]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[cleanup Misc
[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,
30a074c2 963 }
964
0c148415 965
360e1ca5 966class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 967 IE_DESC = 'YouTube'
cb7dfeea 968 _VALID_URL = r"""(?x)^
c5e8d7af 969 (
edb53e2d 970 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 971 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
972 (?:www\.)?deturl\.com/www\.youtube\.com|
973 (?:www\.)?pwnyoutube\.com|
974 (?:www\.)?hooktube\.com|
975 (?:www\.)?yourepeat\.com|
976 tube\.majestyc\.net|
977 %(invidious)s|
978 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
979 (?:.*?\#/)? # handle anchor (#/) redirect urls
980 (?: # the various things that can precede the ID:
b6ce9bb0 981 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 982 |(?: # or the v= param in all its forms
f7000f3a 983 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 984 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 985 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
986 v=
987 )
f4b05232 988 ))
cbaed4bb
S
989 |(?:
990 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
991 vid\.plus| # or vid.plus/xxxx
992 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 993 %(invidious)s
cbaed4bb 994 )/
edb53e2d 995 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 996 )
c5e8d7af 997 )? # all until now is optional -> you can pass the naked ID
201c1459 998 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 999 (?(1).+)? # if we found the ID, everything can follow
9297939e 1000 (?:\#|$)""" % {
d9190e44 1001 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1002 }
7c6eb424 1003 _EMBED_REGEX = [
1004 r'''(?x)
1005 (?:
0ca0f881 1006 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1007 data-video-url=|
1008 <embed[^>]+?src=|
1009 embedSWF\(?:\s*|
1010 <object[^>]+data=|
1011 new\s+SWFObject\(
1012 )
1013 (["\'])
1014 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1015 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1016 \1''',
1017 # https://wordpress.org/plugins/lazy-load-for-videos/
1018 r'''(?xs)
1019 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1020 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1021 ]
1022
e40c758c 1023 _PLAYER_INFO_RE = (
cc2db878 1024 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1025 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$',
545cc85d 1026 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1027 )
2c62dc26 1028 _formats = {
c2d3cb4c 1029 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1030 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1031 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1032 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1033 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1034 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1035 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1036 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1037 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1038 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1039 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1040 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1041 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1042 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1043 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1044 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1045 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1046 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1047
1048
1049 # 3D videos
c2d3cb4c 1050 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1051 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1052 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1053 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1054 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1055 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1056 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1057
96fb5605 1058 # Apple HTTP Live Streaming
11f12195 1059 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1060 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1061 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1062 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1063 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1064 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1065 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1066 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1067
1068 # DASH mp4 video
d23028a8
S
1069 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1070 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1071 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1072 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1073 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1074 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1075 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1076 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1077 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1078 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1079 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1080 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1081
f6f1fc92 1082 # Dash mp4 audio
d23028a8
S
1083 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1084 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1085 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1086 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1087 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1088 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1089 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1090
1091 # Dash webm
d23028a8
S
1092 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1093 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1094 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1095 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1096 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1097 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1098 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1099 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1100 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1101 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1102 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1103 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1104 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1105 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1106 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1107 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1108 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1109 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1110 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1111 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1112 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1113 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1114
1115 # Dash webm audio
d23028a8
S
1116 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1117 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1118
0857baad 1119 # Dash webm audio with opus inside
d23028a8
S
1120 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1121 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1122 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1123
ce6b9a2d
PH
1124 # RTMP (unnamed)
1125 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1126
1127 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1128 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1129 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1130 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1131 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1132 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1133 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1134 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1135 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1136 }
29f7c58a 1137 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1138
fd5c4aab
S
1139 _GEO_BYPASS = False
1140
78caa52a 1141 IE_NAME = 'youtube'
2eb88d95
PH
1142 _TESTS = [
1143 {
2d3d2997 1144 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1145 'info_dict': {
1146 'id': 'BaW_jenozKc',
1147 'ext': 'mp4',
3867038a 1148 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1149 'uploader': 'Philipp Hagemeister',
1150 'uploader_id': 'phihag',
ec85ded8 1151 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1152 'channel': 'Philipp Hagemeister',
dd4c4492
S
1153 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1154 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1155 'upload_date': '20121002',
ff9f925b 1156 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1157 'categories': ['Science & Technology'],
3867038a 1158 'tags': ['youtube-dl'],
556dbe7f 1159 'duration': 10,
dbdaaa23 1160 'view_count': int,
3e7c1224 1161 'like_count': int,
ff9f925b 1162 'availability': 'public',
1163 'playable_in_embed': True,
1164 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1165 'live_status': 'not_live',
1166 'age_limit': 0,
7c80519c 1167 'start_time': 1,
297a564b 1168 'end_time': 9,
12a1b225 1169 'comment_count': int,
6c73052c 1170 'channel_follower_count': int
2eb88d95 1171 }
0e853ca4 1172 },
fccd3771 1173 {
4bc3a23e
PH
1174 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1175 'note': 'Embed-only video (#1746)',
1176 'info_dict': {
1177 'id': 'yZIXLfi8CZQ',
1178 'ext': 'mp4',
1179 'upload_date': '20120608',
1180 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1181 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1182 'uploader': 'SET India',
94bfcd23 1183 'uploader_id': 'setindia',
ec85ded8 1184 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1185 'age_limit': 18,
545cc85d 1186 },
1187 'skip': 'Private video',
fccd3771 1188 },
11b56058 1189 {
8bdd16b4 1190 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1191 'note': 'Use the first video ID in the URL',
1192 'info_dict': {
1193 'id': 'BaW_jenozKc',
1194 'ext': 'mp4',
3867038a 1195 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1196 'uploader': 'Philipp Hagemeister',
1197 'uploader_id': 'phihag',
ec85ded8 1198 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1199 'channel': 'Philipp Hagemeister',
1200 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1201 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1202 'upload_date': '20121002',
976ae3ea 1203 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1204 'categories': ['Science & Technology'],
3867038a 1205 'tags': ['youtube-dl'],
556dbe7f 1206 'duration': 10,
dbdaaa23 1207 'view_count': int,
11b56058 1208 'like_count': int,
976ae3ea 1209 'availability': 'public',
1210 'playable_in_embed': True,
1211 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1212 'live_status': 'not_live',
1213 'age_limit': 0,
12a1b225 1214 'comment_count': int,
6c73052c 1215 'channel_follower_count': int
34a7de29
S
1216 },
1217 'params': {
1218 'skip_download': True,
1219 },
11b56058 1220 },
dd27fd17 1221 {
2d3d2997 1222 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1223 'note': '256k DASH audio (format 141) via DASH manifest',
1224 'info_dict': {
1225 'id': 'a9LDPn-MO4I',
1226 'ext': 'm4a',
1227 'upload_date': '20121002',
1228 'uploader_id': '8KVIDEO',
ec85ded8 1229 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1230 'description': '',
1231 'uploader': '8KVIDEO',
1232 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1233 },
4bc3a23e
PH
1234 'params': {
1235 'youtube_include_dash_manifest': True,
1236 'format': '141',
4919603f 1237 },
de3c7fe0 1238 'skip': 'format 141 not served anymore',
dd27fd17 1239 },
8bdd16b4 1240 # DASH manifest with encrypted signature
1241 {
1242 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1243 'info_dict': {
1244 'id': 'IB3lcPjvWLA',
1245 'ext': 'm4a',
1246 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1247 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1248 'duration': 244,
1249 'uploader': 'AfrojackVEVO',
1250 'uploader_id': 'AfrojackVEVO',
1251 'upload_date': '20131011',
cc2db878 1252 'abr': 129.495,
976ae3ea 1253 'like_count': int,
1254 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1255 'playable_in_embed': True,
1256 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1257 'view_count': int,
1258 'track': 'The Spark',
1259 'live_status': 'not_live',
1260 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1261 'channel': 'Afrojack',
1262 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1263 'tags': 'count:19',
1264 'availability': 'public',
1265 'categories': ['Music'],
1266 'age_limit': 0,
1267 'alt_title': 'The Spark',
6c73052c 1268 'channel_follower_count': int
8bdd16b4 1269 },
1270 'params': {
1271 'youtube_include_dash_manifest': True,
1272 'format': '141/bestaudio[ext=m4a]',
1273 },
1274 },
65c2fde2 1275 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1276 {
65c2fde2 1277 'note': 'Embed allowed age-gate video',
2d3d2997 1278 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1279 'info_dict': {
1280 'id': 'HtVdAasjOgU',
1281 'ext': 'mp4',
1282 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1283 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1284 'duration': 142,
c522adb1
JMF
1285 'uploader': 'The Witcher',
1286 'uploader_id': 'WitcherGame',
ec85ded8 1287 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1288 'upload_date': '20140605',
34952f09 1289 'age_limit': 18,
976ae3ea 1290 'categories': ['Gaming'],
1291 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1292 'availability': 'needs_auth',
1293 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1294 'like_count': int,
1295 'channel': 'The Witcher',
1296 'live_status': 'not_live',
1297 'tags': 'count:17',
1298 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1299 'playable_in_embed': True,
1300 'view_count': int,
6c73052c 1301 'channel_follower_count': int
c522adb1
JMF
1302 },
1303 },
65c2fde2 1304 {
1305 'note': 'Age-gate video with embed allowed in public site',
1306 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1307 'info_dict': {
1308 'id': 'HsUATh_Nc2U',
1309 'ext': 'mp4',
1310 'title': 'Godzilla 2 (Official Video)',
1311 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1312 'upload_date': '20200408',
1313 'uploader_id': 'FlyingKitty900',
1314 'uploader': 'FlyingKitty',
1315 'age_limit': 18,
976ae3ea 1316 'availability': 'needs_auth',
1317 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1318 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1319 'channel': 'FlyingKitty',
1320 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1321 'view_count': int,
1322 'categories': ['Entertainment'],
1323 'live_status': 'not_live',
1324 'tags': ['Flyingkitty', 'godzilla 2'],
1325 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1326 'like_count': int,
1327 'duration': 177,
1328 'playable_in_embed': True,
6c73052c 1329 'channel_follower_count': int
65c2fde2 1330 },
1331 },
1332 {
1333 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1334 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1335 'info_dict': {
1336 'id': 'Tq92D6wQ1mg',
1337 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1338 'ext': 'mp4',
17322130 1339 'upload_date': '20191228',
65c2fde2 1340 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1341 'uploader': 'Projekt Melody',
1342 'description': 'md5:17eccca93a786d51bc67646756894066',
1343 'age_limit': 18,
976ae3ea 1344 'like_count': int,
1345 'availability': 'needs_auth',
1346 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1347 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1348 'view_count': int,
1349 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1350 'channel': 'Projekt Melody',
1351 'live_status': 'not_live',
1352 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1353 'playable_in_embed': True,
1354 'categories': ['Entertainment'],
1355 'duration': 106,
1356 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1357 'comment_count': int,
6c73052c 1358 'channel_follower_count': int
65c2fde2 1359 },
1360 },
1361 {
1362 'note': 'Non-Agegated non-embeddable video',
1363 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1364 'info_dict': {
1365 'id': 'MeJVWBSsPAY',
1366 'ext': 'mp4',
1367 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1368 'uploader': 'Herr Lurik',
1369 'uploader_id': 'st3in234',
1370 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1371 'upload_date': '20130730',
976ae3ea 1372 'track': 'Such mich find mich',
1373 'age_limit': 0,
1374 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1375 'like_count': int,
1376 'playable_in_embed': False,
1377 'creator': 'OOMPH!',
1378 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1379 'view_count': int,
1380 'alt_title': 'Such mich find mich',
1381 'duration': 210,
1382 'channel': 'Herr Lurik',
1383 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1384 'categories': ['Music'],
1385 'availability': 'public',
1386 'uploader_url': 'http://www.youtube.com/user/st3in234',
1387 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1388 'live_status': 'not_live',
1389 'artist': 'OOMPH!',
6c73052c 1390 'channel_follower_count': int
65c2fde2 1391 },
1392 },
1393 {
1394 'note': 'Non-bypassable age-gated video',
1395 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1396 'only_matching': True,
1397 },
8bdd16b4 1398 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1399 # YouTube Red ad is not captured for creator
1400 {
1401 'url': '__2ABJjxzNo',
1402 'info_dict': {
1403 'id': '__2ABJjxzNo',
1404 'ext': 'mp4',
1405 'duration': 266,
1406 'upload_date': '20100430',
1407 'uploader_id': 'deadmau5',
1408 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1409 'creator': 'deadmau5',
1410 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1411 'uploader': 'deadmau5',
1412 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1413 'alt_title': 'Some Chords',
976ae3ea 1414 'availability': 'public',
1415 'tags': 'count:14',
1416 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1417 'view_count': int,
1418 'live_status': 'not_live',
1419 'channel': 'deadmau5',
1420 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1421 'like_count': int,
1422 'track': 'Some Chords',
1423 'artist': 'deadmau5',
1424 'playable_in_embed': True,
1425 'age_limit': 0,
1426 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1427 'categories': ['Music'],
1428 'album': 'Some Chords',
6c73052c 1429 'channel_follower_count': int
8bdd16b4 1430 },
1431 'expected_warnings': [
1432 'DASH manifest missing',
1433 ]
1434 },
067aa17e 1435 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1436 {
1437 'url': 'lqQg6PlCWgI',
1438 'info_dict': {
1439 'id': 'lqQg6PlCWgI',
1440 'ext': 'mp4',
556dbe7f 1441 'duration': 6085,
90227264 1442 'upload_date': '20150827',
cbe2bd91 1443 'uploader_id': 'olympic',
ec85ded8 1444 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1445 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1446 'uploader': 'Olympics',
cbe2bd91 1447 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1448 'like_count': int,
1449 'release_timestamp': 1343767800,
1450 'playable_in_embed': True,
1451 'categories': ['Sports'],
1452 'release_date': '20120731',
1453 'channel': 'Olympics',
1454 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1455 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1456 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1457 'age_limit': 0,
1458 'availability': 'public',
1459 'live_status': 'was_live',
1460 'view_count': int,
1461 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1462 'channel_follower_count': int
cbe2bd91
PH
1463 },
1464 'params': {
1465 'skip_download': 'requires avconv',
e52a40ab 1466 }
cbe2bd91 1467 },
6271f1ca
PH
1468 # Non-square pixels
1469 {
1470 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1471 'info_dict': {
1472 'id': '_b-2C3KPAM0',
1473 'ext': 'mp4',
1474 'stretched_ratio': 16 / 9.,
556dbe7f 1475 'duration': 85,
6271f1ca
PH
1476 'upload_date': '20110310',
1477 'uploader_id': 'AllenMeow',
ec85ded8 1478 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1479 '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 1480 'uploader': '孫ᄋᄅ',
6271f1ca 1481 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1482 'playable_in_embed': True,
1483 'channel': '孫ᄋᄅ',
1484 'age_limit': 0,
1485 'tags': 'count:11',
1486 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1487 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1488 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1489 'view_count': int,
1490 'categories': ['People & Blogs'],
1491 'like_count': int,
1492 'live_status': 'not_live',
1493 'availability': 'unlisted',
12a1b225 1494 'comment_count': int,
6c73052c 1495 'channel_follower_count': int
6271f1ca 1496 },
06b491eb
S
1497 },
1498 # url_encoded_fmt_stream_map is empty string
1499 {
1500 'url': 'qEJwOuvDf7I',
1501 'info_dict': {
1502 'id': 'qEJwOuvDf7I',
f57b7835 1503 'ext': 'webm',
06b491eb
S
1504 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1505 'description': '',
1506 'upload_date': '20150404',
1507 'uploader_id': 'spbelect',
1508 'uploader': 'Наблюдатели Петербурга',
1509 },
1510 'params': {
1511 'skip_download': 'requires avconv',
e323cf3f
S
1512 },
1513 'skip': 'This live event has ended.',
06b491eb 1514 },
067aa17e 1515 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1516 {
1517 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1518 'info_dict': {
1519 'id': 'FIl7x6_3R5Y',
eb6793ba 1520 'ext': 'webm',
da77d856
S
1521 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1522 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1523 'duration': 220,
da77d856
S
1524 'upload_date': '20150625',
1525 'uploader_id': 'dorappi2000',
ec85ded8 1526 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1527 'uploader': 'dorappi2000',
eb6793ba 1528 'formats': 'mincount:31',
da77d856 1529 },
eb6793ba 1530 'skip': 'not actual anymore',
2ee8f5d8 1531 },
8a1a26ce
YCH
1532 # DASH manifest with segment_list
1533 {
1534 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1535 'md5': '8ce563a1d667b599d21064e982ab9e31',
1536 'info_dict': {
1537 'id': 'CsmdDsKjzN8',
1538 'ext': 'mp4',
17ee98e1 1539 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1540 'uploader': 'Airtek',
1541 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1542 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1543 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1544 },
1545 'params': {
1546 'youtube_include_dash_manifest': True,
1547 'format': '135', # bestvideo
be49068d
S
1548 },
1549 'skip': 'This live event has ended.',
2ee8f5d8 1550 },
cf7e015f
S
1551 {
1552 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1553 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1554 'info_dict': {
545cc85d 1555 'id': 'jvGDaLqkpTg',
1556 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1557 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1558 },
1559 'playlist': [{
1560 'info_dict': {
545cc85d 1561 'id': 'jvGDaLqkpTg',
cf7e015f 1562 'ext': 'mp4',
545cc85d 1563 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1564 'description': 'md5:e03b909557865076822aa169218d6a5d',
1565 'duration': 10643,
1566 'upload_date': '20161111',
1567 'uploader': 'Team PGP',
1568 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1569 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1570 },
1571 }, {
1572 'info_dict': {
545cc85d 1573 'id': '3AKt1R1aDnw',
cf7e015f 1574 'ext': 'mp4',
545cc85d 1575 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1576 'description': 'md5:e03b909557865076822aa169218d6a5d',
1577 'duration': 10991,
1578 'upload_date': '20161111',
1579 'uploader': 'Team PGP',
1580 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1581 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1582 },
1583 }, {
1584 'info_dict': {
545cc85d 1585 'id': 'RtAMM00gpVc',
cf7e015f 1586 'ext': 'mp4',
545cc85d 1587 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1588 'description': 'md5:e03b909557865076822aa169218d6a5d',
1589 'duration': 10995,
1590 'upload_date': '20161111',
1591 'uploader': 'Team PGP',
1592 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1593 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1594 },
1595 }, {
1596 'info_dict': {
545cc85d 1597 'id': '6N2fdlP3C5U',
cf7e015f 1598 'ext': 'mp4',
545cc85d 1599 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1600 'description': 'md5:e03b909557865076822aa169218d6a5d',
1601 'duration': 10990,
1602 'upload_date': '20161111',
1603 'uploader': 'Team PGP',
1604 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1605 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1606 },
1607 }],
1608 'params': {
1609 'skip_download': True,
1610 },
65c2fde2 1611 'skip': 'Not multifeed anymore',
cbaed4bb 1612 },
f9f49d87 1613 {
067aa17e 1614 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1615 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1616 'info_dict': {
1617 'id': 'gVfLd0zydlo',
1618 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1619 },
1620 'playlist_count': 2,
be49068d 1621 'skip': 'Not multifeed anymore',
f9f49d87 1622 },
cbaed4bb 1623 {
2d3d2997 1624 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1625 'only_matching': True,
0e49d9a6 1626 },
6d4fc66b 1627 {
2d3d2997 1628 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1629 'only_matching': True,
1630 },
0e49d9a6 1631 {
067aa17e 1632 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1633 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1634 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1635 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1636 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1637 'info_dict': {
1638 'id': 'lsguqyKfVQg',
1639 'ext': 'mp4',
1640 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1641 'alt_title': 'Dark Walk',
0e49d9a6 1642 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1643 'duration': 133,
0e49d9a6
LL
1644 'upload_date': '20151119',
1645 'uploader_id': 'IronSoulElf',
ec85ded8 1646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1647 'uploader': 'IronSoulElf',
11f9be09 1648 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1649 'track': 'Dark Walk',
1650 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1651 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1652 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1653 'categories': ['Film & Animation'],
1654 'view_count': int,
1655 'live_status': 'not_live',
1656 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1657 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1658 'tags': 'count:13',
1659 'availability': 'public',
1660 'channel': 'IronSoulElf',
1661 'playable_in_embed': True,
1662 'like_count': int,
1663 'age_limit': 0,
6c73052c 1664 'channel_follower_count': int
0e49d9a6
LL
1665 },
1666 'params': {
1667 'skip_download': True,
1668 },
1669 },
61f92af1 1670 {
067aa17e 1671 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1672 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1673 'only_matching': True,
1674 },
313dfc45
LL
1675 {
1676 # Video with yt:stretch=17:0
1677 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1678 'info_dict': {
1679 'id': 'Q39EVAstoRM',
1680 'ext': 'mp4',
1681 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1682 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1683 'upload_date': '20151107',
1684 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1685 'uploader': 'CH GAMER DROID',
1686 },
1687 'params': {
1688 'skip_download': True,
1689 },
be49068d 1690 'skip': 'This video does not exist.',
313dfc45 1691 },
201c1459 1692 {
1693 # Video with incomplete 'yt:stretch=16:'
1694 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1695 'only_matching': True,
1696 },
7caf9830
S
1697 {
1698 # Video licensed under Creative Commons
1699 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1700 'info_dict': {
1701 'id': 'M4gD1WSo5mA',
1702 'ext': 'mp4',
1703 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1704 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1705 'duration': 721,
17322130 1706 'upload_date': '20150128',
7caf9830 1707 'uploader_id': 'BerkmanCenter',
ec85ded8 1708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1709 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1710 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1711 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1712 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1713 'like_count': int,
1714 'age_limit': 0,
1715 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1716 'channel': 'The Berkman Klein Center for Internet & Society',
1717 'availability': 'public',
1718 'view_count': int,
1719 'categories': ['Education'],
1720 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1721 'live_status': 'not_live',
1722 'playable_in_embed': True,
12a1b225 1723 'comment_count': int,
d5d1df8a 1724 'channel_follower_count': int,
1725 'chapters': list,
7caf9830
S
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 },
fd050249
S
1731 {
1732 # Channel-like uploader_url
1733 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1734 'info_dict': {
1735 'id': 'eQcmzGIKrzg',
1736 'ext': 'mp4',
1737 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1738 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1739 'duration': 4060,
17322130 1740 'upload_date': '20151120',
eb6793ba 1741 'uploader': 'Bernie Sanders',
fd050249 1742 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1743 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1744 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1745 'playable_in_embed': True,
1746 'tags': 'count:12',
1747 'like_count': int,
1748 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1749 'age_limit': 0,
1750 'availability': 'public',
1751 'categories': ['News & Politics'],
1752 'channel': 'Bernie Sanders',
1753 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1754 'view_count': int,
1755 'live_status': 'not_live',
1756 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1757 'comment_count': int,
d5d1df8a 1758 'channel_follower_count': int,
1759 'chapters': list,
fd050249
S
1760 },
1761 'params': {
1762 'skip_download': True,
1763 },
1764 },
040ac686
S
1765 {
1766 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1767 'only_matching': True,
7f29cf54
S
1768 },
1769 {
067aa17e 1770 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1771 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1772 'only_matching': True,
6496ccb4
S
1773 },
1774 {
1775 # Rental video preview
1776 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1777 'info_dict': {
1778 'id': 'uGpuVWrhIzE',
1779 'ext': 'mp4',
1780 'title': 'Piku - Trailer',
1781 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1782 'upload_date': '20150811',
1783 'uploader': 'FlixMatrix',
1784 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1785 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1786 'license': 'Standard YouTube License',
1787 },
1788 'params': {
1789 'skip_download': True,
1790 },
eb6793ba 1791 'skip': 'This video is not available.',
022a5d66 1792 },
12afdc2a
S
1793 {
1794 # YouTube Red video with episode data
1795 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1796 'info_dict': {
1797 'id': 'iqKdEhx-dD4',
1798 'ext': 'mp4',
1799 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1800 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1801 'duration': 2085,
12afdc2a
S
1802 'upload_date': '20170118',
1803 'uploader': 'Vsauce',
1804 'uploader_id': 'Vsauce',
1805 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1806 'series': 'Mind Field',
1807 'season_number': 1,
1808 'episode_number': 1,
976ae3ea 1809 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1810 'tags': 'count:12',
1811 'view_count': int,
1812 'availability': 'public',
1813 'age_limit': 0,
1814 'channel': 'Vsauce',
1815 'episode': 'Episode 1',
1816 'categories': ['Entertainment'],
1817 'season': 'Season 1',
1818 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1819 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1820 'like_count': int,
1821 'playable_in_embed': True,
1822 'live_status': 'not_live',
6c73052c 1823 'channel_follower_count': int
12afdc2a
S
1824 },
1825 'params': {
1826 'skip_download': True,
1827 },
1828 'expected_warnings': [
1829 'Skipping DASH manifest',
1830 ],
1831 },
c7121fa7
S
1832 {
1833 # The following content has been identified by the YouTube community
1834 # as inappropriate or offensive to some audiences.
1835 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1836 'info_dict': {
1837 'id': '6SJNVb0GnPI',
1838 'ext': 'mp4',
1839 'title': 'Race Differences in Intelligence',
1840 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1841 'duration': 965,
1842 'upload_date': '20140124',
1843 'uploader': 'New Century Foundation',
1844 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1845 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1846 },
1847 'params': {
1848 'skip_download': True,
1849 },
545cc85d 1850 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1851 },
022a5d66
S
1852 {
1853 # itag 212
1854 'url': '1t24XAntNCY',
1855 'only_matching': True,
fd5c4aab
S
1856 },
1857 {
1858 # geo restricted to JP
1859 'url': 'sJL6WA-aGkQ',
1860 'only_matching': True,
1861 },
cd5a74a2
S
1862 {
1863 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1864 'only_matching': True,
1865 },
bc2ca1bb 1866 {
1867 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1868 'only_matching': True,
1869 },
1870 {
1871 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1872 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1873 'only_matching': True,
1874 },
825cd268
RA
1875 {
1876 # DRM protected
1877 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1878 'only_matching': True,
4fe54c12
S
1879 },
1880 {
1881 # Video with unsupported adaptive stream type formats
1882 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1883 'info_dict': {
1884 'id': 'Z4Vy8R84T1U',
1885 'ext': 'mp4',
1886 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1887 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1888 'duration': 433,
1889 'upload_date': '20130923',
1890 'uploader': 'Amelia Putri Harwita',
1891 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1892 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1893 'formats': 'maxcount:10',
1894 },
1895 'params': {
1896 'skip_download': True,
1897 'youtube_include_dash_manifest': False,
1898 },
5429d6a9 1899 'skip': 'not actual anymore',
5caabd3c 1900 },
1901 {
822b9d9c 1902 # Youtube Music Auto-generated description
5caabd3c 1903 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1904 'info_dict': {
1905 'id': 'MgNrAu2pzNs',
1906 'ext': 'mp4',
1907 'title': 'Voyeur Girl',
1908 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1909 'upload_date': '20190312',
5429d6a9
S
1910 'uploader': 'Stephen - Topic',
1911 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1912 'artist': 'Stephen',
1913 'track': 'Voyeur Girl',
1914 'album': 'it\'s too much love to know my dear',
1915 'release_date': '20190313',
1916 'release_year': 2019,
976ae3ea 1917 'alt_title': 'Voyeur Girl',
1918 'view_count': int,
1919 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1920 'playable_in_embed': True,
1921 'like_count': int,
1922 'categories': ['Music'],
1923 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1924 'channel': 'Stephen',
1925 'availability': 'public',
1926 'creator': 'Stephen',
1927 'duration': 169,
1928 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1929 'age_limit': 0,
1930 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1931 'tags': 'count:11',
1932 'live_status': 'not_live',
6c73052c 1933 'channel_follower_count': int
5caabd3c 1934 },
1935 'params': {
1936 'skip_download': True,
1937 },
1938 },
66b48727
RA
1939 {
1940 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1941 'only_matching': True,
1942 },
011e75e6
S
1943 {
1944 # invalid -> valid video id redirection
1945 'url': 'DJztXj2GPfl',
1946 'info_dict': {
1947 'id': 'DJztXj2GPfk',
1948 'ext': 'mp4',
1949 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1950 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1951 'upload_date': '20090125',
1952 'uploader': 'Prochorowka',
1953 'uploader_id': 'Prochorowka',
1954 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1955 'artist': 'Panjabi MC',
1956 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1957 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1958 },
1959 'params': {
1960 'skip_download': True,
1961 },
545cc85d 1962 'skip': 'Video unavailable',
ea74e00b
DP
1963 },
1964 {
1965 # empty description results in an empty string
1966 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1967 'info_dict': {
1968 'id': 'x41yOUIvK2k',
1969 'ext': 'mp4',
1970 'title': 'IMG 3456',
1971 'description': '',
1972 'upload_date': '20170613',
1973 'uploader_id': 'ElevageOrVert',
1974 'uploader': 'ElevageOrVert',
976ae3ea 1975 'view_count': int,
1976 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1977 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1978 'like_count': int,
1979 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1980 'tags': [],
1981 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1982 'availability': 'public',
1983 'age_limit': 0,
1984 'categories': ['Pets & Animals'],
1985 'duration': 7,
1986 'playable_in_embed': True,
1987 'live_status': 'not_live',
1988 'channel': 'ElevageOrVert',
6c73052c 1989 'channel_follower_count': int
ea74e00b
DP
1990 },
1991 'params': {
1992 'skip_download': True,
1993 },
1994 },
a0566bbf 1995 {
29f7c58a 1996 # with '};' inside yt initial data (see [1])
1997 # see [2] for an example with '};' inside ytInitialPlayerResponse
1998 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1999 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2000 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2001 'info_dict': {
2002 'id': 'CHqg6qOn4no',
2003 'ext': 'mp4',
2004 'title': 'Part 77 Sort a list of simple types in c#',
2005 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2006 'upload_date': '20130831',
2007 'uploader_id': 'kudvenkat',
2008 'uploader': 'kudvenkat',
976ae3ea 2009 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2010 'like_count': int,
2011 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2012 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2013 'live_status': 'not_live',
2014 'categories': ['Education'],
2015 'availability': 'public',
2016 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2017 'tags': 'count:12',
2018 'playable_in_embed': True,
2019 'age_limit': 0,
2020 'view_count': int,
2021 'duration': 522,
2022 'channel': 'kudvenkat',
12a1b225 2023 'comment_count': int,
d5d1df8a 2024 'channel_follower_count': int,
2025 'chapters': list,
a0566bbf 2026 },
2027 'params': {
2028 'skip_download': True,
2029 },
2030 },
29f7c58a 2031 {
2032 # another example of '};' in ytInitialData
2033 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2034 'only_matching': True,
2035 },
2036 {
2037 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2038 'only_matching': True,
2039 },
545cc85d 2040 {
cc2db878 2041 # https://github.com/ytdl-org/youtube-dl/pull/28094
2042 'url': 'OtqTfy26tG0',
2043 'info_dict': {
2044 'id': 'OtqTfy26tG0',
2045 'ext': 'mp4',
2046 'title': 'Burn Out',
2047 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2048 'upload_date': '20141120',
2049 'uploader': 'The Cinematic Orchestra - Topic',
2050 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2051 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2052 'artist': 'The Cinematic Orchestra',
2053 'track': 'Burn Out',
2054 'album': 'Every Day',
976ae3ea 2055 'like_count': int,
2056 'live_status': 'not_live',
2057 'alt_title': 'Burn Out',
2058 'duration': 614,
2059 'age_limit': 0,
2060 'view_count': int,
2061 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2062 'creator': 'The Cinematic Orchestra',
2063 'channel': 'The Cinematic Orchestra',
2064 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2065 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2066 'availability': 'public',
2067 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2068 'categories': ['Music'],
2069 'playable_in_embed': True,
6c73052c 2070 'channel_follower_count': int
cc2db878 2071 },
2072 'params': {
2073 'skip_download': True,
2074 },
545cc85d 2075 },
bc2ca1bb 2076 {
2077 # controversial video, only works with bpctr when authenticated with cookies
2078 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2079 'only_matching': True,
2080 },
a1a7907b 2081 {
2082 # controversial video, requires bpctr/contentCheckOk
2083 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2084 'info_dict': {
2085 'id': 'SZJvDhaSDnc',
2086 'ext': 'mp4',
2087 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2088 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2089 'uploader': 'CBS Mornings',
11f9be09 2090 'uploader_id': 'CBSThisMorning',
a1a7907b 2091 'upload_date': '20140716',
976ae3ea 2092 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2093 'duration': 170,
2094 'categories': ['News & Politics'],
2095 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2096 'view_count': int,
2097 'channel': 'CBS Mornings',
2098 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2099 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2100 'age_limit': 18,
2101 'availability': 'needs_auth',
2102 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2103 'like_count': int,
2104 'live_status': 'not_live',
2105 'playable_in_embed': True,
6c73052c 2106 'channel_follower_count': int
a1a7907b 2107 }
2108 },
f7ad7160 2109 {
2110 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2111 'url': 'cBvYw8_A0vQ',
2112 'info_dict': {
2113 'id': 'cBvYw8_A0vQ',
2114 'ext': 'mp4',
2115 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2116 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2117 'upload_date': '20201120',
2118 'uploader': 'Walk around Japan',
2119 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2120 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2121 'duration': 1456,
2122 'categories': ['Travel & Events'],
2123 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2124 'view_count': int,
2125 'channel': 'Walk around Japan',
2126 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2127 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2128 'age_limit': 0,
2129 'availability': 'public',
2130 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2131 'live_status': 'not_live',
2132 'playable_in_embed': True,
6c73052c 2133 'channel_follower_count': int
f7ad7160 2134 },
2135 'params': {
2136 'skip_download': True,
2137 },
0fb983f6 2138 }, {
2139 # Has multiple audio streams
2140 'url': 'WaOKSUlf4TM',
2141 'only_matching': True
9297939e 2142 }, {
2143 # Requires Premium: has format 141 when requested using YTM url
2144 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2145 'only_matching': True
2146 }, {
120916da 2147 # multiple subtitles with same lang_code
2148 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2149 'only_matching': True,
109dd3b2 2150 }, {
2151 # Force use android client fallback
2152 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2153 'info_dict': {
2154 'id': 'YOelRv7fMxY',
11f9be09 2155 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2156 'ext': '3gp',
2157 'upload_date': '20210624',
2158 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2159 'uploader': 'colinfurze',
11f9be09 2160 'uploader_id': 'colinfurze',
109dd3b2 2161 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2162 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2163 'duration': 596,
2164 'categories': ['Entertainment'],
2165 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2166 'view_count': int,
2167 'channel': 'colinfurze',
2168 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2169 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2170 'age_limit': 0,
2171 'availability': 'public',
2172 'like_count': int,
2173 'live_status': 'not_live',
2174 'playable_in_embed': True,
d5d1df8a 2175 'channel_follower_count': int,
2176 'chapters': list,
109dd3b2 2177 },
2178 'params': {
2179 'format': '17', # 3gp format available on android
2180 'extractor_args': {'youtube': {'player_client': ['android']}},
2181 },
120916da 2182 },
109dd3b2 2183 {
2184 # Skip download of additional client configs (remix client config in this case)
2185 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2186 'only_matching': True,
2187 'params': {
2188 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2189 },
8fc54b12 2190 }, {
2191 # shorts
2192 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2193 'only_matching': True,
9222c381 2194 }, {
2195 'note': 'Storyboards',
2196 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2197 'info_dict': {
2198 'id': '5KLPxDtMqe8',
2199 'ext': 'mhtml',
2200 'format_id': 'sb0',
2201 'title': 'Your Brain is Plastic',
2202 'uploader_id': 'scishow',
2203 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2204 'upload_date': '20140324',
2205 'uploader': 'SciShow',
976ae3ea 2206 'like_count': int,
2207 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2208 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2209 'view_count': int,
2210 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2211 'playable_in_embed': True,
2212 'tags': 'count:12',
2213 'uploader_url': 'http://www.youtube.com/user/scishow',
2214 'availability': 'public',
2215 'channel': 'SciShow',
2216 'live_status': 'not_live',
2217 'duration': 248,
2218 'categories': ['Education'],
2219 'age_limit': 0,
d5d1df8a 2220 'channel_follower_count': int,
2221 'chapters': list,
9222c381 2222 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2223 }, {
2224 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2225 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2226 'info_dict': {
2227 'id': '2NUZ8W2llS4',
2228 'ext': 'mp4',
2229 'title': 'The NP that test your phone performance 🙂',
2230 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2231 'uploader': 'Leon Nguyen',
2232 'uploader_id': 'VNSXIII',
2233 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2234 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2235 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2236 'duration': 21,
2237 'view_count': int,
2238 'age_limit': 0,
2239 'categories': ['Gaming'],
2240 'tags': 'count:23',
2241 'playable_in_embed': True,
2242 'live_status': 'not_live',
2243 'upload_date': '20220103',
2244 'like_count': int,
2245 'availability': 'public',
2246 'channel': 'Leon Nguyen',
2247 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2248 'comment_count': int,
992f9a73 2249 'channel_follower_count': int
2250 }
1ff88b7a 2251 }, {
2252 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2253 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2254 'info_dict': {
2255 'id': '2NUZ8W2llS4',
2256 'ext': 'mp4',
2257 'title': 'The NP that test your phone performance 🙂',
2258 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2259 'uploader': 'Leon Nguyen',
2260 'uploader_id': 'VNSXIII',
2261 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2262 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2263 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2264 'duration': 21,
2265 'view_count': int,
2266 'age_limit': 0,
2267 'categories': ['Gaming'],
2268 'tags': 'count:23',
2269 'playable_in_embed': True,
2270 'live_status': 'not_live',
2271 'upload_date': '20220102',
2272 'like_count': int,
2273 'availability': 'public',
2274 'channel': 'Leon Nguyen',
2275 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2276 'comment_count': int,
2277 'channel_follower_count': int
2278 },
2279 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2280 }, {
2281 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2282 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2283 'info_dict': {
2284 'id': 'mzZzzBU6lrM',
2285 'ext': 'mp4',
2286 'title': 'I Met GeorgeNotFound In Real Life...',
2287 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2288 'uploader': 'Quackity',
2289 'uploader_id': 'QuackityHQ',
2290 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2291 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2292 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2293 'duration': 955,
2294 'view_count': int,
2295 'age_limit': 0,
2296 'categories': ['Entertainment'],
2297 'tags': 'count:26',
2298 'playable_in_embed': True,
2299 'live_status': 'not_live',
2300 'release_timestamp': 1641172509,
2301 'release_date': '20220103',
2302 'upload_date': '20220103',
2303 'like_count': int,
2304 'availability': 'public',
2305 'channel': 'Quackity',
2306 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2307 'channel_follower_count': int
2308 }
2309 },
2310 { # continuous livestream. Microformat upload date should be preferred.
2311 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2312 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2313 'info_dict': {
2314 'id': 'kgx4WGK0oNU',
2315 '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}',
2316 'ext': 'mp4',
2317 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2318 'availability': 'public',
2319 'age_limit': 0,
2320 'release_timestamp': 1637975704,
2321 'upload_date': '20210619',
2322 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2323 'live_status': 'is_live',
2324 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2325 'uploader': '阿鲍Abao',
2326 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2327 'channel': 'Abao in Tokyo',
2328 'channel_follower_count': int,
2329 'release_date': '20211127',
2330 'tags': 'count:39',
2331 'categories': ['People & Blogs'],
2332 'like_count': int,
2333 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2334 'view_count': int,
2335 'playable_in_embed': True,
2336 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2337 'concurrent_view_count': int,
992f9a73 2338 },
2339 'params': {'skip_download': True}
6e634cbe 2340 }, {
2341 # Story. Requires specific player params to work.
ee27297f 2342 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2343 'info_dict': {
ee27297f 2344 'id': 'vv8qTUWmulI',
6e634cbe 2345 'ext': 'mp4',
ee27297f 2346 'availability': 'unlisted',
2347 'view_count': int,
2348 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2349 'upload_date': '20220526',
2350 'categories': ['Education'],
2351 'title': 'Story',
2352 'channel': 'IT\'S HISTORY',
2353 'description': '',
2354 'uploader_id': 'BlastfromthePast',
2355 'duration': 12,
2356 'uploader': 'IT\'S HISTORY',
6e634cbe 2357 'playable_in_embed': True,
6e634cbe 2358 'age_limit': 0,
6e634cbe 2359 'live_status': 'not_live',
ee27297f 2360 'tags': [],
2361 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2362 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2363 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2364 },
2365 'skip': 'stories get removed after some period of time',
ee27297f 2366 }, {
2367 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2368 'info_dict': {
2369 'id': 'tjjjtzRLHvA',
2370 'ext': 'mp4',
2371 'title': 'ハッシュタグ無し };if window.ytcsi',
2372 'upload_date': '20220323',
2373 'like_count': int,
2374 'availability': 'unlisted',
2375 'channel': 'nao20010128nao',
2376 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2377 'age_limit': 0,
2378 'uploader': 'nao20010128nao',
2379 'uploader_id': 'nao20010128nao',
2380 'categories': ['Music'],
6e634cbe 2381 'view_count': int,
2382 'description': '',
ee27297f 2383 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2384 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2385 'live_status': 'not_live',
2386 'playable_in_embed': True,
2387 'channel_follower_count': int,
2388 'duration': 6,
2389 'tags': [],
2390 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2391 }
c26f9b99 2392 }, {
2393 # Prefer primary title+description language metadata by default
2394 # Do not prefer translated description if primary is empty
2395 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2396 'info_dict': {
2397 'id': 'el3E4MbxRqQ',
2398 'ext': 'mp4',
2399 'title': 'dlp test video 2 - primary sv no desc',
2400 'description': '',
2401 'channel': 'cole-dlp-test-acc',
2402 'tags': [],
2403 'view_count': int,
2404 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2405 'like_count': int,
2406 'playable_in_embed': True,
2407 'availability': 'unlisted',
2408 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2409 'age_limit': 0,
2410 'duration': 5,
2411 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2412 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2413 'live_status': 'not_live',
2414 'upload_date': '20220908',
2415 'categories': ['People & Blogs'],
2416 'uploader': 'cole-dlp-test-acc',
2417 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2418 },
2419 'params': {'skip_download': True}
2420 }, {
2421 # Extractor argument: prefer translated title+description
2422 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2423 'info_dict': {
2424 'id': 'gHKT4uU8Zng',
2425 'ext': 'mp4',
2426 'channel': 'cole-dlp-test-acc',
2427 'tags': [],
2428 'duration': 5,
2429 'live_status': 'not_live',
2430 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2431 'upload_date': '20220728',
2432 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2433 'view_count': int,
2434 'categories': ['People & Blogs'],
2435 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2436 'title': 'dlp test video title translated (fr)',
2437 'availability': 'public',
2438 'uploader': 'cole-dlp-test-acc',
2439 'age_limit': 0,
2440 'description': 'dlp test video description translated (fr)',
2441 'playable_in_embed': True,
2442 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2443 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2444 },
2445 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2446 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2447 }, {
2448 'note': '6 channel audio',
2449 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2450 'only_matching': True,
6e634cbe 2451 }
2eb88d95
PH
2452 ]
2453
f2e8dbcc 2454 _WEBPAGE_TESTS = [
2455 # YouTube <object> embed
2456 {
2457 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2458 'md5': '873c81d308b979f0e23ee7e620b312a3',
2459 'info_dict': {
2460 'id': 'msN87y-iEx0',
2461 'ext': 'mp4',
2462 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2463 'upload_date': '20080526',
2464 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2465 'uploader': 'Christopher Sykes',
2466 'uploader_id': 'ChristopherJSykes',
2467 'age_limit': 0,
2468 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2469 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2470 'playable_in_embed': True,
2471 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2472 'like_count': int,
2473 'comment_count': int,
2474 'channel': 'Christopher Sykes',
2475 'live_status': 'not_live',
2476 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2477 'availability': 'public',
2478 'duration': 195,
2479 'view_count': int,
2480 'categories': ['Science & Technology'],
2481 'channel_follower_count': int,
2482 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2483 },
2484 'params': {
2485 'skip_download': True,
2486 }
2487 },
2488 ]
2489
201c1459 2490 @classmethod
2491 def suitable(cls, url):
4dfbf869 2492 from ..utils import parse_qs
2493
201c1459 2494 qs = parse_qs(url)
2495 if qs.get('list', [None])[0]:
2496 return False
86e5f3ed 2497 return super().suitable(url)
201c1459 2498
e0df6211 2499 def __init__(self, *args, **kwargs):
86e5f3ed 2500 super().__init__(*args, **kwargs)
545cc85d 2501 self._code_cache = {}
83799698 2502 self._player_cache = {}
e0df6211 2503
4d37720a 2504 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2505 lock = threading.Lock()
185bf310 2506 start_time = time.time()
adbc4ec4
THD
2507 formats = [f for f in formats if f.get('is_from_start')]
2508
185bf310 2509 def refetch_manifest(format_id, delay):
2510 nonlocal formats, start_time, is_live
2511 if time.time() <= start_time + delay:
adbc4ec4
THD
2512 return
2513
2514 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2515 video_details = traverse_obj(
2516 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2517 microformats = traverse_obj(
2518 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2519 expected_type=dict, default=[])
4d37720a
L
2520 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2521 is_live = live_status == 'is_live'
185bf310 2522 start_time = time.time()
adbc4ec4 2523
185bf310 2524 def mpd_feed(format_id, delay):
adbc4ec4
THD
2525 """
2526 @returns (manifest_url, manifest_stream_number, is_live) or None
2527 """
2528 with lock:
185bf310 2529 refetch_manifest(format_id, delay)
adbc4ec4
THD
2530
2531 f = next((f for f in formats if f['format_id'] == format_id), None)
2532 if not f:
185bf310 2533 if not is_live:
2534 self.to_screen(f'{video_id}: Video is no longer live')
2535 else:
2536 self.report_warning(
2537 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2538 return None
2539 return f['manifest_url'], f['manifest_stream_number'], is_live
2540
2541 for f in formats:
4d37720a
L
2542 f['is_live'] = is_live
2543 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2544 live_start_time, mpd_feed, not is_live and f.copy())
2545 if is_live:
2546 f['fragments'] = gen
2547 f['protocol'] = 'http_dash_segments_generator'
2548 else:
2549 f['fragments'] = LazyList(gen({}))
2550 del f['is_from_start']
adbc4ec4 2551
4d37720a 2552 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2553 FETCH_SPAN, MAX_DURATION = 5, 432000
2554
2555 mpd_url, stream_number, is_live = None, None, True
2556
2557 begin_index = 0
2558 download_start_time = ctx.get('start') or time.time()
2559
2560 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2561 if lack_early_segments:
2562 self.report_warning(bug_reports_message(
2563 'Starting download from the last 120 hours of the live stream since '
2564 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2565 lack_early_segments = True
2566
2567 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2568 fragments, fragment_base_url = None, None
2569
a539f065 2570 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2571 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2572 # Obtain from MPD's maximum seq value
2573 old_mpd_url = mpd_url
185bf310 2574 last_error = ctx.pop('last_error', None)
14f25df2 2575 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2576 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2577 or (mpd_url, stream_number, False))
2578 if not refresh_sequence:
2579 if expire_fast and not is_live:
2580 return False, last_seq
2581 elif old_mpd_url == mpd_url:
2582 return True, last_seq
4d37720a
L
2583 if manifestless_orig_fmt:
2584 fmt_info = manifestless_orig_fmt
2585 else:
2586 try:
2587 fmts, _ = self._extract_mpd_formats_and_subtitles(
2588 mpd_url, None, note=False, errnote=False, fatal=False)
2589 except ExtractorError:
2590 fmts = None
2591 if not fmts:
2592 no_fragment_score += 2
2593 return False, last_seq
2594 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2595 fragments = fmt_info['fragments']
2596 fragment_base_url = fmt_info['fragment_base_url']
2597 assert fragment_base_url
2598
2599 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2600 return True, _last_seq
2601
4d37720a 2602 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2603 while is_live:
2604 fetch_time = time.time()
2605 if no_fragment_score > 30:
2606 return
2607 if last_segment_url:
2608 # Obtain from "X-Head-Seqnum" header value from each segment
2609 try:
2610 urlh = self._request_webpage(
2611 last_segment_url, None, note=False, errnote=False, fatal=False)
2612 except ExtractorError:
2613 urlh = None
2614 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2615 if last_seq is None:
a539f065 2616 no_fragment_score += 2
adbc4ec4
THD
2617 last_segment_url = None
2618 continue
2619 else:
a539f065
LNO
2620 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2621 no_fragment_score += 2
185bf310 2622 if not should_continue:
adbc4ec4
THD
2623 continue
2624
2625 if known_idx > last_seq:
2626 last_segment_url = None
2627 continue
2628
2629 last_seq += 1
2630
2631 if begin_index < 0 and known_idx < 0:
2632 # skip from the start when it's negative value
2633 known_idx = last_seq + begin_index
2634 if lack_early_segments:
2635 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2636 try:
2637 for idx in range(known_idx, last_seq):
2638 # do not update sequence here or you'll get skipped some part of it
a539f065 2639 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2640 if not should_continue:
adbc4ec4
THD
2641 known_idx = idx - 1
2642 raise ExtractorError('breaking out of outer loop')
2643 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2644 yield {
2645 'url': last_segment_url,
36195c44 2646 'fragment_count': last_seq,
adbc4ec4
THD
2647 }
2648 if known_idx == last_seq:
2649 no_fragment_score += 5
2650 else:
2651 no_fragment_score = 0
2652 known_idx = last_seq
2653 except ExtractorError:
2654 continue
2655
4d37720a
L
2656 if manifestless_orig_fmt:
2657 # Stop at the first iteration if running for post-live manifestless;
2658 # fragment count no longer increase since it starts
2659 break
2660
adbc4ec4
THD
2661 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2662
b6de707d 2663 def _extract_player_url(self, *ytcfgs, webpage=None):
2664 player_url = traverse_obj(
2665 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2666 get_all=False, expected_type=str)
11f9be09 2667 if not player_url:
b6de707d 2668 return
60f393e4 2669 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2670
b6de707d 2671 def _download_player_url(self, video_id, fatal=False):
2672 res = self._download_webpage(
2673 'https://www.youtube.com/iframe_api',
2674 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2675 if res:
2676 player_version = self._search_regex(
2677 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2678 if player_version:
2679 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2680
60064c53
PH
2681 def _signature_cache_id(self, example_sig):
2682 """ Return a string representation of a signature """
14f25df2 2683 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2684
e40c758c
S
2685 @classmethod
2686 def _extract_player_info(cls, player_url):
2687 for player_re in cls._PLAYER_INFO_RE:
2688 id_m = re.search(player_re, player_url)
2689 if id_m:
2690 break
2691 else:
c081b35c 2692 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2693 return id_m.group('id')
e40c758c 2694
404f611f 2695 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2696 player_id = self._extract_player_info(player_url)
2697 if player_id not in self._code_cache:
1276a43a 2698 code = self._download_webpage(
109dd3b2 2699 player_url, video_id, fatal=fatal,
2700 note='Downloading player ' + player_id,
2701 errnote='Download of %s failed' % player_url)
1276a43a 2702 if code:
2703 self._code_cache[player_id] = code
404f611f 2704 return self._code_cache.get(player_id)
109dd3b2 2705
e40c758c 2706 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2707 player_id = self._extract_player_info(player_url)
e0df6211 2708
c4417ddb 2709 # Read from filesystem cache
86e5f3ed 2710 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2711 assert os.path.basename(func_id) == func_id
a0e07d31 2712
ae61d108 2713 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2714 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2715
580ce007 2716 if not cache_spec:
2717 code = self._load_player(video_id, player_url)
404f611f 2718 if code:
109dd3b2 2719 res = self._parse_sig_js(code)
ac668111 2720 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2721 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2722 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2723
2724 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2725
60064c53 2726 def _print_sig_code(self, func, example_sig):
404f611f 2727 if not self.get_param('youtube_print_sig_code'):
2728 return
2729
edf3e38e
PH
2730 def gen_sig_code(idxs):
2731 def _genslice(start, end, step):
78caa52a 2732 starts = '' if start == 0 else str(start)
8bcc8756 2733 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2734 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2735 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2736
2737 step = None
7af808a5
PH
2738 # Quelch pyflakes warnings - start will be set when step is set
2739 start = '(Never used)'
edf3e38e
PH
2740 for i, prev in zip(idxs[1:], idxs[:-1]):
2741 if step is not None:
2742 if i - prev == step:
2743 continue
2744 yield _genslice(start, prev, step)
2745 step = None
2746 continue
2747 if i - prev in [-1, 1]:
2748 step = i - prev
2749 start = prev
2750 continue
2751 else:
78caa52a 2752 yield 's[%d]' % prev
edf3e38e 2753 if step is None:
78caa52a 2754 yield 's[%d]' % i
edf3e38e
PH
2755 else:
2756 yield _genslice(start, i, step)
2757
ac668111 2758 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2759 cache_res = func(test_string)
edf3e38e 2760 cache_spec = [ord(c) for c in cache_res]
78caa52a 2761 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2762 signature_id_tuple = '(%s)' % (
14f25df2 2763 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2764 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2765 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2766 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2767
e0df6211
PH
2768 def _parse_sig_js(self, jscode):
2769 funcname = self._search_regex(
abefc03f
S
2770 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2771 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
2772 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2773 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2774 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}\(a,\d+\)',
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\(\s*""\s*\)',
31ce6e99 2776 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2777 # Obsolete patterns
2778 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2779 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2780 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2781 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2782 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2783 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2784 r'\bc\s*&&\s*[a-zA-Z0-9]+\.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$]+)\('),
3c90cc8b 2786 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2787
2788 jsi = JSInterpreter(jscode)
2789 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2790 return lambda s: initial_function([s])
2791
580ce007 2792 def _cached(self, func, *cache_id):
2793 def inner(*args, **kwargs):
2794 if cache_id not in self._player_cache:
2795 try:
2796 self._player_cache[cache_id] = func(*args, **kwargs)
2797 except ExtractorError as e:
2798 self._player_cache[cache_id] = e
2799 except Exception as e:
2800 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2801
2802 ret = self._player_cache[cache_id]
2803 if isinstance(ret, Exception):
2804 raise ret
2805 return ret
2806 return inner
2807
545cc85d 2808 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2809 """Turn the encrypted s field into a working signature"""
580ce007 2810 extract_sig = self._cached(
2811 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2812 func = extract_sig(video_id, player_url, s)
2813 self._print_sig_code(func, s)
2814 return func(s)
404f611f 2815
2816 def _decrypt_nsig(self, s, video_id, player_url):
2817 """Turn the encrypted n field into a working signature"""
2818 if player_url is None:
2819 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2820 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2821
b505e851 2822 try:
2823 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2824 except ExtractorError as e:
2825 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 2826 if self.get_param('youtube_print_sig_code'):
2827 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2828
25836db6 2829 try:
2830 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2831 ret = extract_nsig(jsi, func_code)(s)
2832 except JSInterpreter.Exception as e:
2833 try:
992dc6b4 2834 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2835 except ExtractorError:
2836 raise e
2837 self.report_warning(
2838 f'Native nsig extraction failed: Trying with PhantomJS\n'
2839 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 2840 self.write_debug(e, only_once=True)
25836db6 2841
2842 args, func_body = func_code
2843 ret = jsi.execute(
2844 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2845 video_id=video_id, note='Executing signature code').strip()
580ce007 2846
2847 self.write_debug(f'Decrypted nsig {s} => {ret}')
2848 return ret
2849
90a1df30 2850 def _extract_n_function_name(self, jscode):
2851 funcname, idx = self._search_regex(
2852 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2853 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2854 if not idx:
2855 return funcname
2856
2857 return json.loads(js_to_json(self._search_regex(
2858 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2859 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2860
580ce007 2861 def _extract_n_function_code(self, video_id, player_url):
404f611f 2862 player_id = self._extract_player_info(player_url)
05deb747 2863 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 2864 jscode = func_code or self._load_player(video_id, player_url)
2865 jsi = JSInterpreter(jscode)
404f611f 2866
2867 if func_code:
580ce007 2868 return jsi, player_id, func_code
404f611f 2869
b505e851 2870 func_name = self._extract_n_function_name(jscode)
2871
2872 # For redundancy
2873 func_code = self._search_regex(
2874 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
2875 # NB: The end of the regex is intentionally kept strict
2876 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
2877 jscode, 'nsig function', group=('var', 'code'), default=None)
2878 if func_code:
2879 func_code = ([func_code[0]], func_code[1])
2880 else:
2881 self.write_debug('Extracting nsig function with jsinterp')
2882 func_code = jsi.extract_function_code(func_name)
2883
580ce007 2884 self.cache.store('youtube-nsig', player_id, func_code)
2885 return jsi, player_id, func_code
2886
2887 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 2888 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2889
580ce007 2890 def extract_nsig(s):
25836db6 2891 try:
2892 ret = func([s])
2893 except JSInterpreter.Exception:
2894 raise
2895 except Exception as e:
2896 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2897
f6ca640b 2898 if ret.startswith('enhanced_except_'):
25836db6 2899 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 2900 return ret
580ce007 2901
2902 return extract_nsig
e0df6211 2903
109dd3b2 2904 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2905 """
2906 Extract signatureTimestamp (sts)
2907 Required to tell API what sig/player version is in use.
2908 """
2909 sts = None
2910 if isinstance(ytcfg, dict):
2911 sts = int_or_none(ytcfg.get('STS'))
2912
2913 if not sts:
2914 # Attempt to extract from player
2915 if player_url is None:
2916 error_msg = 'Cannot extract signature timestamp without player_url.'
2917 if fatal:
2918 raise ExtractorError(error_msg)
2919 self.report_warning(error_msg)
2920 return
404f611f 2921 code = self._load_player(video_id, player_url, fatal=fatal)
2922 if code:
109dd3b2 2923 sts = int_or_none(self._search_regex(
2924 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2925 'JS player signature timestamp', group='sts', fatal=fatal))
2926 return sts
2927
11f9be09 2928 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2929 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2930 label = 'fully ' if is_full else ''
2931 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2932 expected_type=url_or_none)
2933 if not url:
2934 self.report_warning(f'Unable to mark {label}watched')
2935 return
14f25df2 2936 parsed_url = urllib.parse.urlparse(url)
2937 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2938
2939 # cpn generation algorithm is reverse engineered from base.js.
2940 # In fact it works even with dummy cpn.
2941 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2942 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2943
2944 # # more consistent results setting it to right before the end
2945 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2946
2947 qs.update({
2948 'ver': ['2'],
2949 'cpn': [cpn],
2950 'cmt': video_length,
2951 'el': 'detailpage', # otherwise defaults to "shorts"
2952 })
2953
2954 if is_full:
2955 # these seem to mark watchtime "history" in the real world
2956 # they're required, so send in a single value
2957 qs.update({
2958 'st': video_length,
2959 'et': video_length,
2960 })
2961
14f25df2 2962 url = urllib.parse.urlunparse(
2963 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2964
2965 self._download_webpage(
2966 url, video_id, f'Marking {label}watched',
2967 'Unable to mark watched', fatal=False)
d77ab8e2 2968
bfd973ec 2969 @classmethod
2970 def _extract_from_webpage(cls, url, webpage):
2971 # Invidious Instances
2972 # https://github.com/yt-dlp/yt-dlp/issues/195
2973 # https://github.com/iv-org/invidious/pull/1730
2974 mobj = re.search(
2975 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2976 webpage)
2977 if mobj:
2978 yield cls.url_result(mobj.group('url'), cls)
2979 raise cls.StopExtraction()
2980
2981 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2982
2983 # lazyYT YouTube embed
bfd973ec 2984 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2985 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2986
2987 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2988 for m in re.findall(r'''(?x)<div[^>]+
2989 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2990 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2991 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2992
97665381
PH
2993 @classmethod
2994 def extract_id(cls, url):
ae61d108 2995 video_id = cls.get_temp_id(url)
2996 if not video_id:
2997 raise ExtractorError(f'Invalid URL: {url}')
2998 return video_id
c5e8d7af 2999
7c365c21 3000 def _extract_chapters_from_json(self, data, duration):
3001 chapter_list = traverse_obj(
3002 data, (
3003 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3004 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3005 ), expected_type=list)
3006
3007 return self._extract_chapters(
3008 chapter_list,
3009 chapter_time=lambda chapter: float_or_none(
3010 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3011 chapter_title=lambda chapter: traverse_obj(
3012 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3013 duration=duration)
3014
3015 def _extract_chapters_from_engagement_panel(self, data, duration):
3016 content_list = traverse_obj(
8bdd16b4 3017 data,
7c365c21 3018 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 3019 expected_type=list, default=[])
052e1350 3020 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3021 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3022
1890fc63 3023 return next(filter(None, (
3024 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3025 chapter_time, chapter_title, duration)
3026 for contents in content_list)), [])
7c365c21 3027
1890fc63 3028 def _extract_chapters_from_description(self, description, duration):
3029 return self._extract_chapters(
3030 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
3031 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
3032 duration=duration, strict=False)
84213ea8 3033
1890fc63 3034 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3035 if not duration:
3036 return
3037 chapter_list = [{
3038 'start_time': chapter_time(chapter),
3039 'title': chapter_title(chapter),
3040 } for chapter in chapter_list or []]
3041 if not strict:
3042 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3043
a3976e07 3044 chapters = [{'start_time': 0}]
1890fc63 3045 for idx, chapter in enumerate(chapter_list):
a3976e07 3046 if chapter['start_time'] is None:
1890fc63 3047 self.report_warning(f'Incomplete chapter {idx}')
3048 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3049 chapters.append(chapter)
709ee214 3050 elif chapter not in chapters:
3051 self.report_warning(
3052 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3053 return chapters[1:]
84213ea8 3054
a1c5d2ca
M
3055 def _extract_comment(self, comment_renderer, parent=None):
3056 comment_id = comment_renderer.get('commentId')
3057 if not comment_id:
3058 return
fe93e2c4 3059
052e1350 3060 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3061
c26f9b99 3062 # Timestamp is an estimate calculated from the current time and time_text
3063 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3064 timestamp = self._parse_time_text(time_text)
3065
052e1350 3066 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3067 author_id = try_get(comment_renderer,
14f25df2 3068 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3069
49bd8c66 3070 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3071 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3072 author_thumbnail = try_get(comment_renderer,
14f25df2 3073 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3074
3075 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3076 is_favorited = 'creatorHeart' in (try_get(
3077 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3078 return {
3079 'id': comment_id,
3080 'text': text,
d92f5d5a 3081 'timestamp': timestamp,
a1c5d2ca
M
3082 'time_text': time_text,
3083 'like_count': votes,
97524332 3084 'is_favorited': is_favorited,
a1c5d2ca
M
3085 'author': author,
3086 'author_id': author_id,
3087 'author_thumbnail': author_thumbnail,
3088 'author_is_uploader': author_is_uploader,
3089 'parent': parent or 'root'
3090 }
3091
46383212 3092 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3093
3094 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3095
3096 def extract_header(contents):
2d6659b9 3097 _continuation = None
3098 for content in contents:
46383212 3099 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3100 expected_comment_count = self._get_count(
3101 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3102
2d6659b9 3103 if expected_comment_count:
46383212 3104 tracker['est_total'] = expected_comment_count
3105 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3106 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3107
3108 sort_menu_item = try_get(
3109 comments_header_renderer,
3110 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3111 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3112
3113 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3114 if not _continuation:
3115 continue
3116
46383212 3117 sort_text = str_or_none(sort_menu_item.get('title'))
3118 if not sort_text:
2d6659b9 3119 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3120 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3121 break
a2160aa4 3122 return _continuation
a1c5d2ca 3123
2d6659b9 3124 def extract_thread(contents):
a1c5d2ca 3125 if not parent:
46383212 3126 tracker['current_page_thread'] = 0
a1c5d2ca 3127 for content in contents:
46383212 3128 if not parent and tracker['total_parent_comments'] >= max_parents:
3129 yield
a1c5d2ca 3130 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3131 comment_renderer = get_first(
3132 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3133 expected_type=dict, default={})
a1c5d2ca 3134
a1c5d2ca
M
3135 comment = self._extract_comment(comment_renderer, parent)
3136 if not comment:
3137 continue
46383212 3138
3139 tracker['running_total'] += 1
3140 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3141 yield comment
46383212 3142
a1c5d2ca
M
3143 # Attempt to get the replies
3144 comment_replies_renderer = try_get(
3145 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3146
3147 if comment_replies_renderer:
46383212 3148 tracker['current_page_thread'] += 1
a1c5d2ca 3149 comment_entries_iter = self._comment_entries(
99e9e001 3150 comment_replies_renderer, ytcfg, video_id,
46383212 3151 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3152 yield from itertools.islice(comment_entries_iter, min(
3153 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3154
46383212 3155 # Keeps track of counts across recursive calls
3156 if not tracker:
3157 tracker = dict(
3158 running_total=0,
3159 est_total=0,
3160 current_page_thread=0,
3161 total_parent_comments=0,
3162 total_reply_comments=0)
3163
3164 # TODO: Deprecated
2d6659b9 3165 # YouTube comments have a max depth of 2
46383212 3166 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3167 if max_depth:
da4db748 3168 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3169 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3170 if max_depth == 1 and parent:
3171 return
a1c5d2ca 3172
46383212 3173 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3174 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3175
46383212 3176 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3177
46383212 3178 response = None
6e634cbe 3179 is_forced_continuation = False
2d6659b9 3180 is_first_continuation = parent is None
6e634cbe 3181 if is_first_continuation and not continuation:
3182 # Sometimes you can get comments by generating the continuation yourself,
3183 # even if YouTube initially reports them being disabled - e.g. stories comments.
3184 # Note: if the comment section is actually disabled, YouTube may return a response with
3185 # required check_get_keys missing. So we will disable that check initially in this case.
3186 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3187 is_forced_continuation = True
a1c5d2ca
M
3188
3189 for page_num in itertools.count(0):
3190 if not continuation:
3191 break
46383212 3192 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3193 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3194 if page_num == 0:
3195 if is_first_continuation:
3196 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3197 else:
2d6659b9 3198 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3199 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3200 else:
3201 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3202 ' ' if parent else '', ' replies' if parent else '',
3203 page_num, comment_prog_str)
3204
3205 response = self._extract_response(
fe93e2c4 3206 item_id=None, query=continuation,
2d6659b9 3207 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 3208 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3209 is_forced_continuation = False
46383212 3210 continuation_contents = traverse_obj(
3211 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3212
2d6659b9 3213 continuation = None
46383212 3214 for continuation_section in continuation_contents:
3215 continuation_items = traverse_obj(
3216 continuation_section,
3217 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3218 get_all=False, expected_type=list) or []
3219 if is_first_continuation:
3220 continuation = extract_header(continuation_items)
3221 is_first_continuation = False
2d6659b9 3222 if continuation:
a1c5d2ca 3223 break
46383212 3224 continue
a1c5d2ca 3225
46383212 3226 for entry in extract_thread(continuation_items):
3227 if not entry:
3228 return
3229 yield entry
3230 continuation = self._extract_continuation({'contents': continuation_items})
3231 if continuation:
2d6659b9 3232 break
a1c5d2ca 3233
6e634cbe 3234 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3235 if message and not parent and tracker['running_total'] == 0:
3236 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3237
3238 @staticmethod
3239 def _generate_comment_continuation(video_id):
3240 """
3241 Generates initial comment section continuation token from given video id
3242 """
3243 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3244 return base64.b64encode(token.encode()).decode()
3245
a2160aa4 3246 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3247 """Entry for comment extraction"""
2d6659b9 3248 def _real_comment_extract(contents):
aae16f6e 3249 renderer = next((
3250 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3251 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3252 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3253
a2160aa4 3254 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3255 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3256
109dd3b2 3257 @staticmethod
99e9e001 3258 def _get_checkok_params():
3259 return {'contentCheckOk': True, 'racyCheckOk': True}
3260
3261 @classmethod
3262 def _generate_player_context(cls, sts=None):
109dd3b2 3263 context = {
3264 'html5Preference': 'HTML5_PREF_WANTS',
3265 }
3266 if sts is not None:
3267 context['signatureTimestamp'] = sts
3268 return {
3269 'playbackContext': {
3270 'contentPlaybackContext': context
a1a7907b 3271 },
99e9e001 3272 **cls._get_checkok_params()
109dd3b2 3273 }
3274
e7e94f2a
D
3275 @staticmethod
3276 def _is_agegated(player_response):
3277 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3278 return True
e7e94f2a
D
3279
3280 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3281 AGE_GATE_REASONS = (
3282 'confirm your age', 'age-restricted', 'inappropriate', # reason
3283 'age_verification_required', 'age_check_required', # status
3284 )
3285 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3286
3287 @staticmethod
3288 def _is_unplayable(player_response):
3289 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3290
50ac0e54 3291 _STORY_PLAYER_PARAMS = '8AEB'
3292
3293 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3294
11f9be09 3295 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3296 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3297 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3298 headers = self.generate_api_headers(
99e9e001 3299 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3300
6e634cbe 3301 yt_query = {
3302 'videoId': video_id,
6e634cbe 3303 }
50ac0e54 3304 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3305 yt_query['params'] = self._STORY_PLAYER_PARAMS
3306
11f9be09 3307 yt_query.update(self._generate_player_context(sts))
3308 return self._extract_response(
3309 item_id=video_id, ep='player', query=yt_query,
379e44ed 3310 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3311 default_client=client,
11f9be09 3312 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3313 ) or None
3314
11f9be09 3315 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3316 requested_clients = []
d0d012d4 3317 default = ['android', 'web']
000c15a4 3318 allowed_clients = sorted(
86e5f3ed 3319 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3320 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3321 for client in self._configuration_arg('player_client'):
3322 if client in allowed_clients:
3323 requested_clients.append(client)
d0d012d4 3324 elif client == 'default':
3325 requested_clients.extend(default)
b4c055ba 3326 elif client == 'all':
3327 requested_clients.extend(allowed_clients)
3328 else:
3329 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3330 if not requested_clients:
d0d012d4 3331 requested_clients = default
cf7e015f 3332
11f9be09 3333 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3334 requested_clients.extend(
e7e94f2a 3335 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3336
11f9be09 3337 return orderedSet(requested_clients)
cf7e015f 3338
50ac0e54 3339 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3340 initial_pr = None
3341 if webpage:
b7c47b74 3342 initial_pr = self._search_json(
3343 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3344
ae729626 3345 all_clients = set(clients)
c0bc527b 3346 clients = clients[::-1]
b6de707d 3347 prs = []
e7e94f2a 3348
ae729626 3349 def append_client(*client_names):
e7870111 3350 """ Append the first client name that exists but not already used """
ae729626 3351 for client_name in client_names:
e7870111
D
3352 actual_client = _split_innertube_client(client_name)[0]
3353 if actual_client in INNERTUBE_CLIENTS:
3354 if actual_client not in all_clients:
ae729626 3355 clients.append(client_name)
e7870111
D
3356 all_clients.add(actual_client)
3357 return
e7e94f2a 3358
379e44ed 3359 # Android player_response does not have microFormats which are needed for
3360 # extraction of some data. So we return the initial_pr with formats
3361 # stripped out even if not requested by the user
3362 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3363 if initial_pr:
3364 pr = dict(initial_pr)
3365 pr['streamingData'] = None
b6de707d 3366 prs.append(pr)
379e44ed 3367
3368 last_error = None
b6de707d 3369 tried_iframe_fallback = False
3370 player_url = None
c0bc527b 3371 while clients:
e7870111 3372 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3373 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3374 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3375 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3376
b6de707d 3377 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3378 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3379 if 'js' in self._configuration_arg('player_skip'):
3380 require_js_player = False
3381 player_url = None
3382
3383 if not player_url and not tried_iframe_fallback and require_js_player:
3384 player_url = self._download_player_url(video_id)
3385 tried_iframe_fallback = True
3386
379e44ed 3387 try:
3388 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3389 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3390 except ExtractorError as e:
3391 if last_error:
3392 self.report_warning(last_error)
3393 last_error = e
3394 continue
3395
11f9be09 3396 if pr:
a3e96421 3397 # YouTube may return a different video player response than expected.
3398 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3399 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3400 if pr_video_id and pr_video_id != video_id:
3401 self.report_warning(
c7dcf0b3 3402 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3403 else:
3404 prs.append(pr)
c0bc527b 3405
e7e94f2a 3406 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3407 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3408 append_client(f'{base_client}_creator')
e7e94f2a 3409 elif self._is_agegated(pr):
e7870111
D
3410 if variant == 'tv_embedded':
3411 append_client(f'{base_client}_embedded')
3412 elif not variant:
3413 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3414
379e44ed 3415 if last_error:
b6de707d 3416 if not len(prs):
379e44ed 3417 raise last_error
3418 self.report_warning(last_error)
b6de707d 3419 return prs, player_url
11f9be09 3420
4d37720a
L
3421 def _needs_live_processing(self, live_status, duration):
3422 if (live_status == 'is_live' and self.get_param('live_from_start')
3423 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3424 return live_status
3425
3426 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a0bb6ce5 3427 itags, stream_ids = {}, []
b25cac65 3428 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3429 q = qualities([
2a9c6dcd 3430 # Normally tiny is the smallest video-only formats. But
3431 # audio-only formats with unknown quality may get tagged as tiny
3432 'tiny',
3433 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3434 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3435 ])
11f9be09 3436 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3437
545cc85d 3438 for fmt in streaming_formats:
727029c5 3439 if fmt.get('targetDurationSec'):
545cc85d 3440 continue
321bf820 3441
cc2db878 3442 itag = str_or_none(fmt.get('itag'))
9297939e 3443 audio_track = fmt.get('audioTrack') or {}
3444 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3445 if stream_id in stream_ids:
3446 continue
3447
cc2db878 3448 quality = fmt.get('quality')
2a9c6dcd 3449 height = int_or_none(fmt.get('height'))
d3fc8074 3450 if quality == 'tiny' or not quality:
3451 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3452 # The 3gp format (17) in android client has a quality of "small",
3453 # but is actually worse than other formats
3454 if itag == '17':
3455 quality = 'tiny'
3456 if quality:
3457 if itag:
3458 itag_qualities[itag] = quality
3459 if height:
3460 res_qualities[height] = quality
cc2db878 3461 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3462 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3463 # number of fragment that would subsequently requested with (`&sq=N`)
3464 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3465 continue
3466
545cc85d 3467 fmt_url = fmt.get('url')
3468 if not fmt_url:
14f25df2 3469 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3470 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3471 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3472 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3473 continue
52023f12 3474 try:
3475 fmt_url += '&%s=%s' % (
3476 traverse_obj(sc, ('sp', -1)) or 'signature',
3477 self._decrypt_signature(encrypted_sig, video_id, player_url)
3478 )
3479 except ExtractorError as e:
580ce007 3480 self.report_warning('Signature extraction failed: Some formats may be missing',
3481 video_id=video_id, only_once=True)
52023f12 3482 self.write_debug(e, only_once=True)
201e9eaa 3483 continue
545cc85d 3484
404f611f 3485 query = parse_qs(fmt_url)
3486 throttled = False
b2916526 3487 if query.get('n'):
404f611f 3488 try:
580ce007 3489 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3490 fmt_url = update_url_query(fmt_url, {
580ce007 3491 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3492 })
404f611f 3493 except ExtractorError as e:
25836db6 3494 phantomjs_hint = ''
3495 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3496 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3497 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3498 if player_url:
3499 self.report_warning(
3500 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3501 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3502 self.write_debug(e, only_once=True)
3503 else:
3504 self.report_warning(
3505 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3506 video_id=video_id, only_once=True)
404f611f 3507 throttled = True
3508
545cc85d 3509 if itag:
a0bb6ce5 3510 itags[itag] = 'https'
9297939e 3511 stream_ids.append(stream_id)
3512
0ad92dfb 3513 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3514 language_preference = (
3515 10 if audio_track.get('audioIsDefault') and 10
3516 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3517 else -1)
0ad92dfb 3518 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3519 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3520 # Make sure to avoid false positives with small duration differences.
62b58c09 3521 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3522 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3523 if is_damaged:
0f06bcd7 3524 self.report_warning(
3525 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3526 dct = {
3527 'asr': int_or_none(fmt.get('audioSampleRate')),
3528 'filesize': int_or_none(fmt.get('contentLength')),
3529 'format_id': itag,
34921b43 3530 'format_note': join_nonempty(
26e8e044 3531 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3532 ' (default)' if language_preference > 0 else ''),
404f611f 3533 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3534 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3535 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3536 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3537 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3538 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3539 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3540 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3541 'height': height,
dca3ff4a 3542 'quality': q(quality),
727029c5 3543 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3544 'tbr': tbr,
545cc85d 3545 'url': fmt_url,
2a9c6dcd 3546 'width': int_or_none(fmt.get('width')),
ab6df717 3547 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3548 'desc' if language_preference < -1 else ''),
3549 'language_preference': language_preference,
a405b38f 3550 # Strictly de-prioritize damaged and 3gp formats
3551 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3552 }
60bdb7bd 3553 mime_mobj = re.match(
3554 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3555 if mime_mobj:
3556 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3557 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3558 no_audio = dct.get('acodec') == 'none'
3559 no_video = dct.get('vcodec') == 'none'
3560 if no_audio:
3561 dct['vbr'] = tbr
3562 if no_video:
3563 dct['abr'] = tbr
3564 if no_audio or no_video:
545cc85d 3565 dct['downloader_options'] = {
3566 # Youtube throttles chunks >~10M
3567 'http_chunk_size': 10485760,
bf1317d2 3568 }
7c60c33e 3569 if dct.get('ext'):
3570 dct['container'] = dct['ext'] + '_dash'
11f9be09 3571 yield dct
545cc85d 3572
4d37720a
L
3573 needs_live_processing = self._needs_live_processing(live_status, duration)
3574 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3575
3576 skip_manifests = set(self._configuration_arg('skip'))
3577 if (not self.get_param('youtube_include_hls_manifest', True)
3578 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3579 or needs_live_processing and skip_bad_formats):
3580 skip_manifests.add('hls')
3581
0f06bcd7 3582 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3583 skip_manifests.add('dash')
3584 if self._configuration_arg('include_live_dash'):
3585 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3586 'Use include_incomplete_formats extractor argument instead')
3587 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3588 skip_manifests.add('dash')
5d3a0e79 3589
a0bb6ce5 3590 def process_manifest_format(f, proto, itag):
3591 if itag in itags:
3592 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3593 return False
3594 itag = f'{itag}-{proto}'
3595 if itag:
3596 f['format_id'] = itag
3597 itags[itag] = proto
3598
b25cac65 3599 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3600 if f['quality'] == -1 and f.get('height'):
3601 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3602 return True
2a9c6dcd 3603
c646d76f 3604 subtitles = {}
11f9be09 3605 for sd in streaming_data:
4d37720a 3606 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3607 if hls_manifest_url:
4d37720a
L
3608 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3609 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3610 subtitles = self._merge_subtitles(subs, subtitles)
3611 for f in fmts:
a0bb6ce5 3612 if process_manifest_format(f, 'hls', self._search_regex(
3613 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3614 yield f
545cc85d 3615
4d37720a 3616 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3617 if dash_manifest_url:
c646d76f 3618 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3619 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3620 for f in formats:
a0bb6ce5 3621 if process_manifest_format(f, 'dash', f['format_id']):
3622 f['filesize'] = int_or_none(self._search_regex(
3623 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3624 if needs_live_processing:
adbc4ec4
THD
3625 f['is_from_start'] = True
3626
a0bb6ce5 3627 yield f
c646d76f 3628 yield subtitles
11f9be09 3629
720c3099 3630 def _extract_storyboard(self, player_responses, duration):
3631 spec = get_first(
3632 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3633 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3634 if not base_url:
720c3099 3635 return
720c3099 3636 L = len(spec) - 1
3637 for i, args in enumerate(spec):
3638 args = args.split('#')
3639 counts = list(map(int_or_none, args[:5]))
3640 if len(args) != 8 or not all(counts):
3641 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3642 continue
3643 width, height, frame_count, cols, rows = counts
3644 N, sigh = args[6:]
3645
3646 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3647 fragment_count = frame_count / (cols * rows)
3648 fragment_duration = duration / fragment_count
3649 yield {
3650 'format_id': f'sb{i}',
3651 'format_note': 'storyboard',
3652 'ext': 'mhtml',
3653 'protocol': 'mhtml',
3654 'acodec': 'none',
3655 'vcodec': 'none',
3656 'url': url,
3657 'width': width,
3658 'height': height,
45e8a04e 3659 'fps': frame_count / duration,
3660 'rows': rows,
3661 'columns': cols,
720c3099 3662 'fragments': [{
b3edc806 3663 'url': url.replace('$M', str(j)),
720c3099 3664 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3665 } for j in range(math.ceil(fragment_count))],
3666 }
3667
adbc4ec4 3668 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3669 webpage = None
3670 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3671 query = {'bpctr': '9999999999', 'has_verified': '1'}
3672 if smuggled_data.get('is_story'):
3673 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3674 webpage = self._download_webpage(
50ac0e54 3675 webpage_url, video_id, fatal=False, query=query)
11f9be09 3676
3677 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3678
b6de707d 3679 player_responses, player_url = self._extract_player_responses(
11f9be09 3680 self._get_requested_clients(url, smuggled_data),
50ac0e54 3681 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3682
adbc4ec4
THD
3683 return webpage, master_ytcfg, player_responses, player_url
3684
a1b2d843 3685 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3686 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3687 is_live = get_first(video_details, 'isLive')
3688 if is_live is None:
3689 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3690 live_content = get_first(video_details, 'isLiveContent')
3691 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3692 post_live = get_first(video_details, 'isPostLiveDvr')
3693 live_status = ('post_live' if post_live
3694 else 'is_live' if is_live
3695 else 'is_upcoming' if is_upcoming
6678a4f0 3696 else 'was_live' if live_content
3697 else 'not_live' if False in (is_live, live_content)
3698 else None)
adbc4ec4 3699 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3700 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3701
4d37720a 3702 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3703
3704 def _real_extract(self, url):
3705 url, smuggled_data = unsmuggle_url(url, {})
3706 video_id = self._match_id(url)
3707
3708 base_url = self.http_scheme() + '//www.youtube.com/'
3709 webpage_url = base_url + 'watch?v=' + video_id
3710
3711 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3712
11f9be09 3713 playability_statuses = traverse_obj(
3714 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3715
3716 trailer_video_id = get_first(
3717 playability_statuses,
3718 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3719 expected_type=str)
3720 if trailer_video_id:
3721 return self.url_result(
3722 trailer_video_id, self.ie_key(), trailer_video_id)
3723
3724 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3725 if webpage else (lambda x: None))
3726
3727 video_details = traverse_obj(
3728 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3729 microformats = traverse_obj(
3730 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3731 expected_type=dict, default=[])
c26f9b99 3732
3733 translated_title = self._get_text(microformats, (..., 'title'))
3734 video_title = (self._preferred_lang and translated_title
3735 or get_first(video_details, 'title') # primary
3736 or translated_title
3737 or search_meta(['og:title', 'twitter:title', 'title']))
3738 translated_description = self._get_text(microformats, (..., 'description'))
3739 original_description = get_first(video_details, 'shortDescription')
3740 video_description = (
3741 self._preferred_lang and translated_description
3742 # If original description is blank, it will be an empty string.
3743 # Do not prefer translated description in this case.
3744 or original_description if original_description is not None else translated_description)
11f9be09 3745
d89257f3 3746 multifeed_metadata_list = get_first(
3747 player_responses,
3748 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3749 expected_type=str)
3750 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3751 if self.get_param('noplaylist'):
11f9be09 3752 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3753 else:
3754 entries = []
3755 feed_ids = []
3756 for feed in multifeed_metadata_list.split(','):
3757 # Unquote should take place before split on comma (,) since textual
3758 # fields may contain comma as well (see
3759 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3760 feed_data = urllib.parse.parse_qs(
ac668111 3761 urllib.parse.unquote_plus(feed))
d89257f3 3762
3763 def feed_entry(name):
3764 return try_get(
14f25df2 3765 feed_data, lambda x: x[name][0], str)
d89257f3 3766
3767 feed_id = feed_entry('id')
3768 if not feed_id:
3769 continue
3770 feed_title = feed_entry('title')
3771 title = video_title
3772 if feed_title:
3773 title += ' (%s)' % feed_title
3774 entries.append({
3775 '_type': 'url_transparent',
3776 'ie_key': 'Youtube',
3777 'url': smuggle_url(
3778 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3779 {'force_singlefeed': True}),
3780 'title': title,
3781 })
3782 feed_ids.append(feed_id)
3783 self.to_screen(
3784 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3785 % (', '.join(feed_ids), video_id))
3786 return self.playlist_result(
3787 entries, video_id, video_title, video_description)
11f9be09 3788
a1b2d843 3789 duration = int_or_none(
3790 get_first(video_details, 'lengthSeconds')
3791 or get_first(microformats, 'lengthSeconds')
3792 or parse_duration(search_meta('duration'))) or None
3793
4d37720a
L
3794 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3795 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3796 if live_status == 'post_live':
3797 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3798
545cc85d 3799 if not formats:
11f9be09 3800 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3801 self.report_drm(video_id)
11f9be09 3802 pemr = get_first(
3803 playability_statuses,
3804 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3805 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3806 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3807 if subreason:
545cc85d 3808 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3809 countries = get_first(microformats, 'availableCountries')
545cc85d 3810 if not countries:
3811 regions_allowed = search_meta('regionsAllowed')
3812 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3813 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3814 reason += f'. {subreason}'
545cc85d 3815 if reason:
b7da73eb 3816 self.raise_no_formats(reason, expected=True)
bf1317d2 3817
11f9be09 3818 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3819 if not keywords and webpage:
3820 keywords = [
3821 unescapeHTML(m.group('content'))
3822 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3823 for keyword in keywords:
3824 if keyword.startswith('yt:stretch='):
201c1459 3825 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3826 if mobj:
3827 # NB: float is intentional for forcing float division
3828 w, h = (float(v) for v in mobj.groups())
3829 if w > 0 and h > 0:
3830 ratio = w / h
3831 for f in formats:
3832 if f.get('vcodec') != 'none':
3833 f['stretched_ratio'] = ratio
3834 break
a709d873 3835 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3836 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3837 if thumbnail_url:
3838 thumbnails.append({
3839 'url': thumbnail_url,
ff2751ac 3840 })
fccf5021 3841 original_thumbnails = thumbnails.copy()
3842
0ba692ac 3843 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3844 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3845 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3846 thumbnail_names = [
962ffcf8 3847 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3848 # in resolution, these are not the custom thumbnail. So de-prioritize them
3849 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3850 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3851 ]
cca80fe6 3852 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3853 thumbnails.extend({
3854 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3855 video_id=video_id, name=name, ext=ext,
4d37720a 3856 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 3857 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3858 for thumb in thumbnails:
cca80fe6 3859 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3860 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3861 self._remove_duplicate_formats(thumbnails)
fccf5021 3862 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3863
7ea65411 3864 category = get_first(microformats, 'category') or search_meta('genre')
3865 channel_id = str_or_none(
3866 get_first(video_details, 'channelId')
3867 or get_first(microformats, 'externalChannelId')
3868 or search_meta('channelId'))
7ea65411 3869 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3870
adbc4ec4
THD
3871 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3872 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3873 if not duration and live_end_time and live_start_time:
3874 duration = live_end_time - live_start_time
3875
4d37720a
L
3876 needs_live_processing = self._needs_live_processing(live_status, duration)
3877
3878 def is_bad_format(fmt):
3879 if needs_live_processing and not fmt.get('is_from_start'):
3880 return True
3881 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
3882 and fmt.get('protocol') == 'http_dash_segments'):
3883 return True
3884
3885 for fmt in filter(is_bad_format, formats):
3886 fmt['preference'] = (fmt.get('preference') or -1) - 10
3887 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
3888
3889 if needs_live_processing:
3890 self._prepare_live_from_start_formats(
3891 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 3892
720c3099 3893 formats.extend(self._extract_storyboard(player_responses, duration))
3894
31b532a1 3895 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3896 self._sort_formats(formats, (
3897 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3898
545cc85d 3899 info = {
3900 'id': video_id,
39ca3b5c 3901 'title': video_title,
545cc85d 3902 'formats': formats,
3903 'thumbnails': thumbnails,
fccf5021 3904 # The best thumbnail that we are sure exists. Prevents unnecessary
3905 # URL checking if user don't care about getting the best possible thumbnail
3906 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3907 'description': video_description,
11f9be09 3908 'uploader': get_first(video_details, 'author'),
545cc85d 3909 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3910 'uploader_url': owner_profile_url,
3911 'channel_id': channel_id,
a70635b8 3912 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3913 'duration': duration,
3914 'view_count': int_or_none(
11f9be09 3915 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3916 or search_meta('interactionCount')),
11f9be09 3917 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3918 'age_limit': 18 if (
11f9be09 3919 get_first(microformats, 'isFamilySafe') is False
545cc85d 3920 or search_meta('isFamilyFriendly') == 'false'
3921 or search_meta('og:restrictions:age') == '18+') else 0,
3922 'webpage_url': webpage_url,
3923 'categories': [category] if category else None,
3924 'tags': keywords,
11f9be09 3925 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 3926 'live_status': live_status,
adbc4ec4 3927 'release_timestamp': live_start_time,
545cc85d 3928 }
b477fc13 3929
c646d76f 3930 subtitles = {}
3944e7af 3931 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3932 if pctr:
ecdc9049 3933 def get_lang_code(track):
3934 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3935 or track.get('languageCode'))
3936
3937 # Converted into dicts to remove duplicates
3938 captions = {
3939 get_lang_code(sub): sub
3940 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3941 translation_languages = {
3942 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3943 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3944
774d79cc 3945 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3946 lang_subs = container.setdefault(lang_code, [])
545cc85d 3947 for fmt in self._SUBTITLE_FORMATS:
3948 query.update({
3949 'fmt': fmt,
3950 })
3951 lang_subs.append({
3952 'ext': fmt,
60f393e4 3953 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3954 'name': sub_name,
545cc85d 3955 })
7e72694b 3956
07b47084 3957 # NB: Constructing the full subtitle dictionary is slow
3958 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3959 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3960 for lang_code, caption_track in captions.items():
3961 base_url = caption_track.get('baseUrl')
1235d333 3962 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3963 if not base_url:
3964 continue
ecdc9049 3965 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3966 if caption_track.get('kind') != 'asr':
545cc85d 3967 if not lang_code:
3968 continue
3969 process_language(
ecdc9049 3970 subtitles, base_url, lang_code, lang_name, {})
3971 if not caption_track.get('isTranslatable'):
3972 continue
3944e7af 3973 for trans_code, trans_name in translation_languages.items():
3974 if not trans_code:
545cc85d 3975 continue
1235d333 3976 orig_trans_code = trans_code
ecdc9049 3977 if caption_track.get('kind') != 'asr':
07b47084 3978 if not get_translated_subs:
18e49408 3979 continue
ecdc9049 3980 trans_code += f'-{lang_code}'
a70635b8 3981 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3982 # Add an "-orig" label to the original language so that it can be distinguished.
3983 # The subs are returned without "-orig" as well for compatibility
1235d333 3984 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3985 process_language(
d49669ac 3986 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3987 # Setting tlang=lang returns damaged subtitles.
d49669ac 3988 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3989 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3990
3991 info['automatic_captions'] = automatic_captions
3992 info['subtitles'] = subtitles
7e72694b 3993
14f25df2 3994 parsed_url = urllib.parse.urlparse(url)
545cc85d 3995 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3996 query = urllib.parse.parse_qs(component)
545cc85d 3997 for k, v in query.items():
3998 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3999 d_k += '_time'
4000 if d_k not in info and k in s_ks:
4001 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4002
4003 # Youtube Music Auto-generated description
822b9d9c 4004 if video_description:
1890fc63 4005 mobj = re.search(
4006 r'''(?xs)
4007 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4008 (?P<album>[^\n]+)
4009 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4010 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4011 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4012 .+\nAuto-generated\ by\ YouTube\.\s*$
4013 ''', video_description)
822b9d9c 4014 if mobj:
822b9d9c
RA
4015 release_year = mobj.group('release_year')
4016 release_date = mobj.group('release_date')
4017 if release_date:
4018 release_date = release_date.replace('-', '')
4019 if not release_year:
545cc85d 4020 release_year = release_date[:4]
4021 info.update({
4022 'album': mobj.group('album'.strip()),
4023 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4024 'track': mobj.group('track').strip(),
4025 'release_date': release_date,
cc2db878 4026 'release_year': int_or_none(release_year),
545cc85d 4027 })
7e72694b 4028
545cc85d 4029 initial_data = None
4030 if webpage:
56ba69e4 4031 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4032 if not initial_data:
99e9e001 4033 query = {'videoId': video_id}
4034 query.update(self._get_checkok_params())
109dd3b2 4035 initial_data = self._extract_response(
4036 item_id=video_id, ep='next', fatal=False,
99e9e001 4037 ytcfg=master_ytcfg, query=query,
4038 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4039 note='Downloading initial data API JSON')
545cc85d 4040
0df111a3 4041 info['comment_count'] = traverse_obj(initial_data, (
4042 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4043 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4044 ), (
4045 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4046 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4047 ), expected_type=int_or_none, get_all=False)
4048
19a03940 4049 try: # This will error if there is no livechat
c60ee3a2 4050 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4051 except (KeyError, IndexError, TypeError):
4052 pass
4053 else:
ecdc9049 4054 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4055 # url is needed to set cookies
4056 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4057 'video_id': video_id,
4058 'ext': 'json',
4d37720a
L
4059 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4060 else 'youtube_live_chat_replay'),
c60ee3a2 4061 }]
545cc85d 4062
4063 if initial_data:
7c365c21 4064 info['chapters'] = (
4065 self._extract_chapters_from_json(initial_data, duration)
4066 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4067 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4068 or None)
545cc85d 4069
17322130 4070 contents = traverse_obj(
4071 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4072 expected_type=list, default=[])
4073
4074 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4075 if vpir:
4076 stl = vpir.get('superTitleLink')
4077 if stl:
4078 stl = self._get_text(stl)
4079 if try_get(
4080 vpir,
4081 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4082 info['location'] = stl
4083 else:
affc4fef 4084 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4085 if mobj:
545cc85d 4086 info.update({
17322130 4087 'series': mobj.group(1),
4088 'season_number': int(mobj.group(2)),
4089 'episode_number': int(mobj.group(3)),
545cc85d 4090 })
17322130 4091 for tlb in (try_get(
4092 vpir,
4093 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4094 list) or []):
3ffb2f5b 4095 tbrs = variadic(
4096 traverse_obj(
4097 tlb, 'toggleButtonRenderer',
4098 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4099 default=[]))
4100 for tbr in tbrs:
4101 for getter, regex in [(
4102 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4103 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4104 lambda x: x['accessibility'],
4105 lambda x: x['accessibilityData']['accessibilityData'],
4106 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4107 label = (try_get(tbr, getter, dict) or {}).get('label')
4108 if label:
4109 mobj = re.match(regex, label)
4110 if mobj:
4111 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4112 break
17322130 4113 sbr_tooltip = try_get(
4114 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4115 if sbr_tooltip:
4116 like_count, dislike_count = sbr_tooltip.split(' / ')
4117 info.update({
4118 'like_count': str_to_int(like_count),
4119 'dislike_count': str_to_int(dislike_count),
4120 })
867c66ff
M
4121 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4122 if vcr:
4123 vc = self._get_count(vcr, 'viewCount')
4124 # Upcoming premieres with waiting count are treated as live here
4125 if vcr.get('isLive'):
4126 info['concurrent_view_count'] = vc
4127 elif info.get('view_count') is None:
4128 info['view_count'] = vc
4129
17322130 4130 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4131 if vsir:
4132 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4133 info.update({
4134 'channel': self._get_text(vor, 'title'),
4135 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4136
4137 rows = try_get(
4138 vsir,
4139 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4140 list) or []
4141 multiple_songs = False
4142 for row in rows:
4143 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4144 multiple_songs = True
4145 break
4146 for row in rows:
4147 mrr = row.get('metadataRowRenderer') or {}
4148 mrr_title = mrr.get('title')
4149 if not mrr_title:
4150 continue
4151 mrr_title = self._get_text(mrr, 'title')
4152 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4153 if mrr_title == 'License':
4154 info['license'] = mrr_contents_text
4155 elif not multiple_songs:
4156 if mrr_title == 'Album':
4157 info['album'] = mrr_contents_text
4158 elif mrr_title == 'Artist':
4159 info['artist'] = mrr_contents_text
4160 elif mrr_title == 'Song':
4161 info['track'] = mrr_contents_text
545cc85d 4162
4163 fallbacks = {
4164 'channel': 'uploader',
4165 'channel_id': 'uploader_id',
4166 'channel_url': 'uploader_url',
4167 }
992f9a73 4168
17322130 4169 # The upload date for scheduled, live and past live streams / premieres in microformats
4170 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4171 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4172 upload_date = (
4173 unified_strdate(get_first(microformats, 'uploadDate'))
4174 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4175 if not upload_date or (
4d37720a 4176 live_status in ('not_live', None)
1ff88b7a 4177 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4178 ):
c26f9b99 4179 upload_date = strftime_or_none(
4180 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4181 info['upload_date'] = upload_date
992f9a73 4182
545cc85d 4183 for to, frm in fallbacks.items():
4184 if not info.get(to):
4185 info[to] = info.get(frm)
4186
4187 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4188 v = info.get(s_k)
4189 if v:
4190 info[d_k] = v
b84071c0 4191
c26f9b99 4192 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4193
4194 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4195 or get_first(video_details, 'isPrivate', expected_type=bool))
4196
4197 info['availability'] = (
4198 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4199 else self._availability(
4200 is_private=is_private,
4201 needs_premium=(
4202 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4203 or False if initial_data and is_private is not None else None),
4204 needs_subscription=(
4205 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4206 or False if initial_data and is_private is not None else None),
4207 needs_auth=info['age_limit'] >= 18,
4208 is_unlisted=None if is_private is None else (
4209 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4210 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4211
a2160aa4 4212 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4213
11f9be09 4214 self.mark_watched(video_id, player_responses)
d77ab8e2 4215
545cc85d 4216 return info
c5e8d7af 4217
a61fd4cf 4218
a6213a49 4219class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 4220
182bda88 4221 @staticmethod
4222 def passthrough_smuggled_data(func):
4223 def _smuggle(entries, smuggled_data):
4224 for entry in entries:
4225 # TODO: Convert URL to music.youtube instead.
4226 # Do we need to passthrough any other smuggled_data?
4227 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4228 yield entry
4229
4230 @functools.wraps(func)
4231 def wrapper(self, url):
4232 url, smuggled_data = unsmuggle_url(url, {})
4233 if self.is_music_url(url):
4234 smuggled_data['is_music_url'] = True
4235 info_dict = func(self, url, smuggled_data)
4236 if smuggled_data and info_dict.get('entries'):
4237 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4238 return info_dict
4239 return wrapper
4240
a6213a49 4241 def _extract_channel_id(self, webpage):
4242 channel_id = self._html_search_meta(
4243 'channelId', webpage, 'channel id', default=None)
4244 if channel_id:
4245 return channel_id
4246 channel_url = self._html_search_meta(
4247 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4248 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4249 'twitter:app:url:googleplay'), webpage, 'channel url')
4250 return self._search_regex(
4251 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4252 channel_url, 'channel id')
15f6397c 4253
8bdd16b4 4254 @staticmethod
cd7c66cf 4255 def _extract_basic_item_renderer(item):
4256 # Modified from _extract_grid_item_renderer
201c1459 4257 known_basic_renderers = (
a17526e4 4258 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4259 )
4260 for key, renderer in item.items():
201c1459 4261 if not isinstance(renderer, dict):
cd7c66cf 4262 continue
201c1459 4263 elif key in known_basic_renderers:
4264 return renderer
4265 elif key.startswith('grid') and key.endswith('Renderer'):
4266 return renderer
8bdd16b4 4267
8bdd16b4 4268 def _grid_entries(self, grid_renderer):
4269 for item in grid_renderer['items']:
4270 if not isinstance(item, dict):
39b62db1 4271 continue
cd7c66cf 4272 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4273 if not isinstance(renderer, dict):
4274 continue
052e1350 4275 title = self._get_text(renderer, 'title')
fe93e2c4 4276
8bdd16b4 4277 # playlist
4278 playlist_id = renderer.get('playlistId')
4279 if playlist_id:
4280 yield self.url_result(
4281 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4282 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4283 video_title=title)
201c1459 4284 continue
8bdd16b4 4285 # video
4286 video_id = renderer.get('videoId')
4287 if video_id:
4288 yield self._extract_video(renderer)
201c1459 4289 continue
8bdd16b4 4290 # channel
4291 channel_id = renderer.get('channelId')
4292 if channel_id:
8bdd16b4 4293 yield self.url_result(
4294 'https://www.youtube.com/channel/%s' % channel_id,
4295 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4296 continue
4297 # generic endpoint URL support
4298 ep_url = urljoin('https://www.youtube.com/', try_get(
4299 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4300 str))
201c1459 4301 if ep_url:
4302 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4303 if ie.suitable(ep_url):
4304 yield self.url_result(
4305 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4306 break
8bdd16b4 4307
16aa9ea4 4308 def _music_reponsive_list_entry(self, renderer):
4309 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4310 if video_id:
4311 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4312 ie=YoutubeIE.ie_key(), video_id=video_id)
4313 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4314 if playlist_id:
4315 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4316 if video_id:
4317 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4318 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4319 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4320 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4321 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4322 if browse_id:
4323 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4324 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4325
3d3dddc9 4326 def _shelf_entries_from_content(self, shelf_renderer):
4327 content = shelf_renderer.get('content')
4328 if not isinstance(content, dict):
8bdd16b4 4329 return
cd7c66cf 4330 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4331 if renderer:
4332 # TODO: add support for nested playlists so each shelf is processed
4333 # as separate playlist
4334 # TODO: this includes only first N items
86e5f3ed 4335 yield from self._grid_entries(renderer)
3d3dddc9 4336 renderer = content.get('horizontalListRenderer')
4337 if renderer:
4338 # TODO
4339 pass
8bdd16b4 4340
29f7c58a 4341 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4342 ep = try_get(
4343 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4344 str)
8bdd16b4 4345 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4346 if shelf_url:
29f7c58a 4347 # Skipping links to another channels, note that checking for
4348 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4349 # will not work
4350 if skip_channels and '/channels?' in shelf_url:
4351 return
052e1350 4352 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4353 yield self.url_result(shelf_url, video_title=title)
4354 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4355 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4356
8bdd16b4 4357 def _playlist_entries(self, video_list_renderer):
4358 for content in video_list_renderer['contents']:
4359 if not isinstance(content, dict):
4360 continue
4361 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4362 if not isinstance(renderer, dict):
4363 continue
4364 video_id = renderer.get('videoId')
4365 if not video_id:
4366 continue
4367 yield self._extract_video(renderer)
07aeced6 4368
3462ffa8 4369 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4370 renderer = traverse_obj(
4371 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4372 video_id = renderer.get('videoId')
4373 if not video_id:
4374 return
4375 yield self._extract_video(renderer)
4376
8bdd16b4 4377 def _video_entry(self, video_renderer):
4378 video_id = video_renderer.get('videoId')
4379 if video_id:
4380 return self._extract_video(video_renderer)
dacb3a86 4381
ad210f4f 4382 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4383 url = urljoin('https://youtube.com', traverse_obj(
4384 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4385 if url:
4386 return self.url_result(
4387 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4388
8bdd16b4 4389 def _post_thread_entries(self, post_thread_renderer):
4390 post_renderer = try_get(
4391 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4392 if not post_renderer:
4393 return
4394 # video attachment
4395 video_renderer = try_get(
895b0931 4396 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4397 video_id = video_renderer.get('videoId')
4398 if video_id:
4399 entry = self._extract_video(video_renderer)
8bdd16b4 4400 if entry:
4401 yield entry
895b0931 4402 # playlist attachment
4403 playlist_id = try_get(
14f25df2 4404 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4405 if playlist_id:
4406 yield self.url_result(
e28f1c0a 4407 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4408 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4409 # inline video links
4410 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4411 for run in runs:
4412 if not isinstance(run, dict):
4413 continue
4414 ep_url = try_get(
14f25df2 4415 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4416 if not ep_url:
4417 continue
4418 if not YoutubeIE.suitable(ep_url):
4419 continue
4420 ep_video_id = YoutubeIE._match_id(ep_url)
4421 if video_id == ep_video_id:
4422 continue
895b0931 4423 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4424
8bdd16b4 4425 def _post_thread_continuation_entries(self, post_thread_continuation):
4426 contents = post_thread_continuation.get('contents')
4427 if not isinstance(contents, list):
4428 return
4429 for content in contents:
4430 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4431 if isinstance(renderer, dict):
4432 yield from self._post_thread_entries(renderer)
8bdd16b4 4433 continue
6b0b0a28 4434 renderer = content.get('videoRenderer')
4435 if isinstance(renderer, dict):
4436 yield self._video_entry(renderer)
07aeced6 4437
39ed931e 4438 r''' # unused
4439 def _rich_grid_entries(self, contents):
4440 for content in contents:
4441 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4442 if video_renderer:
4443 entry = self._video_entry(video_renderer)
4444 if entry:
4445 yield entry
4446 '''
52efa4b3 4447
0a5095fe 4448 def _report_history_entries(self, renderer):
4449 for url in traverse_obj(renderer, (
7a32c70d 4450 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4451 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4452 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4453 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4454
a6213a49 4455 def _extract_entries(self, parent_renderer, continuation_list):
4456 # continuation_list is modified in-place with continuation_list = [continuation_token]
4457 continuation_list[:] = [None]
4458 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4459 for content in contents:
4460 if not isinstance(content, dict):
4461 continue
16aa9ea4 4462 is_renderer = traverse_obj(
4463 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4464 expected_type=dict)
a6213a49 4465 if not is_renderer:
0a5095fe 4466 if content.get('richItemRenderer'):
4467 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4468 yield entry
4469 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4470 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4471 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4472 yield from self._report_history_entries(table)
4473 continuation_list[0] = self._extract_continuation(table)
a6213a49 4474 continue
0a5095fe 4475
a6213a49 4476 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4477 for isr_content in isr_contents:
4478 if not isinstance(isr_content, dict):
8bdd16b4 4479 continue
69184e41 4480
a6213a49 4481 known_renderers = {
4482 'playlistVideoListRenderer': self._playlist_entries,
4483 'gridRenderer': self._grid_entries,
a17526e4 4484 'reelShelfRenderer': self._grid_entries,
4485 'shelfRenderer': self._shelf_entries,
16aa9ea4 4486 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4487 'backstagePostThreadRenderer': self._post_thread_entries,
4488 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4489 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4490 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4491 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4492 }
4493 for key, renderer in isr_content.items():
4494 if key not in known_renderers:
4495 continue
4496 for entry in known_renderers[key](renderer):
4497 if entry:
4498 yield entry
4499 continuation_list[0] = self._extract_continuation(renderer)
4500 break
70d5c17b 4501
4502 if not continuation_list[0]:
a6213a49 4503 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4504
a6213a49 4505 if not continuation_list[0]:
4506 continuation_list[0] = self._extract_continuation(parent_renderer)
4507
4508 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4509 continuation_list = [None]
4510 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4511 tab_content = try_get(tab, lambda x: x['content'], dict)
4512 if not tab_content:
4513 return
3462ffa8 4514 parent_renderer = (
29f7c58a 4515 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4516 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4517 yield from extract_entries(parent_renderer)
3462ffa8 4518 continuation = continuation_list[0]
d069eca7 4519
8bdd16b4 4520 for page_num in itertools.count(1):
4521 if not continuation:
4522 break
99e9e001 4523 headers = self.generate_api_headers(
4524 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4525 response = self._extract_response(
86e5f3ed 4526 item_id=f'{item_id} page {page_num}',
fe93e2c4 4527 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4528 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4529
4530 if not response:
8bdd16b4 4531 break
ac56cf38 4532 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4533 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4534 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4535
a1b535bd 4536 known_renderers = {
e4b98809 4537 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4538 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4539 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4540 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4541 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4542 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4543 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4544 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4545 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4546 'playlistVideoListContinuation': (self._playlist_entries, None),
4547 'gridContinuation': (self._grid_entries, None),
4548 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4549 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4550 }
1fb53b94 4551
4552 continuation_items = traverse_obj(response, (
4553 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4554 'appendContinuationItemsAction', 'continuationItems'
4555 ), 'continuationContents', get_all=False)
4556 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4557
a1b535bd 4558 video_items_renderer = None
1fb53b94 4559 for key in continuation_item.keys():
a1b535bd 4560 if key not in known_renderers:
8bdd16b4 4561 continue
1fb53b94 4562 func, parent_key = known_renderers[key]
4563 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4564 continuation_list = [None]
1fb53b94 4565 yield from func(video_items_renderer)
9ba5705a 4566 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4567
4568 if not video_items_renderer:
a1b535bd 4569 break
9558dcec 4570
8bdd16b4 4571 @staticmethod
7c219ea6 4572 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4573 for tab in tabs:
cd684175 4574 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4575 if renderer.get('selected') is True:
4576 return renderer
2b3c2546 4577 else:
7c219ea6 4578 if fatal:
4579 raise ExtractorError('Unable to find selected tab')
b82f815f 4580
61d3665d 4581 def _extract_uploader(self, data):
8bdd16b4 4582 uploader = {}
61d3665d 4583 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4584 owner = try_get(
4585 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4586 if owner:
61d3665d 4587 owner_text = owner.get('text')
4588 uploader['uploader'] = self._search_regex(
4589 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4590 uploader['uploader_id'] = try_get(
14f25df2 4591 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4592 uploader['uploader_url'] = urljoin(
4593 'https://www.youtube.com/',
14f25df2 4594 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
7a32c70d 4595 return filter_dict(uploader)
8bdd16b4 4596
ac56cf38 4597 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4598 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4599 tags = []
b60419c5 4600
8bdd16b4 4601 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4602 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4603 renderer = try_get(
4604 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4605 if renderer:
b60419c5 4606 channel_name = renderer.get('title')
4607 channel_url = renderer.get('channelUrl')
4608 channel_id = renderer.get('externalId')
39ed931e 4609 else:
64c0d954 4610 renderer = try_get(
4611 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4612
8bdd16b4 4613 if renderer:
4614 title = renderer.get('title')
ecc97af3 4615 description = renderer.get('description', '')
b60419c5 4616 playlist_id = channel_id
4617 tags = renderer.get('keywords', '').split()
b60419c5 4618
301d07fc 4619 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4620 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4621 def _get_uncropped(url):
4622 return url_or_none((url or '').split('=')[0] + '=s0')
4623
4624 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4625 if avatar_thumbnails:
4626 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4627 if uncropped_avatar:
4628 avatar_thumbnails.append({
4629 'url': uncropped_avatar,
4630 'id': 'avatar_uncropped',
4631 'preference': 1
4632 })
4633
4634 channel_banners = self._extract_thumbnails(
4635 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4636 for banner in channel_banners:
4637 banner['preference'] = -10
4638
4639 if channel_banners:
4640 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4641 if uncropped_banner:
4642 channel_banners.append({
4643 'url': uncropped_banner,
4644 'id': 'banner_uncropped',
4645 'preference': -5
4646 })
4647
4648 primary_thumbnails = self._extract_thumbnails(
a17526e4 4649 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4650
3462ffa8 4651 if playlist_id is None:
70d5c17b 4652 playlist_id = item_id
f0d785d3 4653
4654 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
c26f9b99 4655 last_updated_unix = self._parse_time_text(self._get_text(playlist_stats, 2))
70d5c17b 4656 if title is None:
f0d785d3 4657 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4658 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4659 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4660
b60419c5 4661 metadata = {
4662 'playlist_id': playlist_id,
4663 'playlist_title': title,
4664 'playlist_description': description,
4665 'uploader': channel_name,
4666 'uploader_id': channel_id,
4667 'uploader_url': channel_url,
301d07fc 4668 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4669 'tags': tags,
f0d785d3 4670 'view_count': self._get_count(playlist_stats, 1),
4671 'availability': self._extract_availability(data),
4672 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4673 'playlist_count': self._get_count(playlist_stats, 0),
4674 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4675 }
4676 if not channel_id:
4677 metadata.update(self._extract_uploader(data))
4678 metadata.update({
4679 'channel': metadata['uploader'],
4680 'channel_id': metadata['uploader_id'],
4681 'channel_url': metadata['uploader_url']})
4682 return self.playlist_result(
d069eca7 4683 self._entries(
ac56cf38 4684 selected_tab, playlist_id, ytcfg,
4685 self._extract_account_syncid(ytcfg, data),
4686 self._extract_visitor_data(data, ytcfg)),
b60419c5 4687 **metadata)
73c4ac2c 4688
6e634cbe 4689 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4690 first_id = last_id = response = None
2be71994 4691 for page_num in itertools.count(1):
cd7c66cf 4692 videos = list(self._playlist_entries(playlist))
4693 if not videos:
4694 return
2be71994 4695 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4696 if start >= len(videos):
4697 return
24146491 4698 yield from videos[start:]
2be71994 4699 first_id = first_id or videos[0]['id']
4700 last_id = videos[-1]['id']
79360d99 4701 watch_endpoint = try_get(
4702 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4703 headers = self.generate_api_headers(
4704 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4705 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4706 query = {
4707 'playlistId': playlist_id,
4708 'videoId': watch_endpoint.get('videoId') or last_id,
4709 'index': watch_endpoint.get('index') or len(videos),
4710 'params': watch_endpoint.get('params') or 'OAE%3D'
4711 }
4712 response = self._extract_response(
4713 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4714 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4715 check_get_keys='contents'
4716 )
cd7c66cf 4717 playlist = try_get(
79360d99 4718 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4719
ac56cf38 4720 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4721 title = playlist.get('title') or try_get(
14f25df2 4722 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4723 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4724
4725 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4726 playlist_url = urljoin(url, try_get(
4727 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4728 str))
6e634cbe 4729
4730 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4731 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4732 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4733
4734 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4735 return self.url_result(
4736 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4737 video_title=title)
cd7c66cf 4738
8bdd16b4 4739 return self.playlist_result(
6e634cbe 4740 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4741 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4742
47193e02 4743 def _extract_availability(self, data):
4744 """
4745 Gets the availability of a given playlist/tab.
4746 Note: Unless YouTube tells us explicitly, we do not assume it is public
4747 @param data: response
4748 """
47193e02 4749 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
c26f9b99 4750
4751 player_header_privacy = traverse_obj(
4752 data, ('header', 'playlistHeaderRenderer', 'privacy'), expected_type=str)
4753
4754 badges = self._extract_badges(renderer)
47193e02 4755
4756 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
c26f9b99 4757 privacy_setting_icon = traverse_obj(
4758 renderer, (
4759 'privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4760 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4761 get_all=False, expected_type=str)
47193e02 4762
c26f9b99 4763 return (
4764 'public' if (
4765 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4766 or player_header_privacy == 'PUBLIC'
4767 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4768 else self._availability(
4769 is_private=(
4770 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4771 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4772 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4773 is_unlisted=(
4774 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4775 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
4776 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None else None),
4777 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4778 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4779 needs_auth=False))
47193e02 4780
4781 @staticmethod
4782 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4783 sidebar_renderer = try_get(
4784 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4785 for item in sidebar_renderer:
4786 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4787 if renderer:
4788 return renderer
4789
ac56cf38 4790 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4791 """
4792 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4793 """
5d342002 4794 browse_id = params = None
47193e02 4795 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4796 if not renderer:
4797 return
4798 menu_renderer = try_get(
4799 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4800 for menu_item in menu_renderer:
4801 if not isinstance(menu_item, dict):
358de58c 4802 continue
47193e02 4803 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4804 text = try_get(
14f25df2 4805 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4806 if not text or text.lower() != 'show unavailable videos':
4807 continue
4808 browse_endpoint = try_get(
4809 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4810 browse_id = browse_endpoint.get('browseId')
4811 params = browse_endpoint.get('params')
4812 break
5d342002 4813
11f9be09 4814 headers = self.generate_api_headers(
99e9e001 4815 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4816 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4817 query = {
4818 'params': params or 'wgYCCAA=',
4819 'browseId': browse_id or 'VL%s' % item_id
4820 }
4821 return self._extract_response(
4822 item_id=item_id, headers=headers, query=query,
fe93e2c4 4823 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4824 note='Downloading API JSON with unavailable videos')
358de58c 4825
2762dbb1 4826 @functools.cached_property
a25bca9f 4827 def skip_webpage(self):
4828 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4829
ac56cf38 4830 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4831 webpage, data = None, None
4832 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4833 try:
be5c1ae8 4834 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4835 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4836 except ExtractorError as e:
4837 if isinstance(e.cause, network_exceptions):
14f25df2 4838 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4839 retry.error = e
4840 continue
4841 self._error_or_warning(e, fatal=fatal)
14fdfea9 4842 break
ac56cf38 4843
be5c1ae8 4844 try:
4845 self._extract_and_report_alerts(data)
4846 except ExtractorError as e:
4847 self._error_or_warning(e, fatal=fatal)
4848 break
ac56cf38 4849
be5c1ae8 4850 # Sometimes youtube returns a webpage with incomplete ytInitialData
4851 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4852 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4853 retry.error = ExtractorError('Incomplete yt initial data received')
4854 continue
ac56cf38 4855
cd7c66cf 4856 return webpage, data
4857
a25bca9f 4858 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4859 """Use if failed to extract ytcfg (and data) from initial webpage"""
4860 if not ytcfg and self.is_authenticated:
4861 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4862 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4863 raise ExtractorError(
4864 f'{msg}. If you are not downloading private content, or '
4865 'your cookies are only for the first account and channel,'
4866 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4867 expected=True)
4868 self.report_warning(msg, only_once=True)
4869
ac56cf38 4870 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4871 data = None
a25bca9f 4872 if not self.skip_webpage:
ac56cf38 4873 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4874 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4875 # Reject webpage data if redirected to home page without explicitly requesting
4876 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4877 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4878 if (url != 'https://www.youtube.com/feed/recommended'
4879 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4880 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4881 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4882 if fatal:
4883 raise ExtractorError(msg, expected=True)
4884 self.report_warning(msg, only_once=True)
ac56cf38 4885 if not data:
a25bca9f 4886 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4887 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4888 return data, ytcfg
4889
4890 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4891 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4892 resolve_response = self._extract_response(
4893 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4894 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4895 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4896 for ep_key, ep in endpoints.items():
4897 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4898 if params:
4899 return self._extract_response(
4900 item_id=item_id, query=params, ep=ep, headers=headers,
4901 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4902 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4903 err_note = 'Failed to resolve url (does the playlist exist?)'
4904 if fatal:
4905 raise ExtractorError(err_note, expected=True)
4906 self.report_warning(err_note, item_id)
4907
a6213a49 4908 _SEARCH_PARAMS = None
4909
af5c1c55 4910 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4911 data = {'query': query}
4912 if params is NO_DEFAULT:
4913 params = self._SEARCH_PARAMS
4914 if params:
4915 data['params'] = params
16aa9ea4 4916
4917 content_keys = (
4918 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4919 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4920 # ytmusic search
4921 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4922 ('continuationContents', ),
4923 )
a25bca9f 4924 display_id = f'query "{query}"'
86e5f3ed 4925 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4926 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4927 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4928
a61fd4cf 4929 continuation_list = [None]
a25bca9f 4930 search = None
a6213a49 4931 for page_num in itertools.count(1):
a61fd4cf 4932 data.update(continuation_list[0] or {})
a25bca9f 4933 headers = self.generate_api_headers(
4934 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4935 search = self._extract_response(
a25bca9f 4936 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4937 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4938 slr_contents = traverse_obj(search, *content_keys)
4939 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4940 if not continuation_list[0]:
a6213a49 4941 break
4942
4943
4944class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4945 IE_DESC = 'YouTube Tabs'
4946 _VALID_URL = r'''(?x:
4947 https?://
4948 (?:\w+\.)?
4949 (?:
4950 youtube(?:kids)?\.com|
4951 %(invidious)s
4952 )/
4953 (?:
4954 (?P<channel_type>channel|c|user|browse)/|
4955 (?P<not_channel>
4956 feed/|hashtag/|
4957 (?:playlist|watch)\?.*?\blist=
4958 )|
4959 (?!(?:%(reserved_names)s)\b) # Direct URLs
4960 )
4961 (?P<id>[^/?\#&]+)
4962 )''' % {
4963 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4964 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4965 }
4966 IE_NAME = 'youtube:tab'
4967
4968 _TESTS = [{
4969 'note': 'playlists, multipage',
4970 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4971 'playlist_mincount': 94,
4972 'info_dict': {
4973 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4974 'title': 'Igor Kleiner - Playlists',
a6213a49 4975 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4976 'uploader': 'Igor Kleiner',
a6213a49 4977 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4978 'channel': 'Igor Kleiner',
4979 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4980 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4981 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4982 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4983 'channel_follower_count': int
a6213a49 4984 },
4985 }, {
4986 'note': 'playlists, multipage, different order',
4987 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4988 'playlist_mincount': 94,
4989 'info_dict': {
4990 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4991 'title': 'Igor Kleiner - Playlists',
a6213a49 4992 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4993 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4994 'uploader': 'Igor Kleiner',
4995 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4996 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4997 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4998 'channel': 'Igor Kleiner',
4999 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5000 'channel_follower_count': int
a6213a49 5001 },
5002 }, {
5003 'note': 'playlists, series',
5004 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5005 'playlist_mincount': 5,
5006 'info_dict': {
5007 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5008 'title': '3Blue1Brown - Playlists',
5009 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5010 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5011 'uploader': '3Blue1Brown',
976ae3ea 5012 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5013 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5014 'channel': '3Blue1Brown',
5015 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5016 'tags': ['Mathematics'],
6c73052c 5017 'channel_follower_count': int
a6213a49 5018 },
5019 }, {
5020 'note': 'playlists, singlepage',
5021 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5022 'playlist_mincount': 4,
5023 'info_dict': {
5024 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5025 'title': 'ThirstForScience - Playlists',
5026 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5027 'uploader': 'ThirstForScience',
5028 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5029 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5030 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5031 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5032 'tags': 'count:13',
5033 'channel': 'ThirstForScience',
6c73052c 5034 'channel_follower_count': int
a6213a49 5035 }
5036 }, {
5037 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5038 'only_matching': True,
5039 }, {
5040 'note': 'basic, single video playlist',
5041 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5042 'info_dict': {
5043 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5044 'uploader': 'Sergey M.',
5045 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5046 'title': 'youtube-dl public playlist',
976ae3ea 5047 'description': '',
5048 'tags': [],
5049 'view_count': int,
5050 'modified_date': '20201130',
5051 'channel': 'Sergey M.',
5052 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5053 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5054 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5055 'availability': 'public',
a6213a49 5056 },
5057 'playlist_count': 1,
5058 }, {
5059 'note': 'empty playlist',
5060 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5061 'info_dict': {
5062 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5063 'uploader': 'Sergey M.',
5064 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5065 'title': 'youtube-dl empty playlist',
976ae3ea 5066 'tags': [],
5067 'channel': 'Sergey M.',
5068 'description': '',
5069 'modified_date': '20160902',
5070 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5071 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5072 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5073 'availability': 'public',
a6213a49 5074 },
5075 'playlist_count': 0,
5076 }, {
5077 'note': 'Home tab',
5078 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5079 'info_dict': {
5080 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5081 'title': 'lex will - Home',
5082 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5083 'uploader': 'lex will',
5084 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5085 'channel': 'lex will',
5086 'tags': ['bible', 'history', 'prophesy'],
5087 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5088 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5089 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5090 'channel_follower_count': int
a6213a49 5091 },
5092 'playlist_mincount': 2,
5093 }, {
5094 'note': 'Videos tab',
5095 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5096 'info_dict': {
5097 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5098 'title': 'lex will - Videos',
5099 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5100 'uploader': 'lex will',
5101 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5102 'tags': ['bible', 'history', 'prophesy'],
5103 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5104 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5105 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5106 'channel': 'lex will',
6c73052c 5107 'channel_follower_count': int
a6213a49 5108 },
5109 'playlist_mincount': 975,
5110 }, {
5111 'note': 'Videos tab, sorted by popular',
5112 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5113 'info_dict': {
5114 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5115 'title': 'lex will - Videos',
5116 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5117 'uploader': 'lex will',
5118 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5119 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5120 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5121 'channel': 'lex will',
5122 'tags': ['bible', 'history', 'prophesy'],
5123 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5124 'channel_follower_count': int
a6213a49 5125 },
5126 'playlist_mincount': 199,
5127 }, {
5128 'note': 'Playlists tab',
5129 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5130 'info_dict': {
5131 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5132 'title': 'lex will - Playlists',
5133 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5134 'uploader': 'lex will',
5135 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5136 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5137 'channel': 'lex will',
5138 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5139 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5140 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5141 'channel_follower_count': int
a6213a49 5142 },
5143 'playlist_mincount': 17,
5144 }, {
5145 'note': 'Community tab',
5146 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5147 'info_dict': {
5148 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5149 'title': 'lex will - Community',
5150 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5151 'uploader': 'lex will',
5152 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5153 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5154 'channel': 'lex will',
5155 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5156 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5157 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5158 'channel_follower_count': int
a6213a49 5159 },
5160 'playlist_mincount': 18,
5161 }, {
5162 'note': 'Channels tab',
5163 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5164 'info_dict': {
5165 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5166 'title': 'lex will - Channels',
5167 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5168 'uploader': 'lex will',
5169 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5170 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5171 'channel': 'lex will',
5172 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5173 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5174 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5175 'channel_follower_count': int
a6213a49 5176 },
5177 'playlist_mincount': 12,
5178 }, {
5179 'note': 'Search tab',
5180 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5181 'playlist_mincount': 40,
5182 'info_dict': {
5183 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5184 'title': '3Blue1Brown - Search - linear algebra',
5185 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5186 'uploader': '3Blue1Brown',
5187 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5188 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5189 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5190 'tags': ['Mathematics'],
5191 'channel': '3Blue1Brown',
5192 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5193 'channel_follower_count': int
a6213a49 5194 },
5195 }, {
5196 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5197 'only_matching': True,
5198 }, {
5199 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5200 'only_matching': True,
5201 }, {
5202 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5203 'only_matching': True,
5204 }, {
5205 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5206 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5207 'info_dict': {
5208 'title': '29C3: Not my department',
5209 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5210 'uploader': 'Christiaan008',
5211 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5212 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5213 'tags': [],
5214 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5215 'view_count': int,
5216 'modified_date': '20150605',
5217 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5218 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5219 'channel': 'Christiaan008',
c26f9b99 5220 'availability': 'public',
a6213a49 5221 },
5222 'playlist_count': 96,
5223 }, {
5224 'note': 'Large playlist',
5225 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5226 'info_dict': {
5227 'title': 'Uploads from Cauchemar',
5228 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5229 'uploader': 'Cauchemar',
5230 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5231 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5232 'tags': [],
5233 'modified_date': r're:\d{8}',
5234 'channel': 'Cauchemar',
5235 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5236 'view_count': int,
5237 'description': '',
5238 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5239 'availability': 'public',
a6213a49 5240 },
5241 'playlist_mincount': 1123,
976ae3ea 5242 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5243 }, {
5244 'note': 'even larger playlist, 8832 videos',
5245 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5246 'only_matching': True,
5247 }, {
5248 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5249 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5250 'info_dict': {
5251 'title': 'Uploads from Interstellar Movie',
5252 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5253 'uploader': 'Interstellar Movie',
5254 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5255 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5256 'tags': [],
5257 'view_count': int,
5258 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5259 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5260 'channel': 'Interstellar Movie',
5261 'description': '',
5262 'modified_date': r're:\d{8}',
c26f9b99 5263 'availability': 'public',
a6213a49 5264 },
5265 'playlist_mincount': 21,
5266 }, {
5267 'note': 'Playlist with "show unavailable videos" button',
5268 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5269 'info_dict': {
5270 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5271 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5272 'uploader': 'Phim Siêu Nhân Nhật Bản',
5273 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5274 'view_count': int,
5275 'channel': 'Phim Siêu Nhân Nhật Bản',
5276 'tags': [],
5277 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5278 'description': '',
5279 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5280 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5281 'modified_date': r're:\d{8}',
c26f9b99 5282 'availability': 'public',
a6213a49 5283 },
5284 'playlist_mincount': 200,
976ae3ea 5285 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5286 }, {
5287 'note': 'Playlist with unavailable videos in page 7',
5288 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5289 'info_dict': {
5290 'title': 'Uploads from BlankTV',
5291 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5292 'uploader': 'BlankTV',
5293 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5294 'channel': 'BlankTV',
5295 'channel_url': 'https://www.youtube.com/c/blanktv',
5296 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5297 'view_count': int,
5298 'tags': [],
5299 'uploader_url': 'https://www.youtube.com/c/blanktv',
5300 'modified_date': r're:\d{8}',
5301 'description': '',
c26f9b99 5302 'availability': 'public',
a6213a49 5303 },
5304 'playlist_mincount': 1000,
976ae3ea 5305 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5306 }, {
5307 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5308 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5309 'info_dict': {
5310 'title': 'Data Analysis with Dr Mike Pound',
5311 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5312 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5313 'uploader': 'Computerphile',
5314 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5315 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5316 'tags': [],
5317 'view_count': int,
5318 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5319 'channel_url': 'https://www.youtube.com/user/Computerphile',
5320 'channel': 'Computerphile',
c26f9b99 5321 'availability': 'public',
a6213a49 5322 },
5323 'playlist_mincount': 11,
5324 }, {
5325 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5326 'only_matching': True,
5327 }, {
5328 'note': 'Playlist URL that does not actually serve a playlist',
5329 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5330 'info_dict': {
5331 'id': 'FqZTN594JQw',
5332 'ext': 'webm',
5333 'title': "Smiley's People 01 detective, Adventure Series, Action",
5334 'uploader': 'STREEM',
5335 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5336 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5337 'upload_date': '20150526',
5338 'license': 'Standard YouTube License',
5339 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5340 'categories': ['People & Blogs'],
5341 'tags': list,
5342 'view_count': int,
5343 'like_count': int,
a6213a49 5344 },
5345 'params': {
5346 'skip_download': True,
5347 },
5348 'skip': 'This video is not available.',
5349 'add_ie': [YoutubeIE.ie_key()],
5350 }, {
5351 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5352 'only_matching': True,
5353 }, {
5354 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5355 'only_matching': True,
5356 }, {
5357 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5358 'info_dict': {
12a1b225 5359 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5360 'ext': 'mp4',
976ae3ea 5361 'title': str,
a6213a49 5362 'uploader': 'Sky News',
5363 'uploader_id': 'skynews',
5364 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5365 'upload_date': r're:\d{8}',
976ae3ea 5366 'description': str,
a6213a49 5367 'categories': ['News & Politics'],
5368 'tags': list,
5369 'like_count': int,
6c73052c 5370 'release_timestamp': 1642502819,
976ae3ea 5371 'channel': 'Sky News',
5372 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5373 'age_limit': 0,
5374 'view_count': int,
6c73052c 5375 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5376 'playable_in_embed': True,
6c73052c 5377 'release_date': '20220118',
976ae3ea 5378 'availability': 'public',
5379 'live_status': 'is_live',
5380 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5381 'channel_follower_count': int
a6213a49 5382 },
5383 'params': {
5384 'skip_download': True,
5385 },
976ae3ea 5386 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5387 }, {
5388 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5389 'info_dict': {
5390 'id': 'a48o2S1cPoo',
5391 'ext': 'mp4',
5392 'title': 'The Young Turks - Live Main Show',
5393 'uploader': 'The Young Turks',
5394 'uploader_id': 'TheYoungTurks',
5395 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5396 'upload_date': '20150715',
5397 'license': 'Standard YouTube License',
5398 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5399 'categories': ['News & Politics'],
5400 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5401 'like_count': int,
a6213a49 5402 },
5403 'params': {
5404 'skip_download': True,
5405 },
5406 'only_matching': True,
5407 }, {
5408 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5409 'only_matching': True,
5410 }, {
5411 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5412 'only_matching': True,
5413 }, {
5414 'note': 'A channel that is not live. Should raise error',
5415 'url': 'https://www.youtube.com/user/numberphile/live',
5416 'only_matching': True,
5417 }, {
5418 'url': 'https://www.youtube.com/feed/trending',
5419 'only_matching': True,
5420 }, {
5421 'url': 'https://www.youtube.com/feed/library',
5422 'only_matching': True,
5423 }, {
5424 'url': 'https://www.youtube.com/feed/history',
5425 'only_matching': True,
5426 }, {
5427 'url': 'https://www.youtube.com/feed/subscriptions',
5428 'only_matching': True,
5429 }, {
5430 'url': 'https://www.youtube.com/feed/watch_later',
5431 'only_matching': True,
5432 }, {
5433 'note': 'Recommended - redirects to home page.',
5434 'url': 'https://www.youtube.com/feed/recommended',
5435 'only_matching': True,
5436 }, {
5437 'note': 'inline playlist with not always working continuations',
5438 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5439 'only_matching': True,
5440 }, {
5441 'url': 'https://www.youtube.com/course',
5442 'only_matching': True,
5443 }, {
5444 'url': 'https://www.youtube.com/zsecurity',
5445 'only_matching': True,
5446 }, {
5447 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5448 'only_matching': True,
5449 }, {
5450 'url': 'https://www.youtube.com/TheYoungTurks/live',
5451 'only_matching': True,
5452 }, {
5453 'url': 'https://www.youtube.com/hashtag/cctv9',
5454 'info_dict': {
5455 'id': 'cctv9',
5456 'title': '#cctv9',
976ae3ea 5457 'tags': [],
a6213a49 5458 },
5459 'playlist_mincount': 350,
5460 }, {
5461 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5462 'only_matching': True,
5463 }, {
5464 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5465 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5466 'only_matching': True
5467 }, {
5468 'note': '/browse/ should redirect to /channel/',
5469 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5470 'only_matching': True
5471 }, {
5472 'note': 'VLPL, should redirect to playlist?list=PL...',
5473 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5474 'info_dict': {
5475 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5476 'uploader': 'NoCopyrightSounds',
5477 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5478 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5479 'title': 'NCS : All Releases 💿',
976ae3ea 5480 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5481 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5482 'modified_date': r're:\d{8}',
5483 'view_count': int,
5484 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5485 'tags': [],
5486 'channel': 'NoCopyrightSounds',
c26f9b99 5487 'availability': 'public',
a6213a49 5488 },
5489 'playlist_mincount': 166,
976ae3ea 5490 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5491 }, {
5492 'note': 'Topic, should redirect to playlist?list=UU...',
5493 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5494 'info_dict': {
5495 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5496 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5497 'title': 'Uploads from Royalty Free Music - Topic',
5498 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5499 'tags': [],
5500 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5501 'channel': 'Royalty Free Music - Topic',
5502 'view_count': int,
5503 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5504 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5505 'modified_date': r're:\d{8}',
5506 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5507 'description': '',
c26f9b99 5508 'availability': 'public',
a6213a49 5509 },
5510 'expected_warnings': [
a6213a49 5511 'The URL does not have a videos tab',
976ae3ea 5512 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5513 ],
5514 'playlist_mincount': 101,
5515 }, {
5516 'note': 'Topic without a UU playlist',
5517 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5518 'info_dict': {
5519 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5520 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5521 'tags': [],
a6213a49 5522 },
5523 'expected_warnings': [
976ae3ea 5524 'the playlist redirect gave error',
a6213a49 5525 ],
5526 'playlist_mincount': 9,
5527 }, {
5528 'note': 'Youtube music Album',
5529 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5530 'info_dict': {
5531 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5532 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5533 'tags': [],
5534 'view_count': int,
5535 'description': '',
5536 'availability': 'unlisted',
5537 'modified_date': r're:\d{8}',
a6213a49 5538 },
5539 'playlist_count': 50,
5540 }, {
5541 'note': 'unlisted single video playlist',
5542 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5543 'info_dict': {
5544 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5545 'uploader': 'colethedj',
5546 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5547 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5548 'availability': 'unlisted',
5549 'tags': [],
12a1b225 5550 'modified_date': '20220418',
976ae3ea 5551 'channel': 'colethedj',
5552 'view_count': int,
5553 'description': '',
5554 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5555 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5556 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5557 },
5558 'playlist_count': 1,
5559 }, {
5560 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5561 'url': 'https://www.youtube.com/feed/recommended',
5562 'info_dict': {
5563 'id': 'recommended',
5564 'title': 'recommended',
6c73052c 5565 'tags': [],
a6213a49 5566 },
5567 'playlist_mincount': 50,
5568 'params': {
5569 'skip_download': True,
5570 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5571 },
5572 }, {
5573 'note': 'API Fallback: /videos tab, sorted by oldest first',
5574 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5575 'info_dict': {
5576 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5577 'title': 'Cody\'sLab - Videos',
5578 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5579 'uploader': 'Cody\'sLab',
5580 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5581 'channel': 'Cody\'sLab',
5582 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5583 'tags': [],
5584 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5585 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5586 'channel_follower_count': int
a6213a49 5587 },
5588 'playlist_mincount': 650,
5589 'params': {
5590 'skip_download': True,
5591 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5592 },
5593 }, {
5594 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5595 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5596 'info_dict': {
5597 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5598 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5599 'title': 'Uploads from Royalty Free Music - Topic',
5600 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5601 'modified_date': r're:\d{8}',
5602 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5603 'description': '',
5604 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5605 'tags': [],
5606 'channel': 'Royalty Free Music - Topic',
5607 'view_count': int,
5608 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5609 'availability': 'public',
a6213a49 5610 },
5611 'expected_warnings': [
976ae3ea 5612 'does not have a videos tab',
5613 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5614 ],
5615 'playlist_mincount': 101,
5616 'params': {
5617 'skip_download': True,
5618 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5619 },
7c219ea6 5620 }, {
5621 'note': 'non-standard redirect to regional channel',
5622 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5623 'only_matching': True
61d3665d 5624 }, {
5625 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5626 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5627 'info_dict': {
5628 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5629 'modified_date': '20220407',
5630 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5631 'tags': [],
5632 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5633 'uploader': 'pukkandan',
5634 'availability': 'unlisted',
5635 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5636 'channel': 'pukkandan',
5637 'description': 'Test for collaborative playlist',
5638 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5639 'view_count': int,
61d3665d 5640 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5641 },
5642 'playlist_mincount': 2
c26f9b99 5643 }, {
5644 'note': 'translated tab name',
5645 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5646 'info_dict': {
5647 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5648 'tags': [],
5649 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5650 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5651 'description': '',
5652 'title': 'cole-dlp-test-acc - 再生リスト',
5653 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5654 'uploader': 'cole-dlp-test-acc',
5655 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5656 'channel': 'cole-dlp-test-acc',
5657 },
5658 'playlist_mincount': 1,
5659 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5660 'expected_warnings': ['Preferring "ja"'],
5661 }, {
5662 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5663 'note': 'preferred lang set with playlist with translated video titles',
5664 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5665 'info_dict': {
5666 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5667 'tags': [],
5668 'view_count': int,
5669 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5670 'uploader': 'cole-dlp-test-acc',
5671 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5672 'channel': 'cole-dlp-test-acc',
5673 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5674 'description': 'test',
5675 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5676 'title': 'dlp test playlist',
5677 'availability': 'public',
5678 },
5679 'playlist_mincount': 1,
5680 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5681 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5682 }, {
5683 # shorts audio pivot for 2GtVksBMYFM.
5684 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5685 'info_dict': {
5686 'id': 'sfv_audio_pivot',
5687 'title': 'sfv_audio_pivot',
5688 'tags': [],
5689 },
5690 'playlist_mincount': 50,
5691
a6213a49 5692 }]
5693
5694 @classmethod
5695 def suitable(cls, url):
86e5f3ed 5696 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5697
64f36541 5698 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5699
182bda88 5700 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5701 def _real_extract(self, url, smuggled_data):
cd7c66cf 5702 item_id = self._match_id(url)
14f25df2 5703 url = urllib.parse.urlunparse(
5704 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5705 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5706
fe03a6cd 5707 def get_mobj(url):
37e57a9f 5708 mobj = self._URL_RE.match(url).groupdict()
07cce701 5709 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5710 return mobj
5711
37e57a9f 5712 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5713 # Youtube returns incomplete data if tabname is not lower case
5714 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5715 if is_channel:
5716 if smuggled_data.get('is_music_url'):
37e57a9f 5717 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5718 item_id = item_id[2:]
37e57a9f 5719 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5720 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5721 mdata = self._extract_tab_endpoint(
37e57a9f 5722 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5723 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5724 get_all=False, expected_type=str)
ac56cf38 5725 if not murl:
37e57a9f 5726 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5727 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5728 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5729 pre = f'https://www.youtube.com/channel/{item_id}'
5730
64f36541 5731 original_tab_name = tab
fe03a6cd 5732 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5733 # Home URLs should redirect to /videos/
37e57a9f 5734 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5735 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5736 tab = '/videos'
5737
5738 url = ''.join((pre, tab, post))
5739 mobj = get_mobj(url)
cd7c66cf 5740
5741 # Handle both video/playlist URLs
201c1459 5742 qs = parse_qs(url)
86e5f3ed 5743 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5744
fe03a6cd 5745 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5746 if not playlist_id:
fe03a6cd 5747 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5748 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5749 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5750 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5751 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5752 mobj = get_mobj(url)
cd7c66cf 5753
5754 if video_id and playlist_id:
a06916d9 5755 if self.get_param('noplaylist'):
37e57a9f 5756 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5757 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5758 ie=YoutubeIE.ie_key(), video_id=video_id)
5759 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5760
ac56cf38 5761 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5762
7c219ea6 5763 # YouTube may provide a non-standard redirect to the regional channel
5764 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5765 redirect_url = traverse_obj(
5766 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5767 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5768 redirect_url = ''.join((
5769 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5770 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5771 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5772
37e57a9f 5773 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5774 if tabs:
5775 selected_tab = self._extract_selected_tab(tabs)
c26f9b99 5776 selected_tab_url = urljoin(
5777 url, traverse_obj(selected_tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5778 translated_tab_name = selected_tab.get('title', '').lower()
5779
5780 # Prefer tab name from tab url as it is always in en,
5781 # but only when preferred lang is set as it may not extract reliably in all cases.
5782 selected_tab_name = (self._preferred_lang in (None, 'en') and translated_tab_name
5783 or selected_tab_url and get_mobj(selected_tab_url)['tab'][1:] # primary
5784 or translated_tab_name)
5785
64f36541 5786 if selected_tab_name == 'home':
5787 selected_tab_name = 'featured'
5788 requested_tab_name = mobj['tab'][1:]
c26f9b99 5789
09f1580e 5790 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5791 if requested_tab_name == 'live': # Live tab should have redirected to the video
5792 raise UserNotLive(video_id=mobj['id'])
64f36541 5793 if requested_tab_name not in ('', selected_tab_name):
5794 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5795 if not original_tab_name:
5796 if item_id[:2] == 'UC':
5797 # Topic channels don't have /videos. Use the equivalent playlist instead
5798 pl_id = f'UU{item_id[2:]}'
5799 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5800 try:
5801 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5802 except ExtractorError:
5803 redirect_warning += ' and the playlist redirect gave error'
5804 else:
5805 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5806 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5807 if selected_tab_name and selected_tab_name != requested_tab_name:
5808 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5809 else:
5810 raise ExtractorError(redirect_warning, expected=True)
18db7548 5811
37e57a9f 5812 if redirect_warning:
64f36541 5813 self.to_screen(redirect_warning)
37e57a9f 5814 self.write_debug(f'Final URL: {url}')
18db7548 5815
358de58c 5816 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5817 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5818 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5819 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5820 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5821 if tabs:
ac56cf38 5822 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5823
37e57a9f 5824 playlist = traverse_obj(
5825 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5826 if playlist:
ac56cf38 5827 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5828
37e57a9f 5829 video_id = traverse_obj(
5830 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5831 if video_id:
09f1580e 5832 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5833 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5834 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5835 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5836
8bdd16b4 5837 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5838
c5e8d7af 5839
8bdd16b4 5840class YoutubePlaylistIE(InfoExtractor):
96565c7e 5841 IE_DESC = 'YouTube playlists'
8bdd16b4 5842 _VALID_URL = r'''(?x)(?:
5843 (?:https?://)?
5844 (?:\w+\.)?
5845 (?:
5846 (?:
5847 youtube(?:kids)?\.com|
d9190e44 5848 %(invidious)s
8bdd16b4 5849 )
5850 /.*?\?.*?\blist=
5851 )?
5852 (?P<id>%(playlist_id)s)
d9190e44
RH
5853 )''' % {
5854 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5855 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5856 }
8bdd16b4 5857 IE_NAME = 'youtube:playlist'
cdc628a4 5858 _TESTS = [{
8bdd16b4 5859 'note': 'issue #673',
5860 'url': 'PLBB231211A4F62143',
cdc628a4 5861 'info_dict': {
8bdd16b4 5862 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5863 'id': 'PLBB231211A4F62143',
976ae3ea 5864 'uploader': 'Wickman',
8bdd16b4 5865 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5866 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5867 'view_count': int,
5868 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5869 'modified_date': r're:\d{8}',
5870 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5871 'channel': 'Wickman',
5872 'tags': [],
5873 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5874 },
5875 'playlist_mincount': 29,
5876 }, {
5877 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5878 'info_dict': {
5879 'title': 'YDL_safe_search',
5880 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5881 },
5882 'playlist_count': 2,
5883 'skip': 'This playlist is private',
9558dcec 5884 }, {
8bdd16b4 5885 'note': 'embedded',
5886 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5887 'playlist_count': 4,
9558dcec 5888 'info_dict': {
8bdd16b4 5889 'title': 'JODA15',
5890 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5891 'uploader': 'milan',
5892 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5893 'description': '',
5894 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5895 'tags': [],
5896 'modified_date': '20140919',
5897 'view_count': int,
5898 'channel': 'milan',
5899 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5900 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 5901 'availability': 'public',
976ae3ea 5902 },
5903 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5904 }, {
8bdd16b4 5905 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5906 'playlist_mincount': 455,
8bdd16b4 5907 'info_dict': {
5908 'title': '2018 Chinese New Singles (11/6 updated)',
5909 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5910 'uploader': 'LBK',
5911 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5912 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5913 'channel': 'LBK',
5914 'view_count': int,
5915 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5916 'tags': [],
5917 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5918 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5919 'modified_date': r're:\d{8}',
c26f9b99 5920 'availability': 'public',
976ae3ea 5921 },
5922 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5923 }, {
29f7c58a 5924 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5925 'only_matching': True,
5926 }, {
5927 # music album playlist
5928 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5929 'only_matching': True,
5930 }]
5931
5932 @classmethod
5933 def suitable(cls, url):
201c1459 5934 if YoutubeTabIE.suitable(url):
5935 return False
49a57e70 5936 from ..utils import parse_qs
201c1459 5937 qs = parse_qs(url)
5938 if qs.get('v', [None])[0]:
5939 return False
86e5f3ed 5940 return super().suitable(url)
29f7c58a 5941
5942 def _real_extract(self, url):
5943 playlist_id = self._match_id(url)
46953e7e 5944 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5945 url = update_url_query(
5946 'https://www.youtube.com/playlist',
5947 parse_qs(url) or {'list': playlist_id})
5948 if is_music_url:
5949 url = smuggle_url(url, {'is_music_url': True})
5950 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5951
5952
5953class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5954 IE_DESC = 'youtu.be'
29f7c58a 5955 _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}
5956 _TESTS = [{
8bdd16b4 5957 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5958 'info_dict': {
5959 'id': 'yeWKywCrFtk',
5960 'ext': 'mp4',
5961 'title': 'Small Scale Baler and Braiding Rugs',
5962 'uploader': 'Backus-Page House Museum',
5963 'uploader_id': 'backuspagemuseum',
5964 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5965 'upload_date': '20161008',
5966 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5967 'categories': ['Nonprofits & Activism'],
5968 'tags': list,
5969 'like_count': int,
976ae3ea 5970 'age_limit': 0,
5971 'playable_in_embed': True,
5972 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5973 'channel': 'Backus-Page House Museum',
5974 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5975 'live_status': 'not_live',
5976 'view_count': int,
5977 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5978 'availability': 'public',
5979 'duration': 59,
12a1b225
A
5980 'comment_count': int,
5981 'channel_follower_count': int
8bdd16b4 5982 },
5983 'params': {
5984 'noplaylist': True,
5985 'skip_download': True,
5986 },
39e7107d 5987 }, {
8bdd16b4 5988 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5989 'only_matching': True,
cdc628a4
PH
5990 }]
5991
8bdd16b4 5992 def _real_extract(self, url):
5ad28e7f 5993 mobj = self._match_valid_url(url)
29f7c58a 5994 video_id = mobj.group('id')
5995 playlist_id = mobj.group('playlist_id')
8bdd16b4 5996 return self.url_result(
29f7c58a 5997 update_url_query('https://www.youtube.com/watch', {
5998 'v': video_id,
5999 'list': playlist_id,
6000 'feature': 'youtu.be',
6001 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6002
6003
b6ce9bb0 6004class YoutubeLivestreamEmbedIE(InfoExtractor):
6005 IE_DESC = 'YouTube livestream embeds'
6006 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6007 _TESTS = [{
6008 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6009 'only_matching': True,
6010 }]
6011
6012 def _real_extract(self, url):
6013 channel_id = self._match_id(url)
6014 return self.url_result(
6015 f'https://www.youtube.com/channel/{channel_id}/live',
6016 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6017
6018
8bdd16b4 6019class YoutubeYtUserIE(InfoExtractor):
96565c7e 6020 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6021 IE_NAME = 'youtube:user'
8bdd16b4 6022 _VALID_URL = r'ytuser:(?P<id>.+)'
6023 _TESTS = [{
6024 'url': 'ytuser:phihag',
6025 'only_matching': True,
6026 }]
6027
6028 def _real_extract(self, url):
6029 user_id = self._match_id(url)
6030 return self.url_result(
c586f9e8 6031 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 6032 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 6033
b05654f0 6034
3d3dddc9 6035class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6036 IE_NAME = 'youtube:favorites'
96565c7e 6037 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6038 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6039 _LOGIN_REQUIRED = True
6040 _TESTS = [{
6041 'url': ':ytfav',
6042 'only_matching': True,
6043 }, {
6044 'url': ':ytfavorites',
6045 'only_matching': True,
6046 }]
6047
6048 def _real_extract(self, url):
6049 return self.url_result(
6050 'https://www.youtube.com/playlist?list=LL',
6051 ie=YoutubeTabIE.ie_key())
6052
6053
ca5300c7 6054class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6055 IE_NAME = 'youtube:notif'
6056 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6057 _VALID_URL = r':ytnotif(?:ication)?s?'
6058 _LOGIN_REQUIRED = True
6059 _TESTS = [{
6060 'url': ':ytnotif',
6061 'only_matching': True,
6062 }, {
6063 'url': ':ytnotifications',
6064 'only_matching': True,
6065 }]
6066
6067 def _extract_notification_menu(self, response, continuation_list):
6068 notification_list = traverse_obj(
6069 response,
6070 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6071 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6072 expected_type=list) or []
6073 continuation_list[0] = None
6074 for item in notification_list:
6075 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6076 if entry:
6077 yield entry
6078 continuation = item.get('continuationItemRenderer')
6079 if continuation:
6080 continuation_list[0] = continuation
6081
6082 def _extract_notification_renderer(self, notification):
6083 video_id = traverse_obj(
6084 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6085 url = f'https://www.youtube.com/watch?v={video_id}'
6086 channel_id = None
6087 if not video_id:
6088 browse_ep = traverse_obj(
6089 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6090 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6091 post_id = self._search_regex(
6092 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6093 'post id', default=None)
6094 if not channel_id or not post_id:
6095 return
6096 # The direct /post url redirects to this in the browser
6097 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6098
6099 channel = traverse_obj(
6100 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6101 expected_type=str)
c7a7baaa 6102 notification_title = self._get_text(notification, 'shortMessage')
6103 if notification_title:
6104 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6105 # TODO: handle recommended videos
ca5300c7 6106 title = self._search_regex(
c7a7baaa 6107 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6108 'video title', default=None)
5225df50 6109 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6110 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6111 else None)
ca5300c7 6112 return {
6113 '_type': 'url',
6114 'url': url,
6115 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6116 'video_id': video_id,
6117 'title': title,
6118 'channel_id': channel_id,
6119 'channel': channel,
6120 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6121 'timestamp': timestamp,
ca5300c7 6122 }
6123
6124 def _notification_menu_entries(self, ytcfg):
6125 continuation_list = [None]
6126 response = None
6127 for page in itertools.count(1):
6128 ctoken = traverse_obj(
6129 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6130 response = self._extract_response(
6131 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6132 ep='notification/get_notification_menu', check_get_keys='actions',
6133 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6134 yield from self._extract_notification_menu(response, continuation_list)
6135 if not continuation_list[0]:
6136 break
6137
6138 def _real_extract(self, url):
6139 display_id = 'notifications'
6140 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6141 self._report_playlist_authcheck(ytcfg)
6142 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6143
6144
a6213a49 6145class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6146 IE_DESC = 'YouTube search'
78caa52a 6147 IE_NAME = 'youtube:search'
b05654f0 6148 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6149 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6150 _TESTS = [{
6151 'url': 'ytsearch5:youtube-dl test video',
6152 'playlist_count': 5,
6153 'info_dict': {
6154 'id': 'youtube-dl test video',
6155 'title': 'youtube-dl test video',
6156 }
6157 }]
b05654f0 6158
a61fd4cf 6159
5f7cb91a 6160class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6161 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6162 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6163 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6164 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6165 _TESTS = [{
6166 'url': 'ytsearchdate5:youtube-dl test video',
6167 'playlist_count': 5,
6168 'info_dict': {
6169 'id': 'youtube-dl test video',
6170 'title': 'youtube-dl test video',
6171 }
6172 }]
75dff0ee 6173
c9ae7b95 6174
a6213a49 6175class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6176 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6177 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6178 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6179 _TESTS = [{
6180 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6181 'playlist_mincount': 5,
6182 'info_dict': {
11f9be09 6183 'id': 'youtube-dl test video',
3462ffa8 6184 'title': 'youtube-dl test video',
6185 }
a61fd4cf 6186 }, {
6187 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6188 'playlist_mincount': 5,
6189 'info_dict': {
6190 'id': 'python',
6191 'title': 'python',
6192 }
ad210f4f 6193 }, {
6194 'url': 'https://www.youtube.com/results?search_query=%23cats',
6195 'playlist_mincount': 1,
6196 'info_dict': {
6197 'id': '#cats',
6198 'title': '#cats',
12a1b225
A
6199 # The test suite does not have support for nested playlists
6200 # 'entries': [{
6201 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6202 # 'title': '#cats',
6203 # }],
ad210f4f 6204 },
3462ffa8 6205 }, {
6206 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6207 'only_matching': True,
6208 }]
6209
6210 def _real_extract(self, url):
4dfbf869 6211 qs = parse_qs(url)
386e1dd9 6212 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6213 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6214
6215
16aa9ea4 6216class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6217 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6218 IE_NAME = 'youtube:music:search_url'
6219 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6220 _TESTS = [{
6221 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6222 'playlist_count': 16,
6223 'info_dict': {
6224 'id': 'royalty free music',
6225 'title': 'royalty free music',
6226 }
6227 }, {
6228 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6229 'playlist_mincount': 30,
6230 'info_dict': {
6231 'id': 'royalty free music - songs',
6232 'title': 'royalty free music - songs',
6233 },
6234 'params': {'extract_flat': 'in_playlist'}
6235 }, {
6236 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6237 'playlist_mincount': 30,
6238 'info_dict': {
6239 'id': 'royalty free music - community playlists',
6240 'title': 'royalty free music - community playlists',
6241 },
6242 'params': {'extract_flat': 'in_playlist'}
6243 }]
6244
6245 _SECTIONS = {
6246 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6247 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6248 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6249 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6250 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6251 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6252 }
6253
6254 def _real_extract(self, url):
6255 qs = parse_qs(url)
6256 query = (qs.get('search_query') or qs.get('q'))[0]
6257 params = qs.get('sp', (None,))[0]
6258 if params:
6259 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6260 else:
ac668111 6261 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6262 params = self._SECTIONS.get(section)
6263 if not params:
6264 section = None
6265 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6266 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6267
6268
182bda88 6269class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6270 """
25f14e9f 6271 Base class for feed extractors
82d02080 6272 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6273 """
b2e8bc1b 6274 _LOGIN_REQUIRED = True
82d02080 6275 _FEED_NAME = 'feeds'
a25bca9f 6276
6277 def _real_initialize(self):
6278 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6279
82d02080 6280 @classproperty
d7ae0639 6281 def IE_NAME(self):
82d02080 6282 return f'youtube:{self._FEED_NAME}'
04cc9617 6283
3853309f 6284 def _real_extract(self, url):
3d3dddc9 6285 return self.url_result(
182bda88 6286 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6287
6288
ef2f3c7f 6289class YoutubeWatchLaterIE(InfoExtractor):
6290 IE_NAME = 'youtube:watchlater'
96565c7e 6291 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6292 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6293 _TESTS = [{
8bdd16b4 6294 'url': ':ytwatchlater',
bc7a9cd8
S
6295 'only_matching': True,
6296 }]
25f14e9f
S
6297
6298 def _real_extract(self, url):
ef2f3c7f 6299 return self.url_result(
6300 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6301
6302
25f14e9f 6303class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6304 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6305 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6306 _FEED_NAME = 'recommended'
45db527f 6307 _LOGIN_REQUIRED = False
3d3dddc9 6308 _TESTS = [{
6309 'url': ':ytrec',
6310 'only_matching': True,
6311 }, {
6312 'url': ':ytrecommended',
6313 'only_matching': True,
6314 }, {
6315 'url': 'https://youtube.com',
6316 'only_matching': True,
6317 }]
1ed5b5c9 6318
1ed5b5c9 6319
25f14e9f 6320class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6321 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6322 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6323 _FEED_NAME = 'subscriptions'
3d3dddc9 6324 _TESTS = [{
6325 'url': ':ytsubs',
6326 'only_matching': True,
6327 }, {
6328 'url': ':ytsubscriptions',
6329 'only_matching': True,
6330 }]
1ed5b5c9 6331
1ed5b5c9 6332
25f14e9f 6333class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6334 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6335 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6336 _FEED_NAME = 'history'
3d3dddc9 6337 _TESTS = [{
6338 'url': ':ythistory',
6339 'only_matching': True,
6340 }]
1ed5b5c9
JMF
6341
6342
6e634cbe 6343class YoutubeStoriesIE(InfoExtractor):
6344 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6345 IE_NAME = 'youtube:stories'
6346 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6347 _TESTS = [{
6348 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6349 'only_matching': True,
6350 }]
6351
6352 def _real_extract(self, url):
6353 playlist_id = f'RLTD{self._match_id(url)}'
6354 return self.url_result(
50ac0e54 6355 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6356 ie=YoutubeTabIE, video_id=playlist_id)
6357
6358
80eb0bd9 6359class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6360 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6361 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6362 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6363 _TESTS = [{
1dd18a88 6364 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6365 'only_matching': True,
6366 }]
6367
6368 @staticmethod
6369 def _generate_audio_pivot_params(video_id):
6370 """
6371 Generates sfv_audio_pivot browse params for this video id
6372 """
6373 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6374 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6375
6376 def _real_extract(self, url):
6377 video_id = self._match_id(url)
6378 return self.url_result(
6379 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6380 ie=YoutubeTabIE)
6381
6382
15870e90
PH
6383class YoutubeTruncatedURLIE(InfoExtractor):
6384 IE_NAME = 'youtube:truncated_url'
6385 IE_DESC = False # Do not list
975d35db 6386 _VALID_URL = r'''(?x)
b95aab84
PH
6387 (?:https?://)?
6388 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6389 (?:watch\?(?:
c4808c60 6390 feature=[a-z_]+|
b95aab84
PH
6391 annotation_id=annotation_[^&]+|
6392 x-yt-cl=[0-9]+|
c1708b89 6393 hl=[^&]*|
287be8c6 6394 t=[0-9]+
b95aab84
PH
6395 )?
6396 |
6397 attribution_link\?a=[^&]+
6398 )
6399 $
975d35db 6400 '''
15870e90 6401
c4808c60 6402 _TESTS = [{
2d3d2997 6403 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6404 'only_matching': True,
dc2fc736 6405 }, {
2d3d2997 6406 'url': 'https://www.youtube.com/watch?',
dc2fc736 6407 'only_matching': True,
b95aab84
PH
6408 }, {
6409 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6410 'only_matching': True,
6411 }, {
6412 'url': 'https://www.youtube.com/watch?feature=foo',
6413 'only_matching': True,
c1708b89
PH
6414 }, {
6415 'url': 'https://www.youtube.com/watch?hl=en-GB',
6416 'only_matching': True,
287be8c6
PH
6417 }, {
6418 'url': 'https://www.youtube.com/watch?t=2372',
6419 'only_matching': True,
c4808c60
PH
6420 }]
6421
15870e90
PH
6422 def _real_extract(self, url):
6423 raise ExtractorError(
78caa52a
PH
6424 'Did you forget to quote the URL? Remember that & is a meta '
6425 'character in most shells, so you want to put the URL in quotes, '
3867038a 6426 'like youtube-dl '
2d3d2997 6427 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6428 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6429 expected=True)
772fd5cc
PH
6430
6431
471d0367 6432class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6433 IE_NAME = 'youtube:clip'
471d0367 6434 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6435 _TESTS = [{
6436 # FIXME: Other metadata should be extracted from the clip, not from the base video
6437 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6438 'info_dict': {
6439 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6440 'ext': 'mp4',
6441 'section_start': 29.0,
6442 'section_end': 39.7,
6443 'duration': 10.7,
12a1b225
A
6444 'age_limit': 0,
6445 'availability': 'public',
6446 'categories': ['Gaming'],
6447 'channel': 'Scott The Woz',
6448 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6449 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6450 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6451 'like_count': int,
6452 'playable_in_embed': True,
6453 'tags': 'count:17',
6454 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6455 'title': 'Mobile Games on Console - Scott The Woz',
6456 'upload_date': '20210920',
6457 'uploader': 'Scott The Woz',
6458 'uploader_id': 'scottthewoz',
6459 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6460 'view_count': int,
6461 'live_status': 'not_live',
6462 'channel_follower_count': int
471d0367 6463 }
6464 }]
3cd786db 6465
6466 def _real_extract(self, url):
471d0367 6467 clip_id = self._match_id(url)
6468 _, data = self._extract_webpage(url, clip_id)
6469
6470 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6471 if not video_id:
6472 raise ExtractorError('Unable to find video ID')
6473
6474 clip_data = traverse_obj(data, (
6475 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6476 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6477 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6478 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6479
6480 return {
6481 '_type': 'url_transparent',
6482 'url': f'https://www.youtube.com/watch?v={video_id}',
6483 'ie_key': YoutubeIE.ie_key(),
6484 'id': clip_id,
6485 'section_start': int(clip_data['startTimeMs']) / 1000,
6486 'section_end': int(clip_data['endTimeMs']) / 1000,
6487 }
3cd786db 6488
6489
772fd5cc
PH
6490class YoutubeTruncatedIDIE(InfoExtractor):
6491 IE_NAME = 'youtube:truncated_id'
6492 IE_DESC = False # Do not list
b95aab84 6493 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6494
6495 _TESTS = [{
6496 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6497 'only_matching': True,
6498 }]
6499
6500 def _real_extract(self, url):
6501 video_id = self._match_id(url)
6502 raise ExtractorError(
86e5f3ed 6503 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6504 expected=True)