]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[youtube:api] Prefer minified JSON response
[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
b2e8bc1b 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
b2e8bc1b 337 def _login(self):
83317f69 338 """
339 Attempt to log in to YouTube.
83317f69 340 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
341 """
9d5d4d64 342
982ee69a
MB
343 if (self._LOGIN_REQUIRED
344 and self.get_param('cookiefile') is None
345 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 346 self.raise_login_required(
347 'Login details are needed to download this content', method='cookies')
68217024 348 username, password = self._get_login_info()
9d5d4d64 349 if username:
24b0a72b 350 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
b2e8bc1b 351
cce889b9 352 def _initialize_consent(self):
353 cookies = self._get_cookies('https://www.youtube.com/')
354 if cookies.get('__Secure-3PSID'):
355 return
356 consent_id = None
357 consent = cookies.get('CONSENT')
358 if consent:
359 if 'YES' in consent.value:
360 return
361 consent_id = self._search_regex(
362 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
363 if not consent_id:
364 consent_id = random.randint(100, 999)
365 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 366
f3aa3c3f 367 def _initialize_pref(self):
368 cookies = self._get_cookies('https://www.youtube.com/')
369 pref_cookie = cookies.get('PREF')
370 pref = {}
371 if pref_cookie:
372 try:
373 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
374 except ValueError:
375 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 376 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 377 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
378
b2e8bc1b 379 def _real_initialize(self):
f3aa3c3f 380 self._initialize_pref()
cce889b9 381 self._initialize_consent()
24b0a72b 382 self._login()
c5e8d7af 383
a0566bbf 384 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 385 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 387
000c15a4 388 def _get_default_ytcfg(self, client='web'):
389 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 390
000c15a4 391 def _get_innertube_host(self, client='web'):
392 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 393
000c15a4 394 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 395 # try_get but with fallback to default ytcfg client values when present
396 _func = lambda y: try_get(y, getter, expected_type)
397 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
398
000c15a4 399 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 400 return self._ytcfg_get_safe(
401 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
402 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 403
000c15a4 404 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 405 return self._ytcfg_get_safe(
406 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
407 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 408
000c15a4 409 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 410 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
411
000c15a4 412 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 413 context = get_first(
414 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 415 # Enforce language and tz for extraction
416 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
417 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 418 return context
419
cf87314d 420 _SAPISID = None
421
109dd3b2 422 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 423 time_now = round(time.time())
cf87314d 424 if self._SAPISID is None:
425 yt_cookies = self._get_cookies('https://www.youtube.com')
426 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
427 # See: https://github.com/yt-dlp/yt-dlp/issues/393
428 sapisid_cookie = dict_get(
429 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
430 if sapisid_cookie and sapisid_cookie.value:
431 self._SAPISID = sapisid_cookie.value
432 self.write_debug('Extracted SAPISID cookie')
433 # SAPISID cookie is required if not already present
434 if not yt_cookies.get('SAPISID'):
435 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
436 self._set_cookie(
437 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
438 else:
439 self._SAPISID = False
440 if not self._SAPISID:
441 return None
1974e99f 442 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
443 sapisidhash = hashlib.sha1(
cf87314d 444 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 445 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
446
447 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 448 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 449 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 450
109dd3b2 451 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 452 data.update(query)
11f9be09 453 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 454 real_headers.update({'content-type': 'application/json'})
455 if headers:
456 real_headers.update(headers)
545cc85d 457 return self._download_json(
109dd3b2 458 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 459 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 460 data=json.dumps(data).encode('utf8'), headers=real_headers,
5dbc77df 461 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
f4f751af 462
ac56cf38 463 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
464 data = self._search_regex(
465 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
466 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
467 if data:
468 return self._parse_json(data, item_id, fatal=fatal)
0c148415 469
99e9e001 470 @staticmethod
471 def _extract_session_index(*data):
472 """
473 Index of current account in account list.
474 See: https://github.com/yt-dlp/yt-dlp/pull/519
475 """
476 for ytcfg in data:
477 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
478 if session_index is not None:
479 return session_index
480
481 # Deprecated?
482 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
483 if ytcfg:
484 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
485 if token:
486 return token
99e9e001 487 if webpage:
488 return self._search_regex(
489 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
490 'identity token', default=None, fatal=False)
a1c5d2ca
M
491
492 @staticmethod
fe93e2c4 493 def _extract_account_syncid(*args):
8ea3f7b9 494 """
495 Extract syncId required to download private playlists of secondary channels
fe93e2c4 496 @params response and/or ytcfg
8ea3f7b9 497 """
fe93e2c4 498 for data in args:
499 # ytcfg includes channel_syncid if on secondary channel
500 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
501 if delegated_sid:
502 return delegated_sid
503 sync_ids = (try_get(
504 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 505 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 506 if len(sync_ids) >= 2 and sync_ids[1]:
507 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
508 # and just "user_syncid||" for primary channel. We only want the channel_syncid
509 return sync_ids[0]
a1c5d2ca 510
ac56cf38 511 @staticmethod
512 def _extract_visitor_data(*args):
513 """
514 Extracts visitorData from an API response or ytcfg
515 Appears to be used to track session state
516 """
9222c381 517 return get_first(
6c73052c 518 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 519 expected_type=str)
ac56cf38 520
99e9e001 521 @property
522 def is_authenticated(self):
523 return bool(self._generate_sapisidhash_header())
524
11f9be09 525 def extract_ytcfg(self, video_id, webpage):
8c54a305 526 if not webpage:
527 return {}
29f7c58a 528 return self._parse_json(
529 self._search_regex(
530 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 531 default='{}'), video_id, fatal=False) or {}
532
11f9be09 533 def generate_api_headers(
99e9e001 534 self, *, ytcfg=None, account_syncid=None, session_index=None,
535 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
536
11f9be09 537 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 538 headers = {
109dd3b2 539 'X-YouTube-Client-Name': compat_str(
11f9be09 540 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
541 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 542 'Origin': origin,
543 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
544 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 545 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 546 }
547 if session_index is None:
314ee305 548 session_index = self._extract_session_index(ytcfg)
549 if account_syncid or session_index is not None:
550 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 551
109dd3b2 552 auth = self._generate_sapisidhash_header(origin)
f4f751af 553 if auth is not None:
554 headers['Authorization'] = auth
109dd3b2 555 headers['X-Origin'] = origin
99e9e001 556 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 557
2d6659b9 558 @staticmethod
559 def _build_api_continuation_query(continuation, ctp=None):
560 query = {
561 'continuation': continuation
562 }
563 # TODO: Inconsistency with clickTrackingParams.
564 # Currently we have a fixed ctp contained within context (from ytcfg)
565 # and a ctp in root query for continuation.
566 if ctp:
567 query['clickTracking'] = {'clickTrackingParams': ctp}
568 return query
569
2d6659b9 570 @classmethod
571 def _extract_next_continuation_data(cls, renderer):
572 next_continuation = try_get(
573 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
574 lambda x: x['continuation']['reloadContinuationData']), dict)
575 if not next_continuation:
576 return
577 continuation = next_continuation.get('continuation')
578 if not continuation:
579 return
580 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 581 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 582
583 @classmethod
584 def _extract_continuation_ep_data(cls, continuation_ep: dict):
585 if isinstance(continuation_ep, dict):
586 continuation = try_get(
587 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
588 if not continuation:
589 return
590 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 591 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 592
593 @classmethod
594 def _extract_continuation(cls, renderer):
595 next_continuation = cls._extract_next_continuation_data(renderer)
596 if next_continuation:
597 return next_continuation
fe93e2c4 598
2d6659b9 599 contents = []
600 for key in ('contents', 'items'):
601 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 602
2d6659b9 603 for content in contents:
604 if not isinstance(content, dict):
605 continue
606 continuation_ep = try_get(
607 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
608 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
609 dict)
610 continuation = cls._extract_continuation_ep_data(continuation_ep)
611 if continuation:
612 return continuation
613
fe93e2c4 614 @classmethod
615 def _extract_alerts(cls, data):
109dd3b2 616 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
617 if not isinstance(alert_dict, dict):
618 continue
619 for alert in alert_dict.values():
620 alert_type = alert.get('type')
621 if not alert_type:
622 continue
052e1350 623 message = cls._get_text(alert, 'text')
109dd3b2 624 if message:
625 yield alert_type, message
626
c0ac49bc 627 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 628 errors = []
629 warnings = []
630 for alert_type, alert_message in alerts:
641ad5d8 631 if alert_type.lower() == 'error' and fatal:
109dd3b2 632 errors.append([alert_type, alert_message])
633 else:
634 warnings.append([alert_type, alert_message])
635
636 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 637 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 638 if errors:
639 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
640
641 def _extract_and_report_alerts(self, data, *args, **kwargs):
642 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
643
47193e02 644 def _extract_badges(self, renderer: dict):
645 badges = set()
646 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
647 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
648 if label:
649 badges.add(label.lower())
650 return badges
651
652 @staticmethod
052e1350 653 def _get_text(data, *path_list, max_runs=None):
654 for path in path_list or [None]:
655 if path is None:
656 obj = [data]
657 else:
658 obj = traverse_obj(data, path, default=[])
659 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
660 obj = [obj]
661 for item in obj:
662 text = try_get(item, lambda x: x['simpleText'], compat_str)
663 if text:
664 return text
665 runs = try_get(item, lambda x: x['runs'], list) or []
666 if not runs and isinstance(item, list):
667 runs = item
668
669 runs = runs[:min(len(runs), max_runs or len(runs))]
670 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
671 if text:
672 return text
47193e02 673
f0d785d3 674 def _get_count(self, data, *path_list):
675 count_text = self._get_text(data, *path_list) or ''
676 count = parse_count(count_text)
677 if count is None:
678 count = str_to_int(
679 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
680 return count
681
a709d873 682 @staticmethod
683 def _extract_thumbnails(data, *path_list):
684 """
685 Extract thumbnails from thumbnails dict
686 @param path_list: path list to level that contains 'thumbnails' key
687 """
688 thumbnails = []
689 for path in path_list or [()]:
690 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
691 thumbnail_url = url_or_none(thumbnail.get('url'))
692 if not thumbnail_url:
693 continue
694 # Sometimes youtube gives a wrong thumbnail URL. See:
695 # https://github.com/yt-dlp/yt-dlp/issues/233
696 # https://github.com/ytdl-org/youtube-dl/issues/28023
697 if 'maxresdefault' in thumbnail_url:
698 thumbnail_url = thumbnail_url.split('?')[0]
699 thumbnails.append({
700 'url': thumbnail_url,
701 'height': int_or_none(thumbnail.get('height')),
702 'width': int_or_none(thumbnail.get('width')),
703 })
704 return thumbnails
705
f3aa3c3f 706 @staticmethod
707 def extract_relative_time(relative_time_text):
708 """
709 Extracts a relative time from string and converts to dt object
f0d785d3 710 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 711 """
f0d785d3 712 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 713 if mobj:
f0d785d3 714 start = mobj.group('start')
715 if start:
716 return datetime_from_str(start)
f3aa3c3f 717 try:
f0d785d3 718 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 719 except ValueError:
720 return None
721
722 def _extract_time_text(self, renderer, *path_list):
723 text = self._get_text(renderer, *path_list) or ''
724 dt = self.extract_relative_time(text)
725 timestamp = None
726 if isinstance(dt, datetime.datetime):
727 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 728
729 if timestamp is None:
730 timestamp = (
731 unified_timestamp(text) or unified_timestamp(
732 self._search_regex(
17322130 733 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 734 text.lower(), 'time text', default=None)))
f0d785d3 735
f3aa3c3f 736 if text and timestamp is None:
17322130 737 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 738 return timestamp, text
739
109dd3b2 740 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
741 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 742 default_client='web'):
109dd3b2 743 response = None
744 last_error = None
745 count = -1
746 retries = self.get_param('extractor_retries', 3)
747 if check_get_keys is None:
748 check_get_keys = []
749 while count < retries:
750 count += 1
751 if last_error:
c0ac49bc 752 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 753 try:
754 response = self._call_api(
755 ep=ep, fatal=True, headers=headers,
756 video_id=item_id, query=query,
757 context=self._extract_context(ytcfg, default_client),
758 api_key=self._extract_api_key(ytcfg, default_client),
759 api_hostname=api_hostname, default_client=default_client,
760 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
761 except ExtractorError as e:
9c0d7f49 762 if isinstance(e.cause, network_exceptions):
87e8e8a7 763 if isinstance(e.cause, compat_HTTPError):
764 first_bytes = e.cause.read(512)
765 if not is_html(first_bytes):
766 yt_error = try_get(
767 self._parse_json(
768 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
769 lambda x: x['error']['message'], compat_str)
770 if yt_error:
771 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 772 # Downloading page may result in intermittent 5xx HTTP error
773 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 774 # We also want to catch all other network exceptions since errors in later pages can be troublesome
775 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
776 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 777 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 778 if count < retries:
779 continue
109dd3b2 780 if fatal:
781 raise
782 else:
783 self.report_warning(error_to_compat_str(e))
784 return
785
786 else:
109dd3b2 787 try:
ac56cf38 788 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 789 except ExtractorError as e:
c0ac49bc 790 # YouTube servers may return errors we want to retry on in a 200 OK response
791 # See: https://github.com/yt-dlp/yt-dlp/issues/839
792 if 'unknown error' in e.msg.lower():
793 last_error = e.msg
794 continue
109dd3b2 795 if fatal:
796 raise
797 self.report_warning(error_to_compat_str(e))
798 return
799 if not check_get_keys or dict_get(response, check_get_keys):
800 break
801 # Youtube sometimes sends incomplete data
802 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
803 last_error = 'Incomplete data received'
804 if count >= retries:
805 if fatal:
806 raise ExtractorError(last_error)
807 else:
808 self.report_warning(last_error)
809 return
810 return response
811
9297939e 812 @staticmethod
813 def is_music_url(url):
814 return re.match(r'https?://music\.youtube\.com/', url) is not None
815
30a074c2 816 def _extract_video(self, renderer):
817 video_id = renderer.get('videoId')
052e1350 818 title = self._get_text(renderer, 'title')
819 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 820 duration = parse_duration(self._get_text(
821 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
f0d785d3 822 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 823
052e1350 824 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 825 channel_id = traverse_obj(
826 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
827 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
828 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
829 overlay_style = traverse_obj(
830 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
831 badges = self._extract_badges(renderer)
a709d873 832 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
833
30a074c2 834 return {
39ed931e 835 '_type': 'url',
30a074c2 836 'ie_key': YoutubeIE.ie_key(),
837 'id': video_id,
5e3f2f8f 838 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 839 'title': title,
840 'description': description,
841 'duration': duration,
842 'view_count': view_count,
843 'uploader': uploader,
f3aa3c3f 844 'channel_id': channel_id,
a709d873 845 'thumbnails': thumbnails,
a30a6ed3 846 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 847 'live_status': ('is_upcoming' if scheduled_timestamp is not None
848 else 'was_live' if 'streamed' in time_text.lower()
849 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
850 else None),
851 'release_timestamp': scheduled_timestamp,
852 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 853 }
854
0c148415 855
360e1ca5 856class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 857 IE_DESC = 'YouTube'
cb7dfeea 858 _VALID_URL = r"""(?x)^
c5e8d7af 859 (
edb53e2d 860 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 861 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
862 (?:www\.)?deturl\.com/www\.youtube\.com|
863 (?:www\.)?pwnyoutube\.com|
864 (?:www\.)?hooktube\.com|
865 (?:www\.)?yourepeat\.com|
866 tube\.majestyc\.net|
867 %(invidious)s|
868 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
869 (?:.*?\#/)? # handle anchor (#/) redirect urls
870 (?: # the various things that can precede the ID:
b6ce9bb0 871 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 872 |(?: # or the v= param in all its forms
f7000f3a 873 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 874 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 875 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
876 v=
877 )
f4b05232 878 ))
cbaed4bb
S
879 |(?:
880 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
881 vid\.plus| # or vid.plus/xxxx
882 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 883 %(invidious)s
cbaed4bb 884 )/
edb53e2d 885 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 886 )
c5e8d7af 887 )? # all until now is optional -> you can pass the naked ID
201c1459 888 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 889 (?(1).+)? # if we found the ID, everything can follow
9297939e 890 (?:\#|$)""" % {
d9190e44 891 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 892 }
e40c758c 893 _PLAYER_INFO_RE = (
cc2db878 894 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
895 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 896 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 897 )
2c62dc26 898 _formats = {
c2d3cb4c 899 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
900 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
901 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
902 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
903 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
904 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
905 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
906 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 907 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 908 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
909 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
910 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
911 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
912 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
913 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 914 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 915 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
916 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 917
918
919 # 3D videos
c2d3cb4c 920 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
921 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
922 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
923 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 924 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
925 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
926 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 927
96fb5605 928 # Apple HTTP Live Streaming
11f12195 929 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 930 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
931 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
932 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
933 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
934 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 935 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
936 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
937
938 # DASH mp4 video
d23028a8
S
939 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
940 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
942 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
943 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 944 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
945 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
946 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
947 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
948 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
949 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
950 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 951
f6f1fc92 952 # Dash mp4 audio
d23028a8
S
953 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
954 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
955 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
956 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
957 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
958 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
959 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
960
961 # Dash webm
d23028a8
S
962 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
963 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
967 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
968 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
969 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
970 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
976 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 977 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
978 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
979 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
980 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
981 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
982 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
983 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
984
985 # Dash webm audio
d23028a8
S
986 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
987 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 988
0857baad 989 # Dash webm audio with opus inside
d23028a8
S
990 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
991 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
992 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 993
ce6b9a2d
PH
994 # RTMP (unnamed)
995 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
996
997 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
998 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
999 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1000 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1001 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1002 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1003 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1004 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1005 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1006 }
29f7c58a 1007 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1008
fd5c4aab
S
1009 _GEO_BYPASS = False
1010
78caa52a 1011 IE_NAME = 'youtube'
2eb88d95
PH
1012 _TESTS = [
1013 {
2d3d2997 1014 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1015 'info_dict': {
1016 'id': 'BaW_jenozKc',
1017 'ext': 'mp4',
3867038a 1018 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1019 'uploader': 'Philipp Hagemeister',
1020 'uploader_id': 'phihag',
ec85ded8 1021 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1022 'channel': 'Philipp Hagemeister',
dd4c4492
S
1023 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1024 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1025 'upload_date': '20121002',
ff9f925b 1026 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1027 'categories': ['Science & Technology'],
3867038a 1028 'tags': ['youtube-dl'],
556dbe7f 1029 'duration': 10,
dbdaaa23 1030 'view_count': int,
3e7c1224 1031 'like_count': int,
ff9f925b 1032 'availability': 'public',
1033 'playable_in_embed': True,
1034 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1035 'live_status': 'not_live',
1036 'age_limit': 0,
7c80519c 1037 'start_time': 1,
297a564b 1038 'end_time': 9,
6c73052c 1039 'channel_follower_count': int
2eb88d95 1040 }
0e853ca4 1041 },
fccd3771 1042 {
4bc3a23e
PH
1043 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1044 'note': 'Embed-only video (#1746)',
1045 'info_dict': {
1046 'id': 'yZIXLfi8CZQ',
1047 'ext': 'mp4',
1048 'upload_date': '20120608',
1049 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1050 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1051 'uploader': 'SET India',
94bfcd23 1052 'uploader_id': 'setindia',
ec85ded8 1053 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1054 'age_limit': 18,
545cc85d 1055 },
1056 'skip': 'Private video',
fccd3771 1057 },
11b56058 1058 {
8bdd16b4 1059 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1060 'note': 'Use the first video ID in the URL',
1061 'info_dict': {
1062 'id': 'BaW_jenozKc',
1063 'ext': 'mp4',
3867038a 1064 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1065 'uploader': 'Philipp Hagemeister',
1066 'uploader_id': 'phihag',
ec85ded8 1067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1068 'channel': 'Philipp Hagemeister',
1069 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1070 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1071 'upload_date': '20121002',
976ae3ea 1072 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1073 'categories': ['Science & Technology'],
3867038a 1074 'tags': ['youtube-dl'],
556dbe7f 1075 'duration': 10,
dbdaaa23 1076 'view_count': int,
11b56058 1077 'like_count': int,
976ae3ea 1078 'availability': 'public',
1079 'playable_in_embed': True,
1080 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1081 'live_status': 'not_live',
1082 'age_limit': 0,
6c73052c 1083 'channel_follower_count': int
34a7de29
S
1084 },
1085 'params': {
1086 'skip_download': True,
1087 },
11b56058 1088 },
dd27fd17 1089 {
2d3d2997 1090 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1091 'note': '256k DASH audio (format 141) via DASH manifest',
1092 'info_dict': {
1093 'id': 'a9LDPn-MO4I',
1094 'ext': 'm4a',
1095 'upload_date': '20121002',
1096 'uploader_id': '8KVIDEO',
ec85ded8 1097 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1098 'description': '',
1099 'uploader': '8KVIDEO',
1100 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1101 },
4bc3a23e
PH
1102 'params': {
1103 'youtube_include_dash_manifest': True,
1104 'format': '141',
4919603f 1105 },
de3c7fe0 1106 'skip': 'format 141 not served anymore',
dd27fd17 1107 },
8bdd16b4 1108 # DASH manifest with encrypted signature
1109 {
1110 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1111 'info_dict': {
1112 'id': 'IB3lcPjvWLA',
1113 'ext': 'm4a',
1114 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1115 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1116 'duration': 244,
1117 'uploader': 'AfrojackVEVO',
1118 'uploader_id': 'AfrojackVEVO',
1119 'upload_date': '20131011',
cc2db878 1120 'abr': 129.495,
976ae3ea 1121 'like_count': int,
1122 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1123 'playable_in_embed': True,
1124 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1125 'view_count': int,
1126 'track': 'The Spark',
1127 'live_status': 'not_live',
1128 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1129 'channel': 'Afrojack',
1130 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1131 'tags': 'count:19',
1132 'availability': 'public',
1133 'categories': ['Music'],
1134 'age_limit': 0,
1135 'alt_title': 'The Spark',
6c73052c 1136 'channel_follower_count': int
8bdd16b4 1137 },
1138 'params': {
1139 'youtube_include_dash_manifest': True,
1140 'format': '141/bestaudio[ext=m4a]',
1141 },
1142 },
65c2fde2 1143 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1144 {
65c2fde2 1145 'note': 'Embed allowed age-gate video',
2d3d2997 1146 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1147 'info_dict': {
1148 'id': 'HtVdAasjOgU',
1149 'ext': 'mp4',
1150 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1151 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1152 'duration': 142,
c522adb1
JMF
1153 'uploader': 'The Witcher',
1154 'uploader_id': 'WitcherGame',
ec85ded8 1155 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1156 'upload_date': '20140605',
34952f09 1157 'age_limit': 18,
976ae3ea 1158 'categories': ['Gaming'],
1159 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1160 'availability': 'needs_auth',
1161 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1162 'like_count': int,
1163 'channel': 'The Witcher',
1164 'live_status': 'not_live',
1165 'tags': 'count:17',
1166 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1167 'playable_in_embed': True,
1168 'view_count': int,
6c73052c 1169 'channel_follower_count': int
c522adb1
JMF
1170 },
1171 },
65c2fde2 1172 {
1173 'note': 'Age-gate video with embed allowed in public site',
1174 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1175 'info_dict': {
1176 'id': 'HsUATh_Nc2U',
1177 'ext': 'mp4',
1178 'title': 'Godzilla 2 (Official Video)',
1179 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1180 'upload_date': '20200408',
1181 'uploader_id': 'FlyingKitty900',
1182 'uploader': 'FlyingKitty',
1183 'age_limit': 18,
976ae3ea 1184 'availability': 'needs_auth',
1185 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1186 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1187 'channel': 'FlyingKitty',
1188 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1189 'view_count': int,
1190 'categories': ['Entertainment'],
1191 'live_status': 'not_live',
1192 'tags': ['Flyingkitty', 'godzilla 2'],
1193 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1194 'like_count': int,
1195 'duration': 177,
1196 'playable_in_embed': True,
6c73052c 1197 'channel_follower_count': int
65c2fde2 1198 },
1199 },
1200 {
1201 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1202 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1203 'info_dict': {
1204 'id': 'Tq92D6wQ1mg',
1205 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1206 'ext': 'mp4',
17322130 1207 'upload_date': '20191228',
65c2fde2 1208 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1209 'uploader': 'Projekt Melody',
1210 'description': 'md5:17eccca93a786d51bc67646756894066',
1211 'age_limit': 18,
976ae3ea 1212 'like_count': int,
1213 'availability': 'needs_auth',
1214 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1215 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1216 'view_count': int,
1217 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1218 'channel': 'Projekt Melody',
1219 'live_status': 'not_live',
1220 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1221 'playable_in_embed': True,
1222 'categories': ['Entertainment'],
1223 'duration': 106,
1224 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1225 'channel_follower_count': int
65c2fde2 1226 },
1227 },
1228 {
1229 'note': 'Non-Agegated non-embeddable video',
1230 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1231 'info_dict': {
1232 'id': 'MeJVWBSsPAY',
1233 'ext': 'mp4',
1234 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1235 'uploader': 'Herr Lurik',
1236 'uploader_id': 'st3in234',
1237 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1238 'upload_date': '20130730',
976ae3ea 1239 'track': 'Such mich find mich',
1240 'age_limit': 0,
1241 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1242 'like_count': int,
1243 'playable_in_embed': False,
1244 'creator': 'OOMPH!',
1245 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1246 'view_count': int,
1247 'alt_title': 'Such mich find mich',
1248 'duration': 210,
1249 'channel': 'Herr Lurik',
1250 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1251 'categories': ['Music'],
1252 'availability': 'public',
1253 'uploader_url': 'http://www.youtube.com/user/st3in234',
1254 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1255 'live_status': 'not_live',
1256 'artist': 'OOMPH!',
6c73052c 1257 'channel_follower_count': int
65c2fde2 1258 },
1259 },
1260 {
1261 'note': 'Non-bypassable age-gated video',
1262 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1263 'only_matching': True,
1264 },
8bdd16b4 1265 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1266 # YouTube Red ad is not captured for creator
1267 {
1268 'url': '__2ABJjxzNo',
1269 'info_dict': {
1270 'id': '__2ABJjxzNo',
1271 'ext': 'mp4',
1272 'duration': 266,
1273 'upload_date': '20100430',
1274 'uploader_id': 'deadmau5',
1275 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1276 'creator': 'deadmau5',
1277 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1278 'uploader': 'deadmau5',
1279 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1280 'alt_title': 'Some Chords',
976ae3ea 1281 'availability': 'public',
1282 'tags': 'count:14',
1283 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1284 'view_count': int,
1285 'live_status': 'not_live',
1286 'channel': 'deadmau5',
1287 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1288 'like_count': int,
1289 'track': 'Some Chords',
1290 'artist': 'deadmau5',
1291 'playable_in_embed': True,
1292 'age_limit': 0,
1293 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1294 'categories': ['Music'],
1295 'album': 'Some Chords',
6c73052c 1296 'channel_follower_count': int
8bdd16b4 1297 },
1298 'expected_warnings': [
1299 'DASH manifest missing',
17322130 1300 'Some formats are possibly damaged'
8bdd16b4 1301 ]
1302 },
067aa17e 1303 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1304 {
1305 'url': 'lqQg6PlCWgI',
1306 'info_dict': {
1307 'id': 'lqQg6PlCWgI',
1308 'ext': 'mp4',
556dbe7f 1309 'duration': 6085,
90227264 1310 'upload_date': '20150827',
cbe2bd91 1311 'uploader_id': 'olympic',
ec85ded8 1312 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1313 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1314 'uploader': 'Olympics',
cbe2bd91 1315 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1316 'like_count': int,
1317 'release_timestamp': 1343767800,
1318 'playable_in_embed': True,
1319 'categories': ['Sports'],
1320 'release_date': '20120731',
1321 'channel': 'Olympics',
1322 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1323 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1324 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1325 'age_limit': 0,
1326 'availability': 'public',
1327 'live_status': 'was_live',
1328 'view_count': int,
1329 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1330 'channel_follower_count': int
cbe2bd91
PH
1331 },
1332 'params': {
1333 'skip_download': 'requires avconv',
e52a40ab 1334 }
cbe2bd91 1335 },
6271f1ca
PH
1336 # Non-square pixels
1337 {
1338 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1339 'info_dict': {
1340 'id': '_b-2C3KPAM0',
1341 'ext': 'mp4',
1342 'stretched_ratio': 16 / 9.,
556dbe7f 1343 'duration': 85,
6271f1ca
PH
1344 'upload_date': '20110310',
1345 'uploader_id': 'AllenMeow',
ec85ded8 1346 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1347 '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 1348 'uploader': '孫ᄋᄅ',
6271f1ca 1349 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1350 'playable_in_embed': True,
1351 'channel': '孫ᄋᄅ',
1352 'age_limit': 0,
1353 'tags': 'count:11',
1354 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1355 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1356 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1357 'view_count': int,
1358 'categories': ['People & Blogs'],
1359 'like_count': int,
1360 'live_status': 'not_live',
1361 'availability': 'unlisted',
6c73052c 1362 'channel_follower_count': int
6271f1ca 1363 },
06b491eb
S
1364 },
1365 # url_encoded_fmt_stream_map is empty string
1366 {
1367 'url': 'qEJwOuvDf7I',
1368 'info_dict': {
1369 'id': 'qEJwOuvDf7I',
f57b7835 1370 'ext': 'webm',
06b491eb
S
1371 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1372 'description': '',
1373 'upload_date': '20150404',
1374 'uploader_id': 'spbelect',
1375 'uploader': 'Наблюдатели Петербурга',
1376 },
1377 'params': {
1378 'skip_download': 'requires avconv',
e323cf3f
S
1379 },
1380 'skip': 'This live event has ended.',
06b491eb 1381 },
067aa17e 1382 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1383 {
1384 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1385 'info_dict': {
1386 'id': 'FIl7x6_3R5Y',
eb6793ba 1387 'ext': 'webm',
da77d856
S
1388 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1389 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1390 'duration': 220,
da77d856
S
1391 'upload_date': '20150625',
1392 'uploader_id': 'dorappi2000',
ec85ded8 1393 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1394 'uploader': 'dorappi2000',
eb6793ba 1395 'formats': 'mincount:31',
da77d856 1396 },
eb6793ba 1397 'skip': 'not actual anymore',
2ee8f5d8 1398 },
8a1a26ce
YCH
1399 # DASH manifest with segment_list
1400 {
1401 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1402 'md5': '8ce563a1d667b599d21064e982ab9e31',
1403 'info_dict': {
1404 'id': 'CsmdDsKjzN8',
1405 'ext': 'mp4',
17ee98e1 1406 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1407 'uploader': 'Airtek',
1408 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1409 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1410 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1411 },
1412 'params': {
1413 'youtube_include_dash_manifest': True,
1414 'format': '135', # bestvideo
be49068d
S
1415 },
1416 'skip': 'This live event has ended.',
2ee8f5d8 1417 },
cf7e015f
S
1418 {
1419 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1420 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1421 'info_dict': {
545cc85d 1422 'id': 'jvGDaLqkpTg',
1423 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1424 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1425 },
1426 'playlist': [{
1427 'info_dict': {
545cc85d 1428 'id': 'jvGDaLqkpTg',
cf7e015f 1429 'ext': 'mp4',
545cc85d 1430 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1431 'description': 'md5:e03b909557865076822aa169218d6a5d',
1432 'duration': 10643,
1433 'upload_date': '20161111',
1434 'uploader': 'Team PGP',
1435 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1436 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1437 },
1438 }, {
1439 'info_dict': {
545cc85d 1440 'id': '3AKt1R1aDnw',
cf7e015f 1441 'ext': 'mp4',
545cc85d 1442 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1443 'description': 'md5:e03b909557865076822aa169218d6a5d',
1444 'duration': 10991,
1445 'upload_date': '20161111',
1446 'uploader': 'Team PGP',
1447 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1448 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1449 },
1450 }, {
1451 'info_dict': {
545cc85d 1452 'id': 'RtAMM00gpVc',
cf7e015f 1453 'ext': 'mp4',
545cc85d 1454 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1455 'description': 'md5:e03b909557865076822aa169218d6a5d',
1456 'duration': 10995,
1457 'upload_date': '20161111',
1458 'uploader': 'Team PGP',
1459 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1460 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1461 },
1462 }, {
1463 'info_dict': {
545cc85d 1464 'id': '6N2fdlP3C5U',
cf7e015f 1465 'ext': 'mp4',
545cc85d 1466 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1467 'description': 'md5:e03b909557865076822aa169218d6a5d',
1468 'duration': 10990,
1469 'upload_date': '20161111',
1470 'uploader': 'Team PGP',
1471 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1472 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1473 },
1474 }],
1475 'params': {
1476 'skip_download': True,
1477 },
65c2fde2 1478 'skip': 'Not multifeed anymore',
cbaed4bb 1479 },
f9f49d87 1480 {
067aa17e 1481 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1482 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1483 'info_dict': {
1484 'id': 'gVfLd0zydlo',
1485 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1486 },
1487 'playlist_count': 2,
be49068d 1488 'skip': 'Not multifeed anymore',
f9f49d87 1489 },
cbaed4bb 1490 {
2d3d2997 1491 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1492 'only_matching': True,
0e49d9a6 1493 },
6d4fc66b 1494 {
2d3d2997 1495 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1496 'only_matching': True,
1497 },
0e49d9a6 1498 {
067aa17e 1499 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1500 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1501 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1502 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1503 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1504 'info_dict': {
1505 'id': 'lsguqyKfVQg',
1506 'ext': 'mp4',
1507 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1508 'alt_title': 'Dark Walk',
0e49d9a6 1509 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1510 'duration': 133,
0e49d9a6
LL
1511 'upload_date': '20151119',
1512 'uploader_id': 'IronSoulElf',
ec85ded8 1513 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1514 'uploader': 'IronSoulElf',
11f9be09 1515 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1516 'track': 'Dark Walk',
1517 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1518 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1519 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1520 'categories': ['Film & Animation'],
1521 'view_count': int,
1522 'live_status': 'not_live',
1523 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1524 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1525 'tags': 'count:13',
1526 'availability': 'public',
1527 'channel': 'IronSoulElf',
1528 'playable_in_embed': True,
1529 'like_count': int,
1530 'age_limit': 0,
6c73052c 1531 'channel_follower_count': int
0e49d9a6
LL
1532 },
1533 'params': {
1534 'skip_download': True,
1535 },
1536 },
61f92af1 1537 {
067aa17e 1538 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1539 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1540 'only_matching': True,
1541 },
313dfc45
LL
1542 {
1543 # Video with yt:stretch=17:0
1544 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1545 'info_dict': {
1546 'id': 'Q39EVAstoRM',
1547 'ext': 'mp4',
1548 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1549 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1550 'upload_date': '20151107',
1551 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1552 'uploader': 'CH GAMER DROID',
1553 },
1554 'params': {
1555 'skip_download': True,
1556 },
be49068d 1557 'skip': 'This video does not exist.',
313dfc45 1558 },
201c1459 1559 {
1560 # Video with incomplete 'yt:stretch=16:'
1561 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1562 'only_matching': True,
1563 },
7caf9830
S
1564 {
1565 # Video licensed under Creative Commons
1566 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1567 'info_dict': {
1568 'id': 'M4gD1WSo5mA',
1569 'ext': 'mp4',
1570 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1571 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1572 'duration': 721,
17322130 1573 'upload_date': '20150128',
7caf9830 1574 'uploader_id': 'BerkmanCenter',
ec85ded8 1575 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1576 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1577 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1578 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1579 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1580 'like_count': int,
1581 'age_limit': 0,
1582 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1583 'channel': 'The Berkman Klein Center for Internet & Society',
1584 'availability': 'public',
1585 'view_count': int,
1586 'categories': ['Education'],
1587 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1588 'live_status': 'not_live',
1589 'playable_in_embed': True,
6c73052c 1590 'channel_follower_count': int
7caf9830
S
1591 },
1592 'params': {
1593 'skip_download': True,
1594 },
1595 },
fd050249
S
1596 {
1597 # Channel-like uploader_url
1598 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1599 'info_dict': {
1600 'id': 'eQcmzGIKrzg',
1601 'ext': 'mp4',
1602 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1603 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1604 'duration': 4060,
17322130 1605 'upload_date': '20151120',
eb6793ba 1606 'uploader': 'Bernie Sanders',
fd050249 1607 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1609 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1610 'playable_in_embed': True,
1611 'tags': 'count:12',
1612 'like_count': int,
1613 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1614 'age_limit': 0,
1615 'availability': 'public',
1616 'categories': ['News & Politics'],
1617 'channel': 'Bernie Sanders',
1618 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1619 'view_count': int,
1620 'live_status': 'not_live',
1621 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1622 'channel_follower_count': int
fd050249
S
1623 },
1624 'params': {
1625 'skip_download': True,
1626 },
1627 },
040ac686
S
1628 {
1629 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1630 'only_matching': True,
7f29cf54
S
1631 },
1632 {
067aa17e 1633 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1634 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1635 'only_matching': True,
6496ccb4
S
1636 },
1637 {
1638 # Rental video preview
1639 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1640 'info_dict': {
1641 'id': 'uGpuVWrhIzE',
1642 'ext': 'mp4',
1643 'title': 'Piku - Trailer',
1644 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1645 'upload_date': '20150811',
1646 'uploader': 'FlixMatrix',
1647 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1648 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1649 'license': 'Standard YouTube License',
1650 },
1651 'params': {
1652 'skip_download': True,
1653 },
eb6793ba 1654 'skip': 'This video is not available.',
022a5d66 1655 },
12afdc2a
S
1656 {
1657 # YouTube Red video with episode data
1658 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1659 'info_dict': {
1660 'id': 'iqKdEhx-dD4',
1661 'ext': 'mp4',
1662 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1663 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1664 'duration': 2085,
12afdc2a
S
1665 'upload_date': '20170118',
1666 'uploader': 'Vsauce',
1667 'uploader_id': 'Vsauce',
1668 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1669 'series': 'Mind Field',
1670 'season_number': 1,
1671 'episode_number': 1,
976ae3ea 1672 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1673 'tags': 'count:12',
1674 'view_count': int,
1675 'availability': 'public',
1676 'age_limit': 0,
1677 'channel': 'Vsauce',
1678 'episode': 'Episode 1',
1679 'categories': ['Entertainment'],
1680 'season': 'Season 1',
1681 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1682 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1683 'like_count': int,
1684 'playable_in_embed': True,
1685 'live_status': 'not_live',
6c73052c 1686 'channel_follower_count': int
12afdc2a
S
1687 },
1688 'params': {
1689 'skip_download': True,
1690 },
1691 'expected_warnings': [
1692 'Skipping DASH manifest',
1693 ],
1694 },
c7121fa7
S
1695 {
1696 # The following content has been identified by the YouTube community
1697 # as inappropriate or offensive to some audiences.
1698 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1699 'info_dict': {
1700 'id': '6SJNVb0GnPI',
1701 'ext': 'mp4',
1702 'title': 'Race Differences in Intelligence',
1703 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1704 'duration': 965,
1705 'upload_date': '20140124',
1706 'uploader': 'New Century Foundation',
1707 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1709 },
1710 'params': {
1711 'skip_download': True,
1712 },
545cc85d 1713 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1714 },
022a5d66
S
1715 {
1716 # itag 212
1717 'url': '1t24XAntNCY',
1718 'only_matching': True,
fd5c4aab
S
1719 },
1720 {
1721 # geo restricted to JP
1722 'url': 'sJL6WA-aGkQ',
1723 'only_matching': True,
1724 },
cd5a74a2
S
1725 {
1726 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1727 'only_matching': True,
1728 },
bc2ca1bb 1729 {
1730 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1731 'only_matching': True,
1732 },
1733 {
1734 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1735 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1736 'only_matching': True,
1737 },
825cd268
RA
1738 {
1739 # DRM protected
1740 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1741 'only_matching': True,
4fe54c12
S
1742 },
1743 {
1744 # Video with unsupported adaptive stream type formats
1745 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1746 'info_dict': {
1747 'id': 'Z4Vy8R84T1U',
1748 'ext': 'mp4',
1749 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1750 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1751 'duration': 433,
1752 'upload_date': '20130923',
1753 'uploader': 'Amelia Putri Harwita',
1754 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1755 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1756 'formats': 'maxcount:10',
1757 },
1758 'params': {
1759 'skip_download': True,
1760 'youtube_include_dash_manifest': False,
1761 },
5429d6a9 1762 'skip': 'not actual anymore',
5caabd3c 1763 },
1764 {
822b9d9c 1765 # Youtube Music Auto-generated description
5caabd3c 1766 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1767 'info_dict': {
1768 'id': 'MgNrAu2pzNs',
1769 'ext': 'mp4',
1770 'title': 'Voyeur Girl',
1771 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1772 'upload_date': '20190312',
5429d6a9
S
1773 'uploader': 'Stephen - Topic',
1774 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1775 'artist': 'Stephen',
1776 'track': 'Voyeur Girl',
1777 'album': 'it\'s too much love to know my dear',
1778 'release_date': '20190313',
1779 'release_year': 2019,
976ae3ea 1780 'alt_title': 'Voyeur Girl',
1781 'view_count': int,
1782 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1783 'playable_in_embed': True,
1784 'like_count': int,
1785 'categories': ['Music'],
1786 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1787 'channel': 'Stephen',
1788 'availability': 'public',
1789 'creator': 'Stephen',
1790 'duration': 169,
1791 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1792 'age_limit': 0,
1793 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1794 'tags': 'count:11',
1795 'live_status': 'not_live',
6c73052c 1796 'channel_follower_count': int
5caabd3c 1797 },
1798 'params': {
1799 'skip_download': True,
1800 },
1801 },
66b48727
RA
1802 {
1803 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1804 'only_matching': True,
1805 },
011e75e6
S
1806 {
1807 # invalid -> valid video id redirection
1808 'url': 'DJztXj2GPfl',
1809 'info_dict': {
1810 'id': 'DJztXj2GPfk',
1811 'ext': 'mp4',
1812 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1813 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1814 'upload_date': '20090125',
1815 'uploader': 'Prochorowka',
1816 'uploader_id': 'Prochorowka',
1817 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1818 'artist': 'Panjabi MC',
1819 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1820 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1821 },
1822 'params': {
1823 'skip_download': True,
1824 },
545cc85d 1825 'skip': 'Video unavailable',
ea74e00b
DP
1826 },
1827 {
1828 # empty description results in an empty string
1829 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1830 'info_dict': {
1831 'id': 'x41yOUIvK2k',
1832 'ext': 'mp4',
1833 'title': 'IMG 3456',
1834 'description': '',
1835 'upload_date': '20170613',
1836 'uploader_id': 'ElevageOrVert',
1837 'uploader': 'ElevageOrVert',
976ae3ea 1838 'view_count': int,
1839 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1840 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1841 'like_count': int,
1842 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1843 'tags': [],
1844 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1845 'availability': 'public',
1846 'age_limit': 0,
1847 'categories': ['Pets & Animals'],
1848 'duration': 7,
1849 'playable_in_embed': True,
1850 'live_status': 'not_live',
1851 'channel': 'ElevageOrVert',
6c73052c 1852 'channel_follower_count': int
ea74e00b
DP
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
1857 },
a0566bbf 1858 {
29f7c58a 1859 # with '};' inside yt initial data (see [1])
1860 # see [2] for an example with '};' inside ytInitialPlayerResponse
1861 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1862 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1863 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1864 'info_dict': {
1865 'id': 'CHqg6qOn4no',
1866 'ext': 'mp4',
1867 'title': 'Part 77 Sort a list of simple types in c#',
1868 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1869 'upload_date': '20130831',
1870 'uploader_id': 'kudvenkat',
1871 'uploader': 'kudvenkat',
976ae3ea 1872 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1873 'like_count': int,
1874 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1875 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1876 'live_status': 'not_live',
1877 'categories': ['Education'],
1878 'availability': 'public',
1879 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1880 'tags': 'count:12',
1881 'playable_in_embed': True,
1882 'age_limit': 0,
1883 'view_count': int,
1884 'duration': 522,
1885 'channel': 'kudvenkat',
6c73052c 1886 'channel_follower_count': int
a0566bbf 1887 },
1888 'params': {
1889 'skip_download': True,
1890 },
1891 },
29f7c58a 1892 {
1893 # another example of '};' in ytInitialData
1894 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1895 'only_matching': True,
1896 },
1897 {
1898 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1899 'only_matching': True,
1900 },
545cc85d 1901 {
cc2db878 1902 # https://github.com/ytdl-org/youtube-dl/pull/28094
1903 'url': 'OtqTfy26tG0',
1904 'info_dict': {
1905 'id': 'OtqTfy26tG0',
1906 'ext': 'mp4',
1907 'title': 'Burn Out',
1908 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1909 'upload_date': '20141120',
1910 'uploader': 'The Cinematic Orchestra - Topic',
1911 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1912 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1913 'artist': 'The Cinematic Orchestra',
1914 'track': 'Burn Out',
1915 'album': 'Every Day',
976ae3ea 1916 'like_count': int,
1917 'live_status': 'not_live',
1918 'alt_title': 'Burn Out',
1919 'duration': 614,
1920 'age_limit': 0,
1921 'view_count': int,
1922 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1923 'creator': 'The Cinematic Orchestra',
1924 'channel': 'The Cinematic Orchestra',
1925 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1926 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1927 'availability': 'public',
1928 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1929 'categories': ['Music'],
1930 'playable_in_embed': True,
6c73052c 1931 'channel_follower_count': int
cc2db878 1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
545cc85d 1936 },
bc2ca1bb 1937 {
1938 # controversial video, only works with bpctr when authenticated with cookies
1939 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1940 'only_matching': True,
1941 },
a1a7907b 1942 {
1943 # controversial video, requires bpctr/contentCheckOk
1944 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1945 'info_dict': {
1946 'id': 'SZJvDhaSDnc',
1947 'ext': 'mp4',
1948 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1949 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1950 'uploader': 'CBS Mornings',
11f9be09 1951 'uploader_id': 'CBSThisMorning',
a1a7907b 1952 'upload_date': '20140716',
976ae3ea 1953 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1954 'duration': 170,
1955 'categories': ['News & Politics'],
1956 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1957 'view_count': int,
1958 'channel': 'CBS Mornings',
1959 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1960 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1961 'age_limit': 18,
1962 'availability': 'needs_auth',
1963 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1964 'like_count': int,
1965 'live_status': 'not_live',
1966 'playable_in_embed': True,
6c73052c 1967 'channel_follower_count': int
a1a7907b 1968 }
1969 },
f7ad7160 1970 {
1971 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1972 'url': 'cBvYw8_A0vQ',
1973 'info_dict': {
1974 'id': 'cBvYw8_A0vQ',
1975 'ext': 'mp4',
1976 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1977 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1978 'upload_date': '20201120',
1979 'uploader': 'Walk around Japan',
1980 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1981 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1982 'duration': 1456,
1983 'categories': ['Travel & Events'],
1984 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1985 'view_count': int,
1986 'channel': 'Walk around Japan',
1987 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1988 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1989 'age_limit': 0,
1990 'availability': 'public',
1991 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1992 'live_status': 'not_live',
1993 'playable_in_embed': True,
6c73052c 1994 'channel_follower_count': int
f7ad7160 1995 },
1996 'params': {
1997 'skip_download': True,
1998 },
0fb983f6 1999 }, {
2000 # Has multiple audio streams
2001 'url': 'WaOKSUlf4TM',
2002 'only_matching': True
9297939e 2003 }, {
2004 # Requires Premium: has format 141 when requested using YTM url
2005 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2006 'only_matching': True
2007 }, {
120916da 2008 # multiple subtitles with same lang_code
2009 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2010 'only_matching': True,
109dd3b2 2011 }, {
2012 # Force use android client fallback
2013 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2014 'info_dict': {
2015 'id': 'YOelRv7fMxY',
11f9be09 2016 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2017 'ext': '3gp',
2018 'upload_date': '20210624',
2019 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2020 'uploader': 'colinfurze',
11f9be09 2021 'uploader_id': 'colinfurze',
109dd3b2 2022 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2023 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2024 'duration': 596,
2025 'categories': ['Entertainment'],
2026 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2027 'view_count': int,
2028 'channel': 'colinfurze',
2029 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2030 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2031 'age_limit': 0,
2032 'availability': 'public',
2033 'like_count': int,
2034 'live_status': 'not_live',
2035 'playable_in_embed': True,
6c73052c 2036 'channel_follower_count': int
109dd3b2 2037 },
2038 'params': {
2039 'format': '17', # 3gp format available on android
2040 'extractor_args': {'youtube': {'player_client': ['android']}},
2041 },
120916da 2042 },
109dd3b2 2043 {
2044 # Skip download of additional client configs (remix client config in this case)
2045 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2046 'only_matching': True,
2047 'params': {
2048 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2049 },
8fc54b12 2050 }, {
2051 # shorts
2052 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2053 'only_matching': True,
9222c381 2054 }, {
2055 'note': 'Storyboards',
2056 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2057 'info_dict': {
2058 'id': '5KLPxDtMqe8',
2059 'ext': 'mhtml',
2060 'format_id': 'sb0',
2061 'title': 'Your Brain is Plastic',
2062 'uploader_id': 'scishow',
2063 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2064 'upload_date': '20140324',
2065 'uploader': 'SciShow',
976ae3ea 2066 'like_count': int,
2067 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2068 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2069 'view_count': int,
2070 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2071 'playable_in_embed': True,
2072 'tags': 'count:12',
2073 'uploader_url': 'http://www.youtube.com/user/scishow',
2074 'availability': 'public',
2075 'channel': 'SciShow',
2076 'live_status': 'not_live',
2077 'duration': 248,
2078 'categories': ['Education'],
2079 'age_limit': 0,
6c73052c 2080 'channel_follower_count': int
9222c381 2081 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2082 }, {
2083 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2084 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2085 'info_dict': {
2086 'id': '2NUZ8W2llS4',
2087 'ext': 'mp4',
2088 'title': 'The NP that test your phone performance 🙂',
2089 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2090 'uploader': 'Leon Nguyen',
2091 'uploader_id': 'VNSXIII',
2092 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2093 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2094 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2095 'duration': 21,
2096 'view_count': int,
2097 'age_limit': 0,
2098 'categories': ['Gaming'],
2099 'tags': 'count:23',
2100 'playable_in_embed': True,
2101 'live_status': 'not_live',
2102 'upload_date': '20220103',
2103 'like_count': int,
2104 'availability': 'public',
2105 'channel': 'Leon Nguyen',
2106 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2107 'channel_follower_count': int
2108 }
2109 }, {
2110 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2111 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2112 'info_dict': {
2113 'id': 'mzZzzBU6lrM',
2114 'ext': 'mp4',
2115 'title': 'I Met GeorgeNotFound In Real Life...',
2116 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2117 'uploader': 'Quackity',
2118 'uploader_id': 'QuackityHQ',
2119 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2120 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2121 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2122 'duration': 955,
2123 'view_count': int,
2124 'age_limit': 0,
2125 'categories': ['Entertainment'],
2126 'tags': 'count:26',
2127 'playable_in_embed': True,
2128 'live_status': 'not_live',
2129 'release_timestamp': 1641172509,
2130 'release_date': '20220103',
2131 'upload_date': '20220103',
2132 'like_count': int,
2133 'availability': 'public',
2134 'channel': 'Quackity',
2135 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2136 'channel_follower_count': int
2137 }
2138 },
2139 { # continuous livestream. Microformat upload date should be preferred.
2140 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2141 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2142 'info_dict': {
2143 'id': 'kgx4WGK0oNU',
2144 '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}',
2145 'ext': 'mp4',
2146 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2147 'availability': 'public',
2148 'age_limit': 0,
2149 'release_timestamp': 1637975704,
2150 'upload_date': '20210619',
2151 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2152 'live_status': 'is_live',
2153 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2154 'uploader': '阿鲍Abao',
2155 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2156 'channel': 'Abao in Tokyo',
2157 'channel_follower_count': int,
2158 'release_date': '20211127',
2159 'tags': 'count:39',
2160 'categories': ['People & Blogs'],
2161 'like_count': int,
2162 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2163 'view_count': int,
2164 'playable_in_embed': True,
2165 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2166 },
2167 'params': {'skip_download': True}
2168 },
2eb88d95
PH
2169 ]
2170
201c1459 2171 @classmethod
2172 def suitable(cls, url):
4dfbf869 2173 from ..utils import parse_qs
2174
201c1459 2175 qs = parse_qs(url)
2176 if qs.get('list', [None])[0]:
2177 return False
2178 return super(YoutubeIE, cls).suitable(url)
2179
e0df6211
PH
2180 def __init__(self, *args, **kwargs):
2181 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2182 self._code_cache = {}
83799698 2183 self._player_cache = {}
e0df6211 2184
adbc4ec4 2185 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2186 lock = threading.Lock()
2187
2188 is_live = True
185bf310 2189 start_time = time.time()
adbc4ec4
THD
2190 formats = [f for f in formats if f.get('is_from_start')]
2191
185bf310 2192 def refetch_manifest(format_id, delay):
2193 nonlocal formats, start_time, is_live
2194 if time.time() <= start_time + delay:
adbc4ec4
THD
2195 return
2196
2197 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2198 video_details = traverse_obj(
2199 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2200 microformats = traverse_obj(
2201 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2202 expected_type=dict, default=[])
2203 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2204 start_time = time.time()
adbc4ec4 2205
185bf310 2206 def mpd_feed(format_id, delay):
adbc4ec4
THD
2207 """
2208 @returns (manifest_url, manifest_stream_number, is_live) or None
2209 """
2210 with lock:
185bf310 2211 refetch_manifest(format_id, delay)
adbc4ec4
THD
2212
2213 f = next((f for f in formats if f['format_id'] == format_id), None)
2214 if not f:
185bf310 2215 if not is_live:
2216 self.to_screen(f'{video_id}: Video is no longer live')
2217 else:
2218 self.report_warning(
2219 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2220 return None
2221 return f['manifest_url'], f['manifest_stream_number'], is_live
2222
2223 for f in formats:
a539f065 2224 f['is_live'] = True
adbc4ec4
THD
2225 f['protocol'] = 'http_dash_segments_generator'
2226 f['fragments'] = functools.partial(
2227 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2228
2229 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2230 FETCH_SPAN, MAX_DURATION = 5, 432000
2231
2232 mpd_url, stream_number, is_live = None, None, True
2233
2234 begin_index = 0
2235 download_start_time = ctx.get('start') or time.time()
2236
2237 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2238 if lack_early_segments:
2239 self.report_warning(bug_reports_message(
2240 'Starting download from the last 120 hours of the live stream since '
2241 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2242 lack_early_segments = True
2243
2244 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2245 fragments, fragment_base_url = None, None
2246
a539f065 2247 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2248 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2249 # Obtain from MPD's maximum seq value
2250 old_mpd_url = mpd_url
185bf310 2251 last_error = ctx.pop('last_error', None)
a539f065 2252 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2253 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2254 or (mpd_url, stream_number, False))
2255 if not refresh_sequence:
2256 if expire_fast and not is_live:
2257 return False, last_seq
2258 elif old_mpd_url == mpd_url:
2259 return True, last_seq
adbc4ec4
THD
2260 try:
2261 fmts, _ = self._extract_mpd_formats_and_subtitles(
2262 mpd_url, None, note=False, errnote=False, fatal=False)
2263 except ExtractorError:
2264 fmts = None
2265 if not fmts:
a539f065 2266 no_fragment_score += 2
adbc4ec4
THD
2267 return False, last_seq
2268 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2269 fragments = fmt_info['fragments']
2270 fragment_base_url = fmt_info['fragment_base_url']
2271 assert fragment_base_url
2272
2273 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2274 return True, _last_seq
2275
2276 while is_live:
2277 fetch_time = time.time()
2278 if no_fragment_score > 30:
2279 return
2280 if last_segment_url:
2281 # Obtain from "X-Head-Seqnum" header value from each segment
2282 try:
2283 urlh = self._request_webpage(
2284 last_segment_url, None, note=False, errnote=False, fatal=False)
2285 except ExtractorError:
2286 urlh = None
2287 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2288 if last_seq is None:
a539f065 2289 no_fragment_score += 2
adbc4ec4
THD
2290 last_segment_url = None
2291 continue
2292 else:
a539f065
LNO
2293 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2294 no_fragment_score += 2
185bf310 2295 if not should_continue:
adbc4ec4
THD
2296 continue
2297
2298 if known_idx > last_seq:
2299 last_segment_url = None
2300 continue
2301
2302 last_seq += 1
2303
2304 if begin_index < 0 and known_idx < 0:
2305 # skip from the start when it's negative value
2306 known_idx = last_seq + begin_index
2307 if lack_early_segments:
2308 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2309 try:
2310 for idx in range(known_idx, last_seq):
2311 # do not update sequence here or you'll get skipped some part of it
a539f065 2312 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2313 if not should_continue:
adbc4ec4
THD
2314 known_idx = idx - 1
2315 raise ExtractorError('breaking out of outer loop')
2316 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2317 yield {
2318 'url': last_segment_url,
2319 }
2320 if known_idx == last_seq:
2321 no_fragment_score += 5
2322 else:
2323 no_fragment_score = 0
2324 known_idx = last_seq
2325 except ExtractorError:
2326 continue
2327
2328 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2329
b6de707d 2330 def _extract_player_url(self, *ytcfgs, webpage=None):
2331 player_url = traverse_obj(
2332 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2333 get_all=False, expected_type=compat_str)
11f9be09 2334 if not player_url:
b6de707d 2335 return
60f393e4 2336 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2337
b6de707d 2338 def _download_player_url(self, video_id, fatal=False):
2339 res = self._download_webpage(
2340 'https://www.youtube.com/iframe_api',
2341 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2342 if res:
2343 player_version = self._search_regex(
2344 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2345 if player_version:
2346 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2347
60064c53
PH
2348 def _signature_cache_id(self, example_sig):
2349 """ Return a string representation of a signature """
78caa52a 2350 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2351
e40c758c
S
2352 @classmethod
2353 def _extract_player_info(cls, player_url):
2354 for player_re in cls._PLAYER_INFO_RE:
2355 id_m = re.search(player_re, player_url)
2356 if id_m:
2357 break
2358 else:
c081b35c 2359 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2360 return id_m.group('id')
e40c758c 2361
404f611f 2362 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2363 player_id = self._extract_player_info(player_url)
2364 if player_id not in self._code_cache:
1276a43a 2365 code = self._download_webpage(
109dd3b2 2366 player_url, video_id, fatal=fatal,
2367 note='Downloading player ' + player_id,
2368 errnote='Download of %s failed' % player_url)
1276a43a 2369 if code:
2370 self._code_cache[player_id] = code
404f611f 2371 return self._code_cache.get(player_id)
109dd3b2 2372
e40c758c 2373 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2374 player_id = self._extract_player_info(player_url)
e0df6211 2375
c4417ddb 2376 # Read from filesystem cache
545cc85d 2377 func_id = 'js_%s_%s' % (
2378 player_id, self._signature_cache_id(example_sig))
c4417ddb 2379 assert os.path.basename(func_id) == func_id
a0e07d31 2380
69ea8ca4 2381 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2382 if cache_spec is not None:
78caa52a 2383 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2384
404f611f 2385 code = self._load_player(video_id, player_url)
2386 if code:
109dd3b2 2387 res = self._parse_sig_js(code)
e0df6211 2388
109dd3b2 2389 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2390 cache_res = res(test_string)
2391 cache_spec = [ord(c) for c in cache_res]
83799698 2392
109dd3b2 2393 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2394 return res
83799698 2395
60064c53 2396 def _print_sig_code(self, func, example_sig):
404f611f 2397 if not self.get_param('youtube_print_sig_code'):
2398 return
2399
edf3e38e
PH
2400 def gen_sig_code(idxs):
2401 def _genslice(start, end, step):
78caa52a 2402 starts = '' if start == 0 else str(start)
8bcc8756 2403 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2404 steps = '' if step == 1 else (':%d' % step)
78caa52a 2405 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2406
2407 step = None
7af808a5
PH
2408 # Quelch pyflakes warnings - start will be set when step is set
2409 start = '(Never used)'
edf3e38e
PH
2410 for i, prev in zip(idxs[1:], idxs[:-1]):
2411 if step is not None:
2412 if i - prev == step:
2413 continue
2414 yield _genslice(start, prev, step)
2415 step = None
2416 continue
2417 if i - prev in [-1, 1]:
2418 step = i - prev
2419 start = prev
2420 continue
2421 else:
78caa52a 2422 yield 's[%d]' % prev
edf3e38e 2423 if step is None:
78caa52a 2424 yield 's[%d]' % i
edf3e38e
PH
2425 else:
2426 yield _genslice(start, i, step)
2427
78caa52a 2428 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2429 cache_res = func(test_string)
edf3e38e 2430 cache_spec = [ord(c) for c in cache_res]
78caa52a 2431 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2432 signature_id_tuple = '(%s)' % (
2433 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2434 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2435 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2436 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2437
e0df6211
PH
2438 def _parse_sig_js(self, jscode):
2439 funcname = self._search_regex(
abefc03f
S
2440 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2441 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
2442 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2443 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2444 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}\(a,\d+\)',
2445 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 2446 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2447 # Obsolete patterns
2448 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2449 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2450 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2451 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2452 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2453 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2454 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2455 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2456 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2457
2458 jsi = JSInterpreter(jscode)
2459 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2460 return lambda s: initial_function([s])
2461
545cc85d 2462 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2463 """Turn the encrypted s field into a working signature"""
6b37f0be 2464
c8bf86d5 2465 if player_url is None:
69ea8ca4 2466 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2467
c8bf86d5 2468 try:
62af3a0e 2469 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2470 if player_id not in self._player_cache:
2471 func = self._extract_signature_function(
60064c53 2472 video_id, player_url, s
c8bf86d5
PH
2473 )
2474 self._player_cache[player_id] = func
2475 func = self._player_cache[player_id]
404f611f 2476 self._print_sig_code(func, s)
c8bf86d5
PH
2477 return func(s)
2478 except Exception as e:
404f611f 2479 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2480
2481 def _decrypt_nsig(self, s, video_id, player_url):
2482 """Turn the encrypted n field into a working signature"""
2483 if player_url is None:
2484 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2485 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2486
2487 sig_id = ('nsig_value', s)
2488 if sig_id in self._player_cache:
2489 return self._player_cache[sig_id]
2490
2491 try:
2492 player_id = ('nsig', player_url)
2493 if player_id not in self._player_cache:
2494 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2495 func = self._player_cache[player_id]
2496 self._player_cache[sig_id] = func(s)
2497 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2498 return self._player_cache[sig_id]
2499 except Exception as e:
aa9369a2 2500 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2501
2502 def _extract_n_function_name(self, jscode):
48416bc4 2503 nfunc, idx = self._search_regex(
c571b3a6 2504 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2505 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2506 if not idx:
2507 return nfunc
2508 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2509 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2510 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2511
2512 def _extract_n_function(self, video_id, player_url):
2513 player_id = self._extract_player_info(player_url)
2514 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2515
2516 if func_code:
2517 jsi = JSInterpreter(func_code)
2518 else:
2519 jscode = self._load_player(video_id, player_url)
2520 funcname = self._extract_n_function_name(jscode)
2521 jsi = JSInterpreter(jscode)
2522 func_code = jsi.extract_function_code(funcname)
2523 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2524
2525 if self.get_param('youtube_print_sig_code'):
2526 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2527
2528 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2529
109dd3b2 2530 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2531 """
2532 Extract signatureTimestamp (sts)
2533 Required to tell API what sig/player version is in use.
2534 """
2535 sts = None
2536 if isinstance(ytcfg, dict):
2537 sts = int_or_none(ytcfg.get('STS'))
2538
2539 if not sts:
2540 # Attempt to extract from player
2541 if player_url is None:
2542 error_msg = 'Cannot extract signature timestamp without player_url.'
2543 if fatal:
2544 raise ExtractorError(error_msg)
2545 self.report_warning(error_msg)
2546 return
404f611f 2547 code = self._load_player(video_id, player_url, fatal=fatal)
2548 if code:
109dd3b2 2549 sts = int_or_none(self._search_regex(
2550 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2551 'JS player signature timestamp', group='sts', fatal=fatal))
2552 return sts
2553
11f9be09 2554 def _mark_watched(self, video_id, player_responses):
9222c381 2555 playback_url = get_first(
2556 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2557 expected_type=url_or_none)
d77ab8e2 2558 if not playback_url:
352d63fd 2559 self.report_warning('Unable to mark watched')
d77ab8e2
S
2560 return
2561 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2562 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2563
2564 # cpn generation algorithm is reverse engineered from base.js.
2565 # In fact it works even with dummy cpn.
2566 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2567 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2568
2569 qs.update({
2570 'ver': ['2'],
2571 'cpn': [cpn],
2572 })
2573 playback_url = compat_urlparse.urlunparse(
15707c7e 2574 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2575
2576 self._download_webpage(
2577 playback_url, video_id, 'Marking watched',
2578 'Unable to mark watched', fatal=False)
2579
66c9fa36
S
2580 @staticmethod
2581 def _extract_urls(webpage):
2582 # Embedded YouTube player
2583 entries = [
2584 unescapeHTML(mobj.group('url'))
2585 for mobj in re.finditer(r'''(?x)
2586 (?:
2587 <iframe[^>]+?src=|
2588 data-video-url=|
2589 <embed[^>]+?src=|
2590 embedSWF\(?:\s*|
2591 <object[^>]+data=|
2592 new\s+SWFObject\(
2593 )
2594 (["\'])
2595 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2596 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2597 \1''', webpage)]
2598
2599 # lazyYT YouTube embed
2600 entries.extend(list(map(
2601 unescapeHTML,
2602 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2603
2604 # Wordpress "YouTube Video Importer" plugin
2605 matches = re.findall(r'''(?x)<div[^>]+
2606 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2607 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2608 entries.extend(m[-1] for m in matches)
2609
2610 return entries
2611
2612 @staticmethod
2613 def _extract_url(webpage):
2614 urls = YoutubeIE._extract_urls(webpage)
2615 return urls[0] if urls else None
2616
97665381
PH
2617 @classmethod
2618 def extract_id(cls, url):
2619 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2620 if mobj is None:
69ea8ca4 2621 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2622 return mobj.group('id')
c5e8d7af 2623
7c365c21 2624 def _extract_chapters_from_json(self, data, duration):
2625 chapter_list = traverse_obj(
2626 data, (
2627 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2628 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2629 ), expected_type=list)
2630
2631 return self._extract_chapters(
2632 chapter_list,
2633 chapter_time=lambda chapter: float_or_none(
2634 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2635 chapter_title=lambda chapter: traverse_obj(
2636 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2637 duration=duration)
2638
2639 def _extract_chapters_from_engagement_panel(self, data, duration):
2640 content_list = traverse_obj(
8bdd16b4 2641 data,
7c365c21 2642 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2643 expected_type=list, default=[])
052e1350 2644 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2645 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2646
2647 return next((
2648 filter(None, (
2649 self._extract_chapters(
2650 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2651 chapter_time, chapter_title, duration)
2652 for contents in content_list
2653 ))), [])
2654
2655 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2656 chapters = []
7c365c21 2657 last_chapter = {'start_time': 0}
2658 for idx, chapter in enumerate(chapter_list or []):
2659 title = chapter_title(chapter)
84213ea8
S
2660 start_time = chapter_time(chapter)
2661 if start_time is None:
2662 continue
7c365c21 2663 last_chapter['end_time'] = start_time
2664 if start_time < last_chapter['start_time']:
2665 if idx == 1:
2666 chapters.pop()
2667 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2668 else:
2669 self.report_warning(f'Invalid start time for chapter "{title}"')
2670 continue
2671 last_chapter = {'start_time': start_time, 'title': title}
2672 chapters.append(last_chapter)
2673 last_chapter['end_time'] = duration
84213ea8
S
2674 return chapters
2675
545cc85d 2676 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2677 return self._parse_json(self._search_regex(
2678 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2679 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2680
a1c5d2ca
M
2681 def _extract_comment(self, comment_renderer, parent=None):
2682 comment_id = comment_renderer.get('commentId')
2683 if not comment_id:
2684 return
fe93e2c4 2685
052e1350 2686 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2687
49bd8c66 2688 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2689 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2690 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2691 author_id = try_get(comment_renderer,
2692 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2693
49bd8c66 2694 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2695 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2696 author_thumbnail = try_get(comment_renderer,
2697 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2698
2699 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2700 is_favorited = 'creatorHeart' in (try_get(
2701 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2702 return {
2703 'id': comment_id,
2704 'text': text,
d92f5d5a 2705 'timestamp': timestamp,
a1c5d2ca
M
2706 'time_text': time_text,
2707 'like_count': votes,
97524332 2708 'is_favorited': is_favorited,
a1c5d2ca
M
2709 'author': author,
2710 'author_id': author_id,
2711 'author_thumbnail': author_thumbnail,
2712 'author_is_uploader': author_is_uploader,
2713 'parent': parent or 'root'
2714 }
2715
46383212 2716 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2717
2718 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2719
2720 def extract_header(contents):
2d6659b9 2721 _continuation = None
2722 for content in contents:
46383212 2723 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2724 expected_comment_count = self._get_count(
2725 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2726
2d6659b9 2727 if expected_comment_count:
46383212 2728 tracker['est_total'] = expected_comment_count
2729 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2730 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2731
2732 sort_menu_item = try_get(
2733 comments_header_renderer,
2734 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2735 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2736
2737 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2738 if not _continuation:
2739 continue
2740
46383212 2741 sort_text = str_or_none(sort_menu_item.get('title'))
2742 if not sort_text:
2d6659b9 2743 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2744 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2745 break
a2160aa4 2746 return _continuation
a1c5d2ca 2747
2d6659b9 2748 def extract_thread(contents):
a1c5d2ca 2749 if not parent:
46383212 2750 tracker['current_page_thread'] = 0
a1c5d2ca 2751 for content in contents:
46383212 2752 if not parent and tracker['total_parent_comments'] >= max_parents:
2753 yield
a1c5d2ca 2754 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2755 comment_renderer = get_first(
2756 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2757 expected_type=dict, default={})
a1c5d2ca 2758
a1c5d2ca
M
2759 comment = self._extract_comment(comment_renderer, parent)
2760 if not comment:
2761 continue
46383212 2762
2763 tracker['running_total'] += 1
2764 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2765 yield comment
46383212 2766
a1c5d2ca
M
2767 # Attempt to get the replies
2768 comment_replies_renderer = try_get(
2769 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2770
2771 if comment_replies_renderer:
46383212 2772 tracker['current_page_thread'] += 1
a1c5d2ca 2773 comment_entries_iter = self._comment_entries(
99e9e001 2774 comment_replies_renderer, ytcfg, video_id,
46383212 2775 parent=comment.get('id'), tracker=tracker)
2776 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2777 yield reply_comment
2778
46383212 2779 # Keeps track of counts across recursive calls
2780 if not tracker:
2781 tracker = dict(
2782 running_total=0,
2783 est_total=0,
2784 current_page_thread=0,
2785 total_parent_comments=0,
2786 total_reply_comments=0)
2787
2788 # TODO: Deprecated
2d6659b9 2789 # YouTube comments have a max depth of 2
46383212 2790 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2791 if max_depth:
2792 self._downloader.deprecation_warning(
2793 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2794 if max_depth == 1 and parent:
2795 return
a1c5d2ca 2796
46383212 2797 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2798 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2799
46383212 2800 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2801 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2802 if message and not parent:
2803 self.report_warning(message, video_id=video_id)
2804
46383212 2805 response = None
2d6659b9 2806 is_first_continuation = parent is None
a1c5d2ca
M
2807
2808 for page_num in itertools.count(0):
2809 if not continuation:
2810 break
46383212 2811 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2812 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2813 if page_num == 0:
2814 if is_first_continuation:
2815 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2816 else:
2d6659b9 2817 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2818 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2819 else:
2820 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2821 ' ' if parent else '', ' replies' if parent else '',
2822 page_num, comment_prog_str)
2823
2824 response = self._extract_response(
fe93e2c4 2825 item_id=None, query=continuation,
2d6659b9 2826 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2827 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2828
46383212 2829 continuation_contents = traverse_obj(
2830 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2831
2d6659b9 2832 continuation = None
46383212 2833 for continuation_section in continuation_contents:
2834 continuation_items = traverse_obj(
2835 continuation_section,
2836 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2837 get_all=False, expected_type=list) or []
2838 if is_first_continuation:
2839 continuation = extract_header(continuation_items)
2840 is_first_continuation = False
2d6659b9 2841 if continuation:
a1c5d2ca 2842 break
46383212 2843 continue
a1c5d2ca 2844
46383212 2845 for entry in extract_thread(continuation_items):
2846 if not entry:
2847 return
2848 yield entry
2849 continuation = self._extract_continuation({'contents': continuation_items})
2850 if continuation:
2d6659b9 2851 break
a1c5d2ca 2852
a2160aa4 2853 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2854 """Entry for comment extraction"""
2d6659b9 2855 def _real_comment_extract(contents):
aae16f6e 2856 renderer = next((
2857 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2858 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2859 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2860
a2160aa4 2861 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2862 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2863
109dd3b2 2864 @staticmethod
99e9e001 2865 def _get_checkok_params():
2866 return {'contentCheckOk': True, 'racyCheckOk': True}
2867
2868 @classmethod
2869 def _generate_player_context(cls, sts=None):
109dd3b2 2870 context = {
2871 'html5Preference': 'HTML5_PREF_WANTS',
2872 }
2873 if sts is not None:
2874 context['signatureTimestamp'] = sts
2875 return {
2876 'playbackContext': {
2877 'contentPlaybackContext': context
a1a7907b 2878 },
99e9e001 2879 **cls._get_checkok_params()
109dd3b2 2880 }
2881
e7e94f2a
D
2882 @staticmethod
2883 def _is_agegated(player_response):
2884 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2885 return True
e7e94f2a
D
2886
2887 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2888 AGE_GATE_REASONS = (
2889 'confirm your age', 'age-restricted', 'inappropriate', # reason
2890 'age_verification_required', 'age_check_required', # status
2891 )
2892 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2893
2894 @staticmethod
2895 def _is_unplayable(player_response):
2896 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2897
99e9e001 2898 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2899
11f9be09 2900 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2901 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2902 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2903 headers = self.generate_api_headers(
99e9e001 2904 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2905
11f9be09 2906 yt_query = {'videoId': video_id}
2907 yt_query.update(self._generate_player_context(sts))
2908 return self._extract_response(
2909 item_id=video_id, ep='player', query=yt_query,
379e44ed 2910 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2911 default_client=client,
11f9be09 2912 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2913 ) or None
2914
11f9be09 2915 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2916 requested_clients = []
d0d012d4 2917 default = ['android', 'web']
000c15a4 2918 allowed_clients = sorted(
2919 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2920 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2921 for client in self._configuration_arg('player_client'):
2922 if client in allowed_clients:
2923 requested_clients.append(client)
d0d012d4 2924 elif client == 'default':
2925 requested_clients.extend(default)
b4c055ba 2926 elif client == 'all':
2927 requested_clients.extend(allowed_clients)
2928 else:
2929 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2930 if not requested_clients:
d0d012d4 2931 requested_clients = default
cf7e015f 2932
11f9be09 2933 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2934 requested_clients.extend(
e7e94f2a 2935 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2936
11f9be09 2937 return orderedSet(requested_clients)
cf7e015f 2938
c0bc527b
M
2939 def _extract_player_ytcfg(self, client, video_id):
2940 url = {
2941 'web_music': 'https://music.youtube.com',
2942 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2943 }.get(client)
2944 if not url:
2945 return {}
18c7683d 2946 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2947 return self.extract_ytcfg(video_id, webpage) or {}
2948
99e9e001 2949 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2950 initial_pr = None
2951 if webpage:
2952 initial_pr = self._extract_yt_initial_variable(
2953 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2954 video_id, 'initial player response')
6b09401b 2955
c0bc527b
M
2956 original_clients = clients
2957 clients = clients[::-1]
b6de707d 2958 prs = []
e7e94f2a
D
2959
2960 def append_client(client_name):
2961 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2962 clients.append(client_name)
2963
379e44ed 2964 # Android player_response does not have microFormats which are needed for
2965 # extraction of some data. So we return the initial_pr with formats
2966 # stripped out even if not requested by the user
2967 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2968 if initial_pr:
2969 pr = dict(initial_pr)
2970 pr['streamingData'] = None
b6de707d 2971 prs.append(pr)
379e44ed 2972
2973 last_error = None
b6de707d 2974 tried_iframe_fallback = False
2975 player_url = None
c0bc527b
M
2976 while clients:
2977 client = clients.pop()
11f9be09 2978 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2979 if 'configs' not in self._configuration_arg('player_skip'):
2980 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2981
b6de707d 2982 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2983 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2984 if 'js' in self._configuration_arg('player_skip'):
2985 require_js_player = False
2986 player_url = None
2987
2988 if not player_url and not tried_iframe_fallback and require_js_player:
2989 player_url = self._download_player_url(video_id)
2990 tried_iframe_fallback = True
2991
379e44ed 2992 try:
2993 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2994 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2995 except ExtractorError as e:
2996 if last_error:
2997 self.report_warning(last_error)
2998 last_error = e
2999 continue
3000
11f9be09 3001 if pr:
b6de707d 3002 prs.append(pr)
c0bc527b 3003
e7e94f2a 3004 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 3005 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
3006 append_client(client.replace('_agegate', '_creator'))
3007 elif self._is_agegated(pr):
3008 append_client(f'{client}_agegate')
c0bc527b 3009
379e44ed 3010 if last_error:
b6de707d 3011 if not len(prs):
379e44ed 3012 raise last_error
3013 self.report_warning(last_error)
b6de707d 3014 return prs, player_url
11f9be09 3015
3016 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
a0bb6ce5 3017 itags, stream_ids = {}, []
2a9c6dcd 3018 itag_qualities, res_qualities = {}, {}
d3fc8074 3019 q = qualities([
2a9c6dcd 3020 # Normally tiny is the smallest video-only formats. But
3021 # audio-only formats with unknown quality may get tagged as tiny
3022 'tiny',
3023 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3024 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3025 ])
11f9be09 3026 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
0ad92dfb 3027 approx_duration = max(traverse_obj(streaming_formats, (..., 'approxDurationMs'), expected_type=float_or_none) or [0]) or None
9297939e 3028
545cc85d 3029 for fmt in streaming_formats:
3030 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
3031 continue
321bf820 3032
cc2db878 3033 itag = str_or_none(fmt.get('itag'))
9297939e 3034 audio_track = fmt.get('audioTrack') or {}
3035 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3036 if stream_id in stream_ids:
3037 continue
3038
cc2db878 3039 quality = fmt.get('quality')
2a9c6dcd 3040 height = int_or_none(fmt.get('height'))
d3fc8074 3041 if quality == 'tiny' or not quality:
3042 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3043 # The 3gp format (17) in android client has a quality of "small",
3044 # but is actually worse than other formats
3045 if itag == '17':
3046 quality = 'tiny'
3047 if quality:
3048 if itag:
3049 itag_qualities[itag] = quality
3050 if height:
3051 res_qualities[height] = quality
cc2db878 3052 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3053 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3054 # number of fragment that would subsequently requested with (`&sq=N`)
3055 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3056 continue
3057
545cc85d 3058 fmt_url = fmt.get('url')
3059 if not fmt_url:
3060 sc = compat_parse_qs(fmt.get('signatureCipher'))
3061 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3062 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3063 if not (sc and fmt_url and encrypted_sig):
3064 continue
545cc85d 3065 if not player_url:
201e9eaa 3066 continue
545cc85d 3067 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3068 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3069 fmt_url += '&' + sp + '=' + signature
3070
404f611f 3071 query = parse_qs(fmt_url)
3072 throttled = False
b2916526 3073 if query.get('n'):
404f611f 3074 try:
3075 fmt_url = update_url_query(fmt_url, {
3076 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3077 except ExtractorError as e:
aa9369a2 3078 self.report_warning(
3079 f'nsig extraction failed: You may experience throttling for some formats\n'
3080 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3081 throttled = True
3082
545cc85d 3083 if itag:
a0bb6ce5 3084 itags[itag] = 'https'
9297939e 3085 stream_ids.append(stream_id)
3086
0ad92dfb 3087 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3088 language_preference = (
3089 10 if audio_track.get('audioIsDefault') and 10
3090 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3091 else -1)
0ad92dfb 3092 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3093 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3094 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) < approx_duration - 10000)
08d30158 3095 if is_damaged:
3096 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3097 dct = {
3098 'asr': int_or_none(fmt.get('audioSampleRate')),
3099 'filesize': int_or_none(fmt.get('contentLength')),
3100 'format_id': itag,
34921b43 3101 'format_note': join_nonempty(
26e8e044 3102 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3103 ' (default)' if language_preference > 0 else ''),
404f611f 3104 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3105 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3106 'source_preference': -10 if throttled else -1,
a4211baf 3107 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3108 'height': height,
dca3ff4a 3109 'quality': q(quality),
cc2db878 3110 'tbr': tbr,
545cc85d 3111 'url': fmt_url,
2a9c6dcd 3112 'width': int_or_none(fmt.get('width')),
ab6df717 3113 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3114 'desc' if language_preference < -1 else ''),
3115 'language_preference': language_preference,
a405b38f 3116 # Strictly de-prioritize damaged and 3gp formats
3117 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3118 }
60bdb7bd 3119 mime_mobj = re.match(
3120 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3121 if mime_mobj:
3122 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3123 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3124 no_audio = dct.get('acodec') == 'none'
3125 no_video = dct.get('vcodec') == 'none'
3126 if no_audio:
3127 dct['vbr'] = tbr
3128 if no_video:
3129 dct['abr'] = tbr
3130 if no_audio or no_video:
545cc85d 3131 dct['downloader_options'] = {
3132 # Youtube throttles chunks >~10M
3133 'http_chunk_size': 10485760,
bf1317d2 3134 }
7c60c33e 3135 if dct.get('ext'):
3136 dct['container'] = dct['ext'] + '_dash'
11f9be09 3137 yield dct
545cc85d 3138
adbc4ec4 3139 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3140 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3141 if not self.get_param('youtube_include_hls_manifest', True):
3142 skip_manifests.append('hls')
3143 get_dash = 'dash' not in skip_manifests and (
3144 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3145 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3146
a0bb6ce5 3147 def process_manifest_format(f, proto, itag):
3148 if itag in itags:
3149 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3150 return False
3151 itag = f'{itag}-{proto}'
3152 if itag:
3153 f['format_id'] = itag
3154 itags[itag] = proto
3155
3156 f['quality'] = next((
3157 q(qdict[val])
e339d25a 3158 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3159 if val in qdict), -1)
3160 return True
2a9c6dcd 3161
11f9be09 3162 for sd in streaming_data:
5d3a0e79 3163 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3164 if hls_manifest_url:
2a9c6dcd 3165 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3166 if process_manifest_format(f, 'hls', self._search_regex(
3167 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3168 yield f
545cc85d 3169
5d3a0e79 3170 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3171 if dash_manifest_url:
2a9c6dcd 3172 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3173 if process_manifest_format(f, 'dash', f['format_id']):
3174 f['filesize'] = int_or_none(self._search_regex(
3175 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3176 if live_from_start:
3177 f['is_from_start'] = True
3178
a0bb6ce5 3179 yield f
11f9be09 3180
720c3099 3181 def _extract_storyboard(self, player_responses, duration):
3182 spec = get_first(
3183 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3184 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3185 if not base_url:
720c3099 3186 return
720c3099 3187 L = len(spec) - 1
3188 for i, args in enumerate(spec):
3189 args = args.split('#')
3190 counts = list(map(int_or_none, args[:5]))
3191 if len(args) != 8 or not all(counts):
3192 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3193 continue
3194 width, height, frame_count, cols, rows = counts
3195 N, sigh = args[6:]
3196
3197 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3198 fragment_count = frame_count / (cols * rows)
3199 fragment_duration = duration / fragment_count
3200 yield {
3201 'format_id': f'sb{i}',
3202 'format_note': 'storyboard',
3203 'ext': 'mhtml',
3204 'protocol': 'mhtml',
3205 'acodec': 'none',
3206 'vcodec': 'none',
3207 'url': url,
3208 'width': width,
3209 'height': height,
3210 'fragments': [{
b3edc806 3211 'url': url.replace('$M', str(j)),
720c3099 3212 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3213 } for j in range(math.ceil(fragment_count))],
3214 }
3215
adbc4ec4 3216 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3217 webpage = None
3218 if 'webpage' not in self._configuration_arg('player_skip'):
3219 webpage = self._download_webpage(
3220 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3221
3222 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3223
b6de707d 3224 player_responses, player_url = self._extract_player_responses(
11f9be09 3225 self._get_requested_clients(url, smuggled_data),
99e9e001 3226 video_id, webpage, master_ytcfg)
11f9be09 3227
adbc4ec4
THD
3228 return webpage, master_ytcfg, player_responses, player_url
3229
3230 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3231 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3232 is_live = get_first(video_details, 'isLive')
3233 if is_live is None:
3234 is_live = get_first(live_broadcast_details, 'isLiveNow')
3235
3236 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3237 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3238
3239 return live_broadcast_details, is_live, streaming_data, formats
3240
3241 def _real_extract(self, url):
3242 url, smuggled_data = unsmuggle_url(url, {})
3243 video_id = self._match_id(url)
3244
3245 base_url = self.http_scheme() + '//www.youtube.com/'
3246 webpage_url = base_url + 'watch?v=' + video_id
3247
3248 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3249
11f9be09 3250 playability_statuses = traverse_obj(
3251 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3252
3253 trailer_video_id = get_first(
3254 playability_statuses,
3255 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3256 expected_type=str)
3257 if trailer_video_id:
3258 return self.url_result(
3259 trailer_video_id, self.ie_key(), trailer_video_id)
3260
3261 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3262 if webpage else (lambda x: None))
3263
3264 video_details = traverse_obj(
3265 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3266 microformats = traverse_obj(
3267 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3268 expected_type=dict, default=[])
3269 video_title = (
3270 get_first(video_details, 'title')
3271 or self._get_text(microformats, (..., 'title'))
3272 or search_meta(['og:title', 'twitter:title', 'title']))
3273 video_description = get_first(video_details, 'shortDescription')
3274
d89257f3 3275 multifeed_metadata_list = get_first(
3276 player_responses,
3277 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3278 expected_type=str)
3279 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3280 if self.get_param('noplaylist'):
11f9be09 3281 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3282 else:
3283 entries = []
3284 feed_ids = []
3285 for feed in multifeed_metadata_list.split(','):
3286 # Unquote should take place before split on comma (,) since textual
3287 # fields may contain comma as well (see
3288 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3289 feed_data = compat_parse_qs(
3290 compat_urllib_parse_unquote_plus(feed))
3291
3292 def feed_entry(name):
3293 return try_get(
3294 feed_data, lambda x: x[name][0], compat_str)
3295
3296 feed_id = feed_entry('id')
3297 if not feed_id:
3298 continue
3299 feed_title = feed_entry('title')
3300 title = video_title
3301 if feed_title:
3302 title += ' (%s)' % feed_title
3303 entries.append({
3304 '_type': 'url_transparent',
3305 'ie_key': 'Youtube',
3306 'url': smuggle_url(
3307 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3308 {'force_singlefeed': True}),
3309 'title': title,
3310 })
3311 feed_ids.append(feed_id)
3312 self.to_screen(
3313 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3314 % (', '.join(feed_ids), video_id))
3315 return self.playlist_result(
3316 entries, video_id, video_title, video_description)
11f9be09 3317
adbc4ec4 3318 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3319
545cc85d 3320 if not formats:
11f9be09 3321 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3322 self.report_drm(video_id)
11f9be09 3323 pemr = get_first(
3324 playability_statuses,
3325 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3326 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3327 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3328 if subreason:
545cc85d 3329 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3330 countries = get_first(microformats, 'availableCountries')
545cc85d 3331 if not countries:
3332 regions_allowed = search_meta('regionsAllowed')
3333 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3334 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3335 reason += f'. {subreason}'
545cc85d 3336 if reason:
b7da73eb 3337 self.raise_no_formats(reason, expected=True)
bf1317d2 3338
11f9be09 3339 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3340 if not keywords and webpage:
3341 keywords = [
3342 unescapeHTML(m.group('content'))
3343 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3344 for keyword in keywords:
3345 if keyword.startswith('yt:stretch='):
201c1459 3346 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3347 if mobj:
3348 # NB: float is intentional for forcing float division
3349 w, h = (float(v) for v in mobj.groups())
3350 if w > 0 and h > 0:
3351 ratio = w / h
3352 for f in formats:
3353 if f.get('vcodec') != 'none':
3354 f['stretched_ratio'] = ratio
3355 break
a709d873 3356 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3357 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3358 if thumbnail_url:
3359 thumbnails.append({
3360 'url': thumbnail_url,
ff2751ac 3361 })
fccf5021 3362 original_thumbnails = thumbnails.copy()
3363
0ba692ac 3364 # The best resolution thumbnails sometimes does not appear in the webpage
3365 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3366 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3367 thumbnail_names = [
3368 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3369 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3370 'mqdefault', 'mq1', 'mq2', 'mq3',
3371 'default', '1', '2', '3'
3372 ]
cca80fe6 3373 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3374 thumbnails.extend({
3375 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3376 video_id=video_id, name=name, ext=ext,
3377 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3378 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3379 for thumb in thumbnails:
cca80fe6 3380 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3381 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3382 self._remove_duplicate_formats(thumbnails)
fccf5021 3383 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3384
7ea65411 3385 category = get_first(microformats, 'category') or search_meta('genre')
3386 channel_id = str_or_none(
3387 get_first(video_details, 'channelId')
3388 or get_first(microformats, 'externalChannelId')
3389 or search_meta('channelId'))
3390 duration = int_or_none(
3391 get_first(video_details, 'lengthSeconds')
3392 or get_first(microformats, 'lengthSeconds')
3393 or parse_duration(search_meta('duration'))) or None
3394 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3395
3396 live_content = get_first(video_details, 'isLiveContent')
3397 is_upcoming = get_first(video_details, 'isUpcoming')
3398 if is_live is None:
3399 if is_upcoming or live_content is False:
3400 is_live = False
3401 if is_upcoming is None and (live_content or is_live):
3402 is_upcoming = False
adbc4ec4
THD
3403 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3404 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3405 if not duration and live_end_time and live_start_time:
3406 duration = live_end_time - live_start_time
3407
3408 if is_live and self.get_param('live_from_start'):
3409 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3410
720c3099 3411 formats.extend(self._extract_storyboard(player_responses, duration))
3412
3413 # Source is given priority since formats that throttle are given lower source_preference
3414 # When throttling issue is fully fixed, remove this
3415 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3416
545cc85d 3417 info = {
3418 'id': video_id,
39ca3b5c 3419 'title': video_title,
545cc85d 3420 'formats': formats,
3421 'thumbnails': thumbnails,
fccf5021 3422 # The best thumbnail that we are sure exists. Prevents unnecessary
3423 # URL checking if user don't care about getting the best possible thumbnail
3424 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3425 'description': video_description,
11f9be09 3426 'uploader': get_first(video_details, 'author'),
545cc85d 3427 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3428 'uploader_url': owner_profile_url,
3429 'channel_id': channel_id,
e0ddbd02 3430 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3431 'duration': duration,
3432 'view_count': int_or_none(
11f9be09 3433 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3434 or search_meta('interactionCount')),
11f9be09 3435 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3436 'age_limit': 18 if (
11f9be09 3437 get_first(microformats, 'isFamilySafe') is False
545cc85d 3438 or search_meta('isFamilyFriendly') == 'false'
3439 or search_meta('og:restrictions:age') == '18+') else 0,
3440 'webpage_url': webpage_url,
3441 'categories': [category] if category else None,
3442 'tags': keywords,
11f9be09 3443 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3444 'is_live': is_live,
3445 'was_live': (False if is_live or is_upcoming or live_content is False
3446 else None if is_live is None or is_upcoming is None
3447 else live_content),
3448 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3449 'release_timestamp': live_start_time,
545cc85d 3450 }
b477fc13 3451
3944e7af 3452 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3453 if pctr:
ecdc9049 3454 def get_lang_code(track):
3455 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3456 or track.get('languageCode'))
3457
3458 # Converted into dicts to remove duplicates
3459 captions = {
3460 get_lang_code(sub): sub
3461 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3462 translation_languages = {
3463 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3464 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3465
774d79cc 3466 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3467 lang_subs = container.setdefault(lang_code, [])
545cc85d 3468 for fmt in self._SUBTITLE_FORMATS:
3469 query.update({
3470 'fmt': fmt,
3471 })
3472 lang_subs.append({
3473 'ext': fmt,
60f393e4 3474 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3475 'name': sub_name,
545cc85d 3476 })
7e72694b 3477
ecdc9049 3478 subtitles, automatic_captions = {}, {}
3479 for lang_code, caption_track in captions.items():
3480 base_url = caption_track.get('baseUrl')
545cc85d 3481 if not base_url:
3482 continue
ecdc9049 3483 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3484 if caption_track.get('kind') != 'asr':
545cc85d 3485 if not lang_code:
3486 continue
3487 process_language(
ecdc9049 3488 subtitles, base_url, lang_code, lang_name, {})
3489 if not caption_track.get('isTranslatable'):
3490 continue
3944e7af 3491 for trans_code, trans_name in translation_languages.items():
3492 if not trans_code:
545cc85d 3493 continue
ecdc9049 3494 if caption_track.get('kind') != 'asr':
3495 trans_code += f'-{lang_code}'
3496 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3497 # Add an "-orig" label to the original language so that it can be distinguished.
3498 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 3499 if lang_code == f'a-{trans_code}':
3500 process_language(
d49669ac 3501 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3502 # Setting tlang=lang returns damaged subtitles.
3503 # Not using lang_code == f'a-{trans_code}' here for future-proofing
3504 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3505 process_language(automatic_captions, base_url, trans_code, trans_name,
3506 {} if orig_lang == trans_code else {'tlang': trans_code})
ecdc9049 3507 info['automatic_captions'] = automatic_captions
3508 info['subtitles'] = subtitles
7e72694b 3509
545cc85d 3510 parsed_url = compat_urllib_parse_urlparse(url)
3511 for component in [parsed_url.fragment, parsed_url.query]:
3512 query = compat_parse_qs(component)
3513 for k, v in query.items():
3514 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3515 d_k += '_time'
3516 if d_k not in info and k in s_ks:
3517 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3518
3519 # Youtube Music Auto-generated description
822b9d9c 3520 if video_description:
38d70284 3521 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
822b9d9c 3522 if mobj:
822b9d9c
RA
3523 release_year = mobj.group('release_year')
3524 release_date = mobj.group('release_date')
3525 if release_date:
3526 release_date = release_date.replace('-', '')
3527 if not release_year:
545cc85d 3528 release_year = release_date[:4]
3529 info.update({
3530 'album': mobj.group('album'.strip()),
3531 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3532 'track': mobj.group('track').strip(),
3533 'release_date': release_date,
cc2db878 3534 'release_year': int_or_none(release_year),
545cc85d 3535 })
7e72694b 3536
545cc85d 3537 initial_data = None
3538 if webpage:
3539 initial_data = self._extract_yt_initial_variable(
3540 webpage, self._YT_INITIAL_DATA_RE, video_id,
3541 'yt initial data')
3542 if not initial_data:
99e9e001 3543 query = {'videoId': video_id}
3544 query.update(self._get_checkok_params())
109dd3b2 3545 initial_data = self._extract_response(
3546 item_id=video_id, ep='next', fatal=False,
99e9e001 3547 ytcfg=master_ytcfg, query=query,
3548 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3549 note='Downloading initial data API JSON')
545cc85d 3550
c60ee3a2 3551 try:
3552 # This will error if there is no livechat
3553 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3554 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3555 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3556 'video_id': video_id,
3557 'ext': 'json',
f6745c49 3558 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3559 }]
3560 except (KeyError, IndexError, TypeError):
3561 pass
545cc85d 3562
3563 if initial_data:
7c365c21 3564 info['chapters'] = (
3565 self._extract_chapters_from_json(initial_data, duration)
3566 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3567 or None)
545cc85d 3568
17322130 3569 contents = traverse_obj(
3570 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3571 expected_type=list, default=[])
3572
3573 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3574 if vpir:
3575 stl = vpir.get('superTitleLink')
3576 if stl:
3577 stl = self._get_text(stl)
3578 if try_get(
3579 vpir,
3580 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3581 info['location'] = stl
3582 else:
3583 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3584 if mobj:
545cc85d 3585 info.update({
17322130 3586 'series': mobj.group(1),
3587 'season_number': int(mobj.group(2)),
3588 'episode_number': int(mobj.group(3)),
545cc85d 3589 })
17322130 3590 for tlb in (try_get(
3591 vpir,
3592 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3593 list) or []):
3594 tbr = tlb.get('toggleButtonRenderer') or {}
3595 for getter, regex in [(
3596 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3597 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3598 lambda x: x['accessibility'],
3599 lambda x: x['accessibilityData']['accessibilityData'],
3600 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3601 label = (try_get(tbr, getter, dict) or {}).get('label')
3602 if label:
3603 mobj = re.match(regex, label)
3604 if mobj:
3605 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3606 break
17322130 3607 sbr_tooltip = try_get(
3608 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3609 if sbr_tooltip:
3610 like_count, dislike_count = sbr_tooltip.split(' / ')
3611 info.update({
3612 'like_count': str_to_int(like_count),
3613 'dislike_count': str_to_int(dislike_count),
3614 })
3615 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3616 if vsir:
3617 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3618 info.update({
3619 'channel': self._get_text(vor, 'title'),
3620 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3621
3622 rows = try_get(
3623 vsir,
3624 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3625 list) or []
3626 multiple_songs = False
3627 for row in rows:
3628 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3629 multiple_songs = True
3630 break
3631 for row in rows:
3632 mrr = row.get('metadataRowRenderer') or {}
3633 mrr_title = mrr.get('title')
3634 if not mrr_title:
3635 continue
3636 mrr_title = self._get_text(mrr, 'title')
3637 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3638 if mrr_title == 'License':
3639 info['license'] = mrr_contents_text
3640 elif not multiple_songs:
3641 if mrr_title == 'Album':
3642 info['album'] = mrr_contents_text
3643 elif mrr_title == 'Artist':
3644 info['artist'] = mrr_contents_text
3645 elif mrr_title == 'Song':
3646 info['track'] = mrr_contents_text
545cc85d 3647
3648 fallbacks = {
3649 'channel': 'uploader',
3650 'channel_id': 'uploader_id',
3651 'channel_url': 'uploader_url',
3652 }
992f9a73 3653
17322130 3654 # The upload date for scheduled, live and past live streams / premieres in microformats
3655 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3656 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3657 upload_date = (
3658 unified_strdate(get_first(microformats, 'uploadDate'))
3659 or unified_strdate(search_meta('uploadDate')))
3660 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3661 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3662 info['upload_date'] = upload_date
992f9a73 3663
545cc85d 3664 for to, frm in fallbacks.items():
3665 if not info.get(to):
3666 info[to] = info.get(frm)
3667
3668 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3669 v = info.get(s_k)
3670 if v:
3671 info[d_k] = v
b84071c0 3672
11f9be09 3673 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3674 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3675 is_membersonly = None
b28f8d24 3676 is_premium = None
c224251a
M
3677 if initial_data and is_private is not None:
3678 is_membersonly = False
b28f8d24 3679 is_premium = False
47193e02 3680 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3681 badge_labels = set()
3682 for content in contents:
3683 if not isinstance(content, dict):
3684 continue
3685 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3686 for badge_label in badge_labels:
3687 if badge_label.lower() == 'members only':
3688 is_membersonly = True
3689 elif badge_label.lower() == 'premium':
3690 is_premium = True
3691 elif badge_label.lower() == 'unlisted':
3692 is_unlisted = True
c224251a 3693
c224251a
M
3694 info['availability'] = self._availability(
3695 is_private=is_private,
b28f8d24 3696 needs_premium=is_premium,
c224251a
M
3697 needs_subscription=is_membersonly,
3698 needs_auth=info['age_limit'] >= 18,
3699 is_unlisted=None if is_private is None else is_unlisted)
3700
a2160aa4 3701 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3702
11f9be09 3703 self.mark_watched(video_id, player_responses)
d77ab8e2 3704
545cc85d 3705 return info
c5e8d7af 3706
a61fd4cf 3707
a6213a49 3708class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3709
182bda88 3710 @staticmethod
3711 def passthrough_smuggled_data(func):
3712 def _smuggle(entries, smuggled_data):
3713 for entry in entries:
3714 # TODO: Convert URL to music.youtube instead.
3715 # Do we need to passthrough any other smuggled_data?
3716 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3717 yield entry
3718
3719 @functools.wraps(func)
3720 def wrapper(self, url):
3721 url, smuggled_data = unsmuggle_url(url, {})
3722 if self.is_music_url(url):
3723 smuggled_data['is_music_url'] = True
3724 info_dict = func(self, url, smuggled_data)
3725 if smuggled_data and info_dict.get('entries'):
3726 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3727 return info_dict
3728 return wrapper
3729
a6213a49 3730 def _extract_channel_id(self, webpage):
3731 channel_id = self._html_search_meta(
3732 'channelId', webpage, 'channel id', default=None)
3733 if channel_id:
3734 return channel_id
3735 channel_url = self._html_search_meta(
3736 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3737 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3738 'twitter:app:url:googleplay'), webpage, 'channel url')
3739 return self._search_regex(
3740 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3741 channel_url, 'channel id')
15f6397c 3742
8bdd16b4 3743 @staticmethod
cd7c66cf 3744 def _extract_basic_item_renderer(item):
3745 # Modified from _extract_grid_item_renderer
201c1459 3746 known_basic_renderers = (
3747 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3748 )
3749 for key, renderer in item.items():
201c1459 3750 if not isinstance(renderer, dict):
cd7c66cf 3751 continue
201c1459 3752 elif key in known_basic_renderers:
3753 return renderer
3754 elif key.startswith('grid') and key.endswith('Renderer'):
3755 return renderer
8bdd16b4 3756
8bdd16b4 3757 def _grid_entries(self, grid_renderer):
3758 for item in grid_renderer['items']:
3759 if not isinstance(item, dict):
39b62db1 3760 continue
cd7c66cf 3761 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3762 if not isinstance(renderer, dict):
3763 continue
052e1350 3764 title = self._get_text(renderer, 'title')
fe93e2c4 3765
8bdd16b4 3766 # playlist
3767 playlist_id = renderer.get('playlistId')
3768 if playlist_id:
3769 yield self.url_result(
3770 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3771 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3772 video_title=title)
201c1459 3773 continue
8bdd16b4 3774 # video
3775 video_id = renderer.get('videoId')
3776 if video_id:
3777 yield self._extract_video(renderer)
201c1459 3778 continue
8bdd16b4 3779 # channel
3780 channel_id = renderer.get('channelId')
3781 if channel_id:
8bdd16b4 3782 yield self.url_result(
3783 'https://www.youtube.com/channel/%s' % channel_id,
3784 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3785 continue
3786 # generic endpoint URL support
3787 ep_url = urljoin('https://www.youtube.com/', try_get(
3788 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3789 compat_str))
3790 if ep_url:
3791 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3792 if ie.suitable(ep_url):
3793 yield self.url_result(
3794 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3795 break
8bdd16b4 3796
16aa9ea4 3797 def _music_reponsive_list_entry(self, renderer):
3798 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3799 if video_id:
3800 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3801 ie=YoutubeIE.ie_key(), video_id=video_id)
3802 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3803 if playlist_id:
3804 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3805 if video_id:
3806 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3807 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3808 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3809 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3810 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3811 if browse_id:
3812 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3813 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3814
3d3dddc9 3815 def _shelf_entries_from_content(self, shelf_renderer):
3816 content = shelf_renderer.get('content')
3817 if not isinstance(content, dict):
8bdd16b4 3818 return
cd7c66cf 3819 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3820 if renderer:
3821 # TODO: add support for nested playlists so each shelf is processed
3822 # as separate playlist
3823 # TODO: this includes only first N items
3824 for entry in self._grid_entries(renderer):
3825 yield entry
3826 renderer = content.get('horizontalListRenderer')
3827 if renderer:
3828 # TODO
3829 pass
8bdd16b4 3830
29f7c58a 3831 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3832 ep = try_get(
3833 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3834 compat_str)
3835 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3836 if shelf_url:
29f7c58a 3837 # Skipping links to another channels, note that checking for
3838 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3839 # will not work
3840 if skip_channels and '/channels?' in shelf_url:
3841 return
052e1350 3842 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3843 yield self.url_result(shelf_url, video_title=title)
3844 # Shelf may not contain shelf URL, fallback to extraction from content
3845 for entry in self._shelf_entries_from_content(shelf_renderer):
3846 yield entry
c5e8d7af 3847
8bdd16b4 3848 def _playlist_entries(self, video_list_renderer):
3849 for content in video_list_renderer['contents']:
3850 if not isinstance(content, dict):
3851 continue
3852 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3853 if not isinstance(renderer, dict):
3854 continue
3855 video_id = renderer.get('videoId')
3856 if not video_id:
3857 continue
3858 yield self._extract_video(renderer)
07aeced6 3859
3462ffa8 3860 def _rich_entries(self, rich_grid_renderer):
3861 renderer = try_get(
70d5c17b 3862 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3863 video_id = renderer.get('videoId')
3864 if not video_id:
3865 return
3866 yield self._extract_video(renderer)
3867
8bdd16b4 3868 def _video_entry(self, video_renderer):
3869 video_id = video_renderer.get('videoId')
3870 if video_id:
3871 return self._extract_video(video_renderer)
dacb3a86 3872
8bdd16b4 3873 def _post_thread_entries(self, post_thread_renderer):
3874 post_renderer = try_get(
3875 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3876 if not post_renderer:
3877 return
3878 # video attachment
3879 video_renderer = try_get(
895b0931 3880 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3881 video_id = video_renderer.get('videoId')
3882 if video_id:
3883 entry = self._extract_video(video_renderer)
8bdd16b4 3884 if entry:
3885 yield entry
895b0931 3886 # playlist attachment
3887 playlist_id = try_get(
3888 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3889 if playlist_id:
3890 yield self.url_result(
e28f1c0a 3891 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3892 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3893 # inline video links
3894 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3895 for run in runs:
3896 if not isinstance(run, dict):
3897 continue
3898 ep_url = try_get(
3899 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3900 if not ep_url:
3901 continue
3902 if not YoutubeIE.suitable(ep_url):
3903 continue
3904 ep_video_id = YoutubeIE._match_id(ep_url)
3905 if video_id == ep_video_id:
3906 continue
895b0931 3907 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3908
8bdd16b4 3909 def _post_thread_continuation_entries(self, post_thread_continuation):
3910 contents = post_thread_continuation.get('contents')
3911 if not isinstance(contents, list):
3912 return
3913 for content in contents:
3914 renderer = content.get('backstagePostThreadRenderer')
3915 if not isinstance(renderer, dict):
3916 continue
3917 for entry in self._post_thread_entries(renderer):
3918 yield entry
07aeced6 3919
39ed931e 3920 r''' # unused
3921 def _rich_grid_entries(self, contents):
3922 for content in contents:
3923 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3924 if video_renderer:
3925 entry = self._video_entry(video_renderer)
3926 if entry:
3927 yield entry
3928 '''
a6213a49 3929 def _extract_entries(self, parent_renderer, continuation_list):
3930 # continuation_list is modified in-place with continuation_list = [continuation_token]
3931 continuation_list[:] = [None]
3932 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3933 for content in contents:
3934 if not isinstance(content, dict):
3935 continue
16aa9ea4 3936 is_renderer = traverse_obj(
3937 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3938 expected_type=dict)
a6213a49 3939 if not is_renderer:
3940 renderer = content.get('richItemRenderer')
3941 if renderer:
3942 for entry in self._rich_entries(renderer):
3943 yield entry
3944 continuation_list[0] = self._extract_continuation(parent_renderer)
3945 continue
3946 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3947 for isr_content in isr_contents:
3948 if not isinstance(isr_content, dict):
8bdd16b4 3949 continue
69184e41 3950
a6213a49 3951 known_renderers = {
3952 'playlistVideoListRenderer': self._playlist_entries,
3953 'gridRenderer': self._grid_entries,
3954 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3955 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3956 'backstagePostThreadRenderer': self._post_thread_entries,
3957 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3958 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3959 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3960 }
3961 for key, renderer in isr_content.items():
3962 if key not in known_renderers:
3963 continue
3964 for entry in known_renderers[key](renderer):
3965 if entry:
3966 yield entry
3967 continuation_list[0] = self._extract_continuation(renderer)
3968 break
70d5c17b 3969
3970 if not continuation_list[0]:
a6213a49 3971 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3972
a6213a49 3973 if not continuation_list[0]:
3974 continuation_list[0] = self._extract_continuation(parent_renderer)
3975
3976 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3977 continuation_list = [None]
3978 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3979 tab_content = try_get(tab, lambda x: x['content'], dict)
3980 if not tab_content:
3981 return
3462ffa8 3982 parent_renderer = (
29f7c58a 3983 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3984 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3985 for entry in extract_entries(parent_renderer):
3986 yield entry
3462ffa8 3987 continuation = continuation_list[0]
d069eca7 3988
8bdd16b4 3989 for page_num in itertools.count(1):
3990 if not continuation:
3991 break
99e9e001 3992 headers = self.generate_api_headers(
3993 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3994 response = self._extract_response(
3995 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3996 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3997 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3998
3999 if not response:
8bdd16b4 4000 break
ac56cf38 4001 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4002 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4003 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4004
69184e41 4005 known_continuation_renderers = {
4006 'playlistVideoListContinuation': self._playlist_entries,
4007 'gridContinuation': self._grid_entries,
4008 'itemSectionContinuation': self._post_thread_continuation_entries,
4009 'sectionListContinuation': extract_entries, # for feeds
4010 }
8bdd16b4 4011 continuation_contents = try_get(
69184e41 4012 response, lambda x: x['continuationContents'], dict) or {}
4013 continuation_renderer = None
4014 for key, value in continuation_contents.items():
4015 if key not in known_continuation_renderers:
3462ffa8 4016 continue
69184e41 4017 continuation_renderer = value
4018 continuation_list = [None]
4019 for entry in known_continuation_renderers[key](continuation_renderer):
4020 yield entry
4021 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4022 break
4023 if continuation_renderer:
4024 continue
c5e8d7af 4025
a1b535bd 4026 known_renderers = {
4027 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4028 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4029 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4030 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4031 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4032 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4033 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4034 }
cce889b9 4035 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4036 continuation_items = try_get(
cce889b9 4037 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4038 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4039 video_items_renderer = None
4040 for key, value in continuation_item.items():
4041 if key not in known_renderers:
8bdd16b4 4042 continue
a1b535bd 4043 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4044 continuation_list = [None]
a1b535bd 4045 for entry in known_renderers[key][0](video_items_renderer):
4046 yield entry
9ba5705a 4047 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4048 break
4049 if video_items_renderer:
4050 continue
8bdd16b4 4051 break
9558dcec 4052
8bdd16b4 4053 @staticmethod
7c219ea6 4054 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4055 for tab in tabs:
cd684175 4056 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4057 if renderer.get('selected') is True:
4058 return renderer
2b3c2546 4059 else:
7c219ea6 4060 if fatal:
4061 raise ExtractorError('Unable to find selected tab')
b82f815f 4062
47193e02 4063 @classmethod
4064 def _extract_uploader(cls, data):
8bdd16b4 4065 uploader = {}
47193e02 4066 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4067 owner = try_get(
4068 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4069 if owner:
4070 uploader['uploader'] = owner.get('text')
4071 uploader['uploader_id'] = try_get(
4072 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4073 uploader['uploader_url'] = urljoin(
4074 'https://www.youtube.com/',
4075 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4076 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4077
ac56cf38 4078 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4079 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4080 tags = []
b60419c5 4081
8bdd16b4 4082 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4083 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4084 renderer = try_get(
4085 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4086 if renderer:
b60419c5 4087 channel_name = renderer.get('title')
4088 channel_url = renderer.get('channelUrl')
4089 channel_id = renderer.get('externalId')
39ed931e 4090 else:
64c0d954 4091 renderer = try_get(
4092 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4093
8bdd16b4 4094 if renderer:
4095 title = renderer.get('title')
ecc97af3 4096 description = renderer.get('description', '')
b60419c5 4097 playlist_id = channel_id
4098 tags = renderer.get('keywords', '').split()
b60419c5 4099
301d07fc 4100 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4101 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4102 def _get_uncropped(url):
4103 return url_or_none((url or '').split('=')[0] + '=s0')
4104
4105 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4106 if avatar_thumbnails:
4107 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4108 if uncropped_avatar:
4109 avatar_thumbnails.append({
4110 'url': uncropped_avatar,
4111 'id': 'avatar_uncropped',
4112 'preference': 1
4113 })
4114
4115 channel_banners = self._extract_thumbnails(
4116 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4117 for banner in channel_banners:
4118 banner['preference'] = -10
4119
4120 if channel_banners:
4121 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4122 if uncropped_banner:
4123 channel_banners.append({
4124 'url': uncropped_banner,
4125 'id': 'banner_uncropped',
4126 'preference': -5
4127 })
4128
4129 primary_thumbnails = self._extract_thumbnails(
4130 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4131
3462ffa8 4132 if playlist_id is None:
70d5c17b 4133 playlist_id = item_id
f0d785d3 4134
4135 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4136 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4137 if title is None:
f0d785d3 4138 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4139 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4140 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4141
b60419c5 4142 metadata = {
4143 'playlist_id': playlist_id,
4144 'playlist_title': title,
4145 'playlist_description': description,
4146 'uploader': channel_name,
4147 'uploader_id': channel_id,
4148 'uploader_url': channel_url,
301d07fc 4149 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4150 'tags': tags,
f0d785d3 4151 'view_count': self._get_count(playlist_stats, 1),
4152 'availability': self._extract_availability(data),
4153 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4154 'playlist_count': self._get_count(playlist_stats, 0),
4155 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4156 }
4157 if not channel_id:
4158 metadata.update(self._extract_uploader(data))
4159 metadata.update({
4160 'channel': metadata['uploader'],
4161 'channel_id': metadata['uploader_id'],
4162 'channel_url': metadata['uploader_url']})
4163 return self.playlist_result(
d069eca7 4164 self._entries(
ac56cf38 4165 selected_tab, playlist_id, ytcfg,
4166 self._extract_account_syncid(ytcfg, data),
4167 self._extract_visitor_data(data, ytcfg)),
b60419c5 4168 **metadata)
73c4ac2c 4169
ac56cf38 4170 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4171 first_id = last_id = response = None
2be71994 4172 for page_num in itertools.count(1):
cd7c66cf 4173 videos = list(self._playlist_entries(playlist))
4174 if not videos:
4175 return
2be71994 4176 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4177 if start >= len(videos):
4178 return
4179 for video in videos[start:]:
4180 if video['id'] == first_id:
4181 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4182 return
4183 yield video
4184 first_id = first_id or videos[0]['id']
4185 last_id = videos[-1]['id']
79360d99 4186 watch_endpoint = try_get(
4187 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4188 headers = self.generate_api_headers(
4189 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4190 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4191 query = {
4192 'playlistId': playlist_id,
4193 'videoId': watch_endpoint.get('videoId') or last_id,
4194 'index': watch_endpoint.get('index') or len(videos),
4195 'params': watch_endpoint.get('params') or 'OAE%3D'
4196 }
4197 response = self._extract_response(
4198 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4199 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4200 check_get_keys='contents'
4201 )
cd7c66cf 4202 playlist = try_get(
79360d99 4203 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4204
ac56cf38 4205 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4206 title = playlist.get('title') or try_get(
4207 data, lambda x: x['titleText']['simpleText'], compat_str)
4208 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4209
4210 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4211 playlist_url = urljoin(url, try_get(
4212 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4213 compat_str))
4214 if playlist_url and playlist_url != url:
4215 return self.url_result(
4216 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4217 video_title=title)
cd7c66cf 4218
8bdd16b4 4219 return self.playlist_result(
ac56cf38 4220 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4221 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4222
47193e02 4223 def _extract_availability(self, data):
4224 """
4225 Gets the availability of a given playlist/tab.
4226 Note: Unless YouTube tells us explicitly, we do not assume it is public
4227 @param data: response
4228 """
4229 is_private = is_unlisted = None
4230 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4231 badge_labels = self._extract_badges(renderer)
4232
4233 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4234 privacy_dropdown_entries = try_get(
4235 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4236 for renderer_dict in privacy_dropdown_entries:
4237 is_selected = try_get(
4238 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4239 if not is_selected:
4240 continue
052e1350 4241 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4242 if label:
4243 badge_labels.add(label.lower())
4244 break
4245
4246 for badge_label in badge_labels:
4247 if badge_label == 'unlisted':
4248 is_unlisted = True
4249 elif badge_label == 'private':
4250 is_private = True
4251 elif badge_label == 'public':
4252 is_unlisted = is_private = False
4253 return self._availability(is_private, False, False, False, is_unlisted)
4254
4255 @staticmethod
4256 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4257 sidebar_renderer = try_get(
4258 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4259 for item in sidebar_renderer:
4260 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4261 if renderer:
4262 return renderer
4263
ac56cf38 4264 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4265 """
4266 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4267 """
5d342002 4268 browse_id = params = None
47193e02 4269 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4270 if not renderer:
4271 return
4272 menu_renderer = try_get(
4273 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4274 for menu_item in menu_renderer:
4275 if not isinstance(menu_item, dict):
358de58c 4276 continue
47193e02 4277 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4278 text = try_get(
4279 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4280 if not text or text.lower() != 'show unavailable videos':
4281 continue
4282 browse_endpoint = try_get(
4283 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4284 browse_id = browse_endpoint.get('browseId')
4285 params = browse_endpoint.get('params')
4286 break
5d342002 4287
11f9be09 4288 headers = self.generate_api_headers(
99e9e001 4289 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4290 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4291 query = {
4292 'params': params or 'wgYCCAA=',
4293 'browseId': browse_id or 'VL%s' % item_id
4294 }
4295 return self._extract_response(
4296 item_id=item_id, headers=headers, query=query,
fe93e2c4 4297 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4298 note='Downloading API JSON with unavailable videos')
358de58c 4299
ac56cf38 4300 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4301 retries = self.get_param('extractor_retries', 3)
62bff2c1 4302 count = -1
ac56cf38 4303 webpage = data = last_error = None
14fdfea9 4304 while count < retries:
62bff2c1 4305 count += 1
14fdfea9 4306 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4307 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4308 if last_error:
c705177d 4309 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4310 try:
4311 webpage = self._download_webpage(
4312 url, item_id,
4313 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4314 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4315 except ExtractorError as e:
4316 if isinstance(e.cause, network_exceptions):
4317 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4318 last_error = error_to_compat_str(e.cause or e.msg)
4319 if count < retries:
4320 continue
4321 if fatal:
4322 raise
4323 self.report_warning(error_to_compat_str(e))
14fdfea9 4324 break
ac56cf38 4325 else:
4326 try:
4327 self._extract_and_report_alerts(data)
4328 except ExtractorError as e:
4329 if fatal:
4330 raise
4331 self.report_warning(error_to_compat_str(e))
4332 break
4333
7c219ea6 4334 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4335 break
4336
4337 last_error = 'Incomplete yt initial data received'
4338 if count >= retries:
4339 if fatal:
4340 raise ExtractorError(last_error)
4341 self.report_warning(last_error)
4342 break
4343
cd7c66cf 4344 return webpage, data
4345
ac56cf38 4346 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4347 data = None
4348 if 'webpage' not in self._configuration_arg('skip'):
4349 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4350 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4351 # Reject webpage data if redirected to home page without explicitly requesting
4352 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4353 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4354 if (url != 'https://www.youtube.com/feed/recommended'
4355 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4356 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4357 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4358 if fatal:
4359 raise ExtractorError(msg, expected=True)
4360 self.report_warning(msg, only_once=True)
ac56cf38 4361 if not data:
4362 if not ytcfg and self.is_authenticated:
4363 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4364 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4365 raise ExtractorError(
4366 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4367 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4368 expected=True)
4369 self.report_warning(msg, only_once=True)
4370 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4371 return data, ytcfg
4372
4373 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4374 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4375 resolve_response = self._extract_response(
4376 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4377 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4378 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4379 for ep_key, ep in endpoints.items():
4380 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4381 if params:
4382 return self._extract_response(
4383 item_id=item_id, query=params, ep=ep, headers=headers,
4384 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4385 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4386 err_note = 'Failed to resolve url (does the playlist exist?)'
4387 if fatal:
4388 raise ExtractorError(err_note, expected=True)
4389 self.report_warning(err_note, item_id)
4390
a6213a49 4391 _SEARCH_PARAMS = None
4392
af5c1c55 4393 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4394 data = {'query': query}
4395 if params is NO_DEFAULT:
4396 params = self._SEARCH_PARAMS
4397 if params:
4398 data['params'] = params
16aa9ea4 4399
4400 content_keys = (
4401 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4402 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4403 # ytmusic search
4404 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4405 ('continuationContents', ),
4406 )
4407 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4408
a61fd4cf 4409 continuation_list = [None]
a6213a49 4410 for page_num in itertools.count(1):
a61fd4cf 4411 data.update(continuation_list[0] or {})
a6213a49 4412 search = self._extract_response(
4413 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4414 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4415 slr_contents = traverse_obj(search, *content_keys)
4416 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4417 if not continuation_list[0]:
a6213a49 4418 break
4419
4420
4421class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4422 IE_DESC = 'YouTube Tabs'
4423 _VALID_URL = r'''(?x:
4424 https?://
4425 (?:\w+\.)?
4426 (?:
4427 youtube(?:kids)?\.com|
4428 %(invidious)s
4429 )/
4430 (?:
4431 (?P<channel_type>channel|c|user|browse)/|
4432 (?P<not_channel>
4433 feed/|hashtag/|
4434 (?:playlist|watch)\?.*?\blist=
4435 )|
4436 (?!(?:%(reserved_names)s)\b) # Direct URLs
4437 )
4438 (?P<id>[^/?\#&]+)
4439 )''' % {
4440 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4441 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4442 }
4443 IE_NAME = 'youtube:tab'
4444
4445 _TESTS = [{
4446 'note': 'playlists, multipage',
4447 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4448 'playlist_mincount': 94,
4449 'info_dict': {
4450 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4451 'title': 'Igor Kleiner - Playlists',
a6213a49 4452 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4453 'uploader': 'Igor Kleiner',
a6213a49 4454 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4455 'channel': 'Igor Kleiner',
4456 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4457 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4458 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4459 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4460 'channel_follower_count': int
a6213a49 4461 },
4462 }, {
4463 'note': 'playlists, multipage, different order',
4464 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4465 'playlist_mincount': 94,
4466 'info_dict': {
4467 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4468 'title': 'Igor Kleiner - Playlists',
a6213a49 4469 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4470 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4471 'uploader': 'Igor Kleiner',
4472 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4473 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4474 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4475 'channel': 'Igor Kleiner',
4476 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4477 'channel_follower_count': int
a6213a49 4478 },
4479 }, {
4480 'note': 'playlists, series',
4481 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4482 'playlist_mincount': 5,
4483 'info_dict': {
4484 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4485 'title': '3Blue1Brown - Playlists',
4486 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4487 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4488 'uploader': '3Blue1Brown',
976ae3ea 4489 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4490 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4491 'channel': '3Blue1Brown',
4492 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4493 'tags': ['Mathematics'],
6c73052c 4494 'channel_follower_count': int
a6213a49 4495 },
4496 }, {
4497 'note': 'playlists, singlepage',
4498 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4499 'playlist_mincount': 4,
4500 'info_dict': {
4501 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4502 'title': 'ThirstForScience - Playlists',
4503 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4504 'uploader': 'ThirstForScience',
4505 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4506 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4507 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4508 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4509 'tags': 'count:13',
4510 'channel': 'ThirstForScience',
6c73052c 4511 'channel_follower_count': int
a6213a49 4512 }
4513 }, {
4514 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4515 'only_matching': True,
4516 }, {
4517 'note': 'basic, single video playlist',
4518 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4519 'info_dict': {
4520 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4521 'uploader': 'Sergey M.',
4522 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4523 'title': 'youtube-dl public playlist',
976ae3ea 4524 'description': '',
4525 'tags': [],
4526 'view_count': int,
4527 'modified_date': '20201130',
4528 'channel': 'Sergey M.',
4529 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4530 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4531 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4532 },
4533 'playlist_count': 1,
4534 }, {
4535 'note': 'empty playlist',
4536 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4537 'info_dict': {
4538 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4539 'uploader': 'Sergey M.',
4540 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4541 'title': 'youtube-dl empty playlist',
976ae3ea 4542 'tags': [],
4543 'channel': 'Sergey M.',
4544 'description': '',
4545 'modified_date': '20160902',
4546 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4547 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4548 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4549 },
4550 'playlist_count': 0,
4551 }, {
4552 'note': 'Home tab',
4553 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4554 'info_dict': {
4555 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4556 'title': 'lex will - Home',
4557 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4558 'uploader': 'lex will',
4559 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4560 'channel': 'lex will',
4561 'tags': ['bible', 'history', 'prophesy'],
4562 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4563 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4564 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4565 'channel_follower_count': int
a6213a49 4566 },
4567 'playlist_mincount': 2,
4568 }, {
4569 'note': 'Videos tab',
4570 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4571 'info_dict': {
4572 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4573 'title': 'lex will - Videos',
4574 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4575 'uploader': 'lex will',
4576 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4577 'tags': ['bible', 'history', 'prophesy'],
4578 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4579 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4580 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4581 'channel': 'lex will',
6c73052c 4582 'channel_follower_count': int
a6213a49 4583 },
4584 'playlist_mincount': 975,
4585 }, {
4586 'note': 'Videos tab, sorted by popular',
4587 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4588 'info_dict': {
4589 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4590 'title': 'lex will - Videos',
4591 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4592 'uploader': 'lex will',
4593 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4594 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4595 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4596 'channel': 'lex will',
4597 'tags': ['bible', 'history', 'prophesy'],
4598 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4599 'channel_follower_count': int
a6213a49 4600 },
4601 'playlist_mincount': 199,
4602 }, {
4603 'note': 'Playlists tab',
4604 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4605 'info_dict': {
4606 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4607 'title': 'lex will - Playlists',
4608 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4609 'uploader': 'lex will',
4610 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4611 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4612 'channel': 'lex will',
4613 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4614 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4615 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4616 'channel_follower_count': int
a6213a49 4617 },
4618 'playlist_mincount': 17,
4619 }, {
4620 'note': 'Community tab',
4621 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4622 'info_dict': {
4623 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4624 'title': 'lex will - Community',
4625 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4626 'uploader': 'lex will',
4627 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4628 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4629 'channel': 'lex will',
4630 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4631 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4632 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4633 'channel_follower_count': int
a6213a49 4634 },
4635 'playlist_mincount': 18,
4636 }, {
4637 'note': 'Channels tab',
4638 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4639 'info_dict': {
4640 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4641 'title': 'lex will - Channels',
4642 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4643 'uploader': 'lex will',
4644 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4645 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4646 'channel': 'lex will',
4647 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4648 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4649 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4650 'channel_follower_count': int
a6213a49 4651 },
4652 'playlist_mincount': 12,
4653 }, {
4654 'note': 'Search tab',
4655 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4656 'playlist_mincount': 40,
4657 'info_dict': {
4658 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4659 'title': '3Blue1Brown - Search - linear algebra',
4660 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4661 'uploader': '3Blue1Brown',
4662 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4663 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4664 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4665 'tags': ['Mathematics'],
4666 'channel': '3Blue1Brown',
4667 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4668 'channel_follower_count': int
a6213a49 4669 },
4670 }, {
4671 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4672 'only_matching': True,
4673 }, {
4674 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4675 'only_matching': True,
4676 }, {
4677 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4678 'only_matching': True,
4679 }, {
4680 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4681 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4682 'info_dict': {
4683 'title': '29C3: Not my department',
4684 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4685 'uploader': 'Christiaan008',
4686 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4687 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4688 'tags': [],
4689 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4690 'view_count': int,
4691 'modified_date': '20150605',
4692 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4693 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4694 'channel': 'Christiaan008',
a6213a49 4695 },
4696 'playlist_count': 96,
4697 }, {
4698 'note': 'Large playlist',
4699 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4700 'info_dict': {
4701 'title': 'Uploads from Cauchemar',
4702 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4703 'uploader': 'Cauchemar',
4704 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4705 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4706 'tags': [],
4707 'modified_date': r're:\d{8}',
4708 'channel': 'Cauchemar',
4709 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4710 'view_count': int,
4711 'description': '',
4712 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4713 },
4714 'playlist_mincount': 1123,
976ae3ea 4715 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4716 }, {
4717 'note': 'even larger playlist, 8832 videos',
4718 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4719 'only_matching': True,
4720 }, {
4721 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4722 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4723 'info_dict': {
4724 'title': 'Uploads from Interstellar Movie',
4725 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4726 'uploader': 'Interstellar Movie',
4727 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4728 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4729 'tags': [],
4730 'view_count': int,
4731 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4732 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4733 'channel': 'Interstellar Movie',
4734 'description': '',
4735 'modified_date': r're:\d{8}',
a6213a49 4736 },
4737 'playlist_mincount': 21,
4738 }, {
4739 'note': 'Playlist with "show unavailable videos" button',
4740 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4741 'info_dict': {
4742 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4743 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4744 'uploader': 'Phim Siêu Nhân Nhật Bản',
4745 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4746 'view_count': int,
4747 'channel': 'Phim Siêu Nhân Nhật Bản',
4748 'tags': [],
4749 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4750 'description': '',
4751 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4752 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4753 'modified_date': r're:\d{8}',
a6213a49 4754 },
4755 'playlist_mincount': 200,
976ae3ea 4756 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4757 }, {
4758 'note': 'Playlist with unavailable videos in page 7',
4759 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4760 'info_dict': {
4761 'title': 'Uploads from BlankTV',
4762 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4763 'uploader': 'BlankTV',
4764 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4765 'channel': 'BlankTV',
4766 'channel_url': 'https://www.youtube.com/c/blanktv',
4767 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4768 'view_count': int,
4769 'tags': [],
4770 'uploader_url': 'https://www.youtube.com/c/blanktv',
4771 'modified_date': r're:\d{8}',
4772 'description': '',
a6213a49 4773 },
4774 'playlist_mincount': 1000,
976ae3ea 4775 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4776 }, {
4777 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4778 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4779 'info_dict': {
4780 'title': 'Data Analysis with Dr Mike Pound',
4781 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4782 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4783 'uploader': 'Computerphile',
4784 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4785 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4786 'tags': [],
4787 'view_count': int,
4788 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4789 'channel_url': 'https://www.youtube.com/user/Computerphile',
4790 'channel': 'Computerphile',
a6213a49 4791 },
4792 'playlist_mincount': 11,
4793 }, {
4794 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4795 'only_matching': True,
4796 }, {
4797 'note': 'Playlist URL that does not actually serve a playlist',
4798 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4799 'info_dict': {
4800 'id': 'FqZTN594JQw',
4801 'ext': 'webm',
4802 'title': "Smiley's People 01 detective, Adventure Series, Action",
4803 'uploader': 'STREEM',
4804 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4805 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4806 'upload_date': '20150526',
4807 'license': 'Standard YouTube License',
4808 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4809 'categories': ['People & Blogs'],
4810 'tags': list,
4811 'view_count': int,
4812 'like_count': int,
a6213a49 4813 },
4814 'params': {
4815 'skip_download': True,
4816 },
4817 'skip': 'This video is not available.',
4818 'add_ie': [YoutubeIE.ie_key()],
4819 }, {
4820 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4821 'only_matching': True,
4822 }, {
4823 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4824 'only_matching': True,
4825 }, {
4826 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4827 'info_dict': {
6c73052c 4828 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4829 'ext': 'mp4',
976ae3ea 4830 'title': str,
a6213a49 4831 'uploader': 'Sky News',
4832 'uploader_id': 'skynews',
4833 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4834 'upload_date': r're:\d{8}',
976ae3ea 4835 'description': str,
a6213a49 4836 'categories': ['News & Politics'],
4837 'tags': list,
4838 'like_count': int,
6c73052c 4839 'release_timestamp': 1642502819,
976ae3ea 4840 'channel': 'Sky News',
4841 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4842 'age_limit': 0,
4843 'view_count': int,
6c73052c 4844 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4845 'playable_in_embed': True,
6c73052c 4846 'release_date': '20220118',
976ae3ea 4847 'availability': 'public',
4848 'live_status': 'is_live',
4849 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4850 'channel_follower_count': int
a6213a49 4851 },
4852 'params': {
4853 'skip_download': True,
4854 },
976ae3ea 4855 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4856 }, {
4857 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4858 'info_dict': {
4859 'id': 'a48o2S1cPoo',
4860 'ext': 'mp4',
4861 'title': 'The Young Turks - Live Main Show',
4862 'uploader': 'The Young Turks',
4863 'uploader_id': 'TheYoungTurks',
4864 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4865 'upload_date': '20150715',
4866 'license': 'Standard YouTube License',
4867 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4868 'categories': ['News & Politics'],
4869 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4870 'like_count': int,
a6213a49 4871 },
4872 'params': {
4873 'skip_download': True,
4874 },
4875 'only_matching': True,
4876 }, {
4877 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4878 'only_matching': True,
4879 }, {
4880 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4881 'only_matching': True,
4882 }, {
4883 'note': 'A channel that is not live. Should raise error',
4884 'url': 'https://www.youtube.com/user/numberphile/live',
4885 'only_matching': True,
4886 }, {
4887 'url': 'https://www.youtube.com/feed/trending',
4888 'only_matching': True,
4889 }, {
4890 'url': 'https://www.youtube.com/feed/library',
4891 'only_matching': True,
4892 }, {
4893 'url': 'https://www.youtube.com/feed/history',
4894 'only_matching': True,
4895 }, {
4896 'url': 'https://www.youtube.com/feed/subscriptions',
4897 'only_matching': True,
4898 }, {
4899 'url': 'https://www.youtube.com/feed/watch_later',
4900 'only_matching': True,
4901 }, {
4902 'note': 'Recommended - redirects to home page.',
4903 'url': 'https://www.youtube.com/feed/recommended',
4904 'only_matching': True,
4905 }, {
4906 'note': 'inline playlist with not always working continuations',
4907 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4908 'only_matching': True,
4909 }, {
4910 'url': 'https://www.youtube.com/course',
4911 'only_matching': True,
4912 }, {
4913 'url': 'https://www.youtube.com/zsecurity',
4914 'only_matching': True,
4915 }, {
4916 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4917 'only_matching': True,
4918 }, {
4919 'url': 'https://www.youtube.com/TheYoungTurks/live',
4920 'only_matching': True,
4921 }, {
4922 'url': 'https://www.youtube.com/hashtag/cctv9',
4923 'info_dict': {
4924 'id': 'cctv9',
4925 'title': '#cctv9',
976ae3ea 4926 'tags': [],
a6213a49 4927 },
4928 'playlist_mincount': 350,
4929 }, {
4930 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4931 'only_matching': True,
4932 }, {
4933 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4934 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4935 'only_matching': True
4936 }, {
4937 'note': '/browse/ should redirect to /channel/',
4938 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4939 'only_matching': True
4940 }, {
4941 'note': 'VLPL, should redirect to playlist?list=PL...',
4942 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4943 'info_dict': {
4944 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4945 'uploader': 'NoCopyrightSounds',
4946 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4947 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4948 'title': 'NCS Releases',
976ae3ea 4949 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4950 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4951 'modified_date': r're:\d{8}',
4952 'view_count': int,
4953 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4954 'tags': [],
4955 'channel': 'NoCopyrightSounds',
a6213a49 4956 },
4957 'playlist_mincount': 166,
976ae3ea 4958 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4959 }, {
4960 'note': 'Topic, should redirect to playlist?list=UU...',
4961 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4962 'info_dict': {
4963 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4964 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4965 'title': 'Uploads from Royalty Free Music - Topic',
4966 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4967 'tags': [],
4968 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4969 'channel': 'Royalty Free Music - Topic',
4970 'view_count': int,
4971 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4972 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4973 'modified_date': r're:\d{8}',
4974 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4975 'description': '',
a6213a49 4976 },
4977 'expected_warnings': [
a6213a49 4978 'The URL does not have a videos tab',
976ae3ea 4979 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4980 ],
4981 'playlist_mincount': 101,
4982 }, {
4983 'note': 'Topic without a UU playlist',
4984 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4985 'info_dict': {
4986 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4987 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4988 'tags': [],
a6213a49 4989 },
4990 'expected_warnings': [
976ae3ea 4991 'the playlist redirect gave error',
a6213a49 4992 ],
4993 'playlist_mincount': 9,
4994 }, {
4995 'note': 'Youtube music Album',
4996 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4997 'info_dict': {
4998 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4999 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5000 'tags': [],
5001 'view_count': int,
5002 'description': '',
5003 'availability': 'unlisted',
5004 'modified_date': r're:\d{8}',
a6213a49 5005 },
5006 'playlist_count': 50,
5007 }, {
5008 'note': 'unlisted single video playlist',
5009 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5010 'info_dict': {
5011 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5012 'uploader': 'colethedj',
5013 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5014 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5015 'availability': 'unlisted',
5016 'tags': [],
5017 'modified_date': '20211208',
5018 'channel': 'colethedj',
5019 'view_count': int,
5020 'description': '',
5021 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5022 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5023 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5024 },
5025 'playlist_count': 1,
5026 }, {
5027 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5028 'url': 'https://www.youtube.com/feed/recommended',
5029 'info_dict': {
5030 'id': 'recommended',
5031 'title': 'recommended',
6c73052c 5032 'tags': [],
a6213a49 5033 },
5034 'playlist_mincount': 50,
5035 'params': {
5036 'skip_download': True,
5037 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5038 },
5039 }, {
5040 'note': 'API Fallback: /videos tab, sorted by oldest first',
5041 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5042 'info_dict': {
5043 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5044 'title': 'Cody\'sLab - Videos',
5045 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5046 'uploader': 'Cody\'sLab',
5047 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5048 'channel': 'Cody\'sLab',
5049 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5050 'tags': [],
5051 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5052 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5053 'channel_follower_count': int
a6213a49 5054 },
5055 'playlist_mincount': 650,
5056 'params': {
5057 'skip_download': True,
5058 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5059 },
5060 }, {
5061 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5062 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5063 'info_dict': {
5064 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5065 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5066 'title': 'Uploads from Royalty Free Music - Topic',
5067 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5068 'modified_date': r're:\d{8}',
5069 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5070 'description': '',
5071 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5072 'tags': [],
5073 'channel': 'Royalty Free Music - Topic',
5074 'view_count': int,
5075 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5076 },
5077 'expected_warnings': [
976ae3ea 5078 'does not have a videos tab',
5079 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5080 ],
5081 'playlist_mincount': 101,
5082 'params': {
5083 'skip_download': True,
5084 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5085 },
7c219ea6 5086 }, {
5087 'note': 'non-standard redirect to regional channel',
5088 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5089 'only_matching': True
a6213a49 5090 }]
5091
5092 @classmethod
5093 def suitable(cls, url):
5094 return False if YoutubeIE.suitable(url) else super(
5095 YoutubeTabIE, cls).suitable(url)
9297939e 5096
64f36541 5097 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5098
182bda88 5099 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5100 def _real_extract(self, url, smuggled_data):
cd7c66cf 5101 item_id = self._match_id(url)
5102 url = compat_urlparse.urlunparse(
5103 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5104 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5105
fe03a6cd 5106 def get_mobj(url):
37e57a9f 5107 mobj = self._URL_RE.match(url).groupdict()
07cce701 5108 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5109 return mobj
5110
37e57a9f 5111 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5112 # Youtube returns incomplete data if tabname is not lower case
5113 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5114 if is_channel:
5115 if smuggled_data.get('is_music_url'):
37e57a9f 5116 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5117 item_id = item_id[2:]
37e57a9f 5118 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5119 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5120 mdata = self._extract_tab_endpoint(
37e57a9f 5121 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5122 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5123 get_all=False, expected_type=compat_str)
ac56cf38 5124 if not murl:
37e57a9f 5125 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5126 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5127 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5128 pre = f'https://www.youtube.com/channel/{item_id}'
5129
64f36541 5130 original_tab_name = tab
fe03a6cd 5131 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5132 # Home URLs should redirect to /videos/
37e57a9f 5133 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5134 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5135 tab = '/videos'
5136
5137 url = ''.join((pre, tab, post))
5138 mobj = get_mobj(url)
cd7c66cf 5139
5140 # Handle both video/playlist URLs
201c1459 5141 qs = parse_qs(url)
37e57a9f 5142 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5143
fe03a6cd 5144 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5145 if not playlist_id:
fe03a6cd 5146 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5147 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5148 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5149 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5150 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5151 mobj = get_mobj(url)
cd7c66cf 5152
5153 if video_id and playlist_id:
a06916d9 5154 if self.get_param('noplaylist'):
37e57a9f 5155 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5156 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5157 ie=YoutubeIE.ie_key(), video_id=video_id)
5158 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5159
ac56cf38 5160 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5161
7c219ea6 5162 # YouTube may provide a non-standard redirect to the regional channel
5163 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5164 redirect_url = traverse_obj(
5165 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5166 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5167 redirect_url = ''.join((
5168 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5169 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5170 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5171
37e57a9f 5172 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5173 if tabs:
5174 selected_tab = self._extract_selected_tab(tabs)
64f36541 5175 selected_tab_name = selected_tab.get('title', '').lower()
5176 if selected_tab_name == 'home':
5177 selected_tab_name = 'featured'
5178 requested_tab_name = mobj['tab'][1:]
09f1580e 5179 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5180 if requested_tab_name == 'live':
09f1580e 5181 # Live tab should have redirected to the video
5182 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5183 if requested_tab_name not in ('', selected_tab_name):
5184 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5185 if not original_tab_name:
5186 if item_id[:2] == 'UC':
5187 # Topic channels don't have /videos. Use the equivalent playlist instead
5188 pl_id = f'UU{item_id[2:]}'
5189 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5190 try:
5191 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5192 except ExtractorError:
5193 redirect_warning += ' and the playlist redirect gave error'
5194 else:
5195 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5196 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5197 if selected_tab_name and selected_tab_name != requested_tab_name:
5198 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5199 else:
5200 raise ExtractorError(redirect_warning, expected=True)
18db7548 5201
37e57a9f 5202 if redirect_warning:
64f36541 5203 self.to_screen(redirect_warning)
37e57a9f 5204 self.write_debug(f'Final URL: {url}')
18db7548 5205
358de58c 5206 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5207 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5208 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5209 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5210 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5211 if tabs:
ac56cf38 5212 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5213
37e57a9f 5214 playlist = traverse_obj(
5215 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5216 if playlist:
ac56cf38 5217 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5218
37e57a9f 5219 video_id = traverse_obj(
5220 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5221 if video_id:
09f1580e 5222 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5223 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5224 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5225 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5226
8bdd16b4 5227 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5228
c5e8d7af 5229
8bdd16b4 5230class YoutubePlaylistIE(InfoExtractor):
96565c7e 5231 IE_DESC = 'YouTube playlists'
8bdd16b4 5232 _VALID_URL = r'''(?x)(?:
5233 (?:https?://)?
5234 (?:\w+\.)?
5235 (?:
5236 (?:
5237 youtube(?:kids)?\.com|
d9190e44 5238 %(invidious)s
8bdd16b4 5239 )
5240 /.*?\?.*?\blist=
5241 )?
5242 (?P<id>%(playlist_id)s)
d9190e44
RH
5243 )''' % {
5244 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5245 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5246 }
8bdd16b4 5247 IE_NAME = 'youtube:playlist'
cdc628a4 5248 _TESTS = [{
8bdd16b4 5249 'note': 'issue #673',
5250 'url': 'PLBB231211A4F62143',
cdc628a4 5251 'info_dict': {
8bdd16b4 5252 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5253 'id': 'PLBB231211A4F62143',
976ae3ea 5254 'uploader': 'Wickman',
8bdd16b4 5255 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5256 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5257 'view_count': int,
5258 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5259 'modified_date': r're:\d{8}',
5260 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5261 'channel': 'Wickman',
5262 'tags': [],
5263 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5264 },
5265 'playlist_mincount': 29,
5266 }, {
5267 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5268 'info_dict': {
5269 'title': 'YDL_safe_search',
5270 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5271 },
5272 'playlist_count': 2,
5273 'skip': 'This playlist is private',
9558dcec 5274 }, {
8bdd16b4 5275 'note': 'embedded',
5276 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5277 'playlist_count': 4,
9558dcec 5278 'info_dict': {
8bdd16b4 5279 'title': 'JODA15',
5280 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5281 'uploader': 'milan',
5282 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5283 'description': '',
5284 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5285 'tags': [],
5286 'modified_date': '20140919',
5287 'view_count': int,
5288 'channel': 'milan',
5289 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5290 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5291 },
5292 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5293 }, {
8bdd16b4 5294 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5295 'playlist_mincount': 654,
8bdd16b4 5296 'info_dict': {
5297 'title': '2018 Chinese New Singles (11/6 updated)',
5298 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5299 'uploader': 'LBK',
5300 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5301 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5302 'channel': 'LBK',
5303 'view_count': int,
5304 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5305 'tags': [],
5306 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5307 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5308 'modified_date': r're:\d{8}',
5309 },
5310 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5311 }, {
29f7c58a 5312 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5313 'only_matching': True,
5314 }, {
5315 # music album playlist
5316 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5317 'only_matching': True,
5318 }]
5319
5320 @classmethod
5321 def suitable(cls, url):
201c1459 5322 if YoutubeTabIE.suitable(url):
5323 return False
49a57e70 5324 from ..utils import parse_qs
201c1459 5325 qs = parse_qs(url)
5326 if qs.get('v', [None])[0]:
5327 return False
5328 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5329
5330 def _real_extract(self, url):
5331 playlist_id = self._match_id(url)
46953e7e 5332 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5333 url = update_url_query(
5334 'https://www.youtube.com/playlist',
5335 parse_qs(url) or {'list': playlist_id})
5336 if is_music_url:
5337 url = smuggle_url(url, {'is_music_url': True})
5338 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5339
5340
5341class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5342 IE_DESC = 'youtu.be'
29f7c58a 5343 _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}
5344 _TESTS = [{
8bdd16b4 5345 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5346 'info_dict': {
5347 'id': 'yeWKywCrFtk',
5348 'ext': 'mp4',
5349 'title': 'Small Scale Baler and Braiding Rugs',
5350 'uploader': 'Backus-Page House Museum',
5351 'uploader_id': 'backuspagemuseum',
5352 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5353 'upload_date': '20161008',
5354 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5355 'categories': ['Nonprofits & Activism'],
5356 'tags': list,
5357 'like_count': int,
976ae3ea 5358 'age_limit': 0,
5359 'playable_in_embed': True,
5360 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5361 'channel': 'Backus-Page House Museum',
5362 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5363 'live_status': 'not_live',
5364 'view_count': int,
5365 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5366 'availability': 'public',
5367 'duration': 59,
8bdd16b4 5368 },
5369 'params': {
5370 'noplaylist': True,
5371 'skip_download': True,
5372 },
39e7107d 5373 }, {
8bdd16b4 5374 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5375 'only_matching': True,
cdc628a4
PH
5376 }]
5377
8bdd16b4 5378 def _real_extract(self, url):
5ad28e7f 5379 mobj = self._match_valid_url(url)
29f7c58a 5380 video_id = mobj.group('id')
5381 playlist_id = mobj.group('playlist_id')
8bdd16b4 5382 return self.url_result(
29f7c58a 5383 update_url_query('https://www.youtube.com/watch', {
5384 'v': video_id,
5385 'list': playlist_id,
5386 'feature': 'youtu.be',
5387 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5388
5389
b6ce9bb0 5390class YoutubeLivestreamEmbedIE(InfoExtractor):
5391 IE_DESC = 'YouTube livestream embeds'
5392 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5393 _TESTS = [{
5394 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5395 'only_matching': True,
5396 }]
5397
5398 def _real_extract(self, url):
5399 channel_id = self._match_id(url)
5400 return self.url_result(
5401 f'https://www.youtube.com/channel/{channel_id}/live',
5402 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5403
5404
8bdd16b4 5405class YoutubeYtUserIE(InfoExtractor):
96565c7e 5406 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5407 IE_NAME = 'youtube:user'
8bdd16b4 5408 _VALID_URL = r'ytuser:(?P<id>.+)'
5409 _TESTS = [{
5410 'url': 'ytuser:phihag',
5411 'only_matching': True,
5412 }]
5413
5414 def _real_extract(self, url):
5415 user_id = self._match_id(url)
5416 return self.url_result(
c586f9e8 5417 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5418 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5419
b05654f0 5420
3d3dddc9 5421class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5422 IE_NAME = 'youtube:favorites'
96565c7e 5423 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5424 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5425 _LOGIN_REQUIRED = True
5426 _TESTS = [{
5427 'url': ':ytfav',
5428 'only_matching': True,
5429 }, {
5430 'url': ':ytfavorites',
5431 'only_matching': True,
5432 }]
5433
5434 def _real_extract(self, url):
5435 return self.url_result(
5436 'https://www.youtube.com/playlist?list=LL',
5437 ie=YoutubeTabIE.ie_key())
5438
5439
a6213a49 5440class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5441 IE_DESC = 'YouTube search'
78caa52a 5442 IE_NAME = 'youtube:search'
b05654f0 5443 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5444 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5445 _TESTS = [{
5446 'url': 'ytsearch5:youtube-dl test video',
5447 'playlist_count': 5,
5448 'info_dict': {
5449 'id': 'youtube-dl test video',
5450 'title': 'youtube-dl test video',
5451 }
5452 }]
b05654f0 5453
a61fd4cf 5454
5f7cb91a 5455class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5456 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5457 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5458 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5459 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5460 _TESTS = [{
5461 'url': 'ytsearchdate5:youtube-dl test video',
5462 'playlist_count': 5,
5463 'info_dict': {
5464 'id': 'youtube-dl test video',
5465 'title': 'youtube-dl test video',
5466 }
5467 }]
75dff0ee 5468
c9ae7b95 5469
a6213a49 5470class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5471 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5472 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5473 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5474 _TESTS = [{
5475 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5476 'playlist_mincount': 5,
5477 'info_dict': {
11f9be09 5478 'id': 'youtube-dl test video',
3462ffa8 5479 'title': 'youtube-dl test video',
5480 }
a61fd4cf 5481 }, {
5482 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5483 'playlist_mincount': 5,
5484 'info_dict': {
5485 'id': 'python',
5486 'title': 'python',
5487 }
5488
3462ffa8 5489 }, {
5490 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5491 'only_matching': True,
5492 }]
5493
5494 def _real_extract(self, url):
4dfbf869 5495 qs = parse_qs(url)
386e1dd9 5496 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5497 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5498
5499
16aa9ea4 5500class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5501 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5502 IE_NAME = 'youtube:music:search_url'
5503 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5504 _TESTS = [{
5505 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5506 'playlist_count': 16,
5507 'info_dict': {
5508 'id': 'royalty free music',
5509 'title': 'royalty free music',
5510 }
5511 }, {
5512 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5513 'playlist_mincount': 30,
5514 'info_dict': {
5515 'id': 'royalty free music - songs',
5516 'title': 'royalty free music - songs',
5517 },
5518 'params': {'extract_flat': 'in_playlist'}
5519 }, {
5520 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5521 'playlist_mincount': 30,
5522 'info_dict': {
5523 'id': 'royalty free music - community playlists',
5524 'title': 'royalty free music - community playlists',
5525 },
5526 'params': {'extract_flat': 'in_playlist'}
5527 }]
5528
5529 _SECTIONS = {
5530 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5531 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5532 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5533 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5534 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5535 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5536 }
5537
5538 def _real_extract(self, url):
5539 qs = parse_qs(url)
5540 query = (qs.get('search_query') or qs.get('q'))[0]
5541 params = qs.get('sp', (None,))[0]
5542 if params:
5543 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5544 else:
5545 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5546 params = self._SECTIONS.get(section)
5547 if not params:
5548 section = None
5549 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5550 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5551
5552
182bda88 5553class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5554 """
25f14e9f 5555 Base class for feed extractors
3d3dddc9 5556 Subclasses must define the _FEED_NAME property.
d7ae0639 5557 """
b2e8bc1b 5558 _LOGIN_REQUIRED = True
ef2f3c7f 5559 _TESTS = []
d7ae0639
JMF
5560
5561 @property
5562 def IE_NAME(self):
78caa52a 5563 return 'youtube:%s' % self._FEED_NAME
04cc9617 5564
3853309f 5565 def _real_extract(self, url):
3d3dddc9 5566 return self.url_result(
182bda88 5567 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5568
5569
ef2f3c7f 5570class YoutubeWatchLaterIE(InfoExtractor):
5571 IE_NAME = 'youtube:watchlater'
96565c7e 5572 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5573 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5574 _TESTS = [{
8bdd16b4 5575 'url': ':ytwatchlater',
bc7a9cd8
S
5576 'only_matching': True,
5577 }]
25f14e9f
S
5578
5579 def _real_extract(self, url):
ef2f3c7f 5580 return self.url_result(
5581 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5582
5583
25f14e9f 5584class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5585 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5586 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5587 _FEED_NAME = 'recommended'
45db527f 5588 _LOGIN_REQUIRED = False
3d3dddc9 5589 _TESTS = [{
5590 'url': ':ytrec',
5591 'only_matching': True,
5592 }, {
5593 'url': ':ytrecommended',
5594 'only_matching': True,
5595 }, {
5596 'url': 'https://youtube.com',
5597 'only_matching': True,
5598 }]
1ed5b5c9 5599
1ed5b5c9 5600
25f14e9f 5601class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5602 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5603 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5604 _FEED_NAME = 'subscriptions'
3d3dddc9 5605 _TESTS = [{
5606 'url': ':ytsubs',
5607 'only_matching': True,
5608 }, {
5609 'url': ':ytsubscriptions',
5610 'only_matching': True,
5611 }]
1ed5b5c9 5612
1ed5b5c9 5613
25f14e9f 5614class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5615 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5616 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5617 _FEED_NAME = 'history'
3d3dddc9 5618 _TESTS = [{
5619 'url': ':ythistory',
5620 'only_matching': True,
5621 }]
1ed5b5c9
JMF
5622
5623
15870e90
PH
5624class YoutubeTruncatedURLIE(InfoExtractor):
5625 IE_NAME = 'youtube:truncated_url'
5626 IE_DESC = False # Do not list
975d35db 5627 _VALID_URL = r'''(?x)
b95aab84
PH
5628 (?:https?://)?
5629 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5630 (?:watch\?(?:
c4808c60 5631 feature=[a-z_]+|
b95aab84
PH
5632 annotation_id=annotation_[^&]+|
5633 x-yt-cl=[0-9]+|
c1708b89 5634 hl=[^&]*|
287be8c6 5635 t=[0-9]+
b95aab84
PH
5636 )?
5637 |
5638 attribution_link\?a=[^&]+
5639 )
5640 $
975d35db 5641 '''
15870e90 5642
c4808c60 5643 _TESTS = [{
2d3d2997 5644 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5645 'only_matching': True,
dc2fc736 5646 }, {
2d3d2997 5647 'url': 'https://www.youtube.com/watch?',
dc2fc736 5648 'only_matching': True,
b95aab84
PH
5649 }, {
5650 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5651 'only_matching': True,
5652 }, {
5653 'url': 'https://www.youtube.com/watch?feature=foo',
5654 'only_matching': True,
c1708b89
PH
5655 }, {
5656 'url': 'https://www.youtube.com/watch?hl=en-GB',
5657 'only_matching': True,
287be8c6
PH
5658 }, {
5659 'url': 'https://www.youtube.com/watch?t=2372',
5660 'only_matching': True,
c4808c60
PH
5661 }]
5662
15870e90
PH
5663 def _real_extract(self, url):
5664 raise ExtractorError(
78caa52a
PH
5665 'Did you forget to quote the URL? Remember that & is a meta '
5666 'character in most shells, so you want to put the URL in quotes, '
3867038a 5667 'like youtube-dl '
2d3d2997 5668 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5669 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5670 expected=True)
772fd5cc
PH
5671
5672
3cd786db 5673class YoutubeClipIE(InfoExtractor):
5674 IE_NAME = 'youtube:clip'
5675 IE_DESC = False # Do not list
5676 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5677
5678 def _real_extract(self, url):
5679 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5680 return self.url_result(url, 'Generic')
5681
5682
772fd5cc
PH
5683class YoutubeTruncatedIDIE(InfoExtractor):
5684 IE_NAME = 'youtube:truncated_id'
5685 IE_DESC = False # Do not list
b95aab84 5686 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5687
5688 _TESTS = [{
5689 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5690 'only_matching': True,
5691 }]
5692
5693 def _real_extract(self, url):
5694 video_id = self._match_id(url)
5695 raise ExtractorError(
5696 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5697 expected=True)