]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[FormatSort] Fix `aext` for `--prefer-free-formats`
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
14f25df2 16import urllib.error
ac668111 17import urllib.parse
c5e8d7af 18
b05654f0 19from .common import InfoExtractor, SearchInfoExtractor
25836db6 20from .openload import PhantomJSwrapper
14f25df2 21from ..compat import functools
545cc85d 22from ..jsinterp import JSInterpreter
4bb4a188 23from ..utils import (
f8271158 24 NO_DEFAULT,
25 ExtractorError,
693f0600 26 UserNotLive,
720c3099 27 bug_reports_message,
82d02080 28 classproperty,
c5e8d7af 29 clean_html,
d92f5d5a 30 datetime_from_str,
11f9be09 31 dict_get,
2d30521a 32 float_or_none,
11f9be09 33 format_field,
ff91cf74 34 get_first,
dd27fd17 35 int_or_none,
641ad5d8 36 is_html,
34921b43 37 join_nonempty,
48416bc4 38 js_to_json,
94278f72 39 mimetype2ext,
9c0d7f49 40 network_exceptions,
11f9be09 41 orderedSet,
6310acf5 42 parse_codecs,
49bd8c66 43 parse_count,
7c80519c 44 parse_duration,
7ea65411 45 parse_iso8601,
4dfbf869 46 parse_qs,
dca3ff4a 47 qualities,
3995d37d 48 remove_start,
cf7e015f 49 smuggle_url,
dbdaaa23 50 str_or_none,
c93d53f5 51 str_to_int,
f3aa3c3f 52 strftime_or_none,
7c365c21 53 traverse_obj,
556dbe7f 54 try_get,
c5e8d7af
PH
55 unescapeHTML,
56 unified_strdate,
f0d785d3 57 unified_timestamp,
cf7e015f 58 unsmuggle_url,
8bdd16b4 59 update_url_query,
21c340b8 60 url_or_none,
fe93e2c4 61 urljoin,
7c365c21 62 variadic,
c5e8d7af
PH
63)
64
962ffcf8 65# any clients starting with _ cannot be explicitly requested by the user
000c15a4 66INNERTUBE_CLIENTS = {
67 'web': {
68 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
69 'INNERTUBE_CONTEXT': {
70 'client': {
71 'clientName': 'WEB',
a0c830f4 72 'clientVersion': '2.20220801.00.00',
000c15a4 73 }
74 },
75 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
76 },
77 'web_embedded': {
78 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
79 'INNERTUBE_CONTEXT': {
80 'client': {
81 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 82 'clientVersion': '1.20220731.00.00',
000c15a4 83 },
84 },
85 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
86 },
87 'web_music': {
88 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
89 'INNERTUBE_HOST': 'music.youtube.com',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_REMIX',
a0c830f4 93 'clientVersion': '1.20220727.01.00',
000c15a4 94 }
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
97 },
e7e94f2a 98 'web_creator': {
18c7683d 99 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
100 'INNERTUBE_CONTEXT': {
101 'client': {
102 'clientName': 'WEB_CREATOR',
a0c830f4 103 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
104 }
105 },
106 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
107 },
000c15a4 108 'android': {
18c7683d 109 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 110 'INNERTUBE_CONTEXT': {
111 'client': {
112 'clientName': 'ANDROID',
50ac0e54 113 'clientVersion': '17.31.35',
114 'androidSdkVersion': 30,
115 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 116 }
117 },
118 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 119 'REQUIRE_JS_PLAYER': False
000c15a4 120 },
121 'android_embedded': {
18c7683d 122 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 123 'INNERTUBE_CONTEXT': {
124 'client': {
125 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 126 'clientVersion': '17.31.35',
127 'androidSdkVersion': 30,
128 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 129 },
130 },
b6de707d 131 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
132 'REQUIRE_JS_PLAYER': False
000c15a4 133 },
134 'android_music': {
18c7683d 135 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 136 'INNERTUBE_CONTEXT': {
137 'client': {
138 'clientName': 'ANDROID_MUSIC',
a0c830f4 139 'clientVersion': '5.16.51',
50ac0e54 140 'androidSdkVersion': 30,
141 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 142 }
143 },
144 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 145 'REQUIRE_JS_PLAYER': False
000c15a4 146 },
e7e94f2a 147 'android_creator': {
18c7683d 148 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
149 'INNERTUBE_CONTEXT': {
150 'client': {
151 'clientName': 'ANDROID_CREATOR',
50ac0e54 152 'clientVersion': '22.30.100',
153 'androidSdkVersion': 30,
154 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
155 },
156 },
b6de707d 157 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
158 'REQUIRE_JS_PLAYER': False
e7e94f2a 159 },
18c7683d 160 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
161 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 162 'ios': {
18c7683d 163 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 164 'INNERTUBE_CONTEXT': {
165 'client': {
166 'clientName': 'IOS',
224b5a35 167 'clientVersion': '17.33.2',
18c7683d 168 'deviceModel': 'iPhone14,3',
224b5a35 169 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 170 }
171 },
b6de707d 172 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
173 'REQUIRE_JS_PLAYER': False
000c15a4 174 },
175 'ios_embedded': {
000c15a4 176 'INNERTUBE_CONTEXT': {
177 'client': {
178 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 179 'clientVersion': '17.33.2',
18c7683d 180 'deviceModel': 'iPhone14,3',
224b5a35 181 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 182 },
183 },
b6de707d 184 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
185 'REQUIRE_JS_PLAYER': False
000c15a4 186 },
187 'ios_music': {
18c7683d 188 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 189 'INNERTUBE_CONTEXT': {
190 'client': {
191 'clientName': 'IOS_MUSIC',
224b5a35
SF
192 'clientVersion': '5.21',
193 'deviceModel': 'iPhone14,3',
194 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 195 },
196 },
b6de707d 197 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
198 'REQUIRE_JS_PLAYER': False
000c15a4 199 },
e7e94f2a
D
200 'ios_creator': {
201 'INNERTUBE_CONTEXT': {
202 'client': {
203 'clientName': 'IOS_CREATOR',
224b5a35
SF
204 'clientVersion': '22.33.101',
205 'deviceModel': 'iPhone14,3',
206 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
207 },
208 },
b6de707d 209 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
210 'REQUIRE_JS_PLAYER': False
e7e94f2a 211 },
3619f78d 212 # mweb has 'ultralow' formats
213 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 214 'mweb': {
18c7683d 215 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 216 'INNERTUBE_CONTEXT': {
217 'client': {
218 'clientName': 'MWEB',
a0c830f4 219 'clientVersion': '2.20220801.00.00',
000c15a4 220 }
221 },
222 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
223 },
224 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
225 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
226 'tv_embedded': {
227 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
228 'INNERTUBE_CONTEXT': {
229 'client': {
230 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
231 'clientVersion': '2.0',
232 },
233 },
234 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
235 },
000c15a4 236}
237
238
e7870111
D
239def _split_innertube_client(client_name):
240 variant, *base = client_name.rsplit('.', 1)
241 if base:
242 return variant, base[0], variant
243 base, *variant = client_name.split('_', 1)
244 return client_name, base, variant[0] if variant else None
245
246
000c15a4 247def build_innertube_clients():
2e4cacd0 248 THIRD_PARTY = {
e7870111 249 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 250 }
e7870111 251 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 252 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 253
254 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 255 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 256 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 257 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 258 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 259
e7870111 260 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 261 ytcfg['priority'] = 10 * priority(base_client)
262
e48b3875 263 if not variant:
e7870111
D
264 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
265 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
266 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
267 embedscreen['priority'] -= 3
268 elif variant == 'embedded':
e48b3875 269 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 270 ytcfg['priority'] -= 2
e48b3875 271 else:
000c15a4 272 ytcfg['priority'] -= 3
273
274
275build_innertube_clients()
276
277
de7f3446 278class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 279 """Provide base functions for Youtube extractors"""
e00eb564 280
3462ffa8 281 _RESERVED_NAMES = (
3cd786db 282 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 283 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 284 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 285 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 286
3619f78d 287 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
288
52efa4b3 289 # _NETRC_MACHINE = 'youtube'
3619f78d 290
b2e8bc1b
JMF
291 # If True it will raise an error if no login info is provided
292 _LOGIN_REQUIRED = False
293
d9190e44
RH
294 _INVIDIOUS_SITES = (
295 # invidious-redirect websites
296 r'(?:www\.)?redirect\.invidious\.io',
297 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 298 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
299 r'(?:www\.)?invidious\.pussthecat\.org',
300 r'(?:www\.)?invidious\.zee\.li',
301 r'(?:www\.)?invidious\.ethibox\.fr',
302 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
303 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
304 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
305 # youtube-dl invidious instances list
306 r'(?:(?:www|no)\.)?invidiou\.sh',
307 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
308 r'(?:www\.)?invidious\.kabi\.tk',
309 r'(?:www\.)?invidious\.mastodon\.host',
310 r'(?:www\.)?invidious\.zapashcanon\.fr',
311 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
312 r'(?:www\.)?invidious\.tinfoil-hat\.net',
313 r'(?:www\.)?invidious\.himiko\.cloud',
314 r'(?:www\.)?invidious\.reallyancient\.tech',
315 r'(?:www\.)?invidious\.tube',
316 r'(?:www\.)?invidiou\.site',
317 r'(?:www\.)?invidious\.site',
318 r'(?:www\.)?invidious\.xyz',
319 r'(?:www\.)?invidious\.nixnet\.xyz',
320 r'(?:www\.)?invidious\.048596\.xyz',
321 r'(?:www\.)?invidious\.drycat\.fr',
322 r'(?:www\.)?inv\.skyn3t\.in',
323 r'(?:www\.)?tube\.poal\.co',
324 r'(?:www\.)?tube\.connect\.cafe',
325 r'(?:www\.)?vid\.wxzm\.sx',
326 r'(?:www\.)?vid\.mint\.lgbt',
327 r'(?:www\.)?vid\.puffyan\.us',
328 r'(?:www\.)?yewtu\.be',
329 r'(?:www\.)?yt\.elukerio\.org',
330 r'(?:www\.)?yt\.lelux\.fi',
331 r'(?:www\.)?invidious\.ggc-project\.de',
332 r'(?:www\.)?yt\.maisputain\.ovh',
333 r'(?:www\.)?ytprivate\.com',
334 r'(?:www\.)?invidious\.13ad\.de',
335 r'(?:www\.)?invidious\.toot\.koeln',
336 r'(?:www\.)?invidious\.fdn\.fr',
337 r'(?:www\.)?watch\.nettohikari\.com',
338 r'(?:www\.)?invidious\.namazso\.eu',
339 r'(?:www\.)?invidious\.silkky\.cloud',
340 r'(?:www\.)?invidious\.exonip\.de',
341 r'(?:www\.)?invidious\.riverside\.rocks',
342 r'(?:www\.)?invidious\.blamefran\.net',
343 r'(?:www\.)?invidious\.moomoo\.de',
344 r'(?:www\.)?ytb\.trom\.tf',
345 r'(?:www\.)?yt\.cyberhost\.uk',
346 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
347 r'(?:www\.)?qklhadlycap4cnod\.onion',
348 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
349 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
350 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
351 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
352 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
353 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
354 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
355 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
356 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
357 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
358 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
359 r'(?:www\.)?piped\.kavin\.rocks',
360 r'(?:www\.)?piped\.silkky\.cloud',
361 r'(?:www\.)?piped\.tokhmi\.xyz',
362 r'(?:www\.)?piped\.moomoo\.me',
363 r'(?:www\.)?il\.ax',
364 r'(?:www\.)?piped\.syncpundit\.com',
365 r'(?:www\.)?piped\.mha\.fi',
366 r'(?:www\.)?piped\.mint\.lgbt',
367 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
368 )
369
cce889b9 370 def _initialize_consent(self):
371 cookies = self._get_cookies('https://www.youtube.com/')
372 if cookies.get('__Secure-3PSID'):
373 return
374 consent_id = None
375 consent = cookies.get('CONSENT')
376 if consent:
377 if 'YES' in consent.value:
378 return
379 consent_id = self._search_regex(
380 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
381 if not consent_id:
382 consent_id = random.randint(100, 999)
383 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 384
f3aa3c3f 385 def _initialize_pref(self):
386 cookies = self._get_cookies('https://www.youtube.com/')
387 pref_cookie = cookies.get('PREF')
388 pref = {}
389 if pref_cookie:
390 try:
14f25df2 391 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 392 except ValueError:
393 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 394 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 395 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 396
b2e8bc1b 397 def _real_initialize(self):
f3aa3c3f 398 self._initialize_pref()
cce889b9 399 self._initialize_consent()
a25bca9f 400 self._check_login_required()
401
402 def _check_login_required(self):
24146491 403 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 404 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 405
b7c47b74 406 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
407 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 408
000c15a4 409 def _get_default_ytcfg(self, client='web'):
410 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 411
000c15a4 412 def _get_innertube_host(self, client='web'):
413 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 414
000c15a4 415 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 416 # try_get but with fallback to default ytcfg client values when present
417 _func = lambda y: try_get(y, getter, expected_type)
418 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
419
000c15a4 420 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 421 return self._ytcfg_get_safe(
422 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 423 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 424
000c15a4 425 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 426 return self._ytcfg_get_safe(
427 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 428 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 429
2ae778b8 430 def _select_api_hostname(self, req_api_hostname, default_client=None):
431 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
432 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
433
000c15a4 434 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 435 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 436
000c15a4 437 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 438 context = get_first(
439 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 440 # Enforce language and tz for extraction
441 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
442 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 443 return context
444
cf87314d 445 _SAPISID = None
446
109dd3b2 447 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 448 time_now = round(time.time())
cf87314d 449 if self._SAPISID is None:
450 yt_cookies = self._get_cookies('https://www.youtube.com')
451 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
452 # See: https://github.com/yt-dlp/yt-dlp/issues/393
453 sapisid_cookie = dict_get(
454 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
455 if sapisid_cookie and sapisid_cookie.value:
456 self._SAPISID = sapisid_cookie.value
457 self.write_debug('Extracted SAPISID cookie')
458 # SAPISID cookie is required if not already present
459 if not yt_cookies.get('SAPISID'):
460 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
461 self._set_cookie(
462 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
463 else:
464 self._SAPISID = False
465 if not self._SAPISID:
466 return None
1974e99f 467 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
468 sapisidhash = hashlib.sha1(
86e5f3ed 469 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 470 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
471
472 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 473 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 474 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 475
109dd3b2 476 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 477 data.update(query)
11f9be09 478 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 479 real_headers.update({'content-type': 'application/json'})
480 if headers:
481 real_headers.update(headers)
2ae778b8 482 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
483 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 484 return self._download_json(
2ae778b8 485 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 486 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 487 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 488 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 489
65141660 490 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
491 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 492
99e9e001 493 @staticmethod
494 def _extract_session_index(*data):
495 """
496 Index of current account in account list.
497 See: https://github.com/yt-dlp/yt-dlp/pull/519
498 """
499 for ytcfg in data:
500 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
501 if session_index is not None:
502 return session_index
503
504 # Deprecated?
505 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 506 if ytcfg:
14f25df2 507 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
508 if token:
509 return token
99e9e001 510 if webpage:
511 return self._search_regex(
512 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
513 'identity token', default=None, fatal=False)
a1c5d2ca
M
514
515 @staticmethod
fe93e2c4 516 def _extract_account_syncid(*args):
8ea3f7b9 517 """
518 Extract syncId required to download private playlists of secondary channels
fe93e2c4 519 @params response and/or ytcfg
8ea3f7b9 520 """
fe93e2c4 521 for data in args:
522 # ytcfg includes channel_syncid if on secondary channel
14f25df2 523 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 524 if delegated_sid:
525 return delegated_sid
526 sync_ids = (try_get(
527 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 528 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 529 if len(sync_ids) >= 2 and sync_ids[1]:
530 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
531 # and just "user_syncid||" for primary channel. We only want the channel_syncid
532 return sync_ids[0]
a1c5d2ca 533
ac56cf38 534 @staticmethod
535 def _extract_visitor_data(*args):
536 """
537 Extracts visitorData from an API response or ytcfg
538 Appears to be used to track session state
539 """
9222c381 540 return get_first(
6c73052c 541 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 542 expected_type=str)
ac56cf38 543
2762dbb1 544 @functools.cached_property
99e9e001 545 def is_authenticated(self):
546 return bool(self._generate_sapisidhash_header())
547
11f9be09 548 def extract_ytcfg(self, video_id, webpage):
8c54a305 549 if not webpage:
550 return {}
29f7c58a 551 return self._parse_json(
552 self._search_regex(
553 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 554 default='{}'), video_id, fatal=False) or {}
555
11f9be09 556 def generate_api_headers(
99e9e001 557 self, *, ytcfg=None, account_syncid=None, session_index=None,
558 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
559
2ae778b8 560 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 561 headers = {
14f25df2 562 'X-YouTube-Client-Name': str(
11f9be09 563 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
564 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 565 'Origin': origin,
566 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
567 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 568 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
569 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 570 }
571 if session_index is None:
314ee305 572 session_index = self._extract_session_index(ytcfg)
573 if account_syncid or session_index is not None:
574 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 575
109dd3b2 576 auth = self._generate_sapisidhash_header(origin)
f4f751af 577 if auth is not None:
578 headers['Authorization'] = auth
109dd3b2 579 headers['X-Origin'] = origin
99e9e001 580 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 581
a25bca9f 582 def _download_ytcfg(self, client, video_id):
583 url = {
584 'web': 'https://www.youtube.com',
585 'web_music': 'https://music.youtube.com',
586 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
587 }.get(client)
588 if not url:
589 return {}
590 webpage = self._download_webpage(
591 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
592 return self.extract_ytcfg(video_id, webpage) or {}
593
2d6659b9 594 @staticmethod
595 def _build_api_continuation_query(continuation, ctp=None):
596 query = {
597 'continuation': continuation
598 }
599 # TODO: Inconsistency with clickTrackingParams.
600 # Currently we have a fixed ctp contained within context (from ytcfg)
601 # and a ctp in root query for continuation.
602 if ctp:
603 query['clickTracking'] = {'clickTrackingParams': ctp}
604 return query
605
2d6659b9 606 @classmethod
607 def _extract_next_continuation_data(cls, renderer):
608 next_continuation = try_get(
609 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
610 lambda x: x['continuation']['reloadContinuationData']), dict)
611 if not next_continuation:
612 return
613 continuation = next_continuation.get('continuation')
614 if not continuation:
615 return
616 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 617 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 618
619 @classmethod
620 def _extract_continuation_ep_data(cls, continuation_ep: dict):
621 if isinstance(continuation_ep, dict):
622 continuation = try_get(
14f25df2 623 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 624 if not continuation:
625 return
626 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 627 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 628
629 @classmethod
630 def _extract_continuation(cls, renderer):
631 next_continuation = cls._extract_next_continuation_data(renderer)
632 if next_continuation:
633 return next_continuation
fe93e2c4 634
2d6659b9 635 contents = []
636 for key in ('contents', 'items'):
637 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 638
2d6659b9 639 for content in contents:
640 if not isinstance(content, dict):
641 continue
642 continuation_ep = try_get(
643 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
644 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
645 dict)
646 continuation = cls._extract_continuation_ep_data(continuation_ep)
647 if continuation:
648 return continuation
649
fe93e2c4 650 @classmethod
651 def _extract_alerts(cls, data):
109dd3b2 652 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
653 if not isinstance(alert_dict, dict):
654 continue
655 for alert in alert_dict.values():
656 alert_type = alert.get('type')
657 if not alert_type:
658 continue
052e1350 659 message = cls._get_text(alert, 'text')
109dd3b2 660 if message:
661 yield alert_type, message
662
c0ac49bc 663 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 664 errors = []
665 warnings = []
666 for alert_type, alert_message in alerts:
641ad5d8 667 if alert_type.lower() == 'error' and fatal:
109dd3b2 668 errors.append([alert_type, alert_message])
669 else:
670 warnings.append([alert_type, alert_message])
671
672 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 673 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 674 if errors:
675 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
676
677 def _extract_and_report_alerts(self, data, *args, **kwargs):
678 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
679
47193e02 680 def _extract_badges(self, renderer: dict):
681 badges = set()
682 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 683 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 684 if label:
685 badges.add(label.lower())
686 return badges
687
688 @staticmethod
052e1350 689 def _get_text(data, *path_list, max_runs=None):
690 for path in path_list or [None]:
691 if path is None:
692 obj = [data]
693 else:
694 obj = traverse_obj(data, path, default=[])
695 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
696 obj = [obj]
697 for item in obj:
14f25df2 698 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 699 if text:
700 return text
701 runs = try_get(item, lambda x: x['runs'], list) or []
702 if not runs and isinstance(item, list):
703 runs = item
704
705 runs = runs[:min(len(runs), max_runs or len(runs))]
706 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
707 if text:
708 return text
47193e02 709
f0d785d3 710 def _get_count(self, data, *path_list):
711 count_text = self._get_text(data, *path_list) or ''
712 count = parse_count(count_text)
713 if count is None:
714 count = str_to_int(
715 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
716 return count
717
a709d873 718 @staticmethod
719 def _extract_thumbnails(data, *path_list):
720 """
721 Extract thumbnails from thumbnails dict
722 @param path_list: path list to level that contains 'thumbnails' key
723 """
724 thumbnails = []
725 for path in path_list or [()]:
726 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
727 thumbnail_url = url_or_none(thumbnail.get('url'))
728 if not thumbnail_url:
729 continue
730 # Sometimes youtube gives a wrong thumbnail URL. See:
731 # https://github.com/yt-dlp/yt-dlp/issues/233
732 # https://github.com/ytdl-org/youtube-dl/issues/28023
733 if 'maxresdefault' in thumbnail_url:
734 thumbnail_url = thumbnail_url.split('?')[0]
735 thumbnails.append({
736 'url': thumbnail_url,
737 'height': int_or_none(thumbnail.get('height')),
738 'width': int_or_none(thumbnail.get('width')),
739 })
740 return thumbnails
741
f3aa3c3f 742 @staticmethod
743 def extract_relative_time(relative_time_text):
744 """
745 Extracts a relative time from string and converts to dt object
f0d785d3 746 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 747 """
f0d785d3 748 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 749 if mobj:
f0d785d3 750 start = mobj.group('start')
751 if start:
752 return datetime_from_str(start)
f3aa3c3f 753 try:
f0d785d3 754 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 755 except ValueError:
756 return None
757
758 def _extract_time_text(self, renderer, *path_list):
a25bca9f 759 """@returns (timestamp, time_text)"""
f3aa3c3f 760 text = self._get_text(renderer, *path_list) or ''
761 dt = self.extract_relative_time(text)
762 timestamp = None
763 if isinstance(dt, datetime.datetime):
764 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 765
766 if timestamp is None:
767 timestamp = (
768 unified_timestamp(text) or unified_timestamp(
769 self._search_regex(
17322130 770 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 771 text.lower(), 'time text', default=None)))
f0d785d3 772
f3aa3c3f 773 if text and timestamp is None:
17322130 774 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 775 return timestamp, text
776
109dd3b2 777 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
778 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 779 default_client='web'):
be5c1ae8 780 for retry in self.RetryManager():
109dd3b2 781 try:
782 response = self._call_api(
783 ep=ep, fatal=True, headers=headers,
be5c1ae8 784 video_id=item_id, query=query, note=note,
109dd3b2 785 context=self._extract_context(ytcfg, default_client),
786 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 787 api_hostname=api_hostname, default_client=default_client)
109dd3b2 788 except ExtractorError as e:
be5c1ae8 789 if not isinstance(e.cause, network_exceptions):
790 return self._error_or_warning(e, fatal=fatal)
791 elif not isinstance(e.cause, urllib.error.HTTPError):
792 retry.error = e
793 continue
109dd3b2 794
be5c1ae8 795 first_bytes = e.cause.read(512)
796 if not is_html(first_bytes):
797 yt_error = try_get(
798 self._parse_json(
799 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
800 lambda x: x['error']['message'], str)
801 if yt_error:
802 self._report_alerts([('ERROR', yt_error)], fatal=False)
803 # Downloading page may result in intermittent 5xx HTTP error
804 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
805 # We also want to catch all other network exceptions since errors in later pages can be troublesome
806 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
807 if e.cause.code not in (403, 429):
808 retry.error = e
809 continue
810 return self._error_or_warning(e, fatal=fatal)
811
812 try:
813 self._extract_and_report_alerts(response, only_once=True)
814 except ExtractorError as e:
815 # YouTube servers may return errors we want to retry on in a 200 OK response
816 # See: https://github.com/yt-dlp/yt-dlp/issues/839
817 if 'unknown error' in e.msg.lower():
818 retry.error = e
819 continue
820 return self._error_or_warning(e, fatal=fatal)
821 # Youtube sometimes sends incomplete data
822 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
823 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 824 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 825 continue
826
827 return response
109dd3b2 828
9297939e 829 @staticmethod
830 def is_music_url(url):
831 return re.match(r'https?://music\.youtube\.com/', url) is not None
832
30a074c2 833 def _extract_video(self, renderer):
834 video_id = renderer.get('videoId')
052e1350 835 title = self._get_text(renderer, 'title')
836 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 837 duration = parse_duration(self._get_text(
838 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 839 if duration is None:
840 duration = parse_duration(self._search_regex(
841 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
842 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
843 video_id, default=None, group='duration'))
844
f0d785d3 845 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 846
052e1350 847 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 848 channel_id = traverse_obj(
a44ca5a4 849 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
850 expected_type=str, get_all=False)
f3aa3c3f 851 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
852 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
853 overlay_style = traverse_obj(
a44ca5a4 854 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
855 get_all=False, expected_type=str)
f3aa3c3f 856 badges = self._extract_badges(renderer)
a709d873 857 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 858 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 859 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
860 expected_type=str)) or ''
fd2ad7cb 861 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 862 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 863 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 864
30a074c2 865 return {
39ed931e 866 '_type': 'url',
30a074c2 867 'ie_key': YoutubeIE.ie_key(),
868 'id': video_id,
fd2ad7cb 869 'url': url,
30a074c2 870 'title': title,
871 'description': description,
872 'duration': duration,
873 'view_count': view_count,
874 'uploader': uploader,
f3aa3c3f 875 'channel_id': channel_id,
a709d873 876 'thumbnails': thumbnails,
a44ca5a4 877 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
878 if self._configuration_arg('approximate_date', ie_key='youtubetab')
879 else None),
f3aa3c3f 880 'live_status': ('is_upcoming' if scheduled_timestamp is not None
881 else 'was_live' if 'streamed' in time_text.lower()
a831c2ea 882 else 'is_live' if overlay_style == 'LIVE' or 'live now' in badges
f3aa3c3f 883 else None),
884 'release_timestamp': scheduled_timestamp,
885 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 886 }
887
0c148415 888
360e1ca5 889class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 890 IE_DESC = 'YouTube'
cb7dfeea 891 _VALID_URL = r"""(?x)^
c5e8d7af 892 (
edb53e2d 893 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 894 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
895 (?:www\.)?deturl\.com/www\.youtube\.com|
896 (?:www\.)?pwnyoutube\.com|
897 (?:www\.)?hooktube\.com|
898 (?:www\.)?yourepeat\.com|
899 tube\.majestyc\.net|
900 %(invidious)s|
901 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
902 (?:.*?\#/)? # handle anchor (#/) redirect urls
903 (?: # the various things that can precede the ID:
b6ce9bb0 904 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 905 |(?: # or the v= param in all its forms
f7000f3a 906 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 907 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 908 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
909 v=
910 )
f4b05232 911 ))
cbaed4bb
S
912 |(?:
913 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
914 vid\.plus| # or vid.plus/xxxx
915 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 916 %(invidious)s
cbaed4bb 917 )/
edb53e2d 918 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 919 )
c5e8d7af 920 )? # all until now is optional -> you can pass the naked ID
201c1459 921 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 922 (?(1).+)? # if we found the ID, everything can follow
9297939e 923 (?:\#|$)""" % {
d9190e44 924 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 925 }
bfd973ec 926 _EMBED_REGEX = [r'''(?x)
927 (?:
928 <iframe[^>]+?src=|
929 data-video-url=|
930 <embed[^>]+?src=|
931 embedSWF\(?:\s*|
932 <object[^>]+data=|
933 new\s+SWFObject\(
934 )
935 (["\'])
936 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
937 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
938 \1''']
e40c758c 939 _PLAYER_INFO_RE = (
cc2db878 940 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
941 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$',
545cc85d 942 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 943 )
2c62dc26 944 _formats = {
c2d3cb4c 945 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
946 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
947 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
948 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
949 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
950 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
951 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
952 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 953 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 954 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
955 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
956 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
957 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
958 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
959 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 960 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 961 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
962 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 963
964
965 # 3D videos
c2d3cb4c 966 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
967 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
968 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
969 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 970 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
971 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
972 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 973
96fb5605 974 # Apple HTTP Live Streaming
11f12195 975 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 976 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
977 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
978 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
979 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
980 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 981 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
982 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
983
984 # DASH mp4 video
d23028a8
S
985 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
989 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 990 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
991 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
992 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
993 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
994 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
995 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
996 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 997
f6f1fc92 998 # Dash mp4 audio
d23028a8
S
999 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1000 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1001 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1002 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1003 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1004 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1005 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1006
1007 # Dash webm
d23028a8
S
1008 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1009 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1010 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1011 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1012 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1013 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1014 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1015 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1019 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1020 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1023 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1024 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1025 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1026 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1027 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1028 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1029 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1030
1031 # Dash webm audio
d23028a8
S
1032 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1033 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1034
0857baad 1035 # Dash webm audio with opus inside
d23028a8
S
1036 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1037 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1038 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1039
ce6b9a2d
PH
1040 # RTMP (unnamed)
1041 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1042
1043 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1044 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1045 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1046 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1047 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1048 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1049 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1050 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1051 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1052 }
29f7c58a 1053 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1054
fd5c4aab
S
1055 _GEO_BYPASS = False
1056
78caa52a 1057 IE_NAME = 'youtube'
2eb88d95
PH
1058 _TESTS = [
1059 {
2d3d2997 1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1061 'info_dict': {
1062 'id': 'BaW_jenozKc',
1063 'ext': 'mp4',
3867038a 1064 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1065 'uploader': 'Philipp Hagemeister',
1066 'uploader_id': 'phihag',
ec85ded8 1067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1068 'channel': 'Philipp Hagemeister',
dd4c4492
S
1069 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1070 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1071 'upload_date': '20121002',
ff9f925b 1072 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1073 'categories': ['Science & Technology'],
3867038a 1074 'tags': ['youtube-dl'],
556dbe7f 1075 'duration': 10,
dbdaaa23 1076 'view_count': int,
3e7c1224 1077 'like_count': int,
ff9f925b 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,
7c80519c 1083 'start_time': 1,
297a564b 1084 'end_time': 9,
12a1b225 1085 'comment_count': int,
6c73052c 1086 'channel_follower_count': int
2eb88d95 1087 }
0e853ca4 1088 },
fccd3771 1089 {
4bc3a23e
PH
1090 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1091 'note': 'Embed-only video (#1746)',
1092 'info_dict': {
1093 'id': 'yZIXLfi8CZQ',
1094 'ext': 'mp4',
1095 'upload_date': '20120608',
1096 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1097 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1098 'uploader': 'SET India',
94bfcd23 1099 'uploader_id': 'setindia',
ec85ded8 1100 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1101 'age_limit': 18,
545cc85d 1102 },
1103 'skip': 'Private video',
fccd3771 1104 },
11b56058 1105 {
8bdd16b4 1106 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1107 'note': 'Use the first video ID in the URL',
1108 'info_dict': {
1109 'id': 'BaW_jenozKc',
1110 'ext': 'mp4',
3867038a 1111 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1112 'uploader': 'Philipp Hagemeister',
1113 'uploader_id': 'phihag',
ec85ded8 1114 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1115 'channel': 'Philipp Hagemeister',
1116 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1117 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1118 'upload_date': '20121002',
976ae3ea 1119 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1120 'categories': ['Science & Technology'],
3867038a 1121 'tags': ['youtube-dl'],
556dbe7f 1122 'duration': 10,
dbdaaa23 1123 'view_count': int,
11b56058 1124 'like_count': int,
976ae3ea 1125 'availability': 'public',
1126 'playable_in_embed': True,
1127 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1128 'live_status': 'not_live',
1129 'age_limit': 0,
12a1b225 1130 'comment_count': int,
6c73052c 1131 'channel_follower_count': int
34a7de29
S
1132 },
1133 'params': {
1134 'skip_download': True,
1135 },
11b56058 1136 },
dd27fd17 1137 {
2d3d2997 1138 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1139 'note': '256k DASH audio (format 141) via DASH manifest',
1140 'info_dict': {
1141 'id': 'a9LDPn-MO4I',
1142 'ext': 'm4a',
1143 'upload_date': '20121002',
1144 'uploader_id': '8KVIDEO',
ec85ded8 1145 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1146 'description': '',
1147 'uploader': '8KVIDEO',
1148 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1149 },
4bc3a23e
PH
1150 'params': {
1151 'youtube_include_dash_manifest': True,
1152 'format': '141',
4919603f 1153 },
de3c7fe0 1154 'skip': 'format 141 not served anymore',
dd27fd17 1155 },
8bdd16b4 1156 # DASH manifest with encrypted signature
1157 {
1158 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1159 'info_dict': {
1160 'id': 'IB3lcPjvWLA',
1161 'ext': 'm4a',
1162 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1163 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1164 'duration': 244,
1165 'uploader': 'AfrojackVEVO',
1166 'uploader_id': 'AfrojackVEVO',
1167 'upload_date': '20131011',
cc2db878 1168 'abr': 129.495,
976ae3ea 1169 'like_count': int,
1170 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1171 'playable_in_embed': True,
1172 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1173 'view_count': int,
1174 'track': 'The Spark',
1175 'live_status': 'not_live',
1176 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1177 'channel': 'Afrojack',
1178 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1179 'tags': 'count:19',
1180 'availability': 'public',
1181 'categories': ['Music'],
1182 'age_limit': 0,
1183 'alt_title': 'The Spark',
6c73052c 1184 'channel_follower_count': int
8bdd16b4 1185 },
1186 'params': {
1187 'youtube_include_dash_manifest': True,
1188 'format': '141/bestaudio[ext=m4a]',
1189 },
1190 },
65c2fde2 1191 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1192 {
65c2fde2 1193 'note': 'Embed allowed age-gate video',
2d3d2997 1194 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1195 'info_dict': {
1196 'id': 'HtVdAasjOgU',
1197 'ext': 'mp4',
1198 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1199 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1200 'duration': 142,
c522adb1
JMF
1201 'uploader': 'The Witcher',
1202 'uploader_id': 'WitcherGame',
ec85ded8 1203 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1204 'upload_date': '20140605',
34952f09 1205 'age_limit': 18,
976ae3ea 1206 'categories': ['Gaming'],
1207 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1208 'availability': 'needs_auth',
1209 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1210 'like_count': int,
1211 'channel': 'The Witcher',
1212 'live_status': 'not_live',
1213 'tags': 'count:17',
1214 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1215 'playable_in_embed': True,
1216 'view_count': int,
6c73052c 1217 'channel_follower_count': int
c522adb1
JMF
1218 },
1219 },
65c2fde2 1220 {
1221 'note': 'Age-gate video with embed allowed in public site',
1222 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1223 'info_dict': {
1224 'id': 'HsUATh_Nc2U',
1225 'ext': 'mp4',
1226 'title': 'Godzilla 2 (Official Video)',
1227 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1228 'upload_date': '20200408',
1229 'uploader_id': 'FlyingKitty900',
1230 'uploader': 'FlyingKitty',
1231 'age_limit': 18,
976ae3ea 1232 'availability': 'needs_auth',
1233 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1234 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1235 'channel': 'FlyingKitty',
1236 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1237 'view_count': int,
1238 'categories': ['Entertainment'],
1239 'live_status': 'not_live',
1240 'tags': ['Flyingkitty', 'godzilla 2'],
1241 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1242 'like_count': int,
1243 'duration': 177,
1244 'playable_in_embed': True,
6c73052c 1245 'channel_follower_count': int
65c2fde2 1246 },
1247 },
1248 {
1249 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1250 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1251 'info_dict': {
1252 'id': 'Tq92D6wQ1mg',
1253 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1254 'ext': 'mp4',
17322130 1255 'upload_date': '20191228',
65c2fde2 1256 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1257 'uploader': 'Projekt Melody',
1258 'description': 'md5:17eccca93a786d51bc67646756894066',
1259 'age_limit': 18,
976ae3ea 1260 'like_count': int,
1261 'availability': 'needs_auth',
1262 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1263 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1264 'view_count': int,
1265 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1266 'channel': 'Projekt Melody',
1267 'live_status': 'not_live',
1268 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1269 'playable_in_embed': True,
1270 'categories': ['Entertainment'],
1271 'duration': 106,
1272 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1273 'comment_count': int,
6c73052c 1274 'channel_follower_count': int
65c2fde2 1275 },
1276 },
1277 {
1278 'note': 'Non-Agegated non-embeddable video',
1279 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1280 'info_dict': {
1281 'id': 'MeJVWBSsPAY',
1282 'ext': 'mp4',
1283 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1284 'uploader': 'Herr Lurik',
1285 'uploader_id': 'st3in234',
1286 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1287 'upload_date': '20130730',
976ae3ea 1288 'track': 'Such mich find mich',
1289 'age_limit': 0,
1290 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1291 'like_count': int,
1292 'playable_in_embed': False,
1293 'creator': 'OOMPH!',
1294 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1295 'view_count': int,
1296 'alt_title': 'Such mich find mich',
1297 'duration': 210,
1298 'channel': 'Herr Lurik',
1299 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1300 'categories': ['Music'],
1301 'availability': 'public',
1302 'uploader_url': 'http://www.youtube.com/user/st3in234',
1303 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1304 'live_status': 'not_live',
1305 'artist': 'OOMPH!',
6c73052c 1306 'channel_follower_count': int
65c2fde2 1307 },
1308 },
1309 {
1310 'note': 'Non-bypassable age-gated video',
1311 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1312 'only_matching': True,
1313 },
8bdd16b4 1314 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1315 # YouTube Red ad is not captured for creator
1316 {
1317 'url': '__2ABJjxzNo',
1318 'info_dict': {
1319 'id': '__2ABJjxzNo',
1320 'ext': 'mp4',
1321 'duration': 266,
1322 'upload_date': '20100430',
1323 'uploader_id': 'deadmau5',
1324 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1325 'creator': 'deadmau5',
1326 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1327 'uploader': 'deadmau5',
1328 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1329 'alt_title': 'Some Chords',
976ae3ea 1330 'availability': 'public',
1331 'tags': 'count:14',
1332 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1333 'view_count': int,
1334 'live_status': 'not_live',
1335 'channel': 'deadmau5',
1336 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1337 'like_count': int,
1338 'track': 'Some Chords',
1339 'artist': 'deadmau5',
1340 'playable_in_embed': True,
1341 'age_limit': 0,
1342 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1343 'categories': ['Music'],
1344 'album': 'Some Chords',
6c73052c 1345 'channel_follower_count': int
8bdd16b4 1346 },
1347 'expected_warnings': [
1348 'DASH manifest missing',
1349 ]
1350 },
067aa17e 1351 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1352 {
1353 'url': 'lqQg6PlCWgI',
1354 'info_dict': {
1355 'id': 'lqQg6PlCWgI',
1356 'ext': 'mp4',
556dbe7f 1357 'duration': 6085,
90227264 1358 'upload_date': '20150827',
cbe2bd91 1359 'uploader_id': 'olympic',
ec85ded8 1360 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1361 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1362 'uploader': 'Olympics',
cbe2bd91 1363 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1364 'like_count': int,
1365 'release_timestamp': 1343767800,
1366 'playable_in_embed': True,
1367 'categories': ['Sports'],
1368 'release_date': '20120731',
1369 'channel': 'Olympics',
1370 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1371 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1372 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1373 'age_limit': 0,
1374 'availability': 'public',
1375 'live_status': 'was_live',
1376 'view_count': int,
1377 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1378 'channel_follower_count': int
cbe2bd91
PH
1379 },
1380 'params': {
1381 'skip_download': 'requires avconv',
e52a40ab 1382 }
cbe2bd91 1383 },
6271f1ca
PH
1384 # Non-square pixels
1385 {
1386 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1387 'info_dict': {
1388 'id': '_b-2C3KPAM0',
1389 'ext': 'mp4',
1390 'stretched_ratio': 16 / 9.,
556dbe7f 1391 'duration': 85,
6271f1ca
PH
1392 'upload_date': '20110310',
1393 'uploader_id': 'AllenMeow',
ec85ded8 1394 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1395 '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 1396 'uploader': '孫ᄋᄅ',
6271f1ca 1397 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1398 'playable_in_embed': True,
1399 'channel': '孫ᄋᄅ',
1400 'age_limit': 0,
1401 'tags': 'count:11',
1402 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1403 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1404 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1405 'view_count': int,
1406 'categories': ['People & Blogs'],
1407 'like_count': int,
1408 'live_status': 'not_live',
1409 'availability': 'unlisted',
12a1b225 1410 'comment_count': int,
6c73052c 1411 'channel_follower_count': int
6271f1ca 1412 },
06b491eb
S
1413 },
1414 # url_encoded_fmt_stream_map is empty string
1415 {
1416 'url': 'qEJwOuvDf7I',
1417 'info_dict': {
1418 'id': 'qEJwOuvDf7I',
f57b7835 1419 'ext': 'webm',
06b491eb
S
1420 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1421 'description': '',
1422 'upload_date': '20150404',
1423 'uploader_id': 'spbelect',
1424 'uploader': 'Наблюдатели Петербурга',
1425 },
1426 'params': {
1427 'skip_download': 'requires avconv',
e323cf3f
S
1428 },
1429 'skip': 'This live event has ended.',
06b491eb 1430 },
067aa17e 1431 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1432 {
1433 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1434 'info_dict': {
1435 'id': 'FIl7x6_3R5Y',
eb6793ba 1436 'ext': 'webm',
da77d856
S
1437 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1438 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1439 'duration': 220,
da77d856
S
1440 'upload_date': '20150625',
1441 'uploader_id': 'dorappi2000',
ec85ded8 1442 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1443 'uploader': 'dorappi2000',
eb6793ba 1444 'formats': 'mincount:31',
da77d856 1445 },
eb6793ba 1446 'skip': 'not actual anymore',
2ee8f5d8 1447 },
8a1a26ce
YCH
1448 # DASH manifest with segment_list
1449 {
1450 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1451 'md5': '8ce563a1d667b599d21064e982ab9e31',
1452 'info_dict': {
1453 'id': 'CsmdDsKjzN8',
1454 'ext': 'mp4',
17ee98e1 1455 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1456 'uploader': 'Airtek',
1457 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1458 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1459 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1460 },
1461 'params': {
1462 'youtube_include_dash_manifest': True,
1463 'format': '135', # bestvideo
be49068d
S
1464 },
1465 'skip': 'This live event has ended.',
2ee8f5d8 1466 },
cf7e015f
S
1467 {
1468 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1469 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1470 'info_dict': {
545cc85d 1471 'id': 'jvGDaLqkpTg',
1472 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1473 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1474 },
1475 'playlist': [{
1476 'info_dict': {
545cc85d 1477 'id': 'jvGDaLqkpTg',
cf7e015f 1478 'ext': 'mp4',
545cc85d 1479 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1480 'description': 'md5:e03b909557865076822aa169218d6a5d',
1481 'duration': 10643,
1482 'upload_date': '20161111',
1483 'uploader': 'Team PGP',
1484 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1485 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1486 },
1487 }, {
1488 'info_dict': {
545cc85d 1489 'id': '3AKt1R1aDnw',
cf7e015f 1490 'ext': 'mp4',
545cc85d 1491 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1492 'description': 'md5:e03b909557865076822aa169218d6a5d',
1493 'duration': 10991,
1494 'upload_date': '20161111',
1495 'uploader': 'Team PGP',
1496 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1498 },
1499 }, {
1500 'info_dict': {
545cc85d 1501 'id': 'RtAMM00gpVc',
cf7e015f 1502 'ext': 'mp4',
545cc85d 1503 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1504 'description': 'md5:e03b909557865076822aa169218d6a5d',
1505 'duration': 10995,
1506 'upload_date': '20161111',
1507 'uploader': 'Team PGP',
1508 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1510 },
1511 }, {
1512 'info_dict': {
545cc85d 1513 'id': '6N2fdlP3C5U',
cf7e015f 1514 'ext': 'mp4',
545cc85d 1515 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1516 'description': 'md5:e03b909557865076822aa169218d6a5d',
1517 'duration': 10990,
1518 'upload_date': '20161111',
1519 'uploader': 'Team PGP',
1520 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1521 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1522 },
1523 }],
1524 'params': {
1525 'skip_download': True,
1526 },
65c2fde2 1527 'skip': 'Not multifeed anymore',
cbaed4bb 1528 },
f9f49d87 1529 {
067aa17e 1530 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1531 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1532 'info_dict': {
1533 'id': 'gVfLd0zydlo',
1534 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1535 },
1536 'playlist_count': 2,
be49068d 1537 'skip': 'Not multifeed anymore',
f9f49d87 1538 },
cbaed4bb 1539 {
2d3d2997 1540 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1541 'only_matching': True,
0e49d9a6 1542 },
6d4fc66b 1543 {
2d3d2997 1544 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1545 'only_matching': True,
1546 },
0e49d9a6 1547 {
067aa17e 1548 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1549 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1550 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1551 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1552 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1553 'info_dict': {
1554 'id': 'lsguqyKfVQg',
1555 'ext': 'mp4',
1556 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1557 'alt_title': 'Dark Walk',
0e49d9a6 1558 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1559 'duration': 133,
0e49d9a6
LL
1560 'upload_date': '20151119',
1561 'uploader_id': 'IronSoulElf',
ec85ded8 1562 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1563 'uploader': 'IronSoulElf',
11f9be09 1564 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1565 'track': 'Dark Walk',
1566 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1567 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1568 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1569 'categories': ['Film & Animation'],
1570 'view_count': int,
1571 'live_status': 'not_live',
1572 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1573 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1574 'tags': 'count:13',
1575 'availability': 'public',
1576 'channel': 'IronSoulElf',
1577 'playable_in_embed': True,
1578 'like_count': int,
1579 'age_limit': 0,
6c73052c 1580 'channel_follower_count': int
0e49d9a6
LL
1581 },
1582 'params': {
1583 'skip_download': True,
1584 },
1585 },
61f92af1 1586 {
067aa17e 1587 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1588 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1589 'only_matching': True,
1590 },
313dfc45
LL
1591 {
1592 # Video with yt:stretch=17:0
1593 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1594 'info_dict': {
1595 'id': 'Q39EVAstoRM',
1596 'ext': 'mp4',
1597 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1598 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1599 'upload_date': '20151107',
1600 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1601 'uploader': 'CH GAMER DROID',
1602 },
1603 'params': {
1604 'skip_download': True,
1605 },
be49068d 1606 'skip': 'This video does not exist.',
313dfc45 1607 },
201c1459 1608 {
1609 # Video with incomplete 'yt:stretch=16:'
1610 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1611 'only_matching': True,
1612 },
7caf9830
S
1613 {
1614 # Video licensed under Creative Commons
1615 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1616 'info_dict': {
1617 'id': 'M4gD1WSo5mA',
1618 'ext': 'mp4',
1619 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1620 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1621 'duration': 721,
17322130 1622 'upload_date': '20150128',
7caf9830 1623 'uploader_id': 'BerkmanCenter',
ec85ded8 1624 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1625 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1626 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1627 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1628 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1629 'like_count': int,
1630 'age_limit': 0,
1631 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1632 'channel': 'The Berkman Klein Center for Internet & Society',
1633 'availability': 'public',
1634 'view_count': int,
1635 'categories': ['Education'],
1636 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1637 'live_status': 'not_live',
1638 'playable_in_embed': True,
12a1b225 1639 'comment_count': int,
6c73052c 1640 'channel_follower_count': int
7caf9830
S
1641 },
1642 'params': {
1643 'skip_download': True,
1644 },
1645 },
fd050249
S
1646 {
1647 # Channel-like uploader_url
1648 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1649 'info_dict': {
1650 'id': 'eQcmzGIKrzg',
1651 'ext': 'mp4',
1652 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1653 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1654 'duration': 4060,
17322130 1655 'upload_date': '20151120',
eb6793ba 1656 'uploader': 'Bernie Sanders',
fd050249 1657 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1658 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1659 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1660 'playable_in_embed': True,
1661 'tags': 'count:12',
1662 'like_count': int,
1663 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1664 'age_limit': 0,
1665 'availability': 'public',
1666 'categories': ['News & Politics'],
1667 'channel': 'Bernie Sanders',
1668 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1669 'view_count': int,
1670 'live_status': 'not_live',
1671 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1672 'comment_count': int,
6c73052c 1673 'channel_follower_count': int
fd050249
S
1674 },
1675 'params': {
1676 'skip_download': True,
1677 },
1678 },
040ac686
S
1679 {
1680 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1681 'only_matching': True,
7f29cf54
S
1682 },
1683 {
067aa17e 1684 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1685 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1686 'only_matching': True,
6496ccb4
S
1687 },
1688 {
1689 # Rental video preview
1690 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1691 'info_dict': {
1692 'id': 'uGpuVWrhIzE',
1693 'ext': 'mp4',
1694 'title': 'Piku - Trailer',
1695 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1696 'upload_date': '20150811',
1697 'uploader': 'FlixMatrix',
1698 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1699 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1700 'license': 'Standard YouTube License',
1701 },
1702 'params': {
1703 'skip_download': True,
1704 },
eb6793ba 1705 'skip': 'This video is not available.',
022a5d66 1706 },
12afdc2a
S
1707 {
1708 # YouTube Red video with episode data
1709 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1710 'info_dict': {
1711 'id': 'iqKdEhx-dD4',
1712 'ext': 'mp4',
1713 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1714 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1715 'duration': 2085,
12afdc2a
S
1716 'upload_date': '20170118',
1717 'uploader': 'Vsauce',
1718 'uploader_id': 'Vsauce',
1719 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1720 'series': 'Mind Field',
1721 'season_number': 1,
1722 'episode_number': 1,
976ae3ea 1723 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1724 'tags': 'count:12',
1725 'view_count': int,
1726 'availability': 'public',
1727 'age_limit': 0,
1728 'channel': 'Vsauce',
1729 'episode': 'Episode 1',
1730 'categories': ['Entertainment'],
1731 'season': 'Season 1',
1732 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1733 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1734 'like_count': int,
1735 'playable_in_embed': True,
1736 'live_status': 'not_live',
6c73052c 1737 'channel_follower_count': int
12afdc2a
S
1738 },
1739 'params': {
1740 'skip_download': True,
1741 },
1742 'expected_warnings': [
1743 'Skipping DASH manifest',
1744 ],
1745 },
c7121fa7
S
1746 {
1747 # The following content has been identified by the YouTube community
1748 # as inappropriate or offensive to some audiences.
1749 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1750 'info_dict': {
1751 'id': '6SJNVb0GnPI',
1752 'ext': 'mp4',
1753 'title': 'Race Differences in Intelligence',
1754 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1755 'duration': 965,
1756 'upload_date': '20140124',
1757 'uploader': 'New Century Foundation',
1758 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1760 },
1761 'params': {
1762 'skip_download': True,
1763 },
545cc85d 1764 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1765 },
022a5d66
S
1766 {
1767 # itag 212
1768 'url': '1t24XAntNCY',
1769 'only_matching': True,
fd5c4aab
S
1770 },
1771 {
1772 # geo restricted to JP
1773 'url': 'sJL6WA-aGkQ',
1774 'only_matching': True,
1775 },
cd5a74a2
S
1776 {
1777 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1778 'only_matching': True,
1779 },
bc2ca1bb 1780 {
1781 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1782 'only_matching': True,
1783 },
1784 {
1785 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1786 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1787 'only_matching': True,
1788 },
825cd268
RA
1789 {
1790 # DRM protected
1791 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1792 'only_matching': True,
4fe54c12
S
1793 },
1794 {
1795 # Video with unsupported adaptive stream type formats
1796 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1797 'info_dict': {
1798 'id': 'Z4Vy8R84T1U',
1799 'ext': 'mp4',
1800 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1801 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1802 'duration': 433,
1803 'upload_date': '20130923',
1804 'uploader': 'Amelia Putri Harwita',
1805 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1806 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1807 'formats': 'maxcount:10',
1808 },
1809 'params': {
1810 'skip_download': True,
1811 'youtube_include_dash_manifest': False,
1812 },
5429d6a9 1813 'skip': 'not actual anymore',
5caabd3c 1814 },
1815 {
822b9d9c 1816 # Youtube Music Auto-generated description
5caabd3c 1817 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1818 'info_dict': {
1819 'id': 'MgNrAu2pzNs',
1820 'ext': 'mp4',
1821 'title': 'Voyeur Girl',
1822 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1823 'upload_date': '20190312',
5429d6a9
S
1824 'uploader': 'Stephen - Topic',
1825 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1826 'artist': 'Stephen',
1827 'track': 'Voyeur Girl',
1828 'album': 'it\'s too much love to know my dear',
1829 'release_date': '20190313',
1830 'release_year': 2019,
976ae3ea 1831 'alt_title': 'Voyeur Girl',
1832 'view_count': int,
1833 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1834 'playable_in_embed': True,
1835 'like_count': int,
1836 'categories': ['Music'],
1837 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1838 'channel': 'Stephen',
1839 'availability': 'public',
1840 'creator': 'Stephen',
1841 'duration': 169,
1842 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1843 'age_limit': 0,
1844 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1845 'tags': 'count:11',
1846 'live_status': 'not_live',
6c73052c 1847 'channel_follower_count': int
5caabd3c 1848 },
1849 'params': {
1850 'skip_download': True,
1851 },
1852 },
66b48727
RA
1853 {
1854 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1855 'only_matching': True,
1856 },
011e75e6
S
1857 {
1858 # invalid -> valid video id redirection
1859 'url': 'DJztXj2GPfl',
1860 'info_dict': {
1861 'id': 'DJztXj2GPfk',
1862 'ext': 'mp4',
1863 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1864 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1865 'upload_date': '20090125',
1866 'uploader': 'Prochorowka',
1867 'uploader_id': 'Prochorowka',
1868 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1869 'artist': 'Panjabi MC',
1870 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1871 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1872 },
1873 'params': {
1874 'skip_download': True,
1875 },
545cc85d 1876 'skip': 'Video unavailable',
ea74e00b
DP
1877 },
1878 {
1879 # empty description results in an empty string
1880 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1881 'info_dict': {
1882 'id': 'x41yOUIvK2k',
1883 'ext': 'mp4',
1884 'title': 'IMG 3456',
1885 'description': '',
1886 'upload_date': '20170613',
1887 'uploader_id': 'ElevageOrVert',
1888 'uploader': 'ElevageOrVert',
976ae3ea 1889 'view_count': int,
1890 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1891 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1892 'like_count': int,
1893 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1894 'tags': [],
1895 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1896 'availability': 'public',
1897 'age_limit': 0,
1898 'categories': ['Pets & Animals'],
1899 'duration': 7,
1900 'playable_in_embed': True,
1901 'live_status': 'not_live',
1902 'channel': 'ElevageOrVert',
6c73052c 1903 'channel_follower_count': int
ea74e00b
DP
1904 },
1905 'params': {
1906 'skip_download': True,
1907 },
1908 },
a0566bbf 1909 {
29f7c58a 1910 # with '};' inside yt initial data (see [1])
1911 # see [2] for an example with '};' inside ytInitialPlayerResponse
1912 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1913 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1914 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1915 'info_dict': {
1916 'id': 'CHqg6qOn4no',
1917 'ext': 'mp4',
1918 'title': 'Part 77 Sort a list of simple types in c#',
1919 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1920 'upload_date': '20130831',
1921 'uploader_id': 'kudvenkat',
1922 'uploader': 'kudvenkat',
976ae3ea 1923 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1924 'like_count': int,
1925 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1926 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1927 'live_status': 'not_live',
1928 'categories': ['Education'],
1929 'availability': 'public',
1930 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1931 'tags': 'count:12',
1932 'playable_in_embed': True,
1933 'age_limit': 0,
1934 'view_count': int,
1935 'duration': 522,
1936 'channel': 'kudvenkat',
12a1b225 1937 'comment_count': int,
6c73052c 1938 'channel_follower_count': int
a0566bbf 1939 },
1940 'params': {
1941 'skip_download': True,
1942 },
1943 },
29f7c58a 1944 {
1945 # another example of '};' in ytInitialData
1946 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1947 'only_matching': True,
1948 },
1949 {
1950 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1951 'only_matching': True,
1952 },
545cc85d 1953 {
cc2db878 1954 # https://github.com/ytdl-org/youtube-dl/pull/28094
1955 'url': 'OtqTfy26tG0',
1956 'info_dict': {
1957 'id': 'OtqTfy26tG0',
1958 'ext': 'mp4',
1959 'title': 'Burn Out',
1960 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1961 'upload_date': '20141120',
1962 'uploader': 'The Cinematic Orchestra - Topic',
1963 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1964 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1965 'artist': 'The Cinematic Orchestra',
1966 'track': 'Burn Out',
1967 'album': 'Every Day',
976ae3ea 1968 'like_count': int,
1969 'live_status': 'not_live',
1970 'alt_title': 'Burn Out',
1971 'duration': 614,
1972 'age_limit': 0,
1973 'view_count': int,
1974 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1975 'creator': 'The Cinematic Orchestra',
1976 'channel': 'The Cinematic Orchestra',
1977 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1978 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1979 'availability': 'public',
1980 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1981 'categories': ['Music'],
1982 'playable_in_embed': True,
6c73052c 1983 'channel_follower_count': int
cc2db878 1984 },
1985 'params': {
1986 'skip_download': True,
1987 },
545cc85d 1988 },
bc2ca1bb 1989 {
1990 # controversial video, only works with bpctr when authenticated with cookies
1991 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1992 'only_matching': True,
1993 },
a1a7907b 1994 {
1995 # controversial video, requires bpctr/contentCheckOk
1996 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1997 'info_dict': {
1998 'id': 'SZJvDhaSDnc',
1999 'ext': 'mp4',
2000 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2001 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2002 'uploader': 'CBS Mornings',
11f9be09 2003 'uploader_id': 'CBSThisMorning',
a1a7907b 2004 'upload_date': '20140716',
976ae3ea 2005 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2006 'duration': 170,
2007 'categories': ['News & Politics'],
2008 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2009 'view_count': int,
2010 'channel': 'CBS Mornings',
2011 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2012 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2013 'age_limit': 18,
2014 'availability': 'needs_auth',
2015 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2016 'like_count': int,
2017 'live_status': 'not_live',
2018 'playable_in_embed': True,
6c73052c 2019 'channel_follower_count': int
a1a7907b 2020 }
2021 },
f7ad7160 2022 {
2023 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2024 'url': 'cBvYw8_A0vQ',
2025 'info_dict': {
2026 'id': 'cBvYw8_A0vQ',
2027 'ext': 'mp4',
2028 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2029 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2030 'upload_date': '20201120',
2031 'uploader': 'Walk around Japan',
2032 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2033 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2034 'duration': 1456,
2035 'categories': ['Travel & Events'],
2036 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2037 'view_count': int,
2038 'channel': 'Walk around Japan',
2039 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2040 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2041 'age_limit': 0,
2042 'availability': 'public',
2043 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2044 'live_status': 'not_live',
2045 'playable_in_embed': True,
6c73052c 2046 'channel_follower_count': int
f7ad7160 2047 },
2048 'params': {
2049 'skip_download': True,
2050 },
0fb983f6 2051 }, {
2052 # Has multiple audio streams
2053 'url': 'WaOKSUlf4TM',
2054 'only_matching': True
9297939e 2055 }, {
2056 # Requires Premium: has format 141 when requested using YTM url
2057 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2058 'only_matching': True
2059 }, {
120916da 2060 # multiple subtitles with same lang_code
2061 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2062 'only_matching': True,
109dd3b2 2063 }, {
2064 # Force use android client fallback
2065 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2066 'info_dict': {
2067 'id': 'YOelRv7fMxY',
11f9be09 2068 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2069 'ext': '3gp',
2070 'upload_date': '20210624',
2071 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2072 'uploader': 'colinfurze',
11f9be09 2073 'uploader_id': 'colinfurze',
109dd3b2 2074 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2075 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2076 'duration': 596,
2077 'categories': ['Entertainment'],
2078 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2079 'view_count': int,
2080 'channel': 'colinfurze',
2081 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2082 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2083 'age_limit': 0,
2084 'availability': 'public',
2085 'like_count': int,
2086 'live_status': 'not_live',
2087 'playable_in_embed': True,
6c73052c 2088 'channel_follower_count': int
109dd3b2 2089 },
2090 'params': {
2091 'format': '17', # 3gp format available on android
2092 'extractor_args': {'youtube': {'player_client': ['android']}},
2093 },
120916da 2094 },
109dd3b2 2095 {
2096 # Skip download of additional client configs (remix client config in this case)
2097 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2098 'only_matching': True,
2099 'params': {
2100 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2101 },
8fc54b12 2102 }, {
2103 # shorts
2104 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2105 'only_matching': True,
9222c381 2106 }, {
2107 'note': 'Storyboards',
2108 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2109 'info_dict': {
2110 'id': '5KLPxDtMqe8',
2111 'ext': 'mhtml',
2112 'format_id': 'sb0',
2113 'title': 'Your Brain is Plastic',
2114 'uploader_id': 'scishow',
2115 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2116 'upload_date': '20140324',
2117 'uploader': 'SciShow',
976ae3ea 2118 'like_count': int,
2119 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2120 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2121 'view_count': int,
2122 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2123 'playable_in_embed': True,
2124 'tags': 'count:12',
2125 'uploader_url': 'http://www.youtube.com/user/scishow',
2126 'availability': 'public',
2127 'channel': 'SciShow',
2128 'live_status': 'not_live',
2129 'duration': 248,
2130 'categories': ['Education'],
2131 'age_limit': 0,
6c73052c 2132 'channel_follower_count': int
9222c381 2133 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2134 }, {
2135 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2136 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2137 'info_dict': {
2138 'id': '2NUZ8W2llS4',
2139 'ext': 'mp4',
2140 'title': 'The NP that test your phone performance 🙂',
2141 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2142 'uploader': 'Leon Nguyen',
2143 'uploader_id': 'VNSXIII',
2144 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2145 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2146 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2147 'duration': 21,
2148 'view_count': int,
2149 'age_limit': 0,
2150 'categories': ['Gaming'],
2151 'tags': 'count:23',
2152 'playable_in_embed': True,
2153 'live_status': 'not_live',
2154 'upload_date': '20220103',
2155 'like_count': int,
2156 'availability': 'public',
2157 'channel': 'Leon Nguyen',
2158 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2159 'comment_count': int,
992f9a73 2160 'channel_follower_count': int
2161 }
1ff88b7a 2162 }, {
2163 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2164 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2165 'info_dict': {
2166 'id': '2NUZ8W2llS4',
2167 'ext': 'mp4',
2168 'title': 'The NP that test your phone performance 🙂',
2169 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2170 'uploader': 'Leon Nguyen',
2171 'uploader_id': 'VNSXIII',
2172 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2173 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2174 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2175 'duration': 21,
2176 'view_count': int,
2177 'age_limit': 0,
2178 'categories': ['Gaming'],
2179 'tags': 'count:23',
2180 'playable_in_embed': True,
2181 'live_status': 'not_live',
2182 'upload_date': '20220102',
2183 'like_count': int,
2184 'availability': 'public',
2185 'channel': 'Leon Nguyen',
2186 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2187 'comment_count': int,
2188 'channel_follower_count': int
2189 },
2190 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2191 }, {
2192 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2193 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2194 'info_dict': {
2195 'id': 'mzZzzBU6lrM',
2196 'ext': 'mp4',
2197 'title': 'I Met GeorgeNotFound In Real Life...',
2198 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2199 'uploader': 'Quackity',
2200 'uploader_id': 'QuackityHQ',
2201 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2202 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2203 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2204 'duration': 955,
2205 'view_count': int,
2206 'age_limit': 0,
2207 'categories': ['Entertainment'],
2208 'tags': 'count:26',
2209 'playable_in_embed': True,
2210 'live_status': 'not_live',
2211 'release_timestamp': 1641172509,
2212 'release_date': '20220103',
2213 'upload_date': '20220103',
2214 'like_count': int,
2215 'availability': 'public',
2216 'channel': 'Quackity',
2217 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2218 'channel_follower_count': int
2219 }
2220 },
2221 { # continuous livestream. Microformat upload date should be preferred.
2222 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2223 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2224 'info_dict': {
2225 'id': 'kgx4WGK0oNU',
2226 '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}',
2227 'ext': 'mp4',
2228 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2229 'availability': 'public',
2230 'age_limit': 0,
2231 'release_timestamp': 1637975704,
2232 'upload_date': '20210619',
2233 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2234 'live_status': 'is_live',
2235 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2236 'uploader': '阿鲍Abao',
2237 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2238 'channel': 'Abao in Tokyo',
2239 'channel_follower_count': int,
2240 'release_date': '20211127',
2241 'tags': 'count:39',
2242 'categories': ['People & Blogs'],
2243 'like_count': int,
2244 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2245 'view_count': int,
2246 'playable_in_embed': True,
2247 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2248 },
2249 'params': {'skip_download': True}
6e634cbe 2250 }, {
2251 # Story. Requires specific player params to work.
ee27297f 2252 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2253 'info_dict': {
ee27297f 2254 'id': 'vv8qTUWmulI',
6e634cbe 2255 'ext': 'mp4',
ee27297f 2256 'availability': 'unlisted',
2257 'view_count': int,
2258 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2259 'upload_date': '20220526',
2260 'categories': ['Education'],
2261 'title': 'Story',
2262 'channel': 'IT\'S HISTORY',
2263 'description': '',
2264 'uploader_id': 'BlastfromthePast',
2265 'duration': 12,
2266 'uploader': 'IT\'S HISTORY',
6e634cbe 2267 'playable_in_embed': True,
6e634cbe 2268 'age_limit': 0,
6e634cbe 2269 'live_status': 'not_live',
ee27297f 2270 'tags': [],
2271 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2272 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2273 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2274 },
2275 'skip': 'stories get removed after some period of time',
ee27297f 2276 }, {
2277 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2278 'info_dict': {
2279 'id': 'tjjjtzRLHvA',
2280 'ext': 'mp4',
2281 'title': 'ハッシュタグ無し };if window.ytcsi',
2282 'upload_date': '20220323',
2283 'like_count': int,
2284 'availability': 'unlisted',
2285 'channel': 'nao20010128nao',
2286 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2287 'age_limit': 0,
2288 'uploader': 'nao20010128nao',
2289 'uploader_id': 'nao20010128nao',
2290 'categories': ['Music'],
6e634cbe 2291 'view_count': int,
2292 'description': '',
ee27297f 2293 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2294 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2295 'live_status': 'not_live',
2296 'playable_in_embed': True,
2297 'channel_follower_count': int,
2298 'duration': 6,
2299 'tags': [],
2300 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2301 }
a4166234 2302 }, {
2303 'note': '6 channel audio',
2304 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2305 'only_matching': True,
6e634cbe 2306 }
2eb88d95
PH
2307 ]
2308
f2e8dbcc 2309 _WEBPAGE_TESTS = [
2310 # YouTube <object> embed
2311 {
2312 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2313 'md5': '873c81d308b979f0e23ee7e620b312a3',
2314 'info_dict': {
2315 'id': 'msN87y-iEx0',
2316 'ext': 'mp4',
2317 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2318 'upload_date': '20080526',
2319 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2320 'uploader': 'Christopher Sykes',
2321 'uploader_id': 'ChristopherJSykes',
2322 'age_limit': 0,
2323 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2324 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2325 'playable_in_embed': True,
2326 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2327 'like_count': int,
2328 'comment_count': int,
2329 'channel': 'Christopher Sykes',
2330 'live_status': 'not_live',
2331 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2332 'availability': 'public',
2333 'duration': 195,
2334 'view_count': int,
2335 'categories': ['Science & Technology'],
2336 'channel_follower_count': int,
2337 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2338 },
2339 'params': {
2340 'skip_download': True,
2341 }
2342 },
2343 ]
2344
201c1459 2345 @classmethod
2346 def suitable(cls, url):
4dfbf869 2347 from ..utils import parse_qs
2348
201c1459 2349 qs = parse_qs(url)
2350 if qs.get('list', [None])[0]:
2351 return False
86e5f3ed 2352 return super().suitable(url)
201c1459 2353
e0df6211 2354 def __init__(self, *args, **kwargs):
86e5f3ed 2355 super().__init__(*args, **kwargs)
545cc85d 2356 self._code_cache = {}
83799698 2357 self._player_cache = {}
e0df6211 2358
adbc4ec4 2359 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2360 lock = threading.Lock()
2361
2362 is_live = True
185bf310 2363 start_time = time.time()
adbc4ec4
THD
2364 formats = [f for f in formats if f.get('is_from_start')]
2365
185bf310 2366 def refetch_manifest(format_id, delay):
2367 nonlocal formats, start_time, is_live
2368 if time.time() <= start_time + delay:
adbc4ec4
THD
2369 return
2370
2371 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2372 video_details = traverse_obj(
2373 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2374 microformats = traverse_obj(
2375 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2376 expected_type=dict, default=[])
c646d76f 2377 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2378 start_time = time.time()
adbc4ec4 2379
185bf310 2380 def mpd_feed(format_id, delay):
adbc4ec4
THD
2381 """
2382 @returns (manifest_url, manifest_stream_number, is_live) or None
2383 """
2384 with lock:
185bf310 2385 refetch_manifest(format_id, delay)
adbc4ec4
THD
2386
2387 f = next((f for f in formats if f['format_id'] == format_id), None)
2388 if not f:
185bf310 2389 if not is_live:
2390 self.to_screen(f'{video_id}: Video is no longer live')
2391 else:
2392 self.report_warning(
2393 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2394 return None
2395 return f['manifest_url'], f['manifest_stream_number'], is_live
2396
2397 for f in formats:
a539f065 2398 f['is_live'] = True
adbc4ec4
THD
2399 f['protocol'] = 'http_dash_segments_generator'
2400 f['fragments'] = functools.partial(
2401 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2402
2403 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2404 FETCH_SPAN, MAX_DURATION = 5, 432000
2405
2406 mpd_url, stream_number, is_live = None, None, True
2407
2408 begin_index = 0
2409 download_start_time = ctx.get('start') or time.time()
2410
2411 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2412 if lack_early_segments:
2413 self.report_warning(bug_reports_message(
2414 'Starting download from the last 120 hours of the live stream since '
2415 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2416 lack_early_segments = True
2417
2418 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2419 fragments, fragment_base_url = None, None
2420
a539f065 2421 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2422 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2423 # Obtain from MPD's maximum seq value
2424 old_mpd_url = mpd_url
185bf310 2425 last_error = ctx.pop('last_error', None)
14f25df2 2426 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2427 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2428 or (mpd_url, stream_number, False))
2429 if not refresh_sequence:
2430 if expire_fast and not is_live:
2431 return False, last_seq
2432 elif old_mpd_url == mpd_url:
2433 return True, last_seq
adbc4ec4
THD
2434 try:
2435 fmts, _ = self._extract_mpd_formats_and_subtitles(
2436 mpd_url, None, note=False, errnote=False, fatal=False)
2437 except ExtractorError:
2438 fmts = None
2439 if not fmts:
a539f065 2440 no_fragment_score += 2
adbc4ec4
THD
2441 return False, last_seq
2442 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2443 fragments = fmt_info['fragments']
2444 fragment_base_url = fmt_info['fragment_base_url']
2445 assert fragment_base_url
2446
2447 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2448 return True, _last_seq
2449
2450 while is_live:
2451 fetch_time = time.time()
2452 if no_fragment_score > 30:
2453 return
2454 if last_segment_url:
2455 # Obtain from "X-Head-Seqnum" header value from each segment
2456 try:
2457 urlh = self._request_webpage(
2458 last_segment_url, None, note=False, errnote=False, fatal=False)
2459 except ExtractorError:
2460 urlh = None
2461 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2462 if last_seq is None:
a539f065 2463 no_fragment_score += 2
adbc4ec4
THD
2464 last_segment_url = None
2465 continue
2466 else:
a539f065
LNO
2467 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2468 no_fragment_score += 2
185bf310 2469 if not should_continue:
adbc4ec4
THD
2470 continue
2471
2472 if known_idx > last_seq:
2473 last_segment_url = None
2474 continue
2475
2476 last_seq += 1
2477
2478 if begin_index < 0 and known_idx < 0:
2479 # skip from the start when it's negative value
2480 known_idx = last_seq + begin_index
2481 if lack_early_segments:
2482 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2483 try:
2484 for idx in range(known_idx, last_seq):
2485 # do not update sequence here or you'll get skipped some part of it
a539f065 2486 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2487 if not should_continue:
adbc4ec4
THD
2488 known_idx = idx - 1
2489 raise ExtractorError('breaking out of outer loop')
2490 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2491 yield {
2492 'url': last_segment_url,
36195c44 2493 'fragment_count': last_seq,
adbc4ec4
THD
2494 }
2495 if known_idx == last_seq:
2496 no_fragment_score += 5
2497 else:
2498 no_fragment_score = 0
2499 known_idx = last_seq
2500 except ExtractorError:
2501 continue
2502
2503 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2504
b6de707d 2505 def _extract_player_url(self, *ytcfgs, webpage=None):
2506 player_url = traverse_obj(
2507 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2508 get_all=False, expected_type=str)
11f9be09 2509 if not player_url:
b6de707d 2510 return
60f393e4 2511 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2512
b6de707d 2513 def _download_player_url(self, video_id, fatal=False):
2514 res = self._download_webpage(
2515 'https://www.youtube.com/iframe_api',
2516 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2517 if res:
2518 player_version = self._search_regex(
2519 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2520 if player_version:
2521 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2522
60064c53
PH
2523 def _signature_cache_id(self, example_sig):
2524 """ Return a string representation of a signature """
14f25df2 2525 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2526
e40c758c
S
2527 @classmethod
2528 def _extract_player_info(cls, player_url):
2529 for player_re in cls._PLAYER_INFO_RE:
2530 id_m = re.search(player_re, player_url)
2531 if id_m:
2532 break
2533 else:
c081b35c 2534 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2535 return id_m.group('id')
e40c758c 2536
404f611f 2537 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2538 player_id = self._extract_player_info(player_url)
2539 if player_id not in self._code_cache:
1276a43a 2540 code = self._download_webpage(
109dd3b2 2541 player_url, video_id, fatal=fatal,
2542 note='Downloading player ' + player_id,
2543 errnote='Download of %s failed' % player_url)
1276a43a 2544 if code:
2545 self._code_cache[player_id] = code
404f611f 2546 return self._code_cache.get(player_id)
109dd3b2 2547
e40c758c 2548 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2549 player_id = self._extract_player_info(player_url)
e0df6211 2550
c4417ddb 2551 # Read from filesystem cache
86e5f3ed 2552 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2553 assert os.path.basename(func_id) == func_id
a0e07d31 2554
ae61d108 2555 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2556 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2557
580ce007 2558 if not cache_spec:
2559 code = self._load_player(video_id, player_url)
404f611f 2560 if code:
109dd3b2 2561 res = self._parse_sig_js(code)
ac668111 2562 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2563 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2564 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2565
2566 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2567
60064c53 2568 def _print_sig_code(self, func, example_sig):
404f611f 2569 if not self.get_param('youtube_print_sig_code'):
2570 return
2571
edf3e38e
PH
2572 def gen_sig_code(idxs):
2573 def _genslice(start, end, step):
78caa52a 2574 starts = '' if start == 0 else str(start)
8bcc8756 2575 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2576 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2577 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2578
2579 step = None
7af808a5
PH
2580 # Quelch pyflakes warnings - start will be set when step is set
2581 start = '(Never used)'
edf3e38e
PH
2582 for i, prev in zip(idxs[1:], idxs[:-1]):
2583 if step is not None:
2584 if i - prev == step:
2585 continue
2586 yield _genslice(start, prev, step)
2587 step = None
2588 continue
2589 if i - prev in [-1, 1]:
2590 step = i - prev
2591 start = prev
2592 continue
2593 else:
78caa52a 2594 yield 's[%d]' % prev
edf3e38e 2595 if step is None:
78caa52a 2596 yield 's[%d]' % i
edf3e38e
PH
2597 else:
2598 yield _genslice(start, i, step)
2599
ac668111 2600 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2601 cache_res = func(test_string)
edf3e38e 2602 cache_spec = [ord(c) for c in cache_res]
78caa52a 2603 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2604 signature_id_tuple = '(%s)' % (
14f25df2 2605 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2606 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2607 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2608 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2609
e0df6211
PH
2610 def _parse_sig_js(self, jscode):
2611 funcname = self._search_regex(
abefc03f
S
2612 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2613 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
2614 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2615 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2616 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}\(a,\d+\)',
2617 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 2618 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2619 # Obsolete patterns
2620 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2621 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2622 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2623 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2624 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2625 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2626 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2627 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2628 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2629
2630 jsi = JSInterpreter(jscode)
2631 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2632 return lambda s: initial_function([s])
2633
580ce007 2634 def _cached(self, func, *cache_id):
2635 def inner(*args, **kwargs):
2636 if cache_id not in self._player_cache:
2637 try:
2638 self._player_cache[cache_id] = func(*args, **kwargs)
2639 except ExtractorError as e:
2640 self._player_cache[cache_id] = e
2641 except Exception as e:
2642 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2643
2644 ret = self._player_cache[cache_id]
2645 if isinstance(ret, Exception):
2646 raise ret
2647 return ret
2648 return inner
2649
545cc85d 2650 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2651 """Turn the encrypted s field into a working signature"""
580ce007 2652 extract_sig = self._cached(
2653 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2654 func = extract_sig(video_id, player_url, s)
2655 self._print_sig_code(func, s)
2656 return func(s)
404f611f 2657
2658 def _decrypt_nsig(self, s, video_id, player_url):
2659 """Turn the encrypted n field into a working signature"""
2660 if player_url is None:
2661 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2662 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2663
580ce007 2664 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2665 if self.get_param('youtube_print_sig_code'):
2666 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2667
25836db6 2668 try:
2669 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2670 ret = extract_nsig(jsi, func_code)(s)
2671 except JSInterpreter.Exception as e:
2672 try:
992dc6b4 2673 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2674 except ExtractorError:
2675 raise e
2676 self.report_warning(
2677 f'Native nsig extraction failed: Trying with PhantomJS\n'
2678 f' n = {s} ; player = {player_url}', video_id)
2679 self.write_debug(e)
2680
2681 args, func_body = func_code
2682 ret = jsi.execute(
2683 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2684 video_id=video_id, note='Executing signature code').strip()
580ce007 2685
2686 self.write_debug(f'Decrypted nsig {s} => {ret}')
2687 return ret
2688
90a1df30 2689 def _extract_n_function_name(self, jscode):
2690 funcname, idx = self._search_regex(
2691 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2692 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2693 if not idx:
2694 return funcname
2695
2696 return json.loads(js_to_json(self._search_regex(
2697 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2698 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2699
580ce007 2700 def _extract_n_function_code(self, video_id, player_url):
404f611f 2701 player_id = self._extract_player_info(player_url)
d81ba7d4 2702 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.08.19.2')
580ce007 2703 jscode = func_code or self._load_player(video_id, player_url)
2704 jsi = JSInterpreter(jscode)
404f611f 2705
2706 if func_code:
580ce007 2707 return jsi, player_id, func_code
404f611f 2708
90a1df30 2709 func_code = jsi.extract_function_code(self._extract_n_function_name(jscode))
580ce007 2710 self.cache.store('youtube-nsig', player_id, func_code)
2711 return jsi, player_id, func_code
2712
2713 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 2714 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2715
580ce007 2716 def extract_nsig(s):
25836db6 2717 try:
2718 ret = func([s])
2719 except JSInterpreter.Exception:
2720 raise
2721 except Exception as e:
2722 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2723
f6ca640b 2724 if ret.startswith('enhanced_except_'):
25836db6 2725 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 2726 return ret
580ce007 2727
2728 return extract_nsig
e0df6211 2729
109dd3b2 2730 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2731 """
2732 Extract signatureTimestamp (sts)
2733 Required to tell API what sig/player version is in use.
2734 """
2735 sts = None
2736 if isinstance(ytcfg, dict):
2737 sts = int_or_none(ytcfg.get('STS'))
2738
2739 if not sts:
2740 # Attempt to extract from player
2741 if player_url is None:
2742 error_msg = 'Cannot extract signature timestamp without player_url.'
2743 if fatal:
2744 raise ExtractorError(error_msg)
2745 self.report_warning(error_msg)
2746 return
404f611f 2747 code = self._load_player(video_id, player_url, fatal=fatal)
2748 if code:
109dd3b2 2749 sts = int_or_none(self._search_regex(
2750 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2751 'JS player signature timestamp', group='sts', fatal=fatal))
2752 return sts
2753
11f9be09 2754 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2755 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2756 label = 'fully ' if is_full else ''
2757 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2758 expected_type=url_or_none)
2759 if not url:
2760 self.report_warning(f'Unable to mark {label}watched')
2761 return
14f25df2 2762 parsed_url = urllib.parse.urlparse(url)
2763 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2764
2765 # cpn generation algorithm is reverse engineered from base.js.
2766 # In fact it works even with dummy cpn.
2767 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2768 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2769
2770 # # more consistent results setting it to right before the end
2771 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2772
2773 qs.update({
2774 'ver': ['2'],
2775 'cpn': [cpn],
2776 'cmt': video_length,
2777 'el': 'detailpage', # otherwise defaults to "shorts"
2778 })
2779
2780 if is_full:
2781 # these seem to mark watchtime "history" in the real world
2782 # they're required, so send in a single value
2783 qs.update({
2784 'st': video_length,
2785 'et': video_length,
2786 })
2787
14f25df2 2788 url = urllib.parse.urlunparse(
2789 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2790
2791 self._download_webpage(
2792 url, video_id, f'Marking {label}watched',
2793 'Unable to mark watched', fatal=False)
d77ab8e2 2794
bfd973ec 2795 @classmethod
2796 def _extract_from_webpage(cls, url, webpage):
2797 # Invidious Instances
2798 # https://github.com/yt-dlp/yt-dlp/issues/195
2799 # https://github.com/iv-org/invidious/pull/1730
2800 mobj = re.search(
2801 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2802 webpage)
2803 if mobj:
2804 yield cls.url_result(mobj.group('url'), cls)
2805 raise cls.StopExtraction()
2806
2807 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2808
2809 # lazyYT YouTube embed
bfd973ec 2810 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2811 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2812
2813 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2814 for m in re.findall(r'''(?x)<div[^>]+
2815 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2816 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2817 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2818
97665381
PH
2819 @classmethod
2820 def extract_id(cls, url):
ae61d108 2821 video_id = cls.get_temp_id(url)
2822 if not video_id:
2823 raise ExtractorError(f'Invalid URL: {url}')
2824 return video_id
c5e8d7af 2825
7c365c21 2826 def _extract_chapters_from_json(self, data, duration):
2827 chapter_list = traverse_obj(
2828 data, (
2829 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2830 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2831 ), expected_type=list)
2832
2833 return self._extract_chapters(
2834 chapter_list,
2835 chapter_time=lambda chapter: float_or_none(
2836 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2837 chapter_title=lambda chapter: traverse_obj(
2838 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2839 duration=duration)
2840
2841 def _extract_chapters_from_engagement_panel(self, data, duration):
2842 content_list = traverse_obj(
8bdd16b4 2843 data,
7c365c21 2844 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2845 expected_type=list, default=[])
052e1350 2846 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2847 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2848
1890fc63 2849 return next(filter(None, (
2850 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2851 chapter_time, chapter_title, duration)
2852 for contents in content_list)), [])
7c365c21 2853
1890fc63 2854 def _extract_chapters_from_description(self, description, duration):
2855 return self._extract_chapters(
2856 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2857 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2858 duration=duration, strict=False)
84213ea8 2859
1890fc63 2860 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2861 if not duration:
2862 return
2863 chapter_list = [{
2864 'start_time': chapter_time(chapter),
2865 'title': chapter_title(chapter),
2866 } for chapter in chapter_list or []]
2867 if not strict:
2868 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2869
a3976e07 2870 chapters = [{'start_time': 0}]
1890fc63 2871 for idx, chapter in enumerate(chapter_list):
a3976e07 2872 if chapter['start_time'] is None:
1890fc63 2873 self.report_warning(f'Incomplete chapter {idx}')
2874 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2875 chapters.append(chapter)
2876 else:
2877 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2878 return chapters[1:]
84213ea8 2879
a1c5d2ca
M
2880 def _extract_comment(self, comment_renderer, parent=None):
2881 comment_id = comment_renderer.get('commentId')
2882 if not comment_id:
2883 return
fe93e2c4 2884
052e1350 2885 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2886
49bd8c66 2887 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2888 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2889 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2890 author_id = try_get(comment_renderer,
14f25df2 2891 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2892
49bd8c66 2893 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2894 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2895 author_thumbnail = try_get(comment_renderer,
14f25df2 2896 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2897
2898 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2899 is_favorited = 'creatorHeart' in (try_get(
2900 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2901 return {
2902 'id': comment_id,
2903 'text': text,
d92f5d5a 2904 'timestamp': timestamp,
a1c5d2ca
M
2905 'time_text': time_text,
2906 'like_count': votes,
97524332 2907 'is_favorited': is_favorited,
a1c5d2ca
M
2908 'author': author,
2909 'author_id': author_id,
2910 'author_thumbnail': author_thumbnail,
2911 'author_is_uploader': author_is_uploader,
2912 'parent': parent or 'root'
2913 }
2914
46383212 2915 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2916
2917 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2918
2919 def extract_header(contents):
2d6659b9 2920 _continuation = None
2921 for content in contents:
46383212 2922 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2923 expected_comment_count = self._get_count(
2924 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2925
2d6659b9 2926 if expected_comment_count:
46383212 2927 tracker['est_total'] = expected_comment_count
2928 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2929 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2930
2931 sort_menu_item = try_get(
2932 comments_header_renderer,
2933 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2934 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2935
2936 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2937 if not _continuation:
2938 continue
2939
46383212 2940 sort_text = str_or_none(sort_menu_item.get('title'))
2941 if not sort_text:
2d6659b9 2942 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2943 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2944 break
a2160aa4 2945 return _continuation
a1c5d2ca 2946
2d6659b9 2947 def extract_thread(contents):
a1c5d2ca 2948 if not parent:
46383212 2949 tracker['current_page_thread'] = 0
a1c5d2ca 2950 for content in contents:
46383212 2951 if not parent and tracker['total_parent_comments'] >= max_parents:
2952 yield
a1c5d2ca 2953 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2954 comment_renderer = get_first(
2955 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2956 expected_type=dict, default={})
a1c5d2ca 2957
a1c5d2ca
M
2958 comment = self._extract_comment(comment_renderer, parent)
2959 if not comment:
2960 continue
46383212 2961
2962 tracker['running_total'] += 1
2963 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2964 yield comment
46383212 2965
a1c5d2ca
M
2966 # Attempt to get the replies
2967 comment_replies_renderer = try_get(
2968 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2969
2970 if comment_replies_renderer:
46383212 2971 tracker['current_page_thread'] += 1
a1c5d2ca 2972 comment_entries_iter = self._comment_entries(
99e9e001 2973 comment_replies_renderer, ytcfg, video_id,
46383212 2974 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2975 yield from itertools.islice(comment_entries_iter, min(
2976 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2977
46383212 2978 # Keeps track of counts across recursive calls
2979 if not tracker:
2980 tracker = dict(
2981 running_total=0,
2982 est_total=0,
2983 current_page_thread=0,
2984 total_parent_comments=0,
2985 total_reply_comments=0)
2986
2987 # TODO: Deprecated
2d6659b9 2988 # YouTube comments have a max depth of 2
46383212 2989 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2990 if max_depth:
da4db748 2991 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
2992 'Set max replies in the max-comments extractor argument instead')
2d6659b9 2993 if max_depth == 1 and parent:
2994 return
a1c5d2ca 2995
46383212 2996 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2997 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2998
46383212 2999 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3000
46383212 3001 response = None
6e634cbe 3002 is_forced_continuation = False
2d6659b9 3003 is_first_continuation = parent is None
6e634cbe 3004 if is_first_continuation and not continuation:
3005 # Sometimes you can get comments by generating the continuation yourself,
3006 # even if YouTube initially reports them being disabled - e.g. stories comments.
3007 # Note: if the comment section is actually disabled, YouTube may return a response with
3008 # required check_get_keys missing. So we will disable that check initially in this case.
3009 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3010 is_forced_continuation = True
a1c5d2ca
M
3011
3012 for page_num in itertools.count(0):
3013 if not continuation:
3014 break
46383212 3015 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3016 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3017 if page_num == 0:
3018 if is_first_continuation:
3019 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3020 else:
2d6659b9 3021 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3022 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3023 else:
3024 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3025 ' ' if parent else '', ' replies' if parent else '',
3026 page_num, comment_prog_str)
3027
3028 response = self._extract_response(
fe93e2c4 3029 item_id=None, query=continuation,
2d6659b9 3030 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 3031 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3032 is_forced_continuation = False
46383212 3033 continuation_contents = traverse_obj(
3034 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3035
2d6659b9 3036 continuation = None
46383212 3037 for continuation_section in continuation_contents:
3038 continuation_items = traverse_obj(
3039 continuation_section,
3040 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3041 get_all=False, expected_type=list) or []
3042 if is_first_continuation:
3043 continuation = extract_header(continuation_items)
3044 is_first_continuation = False
2d6659b9 3045 if continuation:
a1c5d2ca 3046 break
46383212 3047 continue
a1c5d2ca 3048
46383212 3049 for entry in extract_thread(continuation_items):
3050 if not entry:
3051 return
3052 yield entry
3053 continuation = self._extract_continuation({'contents': continuation_items})
3054 if continuation:
2d6659b9 3055 break
a1c5d2ca 3056
6e634cbe 3057 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3058 if message and not parent and tracker['running_total'] == 0:
3059 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3060
3061 @staticmethod
3062 def _generate_comment_continuation(video_id):
3063 """
3064 Generates initial comment section continuation token from given video id
3065 """
3066 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3067 return base64.b64encode(token.encode()).decode()
3068
a2160aa4 3069 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3070 """Entry for comment extraction"""
2d6659b9 3071 def _real_comment_extract(contents):
aae16f6e 3072 renderer = next((
3073 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3074 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3075 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3076
a2160aa4 3077 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3078 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3079
109dd3b2 3080 @staticmethod
99e9e001 3081 def _get_checkok_params():
3082 return {'contentCheckOk': True, 'racyCheckOk': True}
3083
3084 @classmethod
3085 def _generate_player_context(cls, sts=None):
109dd3b2 3086 context = {
3087 'html5Preference': 'HTML5_PREF_WANTS',
3088 }
3089 if sts is not None:
3090 context['signatureTimestamp'] = sts
3091 return {
3092 'playbackContext': {
3093 'contentPlaybackContext': context
a1a7907b 3094 },
99e9e001 3095 **cls._get_checkok_params()
109dd3b2 3096 }
3097
e7e94f2a
D
3098 @staticmethod
3099 def _is_agegated(player_response):
3100 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3101 return True
e7e94f2a
D
3102
3103 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3104 AGE_GATE_REASONS = (
3105 'confirm your age', 'age-restricted', 'inappropriate', # reason
3106 'age_verification_required', 'age_check_required', # status
3107 )
3108 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3109
3110 @staticmethod
3111 def _is_unplayable(player_response):
3112 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3113
50ac0e54 3114 _STORY_PLAYER_PARAMS = '8AEB'
3115
3116 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3117
11f9be09 3118 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3119 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3120 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3121 headers = self.generate_api_headers(
99e9e001 3122 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3123
6e634cbe 3124 yt_query = {
3125 'videoId': video_id,
6e634cbe 3126 }
50ac0e54 3127 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3128 yt_query['params'] = self._STORY_PLAYER_PARAMS
3129
11f9be09 3130 yt_query.update(self._generate_player_context(sts))
3131 return self._extract_response(
3132 item_id=video_id, ep='player', query=yt_query,
379e44ed 3133 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3134 default_client=client,
11f9be09 3135 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3136 ) or None
3137
11f9be09 3138 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3139 requested_clients = []
d0d012d4 3140 default = ['android', 'web']
000c15a4 3141 allowed_clients = sorted(
86e5f3ed 3142 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3143 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3144 for client in self._configuration_arg('player_client'):
3145 if client in allowed_clients:
3146 requested_clients.append(client)
d0d012d4 3147 elif client == 'default':
3148 requested_clients.extend(default)
b4c055ba 3149 elif client == 'all':
3150 requested_clients.extend(allowed_clients)
3151 else:
3152 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3153 if not requested_clients:
d0d012d4 3154 requested_clients = default
cf7e015f 3155
11f9be09 3156 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3157 requested_clients.extend(
e7e94f2a 3158 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3159
11f9be09 3160 return orderedSet(requested_clients)
cf7e015f 3161
50ac0e54 3162 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3163 initial_pr = None
3164 if webpage:
b7c47b74 3165 initial_pr = self._search_json(
3166 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3167
ae729626 3168 all_clients = set(clients)
c0bc527b 3169 clients = clients[::-1]
b6de707d 3170 prs = []
e7e94f2a 3171
ae729626 3172 def append_client(*client_names):
e7870111 3173 """ Append the first client name that exists but not already used """
ae729626 3174 for client_name in client_names:
e7870111
D
3175 actual_client = _split_innertube_client(client_name)[0]
3176 if actual_client in INNERTUBE_CLIENTS:
3177 if actual_client not in all_clients:
ae729626 3178 clients.append(client_name)
e7870111
D
3179 all_clients.add(actual_client)
3180 return
e7e94f2a 3181
379e44ed 3182 # Android player_response does not have microFormats which are needed for
3183 # extraction of some data. So we return the initial_pr with formats
3184 # stripped out even if not requested by the user
3185 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3186 if initial_pr:
3187 pr = dict(initial_pr)
3188 pr['streamingData'] = None
b6de707d 3189 prs.append(pr)
379e44ed 3190
3191 last_error = None
b6de707d 3192 tried_iframe_fallback = False
3193 player_url = None
c0bc527b 3194 while clients:
e7870111 3195 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3196 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3197 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3198 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3199
b6de707d 3200 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3201 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3202 if 'js' in self._configuration_arg('player_skip'):
3203 require_js_player = False
3204 player_url = None
3205
3206 if not player_url and not tried_iframe_fallback and require_js_player:
3207 player_url = self._download_player_url(video_id)
3208 tried_iframe_fallback = True
3209
379e44ed 3210 try:
3211 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3212 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3213 except ExtractorError as e:
3214 if last_error:
3215 self.report_warning(last_error)
3216 last_error = e
3217 continue
3218
11f9be09 3219 if pr:
a3e96421 3220 # YouTube may return a different video player response than expected.
3221 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3222 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3223 if pr_video_id and pr_video_id != video_id:
3224 self.report_warning(
c7dcf0b3 3225 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3226 else:
3227 prs.append(pr)
c0bc527b 3228
e7e94f2a 3229 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3230 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3231 append_client(f'{base_client}_creator')
e7e94f2a 3232 elif self._is_agegated(pr):
e7870111
D
3233 if variant == 'tv_embedded':
3234 append_client(f'{base_client}_embedded')
3235 elif not variant:
3236 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3237
379e44ed 3238 if last_error:
b6de707d 3239 if not len(prs):
379e44ed 3240 raise last_error
3241 self.report_warning(last_error)
b6de707d 3242 return prs, player_url
11f9be09 3243
c646d76f 3244 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3245 itags, stream_ids = {}, []
b25cac65 3246 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3247 q = qualities([
2a9c6dcd 3248 # Normally tiny is the smallest video-only formats. But
3249 # audio-only formats with unknown quality may get tagged as tiny
3250 'tiny',
3251 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3252 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3253 ])
11f9be09 3254 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3255
545cc85d 3256 for fmt in streaming_formats:
727029c5 3257 if fmt.get('targetDurationSec'):
545cc85d 3258 continue
321bf820 3259
cc2db878 3260 itag = str_or_none(fmt.get('itag'))
9297939e 3261 audio_track = fmt.get('audioTrack') or {}
3262 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3263 if stream_id in stream_ids:
3264 continue
3265
cc2db878 3266 quality = fmt.get('quality')
2a9c6dcd 3267 height = int_or_none(fmt.get('height'))
d3fc8074 3268 if quality == 'tiny' or not quality:
3269 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3270 # The 3gp format (17) in android client has a quality of "small",
3271 # but is actually worse than other formats
3272 if itag == '17':
3273 quality = 'tiny'
3274 if quality:
3275 if itag:
3276 itag_qualities[itag] = quality
3277 if height:
3278 res_qualities[height] = quality
cc2db878 3279 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3280 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3281 # number of fragment that would subsequently requested with (`&sq=N`)
3282 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3283 continue
3284
545cc85d 3285 fmt_url = fmt.get('url')
3286 if not fmt_url:
14f25df2 3287 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3288 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3289 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3290 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3291 continue
52023f12 3292 try:
3293 fmt_url += '&%s=%s' % (
3294 traverse_obj(sc, ('sp', -1)) or 'signature',
3295 self._decrypt_signature(encrypted_sig, video_id, player_url)
3296 )
3297 except ExtractorError as e:
580ce007 3298 self.report_warning('Signature extraction failed: Some formats may be missing',
3299 video_id=video_id, only_once=True)
52023f12 3300 self.write_debug(e, only_once=True)
201e9eaa 3301 continue
545cc85d 3302
404f611f 3303 query = parse_qs(fmt_url)
3304 throttled = False
b2916526 3305 if query.get('n'):
404f611f 3306 try:
580ce007 3307 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3308 fmt_url = update_url_query(fmt_url, {
580ce007 3309 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3310 })
404f611f 3311 except ExtractorError as e:
25836db6 3312 phantomjs_hint = ''
3313 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3314 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3315 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
aa9369a2 3316 self.report_warning(
25836db6 3317 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3318 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
52023f12 3319 self.write_debug(e, only_once=True)
404f611f 3320 throttled = True
3321
545cc85d 3322 if itag:
a0bb6ce5 3323 itags[itag] = 'https'
9297939e 3324 stream_ids.append(stream_id)
3325
0ad92dfb 3326 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3327 language_preference = (
3328 10 if audio_track.get('audioIsDefault') and 10
3329 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3330 else -1)
0ad92dfb 3331 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3332 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3333 # Make sure to avoid false positives with small duration differences.
62b58c09 3334 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3335 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3336 if is_damaged:
0f06bcd7 3337 self.report_warning(
3338 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3339 dct = {
3340 'asr': int_or_none(fmt.get('audioSampleRate')),
3341 'filesize': int_or_none(fmt.get('contentLength')),
3342 'format_id': itag,
34921b43 3343 'format_note': join_nonempty(
26e8e044 3344 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3345 ' (default)' if language_preference > 0 else ''),
404f611f 3346 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3347 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3348 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3349 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3350 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3351 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3352 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3353 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3354 'height': height,
dca3ff4a 3355 'quality': q(quality),
727029c5 3356 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3357 'tbr': tbr,
545cc85d 3358 'url': fmt_url,
2a9c6dcd 3359 'width': int_or_none(fmt.get('width')),
ab6df717 3360 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3361 'desc' if language_preference < -1 else ''),
3362 'language_preference': language_preference,
a405b38f 3363 # Strictly de-prioritize damaged and 3gp formats
3364 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3365 }
60bdb7bd 3366 mime_mobj = re.match(
3367 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3368 if mime_mobj:
3369 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3370 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3371 no_audio = dct.get('acodec') == 'none'
3372 no_video = dct.get('vcodec') == 'none'
3373 if no_audio:
3374 dct['vbr'] = tbr
3375 if no_video:
3376 dct['abr'] = tbr
3377 if no_audio or no_video:
545cc85d 3378 dct['downloader_options'] = {
3379 # Youtube throttles chunks >~10M
3380 'http_chunk_size': 10485760,
bf1317d2 3381 }
7c60c33e 3382 if dct.get('ext'):
3383 dct['container'] = dct['ext'] + '_dash'
11f9be09 3384 yield dct
545cc85d 3385
adbc4ec4 3386 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3387 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3388 if not self.get_param('youtube_include_hls_manifest', True):
3389 skip_manifests.append('hls')
0f06bcd7 3390 if not self.get_param('youtube_include_dash_manifest', True):
3391 skip_manifests.append('dash')
adbc4ec4
THD
3392 get_dash = 'dash' not in skip_manifests and (
3393 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3394 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3395
a0bb6ce5 3396 def process_manifest_format(f, proto, itag):
3397 if itag in itags:
3398 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3399 return False
3400 itag = f'{itag}-{proto}'
3401 if itag:
3402 f['format_id'] = itag
3403 itags[itag] = proto
3404
b25cac65 3405 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3406 if f['quality'] == -1 and f.get('height'):
3407 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3408 return True
2a9c6dcd 3409
c646d76f 3410 subtitles = {}
11f9be09 3411 for sd in streaming_data:
5d3a0e79 3412 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3413 if hls_manifest_url:
c646d76f 3414 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3415 subtitles = self._merge_subtitles(subs, subtitles)
3416 for f in fmts:
a0bb6ce5 3417 if process_manifest_format(f, 'hls', self._search_regex(
3418 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3419 yield f
545cc85d 3420
5d3a0e79 3421 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3422 if dash_manifest_url:
c646d76f 3423 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3424 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3425 for f in formats:
a0bb6ce5 3426 if process_manifest_format(f, 'dash', f['format_id']):
3427 f['filesize'] = int_or_none(self._search_regex(
3428 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3429 if live_from_start:
3430 f['is_from_start'] = True
3431
a0bb6ce5 3432 yield f
c646d76f 3433 yield subtitles
11f9be09 3434
720c3099 3435 def _extract_storyboard(self, player_responses, duration):
3436 spec = get_first(
3437 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3438 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3439 if not base_url:
720c3099 3440 return
720c3099 3441 L = len(spec) - 1
3442 for i, args in enumerate(spec):
3443 args = args.split('#')
3444 counts = list(map(int_or_none, args[:5]))
3445 if len(args) != 8 or not all(counts):
3446 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3447 continue
3448 width, height, frame_count, cols, rows = counts
3449 N, sigh = args[6:]
3450
3451 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3452 fragment_count = frame_count / (cols * rows)
3453 fragment_duration = duration / fragment_count
3454 yield {
3455 'format_id': f'sb{i}',
3456 'format_note': 'storyboard',
3457 'ext': 'mhtml',
3458 'protocol': 'mhtml',
3459 'acodec': 'none',
3460 'vcodec': 'none',
3461 'url': url,
3462 'width': width,
3463 'height': height,
45e8a04e 3464 'fps': frame_count / duration,
3465 'rows': rows,
3466 'columns': cols,
720c3099 3467 'fragments': [{
b3edc806 3468 'url': url.replace('$M', str(j)),
720c3099 3469 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3470 } for j in range(math.ceil(fragment_count))],
3471 }
3472
adbc4ec4 3473 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3474 webpage = None
3475 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3476 query = {'bpctr': '9999999999', 'has_verified': '1'}
3477 if smuggled_data.get('is_story'):
3478 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3479 webpage = self._download_webpage(
50ac0e54 3480 webpage_url, video_id, fatal=False, query=query)
11f9be09 3481
3482 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3483
b6de707d 3484 player_responses, player_url = self._extract_player_responses(
11f9be09 3485 self._get_requested_clients(url, smuggled_data),
50ac0e54 3486 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3487
adbc4ec4
THD
3488 return webpage, master_ytcfg, player_responses, player_url
3489
a1b2d843 3490 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3491 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3492 is_live = get_first(video_details, 'isLive')
3493 if is_live is None:
3494 is_live = get_first(live_broadcast_details, 'isLiveNow')
3495
3496 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3497 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3498
c646d76f 3499 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3500
3501 def _real_extract(self, url):
3502 url, smuggled_data = unsmuggle_url(url, {})
3503 video_id = self._match_id(url)
3504
3505 base_url = self.http_scheme() + '//www.youtube.com/'
3506 webpage_url = base_url + 'watch?v=' + video_id
3507
3508 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3509
11f9be09 3510 playability_statuses = traverse_obj(
3511 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3512
3513 trailer_video_id = get_first(
3514 playability_statuses,
3515 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3516 expected_type=str)
3517 if trailer_video_id:
3518 return self.url_result(
3519 trailer_video_id, self.ie_key(), trailer_video_id)
3520
3521 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3522 if webpage else (lambda x: None))
3523
3524 video_details = traverse_obj(
3525 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3526 microformats = traverse_obj(
3527 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3528 expected_type=dict, default=[])
3529 video_title = (
3530 get_first(video_details, 'title')
3531 or self._get_text(microformats, (..., 'title'))
3532 or search_meta(['og:title', 'twitter:title', 'title']))
3533 video_description = get_first(video_details, 'shortDescription')
3534
d89257f3 3535 multifeed_metadata_list = get_first(
3536 player_responses,
3537 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3538 expected_type=str)
3539 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3540 if self.get_param('noplaylist'):
11f9be09 3541 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3542 else:
3543 entries = []
3544 feed_ids = []
3545 for feed in multifeed_metadata_list.split(','):
3546 # Unquote should take place before split on comma (,) since textual
3547 # fields may contain comma as well (see
3548 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3549 feed_data = urllib.parse.parse_qs(
ac668111 3550 urllib.parse.unquote_plus(feed))
d89257f3 3551
3552 def feed_entry(name):
3553 return try_get(
14f25df2 3554 feed_data, lambda x: x[name][0], str)
d89257f3 3555
3556 feed_id = feed_entry('id')
3557 if not feed_id:
3558 continue
3559 feed_title = feed_entry('title')
3560 title = video_title
3561 if feed_title:
3562 title += ' (%s)' % feed_title
3563 entries.append({
3564 '_type': 'url_transparent',
3565 'ie_key': 'Youtube',
3566 'url': smuggle_url(
3567 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3568 {'force_singlefeed': True}),
3569 'title': title,
3570 })
3571 feed_ids.append(feed_id)
3572 self.to_screen(
3573 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3574 % (', '.join(feed_ids), video_id))
3575 return self.playlist_result(
3576 entries, video_id, video_title, video_description)
11f9be09 3577
a1b2d843 3578 duration = int_or_none(
3579 get_first(video_details, 'lengthSeconds')
3580 or get_first(microformats, 'lengthSeconds')
3581 or parse_duration(search_meta('duration'))) or None
3582
c646d76f 3583 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3584 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3585
545cc85d 3586 if not formats:
11f9be09 3587 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3588 self.report_drm(video_id)
11f9be09 3589 pemr = get_first(
3590 playability_statuses,
3591 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3592 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3593 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3594 if subreason:
545cc85d 3595 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3596 countries = get_first(microformats, 'availableCountries')
545cc85d 3597 if not countries:
3598 regions_allowed = search_meta('regionsAllowed')
3599 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3600 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3601 reason += f'. {subreason}'
545cc85d 3602 if reason:
b7da73eb 3603 self.raise_no_formats(reason, expected=True)
bf1317d2 3604
11f9be09 3605 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3606 if not keywords and webpage:
3607 keywords = [
3608 unescapeHTML(m.group('content'))
3609 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3610 for keyword in keywords:
3611 if keyword.startswith('yt:stretch='):
201c1459 3612 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3613 if mobj:
3614 # NB: float is intentional for forcing float division
3615 w, h = (float(v) for v in mobj.groups())
3616 if w > 0 and h > 0:
3617 ratio = w / h
3618 for f in formats:
3619 if f.get('vcodec') != 'none':
3620 f['stretched_ratio'] = ratio
3621 break
a709d873 3622 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3623 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3624 if thumbnail_url:
3625 thumbnails.append({
3626 'url': thumbnail_url,
ff2751ac 3627 })
fccf5021 3628 original_thumbnails = thumbnails.copy()
3629
0ba692ac 3630 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3631 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3632 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3633 thumbnail_names = [
962ffcf8 3634 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3635 # in resolution, these are not the custom thumbnail. So de-prioritize them
3636 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3637 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3638 ]
cca80fe6 3639 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3640 thumbnails.extend({
3641 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3642 video_id=video_id, name=name, ext=ext,
3643 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3644 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3645 for thumb in thumbnails:
cca80fe6 3646 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3647 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3648 self._remove_duplicate_formats(thumbnails)
fccf5021 3649 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3650
7ea65411 3651 category = get_first(microformats, 'category') or search_meta('genre')
3652 channel_id = str_or_none(
3653 get_first(video_details, 'channelId')
3654 or get_first(microformats, 'externalChannelId')
3655 or search_meta('channelId'))
7ea65411 3656 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3657
3658 live_content = get_first(video_details, 'isLiveContent')
3659 is_upcoming = get_first(video_details, 'isUpcoming')
3660 if is_live is None:
3661 if is_upcoming or live_content is False:
3662 is_live = False
3663 if is_upcoming is None and (live_content or is_live):
3664 is_upcoming = False
adbc4ec4
THD
3665 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3666 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3667 if not duration and live_end_time and live_start_time:
3668 duration = live_end_time - live_start_time
3669
3670 if is_live and self.get_param('live_from_start'):
3671 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3672
720c3099 3673 formats.extend(self._extract_storyboard(player_responses, duration))
3674
31b532a1 3675 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3676 self._sort_formats(formats, (
3677 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3678
545cc85d 3679 info = {
3680 'id': video_id,
39ca3b5c 3681 'title': video_title,
545cc85d 3682 'formats': formats,
3683 'thumbnails': thumbnails,
fccf5021 3684 # The best thumbnail that we are sure exists. Prevents unnecessary
3685 # URL checking if user don't care about getting the best possible thumbnail
3686 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3687 'description': video_description,
11f9be09 3688 'uploader': get_first(video_details, 'author'),
545cc85d 3689 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3690 'uploader_url': owner_profile_url,
3691 'channel_id': channel_id,
a70635b8 3692 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3693 'duration': duration,
3694 'view_count': int_or_none(
11f9be09 3695 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3696 or search_meta('interactionCount')),
11f9be09 3697 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3698 'age_limit': 18 if (
11f9be09 3699 get_first(microformats, 'isFamilySafe') is False
545cc85d 3700 or search_meta('isFamilyFriendly') == 'false'
3701 or search_meta('og:restrictions:age') == '18+') else 0,
3702 'webpage_url': webpage_url,
3703 'categories': [category] if category else None,
3704 'tags': keywords,
11f9be09 3705 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3706 'is_live': is_live,
3707 'was_live': (False if is_live or is_upcoming or live_content is False
3708 else None if is_live is None or is_upcoming is None
3709 else live_content),
3710 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3711 'release_timestamp': live_start_time,
545cc85d 3712 }
b477fc13 3713
e325a21a 3714 if get_first(video_details, 'isPostLiveDvr'):
3715 self.write_debug('Video is in Post-Live Manifestless mode')
3716 info['live_status'] = 'post_live'
3717 if (duration or 0) > 4 * 3600:
3718 self.report_warning(
3719 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3720 'This is a known issue and patches are welcome')
3721
c646d76f 3722 subtitles = {}
3944e7af 3723 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3724 if pctr:
ecdc9049 3725 def get_lang_code(track):
3726 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3727 or track.get('languageCode'))
3728
3729 # Converted into dicts to remove duplicates
3730 captions = {
3731 get_lang_code(sub): sub
3732 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3733 translation_languages = {
3734 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3735 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3736
774d79cc 3737 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3738 lang_subs = container.setdefault(lang_code, [])
545cc85d 3739 for fmt in self._SUBTITLE_FORMATS:
3740 query.update({
3741 'fmt': fmt,
3742 })
3743 lang_subs.append({
3744 'ext': fmt,
60f393e4 3745 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3746 'name': sub_name,
545cc85d 3747 })
7e72694b 3748
07b47084 3749 # NB: Constructing the full subtitle dictionary is slow
3750 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3751 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3752 for lang_code, caption_track in captions.items():
3753 base_url = caption_track.get('baseUrl')
1235d333 3754 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3755 if not base_url:
3756 continue
ecdc9049 3757 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3758 if caption_track.get('kind') != 'asr':
545cc85d 3759 if not lang_code:
3760 continue
3761 process_language(
ecdc9049 3762 subtitles, base_url, lang_code, lang_name, {})
3763 if not caption_track.get('isTranslatable'):
3764 continue
3944e7af 3765 for trans_code, trans_name in translation_languages.items():
3766 if not trans_code:
545cc85d 3767 continue
1235d333 3768 orig_trans_code = trans_code
ecdc9049 3769 if caption_track.get('kind') != 'asr':
07b47084 3770 if not get_translated_subs:
18e49408 3771 continue
ecdc9049 3772 trans_code += f'-{lang_code}'
a70635b8 3773 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3774 # Add an "-orig" label to the original language so that it can be distinguished.
3775 # The subs are returned without "-orig" as well for compatibility
1235d333 3776 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3777 process_language(
d49669ac 3778 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3779 # Setting tlang=lang returns damaged subtitles.
d49669ac 3780 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3781 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3782
3783 info['automatic_captions'] = automatic_captions
3784 info['subtitles'] = subtitles
7e72694b 3785
14f25df2 3786 parsed_url = urllib.parse.urlparse(url)
545cc85d 3787 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3788 query = urllib.parse.parse_qs(component)
545cc85d 3789 for k, v in query.items():
3790 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3791 d_k += '_time'
3792 if d_k not in info and k in s_ks:
3793 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3794
3795 # Youtube Music Auto-generated description
822b9d9c 3796 if video_description:
1890fc63 3797 mobj = re.search(
3798 r'''(?xs)
3799 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3800 (?P<album>[^\n]+)
3801 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3802 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3803 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3804 .+\nAuto-generated\ by\ YouTube\.\s*$
3805 ''', video_description)
822b9d9c 3806 if mobj:
822b9d9c
RA
3807 release_year = mobj.group('release_year')
3808 release_date = mobj.group('release_date')
3809 if release_date:
3810 release_date = release_date.replace('-', '')
3811 if not release_year:
545cc85d 3812 release_year = release_date[:4]
3813 info.update({
3814 'album': mobj.group('album'.strip()),
3815 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3816 'track': mobj.group('track').strip(),
3817 'release_date': release_date,
cc2db878 3818 'release_year': int_or_none(release_year),
545cc85d 3819 })
7e72694b 3820
545cc85d 3821 initial_data = None
3822 if webpage:
56ba69e4 3823 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3824 if not initial_data:
99e9e001 3825 query = {'videoId': video_id}
3826 query.update(self._get_checkok_params())
109dd3b2 3827 initial_data = self._extract_response(
3828 item_id=video_id, ep='next', fatal=False,
99e9e001 3829 ytcfg=master_ytcfg, query=query,
3830 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3831 note='Downloading initial data API JSON')
545cc85d 3832
0df111a3 3833 info['comment_count'] = traverse_obj(initial_data, (
3834 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3835 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3836 ), (
3837 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3838 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3839 ), expected_type=int_or_none, get_all=False)
3840
19a03940 3841 try: # This will error if there is no livechat
c60ee3a2 3842 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3843 except (KeyError, IndexError, TypeError):
3844 pass
3845 else:
ecdc9049 3846 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3847 # url is needed to set cookies
3848 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3849 'video_id': video_id,
3850 'ext': 'json',
f6745c49 3851 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3852 }]
545cc85d 3853
3854 if initial_data:
7c365c21 3855 info['chapters'] = (
3856 self._extract_chapters_from_json(initial_data, duration)
3857 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3858 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3859 or None)
545cc85d 3860
17322130 3861 contents = traverse_obj(
3862 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3863 expected_type=list, default=[])
3864
3865 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3866 if vpir:
3867 stl = vpir.get('superTitleLink')
3868 if stl:
3869 stl = self._get_text(stl)
3870 if try_get(
3871 vpir,
3872 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3873 info['location'] = stl
3874 else:
affc4fef 3875 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3876 if mobj:
545cc85d 3877 info.update({
17322130 3878 'series': mobj.group(1),
3879 'season_number': int(mobj.group(2)),
3880 'episode_number': int(mobj.group(3)),
545cc85d 3881 })
17322130 3882 for tlb in (try_get(
3883 vpir,
3884 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3885 list) or []):
3886 tbr = tlb.get('toggleButtonRenderer') or {}
3887 for getter, regex in [(
3888 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3889 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3890 lambda x: x['accessibility'],
3891 lambda x: x['accessibilityData']['accessibilityData'],
3892 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3893 label = (try_get(tbr, getter, dict) or {}).get('label')
3894 if label:
3895 mobj = re.match(regex, label)
3896 if mobj:
3897 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3898 break
17322130 3899 sbr_tooltip = try_get(
3900 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3901 if sbr_tooltip:
3902 like_count, dislike_count = sbr_tooltip.split(' / ')
3903 info.update({
3904 'like_count': str_to_int(like_count),
3905 'dislike_count': str_to_int(dislike_count),
3906 })
3907 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3908 if vsir:
3909 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3910 info.update({
3911 'channel': self._get_text(vor, 'title'),
3912 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3913
3914 rows = try_get(
3915 vsir,
3916 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3917 list) or []
3918 multiple_songs = False
3919 for row in rows:
3920 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3921 multiple_songs = True
3922 break
3923 for row in rows:
3924 mrr = row.get('metadataRowRenderer') or {}
3925 mrr_title = mrr.get('title')
3926 if not mrr_title:
3927 continue
3928 mrr_title = self._get_text(mrr, 'title')
3929 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3930 if mrr_title == 'License':
3931 info['license'] = mrr_contents_text
3932 elif not multiple_songs:
3933 if mrr_title == 'Album':
3934 info['album'] = mrr_contents_text
3935 elif mrr_title == 'Artist':
3936 info['artist'] = mrr_contents_text
3937 elif mrr_title == 'Song':
3938 info['track'] = mrr_contents_text
545cc85d 3939
3940 fallbacks = {
3941 'channel': 'uploader',
3942 'channel_id': 'uploader_id',
3943 'channel_url': 'uploader_url',
3944 }
992f9a73 3945
17322130 3946 # The upload date for scheduled, live and past live streams / premieres in microformats
3947 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3948 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3949 upload_date = (
3950 unified_strdate(get_first(microformats, 'uploadDate'))
3951 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 3952 if not upload_date or (
3953 not info.get('is_live')
3954 and not info.get('was_live')
3955 and info.get('live_status') != 'is_upcoming'
3956 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
3957 ):
6e634cbe 3958 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3959 info['upload_date'] = upload_date
992f9a73 3960
545cc85d 3961 for to, frm in fallbacks.items():
3962 if not info.get(to):
3963 info[to] = info.get(frm)
3964
3965 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3966 v = info.get(s_k)
3967 if v:
3968 info[d_k] = v
b84071c0 3969
11f9be09 3970 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3971 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3972 is_membersonly = None
b28f8d24 3973 is_premium = None
c224251a
M
3974 if initial_data and is_private is not None:
3975 is_membersonly = False
b28f8d24 3976 is_premium = False
47193e02 3977 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3978 badge_labels = set()
3979 for content in contents:
3980 if not isinstance(content, dict):
3981 continue
3982 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3983 for badge_label in badge_labels:
3984 if badge_label.lower() == 'members only':
3985 is_membersonly = True
3986 elif badge_label.lower() == 'premium':
3987 is_premium = True
3988 elif badge_label.lower() == 'unlisted':
3989 is_unlisted = True
c224251a 3990
c224251a
M
3991 info['availability'] = self._availability(
3992 is_private=is_private,
b28f8d24 3993 needs_premium=is_premium,
c224251a
M
3994 needs_subscription=is_membersonly,
3995 needs_auth=info['age_limit'] >= 18,
3996 is_unlisted=None if is_private is None else is_unlisted)
3997
a2160aa4 3998 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3999
11f9be09 4000 self.mark_watched(video_id, player_responses)
d77ab8e2 4001
545cc85d 4002 return info
c5e8d7af 4003
a61fd4cf 4004
a6213a49 4005class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 4006
182bda88 4007 @staticmethod
4008 def passthrough_smuggled_data(func):
4009 def _smuggle(entries, smuggled_data):
4010 for entry in entries:
4011 # TODO: Convert URL to music.youtube instead.
4012 # Do we need to passthrough any other smuggled_data?
4013 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4014 yield entry
4015
4016 @functools.wraps(func)
4017 def wrapper(self, url):
4018 url, smuggled_data = unsmuggle_url(url, {})
4019 if self.is_music_url(url):
4020 smuggled_data['is_music_url'] = True
4021 info_dict = func(self, url, smuggled_data)
4022 if smuggled_data and info_dict.get('entries'):
4023 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4024 return info_dict
4025 return wrapper
4026
a6213a49 4027 def _extract_channel_id(self, webpage):
4028 channel_id = self._html_search_meta(
4029 'channelId', webpage, 'channel id', default=None)
4030 if channel_id:
4031 return channel_id
4032 channel_url = self._html_search_meta(
4033 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4034 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4035 'twitter:app:url:googleplay'), webpage, 'channel url')
4036 return self._search_regex(
4037 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4038 channel_url, 'channel id')
15f6397c 4039
8bdd16b4 4040 @staticmethod
cd7c66cf 4041 def _extract_basic_item_renderer(item):
4042 # Modified from _extract_grid_item_renderer
201c1459 4043 known_basic_renderers = (
a17526e4 4044 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4045 )
4046 for key, renderer in item.items():
201c1459 4047 if not isinstance(renderer, dict):
cd7c66cf 4048 continue
201c1459 4049 elif key in known_basic_renderers:
4050 return renderer
4051 elif key.startswith('grid') and key.endswith('Renderer'):
4052 return renderer
8bdd16b4 4053
8bdd16b4 4054 def _grid_entries(self, grid_renderer):
4055 for item in grid_renderer['items']:
4056 if not isinstance(item, dict):
39b62db1 4057 continue
cd7c66cf 4058 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4059 if not isinstance(renderer, dict):
4060 continue
052e1350 4061 title = self._get_text(renderer, 'title')
fe93e2c4 4062
8bdd16b4 4063 # playlist
4064 playlist_id = renderer.get('playlistId')
4065 if playlist_id:
4066 yield self.url_result(
4067 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4068 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4069 video_title=title)
201c1459 4070 continue
8bdd16b4 4071 # video
4072 video_id = renderer.get('videoId')
4073 if video_id:
4074 yield self._extract_video(renderer)
201c1459 4075 continue
8bdd16b4 4076 # channel
4077 channel_id = renderer.get('channelId')
4078 if channel_id:
8bdd16b4 4079 yield self.url_result(
4080 'https://www.youtube.com/channel/%s' % channel_id,
4081 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4082 continue
4083 # generic endpoint URL support
4084 ep_url = urljoin('https://www.youtube.com/', try_get(
4085 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4086 str))
201c1459 4087 if ep_url:
4088 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4089 if ie.suitable(ep_url):
4090 yield self.url_result(
4091 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4092 break
8bdd16b4 4093
16aa9ea4 4094 def _music_reponsive_list_entry(self, renderer):
4095 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4096 if video_id:
4097 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4098 ie=YoutubeIE.ie_key(), video_id=video_id)
4099 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4100 if playlist_id:
4101 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4102 if video_id:
4103 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4104 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4105 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4106 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4107 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4108 if browse_id:
4109 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4110 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4111
3d3dddc9 4112 def _shelf_entries_from_content(self, shelf_renderer):
4113 content = shelf_renderer.get('content')
4114 if not isinstance(content, dict):
8bdd16b4 4115 return
cd7c66cf 4116 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4117 if renderer:
4118 # TODO: add support for nested playlists so each shelf is processed
4119 # as separate playlist
4120 # TODO: this includes only first N items
86e5f3ed 4121 yield from self._grid_entries(renderer)
3d3dddc9 4122 renderer = content.get('horizontalListRenderer')
4123 if renderer:
4124 # TODO
4125 pass
8bdd16b4 4126
29f7c58a 4127 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4128 ep = try_get(
4129 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4130 str)
8bdd16b4 4131 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4132 if shelf_url:
29f7c58a 4133 # Skipping links to another channels, note that checking for
4134 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4135 # will not work
4136 if skip_channels and '/channels?' in shelf_url:
4137 return
052e1350 4138 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4139 yield self.url_result(shelf_url, video_title=title)
4140 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4141 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4142
8bdd16b4 4143 def _playlist_entries(self, video_list_renderer):
4144 for content in video_list_renderer['contents']:
4145 if not isinstance(content, dict):
4146 continue
4147 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4148 if not isinstance(renderer, dict):
4149 continue
4150 video_id = renderer.get('videoId')
4151 if not video_id:
4152 continue
4153 yield self._extract_video(renderer)
07aeced6 4154
3462ffa8 4155 def _rich_entries(self, rich_grid_renderer):
4156 renderer = try_get(
70d5c17b 4157 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4158 video_id = renderer.get('videoId')
4159 if not video_id:
4160 return
4161 yield self._extract_video(renderer)
4162
8bdd16b4 4163 def _video_entry(self, video_renderer):
4164 video_id = video_renderer.get('videoId')
4165 if video_id:
4166 return self._extract_video(video_renderer)
dacb3a86 4167
ad210f4f 4168 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4169 url = urljoin('https://youtube.com', traverse_obj(
4170 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4171 if url:
4172 return self.url_result(
4173 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4174
8bdd16b4 4175 def _post_thread_entries(self, post_thread_renderer):
4176 post_renderer = try_get(
4177 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4178 if not post_renderer:
4179 return
4180 # video attachment
4181 video_renderer = try_get(
895b0931 4182 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4183 video_id = video_renderer.get('videoId')
4184 if video_id:
4185 entry = self._extract_video(video_renderer)
8bdd16b4 4186 if entry:
4187 yield entry
895b0931 4188 # playlist attachment
4189 playlist_id = try_get(
14f25df2 4190 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4191 if playlist_id:
4192 yield self.url_result(
e28f1c0a 4193 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4194 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4195 # inline video links
4196 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4197 for run in runs:
4198 if not isinstance(run, dict):
4199 continue
4200 ep_url = try_get(
14f25df2 4201 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4202 if not ep_url:
4203 continue
4204 if not YoutubeIE.suitable(ep_url):
4205 continue
4206 ep_video_id = YoutubeIE._match_id(ep_url)
4207 if video_id == ep_video_id:
4208 continue
895b0931 4209 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4210
8bdd16b4 4211 def _post_thread_continuation_entries(self, post_thread_continuation):
4212 contents = post_thread_continuation.get('contents')
4213 if not isinstance(contents, list):
4214 return
4215 for content in contents:
4216 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4217 if isinstance(renderer, dict):
4218 yield from self._post_thread_entries(renderer)
8bdd16b4 4219 continue
6b0b0a28 4220 renderer = content.get('videoRenderer')
4221 if isinstance(renderer, dict):
4222 yield self._video_entry(renderer)
07aeced6 4223
39ed931e 4224 r''' # unused
4225 def _rich_grid_entries(self, contents):
4226 for content in contents:
4227 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4228 if video_renderer:
4229 entry = self._video_entry(video_renderer)
4230 if entry:
4231 yield entry
4232 '''
52efa4b3 4233
a6213a49 4234 def _extract_entries(self, parent_renderer, continuation_list):
4235 # continuation_list is modified in-place with continuation_list = [continuation_token]
4236 continuation_list[:] = [None]
4237 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4238 for content in contents:
4239 if not isinstance(content, dict):
4240 continue
16aa9ea4 4241 is_renderer = traverse_obj(
4242 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4243 expected_type=dict)
a6213a49 4244 if not is_renderer:
4245 renderer = content.get('richItemRenderer')
4246 if renderer:
4247 for entry in self._rich_entries(renderer):
4248 yield entry
4249 continuation_list[0] = self._extract_continuation(parent_renderer)
4250 continue
4251 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4252 for isr_content in isr_contents:
4253 if not isinstance(isr_content, dict):
8bdd16b4 4254 continue
69184e41 4255
a6213a49 4256 known_renderers = {
4257 'playlistVideoListRenderer': self._playlist_entries,
4258 'gridRenderer': self._grid_entries,
a17526e4 4259 'reelShelfRenderer': self._grid_entries,
4260 'shelfRenderer': self._shelf_entries,
16aa9ea4 4261 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4262 'backstagePostThreadRenderer': self._post_thread_entries,
4263 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4264 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4265 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4266 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4267 }
4268 for key, renderer in isr_content.items():
4269 if key not in known_renderers:
4270 continue
4271 for entry in known_renderers[key](renderer):
4272 if entry:
4273 yield entry
4274 continuation_list[0] = self._extract_continuation(renderer)
4275 break
70d5c17b 4276
4277 if not continuation_list[0]:
a6213a49 4278 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4279
a6213a49 4280 if not continuation_list[0]:
4281 continuation_list[0] = self._extract_continuation(parent_renderer)
4282
4283 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4284 continuation_list = [None]
4285 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4286 tab_content = try_get(tab, lambda x: x['content'], dict)
4287 if not tab_content:
4288 return
3462ffa8 4289 parent_renderer = (
29f7c58a 4290 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4291 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4292 yield from extract_entries(parent_renderer)
3462ffa8 4293 continuation = continuation_list[0]
d069eca7 4294
8bdd16b4 4295 for page_num in itertools.count(1):
4296 if not continuation:
4297 break
99e9e001 4298 headers = self.generate_api_headers(
4299 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4300 response = self._extract_response(
86e5f3ed 4301 item_id=f'{item_id} page {page_num}',
fe93e2c4 4302 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4303 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4304
4305 if not response:
8bdd16b4 4306 break
ac56cf38 4307 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4308 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4309 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4310
69184e41 4311 known_continuation_renderers = {
4312 'playlistVideoListContinuation': self._playlist_entries,
4313 'gridContinuation': self._grid_entries,
4314 'itemSectionContinuation': self._post_thread_continuation_entries,
4315 'sectionListContinuation': extract_entries, # for feeds
4316 }
8bdd16b4 4317 continuation_contents = try_get(
69184e41 4318 response, lambda x: x['continuationContents'], dict) or {}
4319 continuation_renderer = None
4320 for key, value in continuation_contents.items():
4321 if key not in known_continuation_renderers:
3462ffa8 4322 continue
69184e41 4323 continuation_renderer = value
4324 continuation_list = [None]
86e5f3ed 4325 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4326 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4327 break
4328 if continuation_renderer:
4329 continue
c5e8d7af 4330
a1b535bd 4331 known_renderers = {
e4b98809 4332 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4333 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4334 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4335 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4336 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4337 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4338 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4339 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4340 }
cce889b9 4341 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4342 continuation_items = try_get(
cce889b9 4343 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4344 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4345 video_items_renderer = None
4346 for key, value in continuation_item.items():
4347 if key not in known_renderers:
8bdd16b4 4348 continue
a1b535bd 4349 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4350 continuation_list = [None]
86e5f3ed 4351 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4352 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4353 break
4354 if video_items_renderer:
4355 continue
8bdd16b4 4356 break
9558dcec 4357
8bdd16b4 4358 @staticmethod
7c219ea6 4359 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4360 for tab in tabs:
cd684175 4361 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4362 if renderer.get('selected') is True:
4363 return renderer
2b3c2546 4364 else:
7c219ea6 4365 if fatal:
4366 raise ExtractorError('Unable to find selected tab')
b82f815f 4367
61d3665d 4368 def _extract_uploader(self, data):
8bdd16b4 4369 uploader = {}
61d3665d 4370 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4371 owner = try_get(
4372 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4373 if owner:
61d3665d 4374 owner_text = owner.get('text')
4375 uploader['uploader'] = self._search_regex(
4376 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4377 uploader['uploader_id'] = try_get(
14f25df2 4378 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4379 uploader['uploader_url'] = urljoin(
4380 'https://www.youtube.com/',
14f25df2 4381 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4382 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4383
ac56cf38 4384 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4385 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4386 tags = []
b60419c5 4387
8bdd16b4 4388 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4389 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4390 renderer = try_get(
4391 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4392 if renderer:
b60419c5 4393 channel_name = renderer.get('title')
4394 channel_url = renderer.get('channelUrl')
4395 channel_id = renderer.get('externalId')
39ed931e 4396 else:
64c0d954 4397 renderer = try_get(
4398 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4399
8bdd16b4 4400 if renderer:
4401 title = renderer.get('title')
ecc97af3 4402 description = renderer.get('description', '')
b60419c5 4403 playlist_id = channel_id
4404 tags = renderer.get('keywords', '').split()
b60419c5 4405
301d07fc 4406 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4407 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4408 def _get_uncropped(url):
4409 return url_or_none((url or '').split('=')[0] + '=s0')
4410
4411 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4412 if avatar_thumbnails:
4413 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4414 if uncropped_avatar:
4415 avatar_thumbnails.append({
4416 'url': uncropped_avatar,
4417 'id': 'avatar_uncropped',
4418 'preference': 1
4419 })
4420
4421 channel_banners = self._extract_thumbnails(
4422 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4423 for banner in channel_banners:
4424 banner['preference'] = -10
4425
4426 if channel_banners:
4427 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4428 if uncropped_banner:
4429 channel_banners.append({
4430 'url': uncropped_banner,
4431 'id': 'banner_uncropped',
4432 'preference': -5
4433 })
4434
4435 primary_thumbnails = self._extract_thumbnails(
a17526e4 4436 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4437
3462ffa8 4438 if playlist_id is None:
70d5c17b 4439 playlist_id = item_id
f0d785d3 4440
4441 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4442 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4443 if title is None:
f0d785d3 4444 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4445 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4446 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4447
b60419c5 4448 metadata = {
4449 'playlist_id': playlist_id,
4450 'playlist_title': title,
4451 'playlist_description': description,
4452 'uploader': channel_name,
4453 'uploader_id': channel_id,
4454 'uploader_url': channel_url,
301d07fc 4455 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4456 'tags': tags,
f0d785d3 4457 'view_count': self._get_count(playlist_stats, 1),
4458 'availability': self._extract_availability(data),
4459 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4460 'playlist_count': self._get_count(playlist_stats, 0),
4461 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4462 }
4463 if not channel_id:
4464 metadata.update(self._extract_uploader(data))
4465 metadata.update({
4466 'channel': metadata['uploader'],
4467 'channel_id': metadata['uploader_id'],
4468 'channel_url': metadata['uploader_url']})
4469 return self.playlist_result(
d069eca7 4470 self._entries(
ac56cf38 4471 selected_tab, playlist_id, ytcfg,
4472 self._extract_account_syncid(ytcfg, data),
4473 self._extract_visitor_data(data, ytcfg)),
b60419c5 4474 **metadata)
73c4ac2c 4475
6e634cbe 4476 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4477 first_id = last_id = response = None
2be71994 4478 for page_num in itertools.count(1):
cd7c66cf 4479 videos = list(self._playlist_entries(playlist))
4480 if not videos:
4481 return
2be71994 4482 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4483 if start >= len(videos):
4484 return
24146491 4485 yield from videos[start:]
2be71994 4486 first_id = first_id or videos[0]['id']
4487 last_id = videos[-1]['id']
79360d99 4488 watch_endpoint = try_get(
4489 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4490 headers = self.generate_api_headers(
4491 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4492 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4493 query = {
4494 'playlistId': playlist_id,
4495 'videoId': watch_endpoint.get('videoId') or last_id,
4496 'index': watch_endpoint.get('index') or len(videos),
4497 'params': watch_endpoint.get('params') or 'OAE%3D'
4498 }
4499 response = self._extract_response(
4500 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4501 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4502 check_get_keys='contents'
4503 )
cd7c66cf 4504 playlist = try_get(
79360d99 4505 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4506
ac56cf38 4507 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4508 title = playlist.get('title') or try_get(
14f25df2 4509 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4510 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4511
4512 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4513 playlist_url = urljoin(url, try_get(
4514 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4515 str))
6e634cbe 4516
4517 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4518 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4519 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4520
4521 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4522 return self.url_result(
4523 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4524 video_title=title)
cd7c66cf 4525
8bdd16b4 4526 return self.playlist_result(
6e634cbe 4527 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4528 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4529
47193e02 4530 def _extract_availability(self, data):
4531 """
4532 Gets the availability of a given playlist/tab.
4533 Note: Unless YouTube tells us explicitly, we do not assume it is public
4534 @param data: response
4535 """
4536 is_private = is_unlisted = None
4537 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4538 badge_labels = self._extract_badges(renderer)
4539
4540 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4541 privacy_dropdown_entries = try_get(
4542 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4543 for renderer_dict in privacy_dropdown_entries:
4544 is_selected = try_get(
4545 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4546 if not is_selected:
4547 continue
052e1350 4548 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4549 if label:
4550 badge_labels.add(label.lower())
4551 break
4552
4553 for badge_label in badge_labels:
4554 if badge_label == 'unlisted':
4555 is_unlisted = True
4556 elif badge_label == 'private':
4557 is_private = True
4558 elif badge_label == 'public':
4559 is_unlisted = is_private = False
4560 return self._availability(is_private, False, False, False, is_unlisted)
4561
4562 @staticmethod
4563 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4564 sidebar_renderer = try_get(
4565 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4566 for item in sidebar_renderer:
4567 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4568 if renderer:
4569 return renderer
4570
ac56cf38 4571 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4572 """
4573 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4574 """
5d342002 4575 browse_id = params = None
47193e02 4576 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4577 if not renderer:
4578 return
4579 menu_renderer = try_get(
4580 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4581 for menu_item in menu_renderer:
4582 if not isinstance(menu_item, dict):
358de58c 4583 continue
47193e02 4584 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4585 text = try_get(
14f25df2 4586 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4587 if not text or text.lower() != 'show unavailable videos':
4588 continue
4589 browse_endpoint = try_get(
4590 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4591 browse_id = browse_endpoint.get('browseId')
4592 params = browse_endpoint.get('params')
4593 break
5d342002 4594
11f9be09 4595 headers = self.generate_api_headers(
99e9e001 4596 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4597 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4598 query = {
4599 'params': params or 'wgYCCAA=',
4600 'browseId': browse_id or 'VL%s' % item_id
4601 }
4602 return self._extract_response(
4603 item_id=item_id, headers=headers, query=query,
fe93e2c4 4604 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4605 note='Downloading API JSON with unavailable videos')
358de58c 4606
2762dbb1 4607 @functools.cached_property
a25bca9f 4608 def skip_webpage(self):
4609 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4610
ac56cf38 4611 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4612 webpage, data = None, None
4613 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4614 try:
be5c1ae8 4615 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4616 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4617 except ExtractorError as e:
4618 if isinstance(e.cause, network_exceptions):
14f25df2 4619 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4620 retry.error = e
4621 continue
4622 self._error_or_warning(e, fatal=fatal)
14fdfea9 4623 break
ac56cf38 4624
be5c1ae8 4625 try:
4626 self._extract_and_report_alerts(data)
4627 except ExtractorError as e:
4628 self._error_or_warning(e, fatal=fatal)
4629 break
ac56cf38 4630
be5c1ae8 4631 # Sometimes youtube returns a webpage with incomplete ytInitialData
4632 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4633 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4634 retry.error = ExtractorError('Incomplete yt initial data received')
4635 continue
ac56cf38 4636
cd7c66cf 4637 return webpage, data
4638
a25bca9f 4639 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4640 """Use if failed to extract ytcfg (and data) from initial webpage"""
4641 if not ytcfg and self.is_authenticated:
4642 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4643 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4644 raise ExtractorError(
4645 f'{msg}. If you are not downloading private content, or '
4646 'your cookies are only for the first account and channel,'
4647 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4648 expected=True)
4649 self.report_warning(msg, only_once=True)
4650
ac56cf38 4651 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4652 data = None
a25bca9f 4653 if not self.skip_webpage:
ac56cf38 4654 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4655 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4656 # Reject webpage data if redirected to home page without explicitly requesting
4657 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4658 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4659 if (url != 'https://www.youtube.com/feed/recommended'
4660 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4661 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4662 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4663 if fatal:
4664 raise ExtractorError(msg, expected=True)
4665 self.report_warning(msg, only_once=True)
ac56cf38 4666 if not data:
a25bca9f 4667 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4668 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4669 return data, ytcfg
4670
4671 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4672 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4673 resolve_response = self._extract_response(
4674 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4675 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4676 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4677 for ep_key, ep in endpoints.items():
4678 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4679 if params:
4680 return self._extract_response(
4681 item_id=item_id, query=params, ep=ep, headers=headers,
4682 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4683 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4684 err_note = 'Failed to resolve url (does the playlist exist?)'
4685 if fatal:
4686 raise ExtractorError(err_note, expected=True)
4687 self.report_warning(err_note, item_id)
4688
a6213a49 4689 _SEARCH_PARAMS = None
4690
af5c1c55 4691 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4692 data = {'query': query}
4693 if params is NO_DEFAULT:
4694 params = self._SEARCH_PARAMS
4695 if params:
4696 data['params'] = params
16aa9ea4 4697
4698 content_keys = (
4699 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4700 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4701 # ytmusic search
4702 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4703 ('continuationContents', ),
4704 )
a25bca9f 4705 display_id = f'query "{query}"'
86e5f3ed 4706 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4707 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4708 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4709
a61fd4cf 4710 continuation_list = [None]
a25bca9f 4711 search = None
a6213a49 4712 for page_num in itertools.count(1):
a61fd4cf 4713 data.update(continuation_list[0] or {})
a25bca9f 4714 headers = self.generate_api_headers(
4715 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4716 search = self._extract_response(
a25bca9f 4717 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4718 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4719 slr_contents = traverse_obj(search, *content_keys)
4720 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4721 if not continuation_list[0]:
a6213a49 4722 break
4723
4724
4725class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4726 IE_DESC = 'YouTube Tabs'
4727 _VALID_URL = r'''(?x:
4728 https?://
4729 (?:\w+\.)?
4730 (?:
4731 youtube(?:kids)?\.com|
4732 %(invidious)s
4733 )/
4734 (?:
4735 (?P<channel_type>channel|c|user|browse)/|
4736 (?P<not_channel>
4737 feed/|hashtag/|
4738 (?:playlist|watch)\?.*?\blist=
4739 )|
4740 (?!(?:%(reserved_names)s)\b) # Direct URLs
4741 )
4742 (?P<id>[^/?\#&]+)
4743 )''' % {
4744 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4745 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4746 }
4747 IE_NAME = 'youtube:tab'
4748
4749 _TESTS = [{
4750 'note': 'playlists, multipage',
4751 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4752 'playlist_mincount': 94,
4753 'info_dict': {
4754 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4755 'title': 'Igor Kleiner - Playlists',
a6213a49 4756 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4757 'uploader': 'Igor Kleiner',
a6213a49 4758 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4759 'channel': 'Igor Kleiner',
4760 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4761 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4762 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4763 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4764 'channel_follower_count': int
a6213a49 4765 },
4766 }, {
4767 'note': 'playlists, multipage, different order',
4768 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4769 'playlist_mincount': 94,
4770 'info_dict': {
4771 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4772 'title': 'Igor Kleiner - Playlists',
a6213a49 4773 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4774 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4775 'uploader': 'Igor Kleiner',
4776 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4777 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4778 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4779 'channel': 'Igor Kleiner',
4780 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4781 'channel_follower_count': int
a6213a49 4782 },
4783 }, {
4784 'note': 'playlists, series',
4785 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4786 'playlist_mincount': 5,
4787 'info_dict': {
4788 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4789 'title': '3Blue1Brown - Playlists',
4790 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4791 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4792 'uploader': '3Blue1Brown',
976ae3ea 4793 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4794 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4795 'channel': '3Blue1Brown',
4796 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4797 'tags': ['Mathematics'],
6c73052c 4798 'channel_follower_count': int
a6213a49 4799 },
4800 }, {
4801 'note': 'playlists, singlepage',
4802 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4803 'playlist_mincount': 4,
4804 'info_dict': {
4805 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4806 'title': 'ThirstForScience - Playlists',
4807 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4808 'uploader': 'ThirstForScience',
4809 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4810 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4811 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4812 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4813 'tags': 'count:13',
4814 'channel': 'ThirstForScience',
6c73052c 4815 'channel_follower_count': int
a6213a49 4816 }
4817 }, {
4818 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4819 'only_matching': True,
4820 }, {
4821 'note': 'basic, single video playlist',
4822 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4823 'info_dict': {
4824 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4825 'uploader': 'Sergey M.',
4826 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4827 'title': 'youtube-dl public playlist',
976ae3ea 4828 'description': '',
4829 'tags': [],
4830 'view_count': int,
4831 'modified_date': '20201130',
4832 'channel': 'Sergey M.',
4833 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4834 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4835 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4836 },
4837 'playlist_count': 1,
4838 }, {
4839 'note': 'empty playlist',
4840 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4841 'info_dict': {
4842 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4843 'uploader': 'Sergey M.',
4844 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4845 'title': 'youtube-dl empty playlist',
976ae3ea 4846 'tags': [],
4847 'channel': 'Sergey M.',
4848 'description': '',
4849 'modified_date': '20160902',
4850 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4851 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4852 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4853 },
4854 'playlist_count': 0,
4855 }, {
4856 'note': 'Home tab',
4857 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4858 'info_dict': {
4859 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4860 'title': 'lex will - Home',
4861 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4862 'uploader': 'lex will',
4863 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4864 'channel': 'lex will',
4865 'tags': ['bible', 'history', 'prophesy'],
4866 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4867 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4868 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4869 'channel_follower_count': int
a6213a49 4870 },
4871 'playlist_mincount': 2,
4872 }, {
4873 'note': 'Videos tab',
4874 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4875 'info_dict': {
4876 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4877 'title': 'lex will - Videos',
4878 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4879 'uploader': 'lex will',
4880 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4881 'tags': ['bible', 'history', 'prophesy'],
4882 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4883 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4884 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4885 'channel': 'lex will',
6c73052c 4886 'channel_follower_count': int
a6213a49 4887 },
4888 'playlist_mincount': 975,
4889 }, {
4890 'note': 'Videos tab, sorted by popular',
4891 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4892 'info_dict': {
4893 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4894 'title': 'lex will - Videos',
4895 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4896 'uploader': 'lex will',
4897 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4898 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4899 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4900 'channel': 'lex will',
4901 'tags': ['bible', 'history', 'prophesy'],
4902 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4903 'channel_follower_count': int
a6213a49 4904 },
4905 'playlist_mincount': 199,
4906 }, {
4907 'note': 'Playlists tab',
4908 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4909 'info_dict': {
4910 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4911 'title': 'lex will - Playlists',
4912 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4913 'uploader': 'lex will',
4914 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4915 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4916 'channel': 'lex will',
4917 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4918 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4919 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4920 'channel_follower_count': int
a6213a49 4921 },
4922 'playlist_mincount': 17,
4923 }, {
4924 'note': 'Community tab',
4925 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4926 'info_dict': {
4927 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4928 'title': 'lex will - Community',
4929 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4930 'uploader': 'lex will',
4931 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4932 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4933 'channel': 'lex will',
4934 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4935 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4936 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4937 'channel_follower_count': int
a6213a49 4938 },
4939 'playlist_mincount': 18,
4940 }, {
4941 'note': 'Channels tab',
4942 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4943 'info_dict': {
4944 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4945 'title': 'lex will - Channels',
4946 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4947 'uploader': 'lex will',
4948 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4949 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4950 'channel': 'lex will',
4951 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4952 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4953 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4954 'channel_follower_count': int
a6213a49 4955 },
4956 'playlist_mincount': 12,
4957 }, {
4958 'note': 'Search tab',
4959 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4960 'playlist_mincount': 40,
4961 'info_dict': {
4962 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4963 'title': '3Blue1Brown - Search - linear algebra',
4964 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4965 'uploader': '3Blue1Brown',
4966 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4967 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4968 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4969 'tags': ['Mathematics'],
4970 'channel': '3Blue1Brown',
4971 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4972 'channel_follower_count': int
a6213a49 4973 },
4974 }, {
4975 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4976 'only_matching': True,
4977 }, {
4978 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4979 'only_matching': True,
4980 }, {
4981 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4982 'only_matching': True,
4983 }, {
4984 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4985 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4986 'info_dict': {
4987 'title': '29C3: Not my department',
4988 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4989 'uploader': 'Christiaan008',
4990 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4991 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4992 'tags': [],
4993 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4994 'view_count': int,
4995 'modified_date': '20150605',
4996 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4997 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4998 'channel': 'Christiaan008',
a6213a49 4999 },
5000 'playlist_count': 96,
5001 }, {
5002 'note': 'Large playlist',
5003 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5004 'info_dict': {
5005 'title': 'Uploads from Cauchemar',
5006 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5007 'uploader': 'Cauchemar',
5008 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5009 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5010 'tags': [],
5011 'modified_date': r're:\d{8}',
5012 'channel': 'Cauchemar',
5013 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5014 'view_count': int,
5015 'description': '',
5016 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 5017 },
5018 'playlist_mincount': 1123,
976ae3ea 5019 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5020 }, {
5021 'note': 'even larger playlist, 8832 videos',
5022 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5023 'only_matching': True,
5024 }, {
5025 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5026 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5027 'info_dict': {
5028 'title': 'Uploads from Interstellar Movie',
5029 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5030 'uploader': 'Interstellar Movie',
5031 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5032 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5033 'tags': [],
5034 'view_count': int,
5035 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5036 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5037 'channel': 'Interstellar Movie',
5038 'description': '',
5039 'modified_date': r're:\d{8}',
a6213a49 5040 },
5041 'playlist_mincount': 21,
5042 }, {
5043 'note': 'Playlist with "show unavailable videos" button',
5044 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5045 'info_dict': {
5046 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5047 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5048 'uploader': 'Phim Siêu Nhân Nhật Bản',
5049 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5050 'view_count': int,
5051 'channel': 'Phim Siêu Nhân Nhật Bản',
5052 'tags': [],
5053 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5054 'description': '',
5055 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5056 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5057 'modified_date': r're:\d{8}',
a6213a49 5058 },
5059 'playlist_mincount': 200,
976ae3ea 5060 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5061 }, {
5062 'note': 'Playlist with unavailable videos in page 7',
5063 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5064 'info_dict': {
5065 'title': 'Uploads from BlankTV',
5066 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5067 'uploader': 'BlankTV',
5068 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5069 'channel': 'BlankTV',
5070 'channel_url': 'https://www.youtube.com/c/blanktv',
5071 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5072 'view_count': int,
5073 'tags': [],
5074 'uploader_url': 'https://www.youtube.com/c/blanktv',
5075 'modified_date': r're:\d{8}',
5076 'description': '',
a6213a49 5077 },
5078 'playlist_mincount': 1000,
976ae3ea 5079 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5080 }, {
5081 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5082 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5083 'info_dict': {
5084 'title': 'Data Analysis with Dr Mike Pound',
5085 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5086 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5087 'uploader': 'Computerphile',
5088 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5089 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5090 'tags': [],
5091 'view_count': int,
5092 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5093 'channel_url': 'https://www.youtube.com/user/Computerphile',
5094 'channel': 'Computerphile',
a6213a49 5095 },
5096 'playlist_mincount': 11,
5097 }, {
5098 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5099 'only_matching': True,
5100 }, {
5101 'note': 'Playlist URL that does not actually serve a playlist',
5102 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5103 'info_dict': {
5104 'id': 'FqZTN594JQw',
5105 'ext': 'webm',
5106 'title': "Smiley's People 01 detective, Adventure Series, Action",
5107 'uploader': 'STREEM',
5108 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5109 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5110 'upload_date': '20150526',
5111 'license': 'Standard YouTube License',
5112 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5113 'categories': ['People & Blogs'],
5114 'tags': list,
5115 'view_count': int,
5116 'like_count': int,
a6213a49 5117 },
5118 'params': {
5119 'skip_download': True,
5120 },
5121 'skip': 'This video is not available.',
5122 'add_ie': [YoutubeIE.ie_key()],
5123 }, {
5124 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5125 'only_matching': True,
5126 }, {
5127 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5128 'only_matching': True,
5129 }, {
5130 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5131 'info_dict': {
12a1b225 5132 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5133 'ext': 'mp4',
976ae3ea 5134 'title': str,
a6213a49 5135 'uploader': 'Sky News',
5136 'uploader_id': 'skynews',
5137 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5138 'upload_date': r're:\d{8}',
976ae3ea 5139 'description': str,
a6213a49 5140 'categories': ['News & Politics'],
5141 'tags': list,
5142 'like_count': int,
6c73052c 5143 'release_timestamp': 1642502819,
976ae3ea 5144 'channel': 'Sky News',
5145 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5146 'age_limit': 0,
5147 'view_count': int,
6c73052c 5148 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5149 'playable_in_embed': True,
6c73052c 5150 'release_date': '20220118',
976ae3ea 5151 'availability': 'public',
5152 'live_status': 'is_live',
5153 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5154 'channel_follower_count': int
a6213a49 5155 },
5156 'params': {
5157 'skip_download': True,
5158 },
976ae3ea 5159 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5160 }, {
5161 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5162 'info_dict': {
5163 'id': 'a48o2S1cPoo',
5164 'ext': 'mp4',
5165 'title': 'The Young Turks - Live Main Show',
5166 'uploader': 'The Young Turks',
5167 'uploader_id': 'TheYoungTurks',
5168 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5169 'upload_date': '20150715',
5170 'license': 'Standard YouTube License',
5171 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5172 'categories': ['News & Politics'],
5173 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5174 'like_count': int,
a6213a49 5175 },
5176 'params': {
5177 'skip_download': True,
5178 },
5179 'only_matching': True,
5180 }, {
5181 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5182 'only_matching': True,
5183 }, {
5184 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5185 'only_matching': True,
5186 }, {
5187 'note': 'A channel that is not live. Should raise error',
5188 'url': 'https://www.youtube.com/user/numberphile/live',
5189 'only_matching': True,
5190 }, {
5191 'url': 'https://www.youtube.com/feed/trending',
5192 'only_matching': True,
5193 }, {
5194 'url': 'https://www.youtube.com/feed/library',
5195 'only_matching': True,
5196 }, {
5197 'url': 'https://www.youtube.com/feed/history',
5198 'only_matching': True,
5199 }, {
5200 'url': 'https://www.youtube.com/feed/subscriptions',
5201 'only_matching': True,
5202 }, {
5203 'url': 'https://www.youtube.com/feed/watch_later',
5204 'only_matching': True,
5205 }, {
5206 'note': 'Recommended - redirects to home page.',
5207 'url': 'https://www.youtube.com/feed/recommended',
5208 'only_matching': True,
5209 }, {
5210 'note': 'inline playlist with not always working continuations',
5211 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5212 'only_matching': True,
5213 }, {
5214 'url': 'https://www.youtube.com/course',
5215 'only_matching': True,
5216 }, {
5217 'url': 'https://www.youtube.com/zsecurity',
5218 'only_matching': True,
5219 }, {
5220 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5221 'only_matching': True,
5222 }, {
5223 'url': 'https://www.youtube.com/TheYoungTurks/live',
5224 'only_matching': True,
5225 }, {
5226 'url': 'https://www.youtube.com/hashtag/cctv9',
5227 'info_dict': {
5228 'id': 'cctv9',
5229 'title': '#cctv9',
976ae3ea 5230 'tags': [],
a6213a49 5231 },
5232 'playlist_mincount': 350,
5233 }, {
5234 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5235 'only_matching': True,
5236 }, {
5237 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5238 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5239 'only_matching': True
5240 }, {
5241 'note': '/browse/ should redirect to /channel/',
5242 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5243 'only_matching': True
5244 }, {
5245 'note': 'VLPL, should redirect to playlist?list=PL...',
5246 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5247 'info_dict': {
5248 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5249 'uploader': 'NoCopyrightSounds',
5250 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5251 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5252 'title': 'NCS : All Releases 💿',
976ae3ea 5253 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5254 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5255 'modified_date': r're:\d{8}',
5256 'view_count': int,
5257 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5258 'tags': [],
5259 'channel': 'NoCopyrightSounds',
a6213a49 5260 },
5261 'playlist_mincount': 166,
976ae3ea 5262 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5263 }, {
5264 'note': 'Topic, should redirect to playlist?list=UU...',
5265 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5266 'info_dict': {
5267 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5268 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5269 'title': 'Uploads from Royalty Free Music - Topic',
5270 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5271 'tags': [],
5272 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5273 'channel': 'Royalty Free Music - Topic',
5274 'view_count': int,
5275 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5276 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5277 'modified_date': r're:\d{8}',
5278 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5279 'description': '',
a6213a49 5280 },
5281 'expected_warnings': [
a6213a49 5282 'The URL does not have a videos tab',
976ae3ea 5283 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5284 ],
5285 'playlist_mincount': 101,
5286 }, {
5287 'note': 'Topic without a UU playlist',
5288 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5289 'info_dict': {
5290 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5291 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5292 'tags': [],
a6213a49 5293 },
5294 'expected_warnings': [
976ae3ea 5295 'the playlist redirect gave error',
a6213a49 5296 ],
5297 'playlist_mincount': 9,
5298 }, {
5299 'note': 'Youtube music Album',
5300 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5301 'info_dict': {
5302 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5303 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5304 'tags': [],
5305 'view_count': int,
5306 'description': '',
5307 'availability': 'unlisted',
5308 'modified_date': r're:\d{8}',
a6213a49 5309 },
5310 'playlist_count': 50,
5311 }, {
5312 'note': 'unlisted single video playlist',
5313 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5314 'info_dict': {
5315 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5316 'uploader': 'colethedj',
5317 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5318 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5319 'availability': 'unlisted',
5320 'tags': [],
12a1b225 5321 'modified_date': '20220418',
976ae3ea 5322 'channel': 'colethedj',
5323 'view_count': int,
5324 'description': '',
5325 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5326 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5327 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5328 },
5329 'playlist_count': 1,
5330 }, {
5331 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5332 'url': 'https://www.youtube.com/feed/recommended',
5333 'info_dict': {
5334 'id': 'recommended',
5335 'title': 'recommended',
6c73052c 5336 'tags': [],
a6213a49 5337 },
5338 'playlist_mincount': 50,
5339 'params': {
5340 'skip_download': True,
5341 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5342 },
5343 }, {
5344 'note': 'API Fallback: /videos tab, sorted by oldest first',
5345 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5346 'info_dict': {
5347 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5348 'title': 'Cody\'sLab - Videos',
5349 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5350 'uploader': 'Cody\'sLab',
5351 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5352 'channel': 'Cody\'sLab',
5353 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5354 'tags': [],
5355 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5356 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5357 'channel_follower_count': int
a6213a49 5358 },
5359 'playlist_mincount': 650,
5360 'params': {
5361 'skip_download': True,
5362 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5363 },
5364 }, {
5365 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5366 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5367 'info_dict': {
5368 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5369 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5370 'title': 'Uploads from Royalty Free Music - Topic',
5371 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5372 'modified_date': r're:\d{8}',
5373 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5374 'description': '',
5375 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5376 'tags': [],
5377 'channel': 'Royalty Free Music - Topic',
5378 'view_count': int,
5379 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5380 },
5381 'expected_warnings': [
976ae3ea 5382 'does not have a videos tab',
5383 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5384 ],
5385 'playlist_mincount': 101,
5386 'params': {
5387 'skip_download': True,
5388 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5389 },
7c219ea6 5390 }, {
5391 'note': 'non-standard redirect to regional channel',
5392 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5393 'only_matching': True
61d3665d 5394 }, {
5395 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5396 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5397 'info_dict': {
5398 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5399 'modified_date': '20220407',
5400 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5401 'tags': [],
5402 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5403 'uploader': 'pukkandan',
5404 'availability': 'unlisted',
5405 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5406 'channel': 'pukkandan',
5407 'description': 'Test for collaborative playlist',
5408 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5409 'view_count': int,
61d3665d 5410 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5411 },
5412 'playlist_mincount': 2
a6213a49 5413 }]
5414
5415 @classmethod
5416 def suitable(cls, url):
86e5f3ed 5417 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5418
64f36541 5419 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5420
182bda88 5421 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5422 def _real_extract(self, url, smuggled_data):
cd7c66cf 5423 item_id = self._match_id(url)
14f25df2 5424 url = urllib.parse.urlunparse(
5425 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5426 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5427
fe03a6cd 5428 def get_mobj(url):
37e57a9f 5429 mobj = self._URL_RE.match(url).groupdict()
07cce701 5430 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5431 return mobj
5432
37e57a9f 5433 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5434 # Youtube returns incomplete data if tabname is not lower case
5435 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5436 if is_channel:
5437 if smuggled_data.get('is_music_url'):
37e57a9f 5438 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5439 item_id = item_id[2:]
37e57a9f 5440 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5441 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5442 mdata = self._extract_tab_endpoint(
37e57a9f 5443 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5444 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5445 get_all=False, expected_type=str)
ac56cf38 5446 if not murl:
37e57a9f 5447 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5448 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5449 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5450 pre = f'https://www.youtube.com/channel/{item_id}'
5451
64f36541 5452 original_tab_name = tab
fe03a6cd 5453 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5454 # Home URLs should redirect to /videos/
37e57a9f 5455 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5456 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5457 tab = '/videos'
5458
5459 url = ''.join((pre, tab, post))
5460 mobj = get_mobj(url)
cd7c66cf 5461
5462 # Handle both video/playlist URLs
201c1459 5463 qs = parse_qs(url)
86e5f3ed 5464 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5465
fe03a6cd 5466 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5467 if not playlist_id:
fe03a6cd 5468 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5469 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5470 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5471 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5472 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5473 mobj = get_mobj(url)
cd7c66cf 5474
5475 if video_id and playlist_id:
a06916d9 5476 if self.get_param('noplaylist'):
37e57a9f 5477 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5478 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5479 ie=YoutubeIE.ie_key(), video_id=video_id)
5480 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5481
ac56cf38 5482 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5483
7c219ea6 5484 # YouTube may provide a non-standard redirect to the regional channel
5485 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5486 redirect_url = traverse_obj(
5487 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5488 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5489 redirect_url = ''.join((
5490 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5491 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5492 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5493
37e57a9f 5494 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5495 if tabs:
5496 selected_tab = self._extract_selected_tab(tabs)
64f36541 5497 selected_tab_name = selected_tab.get('title', '').lower()
5498 if selected_tab_name == 'home':
5499 selected_tab_name = 'featured'
5500 requested_tab_name = mobj['tab'][1:]
09f1580e 5501 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5502 if requested_tab_name == 'live': # Live tab should have redirected to the video
5503 raise UserNotLive(video_id=mobj['id'])
64f36541 5504 if requested_tab_name not in ('', selected_tab_name):
5505 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5506 if not original_tab_name:
5507 if item_id[:2] == 'UC':
5508 # Topic channels don't have /videos. Use the equivalent playlist instead
5509 pl_id = f'UU{item_id[2:]}'
5510 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5511 try:
5512 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5513 except ExtractorError:
5514 redirect_warning += ' and the playlist redirect gave error'
5515 else:
5516 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5517 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5518 if selected_tab_name and selected_tab_name != requested_tab_name:
5519 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5520 else:
5521 raise ExtractorError(redirect_warning, expected=True)
18db7548 5522
37e57a9f 5523 if redirect_warning:
64f36541 5524 self.to_screen(redirect_warning)
37e57a9f 5525 self.write_debug(f'Final URL: {url}')
18db7548 5526
358de58c 5527 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5528 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5529 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5530 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5531 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5532 if tabs:
ac56cf38 5533 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5534
37e57a9f 5535 playlist = traverse_obj(
5536 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5537 if playlist:
ac56cf38 5538 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5539
37e57a9f 5540 video_id = traverse_obj(
5541 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5542 if video_id:
09f1580e 5543 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5544 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5545 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5546 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5547
8bdd16b4 5548 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5549
c5e8d7af 5550
8bdd16b4 5551class YoutubePlaylistIE(InfoExtractor):
96565c7e 5552 IE_DESC = 'YouTube playlists'
8bdd16b4 5553 _VALID_URL = r'''(?x)(?:
5554 (?:https?://)?
5555 (?:\w+\.)?
5556 (?:
5557 (?:
5558 youtube(?:kids)?\.com|
d9190e44 5559 %(invidious)s
8bdd16b4 5560 )
5561 /.*?\?.*?\blist=
5562 )?
5563 (?P<id>%(playlist_id)s)
d9190e44
RH
5564 )''' % {
5565 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5566 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5567 }
8bdd16b4 5568 IE_NAME = 'youtube:playlist'
cdc628a4 5569 _TESTS = [{
8bdd16b4 5570 'note': 'issue #673',
5571 'url': 'PLBB231211A4F62143',
cdc628a4 5572 'info_dict': {
8bdd16b4 5573 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5574 'id': 'PLBB231211A4F62143',
976ae3ea 5575 'uploader': 'Wickman',
8bdd16b4 5576 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5577 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5578 'view_count': int,
5579 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5580 'modified_date': r're:\d{8}',
5581 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5582 'channel': 'Wickman',
5583 'tags': [],
5584 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5585 },
5586 'playlist_mincount': 29,
5587 }, {
5588 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5589 'info_dict': {
5590 'title': 'YDL_safe_search',
5591 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5592 },
5593 'playlist_count': 2,
5594 'skip': 'This playlist is private',
9558dcec 5595 }, {
8bdd16b4 5596 'note': 'embedded',
5597 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5598 'playlist_count': 4,
9558dcec 5599 'info_dict': {
8bdd16b4 5600 'title': 'JODA15',
5601 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5602 'uploader': 'milan',
5603 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5604 'description': '',
5605 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5606 'tags': [],
5607 'modified_date': '20140919',
5608 'view_count': int,
5609 'channel': 'milan',
5610 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5611 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5612 },
5613 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5614 }, {
8bdd16b4 5615 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5616 'playlist_mincount': 455,
8bdd16b4 5617 'info_dict': {
5618 'title': '2018 Chinese New Singles (11/6 updated)',
5619 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5620 'uploader': 'LBK',
5621 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5622 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5623 'channel': 'LBK',
5624 'view_count': int,
5625 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5626 'tags': [],
5627 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5628 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5629 'modified_date': r're:\d{8}',
5630 },
5631 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5632 }, {
29f7c58a 5633 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5634 'only_matching': True,
5635 }, {
5636 # music album playlist
5637 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5638 'only_matching': True,
5639 }]
5640
5641 @classmethod
5642 def suitable(cls, url):
201c1459 5643 if YoutubeTabIE.suitable(url):
5644 return False
49a57e70 5645 from ..utils import parse_qs
201c1459 5646 qs = parse_qs(url)
5647 if qs.get('v', [None])[0]:
5648 return False
86e5f3ed 5649 return super().suitable(url)
29f7c58a 5650
5651 def _real_extract(self, url):
5652 playlist_id = self._match_id(url)
46953e7e 5653 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5654 url = update_url_query(
5655 'https://www.youtube.com/playlist',
5656 parse_qs(url) or {'list': playlist_id})
5657 if is_music_url:
5658 url = smuggle_url(url, {'is_music_url': True})
5659 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5660
5661
5662class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5663 IE_DESC = 'youtu.be'
29f7c58a 5664 _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}
5665 _TESTS = [{
8bdd16b4 5666 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5667 'info_dict': {
5668 'id': 'yeWKywCrFtk',
5669 'ext': 'mp4',
5670 'title': 'Small Scale Baler and Braiding Rugs',
5671 'uploader': 'Backus-Page House Museum',
5672 'uploader_id': 'backuspagemuseum',
5673 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5674 'upload_date': '20161008',
5675 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5676 'categories': ['Nonprofits & Activism'],
5677 'tags': list,
5678 'like_count': int,
976ae3ea 5679 'age_limit': 0,
5680 'playable_in_embed': True,
5681 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5682 'channel': 'Backus-Page House Museum',
5683 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5684 'live_status': 'not_live',
5685 'view_count': int,
5686 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5687 'availability': 'public',
5688 'duration': 59,
12a1b225
A
5689 'comment_count': int,
5690 'channel_follower_count': int
8bdd16b4 5691 },
5692 'params': {
5693 'noplaylist': True,
5694 'skip_download': True,
5695 },
39e7107d 5696 }, {
8bdd16b4 5697 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5698 'only_matching': True,
cdc628a4
PH
5699 }]
5700
8bdd16b4 5701 def _real_extract(self, url):
5ad28e7f 5702 mobj = self._match_valid_url(url)
29f7c58a 5703 video_id = mobj.group('id')
5704 playlist_id = mobj.group('playlist_id')
8bdd16b4 5705 return self.url_result(
29f7c58a 5706 update_url_query('https://www.youtube.com/watch', {
5707 'v': video_id,
5708 'list': playlist_id,
5709 'feature': 'youtu.be',
5710 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5711
5712
b6ce9bb0 5713class YoutubeLivestreamEmbedIE(InfoExtractor):
5714 IE_DESC = 'YouTube livestream embeds'
5715 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5716 _TESTS = [{
5717 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5718 'only_matching': True,
5719 }]
5720
5721 def _real_extract(self, url):
5722 channel_id = self._match_id(url)
5723 return self.url_result(
5724 f'https://www.youtube.com/channel/{channel_id}/live',
5725 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5726
5727
8bdd16b4 5728class YoutubeYtUserIE(InfoExtractor):
96565c7e 5729 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5730 IE_NAME = 'youtube:user'
8bdd16b4 5731 _VALID_URL = r'ytuser:(?P<id>.+)'
5732 _TESTS = [{
5733 'url': 'ytuser:phihag',
5734 'only_matching': True,
5735 }]
5736
5737 def _real_extract(self, url):
5738 user_id = self._match_id(url)
5739 return self.url_result(
c586f9e8 5740 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5741 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5742
b05654f0 5743
3d3dddc9 5744class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5745 IE_NAME = 'youtube:favorites'
96565c7e 5746 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5747 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5748 _LOGIN_REQUIRED = True
5749 _TESTS = [{
5750 'url': ':ytfav',
5751 'only_matching': True,
5752 }, {
5753 'url': ':ytfavorites',
5754 'only_matching': True,
5755 }]
5756
5757 def _real_extract(self, url):
5758 return self.url_result(
5759 'https://www.youtube.com/playlist?list=LL',
5760 ie=YoutubeTabIE.ie_key())
5761
5762
ca5300c7 5763class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5764 IE_NAME = 'youtube:notif'
5765 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5766 _VALID_URL = r':ytnotif(?:ication)?s?'
5767 _LOGIN_REQUIRED = True
5768 _TESTS = [{
5769 'url': ':ytnotif',
5770 'only_matching': True,
5771 }, {
5772 'url': ':ytnotifications',
5773 'only_matching': True,
5774 }]
5775
5776 def _extract_notification_menu(self, response, continuation_list):
5777 notification_list = traverse_obj(
5778 response,
5779 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5780 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5781 expected_type=list) or []
5782 continuation_list[0] = None
5783 for item in notification_list:
5784 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5785 if entry:
5786 yield entry
5787 continuation = item.get('continuationItemRenderer')
5788 if continuation:
5789 continuation_list[0] = continuation
5790
5791 def _extract_notification_renderer(self, notification):
5792 video_id = traverse_obj(
5793 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5794 url = f'https://www.youtube.com/watch?v={video_id}'
5795 channel_id = None
5796 if not video_id:
5797 browse_ep = traverse_obj(
5798 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5799 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5800 post_id = self._search_regex(
5801 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5802 'post id', default=None)
5803 if not channel_id or not post_id:
5804 return
5805 # The direct /post url redirects to this in the browser
5806 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5807
5808 channel = traverse_obj(
5809 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5810 expected_type=str)
c7a7baaa 5811 notification_title = self._get_text(notification, 'shortMessage')
5812 if notification_title:
5813 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5814 # TODO: handle recommended videos
ca5300c7 5815 title = self._search_regex(
c7a7baaa 5816 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5817 'video title', default=None)
ca5300c7 5818 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5819 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5820 else None)
5821 return {
5822 '_type': 'url',
5823 'url': url,
5824 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5825 'video_id': video_id,
5826 'title': title,
5827 'channel_id': channel_id,
5828 'channel': channel,
5829 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5830 'upload_date': upload_date,
5831 }
5832
5833 def _notification_menu_entries(self, ytcfg):
5834 continuation_list = [None]
5835 response = None
5836 for page in itertools.count(1):
5837 ctoken = traverse_obj(
5838 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5839 response = self._extract_response(
5840 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5841 ep='notification/get_notification_menu', check_get_keys='actions',
5842 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5843 yield from self._extract_notification_menu(response, continuation_list)
5844 if not continuation_list[0]:
5845 break
5846
5847 def _real_extract(self, url):
5848 display_id = 'notifications'
5849 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5850 self._report_playlist_authcheck(ytcfg)
5851 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5852
5853
a6213a49 5854class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5855 IE_DESC = 'YouTube search'
78caa52a 5856 IE_NAME = 'youtube:search'
b05654f0 5857 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5858 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5859 _TESTS = [{
5860 'url': 'ytsearch5:youtube-dl test video',
5861 'playlist_count': 5,
5862 'info_dict': {
5863 'id': 'youtube-dl test video',
5864 'title': 'youtube-dl test video',
5865 }
5866 }]
b05654f0 5867
a61fd4cf 5868
5f7cb91a 5869class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5870 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5871 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5872 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5873 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5874 _TESTS = [{
5875 'url': 'ytsearchdate5:youtube-dl test video',
5876 'playlist_count': 5,
5877 'info_dict': {
5878 'id': 'youtube-dl test video',
5879 'title': 'youtube-dl test video',
5880 }
5881 }]
75dff0ee 5882
c9ae7b95 5883
a6213a49 5884class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5885 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5886 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5887 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5888 _TESTS = [{
5889 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5890 'playlist_mincount': 5,
5891 'info_dict': {
11f9be09 5892 'id': 'youtube-dl test video',
3462ffa8 5893 'title': 'youtube-dl test video',
5894 }
a61fd4cf 5895 }, {
5896 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5897 'playlist_mincount': 5,
5898 'info_dict': {
5899 'id': 'python',
5900 'title': 'python',
5901 }
ad210f4f 5902 }, {
5903 'url': 'https://www.youtube.com/results?search_query=%23cats',
5904 'playlist_mincount': 1,
5905 'info_dict': {
5906 'id': '#cats',
5907 'title': '#cats',
12a1b225
A
5908 # The test suite does not have support for nested playlists
5909 # 'entries': [{
5910 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5911 # 'title': '#cats',
5912 # }],
ad210f4f 5913 },
3462ffa8 5914 }, {
5915 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5916 'only_matching': True,
5917 }]
5918
5919 def _real_extract(self, url):
4dfbf869 5920 qs = parse_qs(url)
386e1dd9 5921 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5922 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5923
5924
16aa9ea4 5925class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 5926 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 5927 IE_NAME = 'youtube:music:search_url'
5928 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5929 _TESTS = [{
5930 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5931 'playlist_count': 16,
5932 'info_dict': {
5933 'id': 'royalty free music',
5934 'title': 'royalty free music',
5935 }
5936 }, {
5937 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5938 'playlist_mincount': 30,
5939 'info_dict': {
5940 'id': 'royalty free music - songs',
5941 'title': 'royalty free music - songs',
5942 },
5943 'params': {'extract_flat': 'in_playlist'}
5944 }, {
5945 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5946 'playlist_mincount': 30,
5947 'info_dict': {
5948 'id': 'royalty free music - community playlists',
5949 'title': 'royalty free music - community playlists',
5950 },
5951 'params': {'extract_flat': 'in_playlist'}
5952 }]
5953
5954 _SECTIONS = {
5955 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5956 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5957 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5958 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5959 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5960 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5961 }
5962
5963 def _real_extract(self, url):
5964 qs = parse_qs(url)
5965 query = (qs.get('search_query') or qs.get('q'))[0]
5966 params = qs.get('sp', (None,))[0]
5967 if params:
5968 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5969 else:
ac668111 5970 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5971 params = self._SECTIONS.get(section)
5972 if not params:
5973 section = None
5974 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5975 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5976
5977
182bda88 5978class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5979 """
25f14e9f 5980 Base class for feed extractors
82d02080 5981 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5982 """
b2e8bc1b 5983 _LOGIN_REQUIRED = True
82d02080 5984 _FEED_NAME = 'feeds'
a25bca9f 5985
5986 def _real_initialize(self):
5987 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5988
82d02080 5989 @classproperty
d7ae0639 5990 def IE_NAME(self):
82d02080 5991 return f'youtube:{self._FEED_NAME}'
04cc9617 5992
3853309f 5993 def _real_extract(self, url):
3d3dddc9 5994 return self.url_result(
182bda88 5995 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5996
5997
ef2f3c7f 5998class YoutubeWatchLaterIE(InfoExtractor):
5999 IE_NAME = 'youtube:watchlater'
96565c7e 6000 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6001 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6002 _TESTS = [{
8bdd16b4 6003 'url': ':ytwatchlater',
bc7a9cd8
S
6004 'only_matching': True,
6005 }]
25f14e9f
S
6006
6007 def _real_extract(self, url):
ef2f3c7f 6008 return self.url_result(
6009 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6010
6011
25f14e9f 6012class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6013 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6014 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6015 _FEED_NAME = 'recommended'
45db527f 6016 _LOGIN_REQUIRED = False
3d3dddc9 6017 _TESTS = [{
6018 'url': ':ytrec',
6019 'only_matching': True,
6020 }, {
6021 'url': ':ytrecommended',
6022 'only_matching': True,
6023 }, {
6024 'url': 'https://youtube.com',
6025 'only_matching': True,
6026 }]
1ed5b5c9 6027
1ed5b5c9 6028
25f14e9f 6029class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6030 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6031 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6032 _FEED_NAME = 'subscriptions'
3d3dddc9 6033 _TESTS = [{
6034 'url': ':ytsubs',
6035 'only_matching': True,
6036 }, {
6037 'url': ':ytsubscriptions',
6038 'only_matching': True,
6039 }]
1ed5b5c9 6040
1ed5b5c9 6041
25f14e9f 6042class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6043 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6044 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6045 _FEED_NAME = 'history'
3d3dddc9 6046 _TESTS = [{
6047 'url': ':ythistory',
6048 'only_matching': True,
6049 }]
1ed5b5c9
JMF
6050
6051
6e634cbe 6052class YoutubeStoriesIE(InfoExtractor):
6053 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6054 IE_NAME = 'youtube:stories'
6055 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6056 _TESTS = [{
6057 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6058 'only_matching': True,
6059 }]
6060
6061 def _real_extract(self, url):
6062 playlist_id = f'RLTD{self._match_id(url)}'
6063 return self.url_result(
50ac0e54 6064 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6065 ie=YoutubeTabIE, video_id=playlist_id)
6066
6067
15870e90
PH
6068class YoutubeTruncatedURLIE(InfoExtractor):
6069 IE_NAME = 'youtube:truncated_url'
6070 IE_DESC = False # Do not list
975d35db 6071 _VALID_URL = r'''(?x)
b95aab84
PH
6072 (?:https?://)?
6073 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6074 (?:watch\?(?:
c4808c60 6075 feature=[a-z_]+|
b95aab84
PH
6076 annotation_id=annotation_[^&]+|
6077 x-yt-cl=[0-9]+|
c1708b89 6078 hl=[^&]*|
287be8c6 6079 t=[0-9]+
b95aab84
PH
6080 )?
6081 |
6082 attribution_link\?a=[^&]+
6083 )
6084 $
975d35db 6085 '''
15870e90 6086
c4808c60 6087 _TESTS = [{
2d3d2997 6088 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6089 'only_matching': True,
dc2fc736 6090 }, {
2d3d2997 6091 'url': 'https://www.youtube.com/watch?',
dc2fc736 6092 'only_matching': True,
b95aab84
PH
6093 }, {
6094 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6095 'only_matching': True,
6096 }, {
6097 'url': 'https://www.youtube.com/watch?feature=foo',
6098 'only_matching': True,
c1708b89
PH
6099 }, {
6100 'url': 'https://www.youtube.com/watch?hl=en-GB',
6101 'only_matching': True,
287be8c6
PH
6102 }, {
6103 'url': 'https://www.youtube.com/watch?t=2372',
6104 'only_matching': True,
c4808c60
PH
6105 }]
6106
15870e90
PH
6107 def _real_extract(self, url):
6108 raise ExtractorError(
78caa52a
PH
6109 'Did you forget to quote the URL? Remember that & is a meta '
6110 'character in most shells, so you want to put the URL in quotes, '
3867038a 6111 'like youtube-dl '
2d3d2997 6112 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6113 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6114 expected=True)
772fd5cc
PH
6115
6116
471d0367 6117class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6118 IE_NAME = 'youtube:clip'
471d0367 6119 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6120 _TESTS = [{
6121 # FIXME: Other metadata should be extracted from the clip, not from the base video
6122 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6123 'info_dict': {
6124 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6125 'ext': 'mp4',
6126 'section_start': 29.0,
6127 'section_end': 39.7,
6128 'duration': 10.7,
12a1b225
A
6129 'age_limit': 0,
6130 'availability': 'public',
6131 'categories': ['Gaming'],
6132 'channel': 'Scott The Woz',
6133 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6134 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6135 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6136 'like_count': int,
6137 'playable_in_embed': True,
6138 'tags': 'count:17',
6139 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6140 'title': 'Mobile Games on Console - Scott The Woz',
6141 'upload_date': '20210920',
6142 'uploader': 'Scott The Woz',
6143 'uploader_id': 'scottthewoz',
6144 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6145 'view_count': int,
6146 'live_status': 'not_live',
6147 'channel_follower_count': int
471d0367 6148 }
6149 }]
3cd786db 6150
6151 def _real_extract(self, url):
471d0367 6152 clip_id = self._match_id(url)
6153 _, data = self._extract_webpage(url, clip_id)
6154
6155 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6156 if not video_id:
6157 raise ExtractorError('Unable to find video ID')
6158
6159 clip_data = traverse_obj(data, (
6160 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6161 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6162 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6163 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6164
6165 return {
6166 '_type': 'url_transparent',
6167 'url': f'https://www.youtube.com/watch?v={video_id}',
6168 'ie_key': YoutubeIE.ie_key(),
6169 'id': clip_id,
6170 'section_start': int(clip_data['startTimeMs']) / 1000,
6171 'section_end': int(clip_data['endTimeMs']) / 1000,
6172 }
3cd786db 6173
6174
772fd5cc
PH
6175class YoutubeTruncatedIDIE(InfoExtractor):
6176 IE_NAME = 'youtube:truncated_id'
6177 IE_DESC = False # Do not list
b95aab84 6178 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6179
6180 _TESTS = [{
6181 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6182 'only_matching': True,
6183 }]
6184
6185 def _real_extract(self, url):
6186 video_id = self._match_id(url)
6187 raise ExtractorError(
86e5f3ed 6188 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6189 expected=True)