 'description': '',
4550 'modified_date': '20160902',
4551 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4552 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4553 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4554 },
4555 'playlist_count': 0,
4556 }, {
4557 'note': 'Home tab',
4558 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4559 'info_dict': {
4560 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4561 'title': 'lex will - Home',
4562 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4563 'uploader': 'lex will',
4564 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4565 'channel': 'lex will',
4566 'tags': ['bible', 'history', 'prophesy'],
4567 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4568 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4569 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4570 'channel_follower_count': int
a6213a49 4571 },
4572 'playlist_mincount': 2,
4573 }, {
4574 'note': 'Videos tab',
4575 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4576 'info_dict': {
4577 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4578 'title': 'lex will - Videos',
4579 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4580 'uploader': 'lex will',
4581 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4582 'tags': ['bible', 'history', 'prophesy'],
4583 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4584 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4585 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4586 'channel': 'lex will',
6c73052c 4587 'channel_follower_count': int
a6213a49 4588 },
4589 'playlist_mincount': 975,
4590 }, {
4591 'note': 'Videos tab, sorted by popular',
4592 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4593 'info_dict': {
4594 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4595 'title': 'lex will - Videos',
4596 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4597 'uploader': 'lex will',
4598 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4599 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4600 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4601 'channel': 'lex will',
4602 'tags': ['bible', 'history', 'prophesy'],
4603 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4604 'channel_follower_count': int
a6213a49 4605 },
4606 'playlist_mincount': 199,
4607 }, {
4608 'note': 'Playlists tab',
4609 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4610 'info_dict': {
4611 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4612 'title': 'lex will - Playlists',
4613 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4614 'uploader': 'lex will',
4615 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4616 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4617 'channel': 'lex will',
4618 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4619 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4620 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4621 'channel_follower_count': int
a6213a49 4622 },
4623 'playlist_mincount': 17,
4624 }, {
4625 'note': 'Community tab',
4626 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4627 'info_dict': {
4628 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4629 'title': 'lex will - Community',
4630 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4631 'uploader': 'lex will',
4632 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4633 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4634 'channel': 'lex will',
4635 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4636 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4637 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4638 'channel_follower_count': int
a6213a49 4639 },
4640 'playlist_mincount': 18,
4641 }, {
4642 'note': 'Channels tab',
4643 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4644 'info_dict': {
4645 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4646 'title': 'lex will - Channels',
4647 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4648 'uploader': 'lex will',
4649 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4650 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4651 'channel': 'lex will',
4652 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4653 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4654 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4655 'channel_follower_count': int
a6213a49 4656 },
4657 'playlist_mincount': 12,
4658 }, {
4659 'note': 'Search tab',
4660 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4661 'playlist_mincount': 40,
4662 'info_dict': {
4663 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4664 'title': '3Blue1Brown - Search - linear algebra',
4665 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4666 'uploader': '3Blue1Brown',
4667 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4668 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4669 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4670 'tags': ['Mathematics'],
4671 'channel': '3Blue1Brown',
4672 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4673 'channel_follower_count': int
a6213a49 4674 },
4675 }, {
4676 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4677 'only_matching': True,
4678 }, {
4679 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4680 'only_matching': True,
4681 }, {
4682 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4683 'only_matching': True,
4684 }, {
4685 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4686 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4687 'info_dict': {
4688 'title': '29C3: Not my department',
4689 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4690 'uploader': 'Christiaan008',
4691 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4692 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4693 'tags': [],
4694 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4695 'view_count': int,
4696 'modified_date': '20150605',
4697 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4698 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4699 'channel': 'Christiaan008',
a6213a49 4700 },
4701 'playlist_count': 96,
4702 }, {
4703 'note': 'Large playlist',
4704 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4705 'info_dict': {
4706 'title': 'Uploads from Cauchemar',
4707 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4708 'uploader': 'Cauchemar',
4709 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4710 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4711 'tags': [],
4712 'modified_date': r're:\d{8}',
4713 'channel': 'Cauchemar',
4714 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4715 'view_count': int,
4716 'description': '',
4717 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4718 },
4719 'playlist_mincount': 1123,
976ae3ea 4720 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4721 }, {
4722 'note': 'even larger playlist, 8832 videos',
4723 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4724 'only_matching': True,
4725 }, {
4726 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4727 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4728 'info_dict': {
4729 'title': 'Uploads from Interstellar Movie',
4730 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4731 'uploader': 'Interstellar Movie',
4732 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4733 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4734 'tags': [],
4735 'view_count': int,
4736 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4737 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4738 'channel': 'Interstellar Movie',
4739 'description': '',
4740 'modified_date': r're:\d{8}',
a6213a49 4741 },
4742 'playlist_mincount': 21,
4743 }, {
4744 'note': 'Playlist with "show unavailable videos" button',
4745 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4746 'info_dict': {
4747 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4748 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4749 'uploader': 'Phim Siêu Nhân Nhật Bản',
4750 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4751 'view_count': int,
4752 'channel': 'Phim Siêu Nhân Nhật Bản',
4753 'tags': [],
4754 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4755 'description': '',
4756 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4757 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4758 'modified_date': r're:\d{8}',
a6213a49 4759 },
4760 'playlist_mincount': 200,
976ae3ea 4761 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4762 }, {
4763 'note': 'Playlist with unavailable videos in page 7',
4764 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4765 'info_dict': {
4766 'title': 'Uploads from BlankTV',
4767 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4768 'uploader': 'BlankTV',
4769 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4770 'channel': 'BlankTV',
4771 'channel_url': 'https://www.youtube.com/c/blanktv',
4772 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4773 'view_count': int,
4774 'tags': [],
4775 'uploader_url': 'https://www.youtube.com/c/blanktv',
4776 'modified_date': r're:\d{8}',
4777 'description': '',
a6213a49 4778 },
4779 'playlist_mincount': 1000,
976ae3ea 4780 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4781 }, {
4782 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4783 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4784 'info_dict': {
4785 'title': 'Data Analysis with Dr Mike Pound',
4786 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4787 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4788 'uploader': 'Computerphile',
4789 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4790 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4791 'tags': [],
4792 'view_count': int,
4793 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4794 'channel_url': 'https://www.youtube.com/user/Computerphile',
4795 'channel': 'Computerphile',
a6213a49 4796 },
4797 'playlist_mincount': 11,
4798 }, {
4799 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4800 'only_matching': True,
4801 }, {
4802 'note': 'Playlist URL that does not actually serve a playlist',
4803 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4804 'info_dict': {
4805 'id': 'FqZTN594JQw',
4806 'ext': 'webm',
4807 'title': "Smiley's People 01 detective, Adventure Series, Action",
4808 'uploader': 'STREEM',
4809 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4810 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4811 'upload_date': '20150526',
4812 'license': 'Standard YouTube License',
4813 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4814 'categories': ['People & Blogs'],
4815 'tags': list,
4816 'view_count': int,
4817 'like_count': int,
a6213a49 4818 },
4819 'params': {
4820 'skip_download': True,
4821 },
4822 'skip': 'This video is not available.',
4823 'add_ie': [YoutubeIE.ie_key()],
4824 }, {
4825 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4826 'only_matching': True,
4827 }, {
4828 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4829 'only_matching': True,
4830 }, {
4831 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4832 'info_dict': {
6c73052c 4833 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4834 'ext': 'mp4',
976ae3ea 4835 'title': str,
a6213a49 4836 'uploader': 'Sky News',
4837 'uploader_id': 'skynews',
4838 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4839 'upload_date': r're:\d{8}',
976ae3ea 4840 'description': str,
a6213a49 4841 'categories': ['News & Politics'],
4842 'tags': list,
4843 'like_count': int,
6c73052c 4844 'release_timestamp': 1642502819,
976ae3ea 4845 'channel': 'Sky News',
4846 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4847 'age_limit': 0,
4848 'view_count': int,
6c73052c 4849 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4850 'playable_in_embed': True,
6c73052c 4851 'release_date': '20220118',
976ae3ea 4852 'availability': 'public',
4853 'live_status': 'is_live',
4854 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4855 'channel_follower_count': int
a6213a49 4856 },
4857 'params': {
4858 'skip_download': True,
4859 },
976ae3ea 4860 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4861 }, {
4862 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4863 'info_dict': {
4864 'id': 'a48o2S1cPoo',
4865 'ext': 'mp4',
4866 'title': 'The Young Turks - Live Main Show',
4867 'uploader': 'The Young Turks',
4868 'uploader_id': 'TheYoungTurks',
4869 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4870 'upload_date': '20150715',
4871 'license': 'Standard YouTube License',
4872 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4873 'categories': ['News & Politics'],
4874 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4875 'like_count': int,
a6213a49 4876 },
4877 'params': {
4878 'skip_download': True,
4879 },
4880 'only_matching': True,
4881 }, {
4882 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4883 'only_matching': True,
4884 }, {
4885 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4886 'only_matching': True,
4887 }, {
4888 'note': 'A channel that is not live. Should raise error',
4889 'url': 'https://www.youtube.com/user/numberphile/live',
4890 'only_matching': True,
4891 }, {
4892 'url': 'https://www.youtube.com/feed/trending',
4893 'only_matching': True,
4894 }, {
4895 'url': 'https://www.youtube.com/feed/library',
4896 'only_matching': True,
4897 }, {
4898 'url': 'https://www.youtube.com/feed/history',
4899 'only_matching': True,
4900 }, {
4901 'url': 'https://www.youtube.com/feed/subscriptions',
4902 'only_matching': True,
4903 }, {
4904 'url': 'https://www.youtube.com/feed/watch_later',
4905 'only_matching': True,
4906 }, {
4907 'note': 'Recommended - redirects to home page.',
4908 'url': 'https://www.youtube.com/feed/recommended',
4909 'only_matching': True,
4910 }, {
4911 'note': 'inline playlist with not always working continuations',
4912 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4913 'only_matching': True,
4914 }, {
4915 'url': 'https://www.youtube.com/course',
4916 'only_matching': True,
4917 }, {
4918 'url': 'https://www.youtube.com/zsecurity',
4919 'only_matching': True,
4920 }, {
4921 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4922 'only_matching': True,
4923 }, {
4924 'url': 'https://www.youtube.com/TheYoungTurks/live',
4925 'only_matching': True,
4926 }, {
4927 'url': 'https://www.youtube.com/hashtag/cctv9',
4928 'info_dict': {
4929 'id': 'cctv9',
4930 'title': '#cctv9',
976ae3ea 4931 'tags': [],
a6213a49 4932 },
4933 'playlist_mincount': 350,
4934 }, {
4935 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4936 'only_matching': True,
4937 }, {
4938 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4939 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4940 'only_matching': True
4941 }, {
4942 'note': '/browse/ should redirect to /channel/',
4943 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4944 'only_matching': True
4945 }, {
4946 'note': 'VLPL, should redirect to playlist?list=PL...',
4947 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4948 'info_dict': {
4949 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4950 'uploader': 'NoCopyrightSounds',
4951 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4952 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4953 'title': 'NCS Releases',
976ae3ea 4954 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4955 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4956 'modified_date': r're:\d{8}',
4957 'view_count': int,
4958 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4959 'tags': [],
4960 'channel': 'NoCopyrightSounds',
a6213a49 4961 },
4962 'playlist_mincount': 166,
976ae3ea 4963 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4964 }, {
4965 'note': 'Topic, should redirect to playlist?list=UU...',
4966 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4967 'info_dict': {
4968 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4969 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4970 'title': 'Uploads from Royalty Free Music - Topic',
4971 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4972 'tags': [],
4973 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4974 'channel': 'Royalty Free Music - Topic',
4975 'view_count': int,
4976 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4977 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4978 'modified_date': r're:\d{8}',
4979 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4980 'description': '',
a6213a49 4981 },
4982 'expected_warnings': [
a6213a49 4983 'The URL does not have a videos tab',
976ae3ea 4984 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4985 ],
4986 'playlist_mincount': 101,
4987 }, {
4988 'note': 'Topic without a UU playlist',
4989 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4990 'info_dict': {
4991 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4992 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4993 'tags': [],
a6213a49 4994 },
4995 'expected_warnings': [
976ae3ea 4996 'the playlist redirect gave error',
a6213a49 4997 ],
4998 'playlist_mincount': 9,
4999 }, {
5000 'note': 'Youtube music Album',
5001 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5002 'info_dict': {
5003 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5004 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5005 'tags': [],
5006 'view_count': int,
5007 'description': '',
5008 'availability': 'unlisted',
5009 'modified_date': r're:\d{8}',
a6213a49 5010 },
5011 'playlist_count': 50,
5012 }, {
5013 'note': 'unlisted single video playlist',
5014 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5015 'info_dict': {
5016 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5017 'uploader': 'colethedj',
5018 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5019 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5020 'availability': 'unlisted',
5021 'tags': [],
5022 'modified_date': '20211208',
5023 'channel': 'colethedj',
5024 'view_count': int,
5025 'description': '',
5026 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5027 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5028 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5029 },
5030 'playlist_count': 1,
5031 }, {
5032 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5033 'url': 'https://www.youtube.com/feed/recommended',
5034 'info_dict': {
5035 'id': 'recommended',
5036 'title': 'recommended',
6c73052c 5037 'tags': [],
a6213a49 5038 },
5039 'playlist_mincount': 50,
5040 'params': {
5041 'skip_download': True,
5042 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5043 },
5044 }, {
5045 'note': 'API Fallback: /videos tab, sorted by oldest first',
5046 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5047 'info_dict': {
5048 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5049 'title': 'Cody\'sLab - Videos',
5050 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5051 'uploader': 'Cody\'sLab',
5052 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5053 'channel': 'Cody\'sLab',
5054 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5055 'tags': [],
5056 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5057 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5058 'channel_follower_count': int
a6213a49 5059 },
5060 'playlist_mincount': 650,
5061 'params': {
5062 'skip_download': True,
5063 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5064 },
5065 }, {
5066 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5067 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5068 'info_dict': {
5069 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5070 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5071 'title': 'Uploads from Royalty Free Music - Topic',
5072 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5073 'modified_date': r're:\d{8}',
5074 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5075 'description': '',
5076 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5077 'tags': [],
5078 'channel': 'Royalty Free Music - Topic',
5079 'view_count': int,
5080 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5081 },
5082 'expected_warnings': [
976ae3ea 5083 'does not have a videos tab',
5084 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5085 ],
5086 'playlist_mincount': 101,
5087 'params': {
5088 'skip_download': True,
5089 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5090 },
7c219ea6 5091 }, {
5092 'note': 'non-standard redirect to regional channel',
5093 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5094 'only_matching': True
a6213a49 5095 }]
5096
5097 @classmethod
5098 def suitable(cls, url):
5099 return False if YoutubeIE.suitable(url) else super(
5100 YoutubeTabIE, cls).suitable(url)
9297939e 5101
64f36541 5102 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5103
182bda88 5104 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5105 def _real_extract(self, url, smuggled_data):
cd7c66cf 5106 item_id = self._match_id(url)
5107 url = compat_urlparse.urlunparse(
5108 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5109 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5110
fe03a6cd 5111 def get_mobj(url):
37e57a9f 5112 mobj = self._URL_RE.match(url).groupdict()
07cce701 5113 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5114 return mobj
5115
37e57a9f 5116 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5117 # Youtube returns incomplete data if tabname is not lower case
5118 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5119 if is_channel:
5120 if smuggled_data.get('is_music_url'):
37e57a9f 5121 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5122 item_id = item_id[2:]
37e57a9f 5123 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5124 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5125 mdata = self._extract_tab_endpoint(
37e57a9f 5126 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5127 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5128 get_all=False, expected_type=compat_str)
ac56cf38 5129 if not murl:
37e57a9f 5130 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5131 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5132 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5133 pre = f'https://www.youtube.com/channel/{item_id}'
5134
64f36541 5135 original_tab_name = tab
fe03a6cd 5136 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5137 # Home URLs should redirect to /videos/
37e57a9f 5138 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5139 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5140 tab = '/videos'
5141
5142 url = ''.join((pre, tab, post))
5143 mobj = get_mobj(url)
cd7c66cf 5144
5145 # Handle both video/playlist URLs
201c1459 5146 qs = parse_qs(url)
37e57a9f 5147 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5148
fe03a6cd 5149 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5150 if not playlist_id:
fe03a6cd 5151 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5152 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5153 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5154 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5155 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5156 mobj = get_mobj(url)
cd7c66cf 5157
5158 if video_id and playlist_id:
a06916d9 5159 if self.get_param('noplaylist'):
37e57a9f 5160 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5161 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5162 ie=YoutubeIE.ie_key(), video_id=video_id)
5163 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5164
ac56cf38 5165 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5166
7c219ea6 5167 # YouTube may provide a non-standard redirect to the regional channel
5168 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5169 redirect_url = traverse_obj(
5170 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5171 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5172 redirect_url = ''.join((
5173 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5174 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5175 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5176
37e57a9f 5177 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5178 if tabs:
5179 selected_tab = self._extract_selected_tab(tabs)
64f36541 5180 selected_tab_name = selected_tab.get('title', '').lower()
5181 if selected_tab_name == 'home':
5182 selected_tab_name = 'featured'
5183 requested_tab_name = mobj['tab'][1:]
09f1580e 5184 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5185 if requested_tab_name == 'live':
09f1580e 5186 # Live tab should have redirected to the video
5187 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5188 if requested_tab_name not in ('', selected_tab_name):
5189 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5190 if not original_tab_name:
5191 if item_id[:2] == 'UC':
5192 # Topic channels don't have /videos. Use the equivalent playlist instead
5193 pl_id = f'UU{item_id[2:]}'
5194 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5195 try:
5196 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5197 except ExtractorError:
5198 redirect_warning += ' and the playlist redirect gave error'
5199 else:
5200 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5201 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5202 if selected_tab_name and selected_tab_name != requested_tab_name:
5203 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5204 else:
5205 raise ExtractorError(redirect_warning, expected=True)
18db7548 5206
37e57a9f 5207 if redirect_warning:
64f36541 5208 self.to_screen(redirect_warning)
37e57a9f 5209 self.write_debug(f'Final URL: {url}')
18db7548 5210
358de58c 5211 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5212 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5213 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5214 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5215 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5216 if tabs:
ac56cf38 5217 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5218
37e57a9f 5219 playlist = traverse_obj(
5220 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5221 if playlist:
ac56cf38 5222 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5223
37e57a9f 5224 video_id = traverse_obj(
5225 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5226 if video_id:
09f1580e 5227 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5228 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5229 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5230 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5231
8bdd16b4 5232 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5233
c5e8d7af 5234
8bdd16b4 5235class YoutubePlaylistIE(InfoExtractor):
96565c7e 5236 IE_DESC = 'YouTube playlists'
8bdd16b4 5237 _VALID_URL = r'''(?x)(?:
5238 (?:https?://)?
5239 (?:\w+\.)?
5240 (?:
5241 (?:
5242 youtube(?:kids)?\.com|
d9190e44 5243 %(invidious)s
8bdd16b4 5244 )
5245 /.*?\?.*?\blist=
5246 )?
5247 (?P<id>%(playlist_id)s)
d9190e44
RH
5248 )''' % {
5249 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5250 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5251 }
8bdd16b4 5252 IE_NAME = 'youtube:playlist'
cdc628a4 5253 _TESTS = [{
8bdd16b4 5254 'note': 'issue #673',
5255 'url': 'PLBB231211A4F62143',
cdc628a4 5256 'info_dict': {
8bdd16b4 5257 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5258 'id': 'PLBB231211A4F62143',
976ae3ea 5259 'uploader': 'Wickman',
8bdd16b4 5260 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5261 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5262 'view_count': int,
5263 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5264 'modified_date': r're:\d{8}',
5265 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5266 'channel': 'Wickman',
5267 'tags': [],
5268 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5269 },
5270 'playlist_mincount': 29,
5271 }, {
5272 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5273 'info_dict': {
5274 'title': 'YDL_safe_search',
5275 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5276 },
5277 'playlist_count': 2,
5278 'skip': 'This playlist is private',
9558dcec 5279 }, {
8bdd16b4 5280 'note': 'embedded',
5281 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5282 'playlist_count': 4,
9558dcec 5283 'info_dict': {
8bdd16b4 5284 'title': 'JODA15',
5285 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5286 'uploader': 'milan',
5287 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5288 'description': '',
5289 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5290 'tags': [],
5291 'modified_date': '20140919',
5292 'view_count': int,
5293 'channel': 'milan',
5294 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5295 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5296 },
5297 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5298 }, {
8bdd16b4 5299 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5300 'playlist_mincount': 654,
8bdd16b4 5301 'info_dict': {
5302 'title': '2018 Chinese New Singles (11/6 updated)',
5303 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5304 'uploader': 'LBK',
5305 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5306 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5307 'channel': 'LBK',
5308 'view_count': int,
5309 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5310 'tags': [],
5311 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5312 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5313 'modified_date': r're:\d{8}',
5314 },
5315 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5316 }, {
29f7c58a 5317 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5318 'only_matching': True,
5319 }, {
5320 # music album playlist
5321 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5322 'only_matching': True,
5323 }]
5324
5325 @classmethod
5326 def suitable(cls, url):
201c1459 5327 if YoutubeTabIE.suitable(url):
5328 return False
49a57e70 5329 from ..utils import parse_qs
201c1459 5330 qs = parse_qs(url)
5331 if qs.get('v', [None])[0]:
5332 return False
5333 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5334
5335 def _real_extract(self, url):
5336 playlist_id = self._match_id(url)
46953e7e 5337 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5338 url = update_url_query(
5339 'https://www.youtube.com/playlist',
5340 parse_qs(url) or {'list': playlist_id})
5341 if is_music_url:
5342 url = smuggle_url(url, {'is_music_url': True})
5343 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5344
5345
5346class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5347 IE_DESC = 'youtu.be'
29f7c58a 5348 _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}
5349 _TESTS = [{
8bdd16b4 5350 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5351 'info_dict': {
5352 'id': 'yeWKywCrFtk',
5353 'ext': 'mp4',
5354 'title': 'Small Scale Baler and Braiding Rugs',
5355 'uploader': 'Backus-Page House Museum',
5356 'uploader_id': 'backuspagemuseum',
5357 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5358 'upload_date': '20161008',
5359 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5360 'categories': ['Nonprofits & Activism'],
5361 'tags': list,
5362 'like_count': int,
976ae3ea 5363 'age_limit': 0,
5364 'playable_in_embed': True,
5365 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5366 'channel': 'Backus-Page House Museum',
5367 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5368 'live_status': 'not_live',
5369 'view_count': int,
5370 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5371 'availability': 'public',
5372 'duration': 59,
8bdd16b4 5373 },
5374 'params': {
5375 'noplaylist': True,
5376 'skip_download': True,
5377 },
39e7107d 5378 }, {
8bdd16b4 5379 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5380 'only_matching': True,
cdc628a4
PH
5381 }]
5382
8bdd16b4 5383 def _real_extract(self, url):
5ad28e7f 5384 mobj = self._match_valid_url(url)
29f7c58a 5385 video_id = mobj.group('id')
5386 playlist_id = mobj.group('playlist_id')
8bdd16b4 5387 return self.url_result(
29f7c58a 5388 update_url_query('https://www.youtube.com/watch', {
5389 'v': video_id,
5390 'list': playlist_id,
5391 'feature': 'youtu.be',
5392 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5393
5394
b6ce9bb0 5395class YoutubeLivestreamEmbedIE(InfoExtractor):
5396 IE_DESC = 'YouTube livestream embeds'
5397 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5398 _TESTS = [{
5399 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5400 'only_matching': True,
5401 }]
5402
5403 def _real_extract(self, url):
5404 channel_id = self._match_id(url)
5405 return self.url_result(
5406 f'https://www.youtube.com/channel/{channel_id}/live',
5407 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5408
5409
8bdd16b4 5410class YoutubeYtUserIE(InfoExtractor):
96565c7e 5411 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5412 IE_NAME = 'youtube:user'
8bdd16b4 5413 _VALID_URL = r'ytuser:(?P<id>.+)'
5414 _TESTS = [{
5415 'url': 'ytuser:phihag',
5416 'only_matching': True,
5417 }]
5418
5419 def _real_extract(self, url):
5420 user_id = self._match_id(url)
5421 return self.url_result(
c586f9e8 5422 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5423 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5424
b05654f0 5425
3d3dddc9 5426class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5427 IE_NAME = 'youtube:favorites'
96565c7e 5428 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5429 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5430 _LOGIN_REQUIRED = True
5431 _TESTS = [{
5432 'url': ':ytfav',
5433 'only_matching': True,
5434 }, {
5435 'url': ':ytfavorites',
5436 'only_matching': True,
5437 }]
5438
5439 def _real_extract(self, url):
5440 return self.url_result(
5441 'https://www.youtube.com/playlist?list=LL',
5442 ie=YoutubeTabIE.ie_key())
5443
5444
a6213a49 5445class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5446 IE_DESC = 'YouTube search'
78caa52a 5447 IE_NAME = 'youtube:search'
b05654f0 5448 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5449 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5450 _TESTS = [{
5451 'url': 'ytsearch5:youtube-dl test video',
5452 'playlist_count': 5,
5453 'info_dict': {
5454 'id': 'youtube-dl test video',
5455 'title': 'youtube-dl test video',
5456 }
5457 }]
b05654f0 5458
a61fd4cf 5459
5f7cb91a 5460class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5461 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5462 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5463 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5464 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5465 _TESTS = [{
5466 'url': 'ytsearchdate5:youtube-dl test video',
5467 'playlist_count': 5,
5468 'info_dict': {
5469 'id': 'youtube-dl test video',
5470 'title': 'youtube-dl test video',
5471 }
5472 }]
75dff0ee 5473
c9ae7b95 5474
a6213a49 5475class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5476 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5477 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5478 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5479 _TESTS = [{
5480 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5481 'playlist_mincount': 5,
5482 'info_dict': {
11f9be09 5483 'id': 'youtube-dl test video',
3462ffa8 5484 'title': 'youtube-dl test video',
5485 }
a61fd4cf 5486 }, {
5487 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5488 'playlist_mincount': 5,
5489 'info_dict': {
5490 'id': 'python',
5491 'title': 'python',
5492 }
5493
3462ffa8 5494 }, {
5495 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5496 'only_matching': True,
5497 }]
5498
5499 def _real_extract(self, url):
4dfbf869 5500 qs = parse_qs(url)
386e1dd9 5501 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5502 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5503
5504
16aa9ea4 5505class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5506 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5507 IE_NAME = 'youtube:music:search_url'
5508 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5509 _TESTS = [{
5510 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5511 'playlist_count': 16,
5512 'info_dict': {
5513 'id': 'royalty free music',
5514 'title': 'royalty free music',
5515 }
5516 }, {
5517 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5518 'playlist_mincount': 30,
5519 'info_dict': {
5520 'id': 'royalty free music - songs',
5521 'title': 'royalty free music - songs',
5522 },
5523 'params': {'extract_flat': 'in_playlist'}
5524 }, {
5525 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5526 'playlist_mincount': 30,
5527 'info_dict': {
5528 'id': 'royalty free music - community playlists',
5529 'title': 'royalty free music - community playlists',
5530 },
5531 'params': {'extract_flat': 'in_playlist'}
5532 }]
5533
5534 _SECTIONS = {
5535 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5536 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5537 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5538 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5539 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5540 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5541 }
5542
5543 def _real_extract(self, url):
5544 qs = parse_qs(url)
5545 query = (qs.get('search_query') or qs.get('q'))[0]
5546 params = qs.get('sp', (None,))[0]
5547 if params:
5548 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5549 else:
5550 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5551 params = self._SECTIONS.get(section)
5552 if not params:
5553 section = None
5554 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5555 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5556
5557
182bda88 5558class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5559 """
25f14e9f 5560 Base class for feed extractors
3d3dddc9 5561 Subclasses must define the _FEED_NAME property.
d7ae0639 5562 """
b2e8bc1b 5563 _LOGIN_REQUIRED = True
ef2f3c7f 5564 _TESTS = []
d7ae0639
JMF
5565
5566 @property
5567 def IE_NAME(self):
78caa52a 5568 return 'youtube:%s' % self._FEED_NAME
04cc9617 5569
3853309f 5570 def _real_extract(self, url):
3d3dddc9 5571 return self.url_result(
182bda88 5572 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5573
5574
ef2f3c7f 5575class YoutubeWatchLaterIE(InfoExtractor):
5576 IE_NAME = 'youtube:watchlater'
96565c7e 5577 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5578 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5579 _TESTS = [{
8bdd16b4 5580 'url': ':ytwatchlater',
bc7a9cd8
S
5581 'only_matching': True,
5582 }]
25f14e9f
S
5583
5584 def _real_extract(self, url):
ef2f3c7f 5585 return self.url_result(
5586 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5587
5588
25f14e9f 5589class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5590 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5591 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5592 _FEED_NAME = 'recommended'
45db527f 5593 _LOGIN_REQUIRED = False
3d3dddc9 5594 _TESTS = [{
5595 'url': ':ytrec',
5596 'only_matching': True,
5597 }, {
5598 'url': ':ytrecommended',
5599 'only_matching': True,
5600 }, {
5601 'url': 'https://youtube.com',
5602 'only_matching': True,
5603 }]
1ed5b5c9 5604
1ed5b5c9 5605
25f14e9f 5606class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5607 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5608 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5609 _FEED_NAME = 'subscriptions'
3d3dddc9 5610 _TESTS = [{
5611 'url': ':ytsubs',
5612 'only_matching': True,
5613 }, {
5614 'url': ':ytsubscriptions',
5615 'only_matching': True,
5616 }]
1ed5b5c9 5617
1ed5b5c9 5618
25f14e9f 5619class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5620 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5621 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5622 _FEED_NAME = 'history'
3d3dddc9 5623 _TESTS = [{
5624 'url': ':ythistory',
5625 'only_matching': True,
5626 }]
1ed5b5c9
JMF
5627
5628
15870e90
PH
5629class YoutubeTruncatedURLIE(InfoExtractor):
5630 IE_NAME = 'youtube:truncated_url'
5631 IE_DESC = False # Do not list
975d35db 5632 _VALID_URL = r'''(?x)
b95aab84
PH
5633 (?:https?://)?
5634 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5635 (?:watch\?(?:
c4808c60 5636 feature=[a-z_]+|
b95aab84
PH
5637 annotation_id=annotation_[^&]+|
5638 x-yt-cl=[0-9]+|
c1708b89 5639 hl=[^&]*|
287be8c6 5640 t=[0-9]+
b95aab84
PH
5641 )?
5642 |
5643 attribution_link\?a=[^&]+
5644 )
5645 $
975d35db 5646 '''
15870e90 5647
c4808c60 5648 _TESTS = [{
2d3d2997 5649 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5650 'only_matching': True,
dc2fc736 5651 }, {
2d3d2997 5652 'url': 'https://www.youtube.com/watch?',
dc2fc736 5653 'only_matching': True,
b95aab84
PH
5654 }, {
5655 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5656 'only_matching': True,
5657 }, {
5658 'url': 'https://www.youtube.com/watch?feature=foo',
5659 'only_matching': True,
c1708b89
PH
5660 }, {
5661 'url': 'https://www.youtube.com/watch?hl=en-GB',
5662 'only_matching': True,
287be8c6
PH
5663 }, {
5664 'url': 'https://www.youtube.com/watch?t=2372',
5665 'only_matching': True,
c4808c60
PH
5666 }]
5667
15870e90
PH
5668 def _real_extract(self, url):
5669 raise ExtractorError(
78caa52a
PH
5670 'Did you forget to quote the URL? Remember that & is a meta '
5671 'character in most shells, so you want to put the URL in quotes, '
3867038a 5672 'like youtube-dl '
2d3d2997 5673 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5674 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5675 expected=True)
772fd5cc
PH
5676
5677
3cd786db 5678class YoutubeClipIE(InfoExtractor):
5679 IE_NAME = 'youtube:clip'
5680 IE_DESC = False # Do not list
5681 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5682
5683 def _real_extract(self, url):
5684 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5685 return self.url_result(url, 'Generic')
5686
5687
772fd5cc
PH
5688class YoutubeTruncatedIDIE(InfoExtractor):
5689 IE_NAME = 'youtube:truncated_id'
5690 IE_DESC = False # Do not list
b95aab84 5691 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5692
5693 _TESTS = [{
5694 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5695 'only_matching': True,
5696 }]
5697
5698 def _real_extract(self, url):
5699 video_id = self._match_id(url)
5700 raise ExtractorError(
5701 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5702 expected=True)