]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/youtube] Fix `live_status` extraction for playlist videos
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
c26f9b99 5import enum
a5c56234 6import hashlib
0ca96d48 7import itertools
c5e8d7af 8import json
720c3099 9import math
c4417ddb 10import os.path
d77ab8e2 11import random
c5e8d7af 12import re
46383212 13import sys
f8271158 14import threading
8a784c74 15import time
e0df6211 16import traceback
14f25df2 17import urllib.error
ac668111 18import urllib.parse
c5e8d7af 19
b05654f0 20from .common import InfoExtractor, SearchInfoExtractor
25836db6 21from .openload import PhantomJSwrapper
14f25df2 22from ..compat import functools
545cc85d 23from ..jsinterp import JSInterpreter
4bb4a188 24from ..utils import (
f8271158 25 NO_DEFAULT,
26 ExtractorError,
4d37720a 27 LazyList,
693f0600 28 UserNotLive,
720c3099 29 bug_reports_message,
82d02080 30 classproperty,
c5e8d7af 31 clean_html,
d92f5d5a 32 datetime_from_str,
11f9be09 33 dict_get,
7a32c70d 34 filter_dict,
2d30521a 35 float_or_none,
11f9be09 36 format_field,
ff91cf74 37 get_first,
dd27fd17 38 int_or_none,
641ad5d8 39 is_html,
34921b43 40 join_nonempty,
48416bc4 41 js_to_json,
94278f72 42 mimetype2ext,
9c0d7f49 43 network_exceptions,
11f9be09 44 orderedSet,
6310acf5 45 parse_codecs,
49bd8c66 46 parse_count,
7c80519c 47 parse_duration,
7ea65411 48 parse_iso8601,
4dfbf869 49 parse_qs,
dca3ff4a 50 qualities,
3995d37d 51 remove_start,
cf7e015f 52 smuggle_url,
dbdaaa23 53 str_or_none,
c93d53f5 54 str_to_int,
f3aa3c3f 55 strftime_or_none,
7c365c21 56 traverse_obj,
556dbe7f 57 try_get,
c5e8d7af
PH
58 unescapeHTML,
59 unified_strdate,
f0d785d3 60 unified_timestamp,
cf7e015f 61 unsmuggle_url,
8bdd16b4 62 update_url_query,
21c340b8 63 url_or_none,
fe93e2c4 64 urljoin,
7c365c21 65 variadic,
c5e8d7af
PH
66)
67
962ffcf8 68# any clients starting with _ cannot be explicitly requested by the user
000c15a4 69INNERTUBE_CLIENTS = {
70 'web': {
71 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
72 'INNERTUBE_CONTEXT': {
73 'client': {
74 'clientName': 'WEB',
a0c830f4 75 'clientVersion': '2.20220801.00.00',
000c15a4 76 }
77 },
78 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
79 },
80 'web_embedded': {
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
83 'client': {
84 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 85 'clientVersion': '1.20220731.00.00',
000c15a4 86 },
87 },
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
89 },
90 'web_music': {
91 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
92 'INNERTUBE_HOST': 'music.youtube.com',
93 'INNERTUBE_CONTEXT': {
94 'client': {
95 'clientName': 'WEB_REMIX',
a0c830f4 96 'clientVersion': '1.20220727.01.00',
000c15a4 97 }
98 },
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
100 },
e7e94f2a 101 'web_creator': {
18c7683d 102 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
103 'INNERTUBE_CONTEXT': {
104 'client': {
105 'clientName': 'WEB_CREATOR',
a0c830f4 106 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
107 }
108 },
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
110 },
000c15a4 111 'android': {
18c7683d 112 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 113 'INNERTUBE_CONTEXT': {
114 'client': {
115 'clientName': 'ANDROID',
50ac0e54 116 'clientVersion': '17.31.35',
117 'androidSdkVersion': 30,
118 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 119 }
120 },
121 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 122 'REQUIRE_JS_PLAYER': False
000c15a4 123 },
124 'android_embedded': {
18c7683d 125 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 126 'INNERTUBE_CONTEXT': {
127 'client': {
128 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 129 'clientVersion': '17.31.35',
130 'androidSdkVersion': 30,
131 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 132 },
133 },
b6de707d 134 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
135 'REQUIRE_JS_PLAYER': False
000c15a4 136 },
137 'android_music': {
18c7683d 138 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 139 'INNERTUBE_CONTEXT': {
140 'client': {
141 'clientName': 'ANDROID_MUSIC',
a0c830f4 142 'clientVersion': '5.16.51',
50ac0e54 143 'androidSdkVersion': 30,
144 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 145 }
146 },
147 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 148 'REQUIRE_JS_PLAYER': False
000c15a4 149 },
e7e94f2a 150 'android_creator': {
18c7683d 151 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
152 'INNERTUBE_CONTEXT': {
153 'client': {
154 'clientName': 'ANDROID_CREATOR',
50ac0e54 155 'clientVersion': '22.30.100',
156 'androidSdkVersion': 30,
157 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
158 },
159 },
b6de707d 160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
e7e94f2a 162 },
18c7683d 163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 165 'ios': {
18c7683d 166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS',
224b5a35 170 'clientVersion': '17.33.2',
18c7683d 171 'deviceModel': 'iPhone14,3',
224b5a35 172 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 173 }
174 },
b6de707d 175 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
176 'REQUIRE_JS_PLAYER': False
000c15a4 177 },
178 'ios_embedded': {
000c15a4 179 'INNERTUBE_CONTEXT': {
180 'client': {
181 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 182 'clientVersion': '17.33.2',
18c7683d 183 'deviceModel': 'iPhone14,3',
224b5a35 184 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 185 },
186 },
b6de707d 187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
000c15a4 189 },
190 'ios_music': {
18c7683d 191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_MUSIC',
224b5a35
SF
195 'clientVersion': '5.21',
196 'deviceModel': 'iPhone14,3',
197 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 198 },
199 },
b6de707d 200 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
201 'REQUIRE_JS_PLAYER': False
000c15a4 202 },
e7e94f2a
D
203 'ios_creator': {
204 'INNERTUBE_CONTEXT': {
205 'client': {
206 'clientName': 'IOS_CREATOR',
224b5a35
SF
207 'clientVersion': '22.33.101',
208 'deviceModel': 'iPhone14,3',
209 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
210 },
211 },
b6de707d 212 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
213 'REQUIRE_JS_PLAYER': False
e7e94f2a 214 },
3619f78d 215 # mweb has 'ultralow' formats
216 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 217 'mweb': {
18c7683d 218 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 219 'INNERTUBE_CONTEXT': {
220 'client': {
221 'clientName': 'MWEB',
a0c830f4 222 'clientVersion': '2.20220801.00.00',
000c15a4 223 }
224 },
225 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
226 },
227 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
228 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
229 'tv_embedded': {
230 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
231 'INNERTUBE_CONTEXT': {
232 'client': {
233 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
234 'clientVersion': '2.0',
235 },
236 },
237 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
238 },
000c15a4 239}
240
241
e7870111
D
242def _split_innertube_client(client_name):
243 variant, *base = client_name.rsplit('.', 1)
244 if base:
245 return variant, base[0], variant
246 base, *variant = client_name.split('_', 1)
247 return client_name, base, variant[0] if variant else None
248
249
000c15a4 250def build_innertube_clients():
2e4cacd0 251 THIRD_PARTY = {
e7870111 252 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 253 }
e7870111 254 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 255 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 256
257 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 258 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 259 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 260 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 261 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 262
e7870111 263 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 264 ytcfg['priority'] = 10 * priority(base_client)
265
e48b3875 266 if not variant:
e7870111
D
267 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
268 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
269 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
270 embedscreen['priority'] -= 3
271 elif variant == 'embedded':
e48b3875 272 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 273 ytcfg['priority'] -= 2
e48b3875 274 else:
000c15a4 275 ytcfg['priority'] -= 3
276
277
278build_innertube_clients()
279
280
c26f9b99 281class BadgeType(enum.Enum):
282 AVAILABILITY_UNLISTED = enum.auto()
283 AVAILABILITY_PRIVATE = enum.auto()
284 AVAILABILITY_PUBLIC = enum.auto()
285 AVAILABILITY_PREMIUM = enum.auto()
286 AVAILABILITY_SUBSCRIPTION = enum.auto()
287 LIVE_NOW = enum.auto()
288
289
de7f3446 290class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 291 """Provide base functions for Youtube extractors"""
e00eb564 292
3462ffa8 293 _RESERVED_NAMES = (
3cd786db 294 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 295 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 296 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 297 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 298
3619f78d 299 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
300
52efa4b3 301 # _NETRC_MACHINE = 'youtube'
3619f78d 302
b2e8bc1b
JMF
303 # If True it will raise an error if no login info is provided
304 _LOGIN_REQUIRED = False
305
d9190e44
RH
306 _INVIDIOUS_SITES = (
307 # invidious-redirect websites
308 r'(?:www\.)?redirect\.invidious\.io',
309 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 310 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
311 r'(?:www\.)?invidious\.pussthecat\.org',
312 r'(?:www\.)?invidious\.zee\.li',
313 r'(?:www\.)?invidious\.ethibox\.fr',
314 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
315 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
316 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
317 # youtube-dl invidious instances list
318 r'(?:(?:www|no)\.)?invidiou\.sh',
319 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
320 r'(?:www\.)?invidious\.kabi\.tk',
321 r'(?:www\.)?invidious\.mastodon\.host',
322 r'(?:www\.)?invidious\.zapashcanon\.fr',
323 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
324 r'(?:www\.)?invidious\.tinfoil-hat\.net',
325 r'(?:www\.)?invidious\.himiko\.cloud',
326 r'(?:www\.)?invidious\.reallyancient\.tech',
327 r'(?:www\.)?invidious\.tube',
328 r'(?:www\.)?invidiou\.site',
329 r'(?:www\.)?invidious\.site',
330 r'(?:www\.)?invidious\.xyz',
331 r'(?:www\.)?invidious\.nixnet\.xyz',
332 r'(?:www\.)?invidious\.048596\.xyz',
333 r'(?:www\.)?invidious\.drycat\.fr',
334 r'(?:www\.)?inv\.skyn3t\.in',
335 r'(?:www\.)?tube\.poal\.co',
336 r'(?:www\.)?tube\.connect\.cafe',
337 r'(?:www\.)?vid\.wxzm\.sx',
338 r'(?:www\.)?vid\.mint\.lgbt',
339 r'(?:www\.)?vid\.puffyan\.us',
340 r'(?:www\.)?yewtu\.be',
341 r'(?:www\.)?yt\.elukerio\.org',
342 r'(?:www\.)?yt\.lelux\.fi',
343 r'(?:www\.)?invidious\.ggc-project\.de',
344 r'(?:www\.)?yt\.maisputain\.ovh',
345 r'(?:www\.)?ytprivate\.com',
346 r'(?:www\.)?invidious\.13ad\.de',
347 r'(?:www\.)?invidious\.toot\.koeln',
348 r'(?:www\.)?invidious\.fdn\.fr',
349 r'(?:www\.)?watch\.nettohikari\.com',
350 r'(?:www\.)?invidious\.namazso\.eu',
351 r'(?:www\.)?invidious\.silkky\.cloud',
352 r'(?:www\.)?invidious\.exonip\.de',
353 r'(?:www\.)?invidious\.riverside\.rocks',
354 r'(?:www\.)?invidious\.blamefran\.net',
355 r'(?:www\.)?invidious\.moomoo\.de',
356 r'(?:www\.)?ytb\.trom\.tf',
357 r'(?:www\.)?yt\.cyberhost\.uk',
358 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
359 r'(?:www\.)?qklhadlycap4cnod\.onion',
360 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
361 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
362 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
363 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
364 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
365 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
366 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
367 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
368 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
369 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
370 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
371 r'(?:www\.)?piped\.kavin\.rocks',
372 r'(?:www\.)?piped\.silkky\.cloud',
373 r'(?:www\.)?piped\.tokhmi\.xyz',
374 r'(?:www\.)?piped\.moomoo\.me',
375 r'(?:www\.)?il\.ax',
376 r'(?:www\.)?piped\.syncpundit\.com',
377 r'(?:www\.)?piped\.mha\.fi',
378 r'(?:www\.)?piped\.mint\.lgbt',
379 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
380 )
381
c26f9b99 382 # extracted from account/account_menu ep
383 # XXX: These are the supported YouTube UI and API languages,
384 # which is slightly different from languages supported for translation in YouTube studio
385 _SUPPORTED_LANG_CODES = [
386 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
387 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
388 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
389 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
390 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
391 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
392 ]
393
a057779d 394 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
395
c26f9b99 396 @functools.cached_property
397 def _preferred_lang(self):
398 """
399 Returns a language code supported by YouTube for the user preferred language.
400 Returns None if no preferred language set.
401 """
402 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
403 if not preferred_lang:
404 return
405 if preferred_lang not in self._SUPPORTED_LANG_CODES:
406 raise ExtractorError(
407 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
408 expected=True)
409 elif preferred_lang != 'en':
410 self.report_warning(
411 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
412 return preferred_lang
413
cce889b9 414 def _initialize_consent(self):
415 cookies = self._get_cookies('https://www.youtube.com/')
416 if cookies.get('__Secure-3PSID'):
417 return
418 consent_id = None
419 consent = cookies.get('CONSENT')
420 if consent:
421 if 'YES' in consent.value:
422 return
423 consent_id = self._search_regex(
424 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
425 if not consent_id:
426 consent_id = random.randint(100, 999)
427 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 428
f3aa3c3f 429 def _initialize_pref(self):
430 cookies = self._get_cookies('https://www.youtube.com/')
431 pref_cookie = cookies.get('PREF')
432 pref = {}
433 if pref_cookie:
434 try:
14f25df2 435 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 436 except ValueError:
437 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 438 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 439 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 440
b2e8bc1b 441 def _real_initialize(self):
f3aa3c3f 442 self._initialize_pref()
cce889b9 443 self._initialize_consent()
a25bca9f 444 self._check_login_required()
445
446 def _check_login_required(self):
24146491 447 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 448 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 449
b7c47b74 450 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
451 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 452
000c15a4 453 def _get_default_ytcfg(self, client='web'):
454 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 455
000c15a4 456 def _get_innertube_host(self, client='web'):
457 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 458
000c15a4 459 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 460 # try_get but with fallback to default ytcfg client values when present
461 _func = lambda y: try_get(y, getter, expected_type)
462 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
463
000c15a4 464 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 465 return self._ytcfg_get_safe(
466 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 467 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 468
000c15a4 469 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 470 return self._ytcfg_get_safe(
471 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 472 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 473
2ae778b8 474 def _select_api_hostname(self, req_api_hostname, default_client=None):
475 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
476 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
477
000c15a4 478 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 479 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 480
000c15a4 481 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 482 context = get_first(
483 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 484 # Enforce language and tz for extraction
485 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 486 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 487 return context
488
cf87314d 489 _SAPISID = None
490
109dd3b2 491 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 492 time_now = round(time.time())
cf87314d 493 if self._SAPISID is None:
494 yt_cookies = self._get_cookies('https://www.youtube.com')
495 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
496 # See: https://github.com/yt-dlp/yt-dlp/issues/393
497 sapisid_cookie = dict_get(
498 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
499 if sapisid_cookie and sapisid_cookie.value:
500 self._SAPISID = sapisid_cookie.value
501 self.write_debug('Extracted SAPISID cookie')
502 # SAPISID cookie is required if not already present
503 if not yt_cookies.get('SAPISID'):
504 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
505 self._set_cookie(
506 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
507 else:
508 self._SAPISID = False
509 if not self._SAPISID:
510 return None
1974e99f 511 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
512 sapisidhash = hashlib.sha1(
86e5f3ed 513 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 514 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
515
516 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 517 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 518 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 519
109dd3b2 520 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 521 data.update(query)
11f9be09 522 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 523 real_headers.update({'content-type': 'application/json'})
524 if headers:
525 real_headers.update(headers)
2ae778b8 526 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
527 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 528 return self._download_json(
2ae778b8 529 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 530 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 531 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 532 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 533
65141660 534 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
535 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 536
99e9e001 537 @staticmethod
538 def _extract_session_index(*data):
539 """
540 Index of current account in account list.
541 See: https://github.com/yt-dlp/yt-dlp/pull/519
542 """
543 for ytcfg in data:
544 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
545 if session_index is not None:
546 return session_index
547
548 # Deprecated?
549 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 550 if ytcfg:
14f25df2 551 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
552 if token:
553 return token
99e9e001 554 if webpage:
555 return self._search_regex(
556 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
557 'identity token', default=None, fatal=False)
a1c5d2ca
M
558
559 @staticmethod
fe93e2c4 560 def _extract_account_syncid(*args):
8ea3f7b9 561 """
562 Extract syncId required to download private playlists of secondary channels
fe93e2c4 563 @params response and/or ytcfg
8ea3f7b9 564 """
fe93e2c4 565 for data in args:
566 # ytcfg includes channel_syncid if on secondary channel
14f25df2 567 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 568 if delegated_sid:
569 return delegated_sid
570 sync_ids = (try_get(
571 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 572 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 573 if len(sync_ids) >= 2 and sync_ids[1]:
574 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
575 # and just "user_syncid||" for primary channel. We only want the channel_syncid
576 return sync_ids[0]
a1c5d2ca 577
ac56cf38 578 @staticmethod
579 def _extract_visitor_data(*args):
580 """
581 Extracts visitorData from an API response or ytcfg
582 Appears to be used to track session state
583 """
9222c381 584 return get_first(
6c73052c 585 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 586 expected_type=str)
ac56cf38 587
2762dbb1 588 @functools.cached_property
99e9e001 589 def is_authenticated(self):
590 return bool(self._generate_sapisidhash_header())
591
11f9be09 592 def extract_ytcfg(self, video_id, webpage):
8c54a305 593 if not webpage:
594 return {}
29f7c58a 595 return self._parse_json(
596 self._search_regex(
597 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 598 default='{}'), video_id, fatal=False) or {}
599
11f9be09 600 def generate_api_headers(
99e9e001 601 self, *, ytcfg=None, account_syncid=None, session_index=None,
602 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
603
2ae778b8 604 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 605 headers = {
14f25df2 606 'X-YouTube-Client-Name': str(
11f9be09 607 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
608 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 609 'Origin': origin,
610 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
611 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 612 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
613 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 614 }
615 if session_index is None:
314ee305 616 session_index = self._extract_session_index(ytcfg)
617 if account_syncid or session_index is not None:
618 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 619
109dd3b2 620 auth = self._generate_sapisidhash_header(origin)
f4f751af 621 if auth is not None:
622 headers['Authorization'] = auth
109dd3b2 623 headers['X-Origin'] = origin
7a32c70d 624 return filter_dict(headers)
29f7c58a 625
a25bca9f 626 def _download_ytcfg(self, client, video_id):
627 url = {
628 'web': 'https://www.youtube.com',
629 'web_music': 'https://music.youtube.com',
630 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
631 }.get(client)
632 if not url:
633 return {}
634 webpage = self._download_webpage(
635 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
636 return self.extract_ytcfg(video_id, webpage) or {}
637
2d6659b9 638 @staticmethod
639 def _build_api_continuation_query(continuation, ctp=None):
640 query = {
641 'continuation': continuation
642 }
643 # TODO: Inconsistency with clickTrackingParams.
644 # Currently we have a fixed ctp contained within context (from ytcfg)
645 # and a ctp in root query for continuation.
646 if ctp:
647 query['clickTracking'] = {'clickTrackingParams': ctp}
648 return query
649
2d6659b9 650 @classmethod
651 def _extract_next_continuation_data(cls, renderer):
652 next_continuation = try_get(
653 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
654 lambda x: x['continuation']['reloadContinuationData']), dict)
655 if not next_continuation:
656 return
657 continuation = next_continuation.get('continuation')
658 if not continuation:
659 return
660 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 661 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 662
663 @classmethod
664 def _extract_continuation_ep_data(cls, continuation_ep: dict):
665 if isinstance(continuation_ep, dict):
666 continuation = try_get(
14f25df2 667 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 668 if not continuation:
669 return
670 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 671 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 672
673 @classmethod
674 def _extract_continuation(cls, renderer):
675 next_continuation = cls._extract_next_continuation_data(renderer)
676 if next_continuation:
677 return next_continuation
fe93e2c4 678
7a32c70d 679 return traverse_obj(renderer, (
680 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
681 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
682 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 683
fe93e2c4 684 @classmethod
685 def _extract_alerts(cls, data):
109dd3b2 686 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
687 if not isinstance(alert_dict, dict):
688 continue
689 for alert in alert_dict.values():
690 alert_type = alert.get('type')
691 if not alert_type:
692 continue
052e1350 693 message = cls._get_text(alert, 'text')
109dd3b2 694 if message:
695 yield alert_type, message
696
c0ac49bc 697 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 698 errors, warnings = [], []
109dd3b2 699 for alert_type, alert_message in alerts:
641ad5d8 700 if alert_type.lower() == 'error' and fatal:
109dd3b2 701 errors.append([alert_type, alert_message])
a057779d 702 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 703 warnings.append([alert_type, alert_message])
704
705 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 706 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 707 if errors:
708 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
709
710 def _extract_and_report_alerts(self, data, *args, **kwargs):
711 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
712
47193e02 713 def _extract_badges(self, renderer: dict):
c26f9b99 714 privacy_icon_map = {
715 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
716 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
717 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
718 }
719
720 badge_style_map = {
721 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
722 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
723 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
724 }
725
726 label_map = {
727 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
728 'private': BadgeType.AVAILABILITY_PRIVATE,
729 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
730 'live': BadgeType.LIVE_NOW,
731 'premium': BadgeType.AVAILABILITY_PREMIUM
732 }
733
734 badges = []
735 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer'), default=[]):
736 badge_type = (
737 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
738 or badge_style_map.get(traverse_obj(badge, 'style'))
739 )
740 if badge_type:
741 badges.append({'type': badge_type})
742 continue
743
744 # fallback, won't work in some languages
745 label = traverse_obj(badge, 'label', expected_type=str, default='')
746 for match, label_badge_type in label_map.items():
747 if match in label.lower():
748 badges.append({'type': badge_type})
749 continue
750
47193e02 751 return badges
752
c26f9b99 753 @staticmethod
754 def _has_badge(badges, badge_type):
755 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
756
47193e02 757 @staticmethod
052e1350 758 def _get_text(data, *path_list, max_runs=None):
759 for path in path_list or [None]:
760 if path is None:
761 obj = [data]
762 else:
763 obj = traverse_obj(data, path, default=[])
764 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
765 obj = [obj]
766 for item in obj:
14f25df2 767 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 768 if text:
769 return text
770 runs = try_get(item, lambda x: x['runs'], list) or []
771 if not runs and isinstance(item, list):
772 runs = item
773
774 runs = runs[:min(len(runs), max_runs or len(runs))]
775 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
776 if text:
777 return text
47193e02 778
f0d785d3 779 def _get_count(self, data, *path_list):
780 count_text = self._get_text(data, *path_list) or ''
781 count = parse_count(count_text)
782 if count is None:
783 count = str_to_int(
784 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
785 return count
786
a709d873 787 @staticmethod
788 def _extract_thumbnails(data, *path_list):
789 """
790 Extract thumbnails from thumbnails dict
791 @param path_list: path list to level that contains 'thumbnails' key
792 """
793 thumbnails = []
794 for path in path_list or [()]:
795 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
796 thumbnail_url = url_or_none(thumbnail.get('url'))
797 if not thumbnail_url:
798 continue
799 # Sometimes youtube gives a wrong thumbnail URL. See:
800 # https://github.com/yt-dlp/yt-dlp/issues/233
801 # https://github.com/ytdl-org/youtube-dl/issues/28023
802 if 'maxresdefault' in thumbnail_url:
803 thumbnail_url = thumbnail_url.split('?')[0]
804 thumbnails.append({
805 'url': thumbnail_url,
806 'height': int_or_none(thumbnail.get('height')),
807 'width': int_or_none(thumbnail.get('width')),
808 })
809 return thumbnails
810
f3aa3c3f 811 @staticmethod
812 def extract_relative_time(relative_time_text):
813 """
814 Extracts a relative time from string and converts to dt object
f0d785d3 815 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 816 """
f0d785d3 817 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 818 if mobj:
f0d785d3 819 start = mobj.group('start')
820 if start:
821 return datetime_from_str(start)
f3aa3c3f 822 try:
f0d785d3 823 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 824 except ValueError:
825 return None
826
c26f9b99 827 def _parse_time_text(self, text):
828 if not text:
829 return
f3aa3c3f 830 dt = self.extract_relative_time(text)
831 timestamp = None
832 if isinstance(dt, datetime.datetime):
833 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 834
835 if timestamp is None:
836 timestamp = (
837 unified_timestamp(text) or unified_timestamp(
838 self._search_regex(
17322130 839 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 840 text.lower(), 'time text', default=None)))
f0d785d3 841
c26f9b99 842 if text and timestamp is None and self._preferred_lang in (None, 'en'):
843 self.report_warning(
844 f'Cannot parse localized time text "{text}"', only_once=True)
845 return timestamp
f3aa3c3f 846
109dd3b2 847 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
848 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 849 default_client='web'):
be5c1ae8 850 for retry in self.RetryManager():
109dd3b2 851 try:
852 response = self._call_api(
853 ep=ep, fatal=True, headers=headers,
be5c1ae8 854 video_id=item_id, query=query, note=note,
109dd3b2 855 context=self._extract_context(ytcfg, default_client),
856 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 857 api_hostname=api_hostname, default_client=default_client)
109dd3b2 858 except ExtractorError as e:
be5c1ae8 859 if not isinstance(e.cause, network_exceptions):
860 return self._error_or_warning(e, fatal=fatal)
861 elif not isinstance(e.cause, urllib.error.HTTPError):
862 retry.error = e
863 continue
109dd3b2 864
be5c1ae8 865 first_bytes = e.cause.read(512)
866 if not is_html(first_bytes):
867 yt_error = try_get(
868 self._parse_json(
869 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
870 lambda x: x['error']['message'], str)
871 if yt_error:
872 self._report_alerts([('ERROR', yt_error)], fatal=False)
873 # Downloading page may result in intermittent 5xx HTTP error
874 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
875 # We also want to catch all other network exceptions since errors in later pages can be troublesome
876 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
877 if e.cause.code not in (403, 429):
878 retry.error = e
879 continue
880 return self._error_or_warning(e, fatal=fatal)
881
882 try:
883 self._extract_and_report_alerts(response, only_once=True)
884 except ExtractorError as e:
885 # YouTube servers may return errors we want to retry on in a 200 OK response
886 # See: https://github.com/yt-dlp/yt-dlp/issues/839
887 if 'unknown error' in e.msg.lower():
888 retry.error = e
889 continue
890 return self._error_or_warning(e, fatal=fatal)
891 # Youtube sometimes sends incomplete data
892 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
893 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 894 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 895 continue
896
897 return response
109dd3b2 898
9297939e 899 @staticmethod
900 def is_music_url(url):
901 return re.match(r'https?://music\.youtube\.com/', url) is not None
902
30a074c2 903 def _extract_video(self, renderer):
904 video_id = renderer.get('videoId')
052e1350 905 title = self._get_text(renderer, 'title')
906 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 907 duration = parse_duration(self._get_text(
908 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 909 if duration is None:
910 duration = parse_duration(self._search_regex(
911 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
912 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
913 video_id, default=None, group='duration'))
914
867c66ff 915 view_count = self._get_count(renderer, 'viewCountText', 'shortViewCountText')
052e1350 916 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 917 channel_id = traverse_obj(
a44ca5a4 918 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
919 expected_type=str, get_all=False)
c26f9b99 920 time_text = self._get_text(renderer, 'publishedTimeText') or ''
f3aa3c3f 921 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
922 overlay_style = traverse_obj(
a44ca5a4 923 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
924 get_all=False, expected_type=str)
f3aa3c3f 925 badges = self._extract_badges(renderer)
a709d873 926 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 927 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 928 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
929 expected_type=str)) or ''
fd2ad7cb 930 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 931 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 932 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 933
867c66ff
M
934 live_status = (
935 'is_upcoming' if scheduled_timestamp is not None
936 else 'was_live' if 'streamed' in time_text.lower()
937 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
938 else None)
939
30a074c2 940 return {
39ed931e 941 '_type': 'url',
30a074c2 942 'ie_key': YoutubeIE.ie_key(),
943 'id': video_id,
fd2ad7cb 944 'url': url,
30a074c2 945 'title': title,
946 'description': description,
947 'duration': duration,
30a074c2 948 'uploader': uploader,
f3aa3c3f 949 'channel_id': channel_id,
a709d873 950 'thumbnails': thumbnails,
5225df50 951 'timestamp': (self._parse_time_text(time_text)
952 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
953 else None),
f3aa3c3f 954 'release_timestamp': scheduled_timestamp,
c26f9b99 955 'availability':
956 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
957 else self._availability(
958 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
959 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
960 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff
M
961 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
962 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count': view_count,
e63faa10 963 'live_status': live_status
30a074c2 964 }
965
0c148415 966
360e1ca5 967class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 968 IE_DESC = 'YouTube'
cb7dfeea 969 _VALID_URL = r"""(?x)^
c5e8d7af 970 (
edb53e2d 971 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 972 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
973 (?:www\.)?deturl\.com/www\.youtube\.com|
974 (?:www\.)?pwnyoutube\.com|
975 (?:www\.)?hooktube\.com|
976 (?:www\.)?yourepeat\.com|
977 tube\.majestyc\.net|
978 %(invidious)s|
979 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
980 (?:.*?\#/)? # handle anchor (#/) redirect urls
981 (?: # the various things that can precede the ID:
b6ce9bb0 982 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 983 |(?: # or the v= param in all its forms
f7000f3a 984 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 985 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 986 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
987 v=
988 )
f4b05232 989 ))
cbaed4bb
S
990 |(?:
991 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
992 vid\.plus| # or vid.plus/xxxx
993 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 994 %(invidious)s
cbaed4bb 995 )/
edb53e2d 996 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 997 )
c5e8d7af 998 )? # all until now is optional -> you can pass the naked ID
201c1459 999 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1000 (?(1).+)? # if we found the ID, everything can follow
9297939e 1001 (?:\#|$)""" % {
d9190e44 1002 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1003 }
7c6eb424 1004 _EMBED_REGEX = [
1005 r'''(?x)
1006 (?:
0ca0f881 1007 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1008 data-video-url=|
1009 <embed[^>]+?src=|
1010 embedSWF\(?:\s*|
1011 <object[^>]+data=|
1012 new\s+SWFObject\(
1013 )
1014 (["\'])
1015 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1016 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1017 \1''',
1018 # https://wordpress.org/plugins/lazy-load-for-videos/
1019 r'''(?xs)
1020 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1021 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1022 ]
1023
e40c758c 1024 _PLAYER_INFO_RE = (
cc2db878 1025 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1026 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$',
545cc85d 1027 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1028 )
2c62dc26 1029 _formats = {
c2d3cb4c 1030 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1031 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1032 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1033 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1034 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1035 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1036 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1037 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1038 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1039 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1040 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1041 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1042 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1043 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1044 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1045 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1046 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1047 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1048
1049
1050 # 3D videos
c2d3cb4c 1051 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1052 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1053 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1054 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1055 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1056 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1057 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1058
96fb5605 1059 # Apple HTTP Live Streaming
11f12195 1060 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1061 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1062 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1063 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1064 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1065 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1066 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1067 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1068
1069 # DASH mp4 video
d23028a8
S
1070 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1071 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1072 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1073 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1074 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1075 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1076 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1077 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1078 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1079 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1080 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1081 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1082
f6f1fc92 1083 # Dash mp4 audio
d23028a8
S
1084 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1085 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1086 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1087 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1088 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1089 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1090 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1091
1092 # Dash webm
d23028a8
S
1093 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1094 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1095 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1096 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1097 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1098 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1099 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1100 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1101 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1102 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1103 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1104 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1105 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1106 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1107 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1108 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1109 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1110 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1111 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1112 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1113 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1114 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1115
1116 # Dash webm audio
d23028a8
S
1117 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1118 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1119
0857baad 1120 # Dash webm audio with opus inside
d23028a8
S
1121 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1122 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1123 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1124
ce6b9a2d
PH
1125 # RTMP (unnamed)
1126 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1127
1128 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1129 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1130 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1131 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1132 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1133 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1134 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1135 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1136 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1137 }
29f7c58a 1138 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1139
fd5c4aab
S
1140 _GEO_BYPASS = False
1141
78caa52a 1142 IE_NAME = 'youtube'
2eb88d95
PH
1143 _TESTS = [
1144 {
2d3d2997 1145 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1146 'info_dict': {
1147 'id': 'BaW_jenozKc',
1148 'ext': 'mp4',
3867038a 1149 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1150 'uploader': 'Philipp Hagemeister',
1151 'uploader_id': 'phihag',
ec85ded8 1152 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1153 'channel': 'Philipp Hagemeister',
dd4c4492
S
1154 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1155 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1156 'upload_date': '20121002',
ff9f925b 1157 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1158 'categories': ['Science & Technology'],
3867038a 1159 'tags': ['youtube-dl'],
556dbe7f 1160 'duration': 10,
dbdaaa23 1161 'view_count': int,
3e7c1224 1162 'like_count': int,
ff9f925b 1163 'availability': 'public',
1164 'playable_in_embed': True,
1165 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1166 'live_status': 'not_live',
1167 'age_limit': 0,
7c80519c 1168 'start_time': 1,
297a564b 1169 'end_time': 9,
12a1b225 1170 'comment_count': int,
6c73052c 1171 'channel_follower_count': int
2eb88d95 1172 }
0e853ca4 1173 },
fccd3771 1174 {
4bc3a23e
PH
1175 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1176 'note': 'Embed-only video (#1746)',
1177 'info_dict': {
1178 'id': 'yZIXLfi8CZQ',
1179 'ext': 'mp4',
1180 'upload_date': '20120608',
1181 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1182 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1183 'uploader': 'SET India',
94bfcd23 1184 'uploader_id': 'setindia',
ec85ded8 1185 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1186 'age_limit': 18,
545cc85d 1187 },
1188 'skip': 'Private video',
fccd3771 1189 },
11b56058 1190 {
8bdd16b4 1191 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1192 'note': 'Use the first video ID in the URL',
1193 'info_dict': {
1194 'id': 'BaW_jenozKc',
1195 'ext': 'mp4',
3867038a 1196 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1197 'uploader': 'Philipp Hagemeister',
1198 'uploader_id': 'phihag',
ec85ded8 1199 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1200 'channel': 'Philipp Hagemeister',
1201 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1202 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1203 'upload_date': '20121002',
976ae3ea 1204 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1205 'categories': ['Science & Technology'],
3867038a 1206 'tags': ['youtube-dl'],
556dbe7f 1207 'duration': 10,
dbdaaa23 1208 'view_count': int,
11b56058 1209 'like_count': int,
976ae3ea 1210 'availability': 'public',
1211 'playable_in_embed': True,
1212 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1213 'live_status': 'not_live',
1214 'age_limit': 0,
12a1b225 1215 'comment_count': int,
6c73052c 1216 'channel_follower_count': int
34a7de29
S
1217 },
1218 'params': {
1219 'skip_download': True,
1220 },
11b56058 1221 },
dd27fd17 1222 {
2d3d2997 1223 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1224 'note': '256k DASH audio (format 141) via DASH manifest',
1225 'info_dict': {
1226 'id': 'a9LDPn-MO4I',
1227 'ext': 'm4a',
1228 'upload_date': '20121002',
1229 'uploader_id': '8KVIDEO',
ec85ded8 1230 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1231 'description': '',
1232 'uploader': '8KVIDEO',
1233 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1234 },
4bc3a23e
PH
1235 'params': {
1236 'youtube_include_dash_manifest': True,
1237 'format': '141',
4919603f 1238 },
de3c7fe0 1239 'skip': 'format 141 not served anymore',
dd27fd17 1240 },
8bdd16b4 1241 # DASH manifest with encrypted signature
1242 {
1243 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1244 'info_dict': {
1245 'id': 'IB3lcPjvWLA',
1246 'ext': 'm4a',
1247 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1248 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1249 'duration': 244,
1250 'uploader': 'AfrojackVEVO',
1251 'uploader_id': 'AfrojackVEVO',
1252 'upload_date': '20131011',
cc2db878 1253 'abr': 129.495,
976ae3ea 1254 'like_count': int,
1255 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1256 'playable_in_embed': True,
1257 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1258 'view_count': int,
1259 'track': 'The Spark',
1260 'live_status': 'not_live',
1261 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1262 'channel': 'Afrojack',
1263 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1264 'tags': 'count:19',
1265 'availability': 'public',
1266 'categories': ['Music'],
1267 'age_limit': 0,
1268 'alt_title': 'The Spark',
6c73052c 1269 'channel_follower_count': int
8bdd16b4 1270 },
1271 'params': {
1272 'youtube_include_dash_manifest': True,
1273 'format': '141/bestaudio[ext=m4a]',
1274 },
1275 },
65c2fde2 1276 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1277 {
65c2fde2 1278 'note': 'Embed allowed age-gate video',
2d3d2997 1279 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1280 'info_dict': {
1281 'id': 'HtVdAasjOgU',
1282 'ext': 'mp4',
1283 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1284 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1285 'duration': 142,
c522adb1
JMF
1286 'uploader': 'The Witcher',
1287 'uploader_id': 'WitcherGame',
ec85ded8 1288 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1289 'upload_date': '20140605',
34952f09 1290 'age_limit': 18,
976ae3ea 1291 'categories': ['Gaming'],
1292 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1293 'availability': 'needs_auth',
1294 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1295 'like_count': int,
1296 'channel': 'The Witcher',
1297 'live_status': 'not_live',
1298 'tags': 'count:17',
1299 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1300 'playable_in_embed': True,
1301 'view_count': int,
6c73052c 1302 'channel_follower_count': int
c522adb1
JMF
1303 },
1304 },
65c2fde2 1305 {
1306 'note': 'Age-gate video with embed allowed in public site',
1307 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1308 'info_dict': {
1309 'id': 'HsUATh_Nc2U',
1310 'ext': 'mp4',
1311 'title': 'Godzilla 2 (Official Video)',
1312 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1313 'upload_date': '20200408',
1314 'uploader_id': 'FlyingKitty900',
1315 'uploader': 'FlyingKitty',
1316 'age_limit': 18,
976ae3ea 1317 'availability': 'needs_auth',
1318 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1319 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1320 'channel': 'FlyingKitty',
1321 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1322 'view_count': int,
1323 'categories': ['Entertainment'],
1324 'live_status': 'not_live',
1325 'tags': ['Flyingkitty', 'godzilla 2'],
1326 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1327 'like_count': int,
1328 'duration': 177,
1329 'playable_in_embed': True,
6c73052c 1330 'channel_follower_count': int
65c2fde2 1331 },
1332 },
1333 {
1334 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1335 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1336 'info_dict': {
1337 'id': 'Tq92D6wQ1mg',
1338 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1339 'ext': 'mp4',
17322130 1340 'upload_date': '20191228',
65c2fde2 1341 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1342 'uploader': 'Projekt Melody',
1343 'description': 'md5:17eccca93a786d51bc67646756894066',
1344 'age_limit': 18,
976ae3ea 1345 'like_count': int,
1346 'availability': 'needs_auth',
1347 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1348 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1349 'view_count': int,
1350 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1351 'channel': 'Projekt Melody',
1352 'live_status': 'not_live',
1353 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1354 'playable_in_embed': True,
1355 'categories': ['Entertainment'],
1356 'duration': 106,
1357 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1358 'comment_count': int,
6c73052c 1359 'channel_follower_count': int
65c2fde2 1360 },
1361 },
1362 {
1363 'note': 'Non-Agegated non-embeddable video',
1364 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1365 'info_dict': {
1366 'id': 'MeJVWBSsPAY',
1367 'ext': 'mp4',
1368 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1369 'uploader': 'Herr Lurik',
1370 'uploader_id': 'st3in234',
1371 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1372 'upload_date': '20130730',
976ae3ea 1373 'track': 'Such mich find mich',
1374 'age_limit': 0,
1375 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1376 'like_count': int,
1377 'playable_in_embed': False,
1378 'creator': 'OOMPH!',
1379 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1380 'view_count': int,
1381 'alt_title': 'Such mich find mich',
1382 'duration': 210,
1383 'channel': 'Herr Lurik',
1384 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1385 'categories': ['Music'],
1386 'availability': 'public',
1387 'uploader_url': 'http://www.youtube.com/user/st3in234',
1388 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1389 'live_status': 'not_live',
1390 'artist': 'OOMPH!',
6c73052c 1391 'channel_follower_count': int
65c2fde2 1392 },
1393 },
1394 {
1395 'note': 'Non-bypassable age-gated video',
1396 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1397 'only_matching': True,
1398 },
8bdd16b4 1399 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1400 # YouTube Red ad is not captured for creator
1401 {
1402 'url': '__2ABJjxzNo',
1403 'info_dict': {
1404 'id': '__2ABJjxzNo',
1405 'ext': 'mp4',
1406 'duration': 266,
1407 'upload_date': '20100430',
1408 'uploader_id': 'deadmau5',
1409 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1410 'creator': 'deadmau5',
1411 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1412 'uploader': 'deadmau5',
1413 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1414 'alt_title': 'Some Chords',
976ae3ea 1415 'availability': 'public',
1416 'tags': 'count:14',
1417 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1418 'view_count': int,
1419 'live_status': 'not_live',
1420 'channel': 'deadmau5',
1421 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1422 'like_count': int,
1423 'track': 'Some Chords',
1424 'artist': 'deadmau5',
1425 'playable_in_embed': True,
1426 'age_limit': 0,
1427 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1428 'categories': ['Music'],
1429 'album': 'Some Chords',
6c73052c 1430 'channel_follower_count': int
8bdd16b4 1431 },
1432 'expected_warnings': [
1433 'DASH manifest missing',
1434 ]
1435 },
067aa17e 1436 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1437 {
1438 'url': 'lqQg6PlCWgI',
1439 'info_dict': {
1440 'id': 'lqQg6PlCWgI',
1441 'ext': 'mp4',
556dbe7f 1442 'duration': 6085,
90227264 1443 'upload_date': '20150827',
cbe2bd91 1444 'uploader_id': 'olympic',
ec85ded8 1445 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1446 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1447 'uploader': 'Olympics',
cbe2bd91 1448 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1449 'like_count': int,
1450 'release_timestamp': 1343767800,
1451 'playable_in_embed': True,
1452 'categories': ['Sports'],
1453 'release_date': '20120731',
1454 'channel': 'Olympics',
1455 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1456 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1457 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1458 'age_limit': 0,
1459 'availability': 'public',
1460 'live_status': 'was_live',
1461 'view_count': int,
1462 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1463 'channel_follower_count': int
cbe2bd91
PH
1464 },
1465 'params': {
1466 'skip_download': 'requires avconv',
e52a40ab 1467 }
cbe2bd91 1468 },
6271f1ca
PH
1469 # Non-square pixels
1470 {
1471 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1472 'info_dict': {
1473 'id': '_b-2C3KPAM0',
1474 'ext': 'mp4',
1475 'stretched_ratio': 16 / 9.,
556dbe7f 1476 'duration': 85,
6271f1ca
PH
1477 'upload_date': '20110310',
1478 'uploader_id': 'AllenMeow',
ec85ded8 1479 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1480 '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 1481 'uploader': '孫ᄋᄅ',
6271f1ca 1482 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1483 'playable_in_embed': True,
1484 'channel': '孫ᄋᄅ',
1485 'age_limit': 0,
1486 'tags': 'count:11',
1487 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1488 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1489 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1490 'view_count': int,
1491 'categories': ['People & Blogs'],
1492 'like_count': int,
1493 'live_status': 'not_live',
1494 'availability': 'unlisted',
12a1b225 1495 'comment_count': int,
6c73052c 1496 'channel_follower_count': int
6271f1ca 1497 },
06b491eb
S
1498 },
1499 # url_encoded_fmt_stream_map is empty string
1500 {
1501 'url': 'qEJwOuvDf7I',
1502 'info_dict': {
1503 'id': 'qEJwOuvDf7I',
f57b7835 1504 'ext': 'webm',
06b491eb
S
1505 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1506 'description': '',
1507 'upload_date': '20150404',
1508 'uploader_id': 'spbelect',
1509 'uploader': 'Наблюдатели Петербурга',
1510 },
1511 'params': {
1512 'skip_download': 'requires avconv',
e323cf3f
S
1513 },
1514 'skip': 'This live event has ended.',
06b491eb 1515 },
067aa17e 1516 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1517 {
1518 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1519 'info_dict': {
1520 'id': 'FIl7x6_3R5Y',
eb6793ba 1521 'ext': 'webm',
da77d856
S
1522 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1523 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1524 'duration': 220,
da77d856
S
1525 'upload_date': '20150625',
1526 'uploader_id': 'dorappi2000',
ec85ded8 1527 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1528 'uploader': 'dorappi2000',
eb6793ba 1529 'formats': 'mincount:31',
da77d856 1530 },
eb6793ba 1531 'skip': 'not actual anymore',
2ee8f5d8 1532 },
8a1a26ce
YCH
1533 # DASH manifest with segment_list
1534 {
1535 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1536 'md5': '8ce563a1d667b599d21064e982ab9e31',
1537 'info_dict': {
1538 'id': 'CsmdDsKjzN8',
1539 'ext': 'mp4',
17ee98e1 1540 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1541 'uploader': 'Airtek',
1542 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1543 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1544 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1545 },
1546 'params': {
1547 'youtube_include_dash_manifest': True,
1548 'format': '135', # bestvideo
be49068d
S
1549 },
1550 'skip': 'This live event has ended.',
2ee8f5d8 1551 },
cf7e015f
S
1552 {
1553 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1554 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1555 'info_dict': {
545cc85d 1556 'id': 'jvGDaLqkpTg',
1557 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1558 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1559 },
1560 'playlist': [{
1561 'info_dict': {
545cc85d 1562 'id': 'jvGDaLqkpTg',
cf7e015f 1563 'ext': 'mp4',
545cc85d 1564 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1565 'description': 'md5:e03b909557865076822aa169218d6a5d',
1566 'duration': 10643,
1567 'upload_date': '20161111',
1568 'uploader': 'Team PGP',
1569 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1570 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1571 },
1572 }, {
1573 'info_dict': {
545cc85d 1574 'id': '3AKt1R1aDnw',
cf7e015f 1575 'ext': 'mp4',
545cc85d 1576 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1577 'description': 'md5:e03b909557865076822aa169218d6a5d',
1578 'duration': 10991,
1579 'upload_date': '20161111',
1580 'uploader': 'Team PGP',
1581 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1582 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1583 },
1584 }, {
1585 'info_dict': {
545cc85d 1586 'id': 'RtAMM00gpVc',
cf7e015f 1587 'ext': 'mp4',
545cc85d 1588 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1589 'description': 'md5:e03b909557865076822aa169218d6a5d',
1590 'duration': 10995,
1591 'upload_date': '20161111',
1592 'uploader': 'Team PGP',
1593 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1594 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1595 },
1596 }, {
1597 'info_dict': {
545cc85d 1598 'id': '6N2fdlP3C5U',
cf7e015f 1599 'ext': 'mp4',
545cc85d 1600 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1601 'description': 'md5:e03b909557865076822aa169218d6a5d',
1602 'duration': 10990,
1603 'upload_date': '20161111',
1604 'uploader': 'Team PGP',
1605 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1606 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1607 },
1608 }],
1609 'params': {
1610 'skip_download': True,
1611 },
65c2fde2 1612 'skip': 'Not multifeed anymore',
cbaed4bb 1613 },
f9f49d87 1614 {
067aa17e 1615 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1616 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1617 'info_dict': {
1618 'id': 'gVfLd0zydlo',
1619 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1620 },
1621 'playlist_count': 2,
be49068d 1622 'skip': 'Not multifeed anymore',
f9f49d87 1623 },
cbaed4bb 1624 {
2d3d2997 1625 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1626 'only_matching': True,
0e49d9a6 1627 },
6d4fc66b 1628 {
2d3d2997 1629 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1630 'only_matching': True,
1631 },
0e49d9a6 1632 {
067aa17e 1633 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1634 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1635 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1636 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1637 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1638 'info_dict': {
1639 'id': 'lsguqyKfVQg',
1640 'ext': 'mp4',
1641 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1642 'alt_title': 'Dark Walk',
0e49d9a6 1643 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1644 'duration': 133,
0e49d9a6
LL
1645 'upload_date': '20151119',
1646 'uploader_id': 'IronSoulElf',
ec85ded8 1647 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1648 'uploader': 'IronSoulElf',
11f9be09 1649 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1650 'track': 'Dark Walk',
1651 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1652 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1653 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1654 'categories': ['Film & Animation'],
1655 'view_count': int,
1656 'live_status': 'not_live',
1657 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1658 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1659 'tags': 'count:13',
1660 'availability': 'public',
1661 'channel': 'IronSoulElf',
1662 'playable_in_embed': True,
1663 'like_count': int,
1664 'age_limit': 0,
6c73052c 1665 'channel_follower_count': int
0e49d9a6
LL
1666 },
1667 'params': {
1668 'skip_download': True,
1669 },
1670 },
61f92af1 1671 {
067aa17e 1672 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1673 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1674 'only_matching': True,
1675 },
313dfc45
LL
1676 {
1677 # Video with yt:stretch=17:0
1678 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1679 'info_dict': {
1680 'id': 'Q39EVAstoRM',
1681 'ext': 'mp4',
1682 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1683 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1684 'upload_date': '20151107',
1685 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1686 'uploader': 'CH GAMER DROID',
1687 },
1688 'params': {
1689 'skip_download': True,
1690 },
be49068d 1691 'skip': 'This video does not exist.',
313dfc45 1692 },
201c1459 1693 {
1694 # Video with incomplete 'yt:stretch=16:'
1695 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1696 'only_matching': True,
1697 },
7caf9830
S
1698 {
1699 # Video licensed under Creative Commons
1700 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1701 'info_dict': {
1702 'id': 'M4gD1WSo5mA',
1703 'ext': 'mp4',
1704 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1705 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1706 'duration': 721,
17322130 1707 'upload_date': '20150128',
7caf9830 1708 'uploader_id': 'BerkmanCenter',
ec85ded8 1709 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1710 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1711 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1712 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1713 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1714 'like_count': int,
1715 'age_limit': 0,
1716 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1717 'channel': 'The Berkman Klein Center for Internet & Society',
1718 'availability': 'public',
1719 'view_count': int,
1720 'categories': ['Education'],
1721 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1722 'live_status': 'not_live',
1723 'playable_in_embed': True,
12a1b225 1724 'comment_count': int,
d5d1df8a 1725 'channel_follower_count': int,
1726 'chapters': list,
7caf9830
S
1727 },
1728 'params': {
1729 'skip_download': True,
1730 },
1731 },
fd050249
S
1732 {
1733 # Channel-like uploader_url
1734 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1735 'info_dict': {
1736 'id': 'eQcmzGIKrzg',
1737 'ext': 'mp4',
1738 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1739 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1740 'duration': 4060,
17322130 1741 'upload_date': '20151120',
eb6793ba 1742 'uploader': 'Bernie Sanders',
fd050249 1743 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1744 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1745 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1746 'playable_in_embed': True,
1747 'tags': 'count:12',
1748 'like_count': int,
1749 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1750 'age_limit': 0,
1751 'availability': 'public',
1752 'categories': ['News & Politics'],
1753 'channel': 'Bernie Sanders',
1754 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1755 'view_count': int,
1756 'live_status': 'not_live',
1757 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1758 'comment_count': int,
d5d1df8a 1759 'channel_follower_count': int,
1760 'chapters': list,
fd050249
S
1761 },
1762 'params': {
1763 'skip_download': True,
1764 },
1765 },
040ac686
S
1766 {
1767 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1768 'only_matching': True,
7f29cf54
S
1769 },
1770 {
067aa17e 1771 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1772 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1773 'only_matching': True,
6496ccb4
S
1774 },
1775 {
1776 # Rental video preview
1777 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1778 'info_dict': {
1779 'id': 'uGpuVWrhIzE',
1780 'ext': 'mp4',
1781 'title': 'Piku - Trailer',
1782 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1783 'upload_date': '20150811',
1784 'uploader': 'FlixMatrix',
1785 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1786 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1787 'license': 'Standard YouTube License',
1788 },
1789 'params': {
1790 'skip_download': True,
1791 },
eb6793ba 1792 'skip': 'This video is not available.',
022a5d66 1793 },
12afdc2a
S
1794 {
1795 # YouTube Red video with episode data
1796 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1797 'info_dict': {
1798 'id': 'iqKdEhx-dD4',
1799 'ext': 'mp4',
1800 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1801 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1802 'duration': 2085,
12afdc2a
S
1803 'upload_date': '20170118',
1804 'uploader': 'Vsauce',
1805 'uploader_id': 'Vsauce',
1806 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1807 'series': 'Mind Field',
1808 'season_number': 1,
1809 'episode_number': 1,
976ae3ea 1810 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1811 'tags': 'count:12',
1812 'view_count': int,
1813 'availability': 'public',
1814 'age_limit': 0,
1815 'channel': 'Vsauce',
1816 'episode': 'Episode 1',
1817 'categories': ['Entertainment'],
1818 'season': 'Season 1',
1819 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1820 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1821 'like_count': int,
1822 'playable_in_embed': True,
1823 'live_status': 'not_live',
6c73052c 1824 'channel_follower_count': int
12afdc2a
S
1825 },
1826 'params': {
1827 'skip_download': True,
1828 },
1829 'expected_warnings': [
1830 'Skipping DASH manifest',
1831 ],
1832 },
c7121fa7
S
1833 {
1834 # The following content has been identified by the YouTube community
1835 # as inappropriate or offensive to some audiences.
1836 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1837 'info_dict': {
1838 'id': '6SJNVb0GnPI',
1839 'ext': 'mp4',
1840 'title': 'Race Differences in Intelligence',
1841 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1842 'duration': 965,
1843 'upload_date': '20140124',
1844 'uploader': 'New Century Foundation',
1845 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1846 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1847 },
1848 'params': {
1849 'skip_download': True,
1850 },
545cc85d 1851 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1852 },
022a5d66
S
1853 {
1854 # itag 212
1855 'url': '1t24XAntNCY',
1856 'only_matching': True,
fd5c4aab
S
1857 },
1858 {
1859 # geo restricted to JP
1860 'url': 'sJL6WA-aGkQ',
1861 'only_matching': True,
1862 },
cd5a74a2
S
1863 {
1864 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1865 'only_matching': True,
1866 },
bc2ca1bb 1867 {
1868 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1869 'only_matching': True,
1870 },
1871 {
1872 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1873 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1874 'only_matching': True,
1875 },
825cd268
RA
1876 {
1877 # DRM protected
1878 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1879 'only_matching': True,
4fe54c12
S
1880 },
1881 {
1882 # Video with unsupported adaptive stream type formats
1883 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1884 'info_dict': {
1885 'id': 'Z4Vy8R84T1U',
1886 'ext': 'mp4',
1887 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1888 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1889 'duration': 433,
1890 'upload_date': '20130923',
1891 'uploader': 'Amelia Putri Harwita',
1892 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1893 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1894 'formats': 'maxcount:10',
1895 },
1896 'params': {
1897 'skip_download': True,
1898 'youtube_include_dash_manifest': False,
1899 },
5429d6a9 1900 'skip': 'not actual anymore',
5caabd3c 1901 },
1902 {
822b9d9c 1903 # Youtube Music Auto-generated description
5caabd3c 1904 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1905 'info_dict': {
1906 'id': 'MgNrAu2pzNs',
1907 'ext': 'mp4',
1908 'title': 'Voyeur Girl',
1909 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1910 'upload_date': '20190312',
5429d6a9
S
1911 'uploader': 'Stephen - Topic',
1912 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1913 'artist': 'Stephen',
1914 'track': 'Voyeur Girl',
1915 'album': 'it\'s too much love to know my dear',
1916 'release_date': '20190313',
1917 'release_year': 2019,
976ae3ea 1918 'alt_title': 'Voyeur Girl',
1919 'view_count': int,
1920 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1921 'playable_in_embed': True,
1922 'like_count': int,
1923 'categories': ['Music'],
1924 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1925 'channel': 'Stephen',
1926 'availability': 'public',
1927 'creator': 'Stephen',
1928 'duration': 169,
1929 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1930 'age_limit': 0,
1931 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1932 'tags': 'count:11',
1933 'live_status': 'not_live',
6c73052c 1934 'channel_follower_count': int
5caabd3c 1935 },
1936 'params': {
1937 'skip_download': True,
1938 },
1939 },
66b48727
RA
1940 {
1941 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1942 'only_matching': True,
1943 },
011e75e6
S
1944 {
1945 # invalid -> valid video id redirection
1946 'url': 'DJztXj2GPfl',
1947 'info_dict': {
1948 'id': 'DJztXj2GPfk',
1949 'ext': 'mp4',
1950 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1951 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1952 'upload_date': '20090125',
1953 'uploader': 'Prochorowka',
1954 'uploader_id': 'Prochorowka',
1955 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1956 'artist': 'Panjabi MC',
1957 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1958 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1959 },
1960 'params': {
1961 'skip_download': True,
1962 },
545cc85d 1963 'skip': 'Video unavailable',
ea74e00b
DP
1964 },
1965 {
1966 # empty description results in an empty string
1967 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1968 'info_dict': {
1969 'id': 'x41yOUIvK2k',
1970 'ext': 'mp4',
1971 'title': 'IMG 3456',
1972 'description': '',
1973 'upload_date': '20170613',
1974 'uploader_id': 'ElevageOrVert',
1975 'uploader': 'ElevageOrVert',
976ae3ea 1976 'view_count': int,
1977 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1978 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1979 'like_count': int,
1980 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1981 'tags': [],
1982 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1983 'availability': 'public',
1984 'age_limit': 0,
1985 'categories': ['Pets & Animals'],
1986 'duration': 7,
1987 'playable_in_embed': True,
1988 'live_status': 'not_live',
1989 'channel': 'ElevageOrVert',
6c73052c 1990 'channel_follower_count': int
ea74e00b
DP
1991 },
1992 'params': {
1993 'skip_download': True,
1994 },
1995 },
a0566bbf 1996 {
29f7c58a 1997 # with '};' inside yt initial data (see [1])
1998 # see [2] for an example with '};' inside ytInitialPlayerResponse
1999 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2000 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2001 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2002 'info_dict': {
2003 'id': 'CHqg6qOn4no',
2004 'ext': 'mp4',
2005 'title': 'Part 77 Sort a list of simple types in c#',
2006 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2007 'upload_date': '20130831',
2008 'uploader_id': 'kudvenkat',
2009 'uploader': 'kudvenkat',
976ae3ea 2010 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2011 'like_count': int,
2012 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2013 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2014 'live_status': 'not_live',
2015 'categories': ['Education'],
2016 'availability': 'public',
2017 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2018 'tags': 'count:12',
2019 'playable_in_embed': True,
2020 'age_limit': 0,
2021 'view_count': int,
2022 'duration': 522,
2023 'channel': 'kudvenkat',
12a1b225 2024 'comment_count': int,
d5d1df8a 2025 'channel_follower_count': int,
2026 'chapters': list,
a0566bbf 2027 },
2028 'params': {
2029 'skip_download': True,
2030 },
2031 },
29f7c58a 2032 {
2033 # another example of '};' in ytInitialData
2034 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2035 'only_matching': True,
2036 },
2037 {
2038 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2039 'only_matching': True,
2040 },
545cc85d 2041 {
cc2db878 2042 # https://github.com/ytdl-org/youtube-dl/pull/28094
2043 'url': 'OtqTfy26tG0',
2044 'info_dict': {
2045 'id': 'OtqTfy26tG0',
2046 'ext': 'mp4',
2047 'title': 'Burn Out',
2048 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2049 'upload_date': '20141120',
2050 'uploader': 'The Cinematic Orchestra - Topic',
2051 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2052 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2053 'artist': 'The Cinematic Orchestra',
2054 'track': 'Burn Out',
2055 'album': 'Every Day',
976ae3ea 2056 'like_count': int,
2057 'live_status': 'not_live',
2058 'alt_title': 'Burn Out',
2059 'duration': 614,
2060 'age_limit': 0,
2061 'view_count': int,
2062 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2063 'creator': 'The Cinematic Orchestra',
2064 'channel': 'The Cinematic Orchestra',
2065 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2066 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2067 'availability': 'public',
2068 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2069 'categories': ['Music'],
2070 'playable_in_embed': True,
6c73052c 2071 'channel_follower_count': int
cc2db878 2072 },
2073 'params': {
2074 'skip_download': True,
2075 },
545cc85d 2076 },
bc2ca1bb 2077 {
2078 # controversial video, only works with bpctr when authenticated with cookies
2079 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2080 'only_matching': True,
2081 },
a1a7907b 2082 {
2083 # controversial video, requires bpctr/contentCheckOk
2084 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2085 'info_dict': {
2086 'id': 'SZJvDhaSDnc',
2087 'ext': 'mp4',
2088 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2089 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2090 'uploader': 'CBS Mornings',
11f9be09 2091 'uploader_id': 'CBSThisMorning',
a1a7907b 2092 'upload_date': '20140716',
976ae3ea 2093 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2094 'duration': 170,
2095 'categories': ['News & Politics'],
2096 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2097 'view_count': int,
2098 'channel': 'CBS Mornings',
2099 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2100 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2101 'age_limit': 18,
2102 'availability': 'needs_auth',
2103 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2104 'like_count': int,
2105 'live_status': 'not_live',
2106 'playable_in_embed': True,
6c73052c 2107 'channel_follower_count': int
a1a7907b 2108 }
2109 },
f7ad7160 2110 {
2111 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2112 'url': 'cBvYw8_A0vQ',
2113 'info_dict': {
2114 'id': 'cBvYw8_A0vQ',
2115 'ext': 'mp4',
2116 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2117 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2118 'upload_date': '20201120',
2119 'uploader': 'Walk around Japan',
2120 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2121 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2122 'duration': 1456,
2123 'categories': ['Travel & Events'],
2124 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2125 'view_count': int,
2126 'channel': 'Walk around Japan',
2127 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2128 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2129 'age_limit': 0,
2130 'availability': 'public',
2131 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2132 'live_status': 'not_live',
2133 'playable_in_embed': True,
6c73052c 2134 'channel_follower_count': int
f7ad7160 2135 },
2136 'params': {
2137 'skip_download': True,
2138 },
0fb983f6 2139 }, {
2140 # Has multiple audio streams
2141 'url': 'WaOKSUlf4TM',
2142 'only_matching': True
9297939e 2143 }, {
2144 # Requires Premium: has format 141 when requested using YTM url
2145 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2146 'only_matching': True
2147 }, {
120916da 2148 # multiple subtitles with same lang_code
2149 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2150 'only_matching': True,
109dd3b2 2151 }, {
2152 # Force use android client fallback
2153 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2154 'info_dict': {
2155 'id': 'YOelRv7fMxY',
11f9be09 2156 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2157 'ext': '3gp',
2158 'upload_date': '20210624',
2159 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2160 'uploader': 'colinfurze',
11f9be09 2161 'uploader_id': 'colinfurze',
109dd3b2 2162 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2163 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2164 'duration': 596,
2165 'categories': ['Entertainment'],
2166 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2167 'view_count': int,
2168 'channel': 'colinfurze',
2169 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2170 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2171 'age_limit': 0,
2172 'availability': 'public',
2173 'like_count': int,
2174 'live_status': 'not_live',
2175 'playable_in_embed': True,
d5d1df8a 2176 'channel_follower_count': int,
2177 'chapters': list,
109dd3b2 2178 },
2179 'params': {
2180 'format': '17', # 3gp format available on android
2181 'extractor_args': {'youtube': {'player_client': ['android']}},
2182 },
120916da 2183 },
109dd3b2 2184 {
2185 # Skip download of additional client configs (remix client config in this case)
2186 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2187 'only_matching': True,
2188 'params': {
2189 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2190 },
8fc54b12 2191 }, {
2192 # shorts
2193 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2194 'only_matching': True,
9222c381 2195 }, {
2196 'note': 'Storyboards',
2197 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2198 'info_dict': {
2199 'id': '5KLPxDtMqe8',
2200 'ext': 'mhtml',
2201 'format_id': 'sb0',
2202 'title': 'Your Brain is Plastic',
2203 'uploader_id': 'scishow',
2204 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2205 'upload_date': '20140324',
2206 'uploader': 'SciShow',
976ae3ea 2207 'like_count': int,
2208 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2209 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2210 'view_count': int,
2211 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2212 'playable_in_embed': True,
2213 'tags': 'count:12',
2214 'uploader_url': 'http://www.youtube.com/user/scishow',
2215 'availability': 'public',
2216 'channel': 'SciShow',
2217 'live_status': 'not_live',
2218 'duration': 248,
2219 'categories': ['Education'],
2220 'age_limit': 0,
d5d1df8a 2221 'channel_follower_count': int,
2222 'chapters': list,
9222c381 2223 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2224 }, {
2225 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2226 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2227 'info_dict': {
2228 'id': '2NUZ8W2llS4',
2229 'ext': 'mp4',
2230 'title': 'The NP that test your phone performance 🙂',
2231 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2232 'uploader': 'Leon Nguyen',
2233 'uploader_id': 'VNSXIII',
2234 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2235 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2236 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2237 'duration': 21,
2238 'view_count': int,
2239 'age_limit': 0,
2240 'categories': ['Gaming'],
2241 'tags': 'count:23',
2242 'playable_in_embed': True,
2243 'live_status': 'not_live',
2244 'upload_date': '20220103',
2245 'like_count': int,
2246 'availability': 'public',
2247 'channel': 'Leon Nguyen',
2248 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2249 'comment_count': int,
992f9a73 2250 'channel_follower_count': int
2251 }
1ff88b7a 2252 }, {
2253 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2254 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2255 'info_dict': {
2256 'id': '2NUZ8W2llS4',
2257 'ext': 'mp4',
2258 'title': 'The NP that test your phone performance 🙂',
2259 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2260 'uploader': 'Leon Nguyen',
2261 'uploader_id': 'VNSXIII',
2262 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2263 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2264 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2265 'duration': 21,
2266 'view_count': int,
2267 'age_limit': 0,
2268 'categories': ['Gaming'],
2269 'tags': 'count:23',
2270 'playable_in_embed': True,
2271 'live_status': 'not_live',
2272 'upload_date': '20220102',
2273 'like_count': int,
2274 'availability': 'public',
2275 'channel': 'Leon Nguyen',
2276 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2277 'comment_count': int,
2278 'channel_follower_count': int
2279 },
2280 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2281 }, {
2282 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2283 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2284 'info_dict': {
2285 'id': 'mzZzzBU6lrM',
2286 'ext': 'mp4',
2287 'title': 'I Met GeorgeNotFound In Real Life...',
2288 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2289 'uploader': 'Quackity',
2290 'uploader_id': 'QuackityHQ',
2291 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2292 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2293 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2294 'duration': 955,
2295 'view_count': int,
2296 'age_limit': 0,
2297 'categories': ['Entertainment'],
2298 'tags': 'count:26',
2299 'playable_in_embed': True,
2300 'live_status': 'not_live',
2301 'release_timestamp': 1641172509,
2302 'release_date': '20220103',
2303 'upload_date': '20220103',
2304 'like_count': int,
2305 'availability': 'public',
2306 'channel': 'Quackity',
2307 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2308 'channel_follower_count': int
2309 }
2310 },
2311 { # continuous livestream. Microformat upload date should be preferred.
2312 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2313 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2314 'info_dict': {
2315 'id': 'kgx4WGK0oNU',
2316 '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}',
2317 'ext': 'mp4',
2318 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2319 'availability': 'public',
2320 'age_limit': 0,
2321 'release_timestamp': 1637975704,
2322 'upload_date': '20210619',
2323 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2324 'live_status': 'is_live',
2325 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2326 'uploader': '阿鲍Abao',
2327 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2328 'channel': 'Abao in Tokyo',
2329 'channel_follower_count': int,
2330 'release_date': '20211127',
2331 'tags': 'count:39',
2332 'categories': ['People & Blogs'],
2333 'like_count': int,
2334 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2335 'view_count': int,
2336 'playable_in_embed': True,
2337 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2338 'concurrent_view_count': int,
992f9a73 2339 },
2340 'params': {'skip_download': True}
6e634cbe 2341 }, {
2342 # Story. Requires specific player params to work.
ee27297f 2343 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2344 'info_dict': {
ee27297f 2345 'id': 'vv8qTUWmulI',
6e634cbe 2346 'ext': 'mp4',
ee27297f 2347 'availability': 'unlisted',
2348 'view_count': int,
2349 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2350 'upload_date': '20220526',
2351 'categories': ['Education'],
2352 'title': 'Story',
2353 'channel': 'IT\'S HISTORY',
2354 'description': '',
2355 'uploader_id': 'BlastfromthePast',
2356 'duration': 12,
2357 'uploader': 'IT\'S HISTORY',
6e634cbe 2358 'playable_in_embed': True,
6e634cbe 2359 'age_limit': 0,
6e634cbe 2360 'live_status': 'not_live',
ee27297f 2361 'tags': [],
2362 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2363 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2364 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2365 },
2366 'skip': 'stories get removed after some period of time',
ee27297f 2367 }, {
2368 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2369 'info_dict': {
2370 'id': 'tjjjtzRLHvA',
2371 'ext': 'mp4',
2372 'title': 'ハッシュタグ無し };if window.ytcsi',
2373 'upload_date': '20220323',
2374 'like_count': int,
2375 'availability': 'unlisted',
2376 'channel': 'nao20010128nao',
2377 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2378 'age_limit': 0,
2379 'uploader': 'nao20010128nao',
2380 'uploader_id': 'nao20010128nao',
2381 'categories': ['Music'],
6e634cbe 2382 'view_count': int,
2383 'description': '',
ee27297f 2384 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2385 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2386 'live_status': 'not_live',
2387 'playable_in_embed': True,
2388 'channel_follower_count': int,
2389 'duration': 6,
2390 'tags': [],
2391 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2392 }
c26f9b99 2393 }, {
2394 # Prefer primary title+description language metadata by default
2395 # Do not prefer translated description if primary is empty
2396 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2397 'info_dict': {
2398 'id': 'el3E4MbxRqQ',
2399 'ext': 'mp4',
2400 'title': 'dlp test video 2 - primary sv no desc',
2401 'description': '',
2402 'channel': 'cole-dlp-test-acc',
2403 'tags': [],
2404 'view_count': int,
2405 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2406 'like_count': int,
2407 'playable_in_embed': True,
2408 'availability': 'unlisted',
2409 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2410 'age_limit': 0,
2411 'duration': 5,
2412 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2413 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2414 'live_status': 'not_live',
2415 'upload_date': '20220908',
2416 'categories': ['People & Blogs'],
2417 'uploader': 'cole-dlp-test-acc',
2418 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2419 },
2420 'params': {'skip_download': True}
2421 }, {
2422 # Extractor argument: prefer translated title+description
2423 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2424 'info_dict': {
2425 'id': 'gHKT4uU8Zng',
2426 'ext': 'mp4',
2427 'channel': 'cole-dlp-test-acc',
2428 'tags': [],
2429 'duration': 5,
2430 'live_status': 'not_live',
2431 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2432 'upload_date': '20220728',
2433 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2434 'view_count': int,
2435 'categories': ['People & Blogs'],
2436 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2437 'title': 'dlp test video title translated (fr)',
2438 'availability': 'public',
2439 'uploader': 'cole-dlp-test-acc',
2440 'age_limit': 0,
2441 'description': 'dlp test video description translated (fr)',
2442 'playable_in_embed': True,
2443 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2444 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2445 },
2446 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2447 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2448 }, {
2449 'note': '6 channel audio',
2450 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2451 'only_matching': True,
6e634cbe 2452 }
2eb88d95
PH
2453 ]
2454
f2e8dbcc 2455 _WEBPAGE_TESTS = [
2456 # YouTube <object> embed
2457 {
2458 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2459 'md5': '873c81d308b979f0e23ee7e620b312a3',
2460 'info_dict': {
2461 'id': 'msN87y-iEx0',
2462 'ext': 'mp4',
2463 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2464 'upload_date': '20080526',
2465 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2466 'uploader': 'Christopher Sykes',
2467 'uploader_id': 'ChristopherJSykes',
2468 'age_limit': 0,
2469 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2470 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2471 'playable_in_embed': True,
2472 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2473 'like_count': int,
2474 'comment_count': int,
2475 'channel': 'Christopher Sykes',
2476 'live_status': 'not_live',
2477 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2478 'availability': 'public',
2479 'duration': 195,
2480 'view_count': int,
2481 'categories': ['Science & Technology'],
2482 'channel_follower_count': int,
2483 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2484 },
2485 'params': {
2486 'skip_download': True,
2487 }
2488 },
2489 ]
2490
201c1459 2491 @classmethod
2492 def suitable(cls, url):
4dfbf869 2493 from ..utils import parse_qs
2494
201c1459 2495 qs = parse_qs(url)
2496 if qs.get('list', [None])[0]:
2497 return False
86e5f3ed 2498 return super().suitable(url)
201c1459 2499
e0df6211 2500 def __init__(self, *args, **kwargs):
86e5f3ed 2501 super().__init__(*args, **kwargs)
545cc85d 2502 self._code_cache = {}
83799698 2503 self._player_cache = {}
e0df6211 2504
4d37720a 2505 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2506 lock = threading.Lock()
185bf310 2507 start_time = time.time()
adbc4ec4
THD
2508 formats = [f for f in formats if f.get('is_from_start')]
2509
185bf310 2510 def refetch_manifest(format_id, delay):
2511 nonlocal formats, start_time, is_live
2512 if time.time() <= start_time + delay:
adbc4ec4
THD
2513 return
2514
2515 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2516 video_details = traverse_obj(
2517 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2518 microformats = traverse_obj(
2519 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2520 expected_type=dict, default=[])
4d37720a
L
2521 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2522 is_live = live_status == 'is_live'
185bf310 2523 start_time = time.time()
adbc4ec4 2524
185bf310 2525 def mpd_feed(format_id, delay):
adbc4ec4
THD
2526 """
2527 @returns (manifest_url, manifest_stream_number, is_live) or None
2528 """
2529 with lock:
185bf310 2530 refetch_manifest(format_id, delay)
adbc4ec4
THD
2531
2532 f = next((f for f in formats if f['format_id'] == format_id), None)
2533 if not f:
185bf310 2534 if not is_live:
2535 self.to_screen(f'{video_id}: Video is no longer live')
2536 else:
2537 self.report_warning(
2538 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2539 return None
2540 return f['manifest_url'], f['manifest_stream_number'], is_live
2541
2542 for f in formats:
4d37720a
L
2543 f['is_live'] = is_live
2544 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2545 live_start_time, mpd_feed, not is_live and f.copy())
2546 if is_live:
2547 f['fragments'] = gen
2548 f['protocol'] = 'http_dash_segments_generator'
2549 else:
2550 f['fragments'] = LazyList(gen({}))
2551 del f['is_from_start']
adbc4ec4 2552
4d37720a 2553 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2554 FETCH_SPAN, MAX_DURATION = 5, 432000
2555
2556 mpd_url, stream_number, is_live = None, None, True
2557
2558 begin_index = 0
2559 download_start_time = ctx.get('start') or time.time()
2560
2561 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2562 if lack_early_segments:
2563 self.report_warning(bug_reports_message(
2564 'Starting download from the last 120 hours of the live stream since '
2565 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2566 lack_early_segments = True
2567
2568 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2569 fragments, fragment_base_url = None, None
2570
a539f065 2571 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2572 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2573 # Obtain from MPD's maximum seq value
2574 old_mpd_url = mpd_url
185bf310 2575 last_error = ctx.pop('last_error', None)
14f25df2 2576 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2577 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2578 or (mpd_url, stream_number, False))
2579 if not refresh_sequence:
2580 if expire_fast and not is_live:
2581 return False, last_seq
2582 elif old_mpd_url == mpd_url:
2583 return True, last_seq
4d37720a
L
2584 if manifestless_orig_fmt:
2585 fmt_info = manifestless_orig_fmt
2586 else:
2587 try:
2588 fmts, _ = self._extract_mpd_formats_and_subtitles(
2589 mpd_url, None, note=False, errnote=False, fatal=False)
2590 except ExtractorError:
2591 fmts = None
2592 if not fmts:
2593 no_fragment_score += 2
2594 return False, last_seq
2595 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2596 fragments = fmt_info['fragments']
2597 fragment_base_url = fmt_info['fragment_base_url']
2598 assert fragment_base_url
2599
2600 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2601 return True, _last_seq
2602
4d37720a 2603 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2604 while is_live:
2605 fetch_time = time.time()
2606 if no_fragment_score > 30:
2607 return
2608 if last_segment_url:
2609 # Obtain from "X-Head-Seqnum" header value from each segment
2610 try:
2611 urlh = self._request_webpage(
2612 last_segment_url, None, note=False, errnote=False, fatal=False)
2613 except ExtractorError:
2614 urlh = None
2615 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2616 if last_seq is None:
a539f065 2617 no_fragment_score += 2
adbc4ec4
THD
2618 last_segment_url = None
2619 continue
2620 else:
a539f065
LNO
2621 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2622 no_fragment_score += 2
185bf310 2623 if not should_continue:
adbc4ec4
THD
2624 continue
2625
2626 if known_idx > last_seq:
2627 last_segment_url = None
2628 continue
2629
2630 last_seq += 1
2631
2632 if begin_index < 0 and known_idx < 0:
2633 # skip from the start when it's negative value
2634 known_idx = last_seq + begin_index
2635 if lack_early_segments:
2636 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2637 try:
2638 for idx in range(known_idx, last_seq):
2639 # do not update sequence here or you'll get skipped some part of it
a539f065 2640 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2641 if not should_continue:
adbc4ec4
THD
2642 known_idx = idx - 1
2643 raise ExtractorError('breaking out of outer loop')
2644 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2645 yield {
2646 'url': last_segment_url,
36195c44 2647 'fragment_count': last_seq,
adbc4ec4
THD
2648 }
2649 if known_idx == last_seq:
2650 no_fragment_score += 5
2651 else:
2652 no_fragment_score = 0
2653 known_idx = last_seq
2654 except ExtractorError:
2655 continue
2656
4d37720a
L
2657 if manifestless_orig_fmt:
2658 # Stop at the first iteration if running for post-live manifestless;
2659 # fragment count no longer increase since it starts
2660 break
2661
adbc4ec4
THD
2662 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2663
b6de707d 2664 def _extract_player_url(self, *ytcfgs, webpage=None):
2665 player_url = traverse_obj(
2666 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2667 get_all=False, expected_type=str)
11f9be09 2668 if not player_url:
b6de707d 2669 return
60f393e4 2670 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2671
b6de707d 2672 def _download_player_url(self, video_id, fatal=False):
2673 res = self._download_webpage(
2674 'https://www.youtube.com/iframe_api',
2675 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2676 if res:
2677 player_version = self._search_regex(
2678 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2679 if player_version:
2680 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2681
60064c53
PH
2682 def _signature_cache_id(self, example_sig):
2683 """ Return a string representation of a signature """
14f25df2 2684 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2685
e40c758c
S
2686 @classmethod
2687 def _extract_player_info(cls, player_url):
2688 for player_re in cls._PLAYER_INFO_RE:
2689 id_m = re.search(player_re, player_url)
2690 if id_m:
2691 break
2692 else:
c081b35c 2693 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2694 return id_m.group('id')
e40c758c 2695
404f611f 2696 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2697 player_id = self._extract_player_info(player_url)
2698 if player_id not in self._code_cache:
1276a43a 2699 code = self._download_webpage(
109dd3b2 2700 player_url, video_id, fatal=fatal,
2701 note='Downloading player ' + player_id,
2702 errnote='Download of %s failed' % player_url)
1276a43a 2703 if code:
2704 self._code_cache[player_id] = code
404f611f 2705 return self._code_cache.get(player_id)
109dd3b2 2706
e40c758c 2707 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2708 player_id = self._extract_player_info(player_url)
e0df6211 2709
c4417ddb 2710 # Read from filesystem cache
86e5f3ed 2711 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2712 assert os.path.basename(func_id) == func_id
a0e07d31 2713
ae61d108 2714 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2715 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2716
580ce007 2717 if not cache_spec:
2718 code = self._load_player(video_id, player_url)
404f611f 2719 if code:
109dd3b2 2720 res = self._parse_sig_js(code)
ac668111 2721 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2722 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2723 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2724
2725 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2726
60064c53 2727 def _print_sig_code(self, func, example_sig):
404f611f 2728 if not self.get_param('youtube_print_sig_code'):
2729 return
2730
edf3e38e
PH
2731 def gen_sig_code(idxs):
2732 def _genslice(start, end, step):
78caa52a 2733 starts = '' if start == 0 else str(start)
8bcc8756 2734 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2735 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2736 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2737
2738 step = None
7af808a5
PH
2739 # Quelch pyflakes warnings - start will be set when step is set
2740 start = '(Never used)'
edf3e38e
PH
2741 for i, prev in zip(idxs[1:], idxs[:-1]):
2742 if step is not None:
2743 if i - prev == step:
2744 continue
2745 yield _genslice(start, prev, step)
2746 step = None
2747 continue
2748 if i - prev in [-1, 1]:
2749 step = i - prev
2750 start = prev
2751 continue
2752 else:
78caa52a 2753 yield 's[%d]' % prev
edf3e38e 2754 if step is None:
78caa52a 2755 yield 's[%d]' % i
edf3e38e
PH
2756 else:
2757 yield _genslice(start, i, step)
2758
ac668111 2759 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2760 cache_res = func(test_string)
edf3e38e 2761 cache_spec = [ord(c) for c in cache_res]
78caa52a 2762 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2763 signature_id_tuple = '(%s)' % (
14f25df2 2764 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2765 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2766 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2767 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2768
e0df6211
PH
2769 def _parse_sig_js(self, jscode):
2770 funcname = self._search_regex(
abefc03f
S
2771 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2772 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
2773 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2774 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2775 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}\(a,\d+\)',
2776 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 2777 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2778 # Obsolete patterns
2779 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2780 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2781 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2782 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2783 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2784 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2785 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2786 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2787 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2788
2789 jsi = JSInterpreter(jscode)
2790 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2791 return lambda s: initial_function([s])
2792
580ce007 2793 def _cached(self, func, *cache_id):
2794 def inner(*args, **kwargs):
2795 if cache_id not in self._player_cache:
2796 try:
2797 self._player_cache[cache_id] = func(*args, **kwargs)
2798 except ExtractorError as e:
2799 self._player_cache[cache_id] = e
2800 except Exception as e:
2801 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2802
2803 ret = self._player_cache[cache_id]
2804 if isinstance(ret, Exception):
2805 raise ret
2806 return ret
2807 return inner
2808
545cc85d 2809 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2810 """Turn the encrypted s field into a working signature"""
580ce007 2811 extract_sig = self._cached(
2812 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2813 func = extract_sig(video_id, player_url, s)
2814 self._print_sig_code(func, s)
2815 return func(s)
404f611f 2816
2817 def _decrypt_nsig(self, s, video_id, player_url):
2818 """Turn the encrypted n field into a working signature"""
2819 if player_url is None:
2820 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2821 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2822
b505e851 2823 try:
2824 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2825 except ExtractorError as e:
2826 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 2827 if self.get_param('youtube_print_sig_code'):
2828 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2829
25836db6 2830 try:
2831 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2832 ret = extract_nsig(jsi, func_code)(s)
2833 except JSInterpreter.Exception as e:
2834 try:
992dc6b4 2835 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2836 except ExtractorError:
2837 raise e
2838 self.report_warning(
2839 f'Native nsig extraction failed: Trying with PhantomJS\n'
2840 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 2841 self.write_debug(e, only_once=True)
25836db6 2842
2843 args, func_body = func_code
2844 ret = jsi.execute(
2845 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2846 video_id=video_id, note='Executing signature code').strip()
580ce007 2847
2848 self.write_debug(f'Decrypted nsig {s} => {ret}')
2849 return ret
2850
90a1df30 2851 def _extract_n_function_name(self, jscode):
2852 funcname, idx = self._search_regex(
2853 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2854 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2855 if not idx:
2856 return funcname
2857
2858 return json.loads(js_to_json(self._search_regex(
2859 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2860 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2861
580ce007 2862 def _extract_n_function_code(self, video_id, player_url):
404f611f 2863 player_id = self._extract_player_info(player_url)
05deb747 2864 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 2865 jscode = func_code or self._load_player(video_id, player_url)
2866 jsi = JSInterpreter(jscode)
404f611f 2867
2868 if func_code:
580ce007 2869 return jsi, player_id, func_code
404f611f 2870
b505e851 2871 func_name = self._extract_n_function_name(jscode)
2872
2873 # For redundancy
2874 func_code = self._search_regex(
2875 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
2876 # NB: The end of the regex is intentionally kept strict
2877 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
2878 jscode, 'nsig function', group=('var', 'code'), default=None)
2879 if func_code:
2880 func_code = ([func_code[0]], func_code[1])
2881 else:
2882 self.write_debug('Extracting nsig function with jsinterp')
2883 func_code = jsi.extract_function_code(func_name)
2884
580ce007 2885 self.cache.store('youtube-nsig', player_id, func_code)
2886 return jsi, player_id, func_code
2887
2888 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 2889 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2890
580ce007 2891 def extract_nsig(s):
25836db6 2892 try:
2893 ret = func([s])
2894 except JSInterpreter.Exception:
2895 raise
2896 except Exception as e:
2897 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2898
f6ca640b 2899 if ret.startswith('enhanced_except_'):
25836db6 2900 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 2901 return ret
580ce007 2902
2903 return extract_nsig
e0df6211 2904
109dd3b2 2905 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2906 """
2907 Extract signatureTimestamp (sts)
2908 Required to tell API what sig/player version is in use.
2909 """
2910 sts = None
2911 if isinstance(ytcfg, dict):
2912 sts = int_or_none(ytcfg.get('STS'))
2913
2914 if not sts:
2915 # Attempt to extract from player
2916 if player_url is None:
2917 error_msg = 'Cannot extract signature timestamp without player_url.'
2918 if fatal:
2919 raise ExtractorError(error_msg)
2920 self.report_warning(error_msg)
2921 return
404f611f 2922 code = self._load_player(video_id, player_url, fatal=fatal)
2923 if code:
109dd3b2 2924 sts = int_or_none(self._search_regex(
2925 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2926 'JS player signature timestamp', group='sts', fatal=fatal))
2927 return sts
2928
11f9be09 2929 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2930 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2931 label = 'fully ' if is_full else ''
2932 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2933 expected_type=url_or_none)
2934 if not url:
2935 self.report_warning(f'Unable to mark {label}watched')
2936 return
14f25df2 2937 parsed_url = urllib.parse.urlparse(url)
2938 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2939
2940 # cpn generation algorithm is reverse engineered from base.js.
2941 # In fact it works even with dummy cpn.
2942 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2943 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2944
2945 # # more consistent results setting it to right before the end
2946 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2947
2948 qs.update({
2949 'ver': ['2'],
2950 'cpn': [cpn],
2951 'cmt': video_length,
2952 'el': 'detailpage', # otherwise defaults to "shorts"
2953 })
2954
2955 if is_full:
2956 # these seem to mark watchtime "history" in the real world
2957 # they're required, so send in a single value
2958 qs.update({
5318156f 2959 'st': 0,
06cc8f10
B
2960 'et': video_length,
2961 })
2962
14f25df2 2963 url = urllib.parse.urlunparse(
2964 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2965
2966 self._download_webpage(
2967 url, video_id, f'Marking {label}watched',
2968 'Unable to mark watched', fatal=False)
d77ab8e2 2969
bfd973ec 2970 @classmethod
2971 def _extract_from_webpage(cls, url, webpage):
2972 # Invidious Instances
2973 # https://github.com/yt-dlp/yt-dlp/issues/195
2974 # https://github.com/iv-org/invidious/pull/1730
2975 mobj = re.search(
2976 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2977 webpage)
2978 if mobj:
2979 yield cls.url_result(mobj.group('url'), cls)
2980 raise cls.StopExtraction()
2981
2982 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2983
2984 # lazyYT YouTube embed
bfd973ec 2985 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2986 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2987
2988 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2989 for m in re.findall(r'''(?x)<div[^>]+
2990 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2991 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2992 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2993
97665381
PH
2994 @classmethod
2995 def extract_id(cls, url):
ae61d108 2996 video_id = cls.get_temp_id(url)
2997 if not video_id:
2998 raise ExtractorError(f'Invalid URL: {url}')
2999 return video_id
c5e8d7af 3000
7c365c21 3001 def _extract_chapters_from_json(self, data, duration):
3002 chapter_list = traverse_obj(
3003 data, (
3004 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3005 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3006 ), expected_type=list)
3007
3008 return self._extract_chapters(
3009 chapter_list,
3010 chapter_time=lambda chapter: float_or_none(
3011 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3012 chapter_title=lambda chapter: traverse_obj(
3013 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3014 duration=duration)
3015
3016 def _extract_chapters_from_engagement_panel(self, data, duration):
3017 content_list = traverse_obj(
8bdd16b4 3018 data,
7c365c21 3019 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 3020 expected_type=list, default=[])
052e1350 3021 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3022 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3023
1890fc63 3024 return next(filter(None, (
3025 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3026 chapter_time, chapter_title, duration)
3027 for contents in content_list)), [])
7c365c21 3028
1890fc63 3029 def _extract_chapters_from_description(self, description, duration):
3030 return self._extract_chapters(
3031 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
3032 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
3033 duration=duration, strict=False)
84213ea8 3034
1890fc63 3035 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3036 if not duration:
3037 return
3038 chapter_list = [{
3039 'start_time': chapter_time(chapter),
3040 'title': chapter_title(chapter),
3041 } for chapter in chapter_list or []]
3042 if not strict:
3043 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3044
a3976e07 3045 chapters = [{'start_time': 0}]
1890fc63 3046 for idx, chapter in enumerate(chapter_list):
a3976e07 3047 if chapter['start_time'] is None:
1890fc63 3048 self.report_warning(f'Incomplete chapter {idx}')
3049 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3050 chapters.append(chapter)
709ee214 3051 elif chapter not in chapters:
3052 self.report_warning(
3053 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3054 return chapters[1:]
84213ea8 3055
a1c5d2ca
M
3056 def _extract_comment(self, comment_renderer, parent=None):
3057 comment_id = comment_renderer.get('commentId')
3058 if not comment_id:
3059 return
fe93e2c4 3060
052e1350 3061 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3062
c26f9b99 3063 # Timestamp is an estimate calculated from the current time and time_text
3064 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3065 timestamp = self._parse_time_text(time_text)
3066
052e1350 3067 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3068 author_id = try_get(comment_renderer,
14f25df2 3069 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3070
49bd8c66 3071 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3072 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3073 author_thumbnail = try_get(comment_renderer,
14f25df2 3074 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3075
3076 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3077 is_favorited = 'creatorHeart' in (try_get(
3078 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3079 return {
3080 'id': comment_id,
3081 'text': text,
d92f5d5a 3082 'timestamp': timestamp,
a1c5d2ca
M
3083 'time_text': time_text,
3084 'like_count': votes,
97524332 3085 'is_favorited': is_favorited,
a1c5d2ca
M
3086 'author': author,
3087 'author_id': author_id,
3088 'author_thumbnail': author_thumbnail,
3089 'author_is_uploader': author_is_uploader,
3090 'parent': parent or 'root'
3091 }
3092
46383212 3093 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3094
3095 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3096
3097 def extract_header(contents):
2d6659b9 3098 _continuation = None
3099 for content in contents:
46383212 3100 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3101 expected_comment_count = self._get_count(
3102 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3103
2d6659b9 3104 if expected_comment_count:
46383212 3105 tracker['est_total'] = expected_comment_count
3106 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3107 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3108
3109 sort_menu_item = try_get(
3110 comments_header_renderer,
3111 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3112 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3113
3114 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3115 if not _continuation:
3116 continue
3117
46383212 3118 sort_text = str_or_none(sort_menu_item.get('title'))
3119 if not sort_text:
2d6659b9 3120 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3121 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3122 break
a2160aa4 3123 return _continuation
a1c5d2ca 3124
2d6659b9 3125 def extract_thread(contents):
a1c5d2ca 3126 if not parent:
46383212 3127 tracker['current_page_thread'] = 0
a1c5d2ca 3128 for content in contents:
46383212 3129 if not parent and tracker['total_parent_comments'] >= max_parents:
3130 yield
a1c5d2ca 3131 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3132 comment_renderer = get_first(
3133 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3134 expected_type=dict, default={})
a1c5d2ca 3135
a1c5d2ca
M
3136 comment = self._extract_comment(comment_renderer, parent)
3137 if not comment:
3138 continue
46383212 3139
3140 tracker['running_total'] += 1
3141 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3142 yield comment
46383212 3143
a1c5d2ca
M
3144 # Attempt to get the replies
3145 comment_replies_renderer = try_get(
3146 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3147
3148 if comment_replies_renderer:
46383212 3149 tracker['current_page_thread'] += 1
a1c5d2ca 3150 comment_entries_iter = self._comment_entries(
99e9e001 3151 comment_replies_renderer, ytcfg, video_id,
46383212 3152 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3153 yield from itertools.islice(comment_entries_iter, min(
3154 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3155
46383212 3156 # Keeps track of counts across recursive calls
3157 if not tracker:
3158 tracker = dict(
3159 running_total=0,
3160 est_total=0,
3161 current_page_thread=0,
3162 total_parent_comments=0,
3163 total_reply_comments=0)
3164
3165 # TODO: Deprecated
2d6659b9 3166 # YouTube comments have a max depth of 2
46383212 3167 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3168 if max_depth:
da4db748 3169 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3170 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3171 if max_depth == 1 and parent:
3172 return
a1c5d2ca 3173
46383212 3174 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3175 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3176
46383212 3177 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3178
46383212 3179 response = None
6e634cbe 3180 is_forced_continuation = False
2d6659b9 3181 is_first_continuation = parent is None
6e634cbe 3182 if is_first_continuation and not continuation:
3183 # Sometimes you can get comments by generating the continuation yourself,
3184 # even if YouTube initially reports them being disabled - e.g. stories comments.
3185 # Note: if the comment section is actually disabled, YouTube may return a response with
3186 # required check_get_keys missing. So we will disable that check initially in this case.
3187 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3188 is_forced_continuation = True
a1c5d2ca
M
3189
3190 for page_num in itertools.count(0):
3191 if not continuation:
3192 break
46383212 3193 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3194 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3195 if page_num == 0:
3196 if is_first_continuation:
3197 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3198 else:
2d6659b9 3199 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3200 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3201 else:
3202 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3203 ' ' if parent else '', ' replies' if parent else '',
3204 page_num, comment_prog_str)
3205
3206 response = self._extract_response(
fe93e2c4 3207 item_id=None, query=continuation,
2d6659b9 3208 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 3209 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3210 is_forced_continuation = False
46383212 3211 continuation_contents = traverse_obj(
3212 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3213
2d6659b9 3214 continuation = None
46383212 3215 for continuation_section in continuation_contents:
3216 continuation_items = traverse_obj(
3217 continuation_section,
3218 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3219 get_all=False, expected_type=list) or []
3220 if is_first_continuation:
3221 continuation = extract_header(continuation_items)
3222 is_first_continuation = False
2d6659b9 3223 if continuation:
a1c5d2ca 3224 break
46383212 3225 continue
a1c5d2ca 3226
46383212 3227 for entry in extract_thread(continuation_items):
3228 if not entry:
3229 return
3230 yield entry
3231 continuation = self._extract_continuation({'contents': continuation_items})
3232 if continuation:
2d6659b9 3233 break
a1c5d2ca 3234
6e634cbe 3235 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3236 if message and not parent and tracker['running_total'] == 0:
3237 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3238
3239 @staticmethod
3240 def _generate_comment_continuation(video_id):
3241 """
3242 Generates initial comment section continuation token from given video id
3243 """
3244 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3245 return base64.b64encode(token.encode()).decode()
3246
a2160aa4 3247 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3248 """Entry for comment extraction"""
2d6659b9 3249 def _real_comment_extract(contents):
aae16f6e 3250 renderer = next((
3251 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3252 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3253 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3254
a2160aa4 3255 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3256 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3257
109dd3b2 3258 @staticmethod
99e9e001 3259 def _get_checkok_params():
3260 return {'contentCheckOk': True, 'racyCheckOk': True}
3261
3262 @classmethod
3263 def _generate_player_context(cls, sts=None):
109dd3b2 3264 context = {
3265 'html5Preference': 'HTML5_PREF_WANTS',
3266 }
3267 if sts is not None:
3268 context['signatureTimestamp'] = sts
3269 return {
3270 'playbackContext': {
3271 'contentPlaybackContext': context
a1a7907b 3272 },
99e9e001 3273 **cls._get_checkok_params()
109dd3b2 3274 }
3275
e7e94f2a
D
3276 @staticmethod
3277 def _is_agegated(player_response):
3278 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3279 return True
e7e94f2a
D
3280
3281 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3282 AGE_GATE_REASONS = (
3283 'confirm your age', 'age-restricted', 'inappropriate', # reason
3284 'age_verification_required', 'age_check_required', # status
3285 )
3286 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3287
3288 @staticmethod
3289 def _is_unplayable(player_response):
3290 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3291
50ac0e54 3292 _STORY_PLAYER_PARAMS = '8AEB'
3293
3294 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3295
11f9be09 3296 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3297 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3298 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3299 headers = self.generate_api_headers(
99e9e001 3300 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3301
6e634cbe 3302 yt_query = {
3303 'videoId': video_id,
6e634cbe 3304 }
50ac0e54 3305 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3306 yt_query['params'] = self._STORY_PLAYER_PARAMS
3307
11f9be09 3308 yt_query.update(self._generate_player_context(sts))
3309 return self._extract_response(
3310 item_id=video_id, ep='player', query=yt_query,
379e44ed 3311 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3312 default_client=client,
11f9be09 3313 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3314 ) or None
3315
11f9be09 3316 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3317 requested_clients = []
d0d012d4 3318 default = ['android', 'web']
000c15a4 3319 allowed_clients = sorted(
86e5f3ed 3320 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3321 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3322 for client in self._configuration_arg('player_client'):
3323 if client in allowed_clients:
3324 requested_clients.append(client)
d0d012d4 3325 elif client == 'default':
3326 requested_clients.extend(default)
b4c055ba 3327 elif client == 'all':
3328 requested_clients.extend(allowed_clients)
3329 else:
3330 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3331 if not requested_clients:
d0d012d4 3332 requested_clients = default
cf7e015f 3333
11f9be09 3334 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3335 requested_clients.extend(
e7e94f2a 3336 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3337
11f9be09 3338 return orderedSet(requested_clients)
cf7e015f 3339
50ac0e54 3340 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3341 initial_pr = None
3342 if webpage:
b7c47b74 3343 initial_pr = self._search_json(
3344 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3345
ae729626 3346 all_clients = set(clients)
c0bc527b 3347 clients = clients[::-1]
b6de707d 3348 prs = []
e7e94f2a 3349
ae729626 3350 def append_client(*client_names):
e7870111 3351 """ Append the first client name that exists but not already used """
ae729626 3352 for client_name in client_names:
e7870111
D
3353 actual_client = _split_innertube_client(client_name)[0]
3354 if actual_client in INNERTUBE_CLIENTS:
3355 if actual_client not in all_clients:
ae729626 3356 clients.append(client_name)
e7870111
D
3357 all_clients.add(actual_client)
3358 return
e7e94f2a 3359
379e44ed 3360 # Android player_response does not have microFormats which are needed for
3361 # extraction of some data. So we return the initial_pr with formats
3362 # stripped out even if not requested by the user
3363 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3364 if initial_pr:
3365 pr = dict(initial_pr)
3366 pr['streamingData'] = None
b6de707d 3367 prs.append(pr)
379e44ed 3368
3369 last_error = None
b6de707d 3370 tried_iframe_fallback = False
3371 player_url = None
c0bc527b 3372 while clients:
e7870111 3373 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3374 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3375 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3376 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3377
b6de707d 3378 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3379 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3380 if 'js' in self._configuration_arg('player_skip'):
3381 require_js_player = False
3382 player_url = None
3383
3384 if not player_url and not tried_iframe_fallback and require_js_player:
3385 player_url = self._download_player_url(video_id)
3386 tried_iframe_fallback = True
3387
379e44ed 3388 try:
3389 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3390 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3391 except ExtractorError as e:
3392 if last_error:
3393 self.report_warning(last_error)
3394 last_error = e
3395 continue
3396
11f9be09 3397 if pr:
a3e96421 3398 # YouTube may return a different video player response than expected.
3399 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3400 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3401 if pr_video_id and pr_video_id != video_id:
3402 self.report_warning(
c7dcf0b3 3403 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3404 else:
3405 prs.append(pr)
c0bc527b 3406
e7e94f2a 3407 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3408 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3409 append_client(f'{base_client}_creator')
e7e94f2a 3410 elif self._is_agegated(pr):
e7870111
D
3411 if variant == 'tv_embedded':
3412 append_client(f'{base_client}_embedded')
3413 elif not variant:
3414 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3415
379e44ed 3416 if last_error:
b6de707d 3417 if not len(prs):
379e44ed 3418 raise last_error
3419 self.report_warning(last_error)
b6de707d 3420 return prs, player_url
11f9be09 3421
4d37720a
L
3422 def _needs_live_processing(self, live_status, duration):
3423 if (live_status == 'is_live' and self.get_param('live_from_start')
3424 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3425 return live_status
3426
3427 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a0bb6ce5 3428 itags, stream_ids = {}, []
b25cac65 3429 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3430 q = qualities([
2a9c6dcd 3431 # Normally tiny is the smallest video-only formats. But
3432 # audio-only formats with unknown quality may get tagged as tiny
3433 'tiny',
3434 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3435 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3436 ])
11f9be09 3437 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3438
545cc85d 3439 for fmt in streaming_formats:
727029c5 3440 if fmt.get('targetDurationSec'):
545cc85d 3441 continue
321bf820 3442
cc2db878 3443 itag = str_or_none(fmt.get('itag'))
9297939e 3444 audio_track = fmt.get('audioTrack') or {}
3445 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3446 if stream_id in stream_ids:
3447 continue
3448
cc2db878 3449 quality = fmt.get('quality')
2a9c6dcd 3450 height = int_or_none(fmt.get('height'))
d3fc8074 3451 if quality == 'tiny' or not quality:
3452 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3453 # The 3gp format (17) in android client has a quality of "small",
3454 # but is actually worse than other formats
3455 if itag == '17':
3456 quality = 'tiny'
3457 if quality:
3458 if itag:
3459 itag_qualities[itag] = quality
3460 if height:
3461 res_qualities[height] = quality
cc2db878 3462 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3463 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3464 # number of fragment that would subsequently requested with (`&sq=N`)
3465 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3466 continue
3467
545cc85d 3468 fmt_url = fmt.get('url')
3469 if not fmt_url:
14f25df2 3470 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3471 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3472 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3473 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3474 continue
52023f12 3475 try:
3476 fmt_url += '&%s=%s' % (
3477 traverse_obj(sc, ('sp', -1)) or 'signature',
3478 self._decrypt_signature(encrypted_sig, video_id, player_url)
3479 )
3480 except ExtractorError as e:
580ce007 3481 self.report_warning('Signature extraction failed: Some formats may be missing',
3482 video_id=video_id, only_once=True)
52023f12 3483 self.write_debug(e, only_once=True)
201e9eaa 3484 continue
545cc85d 3485
404f611f 3486 query = parse_qs(fmt_url)
3487 throttled = False
b2916526 3488 if query.get('n'):
404f611f 3489 try:
580ce007 3490 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3491 fmt_url = update_url_query(fmt_url, {
580ce007 3492 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3493 })
404f611f 3494 except ExtractorError as e:
25836db6 3495 phantomjs_hint = ''
3496 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3497 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3498 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3499 if player_url:
3500 self.report_warning(
3501 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3502 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3503 self.write_debug(e, only_once=True)
3504 else:
3505 self.report_warning(
3506 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3507 video_id=video_id, only_once=True)
404f611f 3508 throttled = True
3509
545cc85d 3510 if itag:
a0bb6ce5 3511 itags[itag] = 'https'
9297939e 3512 stream_ids.append(stream_id)
3513
0ad92dfb 3514 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3515 language_preference = (
3516 10 if audio_track.get('audioIsDefault') and 10
3517 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3518 else -1)
0ad92dfb 3519 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3520 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3521 # Make sure to avoid false positives with small duration differences.
62b58c09 3522 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3523 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3524 if is_damaged:
0f06bcd7 3525 self.report_warning(
3526 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3527 dct = {
3528 'asr': int_or_none(fmt.get('audioSampleRate')),
3529 'filesize': int_or_none(fmt.get('contentLength')),
3530 'format_id': itag,
34921b43 3531 'format_note': join_nonempty(
26e8e044 3532 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3533 ' (default)' if language_preference > 0 else ''),
404f611f 3534 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3535 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3536 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3537 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3538 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3539 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3540 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3541 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3542 'height': height,
dca3ff4a 3543 'quality': q(quality),
727029c5 3544 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3545 'tbr': tbr,
545cc85d 3546 'url': fmt_url,
2a9c6dcd 3547 'width': int_or_none(fmt.get('width')),
ab6df717 3548 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3549 'desc' if language_preference < -1 else ''),
3550 'language_preference': language_preference,
a405b38f 3551 # Strictly de-prioritize damaged and 3gp formats
3552 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3553 }
60bdb7bd 3554 mime_mobj = re.match(
3555 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3556 if mime_mobj:
3557 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3558 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3559 no_audio = dct.get('acodec') == 'none'
3560 no_video = dct.get('vcodec') == 'none'
3561 if no_audio:
3562 dct['vbr'] = tbr
3563 if no_video:
3564 dct['abr'] = tbr
3565 if no_audio or no_video:
545cc85d 3566 dct['downloader_options'] = {
3567 # Youtube throttles chunks >~10M
3568 'http_chunk_size': 10485760,
bf1317d2 3569 }
7c60c33e 3570 if dct.get('ext'):
3571 dct['container'] = dct['ext'] + '_dash'
11f9be09 3572 yield dct
545cc85d 3573
4d37720a
L
3574 needs_live_processing = self._needs_live_processing(live_status, duration)
3575 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3576
3577 skip_manifests = set(self._configuration_arg('skip'))
3578 if (not self.get_param('youtube_include_hls_manifest', True)
3579 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3580 or needs_live_processing and skip_bad_formats):
3581 skip_manifests.add('hls')
3582
0f06bcd7 3583 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3584 skip_manifests.add('dash')
3585 if self._configuration_arg('include_live_dash'):
3586 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3587 'Use include_incomplete_formats extractor argument instead')
3588 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3589 skip_manifests.add('dash')
5d3a0e79 3590
a0bb6ce5 3591 def process_manifest_format(f, proto, itag):
3592 if itag in itags:
3593 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3594 return False
3595 itag = f'{itag}-{proto}'
3596 if itag:
3597 f['format_id'] = itag
3598 itags[itag] = proto
3599
b25cac65 3600 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3601 if f['quality'] == -1 and f.get('height'):
3602 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3603 return True
2a9c6dcd 3604
c646d76f 3605 subtitles = {}
11f9be09 3606 for sd in streaming_data:
4d37720a 3607 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3608 if hls_manifest_url:
4d37720a
L
3609 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3610 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3611 subtitles = self._merge_subtitles(subs, subtitles)
3612 for f in fmts:
a0bb6ce5 3613 if process_manifest_format(f, 'hls', self._search_regex(
3614 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3615 yield f
545cc85d 3616
4d37720a 3617 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3618 if dash_manifest_url:
c646d76f 3619 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3620 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3621 for f in formats:
a0bb6ce5 3622 if process_manifest_format(f, 'dash', f['format_id']):
3623 f['filesize'] = int_or_none(self._search_regex(
3624 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3625 if needs_live_processing:
adbc4ec4
THD
3626 f['is_from_start'] = True
3627
a0bb6ce5 3628 yield f
c646d76f 3629 yield subtitles
11f9be09 3630
720c3099 3631 def _extract_storyboard(self, player_responses, duration):
3632 spec = get_first(
3633 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3634 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3635 if not base_url:
720c3099 3636 return
720c3099 3637 L = len(spec) - 1
3638 for i, args in enumerate(spec):
3639 args = args.split('#')
3640 counts = list(map(int_or_none, args[:5]))
3641 if len(args) != 8 or not all(counts):
3642 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3643 continue
3644 width, height, frame_count, cols, rows = counts
3645 N, sigh = args[6:]
3646
3647 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3648 fragment_count = frame_count / (cols * rows)
3649 fragment_duration = duration / fragment_count
3650 yield {
3651 'format_id': f'sb{i}',
3652 'format_note': 'storyboard',
3653 'ext': 'mhtml',
3654 'protocol': 'mhtml',
3655 'acodec': 'none',
3656 'vcodec': 'none',
3657 'url': url,
3658 'width': width,
3659 'height': height,
45e8a04e 3660 'fps': frame_count / duration,
3661 'rows': rows,
3662 'columns': cols,
720c3099 3663 'fragments': [{
b3edc806 3664 'url': url.replace('$M', str(j)),
720c3099 3665 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3666 } for j in range(math.ceil(fragment_count))],
3667 }
3668
adbc4ec4 3669 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3670 webpage = None
3671 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3672 query = {'bpctr': '9999999999', 'has_verified': '1'}
3673 if smuggled_data.get('is_story'):
3674 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3675 webpage = self._download_webpage(
50ac0e54 3676 webpage_url, video_id, fatal=False, query=query)
11f9be09 3677
3678 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3679
b6de707d 3680 player_responses, player_url = self._extract_player_responses(
11f9be09 3681 self._get_requested_clients(url, smuggled_data),
50ac0e54 3682 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3683
adbc4ec4
THD
3684 return webpage, master_ytcfg, player_responses, player_url
3685
a1b2d843 3686 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3687 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3688 is_live = get_first(video_details, 'isLive')
3689 if is_live is None:
3690 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3691 live_content = get_first(video_details, 'isLiveContent')
3692 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3693 post_live = get_first(video_details, 'isPostLiveDvr')
3694 live_status = ('post_live' if post_live
3695 else 'is_live' if is_live
3696 else 'is_upcoming' if is_upcoming
6678a4f0 3697 else 'was_live' if live_content
3698 else 'not_live' if False in (is_live, live_content)
3699 else None)
adbc4ec4 3700 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3701 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3702
4d37720a 3703 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3704
3705 def _real_extract(self, url):
3706 url, smuggled_data = unsmuggle_url(url, {})
3707 video_id = self._match_id(url)
3708
3709 base_url = self.http_scheme() + '//www.youtube.com/'
3710 webpage_url = base_url + 'watch?v=' + video_id
3711
3712 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3713
11f9be09 3714 playability_statuses = traverse_obj(
3715 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3716
3717 trailer_video_id = get_first(
3718 playability_statuses,
3719 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3720 expected_type=str)
3721 if trailer_video_id:
3722 return self.url_result(
3723 trailer_video_id, self.ie_key(), trailer_video_id)
3724
3725 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3726 if webpage else (lambda x: None))
3727
3728 video_details = traverse_obj(
3729 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3730 microformats = traverse_obj(
3731 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3732 expected_type=dict, default=[])
c26f9b99 3733
3734 translated_title = self._get_text(microformats, (..., 'title'))
3735 video_title = (self._preferred_lang and translated_title
3736 or get_first(video_details, 'title') # primary
3737 or translated_title
3738 or search_meta(['og:title', 'twitter:title', 'title']))
3739 translated_description = self._get_text(microformats, (..., 'description'))
3740 original_description = get_first(video_details, 'shortDescription')
3741 video_description = (
3742 self._preferred_lang and translated_description
3743 # If original description is blank, it will be an empty string.
3744 # Do not prefer translated description in this case.
3745 or original_description if original_description is not None else translated_description)
11f9be09 3746
d89257f3 3747 multifeed_metadata_list = get_first(
3748 player_responses,
3749 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3750 expected_type=str)
3751 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3752 if self.get_param('noplaylist'):
11f9be09 3753 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3754 else:
3755 entries = []
3756 feed_ids = []
3757 for feed in multifeed_metadata_list.split(','):
3758 # Unquote should take place before split on comma (,) since textual
3759 # fields may contain comma as well (see
3760 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3761 feed_data = urllib.parse.parse_qs(
ac668111 3762 urllib.parse.unquote_plus(feed))
d89257f3 3763
3764 def feed_entry(name):
3765 return try_get(
14f25df2 3766 feed_data, lambda x: x[name][0], str)
d89257f3 3767
3768 feed_id = feed_entry('id')
3769 if not feed_id:
3770 continue
3771 feed_title = feed_entry('title')
3772 title = video_title
3773 if feed_title:
3774 title += ' (%s)' % feed_title
3775 entries.append({
3776 '_type': 'url_transparent',
3777 'ie_key': 'Youtube',
3778 'url': smuggle_url(
3779 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3780 {'force_singlefeed': True}),
3781 'title': title,
3782 })
3783 feed_ids.append(feed_id)
3784 self.to_screen(
3785 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3786 % (', '.join(feed_ids), video_id))
3787 return self.playlist_result(
3788 entries, video_id, video_title, video_description)
11f9be09 3789
a1b2d843 3790 duration = int_or_none(
3791 get_first(video_details, 'lengthSeconds')
3792 or get_first(microformats, 'lengthSeconds')
3793 or parse_duration(search_meta('duration'))) or None
3794
4d37720a
L
3795 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3796 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3797 if live_status == 'post_live':
3798 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3799
545cc85d 3800 if not formats:
11f9be09 3801 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3802 self.report_drm(video_id)
11f9be09 3803 pemr = get_first(
3804 playability_statuses,
3805 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3806 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3807 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3808 if subreason:
545cc85d 3809 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3810 countries = get_first(microformats, 'availableCountries')
545cc85d 3811 if not countries:
3812 regions_allowed = search_meta('regionsAllowed')
3813 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3814 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3815 reason += f'. {subreason}'
545cc85d 3816 if reason:
b7da73eb 3817 self.raise_no_formats(reason, expected=True)
bf1317d2 3818
11f9be09 3819 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3820 if not keywords and webpage:
3821 keywords = [
3822 unescapeHTML(m.group('content'))
3823 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3824 for keyword in keywords:
3825 if keyword.startswith('yt:stretch='):
201c1459 3826 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3827 if mobj:
3828 # NB: float is intentional for forcing float division
3829 w, h = (float(v) for v in mobj.groups())
3830 if w > 0 and h > 0:
3831 ratio = w / h
3832 for f in formats:
3833 if f.get('vcodec') != 'none':
3834 f['stretched_ratio'] = ratio
3835 break
a709d873 3836 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3837 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3838 if thumbnail_url:
3839 thumbnails.append({
3840 'url': thumbnail_url,
ff2751ac 3841 })
fccf5021 3842 original_thumbnails = thumbnails.copy()
3843
0ba692ac 3844 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3845 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3846 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3847 thumbnail_names = [
962ffcf8 3848 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3849 # in resolution, these are not the custom thumbnail. So de-prioritize them
3850 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3851 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3852 ]
cca80fe6 3853 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3854 thumbnails.extend({
3855 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3856 video_id=video_id, name=name, ext=ext,
4d37720a 3857 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 3858 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3859 for thumb in thumbnails:
cca80fe6 3860 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3861 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3862 self._remove_duplicate_formats(thumbnails)
fccf5021 3863 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3864
7ea65411 3865 category = get_first(microformats, 'category') or search_meta('genre')
3866 channel_id = str_or_none(
3867 get_first(video_details, 'channelId')
3868 or get_first(microformats, 'externalChannelId')
3869 or search_meta('channelId'))
7ea65411 3870 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3871
adbc4ec4
THD
3872 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3873 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3874 if not duration and live_end_time and live_start_time:
3875 duration = live_end_time - live_start_time
3876
4d37720a
L
3877 needs_live_processing = self._needs_live_processing(live_status, duration)
3878
3879 def is_bad_format(fmt):
3880 if needs_live_processing and not fmt.get('is_from_start'):
3881 return True
3882 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
3883 and fmt.get('protocol') == 'http_dash_segments'):
3884 return True
3885
3886 for fmt in filter(is_bad_format, formats):
3887 fmt['preference'] = (fmt.get('preference') or -1) - 10
3888 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
3889
3890 if needs_live_processing:
3891 self._prepare_live_from_start_formats(
3892 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 3893
720c3099 3894 formats.extend(self._extract_storyboard(player_responses, duration))
3895
31b532a1 3896 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3897 self._sort_formats(formats, (
3898 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3899
545cc85d 3900 info = {
3901 'id': video_id,
39ca3b5c 3902 'title': video_title,
545cc85d 3903 'formats': formats,
3904 'thumbnails': thumbnails,
fccf5021 3905 # The best thumbnail that we are sure exists. Prevents unnecessary
3906 # URL checking if user don't care about getting the best possible thumbnail
3907 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3908 'description': video_description,
11f9be09 3909 'uploader': get_first(video_details, 'author'),
545cc85d 3910 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3911 'uploader_url': owner_profile_url,
3912 'channel_id': channel_id,
a70635b8 3913 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3914 'duration': duration,
3915 'view_count': int_or_none(
11f9be09 3916 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3917 or search_meta('interactionCount')),
11f9be09 3918 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3919 'age_limit': 18 if (
11f9be09 3920 get_first(microformats, 'isFamilySafe') is False
545cc85d 3921 or search_meta('isFamilyFriendly') == 'false'
3922 or search_meta('og:restrictions:age') == '18+') else 0,
3923 'webpage_url': webpage_url,
3924 'categories': [category] if category else None,
3925 'tags': keywords,
11f9be09 3926 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 3927 'live_status': live_status,
adbc4ec4 3928 'release_timestamp': live_start_time,
545cc85d 3929 }
b477fc13 3930
c646d76f 3931 subtitles = {}
3944e7af 3932 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3933 if pctr:
ecdc9049 3934 def get_lang_code(track):
3935 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3936 or track.get('languageCode'))
3937
3938 # Converted into dicts to remove duplicates
3939 captions = {
3940 get_lang_code(sub): sub
3941 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3942 translation_languages = {
3943 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3944 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3945
774d79cc 3946 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3947 lang_subs = container.setdefault(lang_code, [])
545cc85d 3948 for fmt in self._SUBTITLE_FORMATS:
3949 query.update({
3950 'fmt': fmt,
3951 })
3952 lang_subs.append({
3953 'ext': fmt,
60f393e4 3954 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3955 'name': sub_name,
545cc85d 3956 })
7e72694b 3957
07b47084 3958 # NB: Constructing the full subtitle dictionary is slow
3959 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3960 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3961 for lang_code, caption_track in captions.items():
3962 base_url = caption_track.get('baseUrl')
1235d333 3963 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3964 if not base_url:
3965 continue
ecdc9049 3966 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3967 if caption_track.get('kind') != 'asr':
545cc85d 3968 if not lang_code:
3969 continue
3970 process_language(
ecdc9049 3971 subtitles, base_url, lang_code, lang_name, {})
3972 if not caption_track.get('isTranslatable'):
3973 continue
3944e7af 3974 for trans_code, trans_name in translation_languages.items():
3975 if not trans_code:
545cc85d 3976 continue
1235d333 3977 orig_trans_code = trans_code
ecdc9049 3978 if caption_track.get('kind') != 'asr':
07b47084 3979 if not get_translated_subs:
18e49408 3980 continue
ecdc9049 3981 trans_code += f'-{lang_code}'
a70635b8 3982 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3983 # Add an "-orig" label to the original language so that it can be distinguished.
3984 # The subs are returned without "-orig" as well for compatibility
1235d333 3985 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3986 process_language(
d49669ac 3987 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3988 # Setting tlang=lang returns damaged subtitles.
d49669ac 3989 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3990 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3991
3992 info['automatic_captions'] = automatic_captions
3993 info['subtitles'] = subtitles
7e72694b 3994
14f25df2 3995 parsed_url = urllib.parse.urlparse(url)
545cc85d 3996 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3997 query = urllib.parse.parse_qs(component)
545cc85d 3998 for k, v in query.items():
3999 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4000 d_k += '_time'
4001 if d_k not in info and k in s_ks:
4002 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4003
4004 # Youtube Music Auto-generated description
822b9d9c 4005 if video_description:
1890fc63 4006 mobj = re.search(
4007 r'''(?xs)
4008 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4009 (?P<album>[^\n]+)
4010 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4011 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4012 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4013 .+\nAuto-generated\ by\ YouTube\.\s*$
4014 ''', video_description)
822b9d9c 4015 if mobj:
822b9d9c
RA
4016 release_year = mobj.group('release_year')
4017 release_date = mobj.group('release_date')
4018 if release_date:
4019 release_date = release_date.replace('-', '')
4020 if not release_year:
545cc85d 4021 release_year = release_date[:4]
4022 info.update({
4023 'album': mobj.group('album'.strip()),
4024 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4025 'track': mobj.group('track').strip(),
4026 'release_date': release_date,
cc2db878 4027 'release_year': int_or_none(release_year),
545cc85d 4028 })
7e72694b 4029
545cc85d 4030 initial_data = None
4031 if webpage:
56ba69e4 4032 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4033 if not initial_data:
99e9e001 4034 query = {'videoId': video_id}
4035 query.update(self._get_checkok_params())
109dd3b2 4036 initial_data = self._extract_response(
4037 item_id=video_id, ep='next', fatal=False,
99e9e001 4038 ytcfg=master_ytcfg, query=query,
4039 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4040 note='Downloading initial data API JSON')
545cc85d 4041
0df111a3 4042 info['comment_count'] = traverse_obj(initial_data, (
4043 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4044 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4045 ), (
4046 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4047 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4048 ), expected_type=int_or_none, get_all=False)
4049
19a03940 4050 try: # This will error if there is no livechat
c60ee3a2 4051 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4052 except (KeyError, IndexError, TypeError):
4053 pass
4054 else:
ecdc9049 4055 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4056 # url is needed to set cookies
4057 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4058 'video_id': video_id,
4059 'ext': 'json',
4d37720a
L
4060 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4061 else 'youtube_live_chat_replay'),
c60ee3a2 4062 }]
545cc85d 4063
4064 if initial_data:
7c365c21 4065 info['chapters'] = (
4066 self._extract_chapters_from_json(initial_data, duration)
4067 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4068 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4069 or None)
545cc85d 4070
17322130 4071 contents = traverse_obj(
4072 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4073 expected_type=list, default=[])
4074
4075 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4076 if vpir:
4077 stl = vpir.get('superTitleLink')
4078 if stl:
4079 stl = self._get_text(stl)
4080 if try_get(
4081 vpir,
4082 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4083 info['location'] = stl
4084 else:
affc4fef 4085 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4086 if mobj:
545cc85d 4087 info.update({
17322130 4088 'series': mobj.group(1),
4089 'season_number': int(mobj.group(2)),
4090 'episode_number': int(mobj.group(3)),
545cc85d 4091 })
17322130 4092 for tlb in (try_get(
4093 vpir,
4094 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4095 list) or []):
3ffb2f5b 4096 tbrs = variadic(
4097 traverse_obj(
4098 tlb, 'toggleButtonRenderer',
4099 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4100 default=[]))
4101 for tbr in tbrs:
4102 for getter, regex in [(
4103 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4104 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4105 lambda x: x['accessibility'],
4106 lambda x: x['accessibilityData']['accessibilityData'],
4107 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4108 label = (try_get(tbr, getter, dict) or {}).get('label')
4109 if label:
4110 mobj = re.match(regex, label)
4111 if mobj:
4112 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4113 break
17322130 4114 sbr_tooltip = try_get(
4115 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4116 if sbr_tooltip:
4117 like_count, dislike_count = sbr_tooltip.split(' / ')
4118 info.update({
4119 'like_count': str_to_int(like_count),
4120 'dislike_count': str_to_int(dislike_count),
4121 })
867c66ff
M
4122 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4123 if vcr:
4124 vc = self._get_count(vcr, 'viewCount')
4125 # Upcoming premieres with waiting count are treated as live here
4126 if vcr.get('isLive'):
4127 info['concurrent_view_count'] = vc
4128 elif info.get('view_count') is None:
4129 info['view_count'] = vc
4130
17322130 4131 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4132 if vsir:
4133 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4134 info.update({
4135 'channel': self._get_text(vor, 'title'),
4136 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4137
4138 rows = try_get(
4139 vsir,
4140 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4141 list) or []
4142 multiple_songs = False
4143 for row in rows:
4144 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4145 multiple_songs = True
4146 break
4147 for row in rows:
4148 mrr = row.get('metadataRowRenderer') or {}
4149 mrr_title = mrr.get('title')
4150 if not mrr_title:
4151 continue
4152 mrr_title = self._get_text(mrr, 'title')
4153 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4154 if mrr_title == 'License':
4155 info['license'] = mrr_contents_text
4156 elif not multiple_songs:
4157 if mrr_title == 'Album':
4158 info['album'] = mrr_contents_text
4159 elif mrr_title == 'Artist':
4160 info['artist'] = mrr_contents_text
4161 elif mrr_title == 'Song':
4162 info['track'] = mrr_contents_text
545cc85d 4163
4164 fallbacks = {
4165 'channel': 'uploader',
4166 'channel_id': 'uploader_id',
4167 'channel_url': 'uploader_url',
4168 }
992f9a73 4169
17322130 4170 # The upload date for scheduled, live and past live streams / premieres in microformats
4171 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4172 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4173 upload_date = (
4174 unified_strdate(get_first(microformats, 'uploadDate'))
4175 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4176 if not upload_date or (
4d37720a 4177 live_status in ('not_live', None)
1ff88b7a 4178 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4179 ):
c26f9b99 4180 upload_date = strftime_or_none(
4181 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4182 info['upload_date'] = upload_date
992f9a73 4183
545cc85d 4184 for to, frm in fallbacks.items():
4185 if not info.get(to):
4186 info[to] = info.get(frm)
4187
4188 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4189 v = info.get(s_k)
4190 if v:
4191 info[d_k] = v
b84071c0 4192
c26f9b99 4193 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4194
4195 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4196 or get_first(video_details, 'isPrivate', expected_type=bool))
4197
4198 info['availability'] = (
4199 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4200 else self._availability(
4201 is_private=is_private,
4202 needs_premium=(
4203 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4204 or False if initial_data and is_private is not None else None),
4205 needs_subscription=(
4206 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4207 or False if initial_data and is_private is not None else None),
4208 needs_auth=info['age_limit'] >= 18,
4209 is_unlisted=None if is_private is None else (
4210 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4211 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4212
a2160aa4 4213 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4214
11f9be09 4215 self.mark_watched(video_id, player_responses)
d77ab8e2 4216
545cc85d 4217 return info
c5e8d7af 4218
a61fd4cf 4219
a6213a49 4220class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 4221
182bda88 4222 @staticmethod
4223 def passthrough_smuggled_data(func):
4224 def _smuggle(entries, smuggled_data):
4225 for entry in entries:
4226 # TODO: Convert URL to music.youtube instead.
4227 # Do we need to passthrough any other smuggled_data?
4228 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4229 yield entry
4230
4231 @functools.wraps(func)
4232 def wrapper(self, url):
4233 url, smuggled_data = unsmuggle_url(url, {})
4234 if self.is_music_url(url):
4235 smuggled_data['is_music_url'] = True
4236 info_dict = func(self, url, smuggled_data)
4237 if smuggled_data and info_dict.get('entries'):
4238 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4239 return info_dict
4240 return wrapper
4241
a6213a49 4242 def _extract_channel_id(self, webpage):
4243 channel_id = self._html_search_meta(
4244 'channelId', webpage, 'channel id', default=None)
4245 if channel_id:
4246 return channel_id
4247 channel_url = self._html_search_meta(
4248 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4249 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4250 'twitter:app:url:googleplay'), webpage, 'channel url')
4251 return self._search_regex(
4252 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4253 channel_url, 'channel id')
15f6397c 4254
8bdd16b4 4255 @staticmethod
cd7c66cf 4256 def _extract_basic_item_renderer(item):
4257 # Modified from _extract_grid_item_renderer
201c1459 4258 known_basic_renderers = (
a17526e4 4259 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4260 )
4261 for key, renderer in item.items():
201c1459 4262 if not isinstance(renderer, dict):
cd7c66cf 4263 continue
201c1459 4264 elif key in known_basic_renderers:
4265 return renderer
4266 elif key.startswith('grid') and key.endswith('Renderer'):
4267 return renderer
8bdd16b4 4268
8bdd16b4 4269 def _grid_entries(self, grid_renderer):
4270 for item in grid_renderer['items']:
4271 if not isinstance(item, dict):
39b62db1 4272 continue
cd7c66cf 4273 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4274 if not isinstance(renderer, dict):
4275 continue
052e1350 4276 title = self._get_text(renderer, 'title')
fe93e2c4 4277
8bdd16b4 4278 # playlist
4279 playlist_id = renderer.get('playlistId')
4280 if playlist_id:
4281 yield self.url_result(
4282 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4283 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4284 video_title=title)
201c1459 4285 continue
8bdd16b4 4286 # video
4287 video_id = renderer.get('videoId')
4288 if video_id:
4289 yield self._extract_video(renderer)
201c1459 4290 continue
8bdd16b4 4291 # channel
4292 channel_id = renderer.get('channelId')
4293 if channel_id:
8bdd16b4 4294 yield self.url_result(
4295 'https://www.youtube.com/channel/%s' % channel_id,
4296 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4297 continue
4298 # generic endpoint URL support
4299 ep_url = urljoin('https://www.youtube.com/', try_get(
4300 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4301 str))
201c1459 4302 if ep_url:
4303 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4304 if ie.suitable(ep_url):
4305 yield self.url_result(
4306 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4307 break
8bdd16b4 4308
16aa9ea4 4309 def _music_reponsive_list_entry(self, renderer):
4310 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4311 if video_id:
4312 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4313 ie=YoutubeIE.ie_key(), video_id=video_id)
4314 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4315 if playlist_id:
4316 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4317 if video_id:
4318 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4319 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4320 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4321 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4322 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4323 if browse_id:
4324 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4325 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4326
3d3dddc9 4327 def _shelf_entries_from_content(self, shelf_renderer):
4328 content = shelf_renderer.get('content')
4329 if not isinstance(content, dict):
8bdd16b4 4330 return
cd7c66cf 4331 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4332 if renderer:
4333 # TODO: add support for nested playlists so each shelf is processed
4334 # as separate playlist
4335 # TODO: this includes only first N items
86e5f3ed 4336 yield from self._grid_entries(renderer)
3d3dddc9 4337 renderer = content.get('horizontalListRenderer')
4338 if renderer:
4339 # TODO
4340 pass
8bdd16b4 4341
29f7c58a 4342 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4343 ep = try_get(
4344 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4345 str)
8bdd16b4 4346 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4347 if shelf_url:
29f7c58a 4348 # Skipping links to another channels, note that checking for
4349 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4350 # will not work
4351 if skip_channels and '/channels?' in shelf_url:
4352 return
052e1350 4353 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4354 yield self.url_result(shelf_url, video_title=title)
4355 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4356 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4357
8bdd16b4 4358 def _playlist_entries(self, video_list_renderer):
4359 for content in video_list_renderer['contents']:
4360 if not isinstance(content, dict):
4361 continue
4362 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4363 if not isinstance(renderer, dict):
4364 continue
4365 video_id = renderer.get('videoId')
4366 if not video_id:
4367 continue
4368 yield self._extract_video(renderer)
07aeced6 4369
3462ffa8 4370 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4371 renderer = traverse_obj(
4372 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4373 video_id = renderer.get('videoId')
4374 if not video_id:
4375 return
4376 yield self._extract_video(renderer)
4377
8bdd16b4 4378 def _video_entry(self, video_renderer):
4379 video_id = video_renderer.get('videoId')
4380 if video_id:
4381 return self._extract_video(video_renderer)
dacb3a86 4382
ad210f4f 4383 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4384 url = urljoin('https://youtube.com', traverse_obj(
4385 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4386 if url:
4387 return self.url_result(
4388 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4389
8bdd16b4 4390 def _post_thread_entries(self, post_thread_renderer):
4391 post_renderer = try_get(
4392 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4393 if not post_renderer:
4394 return
4395 # video attachment
4396 video_renderer = try_get(
895b0931 4397 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4398 video_id = video_renderer.get('videoId')
4399 if video_id:
4400 entry = self._extract_video(video_renderer)
8bdd16b4 4401 if entry:
4402 yield entry
895b0931 4403 # playlist attachment
4404 playlist_id = try_get(
14f25df2 4405 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4406 if playlist_id:
4407 yield self.url_result(
e28f1c0a 4408 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4409 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4410 # inline video links
4411 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4412 for run in runs:
4413 if not isinstance(run, dict):
4414 continue
4415 ep_url = try_get(
14f25df2 4416 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4417 if not ep_url:
4418 continue
4419 if not YoutubeIE.suitable(ep_url):
4420 continue
4421 ep_video_id = YoutubeIE._match_id(ep_url)
4422 if video_id == ep_video_id:
4423 continue
895b0931 4424 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4425
8bdd16b4 4426 def _post_thread_continuation_entries(self, post_thread_continuation):
4427 contents = post_thread_continuation.get('contents')
4428 if not isinstance(contents, list):
4429 return
4430 for content in contents:
4431 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4432 if isinstance(renderer, dict):
4433 yield from self._post_thread_entries(renderer)
8bdd16b4 4434 continue
6b0b0a28 4435 renderer = content.get('videoRenderer')
4436 if isinstance(renderer, dict):
4437 yield self._video_entry(renderer)
07aeced6 4438
39ed931e 4439 r''' # unused
4440 def _rich_grid_entries(self, contents):
4441 for content in contents:
4442 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4443 if video_renderer:
4444 entry = self._video_entry(video_renderer)
4445 if entry:
4446 yield entry
4447 '''
52efa4b3 4448
0a5095fe 4449 def _report_history_entries(self, renderer):
4450 for url in traverse_obj(renderer, (
7a32c70d 4451 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4452 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4453 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4454 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4455
a6213a49 4456 def _extract_entries(self, parent_renderer, continuation_list):
4457 # continuation_list is modified in-place with continuation_list = [continuation_token]
4458 continuation_list[:] = [None]
4459 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4460 for content in contents:
4461 if not isinstance(content, dict):
4462 continue
16aa9ea4 4463 is_renderer = traverse_obj(
4464 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4465 expected_type=dict)
a6213a49 4466 if not is_renderer:
0a5095fe 4467 if content.get('richItemRenderer'):
4468 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4469 yield entry
4470 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4471 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4472 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4473 yield from self._report_history_entries(table)
4474 continuation_list[0] = self._extract_continuation(table)
a6213a49 4475 continue
0a5095fe 4476
a6213a49 4477 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4478 for isr_content in isr_contents:
4479 if not isinstance(isr_content, dict):
8bdd16b4 4480 continue
69184e41 4481
a6213a49 4482 known_renderers = {
4483 'playlistVideoListRenderer': self._playlist_entries,
4484 'gridRenderer': self._grid_entries,
a17526e4 4485 'reelShelfRenderer': self._grid_entries,
4486 'shelfRenderer': self._shelf_entries,
16aa9ea4 4487 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4488 'backstagePostThreadRenderer': self._post_thread_entries,
4489 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4490 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4491 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4492 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4493 }
4494 for key, renderer in isr_content.items():
4495 if key not in known_renderers:
4496 continue
4497 for entry in known_renderers[key](renderer):
4498 if entry:
4499 yield entry
4500 continuation_list[0] = self._extract_continuation(renderer)
4501 break
70d5c17b 4502
4503 if not continuation_list[0]:
a6213a49 4504 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4505
a6213a49 4506 if not continuation_list[0]:
4507 continuation_list[0] = self._extract_continuation(parent_renderer)
4508
4509 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4510 continuation_list = [None]
4511 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4512 tab_content = try_get(tab, lambda x: x['content'], dict)
4513 if not tab_content:
4514 return
3462ffa8 4515 parent_renderer = (
29f7c58a 4516 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4517 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4518 yield from extract_entries(parent_renderer)
3462ffa8 4519 continuation = continuation_list[0]
d069eca7 4520
8bdd16b4 4521 for page_num in itertools.count(1):
4522 if not continuation:
4523 break
99e9e001 4524 headers = self.generate_api_headers(
4525 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4526 response = self._extract_response(
86e5f3ed 4527 item_id=f'{item_id} page {page_num}',
fe93e2c4 4528 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4529 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4530
4531 if not response:
8bdd16b4 4532 break
ac56cf38 4533 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4534 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4535 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4536
a1b535bd 4537 known_renderers = {
e4b98809 4538 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4539 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4540 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4541 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4542 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4543 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4544 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4545 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4546 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4547 'playlistVideoListContinuation': (self._playlist_entries, None),
4548 'gridContinuation': (self._grid_entries, None),
4549 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4550 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4551 }
1fb53b94 4552
4553 continuation_items = traverse_obj(response, (
4554 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4555 'appendContinuationItemsAction', 'continuationItems'
4556 ), 'continuationContents', get_all=False)
4557 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4558
a1b535bd 4559 video_items_renderer = None
1fb53b94 4560 for key in continuation_item.keys():
a1b535bd 4561 if key not in known_renderers:
8bdd16b4 4562 continue
1fb53b94 4563 func, parent_key = known_renderers[key]
4564 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4565 continuation_list = [None]
1fb53b94 4566 yield from func(video_items_renderer)
9ba5705a 4567 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4568
4569 if not video_items_renderer:
a1b535bd 4570 break
9558dcec 4571
8bdd16b4 4572 @staticmethod
7c219ea6 4573 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4574 for tab in tabs:
cd684175 4575 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4576 if renderer.get('selected') is True:
4577 return renderer
2b3c2546 4578 else:
7c219ea6 4579 if fatal:
4580 raise ExtractorError('Unable to find selected tab')
b82f815f 4581
61d3665d 4582 def _extract_uploader(self, data):
8bdd16b4 4583 uploader = {}
61d3665d 4584 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4585 owner = try_get(
4586 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4587 if owner:
61d3665d 4588 owner_text = owner.get('text')
4589 uploader['uploader'] = self._search_regex(
4590 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4591 uploader['uploader_id'] = try_get(
14f25df2 4592 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4593 uploader['uploader_url'] = urljoin(
4594 'https://www.youtube.com/',
14f25df2 4595 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
7a32c70d 4596 return filter_dict(uploader)
8bdd16b4 4597
ac56cf38 4598 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4599 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4600 tags = []
b60419c5 4601
8bdd16b4 4602 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4603 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4604 renderer = try_get(
4605 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4606 if renderer:
b60419c5 4607 channel_name = renderer.get('title')
4608 channel_url = renderer.get('channelUrl')
4609 channel_id = renderer.get('externalId')
39ed931e 4610 else:
64c0d954 4611 renderer = try_get(
4612 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4613
8bdd16b4 4614 if renderer:
4615 title = renderer.get('title')
ecc97af3 4616 description = renderer.get('description', '')
b60419c5 4617 playlist_id = channel_id
4618 tags = renderer.get('keywords', '').split()
b60419c5 4619
301d07fc 4620 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4621 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4622 def _get_uncropped(url):
4623 return url_or_none((url or '').split('=')[0] + '=s0')
4624
4625 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4626 if avatar_thumbnails:
4627 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4628 if uncropped_avatar:
4629 avatar_thumbnails.append({
4630 'url': uncropped_avatar,
4631 'id': 'avatar_uncropped',
4632 'preference': 1
4633 })
4634
4635 channel_banners = self._extract_thumbnails(
4636 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4637 for banner in channel_banners:
4638 banner['preference'] = -10
4639
4640 if channel_banners:
4641 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4642 if uncropped_banner:
4643 channel_banners.append({
4644 'url': uncropped_banner,
4645 'id': 'banner_uncropped',
4646 'preference': -5
4647 })
4648
4649 primary_thumbnails = self._extract_thumbnails(
a17526e4 4650 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4651
3462ffa8 4652 if playlist_id is None:
70d5c17b 4653 playlist_id = item_id
f0d785d3 4654
4655 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
c26f9b99 4656 last_updated_unix = self._parse_time_text(self._get_text(playlist_stats, 2))
70d5c17b 4657 if title is None:
f0d785d3 4658 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4659 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4660 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4661
b60419c5 4662 metadata = {
4663 'playlist_id': playlist_id,
4664 'playlist_title': title,
4665 'playlist_description': description,
4666 'uploader': channel_name,
4667 'uploader_id': channel_id,
4668 'uploader_url': channel_url,
301d07fc 4669 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4670 'tags': tags,
f0d785d3 4671 'view_count': self._get_count(playlist_stats, 1),
4672 'availability': self._extract_availability(data),
4673 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4674 'playlist_count': self._get_count(playlist_stats, 0),
4675 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4676 }
4677 if not channel_id:
4678 metadata.update(self._extract_uploader(data))
4679 metadata.update({
4680 'channel': metadata['uploader'],
4681 'channel_id': metadata['uploader_id'],
4682 'channel_url': metadata['uploader_url']})
4683 return self.playlist_result(
d069eca7 4684 self._entries(
ac56cf38 4685 selected_tab, playlist_id, ytcfg,
4686 self._extract_account_syncid(ytcfg, data),
4687 self._extract_visitor_data(data, ytcfg)),
b60419c5 4688 **metadata)
73c4ac2c 4689
6e634cbe 4690 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4691 first_id = last_id = response = None
2be71994 4692 for page_num in itertools.count(1):
cd7c66cf 4693 videos = list(self._playlist_entries(playlist))
4694 if not videos:
4695 return
2be71994 4696 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4697 if start >= len(videos):
4698 return
24146491 4699 yield from videos[start:]
2be71994 4700 first_id = first_id or videos[0]['id']
4701 last_id = videos[-1]['id']
79360d99 4702 watch_endpoint = try_get(
4703 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4704 headers = self.generate_api_headers(
4705 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4706 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4707 query = {
4708 'playlistId': playlist_id,
4709 'videoId': watch_endpoint.get('videoId') or last_id,
4710 'index': watch_endpoint.get('index') or len(videos),
4711 'params': watch_endpoint.get('params') or 'OAE%3D'
4712 }
4713 response = self._extract_response(
4714 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4715 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4716 check_get_keys='contents'
4717 )
cd7c66cf 4718 playlist = try_get(
79360d99 4719 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4720
ac56cf38 4721 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4722 title = playlist.get('title') or try_get(
14f25df2 4723 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4724 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4725
4726 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4727 playlist_url = urljoin(url, try_get(
4728 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4729 str))
6e634cbe 4730
4731 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4732 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4733 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4734
4735 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4736 return self.url_result(
4737 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4738 video_title=title)
cd7c66cf 4739
8bdd16b4 4740 return self.playlist_result(
6e634cbe 4741 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4742 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4743
47193e02 4744 def _extract_availability(self, data):
4745 """
4746 Gets the availability of a given playlist/tab.
4747 Note: Unless YouTube tells us explicitly, we do not assume it is public
4748 @param data: response
4749 """
47193e02 4750 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
c26f9b99 4751
4752 player_header_privacy = traverse_obj(
4753 data, ('header', 'playlistHeaderRenderer', 'privacy'), expected_type=str)
4754
4755 badges = self._extract_badges(renderer)
47193e02 4756
4757 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
c26f9b99 4758 privacy_setting_icon = traverse_obj(
4759 renderer, (
4760 'privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4761 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4762 get_all=False, expected_type=str)
47193e02 4763
c26f9b99 4764 return (
4765 'public' if (
4766 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4767 or player_header_privacy == 'PUBLIC'
4768 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4769 else self._availability(
4770 is_private=(
4771 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4772 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4773 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4774 is_unlisted=(
4775 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4776 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
4777 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None else None),
4778 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4779 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4780 needs_auth=False))
47193e02 4781
4782 @staticmethod
4783 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4784 sidebar_renderer = try_get(
4785 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4786 for item in sidebar_renderer:
4787 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4788 if renderer:
4789 return renderer
4790
ac56cf38 4791 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4792 """
4793 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4794 """
5d342002 4795 browse_id = params = None
47193e02 4796 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4797 if not renderer:
4798 return
4799 menu_renderer = try_get(
4800 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4801 for menu_item in menu_renderer:
4802 if not isinstance(menu_item, dict):
358de58c 4803 continue
47193e02 4804 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4805 text = try_get(
14f25df2 4806 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4807 if not text or text.lower() != 'show unavailable videos':
4808 continue
4809 browse_endpoint = try_get(
4810 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4811 browse_id = browse_endpoint.get('browseId')
4812 params = browse_endpoint.get('params')
4813 break
5d342002 4814
11f9be09 4815 headers = self.generate_api_headers(
99e9e001 4816 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4817 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4818 query = {
4819 'params': params or 'wgYCCAA=',
4820 'browseId': browse_id or 'VL%s' % item_id
4821 }
4822 return self._extract_response(
4823 item_id=item_id, headers=headers, query=query,
fe93e2c4 4824 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4825 note='Downloading API JSON with unavailable videos')
358de58c 4826
2762dbb1 4827 @functools.cached_property
a25bca9f 4828 def skip_webpage(self):
4829 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4830
ac56cf38 4831 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4832 webpage, data = None, None
4833 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4834 try:
be5c1ae8 4835 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4836 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4837 except ExtractorError as e:
4838 if isinstance(e.cause, network_exceptions):
14f25df2 4839 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4840 retry.error = e
4841 continue
4842 self._error_or_warning(e, fatal=fatal)
14fdfea9 4843 break
ac56cf38 4844
be5c1ae8 4845 try:
4846 self._extract_and_report_alerts(data)
4847 except ExtractorError as e:
4848 self._error_or_warning(e, fatal=fatal)
4849 break
ac56cf38 4850
be5c1ae8 4851 # Sometimes youtube returns a webpage with incomplete ytInitialData
4852 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4853 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4854 retry.error = ExtractorError('Incomplete yt initial data received')
4855 continue
ac56cf38 4856
cd7c66cf 4857 return webpage, data
4858
a25bca9f 4859 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4860 """Use if failed to extract ytcfg (and data) from initial webpage"""
4861 if not ytcfg and self.is_authenticated:
4862 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4863 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4864 raise ExtractorError(
4865 f'{msg}. If you are not downloading private content, or '
4866 'your cookies are only for the first account and channel,'
4867 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4868 expected=True)
4869 self.report_warning(msg, only_once=True)
4870
ac56cf38 4871 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4872 data = None
a25bca9f 4873 if not self.skip_webpage:
ac56cf38 4874 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4875 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4876 # Reject webpage data if redirected to home page without explicitly requesting
4877 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4878 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4879 if (url != 'https://www.youtube.com/feed/recommended'
4880 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4881 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4882 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4883 if fatal:
4884 raise ExtractorError(msg, expected=True)
4885 self.report_warning(msg, only_once=True)
ac56cf38 4886 if not data:
a25bca9f 4887 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4888 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4889 return data, ytcfg
4890
4891 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4892 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4893 resolve_response = self._extract_response(
4894 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4895 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4896 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4897 for ep_key, ep in endpoints.items():
4898 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4899 if params:
4900 return self._extract_response(
4901 item_id=item_id, query=params, ep=ep, headers=headers,
4902 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4903 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4904 err_note = 'Failed to resolve url (does the playlist exist?)'
4905 if fatal:
4906 raise ExtractorError(err_note, expected=True)
4907 self.report_warning(err_note, item_id)
4908
a6213a49 4909 _SEARCH_PARAMS = None
4910
af5c1c55 4911 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4912 data = {'query': query}
4913 if params is NO_DEFAULT:
4914 params = self._SEARCH_PARAMS
4915 if params:
4916 data['params'] = params
16aa9ea4 4917
4918 content_keys = (
4919 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4920 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4921 # ytmusic search
4922 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4923 ('continuationContents', ),
4924 )
a25bca9f 4925 display_id = f'query "{query}"'
86e5f3ed 4926 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4927 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4928 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4929
a61fd4cf 4930 continuation_list = [None]
a25bca9f 4931 search = None
a6213a49 4932 for page_num in itertools.count(1):
a61fd4cf 4933 data.update(continuation_list[0] or {})
a25bca9f 4934 headers = self.generate_api_headers(
4935 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4936 search = self._extract_response(
a25bca9f 4937 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4938 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4939 slr_contents = traverse_obj(search, *content_keys)
4940 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4941 if not continuation_list[0]:
a6213a49 4942 break
4943
4944
4945class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4946 IE_DESC = 'YouTube Tabs'
4947 _VALID_URL = r'''(?x:
4948 https?://
4949 (?:\w+\.)?
4950 (?:
4951 youtube(?:kids)?\.com|
4952 %(invidious)s
4953 )/
4954 (?:
4955 (?P<channel_type>channel|c|user|browse)/|
4956 (?P<not_channel>
4957 feed/|hashtag/|
4958 (?:playlist|watch)\?.*?\blist=
4959 )|
4960 (?!(?:%(reserved_names)s)\b) # Direct URLs
4961 )
4962 (?P<id>[^/?\#&]+)
4963 )''' % {
4964 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4965 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4966 }
4967 IE_NAME = 'youtube:tab'
4968
4969 _TESTS = [{
4970 'note': 'playlists, multipage',
4971 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4972 'playlist_mincount': 94,
4973 'info_dict': {
4974 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4975 'title': 'Igor Kleiner - Playlists',
a6213a49 4976 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4977 'uploader': 'Igor Kleiner',
a6213a49 4978 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4979 'channel': 'Igor Kleiner',
4980 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4981 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4982 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4983 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4984 'channel_follower_count': int
a6213a49 4985 },
4986 }, {
4987 'note': 'playlists, multipage, different order',
4988 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4989 'playlist_mincount': 94,
4990 'info_dict': {
4991 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4992 'title': 'Igor Kleiner - Playlists',
a6213a49 4993 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4994 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4995 'uploader': 'Igor Kleiner',
4996 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4997 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4998 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4999 'channel': 'Igor Kleiner',
5000 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5001 'channel_follower_count': int
a6213a49 5002 },
5003 }, {
5004 'note': 'playlists, series',
5005 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5006 'playlist_mincount': 5,
5007 'info_dict': {
5008 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5009 'title': '3Blue1Brown - Playlists',
5010 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5011 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5012 'uploader': '3Blue1Brown',
976ae3ea 5013 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5014 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5015 'channel': '3Blue1Brown',
5016 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5017 'tags': ['Mathematics'],
6c73052c 5018 'channel_follower_count': int
a6213a49 5019 },
5020 }, {
5021 'note': 'playlists, singlepage',
5022 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5023 'playlist_mincount': 4,
5024 'info_dict': {
5025 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5026 'title': 'ThirstForScience - Playlists',
5027 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5028 'uploader': 'ThirstForScience',
5029 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5030 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5031 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5032 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5033 'tags': 'count:13',
5034 'channel': 'ThirstForScience',
6c73052c 5035 'channel_follower_count': int
a6213a49 5036 }
5037 }, {
5038 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5039 'only_matching': True,
5040 }, {
5041 'note': 'basic, single video playlist',
5042 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5043 'info_dict': {
5044 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5045 'uploader': 'Sergey M.',
5046 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5047 'title': 'youtube-dl public playlist',
976ae3ea 5048 'description': '',
5049 'tags': [],
5050 'view_count': int,
5051 'modified_date': '20201130',
5052 'channel': 'Sergey M.',
5053 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5054 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5055 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5056 'availability': 'public',
a6213a49 5057 },
5058 'playlist_count': 1,
5059 }, {
5060 'note': 'empty playlist',
5061 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5062 'info_dict': {
5063 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5064 'uploader': 'Sergey M.',
5065 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5066 'title': 'youtube-dl empty playlist',
976ae3ea 5067 'tags': [],
5068 'channel': 'Sergey M.',
5069 'description': '',
5070 'modified_date': '20160902',
5071 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5072 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5073 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5074 'availability': 'public',
a6213a49 5075 },
5076 'playlist_count': 0,
5077 }, {
5078 'note': 'Home tab',
5079 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5080 'info_dict': {
5081 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5082 'title': 'lex will - Home',
5083 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5084 'uploader': 'lex will',
5085 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5086 'channel': 'lex will',
5087 'tags': ['bible', 'history', 'prophesy'],
5088 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5089 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5090 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5091 'channel_follower_count': int
a6213a49 5092 },
5093 'playlist_mincount': 2,
5094 }, {
5095 'note': 'Videos tab',
5096 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5097 'info_dict': {
5098 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5099 'title': 'lex will - Videos',
5100 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5101 'uploader': 'lex will',
5102 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5103 'tags': ['bible', 'history', 'prophesy'],
5104 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5105 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5106 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5107 'channel': 'lex will',
6c73052c 5108 'channel_follower_count': int
a6213a49 5109 },
5110 'playlist_mincount': 975,
5111 }, {
5112 'note': 'Videos tab, sorted by popular',
5113 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5114 'info_dict': {
5115 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5116 'title': 'lex will - Videos',
5117 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5118 'uploader': 'lex will',
5119 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5120 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5121 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5122 'channel': 'lex will',
5123 'tags': ['bible', 'history', 'prophesy'],
5124 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5125 'channel_follower_count': int
a6213a49 5126 },
5127 'playlist_mincount': 199,
5128 }, {
5129 'note': 'Playlists tab',
5130 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5131 'info_dict': {
5132 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5133 'title': 'lex will - Playlists',
5134 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5135 'uploader': 'lex will',
5136 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5137 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5138 'channel': 'lex will',
5139 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5140 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5141 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5142 'channel_follower_count': int
a6213a49 5143 },
5144 'playlist_mincount': 17,
5145 }, {
5146 'note': 'Community tab',
5147 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5148 'info_dict': {
5149 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5150 'title': 'lex will - Community',
5151 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5152 'uploader': 'lex will',
5153 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5154 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5155 'channel': 'lex will',
5156 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5157 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5158 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5159 'channel_follower_count': int
a6213a49 5160 },
5161 'playlist_mincount': 18,
5162 }, {
5163 'note': 'Channels tab',
5164 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5165 'info_dict': {
5166 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5167 'title': 'lex will - Channels',
5168 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5169 'uploader': 'lex will',
5170 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5171 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5172 'channel': 'lex will',
5173 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5174 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5175 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5176 'channel_follower_count': int
a6213a49 5177 },
5178 'playlist_mincount': 12,
5179 }, {
5180 'note': 'Search tab',
5181 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5182 'playlist_mincount': 40,
5183 'info_dict': {
5184 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5185 'title': '3Blue1Brown - Search - linear algebra',
5186 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5187 'uploader': '3Blue1Brown',
5188 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5189 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5190 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5191 'tags': ['Mathematics'],
5192 'channel': '3Blue1Brown',
5193 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5194 'channel_follower_count': int
a6213a49 5195 },
5196 }, {
5197 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5198 'only_matching': True,
5199 }, {
5200 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5201 'only_matching': True,
5202 }, {
5203 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5204 'only_matching': True,
5205 }, {
5206 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5207 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5208 'info_dict': {
5209 'title': '29C3: Not my department',
5210 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5211 'uploader': 'Christiaan008',
5212 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5213 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5214 'tags': [],
5215 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5216 'view_count': int,
5217 'modified_date': '20150605',
5218 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5219 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5220 'channel': 'Christiaan008',
c26f9b99 5221 'availability': 'public',
a6213a49 5222 },
5223 'playlist_count': 96,
5224 }, {
5225 'note': 'Large playlist',
5226 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5227 'info_dict': {
5228 'title': 'Uploads from Cauchemar',
5229 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5230 'uploader': 'Cauchemar',
5231 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5232 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5233 'tags': [],
5234 'modified_date': r're:\d{8}',
5235 'channel': 'Cauchemar',
5236 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5237 'view_count': int,
5238 'description': '',
5239 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5240 'availability': 'public',
a6213a49 5241 },
5242 'playlist_mincount': 1123,
976ae3ea 5243 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5244 }, {
5245 'note': 'even larger playlist, 8832 videos',
5246 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5247 'only_matching': True,
5248 }, {
5249 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5250 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5251 'info_dict': {
5252 'title': 'Uploads from Interstellar Movie',
5253 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5254 'uploader': 'Interstellar Movie',
5255 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5256 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5257 'tags': [],
5258 'view_count': int,
5259 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5260 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5261 'channel': 'Interstellar Movie',
5262 'description': '',
5263 'modified_date': r're:\d{8}',
c26f9b99 5264 'availability': 'public',
a6213a49 5265 },
5266 'playlist_mincount': 21,
5267 }, {
5268 'note': 'Playlist with "show unavailable videos" button',
5269 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5270 'info_dict': {
5271 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5272 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5273 'uploader': 'Phim Siêu Nhân Nhật Bản',
5274 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5275 'view_count': int,
5276 'channel': 'Phim Siêu Nhân Nhật Bản',
5277 'tags': [],
5278 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5279 'description': '',
5280 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5281 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5282 'modified_date': r're:\d{8}',
c26f9b99 5283 'availability': 'public',
a6213a49 5284 },
5285 'playlist_mincount': 200,
976ae3ea 5286 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5287 }, {
5288 'note': 'Playlist with unavailable videos in page 7',
5289 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5290 'info_dict': {
5291 'title': 'Uploads from BlankTV',
5292 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5293 'uploader': 'BlankTV',
5294 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5295 'channel': 'BlankTV',
5296 'channel_url': 'https://www.youtube.com/c/blanktv',
5297 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5298 'view_count': int,
5299 'tags': [],
5300 'uploader_url': 'https://www.youtube.com/c/blanktv',
5301 'modified_date': r're:\d{8}',
5302 'description': '',
c26f9b99 5303 'availability': 'public',
a6213a49 5304 },
5305 'playlist_mincount': 1000,
976ae3ea 5306 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5307 }, {
5308 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5309 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5310 'info_dict': {
5311 'title': 'Data Analysis with Dr Mike Pound',
5312 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5313 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5314 'uploader': 'Computerphile',
5315 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5316 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5317 'tags': [],
5318 'view_count': int,
5319 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5320 'channel_url': 'https://www.youtube.com/user/Computerphile',
5321 'channel': 'Computerphile',
c26f9b99 5322 'availability': 'public',
a6213a49 5323 },
5324 'playlist_mincount': 11,
5325 }, {
5326 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5327 'only_matching': True,
5328 }, {
5329 'note': 'Playlist URL that does not actually serve a playlist',
5330 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5331 'info_dict': {
5332 'id': 'FqZTN594JQw',
5333 'ext': 'webm',
5334 'title': "Smiley's People 01 detective, Adventure Series, Action",
5335 'uploader': 'STREEM',
5336 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5337 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5338 'upload_date': '20150526',
5339 'license': 'Standard YouTube License',
5340 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5341 'categories': ['People & Blogs'],
5342 'tags': list,
5343 'view_count': int,
5344 'like_count': int,
a6213a49 5345 },
5346 'params': {
5347 'skip_download': True,
5348 },
5349 'skip': 'This video is not available.',
5350 'add_ie': [YoutubeIE.ie_key()],
5351 }, {
5352 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5353 'only_matching': True,
5354 }, {
5355 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5356 'only_matching': True,
5357 }, {
5358 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5359 'info_dict': {
12a1b225 5360 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5361 'ext': 'mp4',
976ae3ea 5362 'title': str,
a6213a49 5363 'uploader': 'Sky News',
5364 'uploader_id': 'skynews',
5365 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5366 'upload_date': r're:\d{8}',
976ae3ea 5367 'description': str,
a6213a49 5368 'categories': ['News & Politics'],
5369 'tags': list,
5370 'like_count': int,
6c73052c 5371 'release_timestamp': 1642502819,
976ae3ea 5372 'channel': 'Sky News',
5373 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5374 'age_limit': 0,
5375 'view_count': int,
6c73052c 5376 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5377 'playable_in_embed': True,
6c73052c 5378 'release_date': '20220118',
976ae3ea 5379 'availability': 'public',
5380 'live_status': 'is_live',
5381 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5382 'channel_follower_count': int
a6213a49 5383 },
5384 'params': {
5385 'skip_download': True,
5386 },
976ae3ea 5387 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5388 }, {
5389 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5390 'info_dict': {
5391 'id': 'a48o2S1cPoo',
5392 'ext': 'mp4',
5393 'title': 'The Young Turks - Live Main Show',
5394 'uploader': 'The Young Turks',
5395 'uploader_id': 'TheYoungTurks',
5396 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5397 'upload_date': '20150715',
5398 'license': 'Standard YouTube License',
5399 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5400 'categories': ['News & Politics'],
5401 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5402 'like_count': int,
a6213a49 5403 },
5404 'params': {
5405 'skip_download': True,
5406 },
5407 'only_matching': True,
5408 }, {
5409 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5410 'only_matching': True,
5411 }, {
5412 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5413 'only_matching': True,
5414 }, {
5415 'note': 'A channel that is not live. Should raise error',
5416 'url': 'https://www.youtube.com/user/numberphile/live',
5417 'only_matching': True,
5418 }, {
5419 'url': 'https://www.youtube.com/feed/trending',
5420 'only_matching': True,
5421 }, {
5422 'url': 'https://www.youtube.com/feed/library',
5423 'only_matching': True,
5424 }, {
5425 'url': 'https://www.youtube.com/feed/history',
5426 'only_matching': True,
5427 }, {
5428 'url': 'https://www.youtube.com/feed/subscriptions',
5429 'only_matching': True,
5430 }, {
5431 'url': 'https://www.youtube.com/feed/watch_later',
5432 'only_matching': True,
5433 }, {
5434 'note': 'Recommended - redirects to home page.',
5435 'url': 'https://www.youtube.com/feed/recommended',
5436 'only_matching': True,
5437 }, {
5438 'note': 'inline playlist with not always working continuations',
5439 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5440 'only_matching': True,
5441 }, {
5442 'url': 'https://www.youtube.com/course',
5443 'only_matching': True,
5444 }, {
5445 'url': 'https://www.youtube.com/zsecurity',
5446 'only_matching': True,
5447 }, {
5448 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5449 'only_matching': True,
5450 }, {
5451 'url': 'https://www.youtube.com/TheYoungTurks/live',
5452 'only_matching': True,
5453 }, {
5454 'url': 'https://www.youtube.com/hashtag/cctv9',
5455 'info_dict': {
5456 'id': 'cctv9',
5457 'title': '#cctv9',
976ae3ea 5458 'tags': [],
a6213a49 5459 },
5460 'playlist_mincount': 350,
5461 }, {
5462 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5463 'only_matching': True,
5464 }, {
5465 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5466 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5467 'only_matching': True
5468 }, {
5469 'note': '/browse/ should redirect to /channel/',
5470 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5471 'only_matching': True
5472 }, {
5473 'note': 'VLPL, should redirect to playlist?list=PL...',
5474 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5475 'info_dict': {
5476 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5477 'uploader': 'NoCopyrightSounds',
5478 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5479 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5480 'title': 'NCS : All Releases 💿',
976ae3ea 5481 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5482 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5483 'modified_date': r're:\d{8}',
5484 'view_count': int,
5485 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5486 'tags': [],
5487 'channel': 'NoCopyrightSounds',
c26f9b99 5488 'availability': 'public',
a6213a49 5489 },
5490 'playlist_mincount': 166,
976ae3ea 5491 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5492 }, {
5493 'note': 'Topic, should redirect to playlist?list=UU...',
5494 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5495 'info_dict': {
5496 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5497 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5498 'title': 'Uploads from Royalty Free Music - Topic',
5499 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5500 'tags': [],
5501 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5502 'channel': 'Royalty Free Music - Topic',
5503 'view_count': int,
5504 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5505 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5506 'modified_date': r're:\d{8}',
5507 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5508 'description': '',
c26f9b99 5509 'availability': 'public',
a6213a49 5510 },
5511 'expected_warnings': [
a6213a49 5512 'The URL does not have a videos tab',
976ae3ea 5513 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5514 ],
5515 'playlist_mincount': 101,
5516 }, {
5517 'note': 'Topic without a UU playlist',
5518 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5519 'info_dict': {
5520 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5521 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5522 'tags': [],
a6213a49 5523 },
5524 'expected_warnings': [
976ae3ea 5525 'the playlist redirect gave error',
a6213a49 5526 ],
5527 'playlist_mincount': 9,
5528 }, {
5529 'note': 'Youtube music Album',
5530 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5531 'info_dict': {
5532 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5533 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5534 'tags': [],
5535 'view_count': int,
5536 'description': '',
5537 'availability': 'unlisted',
5538 'modified_date': r're:\d{8}',
a6213a49 5539 },
5540 'playlist_count': 50,
5541 }, {
5542 'note': 'unlisted single video playlist',
5543 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5544 'info_dict': {
5545 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5546 'uploader': 'colethedj',
5547 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5548 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5549 'availability': 'unlisted',
5550 'tags': [],
12a1b225 5551 'modified_date': '20220418',
976ae3ea 5552 'channel': 'colethedj',
5553 'view_count': int,
5554 'description': '',
5555 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5556 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5557 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5558 },
5559 'playlist_count': 1,
5560 }, {
5561 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5562 'url': 'https://www.youtube.com/feed/recommended',
5563 'info_dict': {
5564 'id': 'recommended',
5565 'title': 'recommended',
6c73052c 5566 'tags': [],
a6213a49 5567 },
5568 'playlist_mincount': 50,
5569 'params': {
5570 'skip_download': True,
5571 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5572 },
5573 }, {
5574 'note': 'API Fallback: /videos tab, sorted by oldest first',
5575 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5576 'info_dict': {
5577 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5578 'title': 'Cody\'sLab - Videos',
5579 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5580 'uploader': 'Cody\'sLab',
5581 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5582 'channel': 'Cody\'sLab',
5583 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5584 'tags': [],
5585 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5586 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5587 'channel_follower_count': int
a6213a49 5588 },
5589 'playlist_mincount': 650,
5590 'params': {
5591 'skip_download': True,
5592 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5593 },
5594 }, {
5595 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5596 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5597 'info_dict': {
5598 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5599 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5600 'title': 'Uploads from Royalty Free Music - Topic',
5601 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5602 'modified_date': r're:\d{8}',
5603 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5604 'description': '',
5605 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5606 'tags': [],
5607 'channel': 'Royalty Free Music - Topic',
5608 'view_count': int,
5609 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5610 'availability': 'public',
a6213a49 5611 },
5612 'expected_warnings': [
976ae3ea 5613 'does not have a videos tab',
5614 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5615 ],
5616 'playlist_mincount': 101,
5617 'params': {
5618 'skip_download': True,
5619 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5620 },
7c219ea6 5621 }, {
5622 'note': 'non-standard redirect to regional channel',
5623 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5624 'only_matching': True
61d3665d 5625 }, {
5626 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5627 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5628 'info_dict': {
5629 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5630 'modified_date': '20220407',
5631 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5632 'tags': [],
5633 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5634 'uploader': 'pukkandan',
5635 'availability': 'unlisted',
5636 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5637 'channel': 'pukkandan',
5638 'description': 'Test for collaborative playlist',
5639 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5640 'view_count': int,
61d3665d 5641 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5642 },
5643 'playlist_mincount': 2
c26f9b99 5644 }, {
5645 'note': 'translated tab name',
5646 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5647 'info_dict': {
5648 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5649 'tags': [],
5650 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5651 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5652 'description': '',
5653 'title': 'cole-dlp-test-acc - 再生リスト',
5654 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5655 'uploader': 'cole-dlp-test-acc',
5656 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5657 'channel': 'cole-dlp-test-acc',
5658 },
5659 'playlist_mincount': 1,
5660 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5661 'expected_warnings': ['Preferring "ja"'],
5662 }, {
5663 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5664 'note': 'preferred lang set with playlist with translated video titles',
5665 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5666 'info_dict': {
5667 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5668 'tags': [],
5669 'view_count': int,
5670 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5671 'uploader': 'cole-dlp-test-acc',
5672 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5673 'channel': 'cole-dlp-test-acc',
5674 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5675 'description': 'test',
5676 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5677 'title': 'dlp test playlist',
5678 'availability': 'public',
5679 },
5680 'playlist_mincount': 1,
5681 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5682 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5683 }, {
5684 # shorts audio pivot for 2GtVksBMYFM.
5685 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5686 'info_dict': {
5687 'id': 'sfv_audio_pivot',
5688 'title': 'sfv_audio_pivot',
5689 'tags': [],
5690 },
5691 'playlist_mincount': 50,
5692
a6213a49 5693 }]
5694
5695 @classmethod
5696 def suitable(cls, url):
86e5f3ed 5697 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5698
64f36541 5699 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5700
182bda88 5701 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5702 def _real_extract(self, url, smuggled_data):
cd7c66cf 5703 item_id = self._match_id(url)
14f25df2 5704 url = urllib.parse.urlunparse(
5705 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5706 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5707
fe03a6cd 5708 def get_mobj(url):
37e57a9f 5709 mobj = self._URL_RE.match(url).groupdict()
07cce701 5710 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5711 return mobj
5712
37e57a9f 5713 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5714 # Youtube returns incomplete data if tabname is not lower case
5715 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5716 if is_channel:
5717 if smuggled_data.get('is_music_url'):
37e57a9f 5718 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5719 item_id = item_id[2:]
37e57a9f 5720 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5721 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5722 mdata = self._extract_tab_endpoint(
37e57a9f 5723 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5724 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5725 get_all=False, expected_type=str)
ac56cf38 5726 if not murl:
37e57a9f 5727 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5728 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5729 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5730 pre = f'https://www.youtube.com/channel/{item_id}'
5731
64f36541 5732 original_tab_name = tab
fe03a6cd 5733 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5734 # Home URLs should redirect to /videos/
37e57a9f 5735 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5736 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5737 tab = '/videos'
5738
5739 url = ''.join((pre, tab, post))
5740 mobj = get_mobj(url)
cd7c66cf 5741
5742 # Handle both video/playlist URLs
201c1459 5743 qs = parse_qs(url)
86e5f3ed 5744 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5745
fe03a6cd 5746 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5747 if not playlist_id:
fe03a6cd 5748 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5749 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5750 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5751 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5752 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5753 mobj = get_mobj(url)
cd7c66cf 5754
5755 if video_id and playlist_id:
a06916d9 5756 if self.get_param('noplaylist'):
37e57a9f 5757 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5758 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5759 ie=YoutubeIE.ie_key(), video_id=video_id)
5760 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5761
ac56cf38 5762 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5763
7c219ea6 5764 # YouTube may provide a non-standard redirect to the regional channel
5765 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5766 redirect_url = traverse_obj(
5767 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5768 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5769 redirect_url = ''.join((
5770 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5771 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5772 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5773
37e57a9f 5774 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5775 if tabs:
5776 selected_tab = self._extract_selected_tab(tabs)
c26f9b99 5777 selected_tab_url = urljoin(
5778 url, traverse_obj(selected_tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5779 translated_tab_name = selected_tab.get('title', '').lower()
5780
5781 # Prefer tab name from tab url as it is always in en,
5782 # but only when preferred lang is set as it may not extract reliably in all cases.
5783 selected_tab_name = (self._preferred_lang in (None, 'en') and translated_tab_name
5784 or selected_tab_url and get_mobj(selected_tab_url)['tab'][1:] # primary
5785 or translated_tab_name)
5786
64f36541 5787 if selected_tab_name == 'home':
5788 selected_tab_name = 'featured'
5789 requested_tab_name = mobj['tab'][1:]
c26f9b99 5790
09f1580e 5791 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5792 if requested_tab_name == 'live': # Live tab should have redirected to the video
5793 raise UserNotLive(video_id=mobj['id'])
64f36541 5794 if requested_tab_name not in ('', selected_tab_name):
5795 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5796 if not original_tab_name:
5797 if item_id[:2] == 'UC':
5798 # Topic channels don't have /videos. Use the equivalent playlist instead
5799 pl_id = f'UU{item_id[2:]}'
5800 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5801 try:
5802 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5803 except ExtractorError:
5804 redirect_warning += ' and the playlist redirect gave error'
5805 else:
5806 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5807 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5808 if selected_tab_name and selected_tab_name != requested_tab_name:
5809 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5810 else:
5811 raise ExtractorError(redirect_warning, expected=True)
18db7548 5812
37e57a9f 5813 if redirect_warning:
64f36541 5814 self.to_screen(redirect_warning)
37e57a9f 5815 self.write_debug(f'Final URL: {url}')
18db7548 5816
358de58c 5817 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5818 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5819 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5820 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5821 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5822 if tabs:
ac56cf38 5823 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5824
37e57a9f 5825 playlist = traverse_obj(
5826 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5827 if playlist:
ac56cf38 5828 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5829
37e57a9f 5830 video_id = traverse_obj(
5831 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5832 if video_id:
09f1580e 5833 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5834 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5835 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5836 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5837
8bdd16b4 5838 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5839
c5e8d7af 5840
8bdd16b4 5841class YoutubePlaylistIE(InfoExtractor):
96565c7e 5842 IE_DESC = 'YouTube playlists'
8bdd16b4 5843 _VALID_URL = r'''(?x)(?:
5844 (?:https?://)?
5845 (?:\w+\.)?
5846 (?:
5847 (?:
5848 youtube(?:kids)?\.com|
d9190e44 5849 %(invidious)s
8bdd16b4 5850 )
5851 /.*?\?.*?\blist=
5852 )?
5853 (?P<id>%(playlist_id)s)
d9190e44
RH
5854 )''' % {
5855 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5856 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5857 }
8bdd16b4 5858 IE_NAME = 'youtube:playlist'
cdc628a4 5859 _TESTS = [{
8bdd16b4 5860 'note': 'issue #673',
5861 'url': 'PLBB231211A4F62143',
cdc628a4 5862 'info_dict': {
8bdd16b4 5863 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5864 'id': 'PLBB231211A4F62143',
976ae3ea 5865 'uploader': 'Wickman',
8bdd16b4 5866 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5867 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5868 'view_count': int,
5869 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5870 'modified_date': r're:\d{8}',
5871 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5872 'channel': 'Wickman',
5873 'tags': [],
5874 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5875 },
5876 'playlist_mincount': 29,
5877 }, {
5878 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5879 'info_dict': {
5880 'title': 'YDL_safe_search',
5881 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5882 },
5883 'playlist_count': 2,
5884 'skip': 'This playlist is private',
9558dcec 5885 }, {
8bdd16b4 5886 'note': 'embedded',
5887 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5888 'playlist_count': 4,
9558dcec 5889 'info_dict': {
8bdd16b4 5890 'title': 'JODA15',
5891 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5892 'uploader': 'milan',
5893 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5894 'description': '',
5895 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5896 'tags': [],
5897 'modified_date': '20140919',
5898 'view_count': int,
5899 'channel': 'milan',
5900 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5901 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 5902 'availability': 'public',
976ae3ea 5903 },
5904 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5905 }, {
8bdd16b4 5906 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5907 'playlist_mincount': 455,
8bdd16b4 5908 'info_dict': {
5909 'title': '2018 Chinese New Singles (11/6 updated)',
5910 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5911 'uploader': 'LBK',
5912 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5913 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5914 'channel': 'LBK',
5915 'view_count': int,
5916 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5917 'tags': [],
5918 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5919 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5920 'modified_date': r're:\d{8}',
c26f9b99 5921 'availability': 'public',
976ae3ea 5922 },
5923 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5924 }, {
29f7c58a 5925 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5926 'only_matching': True,
5927 }, {
5928 # music album playlist
5929 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5930 'only_matching': True,
5931 }]
5932
5933 @classmethod
5934 def suitable(cls, url):
201c1459 5935 if YoutubeTabIE.suitable(url):
5936 return False
49a57e70 5937 from ..utils import parse_qs
201c1459 5938 qs = parse_qs(url)
5939 if qs.get('v', [None])[0]:
5940 return False
86e5f3ed 5941 return super().suitable(url)
29f7c58a 5942
5943 def _real_extract(self, url):
5944 playlist_id = self._match_id(url)
46953e7e 5945 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5946 url = update_url_query(
5947 'https://www.youtube.com/playlist',
5948 parse_qs(url) or {'list': playlist_id})
5949 if is_music_url:
5950 url = smuggle_url(url, {'is_music_url': True})
5951 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5952
5953
5954class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5955 IE_DESC = 'youtu.be'
29f7c58a 5956 _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}
5957 _TESTS = [{
8bdd16b4 5958 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5959 'info_dict': {
5960 'id': 'yeWKywCrFtk',
5961 'ext': 'mp4',
5962 'title': 'Small Scale Baler and Braiding Rugs',
5963 'uploader': 'Backus-Page House Museum',
5964 'uploader_id': 'backuspagemuseum',
5965 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5966 'upload_date': '20161008',
5967 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5968 'categories': ['Nonprofits & Activism'],
5969 'tags': list,
5970 'like_count': int,
976ae3ea 5971 'age_limit': 0,
5972 'playable_in_embed': True,
5973 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5974 'channel': 'Backus-Page House Museum',
5975 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5976 'live_status': 'not_live',
5977 'view_count': int,
5978 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5979 'availability': 'public',
5980 'duration': 59,
12a1b225
A
5981 'comment_count': int,
5982 'channel_follower_count': int
8bdd16b4 5983 },
5984 'params': {
5985 'noplaylist': True,
5986 'skip_download': True,
5987 },
39e7107d 5988 }, {
8bdd16b4 5989 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5990 'only_matching': True,
cdc628a4
PH
5991 }]
5992
8bdd16b4 5993 def _real_extract(self, url):
5ad28e7f 5994 mobj = self._match_valid_url(url)
29f7c58a 5995 video_id = mobj.group('id')
5996 playlist_id = mobj.group('playlist_id')
8bdd16b4 5997 return self.url_result(
29f7c58a 5998 update_url_query('https://www.youtube.com/watch', {
5999 'v': video_id,
6000 'list': playlist_id,
6001 'feature': 'youtu.be',
6002 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6003
6004
b6ce9bb0 6005class YoutubeLivestreamEmbedIE(InfoExtractor):
6006 IE_DESC = 'YouTube livestream embeds'
6007 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6008 _TESTS = [{
6009 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6010 'only_matching': True,
6011 }]
6012
6013 def _real_extract(self, url):
6014 channel_id = self._match_id(url)
6015 return self.url_result(
6016 f'https://www.youtube.com/channel/{channel_id}/live',
6017 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6018
6019
8bdd16b4 6020class YoutubeYtUserIE(InfoExtractor):
96565c7e 6021 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6022 IE_NAME = 'youtube:user'
8bdd16b4 6023 _VALID_URL = r'ytuser:(?P<id>.+)'
6024 _TESTS = [{
6025 'url': 'ytuser:phihag',
6026 'only_matching': True,
6027 }]
6028
6029 def _real_extract(self, url):
6030 user_id = self._match_id(url)
6031 return self.url_result(
c586f9e8 6032 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 6033 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 6034
b05654f0 6035
3d3dddc9 6036class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6037 IE_NAME = 'youtube:favorites'
96565c7e 6038 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6039 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6040 _LOGIN_REQUIRED = True
6041 _TESTS = [{
6042 'url': ':ytfav',
6043 'only_matching': True,
6044 }, {
6045 'url': ':ytfavorites',
6046 'only_matching': True,
6047 }]
6048
6049 def _real_extract(self, url):
6050 return self.url_result(
6051 'https://www.youtube.com/playlist?list=LL',
6052 ie=YoutubeTabIE.ie_key())
6053
6054
ca5300c7 6055class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6056 IE_NAME = 'youtube:notif'
6057 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6058 _VALID_URL = r':ytnotif(?:ication)?s?'
6059 _LOGIN_REQUIRED = True
6060 _TESTS = [{
6061 'url': ':ytnotif',
6062 'only_matching': True,
6063 }, {
6064 'url': ':ytnotifications',
6065 'only_matching': True,
6066 }]
6067
6068 def _extract_notification_menu(self, response, continuation_list):
6069 notification_list = traverse_obj(
6070 response,
6071 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6072 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6073 expected_type=list) or []
6074 continuation_list[0] = None
6075 for item in notification_list:
6076 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6077 if entry:
6078 yield entry
6079 continuation = item.get('continuationItemRenderer')
6080 if continuation:
6081 continuation_list[0] = continuation
6082
6083 def _extract_notification_renderer(self, notification):
6084 video_id = traverse_obj(
6085 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6086 url = f'https://www.youtube.com/watch?v={video_id}'
6087 channel_id = None
6088 if not video_id:
6089 browse_ep = traverse_obj(
6090 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6091 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6092 post_id = self._search_regex(
6093 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6094 'post id', default=None)
6095 if not channel_id or not post_id:
6096 return
6097 # The direct /post url redirects to this in the browser
6098 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6099
6100 channel = traverse_obj(
6101 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6102 expected_type=str)
c7a7baaa 6103 notification_title = self._get_text(notification, 'shortMessage')
6104 if notification_title:
6105 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6106 # TODO: handle recommended videos
ca5300c7 6107 title = self._search_regex(
c7a7baaa 6108 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6109 'video title', default=None)
5225df50 6110 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6111 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6112 else None)
ca5300c7 6113 return {
6114 '_type': 'url',
6115 'url': url,
6116 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6117 'video_id': video_id,
6118 'title': title,
6119 'channel_id': channel_id,
6120 'channel': channel,
6121 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6122 'timestamp': timestamp,
ca5300c7 6123 }
6124
6125 def _notification_menu_entries(self, ytcfg):
6126 continuation_list = [None]
6127 response = None
6128 for page in itertools.count(1):
6129 ctoken = traverse_obj(
6130 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6131 response = self._extract_response(
6132 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6133 ep='notification/get_notification_menu', check_get_keys='actions',
6134 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6135 yield from self._extract_notification_menu(response, continuation_list)
6136 if not continuation_list[0]:
6137 break
6138
6139 def _real_extract(self, url):
6140 display_id = 'notifications'
6141 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6142 self._report_playlist_authcheck(ytcfg)
6143 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6144
6145
a6213a49 6146class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6147 IE_DESC = 'YouTube search'
78caa52a 6148 IE_NAME = 'youtube:search'
b05654f0 6149 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6150 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6151 _TESTS = [{
6152 'url': 'ytsearch5:youtube-dl test video',
6153 'playlist_count': 5,
6154 'info_dict': {
6155 'id': 'youtube-dl test video',
6156 'title': 'youtube-dl test video',
6157 }
6158 }]
b05654f0 6159
a61fd4cf 6160
5f7cb91a 6161class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6162 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6163 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6164 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6165 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6166 _TESTS = [{
6167 'url': 'ytsearchdate5:youtube-dl test video',
6168 'playlist_count': 5,
6169 'info_dict': {
6170 'id': 'youtube-dl test video',
6171 'title': 'youtube-dl test video',
6172 }
6173 }]
75dff0ee 6174
c9ae7b95 6175
a6213a49 6176class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6177 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6178 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6179 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6180 _TESTS = [{
6181 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6182 'playlist_mincount': 5,
6183 'info_dict': {
11f9be09 6184 'id': 'youtube-dl test video',
3462ffa8 6185 'title': 'youtube-dl test video',
6186 }
a61fd4cf 6187 }, {
6188 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6189 'playlist_mincount': 5,
6190 'info_dict': {
6191 'id': 'python',
6192 'title': 'python',
6193 }
ad210f4f 6194 }, {
6195 'url': 'https://www.youtube.com/results?search_query=%23cats',
6196 'playlist_mincount': 1,
6197 'info_dict': {
6198 'id': '#cats',
6199 'title': '#cats',
12a1b225
A
6200 # The test suite does not have support for nested playlists
6201 # 'entries': [{
6202 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6203 # 'title': '#cats',
6204 # }],
ad210f4f 6205 },
3462ffa8 6206 }, {
6207 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6208 'only_matching': True,
6209 }]
6210
6211 def _real_extract(self, url):
4dfbf869 6212 qs = parse_qs(url)
386e1dd9 6213 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6214 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6215
6216
16aa9ea4 6217class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6218 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6219 IE_NAME = 'youtube:music:search_url'
6220 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6221 _TESTS = [{
6222 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6223 'playlist_count': 16,
6224 'info_dict': {
6225 'id': 'royalty free music',
6226 'title': 'royalty free music',
6227 }
6228 }, {
6229 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6230 'playlist_mincount': 30,
6231 'info_dict': {
6232 'id': 'royalty free music - songs',
6233 'title': 'royalty free music - songs',
6234 },
6235 'params': {'extract_flat': 'in_playlist'}
6236 }, {
6237 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6238 'playlist_mincount': 30,
6239 'info_dict': {
6240 'id': 'royalty free music - community playlists',
6241 'title': 'royalty free music - community playlists',
6242 },
6243 'params': {'extract_flat': 'in_playlist'}
6244 }]
6245
6246 _SECTIONS = {
6247 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6248 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6249 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6250 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6251 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6252 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6253 }
6254
6255 def _real_extract(self, url):
6256 qs = parse_qs(url)
6257 query = (qs.get('search_query') or qs.get('q'))[0]
6258 params = qs.get('sp', (None,))[0]
6259 if params:
6260 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6261 else:
ac668111 6262 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6263 params = self._SECTIONS.get(section)
6264 if not params:
6265 section = None
6266 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6267 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6268
6269
182bda88 6270class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6271 """
25f14e9f 6272 Base class for feed extractors
82d02080 6273 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6274 """
b2e8bc1b 6275 _LOGIN_REQUIRED = True
82d02080 6276 _FEED_NAME = 'feeds'
a25bca9f 6277
6278 def _real_initialize(self):
6279 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6280
82d02080 6281 @classproperty
d7ae0639 6282 def IE_NAME(self):
82d02080 6283 return f'youtube:{self._FEED_NAME}'
04cc9617 6284
3853309f 6285 def _real_extract(self, url):
3d3dddc9 6286 return self.url_result(
182bda88 6287 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6288
6289
ef2f3c7f 6290class YoutubeWatchLaterIE(InfoExtractor):
6291 IE_NAME = 'youtube:watchlater'
96565c7e 6292 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6293 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6294 _TESTS = [{
8bdd16b4 6295 'url': ':ytwatchlater',
bc7a9cd8
S
6296 'only_matching': True,
6297 }]
25f14e9f
S
6298
6299 def _real_extract(self, url):
ef2f3c7f 6300 return self.url_result(
6301 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6302
6303
25f14e9f 6304class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6305 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6306 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6307 _FEED_NAME = 'recommended'
45db527f 6308 _LOGIN_REQUIRED = False
3d3dddc9 6309 _TESTS = [{
6310 'url': ':ytrec',
6311 'only_matching': True,
6312 }, {
6313 'url': ':ytrecommended',
6314 'only_matching': True,
6315 }, {
6316 'url': 'https://youtube.com',
6317 'only_matching': True,
6318 }]
1ed5b5c9 6319
1ed5b5c9 6320
25f14e9f 6321class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6322 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6323 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6324 _FEED_NAME = 'subscriptions'
3d3dddc9 6325 _TESTS = [{
6326 'url': ':ytsubs',
6327 'only_matching': True,
6328 }, {
6329 'url': ':ytsubscriptions',
6330 'only_matching': True,
6331 }]
1ed5b5c9 6332
1ed5b5c9 6333
25f14e9f 6334class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6335 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6336 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6337 _FEED_NAME = 'history'
3d3dddc9 6338 _TESTS = [{
6339 'url': ':ythistory',
6340 'only_matching': True,
6341 }]
1ed5b5c9
JMF
6342
6343
6e634cbe 6344class YoutubeStoriesIE(InfoExtractor):
6345 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6346 IE_NAME = 'youtube:stories'
6347 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6348 _TESTS = [{
6349 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6350 'only_matching': True,
6351 }]
6352
6353 def _real_extract(self, url):
6354 playlist_id = f'RLTD{self._match_id(url)}'
6355 return self.url_result(
50ac0e54 6356 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6357 ie=YoutubeTabIE, video_id=playlist_id)
6358
6359
80eb0bd9 6360class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6361 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6362 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6363 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6364 _TESTS = [{
1dd18a88 6365 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6366 'only_matching': True,
6367 }]
6368
6369 @staticmethod
6370 def _generate_audio_pivot_params(video_id):
6371 """
6372 Generates sfv_audio_pivot browse params for this video id
6373 """
6374 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6375 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6376
6377 def _real_extract(self, url):
6378 video_id = self._match_id(url)
6379 return self.url_result(
6380 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6381 ie=YoutubeTabIE)
6382
6383
15870e90
PH
6384class YoutubeTruncatedURLIE(InfoExtractor):
6385 IE_NAME = 'youtube:truncated_url'
6386 IE_DESC = False # Do not list
975d35db 6387 _VALID_URL = r'''(?x)
b95aab84
PH
6388 (?:https?://)?
6389 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6390 (?:watch\?(?:
c4808c60 6391 feature=[a-z_]+|
b95aab84
PH
6392 annotation_id=annotation_[^&]+|
6393 x-yt-cl=[0-9]+|
c1708b89 6394 hl=[^&]*|
287be8c6 6395 t=[0-9]+
b95aab84
PH
6396 )?
6397 |
6398 attribution_link\?a=[^&]+
6399 )
6400 $
975d35db 6401 '''
15870e90 6402
c4808c60 6403 _TESTS = [{
2d3d2997 6404 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6405 'only_matching': True,
dc2fc736 6406 }, {
2d3d2997 6407 'url': 'https://www.youtube.com/watch?',
dc2fc736 6408 'only_matching': True,
b95aab84
PH
6409 }, {
6410 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6411 'only_matching': True,
6412 }, {
6413 'url': 'https://www.youtube.com/watch?feature=foo',
6414 'only_matching': True,
c1708b89
PH
6415 }, {
6416 'url': 'https://www.youtube.com/watch?hl=en-GB',
6417 'only_matching': True,
287be8c6
PH
6418 }, {
6419 'url': 'https://www.youtube.com/watch?t=2372',
6420 'only_matching': True,
c4808c60
PH
6421 }]
6422
15870e90
PH
6423 def _real_extract(self, url):
6424 raise ExtractorError(
78caa52a
PH
6425 'Did you forget to quote the URL? Remember that & is a meta '
6426 'character in most shells, so you want to put the URL in quotes, '
3867038a 6427 'like youtube-dl '
2d3d2997 6428 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6429 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6430 expected=True)
772fd5cc
PH
6431
6432
471d0367 6433class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6434 IE_NAME = 'youtube:clip'
471d0367 6435 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6436 _TESTS = [{
6437 # FIXME: Other metadata should be extracted from the clip, not from the base video
6438 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6439 'info_dict': {
6440 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6441 'ext': 'mp4',
6442 'section_start': 29.0,
6443 'section_end': 39.7,
6444 'duration': 10.7,
12a1b225
A
6445 'age_limit': 0,
6446 'availability': 'public',
6447 'categories': ['Gaming'],
6448 'channel': 'Scott The Woz',
6449 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6450 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6451 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6452 'like_count': int,
6453 'playable_in_embed': True,
6454 'tags': 'count:17',
6455 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6456 'title': 'Mobile Games on Console - Scott The Woz',
6457 'upload_date': '20210920',
6458 'uploader': 'Scott The Woz',
6459 'uploader_id': 'scottthewoz',
6460 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6461 'view_count': int,
6462 'live_status': 'not_live',
6463 'channel_follower_count': int
471d0367 6464 }
6465 }]
3cd786db 6466
6467 def _real_extract(self, url):
471d0367 6468 clip_id = self._match_id(url)
6469 _, data = self._extract_webpage(url, clip_id)
6470
6471 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6472 if not video_id:
6473 raise ExtractorError('Unable to find video ID')
6474
6475 clip_data = traverse_obj(data, (
6476 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6477 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6478 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6479 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6480
6481 return {
6482 '_type': 'url_transparent',
6483 'url': f'https://www.youtube.com/watch?v={video_id}',
6484 'ie_key': YoutubeIE.ie_key(),
6485 'id': clip_id,
6486 'section_start': int(clip_data['startTimeMs']) / 1000,
6487 'section_end': int(clip_data['endTimeMs']) / 1000,
6488 }
3cd786db 6489
6490
772fd5cc
PH
6491class YoutubeTruncatedIDIE(InfoExtractor):
6492 IE_NAME = 'youtube:truncated_id'
6493 IE_DESC = False # Do not list
b95aab84 6494 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6495
6496 _TESTS = [{
6497 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6498 'only_matching': True,
6499 }]
6500
6501 def _real_extract(self, url):
6502 video_id = self._match_id(url)
6503 raise ExtractorError(
86e5f3ed 6504 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6505 expected=True)