]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[utils] `strftime_or_none`: Workaround Python bug on Windows
[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,
c26f9b99 951 'upload_date': (strftime_or_none(self._parse_time_text(time_text), '%Y%m%d')
a44ca5a4 952 if self._configuration_arg('approximate_date', ie_key='youtubetab')
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,
6c73052c 1724 'channel_follower_count': int
7caf9830
S
1725 },
1726 'params': {
1727 'skip_download': True,
1728 },
1729 },
fd050249
S
1730 {
1731 # Channel-like uploader_url
1732 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1733 'info_dict': {
1734 'id': 'eQcmzGIKrzg',
1735 'ext': 'mp4',
1736 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1737 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1738 'duration': 4060,
17322130 1739 'upload_date': '20151120',
eb6793ba 1740 'uploader': 'Bernie Sanders',
fd050249 1741 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1742 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1743 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1744 'playable_in_embed': True,
1745 'tags': 'count:12',
1746 'like_count': int,
1747 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1748 'age_limit': 0,
1749 'availability': 'public',
1750 'categories': ['News & Politics'],
1751 'channel': 'Bernie Sanders',
1752 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1753 'view_count': int,
1754 'live_status': 'not_live',
1755 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1756 'comment_count': int,
6c73052c 1757 'channel_follower_count': int
fd050249
S
1758 },
1759 'params': {
1760 'skip_download': True,
1761 },
1762 },
040ac686
S
1763 {
1764 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1765 'only_matching': True,
7f29cf54
S
1766 },
1767 {
067aa17e 1768 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1769 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1770 'only_matching': True,
6496ccb4
S
1771 },
1772 {
1773 # Rental video preview
1774 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1775 'info_dict': {
1776 'id': 'uGpuVWrhIzE',
1777 'ext': 'mp4',
1778 'title': 'Piku - Trailer',
1779 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1780 'upload_date': '20150811',
1781 'uploader': 'FlixMatrix',
1782 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1783 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1784 'license': 'Standard YouTube License',
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
eb6793ba 1789 'skip': 'This video is not available.',
022a5d66 1790 },
12afdc2a
S
1791 {
1792 # YouTube Red video with episode data
1793 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1794 'info_dict': {
1795 'id': 'iqKdEhx-dD4',
1796 'ext': 'mp4',
1797 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1798 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1799 'duration': 2085,
12afdc2a
S
1800 'upload_date': '20170118',
1801 'uploader': 'Vsauce',
1802 'uploader_id': 'Vsauce',
1803 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1804 'series': 'Mind Field',
1805 'season_number': 1,
1806 'episode_number': 1,
976ae3ea 1807 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1808 'tags': 'count:12',
1809 'view_count': int,
1810 'availability': 'public',
1811 'age_limit': 0,
1812 'channel': 'Vsauce',
1813 'episode': 'Episode 1',
1814 'categories': ['Entertainment'],
1815 'season': 'Season 1',
1816 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1817 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1818 'like_count': int,
1819 'playable_in_embed': True,
1820 'live_status': 'not_live',
6c73052c 1821 'channel_follower_count': int
12afdc2a
S
1822 },
1823 'params': {
1824 'skip_download': True,
1825 },
1826 'expected_warnings': [
1827 'Skipping DASH manifest',
1828 ],
1829 },
c7121fa7
S
1830 {
1831 # The following content has been identified by the YouTube community
1832 # as inappropriate or offensive to some audiences.
1833 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1834 'info_dict': {
1835 'id': '6SJNVb0GnPI',
1836 'ext': 'mp4',
1837 'title': 'Race Differences in Intelligence',
1838 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1839 'duration': 965,
1840 'upload_date': '20140124',
1841 'uploader': 'New Century Foundation',
1842 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1843 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1844 },
1845 'params': {
1846 'skip_download': True,
1847 },
545cc85d 1848 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1849 },
022a5d66
S
1850 {
1851 # itag 212
1852 'url': '1t24XAntNCY',
1853 'only_matching': True,
fd5c4aab
S
1854 },
1855 {
1856 # geo restricted to JP
1857 'url': 'sJL6WA-aGkQ',
1858 'only_matching': True,
1859 },
cd5a74a2
S
1860 {
1861 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1862 'only_matching': True,
1863 },
bc2ca1bb 1864 {
1865 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1866 'only_matching': True,
1867 },
1868 {
1869 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1870 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1871 'only_matching': True,
1872 },
825cd268
RA
1873 {
1874 # DRM protected
1875 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1876 'only_matching': True,
4fe54c12
S
1877 },
1878 {
1879 # Video with unsupported adaptive stream type formats
1880 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1881 'info_dict': {
1882 'id': 'Z4Vy8R84T1U',
1883 'ext': 'mp4',
1884 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1885 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1886 'duration': 433,
1887 'upload_date': '20130923',
1888 'uploader': 'Amelia Putri Harwita',
1889 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1890 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1891 'formats': 'maxcount:10',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 'youtube_include_dash_manifest': False,
1896 },
5429d6a9 1897 'skip': 'not actual anymore',
5caabd3c 1898 },
1899 {
822b9d9c 1900 # Youtube Music Auto-generated description
5caabd3c 1901 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1902 'info_dict': {
1903 'id': 'MgNrAu2pzNs',
1904 'ext': 'mp4',
1905 'title': 'Voyeur Girl',
1906 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1907 'upload_date': '20190312',
5429d6a9
S
1908 'uploader': 'Stephen - Topic',
1909 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1910 'artist': 'Stephen',
1911 'track': 'Voyeur Girl',
1912 'album': 'it\'s too much love to know my dear',
1913 'release_date': '20190313',
1914 'release_year': 2019,
976ae3ea 1915 'alt_title': 'Voyeur Girl',
1916 'view_count': int,
1917 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1918 'playable_in_embed': True,
1919 'like_count': int,
1920 'categories': ['Music'],
1921 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1922 'channel': 'Stephen',
1923 'availability': 'public',
1924 'creator': 'Stephen',
1925 'duration': 169,
1926 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1927 'age_limit': 0,
1928 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1929 'tags': 'count:11',
1930 'live_status': 'not_live',
6c73052c 1931 'channel_follower_count': int
5caabd3c 1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
1936 },
66b48727
RA
1937 {
1938 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1939 'only_matching': True,
1940 },
011e75e6
S
1941 {
1942 # invalid -> valid video id redirection
1943 'url': 'DJztXj2GPfl',
1944 'info_dict': {
1945 'id': 'DJztXj2GPfk',
1946 'ext': 'mp4',
1947 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1948 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1949 'upload_date': '20090125',
1950 'uploader': 'Prochorowka',
1951 'uploader_id': 'Prochorowka',
1952 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1953 'artist': 'Panjabi MC',
1954 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1955 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1956 },
1957 'params': {
1958 'skip_download': True,
1959 },
545cc85d 1960 'skip': 'Video unavailable',
ea74e00b
DP
1961 },
1962 {
1963 # empty description results in an empty string
1964 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1965 'info_dict': {
1966 'id': 'x41yOUIvK2k',
1967 'ext': 'mp4',
1968 'title': 'IMG 3456',
1969 'description': '',
1970 'upload_date': '20170613',
1971 'uploader_id': 'ElevageOrVert',
1972 'uploader': 'ElevageOrVert',
976ae3ea 1973 'view_count': int,
1974 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1975 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1976 'like_count': int,
1977 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1978 'tags': [],
1979 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1980 'availability': 'public',
1981 'age_limit': 0,
1982 'categories': ['Pets & Animals'],
1983 'duration': 7,
1984 'playable_in_embed': True,
1985 'live_status': 'not_live',
1986 'channel': 'ElevageOrVert',
6c73052c 1987 'channel_follower_count': int
ea74e00b
DP
1988 },
1989 'params': {
1990 'skip_download': True,
1991 },
1992 },
a0566bbf 1993 {
29f7c58a 1994 # with '};' inside yt initial data (see [1])
1995 # see [2] for an example with '};' inside ytInitialPlayerResponse
1996 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1997 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1998 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1999 'info_dict': {
2000 'id': 'CHqg6qOn4no',
2001 'ext': 'mp4',
2002 'title': 'Part 77 Sort a list of simple types in c#',
2003 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2004 'upload_date': '20130831',
2005 'uploader_id': 'kudvenkat',
2006 'uploader': 'kudvenkat',
976ae3ea 2007 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2008 'like_count': int,
2009 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2010 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2011 'live_status': 'not_live',
2012 'categories': ['Education'],
2013 'availability': 'public',
2014 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2015 'tags': 'count:12',
2016 'playable_in_embed': True,
2017 'age_limit': 0,
2018 'view_count': int,
2019 'duration': 522,
2020 'channel': 'kudvenkat',
12a1b225 2021 'comment_count': int,
6c73052c 2022 'channel_follower_count': int
a0566bbf 2023 },
2024 'params': {
2025 'skip_download': True,
2026 },
2027 },
29f7c58a 2028 {
2029 # another example of '};' in ytInitialData
2030 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2031 'only_matching': True,
2032 },
2033 {
2034 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2035 'only_matching': True,
2036 },
545cc85d 2037 {
cc2db878 2038 # https://github.com/ytdl-org/youtube-dl/pull/28094
2039 'url': 'OtqTfy26tG0',
2040 'info_dict': {
2041 'id': 'OtqTfy26tG0',
2042 'ext': 'mp4',
2043 'title': 'Burn Out',
2044 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2045 'upload_date': '20141120',
2046 'uploader': 'The Cinematic Orchestra - Topic',
2047 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2048 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2049 'artist': 'The Cinematic Orchestra',
2050 'track': 'Burn Out',
2051 'album': 'Every Day',
976ae3ea 2052 'like_count': int,
2053 'live_status': 'not_live',
2054 'alt_title': 'Burn Out',
2055 'duration': 614,
2056 'age_limit': 0,
2057 'view_count': int,
2058 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2059 'creator': 'The Cinematic Orchestra',
2060 'channel': 'The Cinematic Orchestra',
2061 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2062 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2063 'availability': 'public',
2064 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2065 'categories': ['Music'],
2066 'playable_in_embed': True,
6c73052c 2067 'channel_follower_count': int
cc2db878 2068 },
2069 'params': {
2070 'skip_download': True,
2071 },
545cc85d 2072 },
bc2ca1bb 2073 {
2074 # controversial video, only works with bpctr when authenticated with cookies
2075 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2076 'only_matching': True,
2077 },
a1a7907b 2078 {
2079 # controversial video, requires bpctr/contentCheckOk
2080 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2081 'info_dict': {
2082 'id': 'SZJvDhaSDnc',
2083 'ext': 'mp4',
2084 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2085 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2086 'uploader': 'CBS Mornings',
11f9be09 2087 'uploader_id': 'CBSThisMorning',
a1a7907b 2088 'upload_date': '20140716',
976ae3ea 2089 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2090 'duration': 170,
2091 'categories': ['News & Politics'],
2092 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2093 'view_count': int,
2094 'channel': 'CBS Mornings',
2095 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2096 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2097 'age_limit': 18,
2098 'availability': 'needs_auth',
2099 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2100 'like_count': int,
2101 'live_status': 'not_live',
2102 'playable_in_embed': True,
6c73052c 2103 'channel_follower_count': int
a1a7907b 2104 }
2105 },
f7ad7160 2106 {
2107 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2108 'url': 'cBvYw8_A0vQ',
2109 'info_dict': {
2110 'id': 'cBvYw8_A0vQ',
2111 'ext': 'mp4',
2112 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2113 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2114 'upload_date': '20201120',
2115 'uploader': 'Walk around Japan',
2116 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2117 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2118 'duration': 1456,
2119 'categories': ['Travel & Events'],
2120 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2121 'view_count': int,
2122 'channel': 'Walk around Japan',
2123 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2124 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2125 'age_limit': 0,
2126 'availability': 'public',
2127 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2128 'live_status': 'not_live',
2129 'playable_in_embed': True,
6c73052c 2130 'channel_follower_count': int
f7ad7160 2131 },
2132 'params': {
2133 'skip_download': True,
2134 },
0fb983f6 2135 }, {
2136 # Has multiple audio streams
2137 'url': 'WaOKSUlf4TM',
2138 'only_matching': True
9297939e 2139 }, {
2140 # Requires Premium: has format 141 when requested using YTM url
2141 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2142 'only_matching': True
2143 }, {
120916da 2144 # multiple subtitles with same lang_code
2145 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2146 'only_matching': True,
109dd3b2 2147 }, {
2148 # Force use android client fallback
2149 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2150 'info_dict': {
2151 'id': 'YOelRv7fMxY',
11f9be09 2152 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2153 'ext': '3gp',
2154 'upload_date': '20210624',
2155 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2156 'uploader': 'colinfurze',
11f9be09 2157 'uploader_id': 'colinfurze',
109dd3b2 2158 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2159 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2160 'duration': 596,
2161 'categories': ['Entertainment'],
2162 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2163 'view_count': int,
2164 'channel': 'colinfurze',
2165 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2166 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2167 'age_limit': 0,
2168 'availability': 'public',
2169 'like_count': int,
2170 'live_status': 'not_live',
2171 'playable_in_embed': True,
6c73052c 2172 'channel_follower_count': int
109dd3b2 2173 },
2174 'params': {
2175 'format': '17', # 3gp format available on android
2176 'extractor_args': {'youtube': {'player_client': ['android']}},
2177 },
120916da 2178 },
109dd3b2 2179 {
2180 # Skip download of additional client configs (remix client config in this case)
2181 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2182 'only_matching': True,
2183 'params': {
2184 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2185 },
8fc54b12 2186 }, {
2187 # shorts
2188 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2189 'only_matching': True,
9222c381 2190 }, {
2191 'note': 'Storyboards',
2192 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2193 'info_dict': {
2194 'id': '5KLPxDtMqe8',
2195 'ext': 'mhtml',
2196 'format_id': 'sb0',
2197 'title': 'Your Brain is Plastic',
2198 'uploader_id': 'scishow',
2199 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2200 'upload_date': '20140324',
2201 'uploader': 'SciShow',
976ae3ea 2202 'like_count': int,
2203 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2204 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2205 'view_count': int,
2206 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2207 'playable_in_embed': True,
2208 'tags': 'count:12',
2209 'uploader_url': 'http://www.youtube.com/user/scishow',
2210 'availability': 'public',
2211 'channel': 'SciShow',
2212 'live_status': 'not_live',
2213 'duration': 248,
2214 'categories': ['Education'],
2215 'age_limit': 0,
6c73052c 2216 'channel_follower_count': int
9222c381 2217 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2218 }, {
2219 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2220 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2221 'info_dict': {
2222 'id': '2NUZ8W2llS4',
2223 'ext': 'mp4',
2224 'title': 'The NP that test your phone performance 🙂',
2225 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2226 'uploader': 'Leon Nguyen',
2227 'uploader_id': 'VNSXIII',
2228 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2229 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2230 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2231 'duration': 21,
2232 'view_count': int,
2233 'age_limit': 0,
2234 'categories': ['Gaming'],
2235 'tags': 'count:23',
2236 'playable_in_embed': True,
2237 'live_status': 'not_live',
2238 'upload_date': '20220103',
2239 'like_count': int,
2240 'availability': 'public',
2241 'channel': 'Leon Nguyen',
2242 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2243 'comment_count': int,
992f9a73 2244 'channel_follower_count': int
2245 }
1ff88b7a 2246 }, {
2247 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2248 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2249 'info_dict': {
2250 'id': '2NUZ8W2llS4',
2251 'ext': 'mp4',
2252 'title': 'The NP that test your phone performance 🙂',
2253 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2254 'uploader': 'Leon Nguyen',
2255 'uploader_id': 'VNSXIII',
2256 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2257 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2258 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2259 'duration': 21,
2260 'view_count': int,
2261 'age_limit': 0,
2262 'categories': ['Gaming'],
2263 'tags': 'count:23',
2264 'playable_in_embed': True,
2265 'live_status': 'not_live',
2266 'upload_date': '20220102',
2267 'like_count': int,
2268 'availability': 'public',
2269 'channel': 'Leon Nguyen',
2270 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2271 'comment_count': int,
2272 'channel_follower_count': int
2273 },
2274 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2275 }, {
2276 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2277 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2278 'info_dict': {
2279 'id': 'mzZzzBU6lrM',
2280 'ext': 'mp4',
2281 'title': 'I Met GeorgeNotFound In Real Life...',
2282 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2283 'uploader': 'Quackity',
2284 'uploader_id': 'QuackityHQ',
2285 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2286 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2287 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2288 'duration': 955,
2289 'view_count': int,
2290 'age_limit': 0,
2291 'categories': ['Entertainment'],
2292 'tags': 'count:26',
2293 'playable_in_embed': True,
2294 'live_status': 'not_live',
2295 'release_timestamp': 1641172509,
2296 'release_date': '20220103',
2297 'upload_date': '20220103',
2298 'like_count': int,
2299 'availability': 'public',
2300 'channel': 'Quackity',
2301 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2302 'channel_follower_count': int
2303 }
2304 },
2305 { # continuous livestream. Microformat upload date should be preferred.
2306 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2307 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2308 'info_dict': {
2309 'id': 'kgx4WGK0oNU',
2310 '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}',
2311 'ext': 'mp4',
2312 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2313 'availability': 'public',
2314 'age_limit': 0,
2315 'release_timestamp': 1637975704,
2316 'upload_date': '20210619',
2317 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2318 'live_status': 'is_live',
2319 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2320 'uploader': '阿鲍Abao',
2321 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2322 'channel': 'Abao in Tokyo',
2323 'channel_follower_count': int,
2324 'release_date': '20211127',
2325 'tags': 'count:39',
2326 'categories': ['People & Blogs'],
2327 'like_count': int,
2328 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2329 'view_count': int,
2330 'playable_in_embed': True,
2331 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2332 'concurrent_view_count': int,
992f9a73 2333 },
2334 'params': {'skip_download': True}
6e634cbe 2335 }, {
2336 # Story. Requires specific player params to work.
ee27297f 2337 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2338 'info_dict': {
ee27297f 2339 'id': 'vv8qTUWmulI',
6e634cbe 2340 'ext': 'mp4',
ee27297f 2341 'availability': 'unlisted',
2342 'view_count': int,
2343 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2344 'upload_date': '20220526',
2345 'categories': ['Education'],
2346 'title': 'Story',
2347 'channel': 'IT\'S HISTORY',
2348 'description': '',
2349 'uploader_id': 'BlastfromthePast',
2350 'duration': 12,
2351 'uploader': 'IT\'S HISTORY',
6e634cbe 2352 'playable_in_embed': True,
6e634cbe 2353 'age_limit': 0,
6e634cbe 2354 'live_status': 'not_live',
ee27297f 2355 'tags': [],
2356 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2357 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2358 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2359 },
2360 'skip': 'stories get removed after some period of time',
ee27297f 2361 }, {
2362 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2363 'info_dict': {
2364 'id': 'tjjjtzRLHvA',
2365 'ext': 'mp4',
2366 'title': 'ハッシュタグ無し };if window.ytcsi',
2367 'upload_date': '20220323',
2368 'like_count': int,
2369 'availability': 'unlisted',
2370 'channel': 'nao20010128nao',
2371 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2372 'age_limit': 0,
2373 'uploader': 'nao20010128nao',
2374 'uploader_id': 'nao20010128nao',
2375 'categories': ['Music'],
6e634cbe 2376 'view_count': int,
2377 'description': '',
ee27297f 2378 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2379 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2380 'live_status': 'not_live',
2381 'playable_in_embed': True,
2382 'channel_follower_count': int,
2383 'duration': 6,
2384 'tags': [],
2385 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2386 }
c26f9b99 2387 }, {
2388 # Prefer primary title+description language metadata by default
2389 # Do not prefer translated description if primary is empty
2390 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2391 'info_dict': {
2392 'id': 'el3E4MbxRqQ',
2393 'ext': 'mp4',
2394 'title': 'dlp test video 2 - primary sv no desc',
2395 'description': '',
2396 'channel': 'cole-dlp-test-acc',
2397 'tags': [],
2398 'view_count': int,
2399 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2400 'like_count': int,
2401 'playable_in_embed': True,
2402 'availability': 'unlisted',
2403 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2404 'age_limit': 0,
2405 'duration': 5,
2406 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2407 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2408 'live_status': 'not_live',
2409 'upload_date': '20220908',
2410 'categories': ['People & Blogs'],
2411 'uploader': 'cole-dlp-test-acc',
2412 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2413 },
2414 'params': {'skip_download': True}
2415 }, {
2416 # Extractor argument: prefer translated title+description
2417 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2418 'info_dict': {
2419 'id': 'gHKT4uU8Zng',
2420 'ext': 'mp4',
2421 'channel': 'cole-dlp-test-acc',
2422 'tags': [],
2423 'duration': 5,
2424 'live_status': 'not_live',
2425 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2426 'upload_date': '20220728',
2427 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2428 'view_count': int,
2429 'categories': ['People & Blogs'],
2430 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2431 'title': 'dlp test video title translated (fr)',
2432 'availability': 'public',
2433 'uploader': 'cole-dlp-test-acc',
2434 'age_limit': 0,
2435 'description': 'dlp test video description translated (fr)',
2436 'playable_in_embed': True,
2437 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2438 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2439 },
2440 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2441 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2442 }, {
2443 'note': '6 channel audio',
2444 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2445 'only_matching': True,
6e634cbe 2446 }
2eb88d95
PH
2447 ]
2448
f2e8dbcc 2449 _WEBPAGE_TESTS = [
2450 # YouTube <object> embed
2451 {
2452 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2453 'md5': '873c81d308b979f0e23ee7e620b312a3',
2454 'info_dict': {
2455 'id': 'msN87y-iEx0',
2456 'ext': 'mp4',
2457 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2458 'upload_date': '20080526',
2459 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2460 'uploader': 'Christopher Sykes',
2461 'uploader_id': 'ChristopherJSykes',
2462 'age_limit': 0,
2463 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2464 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2465 'playable_in_embed': True,
2466 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2467 'like_count': int,
2468 'comment_count': int,
2469 'channel': 'Christopher Sykes',
2470 'live_status': 'not_live',
2471 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2472 'availability': 'public',
2473 'duration': 195,
2474 'view_count': int,
2475 'categories': ['Science & Technology'],
2476 'channel_follower_count': int,
2477 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2478 },
2479 'params': {
2480 'skip_download': True,
2481 }
2482 },
2483 ]
2484
201c1459 2485 @classmethod
2486 def suitable(cls, url):
4dfbf869 2487 from ..utils import parse_qs
2488
201c1459 2489 qs = parse_qs(url)
2490 if qs.get('list', [None])[0]:
2491 return False
86e5f3ed 2492 return super().suitable(url)
201c1459 2493
e0df6211 2494 def __init__(self, *args, **kwargs):
86e5f3ed 2495 super().__init__(*args, **kwargs)
545cc85d 2496 self._code_cache = {}
83799698 2497 self._player_cache = {}
e0df6211 2498
4d37720a 2499 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2500 lock = threading.Lock()
185bf310 2501 start_time = time.time()
adbc4ec4
THD
2502 formats = [f for f in formats if f.get('is_from_start')]
2503
185bf310 2504 def refetch_manifest(format_id, delay):
2505 nonlocal formats, start_time, is_live
2506 if time.time() <= start_time + delay:
adbc4ec4
THD
2507 return
2508
2509 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2510 video_details = traverse_obj(
2511 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2512 microformats = traverse_obj(
2513 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2514 expected_type=dict, default=[])
4d37720a
L
2515 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2516 is_live = live_status == 'is_live'
185bf310 2517 start_time = time.time()
adbc4ec4 2518
185bf310 2519 def mpd_feed(format_id, delay):
adbc4ec4
THD
2520 """
2521 @returns (manifest_url, manifest_stream_number, is_live) or None
2522 """
2523 with lock:
185bf310 2524 refetch_manifest(format_id, delay)
adbc4ec4
THD
2525
2526 f = next((f for f in formats if f['format_id'] == format_id), None)
2527 if not f:
185bf310 2528 if not is_live:
2529 self.to_screen(f'{video_id}: Video is no longer live')
2530 else:
2531 self.report_warning(
2532 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2533 return None
2534 return f['manifest_url'], f['manifest_stream_number'], is_live
2535
2536 for f in formats:
4d37720a
L
2537 f['is_live'] = is_live
2538 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2539 live_start_time, mpd_feed, not is_live and f.copy())
2540 if is_live:
2541 f['fragments'] = gen
2542 f['protocol'] = 'http_dash_segments_generator'
2543 else:
2544 f['fragments'] = LazyList(gen({}))
2545 del f['is_from_start']
adbc4ec4 2546
4d37720a 2547 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2548 FETCH_SPAN, MAX_DURATION = 5, 432000
2549
2550 mpd_url, stream_number, is_live = None, None, True
2551
2552 begin_index = 0
2553 download_start_time = ctx.get('start') or time.time()
2554
2555 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2556 if lack_early_segments:
2557 self.report_warning(bug_reports_message(
2558 'Starting download from the last 120 hours of the live stream since '
2559 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2560 lack_early_segments = True
2561
2562 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2563 fragments, fragment_base_url = None, None
2564
a539f065 2565 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2566 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2567 # Obtain from MPD's maximum seq value
2568 old_mpd_url = mpd_url
185bf310 2569 last_error = ctx.pop('last_error', None)
14f25df2 2570 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2571 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2572 or (mpd_url, stream_number, False))
2573 if not refresh_sequence:
2574 if expire_fast and not is_live:
2575 return False, last_seq
2576 elif old_mpd_url == mpd_url:
2577 return True, last_seq
4d37720a
L
2578 if manifestless_orig_fmt:
2579 fmt_info = manifestless_orig_fmt
2580 else:
2581 try:
2582 fmts, _ = self._extract_mpd_formats_and_subtitles(
2583 mpd_url, None, note=False, errnote=False, fatal=False)
2584 except ExtractorError:
2585 fmts = None
2586 if not fmts:
2587 no_fragment_score += 2
2588 return False, last_seq
2589 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2590 fragments = fmt_info['fragments']
2591 fragment_base_url = fmt_info['fragment_base_url']
2592 assert fragment_base_url
2593
2594 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2595 return True, _last_seq
2596
4d37720a 2597 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2598 while is_live:
2599 fetch_time = time.time()
2600 if no_fragment_score > 30:
2601 return
2602 if last_segment_url:
2603 # Obtain from "X-Head-Seqnum" header value from each segment
2604 try:
2605 urlh = self._request_webpage(
2606 last_segment_url, None, note=False, errnote=False, fatal=False)
2607 except ExtractorError:
2608 urlh = None
2609 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2610 if last_seq is None:
a539f065 2611 no_fragment_score += 2
adbc4ec4
THD
2612 last_segment_url = None
2613 continue
2614 else:
a539f065
LNO
2615 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2616 no_fragment_score += 2
185bf310 2617 if not should_continue:
adbc4ec4
THD
2618 continue
2619
2620 if known_idx > last_seq:
2621 last_segment_url = None
2622 continue
2623
2624 last_seq += 1
2625
2626 if begin_index < 0 and known_idx < 0:
2627 # skip from the start when it's negative value
2628 known_idx = last_seq + begin_index
2629 if lack_early_segments:
2630 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2631 try:
2632 for idx in range(known_idx, last_seq):
2633 # do not update sequence here or you'll get skipped some part of it
a539f065 2634 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2635 if not should_continue:
adbc4ec4
THD
2636 known_idx = idx - 1
2637 raise ExtractorError('breaking out of outer loop')
2638 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2639 yield {
2640 'url': last_segment_url,
36195c44 2641 'fragment_count': last_seq,
adbc4ec4
THD
2642 }
2643 if known_idx == last_seq:
2644 no_fragment_score += 5
2645 else:
2646 no_fragment_score = 0
2647 known_idx = last_seq
2648 except ExtractorError:
2649 continue
2650
4d37720a
L
2651 if manifestless_orig_fmt:
2652 # Stop at the first iteration if running for post-live manifestless;
2653 # fragment count no longer increase since it starts
2654 break
2655
adbc4ec4
THD
2656 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2657
b6de707d 2658 def _extract_player_url(self, *ytcfgs, webpage=None):
2659 player_url = traverse_obj(
2660 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2661 get_all=False, expected_type=str)
11f9be09 2662 if not player_url:
b6de707d 2663 return
60f393e4 2664 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2665
b6de707d 2666 def _download_player_url(self, video_id, fatal=False):
2667 res = self._download_webpage(
2668 'https://www.youtube.com/iframe_api',
2669 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2670 if res:
2671 player_version = self._search_regex(
2672 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2673 if player_version:
2674 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2675
60064c53
PH
2676 def _signature_cache_id(self, example_sig):
2677 """ Return a string representation of a signature """
14f25df2 2678 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2679
e40c758c
S
2680 @classmethod
2681 def _extract_player_info(cls, player_url):
2682 for player_re in cls._PLAYER_INFO_RE:
2683 id_m = re.search(player_re, player_url)
2684 if id_m:
2685 break
2686 else:
c081b35c 2687 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2688 return id_m.group('id')
e40c758c 2689
404f611f 2690 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2691 player_id = self._extract_player_info(player_url)
2692 if player_id not in self._code_cache:
1276a43a 2693 code = self._download_webpage(
109dd3b2 2694 player_url, video_id, fatal=fatal,
2695 note='Downloading player ' + player_id,
2696 errnote='Download of %s failed' % player_url)
1276a43a 2697 if code:
2698 self._code_cache[player_id] = code
404f611f 2699 return self._code_cache.get(player_id)
109dd3b2 2700
e40c758c 2701 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2702 player_id = self._extract_player_info(player_url)
e0df6211 2703
c4417ddb 2704 # Read from filesystem cache
86e5f3ed 2705 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2706 assert os.path.basename(func_id) == func_id
a0e07d31 2707
ae61d108 2708 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2709 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2710
580ce007 2711 if not cache_spec:
2712 code = self._load_player(video_id, player_url)
404f611f 2713 if code:
109dd3b2 2714 res = self._parse_sig_js(code)
ac668111 2715 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2716 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2717 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2718
2719 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2720
60064c53 2721 def _print_sig_code(self, func, example_sig):
404f611f 2722 if not self.get_param('youtube_print_sig_code'):
2723 return
2724
edf3e38e
PH
2725 def gen_sig_code(idxs):
2726 def _genslice(start, end, step):
78caa52a 2727 starts = '' if start == 0 else str(start)
8bcc8756 2728 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2729 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2730 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2731
2732 step = None
7af808a5
PH
2733 # Quelch pyflakes warnings - start will be set when step is set
2734 start = '(Never used)'
edf3e38e
PH
2735 for i, prev in zip(idxs[1:], idxs[:-1]):
2736 if step is not None:
2737 if i - prev == step:
2738 continue
2739 yield _genslice(start, prev, step)
2740 step = None
2741 continue
2742 if i - prev in [-1, 1]:
2743 step = i - prev
2744 start = prev
2745 continue
2746 else:
78caa52a 2747 yield 's[%d]' % prev
edf3e38e 2748 if step is None:
78caa52a 2749 yield 's[%d]' % i
edf3e38e
PH
2750 else:
2751 yield _genslice(start, i, step)
2752
ac668111 2753 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2754 cache_res = func(test_string)
edf3e38e 2755 cache_spec = [ord(c) for c in cache_res]
78caa52a 2756 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2757 signature_id_tuple = '(%s)' % (
14f25df2 2758 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2759 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2760 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2761 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2762
e0df6211
PH
2763 def _parse_sig_js(self, jscode):
2764 funcname = self._search_regex(
abefc03f
S
2765 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2766 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
2767 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2768 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2769 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}\(a,\d+\)',
2770 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 2771 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2772 # Obsolete patterns
2773 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2774 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2775 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2776 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2777 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2778 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2779 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2780 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2781 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2782
2783 jsi = JSInterpreter(jscode)
2784 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2785 return lambda s: initial_function([s])
2786
580ce007 2787 def _cached(self, func, *cache_id):
2788 def inner(*args, **kwargs):
2789 if cache_id not in self._player_cache:
2790 try:
2791 self._player_cache[cache_id] = func(*args, **kwargs)
2792 except ExtractorError as e:
2793 self._player_cache[cache_id] = e
2794 except Exception as e:
2795 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2796
2797 ret = self._player_cache[cache_id]
2798 if isinstance(ret, Exception):
2799 raise ret
2800 return ret
2801 return inner
2802
545cc85d 2803 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2804 """Turn the encrypted s field into a working signature"""
580ce007 2805 extract_sig = self._cached(
2806 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2807 func = extract_sig(video_id, player_url, s)
2808 self._print_sig_code(func, s)
2809 return func(s)
404f611f 2810
2811 def _decrypt_nsig(self, s, video_id, player_url):
2812 """Turn the encrypted n field into a working signature"""
2813 if player_url is None:
2814 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2815 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2816
b505e851 2817 try:
2818 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2819 except ExtractorError as e:
2820 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 2821 if self.get_param('youtube_print_sig_code'):
2822 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2823
25836db6 2824 try:
2825 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2826 ret = extract_nsig(jsi, func_code)(s)
2827 except JSInterpreter.Exception as e:
2828 try:
992dc6b4 2829 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2830 except ExtractorError:
2831 raise e
2832 self.report_warning(
2833 f'Native nsig extraction failed: Trying with PhantomJS\n'
2834 f' n = {s} ; player = {player_url}', video_id)
2835 self.write_debug(e)
2836
2837 args, func_body = func_code
2838 ret = jsi.execute(
2839 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2840 video_id=video_id, note='Executing signature code').strip()
580ce007 2841
2842 self.write_debug(f'Decrypted nsig {s} => {ret}')
2843 return ret
2844
90a1df30 2845 def _extract_n_function_name(self, jscode):
2846 funcname, idx = self._search_regex(
2847 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2848 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2849 if not idx:
2850 return funcname
2851
2852 return json.loads(js_to_json(self._search_regex(
2853 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2854 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2855
580ce007 2856 def _extract_n_function_code(self, video_id, player_url):
404f611f 2857 player_id = self._extract_player_info(player_url)
05deb747 2858 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 2859 jscode = func_code or self._load_player(video_id, player_url)
2860 jsi = JSInterpreter(jscode)
404f611f 2861
2862 if func_code:
580ce007 2863 return jsi, player_id, func_code
404f611f 2864
b505e851 2865 func_name = self._extract_n_function_name(jscode)
2866
2867 # For redundancy
2868 func_code = self._search_regex(
2869 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
2870 # NB: The end of the regex is intentionally kept strict
2871 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
2872 jscode, 'nsig function', group=('var', 'code'), default=None)
2873 if func_code:
2874 func_code = ([func_code[0]], func_code[1])
2875 else:
2876 self.write_debug('Extracting nsig function with jsinterp')
2877 func_code = jsi.extract_function_code(func_name)
2878
580ce007 2879 self.cache.store('youtube-nsig', player_id, func_code)
2880 return jsi, player_id, func_code
2881
2882 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 2883 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2884
580ce007 2885 def extract_nsig(s):
25836db6 2886 try:
2887 ret = func([s])
2888 except JSInterpreter.Exception:
2889 raise
2890 except Exception as e:
2891 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2892
f6ca640b 2893 if ret.startswith('enhanced_except_'):
25836db6 2894 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 2895 return ret
580ce007 2896
2897 return extract_nsig
e0df6211 2898
109dd3b2 2899 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2900 """
2901 Extract signatureTimestamp (sts)
2902 Required to tell API what sig/player version is in use.
2903 """
2904 sts = None
2905 if isinstance(ytcfg, dict):
2906 sts = int_or_none(ytcfg.get('STS'))
2907
2908 if not sts:
2909 # Attempt to extract from player
2910 if player_url is None:
2911 error_msg = 'Cannot extract signature timestamp without player_url.'
2912 if fatal:
2913 raise ExtractorError(error_msg)
2914 self.report_warning(error_msg)
2915 return
404f611f 2916 code = self._load_player(video_id, player_url, fatal=fatal)
2917 if code:
109dd3b2 2918 sts = int_or_none(self._search_regex(
2919 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2920 'JS player signature timestamp', group='sts', fatal=fatal))
2921 return sts
2922
11f9be09 2923 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2924 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2925 label = 'fully ' if is_full else ''
2926 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2927 expected_type=url_or_none)
2928 if not url:
2929 self.report_warning(f'Unable to mark {label}watched')
2930 return
14f25df2 2931 parsed_url = urllib.parse.urlparse(url)
2932 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2933
2934 # cpn generation algorithm is reverse engineered from base.js.
2935 # In fact it works even with dummy cpn.
2936 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2937 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2938
2939 # # more consistent results setting it to right before the end
2940 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2941
2942 qs.update({
2943 'ver': ['2'],
2944 'cpn': [cpn],
2945 'cmt': video_length,
2946 'el': 'detailpage', # otherwise defaults to "shorts"
2947 })
2948
2949 if is_full:
2950 # these seem to mark watchtime "history" in the real world
2951 # they're required, so send in a single value
2952 qs.update({
2953 'st': video_length,
2954 'et': video_length,
2955 })
2956
14f25df2 2957 url = urllib.parse.urlunparse(
2958 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2959
2960 self._download_webpage(
2961 url, video_id, f'Marking {label}watched',
2962 'Unable to mark watched', fatal=False)
d77ab8e2 2963
bfd973ec 2964 @classmethod
2965 def _extract_from_webpage(cls, url, webpage):
2966 # Invidious Instances
2967 # https://github.com/yt-dlp/yt-dlp/issues/195
2968 # https://github.com/iv-org/invidious/pull/1730
2969 mobj = re.search(
2970 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2971 webpage)
2972 if mobj:
2973 yield cls.url_result(mobj.group('url'), cls)
2974 raise cls.StopExtraction()
2975
2976 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2977
2978 # lazyYT YouTube embed
bfd973ec 2979 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2980 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2981
2982 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2983 for m in re.findall(r'''(?x)<div[^>]+
2984 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2985 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2986 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2987
97665381
PH
2988 @classmethod
2989 def extract_id(cls, url):
ae61d108 2990 video_id = cls.get_temp_id(url)
2991 if not video_id:
2992 raise ExtractorError(f'Invalid URL: {url}')
2993 return video_id
c5e8d7af 2994
7c365c21 2995 def _extract_chapters_from_json(self, data, duration):
2996 chapter_list = traverse_obj(
2997 data, (
2998 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2999 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3000 ), expected_type=list)
3001
3002 return self._extract_chapters(
3003 chapter_list,
3004 chapter_time=lambda chapter: float_or_none(
3005 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3006 chapter_title=lambda chapter: traverse_obj(
3007 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3008 duration=duration)
3009
3010 def _extract_chapters_from_engagement_panel(self, data, duration):
3011 content_list = traverse_obj(
8bdd16b4 3012 data,
7c365c21 3013 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 3014 expected_type=list, default=[])
052e1350 3015 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3016 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3017
1890fc63 3018 return next(filter(None, (
3019 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3020 chapter_time, chapter_title, duration)
3021 for contents in content_list)), [])
7c365c21 3022
1890fc63 3023 def _extract_chapters_from_description(self, description, duration):
3024 return self._extract_chapters(
3025 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
3026 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
3027 duration=duration, strict=False)
84213ea8 3028
1890fc63 3029 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3030 if not duration:
3031 return
3032 chapter_list = [{
3033 'start_time': chapter_time(chapter),
3034 'title': chapter_title(chapter),
3035 } for chapter in chapter_list or []]
3036 if not strict:
3037 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3038
a3976e07 3039 chapters = [{'start_time': 0}]
1890fc63 3040 for idx, chapter in enumerate(chapter_list):
a3976e07 3041 if chapter['start_time'] is None:
1890fc63 3042 self.report_warning(f'Incomplete chapter {idx}')
3043 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3044 chapters.append(chapter)
709ee214 3045 elif chapter not in chapters:
3046 self.report_warning(
3047 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3048 return chapters[1:]
84213ea8 3049
a1c5d2ca
M
3050 def _extract_comment(self, comment_renderer, parent=None):
3051 comment_id = comment_renderer.get('commentId')
3052 if not comment_id:
3053 return
fe93e2c4 3054
052e1350 3055 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3056
c26f9b99 3057 # Timestamp is an estimate calculated from the current time and time_text
3058 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3059 timestamp = self._parse_time_text(time_text)
3060
052e1350 3061 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3062 author_id = try_get(comment_renderer,
14f25df2 3063 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3064
49bd8c66 3065 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3066 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3067 author_thumbnail = try_get(comment_renderer,
14f25df2 3068 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3069
3070 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3071 is_favorited = 'creatorHeart' in (try_get(
3072 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3073 return {
3074 'id': comment_id,
3075 'text': text,
d92f5d5a 3076 'timestamp': timestamp,
a1c5d2ca
M
3077 'time_text': time_text,
3078 'like_count': votes,
97524332 3079 'is_favorited': is_favorited,
a1c5d2ca
M
3080 'author': author,
3081 'author_id': author_id,
3082 'author_thumbnail': author_thumbnail,
3083 'author_is_uploader': author_is_uploader,
3084 'parent': parent or 'root'
3085 }
3086
46383212 3087 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3088
3089 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3090
3091 def extract_header(contents):
2d6659b9 3092 _continuation = None
3093 for content in contents:
46383212 3094 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3095 expected_comment_count = self._get_count(
3096 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3097
2d6659b9 3098 if expected_comment_count:
46383212 3099 tracker['est_total'] = expected_comment_count
3100 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3101 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3102
3103 sort_menu_item = try_get(
3104 comments_header_renderer,
3105 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3106 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3107
3108 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3109 if not _continuation:
3110 continue
3111
46383212 3112 sort_text = str_or_none(sort_menu_item.get('title'))
3113 if not sort_text:
2d6659b9 3114 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3115 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3116 break
a2160aa4 3117 return _continuation
a1c5d2ca 3118
2d6659b9 3119 def extract_thread(contents):
a1c5d2ca 3120 if not parent:
46383212 3121 tracker['current_page_thread'] = 0
a1c5d2ca 3122 for content in contents:
46383212 3123 if not parent and tracker['total_parent_comments'] >= max_parents:
3124 yield
a1c5d2ca 3125 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3126 comment_renderer = get_first(
3127 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3128 expected_type=dict, default={})
a1c5d2ca 3129
a1c5d2ca
M
3130 comment = self._extract_comment(comment_renderer, parent)
3131 if not comment:
3132 continue
46383212 3133
3134 tracker['running_total'] += 1
3135 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3136 yield comment
46383212 3137
a1c5d2ca
M
3138 # Attempt to get the replies
3139 comment_replies_renderer = try_get(
3140 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3141
3142 if comment_replies_renderer:
46383212 3143 tracker['current_page_thread'] += 1
a1c5d2ca 3144 comment_entries_iter = self._comment_entries(
99e9e001 3145 comment_replies_renderer, ytcfg, video_id,
46383212 3146 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3147 yield from itertools.islice(comment_entries_iter, min(
3148 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3149
46383212 3150 # Keeps track of counts across recursive calls
3151 if not tracker:
3152 tracker = dict(
3153 running_total=0,
3154 est_total=0,
3155 current_page_thread=0,
3156 total_parent_comments=0,
3157 total_reply_comments=0)
3158
3159 # TODO: Deprecated
2d6659b9 3160 # YouTube comments have a max depth of 2
46383212 3161 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3162 if max_depth:
da4db748 3163 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3164 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3165 if max_depth == 1 and parent:
3166 return
a1c5d2ca 3167
46383212 3168 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3169 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3170
46383212 3171 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3172
46383212 3173 response = None
6e634cbe 3174 is_forced_continuation = False
2d6659b9 3175 is_first_continuation = parent is None
6e634cbe 3176 if is_first_continuation and not continuation:
3177 # Sometimes you can get comments by generating the continuation yourself,
3178 # even if YouTube initially reports them being disabled - e.g. stories comments.
3179 # Note: if the comment section is actually disabled, YouTube may return a response with
3180 # required check_get_keys missing. So we will disable that check initially in this case.
3181 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3182 is_forced_continuation = True
a1c5d2ca
M
3183
3184 for page_num in itertools.count(0):
3185 if not continuation:
3186 break
46383212 3187 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3188 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3189 if page_num == 0:
3190 if is_first_continuation:
3191 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3192 else:
2d6659b9 3193 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3194 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3195 else:
3196 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3197 ' ' if parent else '', ' replies' if parent else '',
3198 page_num, comment_prog_str)
3199
3200 response = self._extract_response(
fe93e2c4 3201 item_id=None, query=continuation,
2d6659b9 3202 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 3203 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3204 is_forced_continuation = False
46383212 3205 continuation_contents = traverse_obj(
3206 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3207
2d6659b9 3208 continuation = None
46383212 3209 for continuation_section in continuation_contents:
3210 continuation_items = traverse_obj(
3211 continuation_section,
3212 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3213 get_all=False, expected_type=list) or []
3214 if is_first_continuation:
3215 continuation = extract_header(continuation_items)
3216 is_first_continuation = False
2d6659b9 3217 if continuation:
a1c5d2ca 3218 break
46383212 3219 continue
a1c5d2ca 3220
46383212 3221 for entry in extract_thread(continuation_items):
3222 if not entry:
3223 return
3224 yield entry
3225 continuation = self._extract_continuation({'contents': continuation_items})
3226 if continuation:
2d6659b9 3227 break
a1c5d2ca 3228
6e634cbe 3229 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3230 if message and not parent and tracker['running_total'] == 0:
3231 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3232
3233 @staticmethod
3234 def _generate_comment_continuation(video_id):
3235 """
3236 Generates initial comment section continuation token from given video id
3237 """
3238 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3239 return base64.b64encode(token.encode()).decode()
3240
a2160aa4 3241 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3242 """Entry for comment extraction"""
2d6659b9 3243 def _real_comment_extract(contents):
aae16f6e 3244 renderer = next((
3245 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3246 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3247 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3248
a2160aa4 3249 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3250 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3251
109dd3b2 3252 @staticmethod
99e9e001 3253 def _get_checkok_params():
3254 return {'contentCheckOk': True, 'racyCheckOk': True}
3255
3256 @classmethod
3257 def _generate_player_context(cls, sts=None):
109dd3b2 3258 context = {
3259 'html5Preference': 'HTML5_PREF_WANTS',
3260 }
3261 if sts is not None:
3262 context['signatureTimestamp'] = sts
3263 return {
3264 'playbackContext': {
3265 'contentPlaybackContext': context
a1a7907b 3266 },
99e9e001 3267 **cls._get_checkok_params()
109dd3b2 3268 }
3269
e7e94f2a
D
3270 @staticmethod
3271 def _is_agegated(player_response):
3272 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3273 return True
e7e94f2a
D
3274
3275 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3276 AGE_GATE_REASONS = (
3277 'confirm your age', 'age-restricted', 'inappropriate', # reason
3278 'age_verification_required', 'age_check_required', # status
3279 )
3280 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3281
3282 @staticmethod
3283 def _is_unplayable(player_response):
3284 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3285
50ac0e54 3286 _STORY_PLAYER_PARAMS = '8AEB'
3287
3288 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3289
11f9be09 3290 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3291 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3292 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3293 headers = self.generate_api_headers(
99e9e001 3294 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3295
6e634cbe 3296 yt_query = {
3297 'videoId': video_id,
6e634cbe 3298 }
50ac0e54 3299 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3300 yt_query['params'] = self._STORY_PLAYER_PARAMS
3301
11f9be09 3302 yt_query.update(self._generate_player_context(sts))
3303 return self._extract_response(
3304 item_id=video_id, ep='player', query=yt_query,
379e44ed 3305 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3306 default_client=client,
11f9be09 3307 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3308 ) or None
3309
11f9be09 3310 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3311 requested_clients = []
d0d012d4 3312 default = ['android', 'web']
000c15a4 3313 allowed_clients = sorted(
86e5f3ed 3314 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3315 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3316 for client in self._configuration_arg('player_client'):
3317 if client in allowed_clients:
3318 requested_clients.append(client)
d0d012d4 3319 elif client == 'default':
3320 requested_clients.extend(default)
b4c055ba 3321 elif client == 'all':
3322 requested_clients.extend(allowed_clients)
3323 else:
3324 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3325 if not requested_clients:
d0d012d4 3326 requested_clients = default
cf7e015f 3327
11f9be09 3328 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3329 requested_clients.extend(
e7e94f2a 3330 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3331
11f9be09 3332 return orderedSet(requested_clients)
cf7e015f 3333
50ac0e54 3334 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3335 initial_pr = None
3336 if webpage:
b7c47b74 3337 initial_pr = self._search_json(
3338 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3339
ae729626 3340 all_clients = set(clients)
c0bc527b 3341 clients = clients[::-1]
b6de707d 3342 prs = []
e7e94f2a 3343
ae729626 3344 def append_client(*client_names):
e7870111 3345 """ Append the first client name that exists but not already used """
ae729626 3346 for client_name in client_names:
e7870111
D
3347 actual_client = _split_innertube_client(client_name)[0]
3348 if actual_client in INNERTUBE_CLIENTS:
3349 if actual_client not in all_clients:
ae729626 3350 clients.append(client_name)
e7870111
D
3351 all_clients.add(actual_client)
3352 return
e7e94f2a 3353
379e44ed 3354 # Android player_response does not have microFormats which are needed for
3355 # extraction of some data. So we return the initial_pr with formats
3356 # stripped out even if not requested by the user
3357 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3358 if initial_pr:
3359 pr = dict(initial_pr)
3360 pr['streamingData'] = None
b6de707d 3361 prs.append(pr)
379e44ed 3362
3363 last_error = None
b6de707d 3364 tried_iframe_fallback = False
3365 player_url = None
c0bc527b 3366 while clients:
e7870111 3367 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3368 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3369 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3370 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3371
b6de707d 3372 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3373 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3374 if 'js' in self._configuration_arg('player_skip'):
3375 require_js_player = False
3376 player_url = None
3377
3378 if not player_url and not tried_iframe_fallback and require_js_player:
3379 player_url = self._download_player_url(video_id)
3380 tried_iframe_fallback = True
3381
379e44ed 3382 try:
3383 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3384 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3385 except ExtractorError as e:
3386 if last_error:
3387 self.report_warning(last_error)
3388 last_error = e
3389 continue
3390
11f9be09 3391 if pr:
a3e96421 3392 # YouTube may return a different video player response than expected.
3393 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3394 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3395 if pr_video_id and pr_video_id != video_id:
3396 self.report_warning(
c7dcf0b3 3397 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3398 else:
3399 prs.append(pr)
c0bc527b 3400
e7e94f2a 3401 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3402 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3403 append_client(f'{base_client}_creator')
e7e94f2a 3404 elif self._is_agegated(pr):
e7870111
D
3405 if variant == 'tv_embedded':
3406 append_client(f'{base_client}_embedded')
3407 elif not variant:
3408 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3409
379e44ed 3410 if last_error:
b6de707d 3411 if not len(prs):
379e44ed 3412 raise last_error
3413 self.report_warning(last_error)
b6de707d 3414 return prs, player_url
11f9be09 3415
4d37720a
L
3416 def _needs_live_processing(self, live_status, duration):
3417 if (live_status == 'is_live' and self.get_param('live_from_start')
3418 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3419 return live_status
3420
3421 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a0bb6ce5 3422 itags, stream_ids = {}, []
b25cac65 3423 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3424 q = qualities([
2a9c6dcd 3425 # Normally tiny is the smallest video-only formats. But
3426 # audio-only formats with unknown quality may get tagged as tiny
3427 'tiny',
3428 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3429 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3430 ])
11f9be09 3431 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3432
545cc85d 3433 for fmt in streaming_formats:
727029c5 3434 if fmt.get('targetDurationSec'):
545cc85d 3435 continue
321bf820 3436
cc2db878 3437 itag = str_or_none(fmt.get('itag'))
9297939e 3438 audio_track = fmt.get('audioTrack') or {}
3439 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3440 if stream_id in stream_ids:
3441 continue
3442
cc2db878 3443 quality = fmt.get('quality')
2a9c6dcd 3444 height = int_or_none(fmt.get('height'))
d3fc8074 3445 if quality == 'tiny' or not quality:
3446 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3447 # The 3gp format (17) in android client has a quality of "small",
3448 # but is actually worse than other formats
3449 if itag == '17':
3450 quality = 'tiny'
3451 if quality:
3452 if itag:
3453 itag_qualities[itag] = quality
3454 if height:
3455 res_qualities[height] = quality
cc2db878 3456 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3457 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3458 # number of fragment that would subsequently requested with (`&sq=N`)
3459 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3460 continue
3461
545cc85d 3462 fmt_url = fmt.get('url')
3463 if not fmt_url:
14f25df2 3464 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3465 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3466 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3467 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3468 continue
52023f12 3469 try:
3470 fmt_url += '&%s=%s' % (
3471 traverse_obj(sc, ('sp', -1)) or 'signature',
3472 self._decrypt_signature(encrypted_sig, video_id, player_url)
3473 )
3474 except ExtractorError as e:
580ce007 3475 self.report_warning('Signature extraction failed: Some formats may be missing',
3476 video_id=video_id, only_once=True)
52023f12 3477 self.write_debug(e, only_once=True)
201e9eaa 3478 continue
545cc85d 3479
404f611f 3480 query = parse_qs(fmt_url)
3481 throttled = False
b2916526 3482 if query.get('n'):
404f611f 3483 try:
580ce007 3484 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3485 fmt_url = update_url_query(fmt_url, {
580ce007 3486 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3487 })
404f611f 3488 except ExtractorError as e:
25836db6 3489 phantomjs_hint = ''
3490 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3491 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3492 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3493 if player_url:
3494 self.report_warning(
3495 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3496 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3497 self.write_debug(e, only_once=True)
3498 else:
3499 self.report_warning(
3500 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3501 video_id=video_id, only_once=True)
404f611f 3502 throttled = True
3503
545cc85d 3504 if itag:
a0bb6ce5 3505 itags[itag] = 'https'
9297939e 3506 stream_ids.append(stream_id)
3507
0ad92dfb 3508 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3509 language_preference = (
3510 10 if audio_track.get('audioIsDefault') and 10
3511 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3512 else -1)
0ad92dfb 3513 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3514 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3515 # Make sure to avoid false positives with small duration differences.
62b58c09 3516 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3517 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3518 if is_damaged:
0f06bcd7 3519 self.report_warning(
3520 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3521 dct = {
3522 'asr': int_or_none(fmt.get('audioSampleRate')),
3523 'filesize': int_or_none(fmt.get('contentLength')),
3524 'format_id': itag,
34921b43 3525 'format_note': join_nonempty(
26e8e044 3526 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3527 ' (default)' if language_preference > 0 else ''),
404f611f 3528 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3529 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3530 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3531 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3532 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3533 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3534 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3535 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3536 'height': height,
dca3ff4a 3537 'quality': q(quality),
727029c5 3538 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3539 'tbr': tbr,
545cc85d 3540 'url': fmt_url,
2a9c6dcd 3541 'width': int_or_none(fmt.get('width')),
ab6df717 3542 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3543 'desc' if language_preference < -1 else ''),
3544 'language_preference': language_preference,
a405b38f 3545 # Strictly de-prioritize damaged and 3gp formats
3546 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3547 }
60bdb7bd 3548 mime_mobj = re.match(
3549 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3550 if mime_mobj:
3551 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3552 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3553 no_audio = dct.get('acodec') == 'none'
3554 no_video = dct.get('vcodec') == 'none'
3555 if no_audio:
3556 dct['vbr'] = tbr
3557 if no_video:
3558 dct['abr'] = tbr
3559 if no_audio or no_video:
545cc85d 3560 dct['downloader_options'] = {
3561 # Youtube throttles chunks >~10M
3562 'http_chunk_size': 10485760,
bf1317d2 3563 }
7c60c33e 3564 if dct.get('ext'):
3565 dct['container'] = dct['ext'] + '_dash'
11f9be09 3566 yield dct
545cc85d 3567
4d37720a
L
3568 needs_live_processing = self._needs_live_processing(live_status, duration)
3569 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3570
3571 skip_manifests = set(self._configuration_arg('skip'))
3572 if (not self.get_param('youtube_include_hls_manifest', True)
3573 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3574 or needs_live_processing and skip_bad_formats):
3575 skip_manifests.add('hls')
3576
0f06bcd7 3577 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3578 skip_manifests.add('dash')
3579 if self._configuration_arg('include_live_dash'):
3580 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3581 'Use include_incomplete_formats extractor argument instead')
3582 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3583 skip_manifests.add('dash')
5d3a0e79 3584
a0bb6ce5 3585 def process_manifest_format(f, proto, itag):
3586 if itag in itags:
3587 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3588 return False
3589 itag = f'{itag}-{proto}'
3590 if itag:
3591 f['format_id'] = itag
3592 itags[itag] = proto
3593
b25cac65 3594 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3595 if f['quality'] == -1 and f.get('height'):
3596 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3597 return True
2a9c6dcd 3598
c646d76f 3599 subtitles = {}
11f9be09 3600 for sd in streaming_data:
4d37720a 3601 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3602 if hls_manifest_url:
4d37720a
L
3603 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3604 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3605 subtitles = self._merge_subtitles(subs, subtitles)
3606 for f in fmts:
a0bb6ce5 3607 if process_manifest_format(f, 'hls', self._search_regex(
3608 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3609 yield f
545cc85d 3610
4d37720a 3611 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3612 if dash_manifest_url:
c646d76f 3613 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3614 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3615 for f in formats:
a0bb6ce5 3616 if process_manifest_format(f, 'dash', f['format_id']):
3617 f['filesize'] = int_or_none(self._search_regex(
3618 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3619 if needs_live_processing:
adbc4ec4
THD
3620 f['is_from_start'] = True
3621
a0bb6ce5 3622 yield f
c646d76f 3623 yield subtitles
11f9be09 3624
720c3099 3625 def _extract_storyboard(self, player_responses, duration):
3626 spec = get_first(
3627 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3628 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3629 if not base_url:
720c3099 3630 return
720c3099 3631 L = len(spec) - 1
3632 for i, args in enumerate(spec):
3633 args = args.split('#')
3634 counts = list(map(int_or_none, args[:5]))
3635 if len(args) != 8 or not all(counts):
3636 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3637 continue
3638 width, height, frame_count, cols, rows = counts
3639 N, sigh = args[6:]
3640
3641 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3642 fragment_count = frame_count / (cols * rows)
3643 fragment_duration = duration / fragment_count
3644 yield {
3645 'format_id': f'sb{i}',
3646 'format_note': 'storyboard',
3647 'ext': 'mhtml',
3648 'protocol': 'mhtml',
3649 'acodec': 'none',
3650 'vcodec': 'none',
3651 'url': url,
3652 'width': width,
3653 'height': height,
45e8a04e 3654 'fps': frame_count / duration,
3655 'rows': rows,
3656 'columns': cols,
720c3099 3657 'fragments': [{
b3edc806 3658 'url': url.replace('$M', str(j)),
720c3099 3659 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3660 } for j in range(math.ceil(fragment_count))],
3661 }
3662
adbc4ec4 3663 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3664 webpage = None
3665 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3666 query = {'bpctr': '9999999999', 'has_verified': '1'}
3667 if smuggled_data.get('is_story'):
3668 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3669 webpage = self._download_webpage(
50ac0e54 3670 webpage_url, video_id, fatal=False, query=query)
11f9be09 3671
3672 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3673
b6de707d 3674 player_responses, player_url = self._extract_player_responses(
11f9be09 3675 self._get_requested_clients(url, smuggled_data),
50ac0e54 3676 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3677
adbc4ec4
THD
3678 return webpage, master_ytcfg, player_responses, player_url
3679
a1b2d843 3680 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3681 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3682 is_live = get_first(video_details, 'isLive')
3683 if is_live is None:
3684 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3685 live_content = get_first(video_details, 'isLiveContent')
3686 is_upcoming = get_first(video_details, 'isUpcoming')
3687 if is_live is None and is_upcoming or live_content is False:
3688 is_live = False
3689 if is_upcoming is None and (live_content or is_live):
3690 is_upcoming = False
3691 post_live = get_first(video_details, 'isPostLiveDvr')
3692 live_status = ('post_live' if post_live
3693 else 'is_live' if is_live
3694 else 'is_upcoming' if is_upcoming
3695 else None if None in (is_live, is_upcoming, live_content)
3696 else 'was_live' if live_content else 'not_live')
adbc4ec4
THD
3697
3698 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3699 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3700
4d37720a 3701 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3702
3703 def _real_extract(self, url):
3704 url, smuggled_data = unsmuggle_url(url, {})
3705 video_id = self._match_id(url)
3706
3707 base_url = self.http_scheme() + '//www.youtube.com/'
3708 webpage_url = base_url + 'watch?v=' + video_id
3709
3710 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3711
11f9be09 3712 playability_statuses = traverse_obj(
3713 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3714
3715 trailer_video_id = get_first(
3716 playability_statuses,
3717 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3718 expected_type=str)
3719 if trailer_video_id:
3720 return self.url_result(
3721 trailer_video_id, self.ie_key(), trailer_video_id)
3722
3723 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3724 if webpage else (lambda x: None))
3725
3726 video_details = traverse_obj(
3727 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3728 microformats = traverse_obj(
3729 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3730 expected_type=dict, default=[])
c26f9b99 3731
3732 translated_title = self._get_text(microformats, (..., 'title'))
3733 video_title = (self._preferred_lang and translated_title
3734 or get_first(video_details, 'title') # primary
3735 or translated_title
3736 or search_meta(['og:title', 'twitter:title', 'title']))
3737 translated_description = self._get_text(microformats, (..., 'description'))
3738 original_description = get_first(video_details, 'shortDescription')
3739 video_description = (
3740 self._preferred_lang and translated_description
3741 # If original description is blank, it will be an empty string.
3742 # Do not prefer translated description in this case.
3743 or original_description if original_description is not None else translated_description)
11f9be09 3744
d89257f3 3745 multifeed_metadata_list = get_first(
3746 player_responses,
3747 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3748 expected_type=str)
3749 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3750 if self.get_param('noplaylist'):
11f9be09 3751 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3752 else:
3753 entries = []
3754 feed_ids = []
3755 for feed in multifeed_metadata_list.split(','):
3756 # Unquote should take place before split on comma (,) since textual
3757 # fields may contain comma as well (see
3758 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3759 feed_data = urllib.parse.parse_qs(
ac668111 3760 urllib.parse.unquote_plus(feed))
d89257f3 3761
3762 def feed_entry(name):
3763 return try_get(
14f25df2 3764 feed_data, lambda x: x[name][0], str)
d89257f3 3765
3766 feed_id = feed_entry('id')
3767 if not feed_id:
3768 continue
3769 feed_title = feed_entry('title')
3770 title = video_title
3771 if feed_title:
3772 title += ' (%s)' % feed_title
3773 entries.append({
3774 '_type': 'url_transparent',
3775 'ie_key': 'Youtube',
3776 'url': smuggle_url(
3777 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3778 {'force_singlefeed': True}),
3779 'title': title,
3780 })
3781 feed_ids.append(feed_id)
3782 self.to_screen(
3783 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3784 % (', '.join(feed_ids), video_id))
3785 return self.playlist_result(
3786 entries, video_id, video_title, video_description)
11f9be09 3787
a1b2d843 3788 duration = int_or_none(
3789 get_first(video_details, 'lengthSeconds')
3790 or get_first(microformats, 'lengthSeconds')
3791 or parse_duration(search_meta('duration'))) or None
3792
4d37720a
L
3793 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3794 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3795 if live_status == 'post_live':
3796 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3797
545cc85d 3798 if not formats:
11f9be09 3799 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3800 self.report_drm(video_id)
11f9be09 3801 pemr = get_first(
3802 playability_statuses,
3803 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3804 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3805 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3806 if subreason:
545cc85d 3807 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3808 countries = get_first(microformats, 'availableCountries')
545cc85d 3809 if not countries:
3810 regions_allowed = search_meta('regionsAllowed')
3811 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3812 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3813 reason += f'. {subreason}'
545cc85d 3814 if reason:
b7da73eb 3815 self.raise_no_formats(reason, expected=True)
bf1317d2 3816
11f9be09 3817 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3818 if not keywords and webpage:
3819 keywords = [
3820 unescapeHTML(m.group('content'))
3821 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3822 for keyword in keywords:
3823 if keyword.startswith('yt:stretch='):
201c1459 3824 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3825 if mobj:
3826 # NB: float is intentional for forcing float division
3827 w, h = (float(v) for v in mobj.groups())
3828 if w > 0 and h > 0:
3829 ratio = w / h
3830 for f in formats:
3831 if f.get('vcodec') != 'none':
3832 f['stretched_ratio'] = ratio
3833 break
a709d873 3834 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3835 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3836 if thumbnail_url:
3837 thumbnails.append({
3838 'url': thumbnail_url,
ff2751ac 3839 })
fccf5021 3840 original_thumbnails = thumbnails.copy()
3841
0ba692ac 3842 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3843 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3844 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3845 thumbnail_names = [
962ffcf8 3846 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3847 # in resolution, these are not the custom thumbnail. So de-prioritize them
3848 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3849 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3850 ]
cca80fe6 3851 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3852 thumbnails.extend({
3853 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3854 video_id=video_id, name=name, ext=ext,
4d37720a 3855 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 3856 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3857 for thumb in thumbnails:
cca80fe6 3858 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3859 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3860 self._remove_duplicate_formats(thumbnails)
fccf5021 3861 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3862
7ea65411 3863 category = get_first(microformats, 'category') or search_meta('genre')
3864 channel_id = str_or_none(
3865 get_first(video_details, 'channelId')
3866 or get_first(microformats, 'externalChannelId')
3867 or search_meta('channelId'))
7ea65411 3868 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3869
adbc4ec4
THD
3870 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3871 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3872 if not duration and live_end_time and live_start_time:
3873 duration = live_end_time - live_start_time
3874
4d37720a
L
3875 needs_live_processing = self._needs_live_processing(live_status, duration)
3876
3877 def is_bad_format(fmt):
3878 if needs_live_processing and not fmt.get('is_from_start'):
3879 return True
3880 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
3881 and fmt.get('protocol') == 'http_dash_segments'):
3882 return True
3883
3884 for fmt in filter(is_bad_format, formats):
3885 fmt['preference'] = (fmt.get('preference') or -1) - 10
3886 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
3887
3888 if needs_live_processing:
3889 self._prepare_live_from_start_formats(
3890 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 3891
720c3099 3892 formats.extend(self._extract_storyboard(player_responses, duration))
3893
31b532a1 3894 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3895 self._sort_formats(formats, (
3896 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3897
545cc85d 3898 info = {
3899 'id': video_id,
39ca3b5c 3900 'title': video_title,
545cc85d 3901 'formats': formats,
3902 'thumbnails': thumbnails,
fccf5021 3903 # The best thumbnail that we are sure exists. Prevents unnecessary
3904 # URL checking if user don't care about getting the best possible thumbnail
3905 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3906 'description': video_description,
11f9be09 3907 'uploader': get_first(video_details, 'author'),
545cc85d 3908 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3909 'uploader_url': owner_profile_url,
3910 'channel_id': channel_id,
a70635b8 3911 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3912 'duration': duration,
3913 'view_count': int_or_none(
11f9be09 3914 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3915 or search_meta('interactionCount')),
11f9be09 3916 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3917 'age_limit': 18 if (
11f9be09 3918 get_first(microformats, 'isFamilySafe') is False
545cc85d 3919 or search_meta('isFamilyFriendly') == 'false'
3920 or search_meta('og:restrictions:age') == '18+') else 0,
3921 'webpage_url': webpage_url,
3922 'categories': [category] if category else None,
3923 'tags': keywords,
11f9be09 3924 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 3925 'live_status': live_status,
adbc4ec4 3926 'release_timestamp': live_start_time,
545cc85d 3927 }
b477fc13 3928
c646d76f 3929 subtitles = {}
3944e7af 3930 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3931 if pctr:
ecdc9049 3932 def get_lang_code(track):
3933 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3934 or track.get('languageCode'))
3935
3936 # Converted into dicts to remove duplicates
3937 captions = {
3938 get_lang_code(sub): sub
3939 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3940 translation_languages = {
3941 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3942 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3943
774d79cc 3944 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3945 lang_subs = container.setdefault(lang_code, [])
545cc85d 3946 for fmt in self._SUBTITLE_FORMATS:
3947 query.update({
3948 'fmt': fmt,
3949 })
3950 lang_subs.append({
3951 'ext': fmt,
60f393e4 3952 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3953 'name': sub_name,
545cc85d 3954 })
7e72694b 3955
07b47084 3956 # NB: Constructing the full subtitle dictionary is slow
3957 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3958 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3959 for lang_code, caption_track in captions.items():
3960 base_url = caption_track.get('baseUrl')
1235d333 3961 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3962 if not base_url:
3963 continue
ecdc9049 3964 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3965 if caption_track.get('kind') != 'asr':
545cc85d 3966 if not lang_code:
3967 continue
3968 process_language(
ecdc9049 3969 subtitles, base_url, lang_code, lang_name, {})
3970 if not caption_track.get('isTranslatable'):
3971 continue
3944e7af 3972 for trans_code, trans_name in translation_languages.items():
3973 if not trans_code:
545cc85d 3974 continue
1235d333 3975 orig_trans_code = trans_code
ecdc9049 3976 if caption_track.get('kind') != 'asr':
07b47084 3977 if not get_translated_subs:
18e49408 3978 continue
ecdc9049 3979 trans_code += f'-{lang_code}'
a70635b8 3980 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3981 # Add an "-orig" label to the original language so that it can be distinguished.
3982 # The subs are returned without "-orig" as well for compatibility
1235d333 3983 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3984 process_language(
d49669ac 3985 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3986 # Setting tlang=lang returns damaged subtitles.
d49669ac 3987 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3988 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3989
3990 info['automatic_captions'] = automatic_captions
3991 info['subtitles'] = subtitles
7e72694b 3992
14f25df2 3993 parsed_url = urllib.parse.urlparse(url)
545cc85d 3994 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3995 query = urllib.parse.parse_qs(component)
545cc85d 3996 for k, v in query.items():
3997 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3998 d_k += '_time'
3999 if d_k not in info and k in s_ks:
4000 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4001
4002 # Youtube Music Auto-generated description
822b9d9c 4003 if video_description:
1890fc63 4004 mobj = re.search(
4005 r'''(?xs)
4006 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4007 (?P<album>[^\n]+)
4008 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4009 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4010 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4011 .+\nAuto-generated\ by\ YouTube\.\s*$
4012 ''', video_description)
822b9d9c 4013 if mobj:
822b9d9c
RA
4014 release_year = mobj.group('release_year')
4015 release_date = mobj.group('release_date')
4016 if release_date:
4017 release_date = release_date.replace('-', '')
4018 if not release_year:
545cc85d 4019 release_year = release_date[:4]
4020 info.update({
4021 'album': mobj.group('album'.strip()),
4022 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4023 'track': mobj.group('track').strip(),
4024 'release_date': release_date,
cc2db878 4025 'release_year': int_or_none(release_year),
545cc85d 4026 })
7e72694b 4027
545cc85d 4028 initial_data = None
4029 if webpage:
56ba69e4 4030 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4031 if not initial_data:
99e9e001 4032 query = {'videoId': video_id}
4033 query.update(self._get_checkok_params())
109dd3b2 4034 initial_data = self._extract_response(
4035 item_id=video_id, ep='next', fatal=False,
99e9e001 4036 ytcfg=master_ytcfg, query=query,
4037 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4038 note='Downloading initial data API JSON')
545cc85d 4039
0df111a3 4040 info['comment_count'] = traverse_obj(initial_data, (
4041 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4042 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4043 ), (
4044 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4045 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4046 ), expected_type=int_or_none, get_all=False)
4047
19a03940 4048 try: # This will error if there is no livechat
c60ee3a2 4049 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4050 except (KeyError, IndexError, TypeError):
4051 pass
4052 else:
ecdc9049 4053 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4054 # url is needed to set cookies
4055 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4056 'video_id': video_id,
4057 'ext': 'json',
4d37720a
L
4058 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4059 else 'youtube_live_chat_replay'),
c60ee3a2 4060 }]
545cc85d 4061
4062 if initial_data:
7c365c21 4063 info['chapters'] = (
4064 self._extract_chapters_from_json(initial_data, duration)
4065 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4066 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4067 or None)
545cc85d 4068
17322130 4069 contents = traverse_obj(
4070 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4071 expected_type=list, default=[])
4072
4073 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4074 if vpir:
4075 stl = vpir.get('superTitleLink')
4076 if stl:
4077 stl = self._get_text(stl)
4078 if try_get(
4079 vpir,
4080 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4081 info['location'] = stl
4082 else:
affc4fef 4083 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4084 if mobj:
545cc85d 4085 info.update({
17322130 4086 'series': mobj.group(1),
4087 'season_number': int(mobj.group(2)),
4088 'episode_number': int(mobj.group(3)),
545cc85d 4089 })
17322130 4090 for tlb in (try_get(
4091 vpir,
4092 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4093 list) or []):
3ffb2f5b 4094 tbrs = variadic(
4095 traverse_obj(
4096 tlb, 'toggleButtonRenderer',
4097 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4098 default=[]))
4099 for tbr in tbrs:
4100 for getter, regex in [(
4101 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4102 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4103 lambda x: x['accessibility'],
4104 lambda x: x['accessibilityData']['accessibilityData'],
4105 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4106 label = (try_get(tbr, getter, dict) or {}).get('label')
4107 if label:
4108 mobj = re.match(regex, label)
4109 if mobj:
4110 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4111 break
17322130 4112 sbr_tooltip = try_get(
4113 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4114 if sbr_tooltip:
4115 like_count, dislike_count = sbr_tooltip.split(' / ')
4116 info.update({
4117 'like_count': str_to_int(like_count),
4118 'dislike_count': str_to_int(dislike_count),
4119 })
867c66ff
M
4120 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4121 if vcr:
4122 vc = self._get_count(vcr, 'viewCount')
4123 # Upcoming premieres with waiting count are treated as live here
4124 if vcr.get('isLive'):
4125 info['concurrent_view_count'] = vc
4126 elif info.get('view_count') is None:
4127 info['view_count'] = vc
4128
17322130 4129 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4130 if vsir:
4131 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4132 info.update({
4133 'channel': self._get_text(vor, 'title'),
4134 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4135
4136 rows = try_get(
4137 vsir,
4138 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4139 list) or []
4140 multiple_songs = False
4141 for row in rows:
4142 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4143 multiple_songs = True
4144 break
4145 for row in rows:
4146 mrr = row.get('metadataRowRenderer') or {}
4147 mrr_title = mrr.get('title')
4148 if not mrr_title:
4149 continue
4150 mrr_title = self._get_text(mrr, 'title')
4151 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4152 if mrr_title == 'License':
4153 info['license'] = mrr_contents_text
4154 elif not multiple_songs:
4155 if mrr_title == 'Album':
4156 info['album'] = mrr_contents_text
4157 elif mrr_title == 'Artist':
4158 info['artist'] = mrr_contents_text
4159 elif mrr_title == 'Song':
4160 info['track'] = mrr_contents_text
545cc85d 4161
4162 fallbacks = {
4163 'channel': 'uploader',
4164 'channel_id': 'uploader_id',
4165 'channel_url': 'uploader_url',
4166 }
992f9a73 4167
17322130 4168 # The upload date for scheduled, live and past live streams / premieres in microformats
4169 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4170 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4171 upload_date = (
4172 unified_strdate(get_first(microformats, 'uploadDate'))
4173 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4174 if not upload_date or (
4d37720a 4175 live_status in ('not_live', None)
1ff88b7a 4176 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4177 ):
c26f9b99 4178 upload_date = strftime_or_none(
4179 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4180 info['upload_date'] = upload_date
992f9a73 4181
545cc85d 4182 for to, frm in fallbacks.items():
4183 if not info.get(to):
4184 info[to] = info.get(frm)
4185
4186 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4187 v = info.get(s_k)
4188 if v:
4189 info[d_k] = v
b84071c0 4190
c26f9b99 4191 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4192
4193 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4194 or get_first(video_details, 'isPrivate', expected_type=bool))
4195
4196 info['availability'] = (
4197 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4198 else self._availability(
4199 is_private=is_private,
4200 needs_premium=(
4201 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4202 or False if initial_data and is_private is not None else None),
4203 needs_subscription=(
4204 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4205 or False if initial_data and is_private is not None else None),
4206 needs_auth=info['age_limit'] >= 18,
4207 is_unlisted=None if is_private is None else (
4208 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4209 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4210
a2160aa4 4211 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4212
11f9be09 4213 self.mark_watched(video_id, player_responses)
d77ab8e2 4214
545cc85d 4215 return info
c5e8d7af 4216
a61fd4cf 4217
a6213a49 4218class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 4219
182bda88 4220 @staticmethod
4221 def passthrough_smuggled_data(func):
4222 def _smuggle(entries, smuggled_data):
4223 for entry in entries:
4224 # TODO: Convert URL to music.youtube instead.
4225 # Do we need to passthrough any other smuggled_data?
4226 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4227 yield entry
4228
4229 @functools.wraps(func)
4230 def wrapper(self, url):
4231 url, smuggled_data = unsmuggle_url(url, {})
4232 if self.is_music_url(url):
4233 smuggled_data['is_music_url'] = True
4234 info_dict = func(self, url, smuggled_data)
4235 if smuggled_data and info_dict.get('entries'):
4236 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4237 return info_dict
4238 return wrapper
4239
a6213a49 4240 def _extract_channel_id(self, webpage):
4241 channel_id = self._html_search_meta(
4242 'channelId', webpage, 'channel id', default=None)
4243 if channel_id:
4244 return channel_id
4245 channel_url = self._html_search_meta(
4246 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4247 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4248 'twitter:app:url:googleplay'), webpage, 'channel url')
4249 return self._search_regex(
4250 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4251 channel_url, 'channel id')
15f6397c 4252
8bdd16b4 4253 @staticmethod
cd7c66cf 4254 def _extract_basic_item_renderer(item):
4255 # Modified from _extract_grid_item_renderer
201c1459 4256 known_basic_renderers = (
a17526e4 4257 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4258 )
4259 for key, renderer in item.items():
201c1459 4260 if not isinstance(renderer, dict):
cd7c66cf 4261 continue
201c1459 4262 elif key in known_basic_renderers:
4263 return renderer
4264 elif key.startswith('grid') and key.endswith('Renderer'):
4265 return renderer
8bdd16b4 4266
8bdd16b4 4267 def _grid_entries(self, grid_renderer):
4268 for item in grid_renderer['items']:
4269 if not isinstance(item, dict):
39b62db1 4270 continue
cd7c66cf 4271 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4272 if not isinstance(renderer, dict):
4273 continue
052e1350 4274 title = self._get_text(renderer, 'title')
fe93e2c4 4275
8bdd16b4 4276 # playlist
4277 playlist_id = renderer.get('playlistId')
4278 if playlist_id:
4279 yield self.url_result(
4280 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4281 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4282 video_title=title)
201c1459 4283 continue
8bdd16b4 4284 # video
4285 video_id = renderer.get('videoId')
4286 if video_id:
4287 yield self._extract_video(renderer)
201c1459 4288 continue
8bdd16b4 4289 # channel
4290 channel_id = renderer.get('channelId')
4291 if channel_id:
8bdd16b4 4292 yield self.url_result(
4293 'https://www.youtube.com/channel/%s' % channel_id,
4294 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4295 continue
4296 # generic endpoint URL support
4297 ep_url = urljoin('https://www.youtube.com/', try_get(
4298 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4299 str))
201c1459 4300 if ep_url:
4301 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4302 if ie.suitable(ep_url):
4303 yield self.url_result(
4304 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4305 break
8bdd16b4 4306
16aa9ea4 4307 def _music_reponsive_list_entry(self, renderer):
4308 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4309 if video_id:
4310 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4311 ie=YoutubeIE.ie_key(), video_id=video_id)
4312 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4313 if playlist_id:
4314 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4315 if video_id:
4316 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4317 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4318 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4319 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4320 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4321 if browse_id:
4322 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4323 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4324
3d3dddc9 4325 def _shelf_entries_from_content(self, shelf_renderer):
4326 content = shelf_renderer.get('content')
4327 if not isinstance(content, dict):
8bdd16b4 4328 return
cd7c66cf 4329 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4330 if renderer:
4331 # TODO: add support for nested playlists so each shelf is processed
4332 # as separate playlist
4333 # TODO: this includes only first N items
86e5f3ed 4334 yield from self._grid_entries(renderer)
3d3dddc9 4335 renderer = content.get('horizontalListRenderer')
4336 if renderer:
4337 # TODO
4338 pass
8bdd16b4 4339
29f7c58a 4340 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4341 ep = try_get(
4342 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4343 str)
8bdd16b4 4344 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4345 if shelf_url:
29f7c58a 4346 # Skipping links to another channels, note that checking for
4347 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4348 # will not work
4349 if skip_channels and '/channels?' in shelf_url:
4350 return
052e1350 4351 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4352 yield self.url_result(shelf_url, video_title=title)
4353 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4354 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4355
8bdd16b4 4356 def _playlist_entries(self, video_list_renderer):
4357 for content in video_list_renderer['contents']:
4358 if not isinstance(content, dict):
4359 continue
4360 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4361 if not isinstance(renderer, dict):
4362 continue
4363 video_id = renderer.get('videoId')
4364 if not video_id:
4365 continue
4366 yield self._extract_video(renderer)
07aeced6 4367
3462ffa8 4368 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4369 renderer = traverse_obj(
4370 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4371 video_id = renderer.get('videoId')
4372 if not video_id:
4373 return
4374 yield self._extract_video(renderer)
4375
8bdd16b4 4376 def _video_entry(self, video_renderer):
4377 video_id = video_renderer.get('videoId')
4378 if video_id:
4379 return self._extract_video(video_renderer)
dacb3a86 4380
ad210f4f 4381 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4382 url = urljoin('https://youtube.com', traverse_obj(
4383 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4384 if url:
4385 return self.url_result(
4386 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4387
8bdd16b4 4388 def _post_thread_entries(self, post_thread_renderer):
4389 post_renderer = try_get(
4390 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4391 if not post_renderer:
4392 return
4393 # video attachment
4394 video_renderer = try_get(
895b0931 4395 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4396 video_id = video_renderer.get('videoId')
4397 if video_id:
4398 entry = self._extract_video(video_renderer)
8bdd16b4 4399 if entry:
4400 yield entry
895b0931 4401 # playlist attachment
4402 playlist_id = try_get(
14f25df2 4403 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4404 if playlist_id:
4405 yield self.url_result(
e28f1c0a 4406 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4407 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4408 # inline video links
4409 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4410 for run in runs:
4411 if not isinstance(run, dict):
4412 continue
4413 ep_url = try_get(
14f25df2 4414 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4415 if not ep_url:
4416 continue
4417 if not YoutubeIE.suitable(ep_url):
4418 continue
4419 ep_video_id = YoutubeIE._match_id(ep_url)
4420 if video_id == ep_video_id:
4421 continue
895b0931 4422 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4423
8bdd16b4 4424 def _post_thread_continuation_entries(self, post_thread_continuation):
4425 contents = post_thread_continuation.get('contents')
4426 if not isinstance(contents, list):
4427 return
4428 for content in contents:
4429 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4430 if isinstance(renderer, dict):
4431 yield from self._post_thread_entries(renderer)
8bdd16b4 4432 continue
6b0b0a28 4433 renderer = content.get('videoRenderer')
4434 if isinstance(renderer, dict):
4435 yield self._video_entry(renderer)
07aeced6 4436
39ed931e 4437 r''' # unused
4438 def _rich_grid_entries(self, contents):
4439 for content in contents:
4440 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4441 if video_renderer:
4442 entry = self._video_entry(video_renderer)
4443 if entry:
4444 yield entry
4445 '''
52efa4b3 4446
0a5095fe 4447 def _report_history_entries(self, renderer):
4448 for url in traverse_obj(renderer, (
7a32c70d 4449 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4450 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4451 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4452 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4453
a6213a49 4454 def _extract_entries(self, parent_renderer, continuation_list):
4455 # continuation_list is modified in-place with continuation_list = [continuation_token]
4456 continuation_list[:] = [None]
4457 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4458 for content in contents:
4459 if not isinstance(content, dict):
4460 continue
16aa9ea4 4461 is_renderer = traverse_obj(
4462 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4463 expected_type=dict)
a6213a49 4464 if not is_renderer:
0a5095fe 4465 if content.get('richItemRenderer'):
4466 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4467 yield entry
4468 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4469 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4470 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4471 yield from self._report_history_entries(table)
4472 continuation_list[0] = self._extract_continuation(table)
a6213a49 4473 continue
0a5095fe 4474
a6213a49 4475 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4476 for isr_content in isr_contents:
4477 if not isinstance(isr_content, dict):
8bdd16b4 4478 continue
69184e41 4479
a6213a49 4480 known_renderers = {
4481 'playlistVideoListRenderer': self._playlist_entries,
4482 'gridRenderer': self._grid_entries,
a17526e4 4483 'reelShelfRenderer': self._grid_entries,
4484 'shelfRenderer': self._shelf_entries,
16aa9ea4 4485 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4486 'backstagePostThreadRenderer': self._post_thread_entries,
4487 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4488 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4489 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4490 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4491 }
4492 for key, renderer in isr_content.items():
4493 if key not in known_renderers:
4494 continue
4495 for entry in known_renderers[key](renderer):
4496 if entry:
4497 yield entry
4498 continuation_list[0] = self._extract_continuation(renderer)
4499 break
70d5c17b 4500
4501 if not continuation_list[0]:
a6213a49 4502 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4503
a6213a49 4504 if not continuation_list[0]:
4505 continuation_list[0] = self._extract_continuation(parent_renderer)
4506
4507 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4508 continuation_list = [None]
4509 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4510 tab_content = try_get(tab, lambda x: x['content'], dict)
4511 if not tab_content:
4512 return
3462ffa8 4513 parent_renderer = (
29f7c58a 4514 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4515 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4516 yield from extract_entries(parent_renderer)
3462ffa8 4517 continuation = continuation_list[0]
d069eca7 4518
8bdd16b4 4519 for page_num in itertools.count(1):
4520 if not continuation:
4521 break
99e9e001 4522 headers = self.generate_api_headers(
4523 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4524 response = self._extract_response(
86e5f3ed 4525 item_id=f'{item_id} page {page_num}',
fe93e2c4 4526 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4527 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4528
4529 if not response:
8bdd16b4 4530 break
ac56cf38 4531 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4532 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4533 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4534
a1b535bd 4535 known_renderers = {
e4b98809 4536 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4537 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4538 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4539 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4540 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4541 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4542 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4543 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4544 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4545 'playlistVideoListContinuation': (self._playlist_entries, None),
4546 'gridContinuation': (self._grid_entries, None),
4547 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4548 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4549 }
1fb53b94 4550
4551 continuation_items = traverse_obj(response, (
4552 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4553 'appendContinuationItemsAction', 'continuationItems'
4554 ), 'continuationContents', get_all=False)
4555 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4556
a1b535bd 4557 video_items_renderer = None
1fb53b94 4558 for key in continuation_item.keys():
a1b535bd 4559 if key not in known_renderers:
8bdd16b4 4560 continue
1fb53b94 4561 func, parent_key = known_renderers[key]
4562 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4563 continuation_list = [None]
1fb53b94 4564 yield from func(video_items_renderer)
9ba5705a 4565 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4566
4567 if not video_items_renderer:
a1b535bd 4568 break
9558dcec 4569
8bdd16b4 4570 @staticmethod
7c219ea6 4571 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4572 for tab in tabs:
cd684175 4573 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4574 if renderer.get('selected') is True:
4575 return renderer
2b3c2546 4576 else:
7c219ea6 4577 if fatal:
4578 raise ExtractorError('Unable to find selected tab')
b82f815f 4579
61d3665d 4580 def _extract_uploader(self, data):
8bdd16b4 4581 uploader = {}
61d3665d 4582 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4583 owner = try_get(
4584 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4585 if owner:
61d3665d 4586 owner_text = owner.get('text')
4587 uploader['uploader'] = self._search_regex(
4588 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4589 uploader['uploader_id'] = try_get(
14f25df2 4590 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4591 uploader['uploader_url'] = urljoin(
4592 'https://www.youtube.com/',
14f25df2 4593 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
7a32c70d 4594 return filter_dict(uploader)
8bdd16b4 4595
ac56cf38 4596 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4597 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4598 tags = []
b60419c5 4599
8bdd16b4 4600 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4601 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4602 renderer = try_get(
4603 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4604 if renderer:
b60419c5 4605 channel_name = renderer.get('title')
4606 channel_url = renderer.get('channelUrl')
4607 channel_id = renderer.get('externalId')
39ed931e 4608 else:
64c0d954 4609 renderer = try_get(
4610 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4611
8bdd16b4 4612 if renderer:
4613 title = renderer.get('title')
ecc97af3 4614 description = renderer.get('description', '')
b60419c5 4615 playlist_id = channel_id
4616 tags = renderer.get('keywords', '').split()
b60419c5 4617
301d07fc 4618 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4619 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4620 def _get_uncropped(url):
4621 return url_or_none((url or '').split('=')[0] + '=s0')
4622
4623 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4624 if avatar_thumbnails:
4625 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4626 if uncropped_avatar:
4627 avatar_thumbnails.append({
4628 'url': uncropped_avatar,
4629 'id': 'avatar_uncropped',
4630 'preference': 1
4631 })
4632
4633 channel_banners = self._extract_thumbnails(
4634 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4635 for banner in channel_banners:
4636 banner['preference'] = -10
4637
4638 if channel_banners:
4639 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4640 if uncropped_banner:
4641 channel_banners.append({
4642 'url': uncropped_banner,
4643 'id': 'banner_uncropped',
4644 'preference': -5
4645 })
4646
4647 primary_thumbnails = self._extract_thumbnails(
a17526e4 4648 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4649
3462ffa8 4650 if playlist_id is None:
70d5c17b 4651 playlist_id = item_id
f0d785d3 4652
4653 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
c26f9b99 4654 last_updated_unix = self._parse_time_text(self._get_text(playlist_stats, 2))
70d5c17b 4655 if title is None:
f0d785d3 4656 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4657 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4658 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4659
b60419c5 4660 metadata = {
4661 'playlist_id': playlist_id,
4662 'playlist_title': title,
4663 'playlist_description': description,
4664 'uploader': channel_name,
4665 'uploader_id': channel_id,
4666 'uploader_url': channel_url,
301d07fc 4667 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4668 'tags': tags,
f0d785d3 4669 'view_count': self._get_count(playlist_stats, 1),
4670 'availability': self._extract_availability(data),
4671 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4672 'playlist_count': self._get_count(playlist_stats, 0),
4673 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4674 }
4675 if not channel_id:
4676 metadata.update(self._extract_uploader(data))
4677 metadata.update({
4678 'channel': metadata['uploader'],
4679 'channel_id': metadata['uploader_id'],
4680 'channel_url': metadata['uploader_url']})
4681 return self.playlist_result(
d069eca7 4682 self._entries(
ac56cf38 4683 selected_tab, playlist_id, ytcfg,
4684 self._extract_account_syncid(ytcfg, data),
4685 self._extract_visitor_data(data, ytcfg)),
b60419c5 4686 **metadata)
73c4ac2c 4687
6e634cbe 4688 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4689 first_id = last_id = response = None
2be71994 4690 for page_num in itertools.count(1):
cd7c66cf 4691 videos = list(self._playlist_entries(playlist))
4692 if not videos:
4693 return
2be71994 4694 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4695 if start >= len(videos):
4696 return
24146491 4697 yield from videos[start:]
2be71994 4698 first_id = first_id or videos[0]['id']
4699 last_id = videos[-1]['id']
79360d99 4700 watch_endpoint = try_get(
4701 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4702 headers = self.generate_api_headers(
4703 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4704 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4705 query = {
4706 'playlistId': playlist_id,
4707 'videoId': watch_endpoint.get('videoId') or last_id,
4708 'index': watch_endpoint.get('index') or len(videos),
4709 'params': watch_endpoint.get('params') or 'OAE%3D'
4710 }
4711 response = self._extract_response(
4712 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4713 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4714 check_get_keys='contents'
4715 )
cd7c66cf 4716 playlist = try_get(
79360d99 4717 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4718
ac56cf38 4719 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4720 title = playlist.get('title') or try_get(
14f25df2 4721 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4722 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4723
4724 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4725 playlist_url = urljoin(url, try_get(
4726 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4727 str))
6e634cbe 4728
4729 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4730 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4731 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4732
4733 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4734 return self.url_result(
4735 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4736 video_title=title)
cd7c66cf 4737
8bdd16b4 4738 return self.playlist_result(
6e634cbe 4739 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4740 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4741
47193e02 4742 def _extract_availability(self, data):
4743 """
4744 Gets the availability of a given playlist/tab.
4745 Note: Unless YouTube tells us explicitly, we do not assume it is public
4746 @param data: response
4747 """
47193e02 4748 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
c26f9b99 4749
4750 player_header_privacy = traverse_obj(
4751 data, ('header', 'playlistHeaderRenderer', 'privacy'), expected_type=str)
4752
4753 badges = self._extract_badges(renderer)
47193e02 4754
4755 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
c26f9b99 4756 privacy_setting_icon = traverse_obj(
4757 renderer, (
4758 'privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4759 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4760 get_all=False, expected_type=str)
47193e02 4761
c26f9b99 4762 return (
4763 'public' if (
4764 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4765 or player_header_privacy == 'PUBLIC'
4766 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4767 else self._availability(
4768 is_private=(
4769 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4770 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4771 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4772 is_unlisted=(
4773 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4774 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
4775 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None else None),
4776 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4777 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4778 needs_auth=False))
47193e02 4779
4780 @staticmethod
4781 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4782 sidebar_renderer = try_get(
4783 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4784 for item in sidebar_renderer:
4785 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4786 if renderer:
4787 return renderer
4788
ac56cf38 4789 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4790 """
4791 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4792 """
5d342002 4793 browse_id = params = None
47193e02 4794 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4795 if not renderer:
4796 return
4797 menu_renderer = try_get(
4798 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4799 for menu_item in menu_renderer:
4800 if not isinstance(menu_item, dict):
358de58c 4801 continue
47193e02 4802 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4803 text = try_get(
14f25df2 4804 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4805 if not text or text.lower() != 'show unavailable videos':
4806 continue
4807 browse_endpoint = try_get(
4808 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4809 browse_id = browse_endpoint.get('browseId')
4810 params = browse_endpoint.get('params')
4811 break
5d342002 4812
11f9be09 4813 headers = self.generate_api_headers(
99e9e001 4814 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4815 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4816 query = {
4817 'params': params or 'wgYCCAA=',
4818 'browseId': browse_id or 'VL%s' % item_id
4819 }
4820 return self._extract_response(
4821 item_id=item_id, headers=headers, query=query,
fe93e2c4 4822 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4823 note='Downloading API JSON with unavailable videos')
358de58c 4824
2762dbb1 4825 @functools.cached_property
a25bca9f 4826 def skip_webpage(self):
4827 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4828
ac56cf38 4829 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4830 webpage, data = None, None
4831 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4832 try:
be5c1ae8 4833 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4834 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4835 except ExtractorError as e:
4836 if isinstance(e.cause, network_exceptions):
14f25df2 4837 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4838 retry.error = e
4839 continue
4840 self._error_or_warning(e, fatal=fatal)
14fdfea9 4841 break
ac56cf38 4842
be5c1ae8 4843 try:
4844 self._extract_and_report_alerts(data)
4845 except ExtractorError as e:
4846 self._error_or_warning(e, fatal=fatal)
4847 break
ac56cf38 4848
be5c1ae8 4849 # Sometimes youtube returns a webpage with incomplete ytInitialData
4850 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4851 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4852 retry.error = ExtractorError('Incomplete yt initial data received')
4853 continue
ac56cf38 4854
cd7c66cf 4855 return webpage, data
4856
a25bca9f 4857 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4858 """Use if failed to extract ytcfg (and data) from initial webpage"""
4859 if not ytcfg and self.is_authenticated:
4860 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4861 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4862 raise ExtractorError(
4863 f'{msg}. If you are not downloading private content, or '
4864 'your cookies are only for the first account and channel,'
4865 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4866 expected=True)
4867 self.report_warning(msg, only_once=True)
4868
ac56cf38 4869 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4870 data = None
a25bca9f 4871 if not self.skip_webpage:
ac56cf38 4872 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4873 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4874 # Reject webpage data if redirected to home page without explicitly requesting
4875 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4876 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4877 if (url != 'https://www.youtube.com/feed/recommended'
4878 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4879 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4880 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4881 if fatal:
4882 raise ExtractorError(msg, expected=True)
4883 self.report_warning(msg, only_once=True)
ac56cf38 4884 if not data:
a25bca9f 4885 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4886 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4887 return data, ytcfg
4888
4889 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4890 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4891 resolve_response = self._extract_response(
4892 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4893 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4894 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4895 for ep_key, ep in endpoints.items():
4896 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4897 if params:
4898 return self._extract_response(
4899 item_id=item_id, query=params, ep=ep, headers=headers,
4900 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4901 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4902 err_note = 'Failed to resolve url (does the playlist exist?)'
4903 if fatal:
4904 raise ExtractorError(err_note, expected=True)
4905 self.report_warning(err_note, item_id)
4906
a6213a49 4907 _SEARCH_PARAMS = None
4908
af5c1c55 4909 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4910 data = {'query': query}
4911 if params is NO_DEFAULT:
4912 params = self._SEARCH_PARAMS
4913 if params:
4914 data['params'] = params
16aa9ea4 4915
4916 content_keys = (
4917 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4918 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4919 # ytmusic search
4920 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4921 ('continuationContents', ),
4922 )
a25bca9f 4923 display_id = f'query "{query}"'
86e5f3ed 4924 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4925 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4926 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4927
a61fd4cf 4928 continuation_list = [None]
a25bca9f 4929 search = None
a6213a49 4930 for page_num in itertools.count(1):
a61fd4cf 4931 data.update(continuation_list[0] or {})
a25bca9f 4932 headers = self.generate_api_headers(
4933 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4934 search = self._extract_response(
a25bca9f 4935 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4936 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4937 slr_contents = traverse_obj(search, *content_keys)
4938 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4939 if not continuation_list[0]:
a6213a49 4940 break
4941
4942
4943class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4944 IE_DESC = 'YouTube Tabs'
4945 _VALID_URL = r'''(?x:
4946 https?://
4947 (?:\w+\.)?
4948 (?:
4949 youtube(?:kids)?\.com|
4950 %(invidious)s
4951 )/
4952 (?:
4953 (?P<channel_type>channel|c|user|browse)/|
4954 (?P<not_channel>
4955 feed/|hashtag/|
4956 (?:playlist|watch)\?.*?\blist=
4957 )|
4958 (?!(?:%(reserved_names)s)\b) # Direct URLs
4959 )
4960 (?P<id>[^/?\#&]+)
4961 )''' % {
4962 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4963 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4964 }
4965 IE_NAME = 'youtube:tab'
4966
4967 _TESTS = [{
4968 'note': 'playlists, multipage',
4969 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4970 'playlist_mincount': 94,
4971 'info_dict': {
4972 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4973 'title': 'Igor Kleiner - Playlists',
a6213a49 4974 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4975 'uploader': 'Igor Kleiner',
a6213a49 4976 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4977 'channel': 'Igor Kleiner',
4978 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4979 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4980 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4981 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4982 'channel_follower_count': int
a6213a49 4983 },
4984 }, {
4985 'note': 'playlists, multipage, different order',
4986 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4987 'playlist_mincount': 94,
4988 'info_dict': {
4989 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4990 'title': 'Igor Kleiner - Playlists',
a6213a49 4991 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4992 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4993 'uploader': 'Igor Kleiner',
4994 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4995 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4996 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4997 'channel': 'Igor Kleiner',
4998 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4999 'channel_follower_count': int
a6213a49 5000 },
5001 }, {
5002 'note': 'playlists, series',
5003 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5004 'playlist_mincount': 5,
5005 'info_dict': {
5006 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5007 'title': '3Blue1Brown - Playlists',
5008 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5009 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5010 'uploader': '3Blue1Brown',
976ae3ea 5011 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5012 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5013 'channel': '3Blue1Brown',
5014 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5015 'tags': ['Mathematics'],
6c73052c 5016 'channel_follower_count': int
a6213a49 5017 },
5018 }, {
5019 'note': 'playlists, singlepage',
5020 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5021 'playlist_mincount': 4,
5022 'info_dict': {
5023 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5024 'title': 'ThirstForScience - Playlists',
5025 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5026 'uploader': 'ThirstForScience',
5027 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5028 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5029 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5030 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5031 'tags': 'count:13',
5032 'channel': 'ThirstForScience',
6c73052c 5033 'channel_follower_count': int
a6213a49 5034 }
5035 }, {
5036 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5037 'only_matching': True,
5038 }, {
5039 'note': 'basic, single video playlist',
5040 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5041 'info_dict': {
5042 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5043 'uploader': 'Sergey M.',
5044 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5045 'title': 'youtube-dl public playlist',
976ae3ea 5046 'description': '',
5047 'tags': [],
5048 'view_count': int,
5049 'modified_date': '20201130',
5050 'channel': 'Sergey M.',
5051 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5052 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5053 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5054 'availability': 'public',
a6213a49 5055 },
5056 'playlist_count': 1,
5057 }, {
5058 'note': 'empty playlist',
5059 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5060 'info_dict': {
5061 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5062 'uploader': 'Sergey M.',
5063 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5064 'title': 'youtube-dl empty playlist',
976ae3ea 5065 'tags': [],
5066 'channel': 'Sergey M.',
5067 'description': '',
5068 'modified_date': '20160902',
5069 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5070 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5071 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5072 'availability': 'public',
a6213a49 5073 },
5074 'playlist_count': 0,
5075 }, {
5076 'note': 'Home tab',
5077 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5078 'info_dict': {
5079 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5080 'title': 'lex will - Home',
5081 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5082 'uploader': 'lex will',
5083 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5084 'channel': 'lex will',
5085 'tags': ['bible', 'history', 'prophesy'],
5086 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5087 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5088 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5089 'channel_follower_count': int
a6213a49 5090 },
5091 'playlist_mincount': 2,
5092 }, {
5093 'note': 'Videos tab',
5094 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5095 'info_dict': {
5096 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5097 'title': 'lex will - Videos',
5098 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5099 'uploader': 'lex will',
5100 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5101 'tags': ['bible', 'history', 'prophesy'],
5102 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5103 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5104 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5105 'channel': 'lex will',
6c73052c 5106 'channel_follower_count': int
a6213a49 5107 },
5108 'playlist_mincount': 975,
5109 }, {
5110 'note': 'Videos tab, sorted by popular',
5111 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5112 'info_dict': {
5113 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5114 'title': 'lex will - Videos',
5115 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5116 'uploader': 'lex will',
5117 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5118 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5119 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5120 'channel': 'lex will',
5121 'tags': ['bible', 'history', 'prophesy'],
5122 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5123 'channel_follower_count': int
a6213a49 5124 },
5125 'playlist_mincount': 199,
5126 }, {
5127 'note': 'Playlists tab',
5128 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5129 'info_dict': {
5130 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5131 'title': 'lex will - Playlists',
5132 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5133 'uploader': 'lex will',
5134 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5135 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5136 'channel': 'lex will',
5137 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5138 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5139 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5140 'channel_follower_count': int
a6213a49 5141 },
5142 'playlist_mincount': 17,
5143 }, {
5144 'note': 'Community tab',
5145 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5146 'info_dict': {
5147 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5148 'title': 'lex will - Community',
5149 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5150 'uploader': 'lex will',
5151 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5152 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5153 'channel': 'lex will',
5154 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5155 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5156 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5157 'channel_follower_count': int
a6213a49 5158 },
5159 'playlist_mincount': 18,
5160 }, {
5161 'note': 'Channels tab',
5162 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5163 'info_dict': {
5164 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5165 'title': 'lex will - Channels',
5166 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5167 'uploader': 'lex will',
5168 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5169 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5170 'channel': 'lex will',
5171 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5172 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5173 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5174 'channel_follower_count': int
a6213a49 5175 },
5176 'playlist_mincount': 12,
5177 }, {
5178 'note': 'Search tab',
5179 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5180 'playlist_mincount': 40,
5181 'info_dict': {
5182 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5183 'title': '3Blue1Brown - Search - linear algebra',
5184 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5185 'uploader': '3Blue1Brown',
5186 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5187 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5188 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5189 'tags': ['Mathematics'],
5190 'channel': '3Blue1Brown',
5191 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5192 'channel_follower_count': int
a6213a49 5193 },
5194 }, {
5195 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5196 'only_matching': True,
5197 }, {
5198 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5199 'only_matching': True,
5200 }, {
5201 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5202 'only_matching': True,
5203 }, {
5204 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5205 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5206 'info_dict': {
5207 'title': '29C3: Not my department',
5208 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5209 'uploader': 'Christiaan008',
5210 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5211 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5212 'tags': [],
5213 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5214 'view_count': int,
5215 'modified_date': '20150605',
5216 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5217 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5218 'channel': 'Christiaan008',
c26f9b99 5219 'availability': 'public',
a6213a49 5220 },
5221 'playlist_count': 96,
5222 }, {
5223 'note': 'Large playlist',
5224 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5225 'info_dict': {
5226 'title': 'Uploads from Cauchemar',
5227 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5228 'uploader': 'Cauchemar',
5229 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5230 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5231 'tags': [],
5232 'modified_date': r're:\d{8}',
5233 'channel': 'Cauchemar',
5234 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5235 'view_count': int,
5236 'description': '',
5237 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5238 'availability': 'public',
a6213a49 5239 },
5240 'playlist_mincount': 1123,
976ae3ea 5241 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5242 }, {
5243 'note': 'even larger playlist, 8832 videos',
5244 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5245 'only_matching': True,
5246 }, {
5247 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5248 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5249 'info_dict': {
5250 'title': 'Uploads from Interstellar Movie',
5251 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5252 'uploader': 'Interstellar Movie',
5253 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5254 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5255 'tags': [],
5256 'view_count': int,
5257 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5258 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5259 'channel': 'Interstellar Movie',
5260 'description': '',
5261 'modified_date': r're:\d{8}',
c26f9b99 5262 'availability': 'public',
a6213a49 5263 },
5264 'playlist_mincount': 21,
5265 }, {
5266 'note': 'Playlist with "show unavailable videos" button',
5267 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5268 'info_dict': {
5269 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5270 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5271 'uploader': 'Phim Siêu Nhân Nhật Bản',
5272 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5273 'view_count': int,
5274 'channel': 'Phim Siêu Nhân Nhật Bản',
5275 'tags': [],
5276 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5277 'description': '',
5278 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5279 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5280 'modified_date': r're:\d{8}',
c26f9b99 5281 'availability': 'public',
a6213a49 5282 },
5283 'playlist_mincount': 200,
976ae3ea 5284 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5285 }, {
5286 'note': 'Playlist with unavailable videos in page 7',
5287 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5288 'info_dict': {
5289 'title': 'Uploads from BlankTV',
5290 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5291 'uploader': 'BlankTV',
5292 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5293 'channel': 'BlankTV',
5294 'channel_url': 'https://www.youtube.com/c/blanktv',
5295 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5296 'view_count': int,
5297 'tags': [],
5298 'uploader_url': 'https://www.youtube.com/c/blanktv',
5299 'modified_date': r're:\d{8}',
5300 'description': '',
c26f9b99 5301 'availability': 'public',
a6213a49 5302 },
5303 'playlist_mincount': 1000,
976ae3ea 5304 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5305 }, {
5306 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5307 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5308 'info_dict': {
5309 'title': 'Data Analysis with Dr Mike Pound',
5310 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5311 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5312 'uploader': 'Computerphile',
5313 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5314 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5315 'tags': [],
5316 'view_count': int,
5317 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5318 'channel_url': 'https://www.youtube.com/user/Computerphile',
5319 'channel': 'Computerphile',
c26f9b99 5320 'availability': 'public',
a6213a49 5321 },
5322 'playlist_mincount': 11,
5323 }, {
5324 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5325 'only_matching': True,
5326 }, {
5327 'note': 'Playlist URL that does not actually serve a playlist',
5328 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5329 'info_dict': {
5330 'id': 'FqZTN594JQw',
5331 'ext': 'webm',
5332 'title': "Smiley's People 01 detective, Adventure Series, Action",
5333 'uploader': 'STREEM',
5334 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5335 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5336 'upload_date': '20150526',
5337 'license': 'Standard YouTube License',
5338 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5339 'categories': ['People & Blogs'],
5340 'tags': list,
5341 'view_count': int,
5342 'like_count': int,
a6213a49 5343 },
5344 'params': {
5345 'skip_download': True,
5346 },
5347 'skip': 'This video is not available.',
5348 'add_ie': [YoutubeIE.ie_key()],
5349 }, {
5350 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5351 'only_matching': True,
5352 }, {
5353 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5354 'only_matching': True,
5355 }, {
5356 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5357 'info_dict': {
12a1b225 5358 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5359 'ext': 'mp4',
976ae3ea 5360 'title': str,
a6213a49 5361 'uploader': 'Sky News',
5362 'uploader_id': 'skynews',
5363 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5364 'upload_date': r're:\d{8}',
976ae3ea 5365 'description': str,
a6213a49 5366 'categories': ['News & Politics'],
5367 'tags': list,
5368 'like_count': int,
6c73052c 5369 'release_timestamp': 1642502819,
976ae3ea 5370 'channel': 'Sky News',
5371 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5372 'age_limit': 0,
5373 'view_count': int,
6c73052c 5374 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5375 'playable_in_embed': True,
6c73052c 5376 'release_date': '20220118',
976ae3ea 5377 'availability': 'public',
5378 'live_status': 'is_live',
5379 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5380 'channel_follower_count': int
a6213a49 5381 },
5382 'params': {
5383 'skip_download': True,
5384 },
976ae3ea 5385 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5386 }, {
5387 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5388 'info_dict': {
5389 'id': 'a48o2S1cPoo',
5390 'ext': 'mp4',
5391 'title': 'The Young Turks - Live Main Show',
5392 'uploader': 'The Young Turks',
5393 'uploader_id': 'TheYoungTurks',
5394 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5395 'upload_date': '20150715',
5396 'license': 'Standard YouTube License',
5397 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5398 'categories': ['News & Politics'],
5399 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5400 'like_count': int,
a6213a49 5401 },
5402 'params': {
5403 'skip_download': True,
5404 },
5405 'only_matching': True,
5406 }, {
5407 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5408 'only_matching': True,
5409 }, {
5410 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5411 'only_matching': True,
5412 }, {
5413 'note': 'A channel that is not live. Should raise error',
5414 'url': 'https://www.youtube.com/user/numberphile/live',
5415 'only_matching': True,
5416 }, {
5417 'url': 'https://www.youtube.com/feed/trending',
5418 'only_matching': True,
5419 }, {
5420 'url': 'https://www.youtube.com/feed/library',
5421 'only_matching': True,
5422 }, {
5423 'url': 'https://www.youtube.com/feed/history',
5424 'only_matching': True,
5425 }, {
5426 'url': 'https://www.youtube.com/feed/subscriptions',
5427 'only_matching': True,
5428 }, {
5429 'url': 'https://www.youtube.com/feed/watch_later',
5430 'only_matching': True,
5431 }, {
5432 'note': 'Recommended - redirects to home page.',
5433 'url': 'https://www.youtube.com/feed/recommended',
5434 'only_matching': True,
5435 }, {
5436 'note': 'inline playlist with not always working continuations',
5437 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5438 'only_matching': True,
5439 }, {
5440 'url': 'https://www.youtube.com/course',
5441 'only_matching': True,
5442 }, {
5443 'url': 'https://www.youtube.com/zsecurity',
5444 'only_matching': True,
5445 }, {
5446 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5447 'only_matching': True,
5448 }, {
5449 'url': 'https://www.youtube.com/TheYoungTurks/live',
5450 'only_matching': True,
5451 }, {
5452 'url': 'https://www.youtube.com/hashtag/cctv9',
5453 'info_dict': {
5454 'id': 'cctv9',
5455 'title': '#cctv9',
976ae3ea 5456 'tags': [],
a6213a49 5457 },
5458 'playlist_mincount': 350,
5459 }, {
5460 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5461 'only_matching': True,
5462 }, {
5463 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5464 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5465 'only_matching': True
5466 }, {
5467 'note': '/browse/ should redirect to /channel/',
5468 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5469 'only_matching': True
5470 }, {
5471 'note': 'VLPL, should redirect to playlist?list=PL...',
5472 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5473 'info_dict': {
5474 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5475 'uploader': 'NoCopyrightSounds',
5476 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5477 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5478 'title': 'NCS : All Releases 💿',
976ae3ea 5479 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5480 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5481 'modified_date': r're:\d{8}',
5482 'view_count': int,
5483 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5484 'tags': [],
5485 'channel': 'NoCopyrightSounds',
c26f9b99 5486 'availability': 'public',
a6213a49 5487 },
5488 'playlist_mincount': 166,
976ae3ea 5489 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5490 }, {
5491 'note': 'Topic, should redirect to playlist?list=UU...',
5492 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5493 'info_dict': {
5494 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5495 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5496 'title': 'Uploads from Royalty Free Music - Topic',
5497 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5498 'tags': [],
5499 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5500 'channel': 'Royalty Free Music - Topic',
5501 'view_count': int,
5502 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5503 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5504 'modified_date': r're:\d{8}',
5505 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5506 'description': '',
c26f9b99 5507 'availability': 'public',
a6213a49 5508 },
5509 'expected_warnings': [
a6213a49 5510 'The URL does not have a videos tab',
976ae3ea 5511 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5512 ],
5513 'playlist_mincount': 101,
5514 }, {
5515 'note': 'Topic without a UU playlist',
5516 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5517 'info_dict': {
5518 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5519 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5520 'tags': [],
a6213a49 5521 },
5522 'expected_warnings': [
976ae3ea 5523 'the playlist redirect gave error',
a6213a49 5524 ],
5525 'playlist_mincount': 9,
5526 }, {
5527 'note': 'Youtube music Album',
5528 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5529 'info_dict': {
5530 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5531 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5532 'tags': [],
5533 'view_count': int,
5534 'description': '',
5535 'availability': 'unlisted',
5536 'modified_date': r're:\d{8}',
a6213a49 5537 },
5538 'playlist_count': 50,
5539 }, {
5540 'note': 'unlisted single video playlist',
5541 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5542 'info_dict': {
5543 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5544 'uploader': 'colethedj',
5545 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5546 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5547 'availability': 'unlisted',
5548 'tags': [],
12a1b225 5549 'modified_date': '20220418',
976ae3ea 5550 'channel': 'colethedj',
5551 'view_count': int,
5552 'description': '',
5553 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5554 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5555 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5556 },
5557 'playlist_count': 1,
5558 }, {
5559 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5560 'url': 'https://www.youtube.com/feed/recommended',
5561 'info_dict': {
5562 'id': 'recommended',
5563 'title': 'recommended',
6c73052c 5564 'tags': [],
a6213a49 5565 },
5566 'playlist_mincount': 50,
5567 'params': {
5568 'skip_download': True,
5569 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5570 },
5571 }, {
5572 'note': 'API Fallback: /videos tab, sorted by oldest first',
5573 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5574 'info_dict': {
5575 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5576 'title': 'Cody\'sLab - Videos',
5577 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5578 'uploader': 'Cody\'sLab',
5579 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5580 'channel': 'Cody\'sLab',
5581 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5582 'tags': [],
5583 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5584 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5585 'channel_follower_count': int
a6213a49 5586 },
5587 'playlist_mincount': 650,
5588 'params': {
5589 'skip_download': True,
5590 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5591 },
5592 }, {
5593 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5594 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5595 'info_dict': {
5596 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5597 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5598 'title': 'Uploads from Royalty Free Music - Topic',
5599 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5600 'modified_date': r're:\d{8}',
5601 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5602 'description': '',
5603 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5604 'tags': [],
5605 'channel': 'Royalty Free Music - Topic',
5606 'view_count': int,
5607 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5608 'availability': 'public',
a6213a49 5609 },
5610 'expected_warnings': [
976ae3ea 5611 'does not have a videos tab',
5612 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5613 ],
5614 'playlist_mincount': 101,
5615 'params': {
5616 'skip_download': True,
5617 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5618 },
7c219ea6 5619 }, {
5620 'note': 'non-standard redirect to regional channel',
5621 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5622 'only_matching': True
61d3665d 5623 }, {
5624 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5625 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5626 'info_dict': {
5627 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5628 'modified_date': '20220407',
5629 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5630 'tags': [],
5631 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5632 'uploader': 'pukkandan',
5633 'availability': 'unlisted',
5634 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5635 'channel': 'pukkandan',
5636 'description': 'Test for collaborative playlist',
5637 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5638 'view_count': int,
61d3665d 5639 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5640 },
5641 'playlist_mincount': 2
c26f9b99 5642 }, {
5643 'note': 'translated tab name',
5644 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5645 'info_dict': {
5646 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5647 'tags': [],
5648 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5649 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5650 'description': '',
5651 'title': 'cole-dlp-test-acc - 再生リスト',
5652 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5653 'uploader': 'cole-dlp-test-acc',
5654 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5655 'channel': 'cole-dlp-test-acc',
5656 },
5657 'playlist_mincount': 1,
5658 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5659 'expected_warnings': ['Preferring "ja"'],
5660 }, {
5661 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5662 'note': 'preferred lang set with playlist with translated video titles',
5663 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5664 'info_dict': {
5665 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5666 'tags': [],
5667 'view_count': int,
5668 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5669 'uploader': 'cole-dlp-test-acc',
5670 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5671 'channel': 'cole-dlp-test-acc',
5672 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5673 'description': 'test',
5674 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5675 'title': 'dlp test playlist',
5676 'availability': 'public',
5677 },
5678 'playlist_mincount': 1,
5679 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5680 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5681 }, {
5682 # shorts audio pivot for 2GtVksBMYFM.
5683 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5684 'info_dict': {
5685 'id': 'sfv_audio_pivot',
5686 'title': 'sfv_audio_pivot',
5687 'tags': [],
5688 },
5689 'playlist_mincount': 50,
5690
a6213a49 5691 }]
5692
5693 @classmethod
5694 def suitable(cls, url):
86e5f3ed 5695 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5696
64f36541 5697 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5698
182bda88 5699 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5700 def _real_extract(self, url, smuggled_data):
cd7c66cf 5701 item_id = self._match_id(url)
14f25df2 5702 url = urllib.parse.urlunparse(
5703 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5704 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5705
fe03a6cd 5706 def get_mobj(url):
37e57a9f 5707 mobj = self._URL_RE.match(url).groupdict()
07cce701 5708 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5709 return mobj
5710
37e57a9f 5711 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5712 # Youtube returns incomplete data if tabname is not lower case
5713 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5714 if is_channel:
5715 if smuggled_data.get('is_music_url'):
37e57a9f 5716 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5717 item_id = item_id[2:]
37e57a9f 5718 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5719 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5720 mdata = self._extract_tab_endpoint(
37e57a9f 5721 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5722 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5723 get_all=False, expected_type=str)
ac56cf38 5724 if not murl:
37e57a9f 5725 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5726 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5727 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5728 pre = f'https://www.youtube.com/channel/{item_id}'
5729
64f36541 5730 original_tab_name = tab
fe03a6cd 5731 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5732 # Home URLs should redirect to /videos/
37e57a9f 5733 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5734 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5735 tab = '/videos'
5736
5737 url = ''.join((pre, tab, post))
5738 mobj = get_mobj(url)
cd7c66cf 5739
5740 # Handle both video/playlist URLs
201c1459 5741 qs = parse_qs(url)
86e5f3ed 5742 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5743
fe03a6cd 5744 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5745 if not playlist_id:
fe03a6cd 5746 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5747 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5748 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5749 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5750 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5751 mobj = get_mobj(url)
cd7c66cf 5752
5753 if video_id and playlist_id:
a06916d9 5754 if self.get_param('noplaylist'):
37e57a9f 5755 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5756 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5757 ie=YoutubeIE.ie_key(), video_id=video_id)
5758 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5759
ac56cf38 5760 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5761
7c219ea6 5762 # YouTube may provide a non-standard redirect to the regional channel
5763 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5764 redirect_url = traverse_obj(
5765 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5766 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5767 redirect_url = ''.join((
5768 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5769 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5770 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5771
37e57a9f 5772 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5773 if tabs:
5774 selected_tab = self._extract_selected_tab(tabs)
c26f9b99 5775 selected_tab_url = urljoin(
5776 url, traverse_obj(selected_tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5777 translated_tab_name = selected_tab.get('title', '').lower()
5778
5779 # Prefer tab name from tab url as it is always in en,
5780 # but only when preferred lang is set as it may not extract reliably in all cases.
5781 selected_tab_name = (self._preferred_lang in (None, 'en') and translated_tab_name
5782 or selected_tab_url and get_mobj(selected_tab_url)['tab'][1:] # primary
5783 or translated_tab_name)
5784
64f36541 5785 if selected_tab_name == 'home':
5786 selected_tab_name = 'featured'
5787 requested_tab_name = mobj['tab'][1:]
c26f9b99 5788
09f1580e 5789 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5790 if requested_tab_name == 'live': # Live tab should have redirected to the video
5791 raise UserNotLive(video_id=mobj['id'])
64f36541 5792 if requested_tab_name not in ('', selected_tab_name):
5793 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5794 if not original_tab_name:
5795 if item_id[:2] == 'UC':
5796 # Topic channels don't have /videos. Use the equivalent playlist instead
5797 pl_id = f'UU{item_id[2:]}'
5798 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5799 try:
5800 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5801 except ExtractorError:
5802 redirect_warning += ' and the playlist redirect gave error'
5803 else:
5804 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5805 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5806 if selected_tab_name and selected_tab_name != requested_tab_name:
5807 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5808 else:
5809 raise ExtractorError(redirect_warning, expected=True)
18db7548 5810
37e57a9f 5811 if redirect_warning:
64f36541 5812 self.to_screen(redirect_warning)
37e57a9f 5813 self.write_debug(f'Final URL: {url}')
18db7548 5814
358de58c 5815 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5816 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5817 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5818 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5819 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5820 if tabs:
ac56cf38 5821 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5822
37e57a9f 5823 playlist = traverse_obj(
5824 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5825 if playlist:
ac56cf38 5826 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5827
37e57a9f 5828 video_id = traverse_obj(
5829 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5830 if video_id:
09f1580e 5831 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5832 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5833 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5834 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5835
8bdd16b4 5836 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5837
c5e8d7af 5838
8bdd16b4 5839class YoutubePlaylistIE(InfoExtractor):
96565c7e 5840 IE_DESC = 'YouTube playlists'
8bdd16b4 5841 _VALID_URL = r'''(?x)(?:
5842 (?:https?://)?
5843 (?:\w+\.)?
5844 (?:
5845 (?:
5846 youtube(?:kids)?\.com|
d9190e44 5847 %(invidious)s
8bdd16b4 5848 )
5849 /.*?\?.*?\blist=
5850 )?
5851 (?P<id>%(playlist_id)s)
d9190e44
RH
5852 )''' % {
5853 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5854 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5855 }
8bdd16b4 5856 IE_NAME = 'youtube:playlist'
cdc628a4 5857 _TESTS = [{
8bdd16b4 5858 'note': 'issue #673',
5859 'url': 'PLBB231211A4F62143',
cdc628a4 5860 'info_dict': {
8bdd16b4 5861 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5862 'id': 'PLBB231211A4F62143',
976ae3ea 5863 'uploader': 'Wickman',
8bdd16b4 5864 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5865 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5866 'view_count': int,
5867 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5868 'modified_date': r're:\d{8}',
5869 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5870 'channel': 'Wickman',
5871 'tags': [],
5872 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5873 },
5874 'playlist_mincount': 29,
5875 }, {
5876 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5877 'info_dict': {
5878 'title': 'YDL_safe_search',
5879 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5880 },
5881 'playlist_count': 2,
5882 'skip': 'This playlist is private',
9558dcec 5883 }, {
8bdd16b4 5884 'note': 'embedded',
5885 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5886 'playlist_count': 4,
9558dcec 5887 'info_dict': {
8bdd16b4 5888 'title': 'JODA15',
5889 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5890 'uploader': 'milan',
5891 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5892 'description': '',
5893 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5894 'tags': [],
5895 'modified_date': '20140919',
5896 'view_count': int,
5897 'channel': 'milan',
5898 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5899 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 5900 'availability': 'public',
976ae3ea 5901 },
5902 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5903 }, {
8bdd16b4 5904 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5905 'playlist_mincount': 455,
8bdd16b4 5906 'info_dict': {
5907 'title': '2018 Chinese New Singles (11/6 updated)',
5908 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5909 'uploader': 'LBK',
5910 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5911 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5912 'channel': 'LBK',
5913 'view_count': int,
5914 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5915 'tags': [],
5916 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5917 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5918 'modified_date': r're:\d{8}',
c26f9b99 5919 'availability': 'public',
976ae3ea 5920 },
5921 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5922 }, {
29f7c58a 5923 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5924 'only_matching': True,
5925 }, {
5926 # music album playlist
5927 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5928 'only_matching': True,
5929 }]
5930
5931 @classmethod
5932 def suitable(cls, url):
201c1459 5933 if YoutubeTabIE.suitable(url):
5934 return False
49a57e70 5935 from ..utils import parse_qs
201c1459 5936 qs = parse_qs(url)
5937 if qs.get('v', [None])[0]:
5938 return False
86e5f3ed 5939 return super().suitable(url)
29f7c58a 5940
5941 def _real_extract(self, url):
5942 playlist_id = self._match_id(url)
46953e7e 5943 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5944 url = update_url_query(
5945 'https://www.youtube.com/playlist',
5946 parse_qs(url) or {'list': playlist_id})
5947 if is_music_url:
5948 url = smuggle_url(url, {'is_music_url': True})
5949 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5950
5951
5952class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5953 IE_DESC = 'youtu.be'
29f7c58a 5954 _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}
5955 _TESTS = [{
8bdd16b4 5956 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5957 'info_dict': {
5958 'id': 'yeWKywCrFtk',
5959 'ext': 'mp4',
5960 'title': 'Small Scale Baler and Braiding Rugs',
5961 'uploader': 'Backus-Page House Museum',
5962 'uploader_id': 'backuspagemuseum',
5963 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5964 'upload_date': '20161008',
5965 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5966 'categories': ['Nonprofits & Activism'],
5967 'tags': list,
5968 'like_count': int,
976ae3ea 5969 'age_limit': 0,
5970 'playable_in_embed': True,
5971 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5972 'channel': 'Backus-Page House Museum',
5973 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5974 'live_status': 'not_live',
5975 'view_count': int,
5976 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5977 'availability': 'public',
5978 'duration': 59,
12a1b225
A
5979 'comment_count': int,
5980 'channel_follower_count': int
8bdd16b4 5981 },
5982 'params': {
5983 'noplaylist': True,
5984 'skip_download': True,
5985 },
39e7107d 5986 }, {
8bdd16b4 5987 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5988 'only_matching': True,
cdc628a4
PH
5989 }]
5990
8bdd16b4 5991 def _real_extract(self, url):
5ad28e7f 5992 mobj = self._match_valid_url(url)
29f7c58a 5993 video_id = mobj.group('id')
5994 playlist_id = mobj.group('playlist_id')
8bdd16b4 5995 return self.url_result(
29f7c58a 5996 update_url_query('https://www.youtube.com/watch', {
5997 'v': video_id,
5998 'list': playlist_id,
5999 'feature': 'youtu.be',
6000 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6001
6002
b6ce9bb0 6003class YoutubeLivestreamEmbedIE(InfoExtractor):
6004 IE_DESC = 'YouTube livestream embeds'
6005 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6006 _TESTS = [{
6007 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6008 'only_matching': True,
6009 }]
6010
6011 def _real_extract(self, url):
6012 channel_id = self._match_id(url)
6013 return self.url_result(
6014 f'https://www.youtube.com/channel/{channel_id}/live',
6015 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6016
6017
8bdd16b4 6018class YoutubeYtUserIE(InfoExtractor):
96565c7e 6019 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6020 IE_NAME = 'youtube:user'
8bdd16b4 6021 _VALID_URL = r'ytuser:(?P<id>.+)'
6022 _TESTS = [{
6023 'url': 'ytuser:phihag',
6024 'only_matching': True,
6025 }]
6026
6027 def _real_extract(self, url):
6028 user_id = self._match_id(url)
6029 return self.url_result(
c586f9e8 6030 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 6031 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 6032
b05654f0 6033
3d3dddc9 6034class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6035 IE_NAME = 'youtube:favorites'
96565c7e 6036 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6037 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6038 _LOGIN_REQUIRED = True
6039 _TESTS = [{
6040 'url': ':ytfav',
6041 'only_matching': True,
6042 }, {
6043 'url': ':ytfavorites',
6044 'only_matching': True,
6045 }]
6046
6047 def _real_extract(self, url):
6048 return self.url_result(
6049 'https://www.youtube.com/playlist?list=LL',
6050 ie=YoutubeTabIE.ie_key())
6051
6052
ca5300c7 6053class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6054 IE_NAME = 'youtube:notif'
6055 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6056 _VALID_URL = r':ytnotif(?:ication)?s?'
6057 _LOGIN_REQUIRED = True
6058 _TESTS = [{
6059 'url': ':ytnotif',
6060 'only_matching': True,
6061 }, {
6062 'url': ':ytnotifications',
6063 'only_matching': True,
6064 }]
6065
6066 def _extract_notification_menu(self, response, continuation_list):
6067 notification_list = traverse_obj(
6068 response,
6069 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6070 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6071 expected_type=list) or []
6072 continuation_list[0] = None
6073 for item in notification_list:
6074 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6075 if entry:
6076 yield entry
6077 continuation = item.get('continuationItemRenderer')
6078 if continuation:
6079 continuation_list[0] = continuation
6080
6081 def _extract_notification_renderer(self, notification):
6082 video_id = traverse_obj(
6083 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6084 url = f'https://www.youtube.com/watch?v={video_id}'
6085 channel_id = None
6086 if not video_id:
6087 browse_ep = traverse_obj(
6088 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6089 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6090 post_id = self._search_regex(
6091 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6092 'post id', default=None)
6093 if not channel_id or not post_id:
6094 return
6095 # The direct /post url redirects to this in the browser
6096 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6097
6098 channel = traverse_obj(
6099 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6100 expected_type=str)
c7a7baaa 6101 notification_title = self._get_text(notification, 'shortMessage')
6102 if notification_title:
6103 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6104 # TODO: handle recommended videos
ca5300c7 6105 title = self._search_regex(
c7a7baaa 6106 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6107 'video title', default=None)
c26f9b99 6108 upload_date = (strftime_or_none(self._parse_time_text(self._get_text(notification, 'sentTimeText')), '%Y%m%d')
ca5300c7 6109 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
6110 else None)
6111 return {
6112 '_type': 'url',
6113 'url': url,
6114 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6115 'video_id': video_id,
6116 'title': title,
6117 'channel_id': channel_id,
6118 'channel': channel,
6119 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
6120 'upload_date': upload_date,
6121 }
6122
6123 def _notification_menu_entries(self, ytcfg):
6124 continuation_list = [None]
6125 response = None
6126 for page in itertools.count(1):
6127 ctoken = traverse_obj(
6128 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6129 response = self._extract_response(
6130 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6131 ep='notification/get_notification_menu', check_get_keys='actions',
6132 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6133 yield from self._extract_notification_menu(response, continuation_list)
6134 if not continuation_list[0]:
6135 break
6136
6137 def _real_extract(self, url):
6138 display_id = 'notifications'
6139 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6140 self._report_playlist_authcheck(ytcfg)
6141 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6142
6143
a6213a49 6144class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6145 IE_DESC = 'YouTube search'
78caa52a 6146 IE_NAME = 'youtube:search'
b05654f0 6147 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6148 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6149 _TESTS = [{
6150 'url': 'ytsearch5:youtube-dl test video',
6151 'playlist_count': 5,
6152 'info_dict': {
6153 'id': 'youtube-dl test video',
6154 'title': 'youtube-dl test video',
6155 }
6156 }]
b05654f0 6157
a61fd4cf 6158
5f7cb91a 6159class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6160 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6161 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6162 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6163 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6164 _TESTS = [{
6165 'url': 'ytsearchdate5:youtube-dl test video',
6166 'playlist_count': 5,
6167 'info_dict': {
6168 'id': 'youtube-dl test video',
6169 'title': 'youtube-dl test video',
6170 }
6171 }]
75dff0ee 6172
c9ae7b95 6173
a6213a49 6174class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6175 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6176 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6177 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6178 _TESTS = [{
6179 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6180 'playlist_mincount': 5,
6181 'info_dict': {
11f9be09 6182 'id': 'youtube-dl test video',
3462ffa8 6183 'title': 'youtube-dl test video',
6184 }
a61fd4cf 6185 }, {
6186 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6187 'playlist_mincount': 5,
6188 'info_dict': {
6189 'id': 'python',
6190 'title': 'python',
6191 }
ad210f4f 6192 }, {
6193 'url': 'https://www.youtube.com/results?search_query=%23cats',
6194 'playlist_mincount': 1,
6195 'info_dict': {
6196 'id': '#cats',
6197 'title': '#cats',
12a1b225
A
6198 # The test suite does not have support for nested playlists
6199 # 'entries': [{
6200 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6201 # 'title': '#cats',
6202 # }],
ad210f4f 6203 },
3462ffa8 6204 }, {
6205 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6206 'only_matching': True,
6207 }]
6208
6209 def _real_extract(self, url):
4dfbf869 6210 qs = parse_qs(url)
386e1dd9 6211 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6212 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6213
6214
16aa9ea4 6215class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6216 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6217 IE_NAME = 'youtube:music:search_url'
6218 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6219 _TESTS = [{
6220 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6221 'playlist_count': 16,
6222 'info_dict': {
6223 'id': 'royalty free music',
6224 'title': 'royalty free music',
6225 }
6226 }, {
6227 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6228 'playlist_mincount': 30,
6229 'info_dict': {
6230 'id': 'royalty free music - songs',
6231 'title': 'royalty free music - songs',
6232 },
6233 'params': {'extract_flat': 'in_playlist'}
6234 }, {
6235 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6236 'playlist_mincount': 30,
6237 'info_dict': {
6238 'id': 'royalty free music - community playlists',
6239 'title': 'royalty free music - community playlists',
6240 },
6241 'params': {'extract_flat': 'in_playlist'}
6242 }]
6243
6244 _SECTIONS = {
6245 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6246 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6247 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6248 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6249 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6250 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6251 }
6252
6253 def _real_extract(self, url):
6254 qs = parse_qs(url)
6255 query = (qs.get('search_query') or qs.get('q'))[0]
6256 params = qs.get('sp', (None,))[0]
6257 if params:
6258 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6259 else:
ac668111 6260 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6261 params = self._SECTIONS.get(section)
6262 if not params:
6263 section = None
6264 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6265 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6266
6267
182bda88 6268class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6269 """
25f14e9f 6270 Base class for feed extractors
82d02080 6271 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6272 """
b2e8bc1b 6273 _LOGIN_REQUIRED = True
82d02080 6274 _FEED_NAME = 'feeds'
a25bca9f 6275
6276 def _real_initialize(self):
6277 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6278
82d02080 6279 @classproperty
d7ae0639 6280 def IE_NAME(self):
82d02080 6281 return f'youtube:{self._FEED_NAME}'
04cc9617 6282
3853309f 6283 def _real_extract(self, url):
3d3dddc9 6284 return self.url_result(
182bda88 6285 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6286
6287
ef2f3c7f 6288class YoutubeWatchLaterIE(InfoExtractor):
6289 IE_NAME = 'youtube:watchlater'
96565c7e 6290 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6291 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6292 _TESTS = [{
8bdd16b4 6293 'url': ':ytwatchlater',
bc7a9cd8
S
6294 'only_matching': True,
6295 }]
25f14e9f
S
6296
6297 def _real_extract(self, url):
ef2f3c7f 6298 return self.url_result(
6299 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6300
6301
25f14e9f 6302class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6303 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6304 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6305 _FEED_NAME = 'recommended'
45db527f 6306 _LOGIN_REQUIRED = False
3d3dddc9 6307 _TESTS = [{
6308 'url': ':ytrec',
6309 'only_matching': True,
6310 }, {
6311 'url': ':ytrecommended',
6312 'only_matching': True,
6313 }, {
6314 'url': 'https://youtube.com',
6315 'only_matching': True,
6316 }]
1ed5b5c9 6317
1ed5b5c9 6318
25f14e9f 6319class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6320 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6321 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6322 _FEED_NAME = 'subscriptions'
3d3dddc9 6323 _TESTS = [{
6324 'url': ':ytsubs',
6325 'only_matching': True,
6326 }, {
6327 'url': ':ytsubscriptions',
6328 'only_matching': True,
6329 }]
1ed5b5c9 6330
1ed5b5c9 6331
25f14e9f 6332class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6333 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6334 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6335 _FEED_NAME = 'history'
3d3dddc9 6336 _TESTS = [{
6337 'url': ':ythistory',
6338 'only_matching': True,
6339 }]
1ed5b5c9
JMF
6340
6341
6e634cbe 6342class YoutubeStoriesIE(InfoExtractor):
6343 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6344 IE_NAME = 'youtube:stories'
6345 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6346 _TESTS = [{
6347 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6348 'only_matching': True,
6349 }]
6350
6351 def _real_extract(self, url):
6352 playlist_id = f'RLTD{self._match_id(url)}'
6353 return self.url_result(
50ac0e54 6354 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6355 ie=YoutubeTabIE, video_id=playlist_id)
6356
6357
80eb0bd9 6358class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6359 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6360 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6361 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6362 _TESTS = [{
1dd18a88 6363 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6364 'only_matching': True,
6365 }]
6366
6367 @staticmethod
6368 def _generate_audio_pivot_params(video_id):
6369 """
6370 Generates sfv_audio_pivot browse params for this video id
6371 """
6372 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6373 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6374
6375 def _real_extract(self, url):
6376 video_id = self._match_id(url)
6377 return self.url_result(
6378 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6379 ie=YoutubeTabIE)
6380
6381
15870e90
PH
6382class YoutubeTruncatedURLIE(InfoExtractor):
6383 IE_NAME = 'youtube:truncated_url'
6384 IE_DESC = False # Do not list
975d35db 6385 _VALID_URL = r'''(?x)
b95aab84
PH
6386 (?:https?://)?
6387 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6388 (?:watch\?(?:
c4808c60 6389 feature=[a-z_]+|
b95aab84
PH
6390 annotation_id=annotation_[^&]+|
6391 x-yt-cl=[0-9]+|
c1708b89 6392 hl=[^&]*|
287be8c6 6393 t=[0-9]+
b95aab84
PH
6394 )?
6395 |
6396 attribution_link\?a=[^&]+
6397 )
6398 $
975d35db 6399 '''
15870e90 6400
c4808c60 6401 _TESTS = [{
2d3d2997 6402 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6403 'only_matching': True,
dc2fc736 6404 }, {
2d3d2997 6405 'url': 'https://www.youtube.com/watch?',
dc2fc736 6406 'only_matching': True,
b95aab84
PH
6407 }, {
6408 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6409 'only_matching': True,
6410 }, {
6411 'url': 'https://www.youtube.com/watch?feature=foo',
6412 'only_matching': True,
c1708b89
PH
6413 }, {
6414 'url': 'https://www.youtube.com/watch?hl=en-GB',
6415 'only_matching': True,
287be8c6
PH
6416 }, {
6417 'url': 'https://www.youtube.com/watch?t=2372',
6418 'only_matching': True,
c4808c60
PH
6419 }]
6420
15870e90
PH
6421 def _real_extract(self, url):
6422 raise ExtractorError(
78caa52a
PH
6423 'Did you forget to quote the URL? Remember that & is a meta '
6424 'character in most shells, so you want to put the URL in quotes, '
3867038a 6425 'like youtube-dl '
2d3d2997 6426 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6427 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6428 expected=True)
772fd5cc
PH
6429
6430
471d0367 6431class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6432 IE_NAME = 'youtube:clip'
471d0367 6433 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6434 _TESTS = [{
6435 # FIXME: Other metadata should be extracted from the clip, not from the base video
6436 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6437 'info_dict': {
6438 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6439 'ext': 'mp4',
6440 'section_start': 29.0,
6441 'section_end': 39.7,
6442 'duration': 10.7,
12a1b225
A
6443 'age_limit': 0,
6444 'availability': 'public',
6445 'categories': ['Gaming'],
6446 'channel': 'Scott The Woz',
6447 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6448 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6449 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6450 'like_count': int,
6451 'playable_in_embed': True,
6452 'tags': 'count:17',
6453 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6454 'title': 'Mobile Games on Console - Scott The Woz',
6455 'upload_date': '20210920',
6456 'uploader': 'Scott The Woz',
6457 'uploader_id': 'scottthewoz',
6458 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6459 'view_count': int,
6460 'live_status': 'not_live',
6461 'channel_follower_count': int
471d0367 6462 }
6463 }]
3cd786db 6464
6465 def _real_extract(self, url):
471d0367 6466 clip_id = self._match_id(url)
6467 _, data = self._extract_webpage(url, clip_id)
6468
6469 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6470 if not video_id:
6471 raise ExtractorError('Unable to find video ID')
6472
6473 clip_data = traverse_obj(data, (
6474 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6475 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6476 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6477 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6478
6479 return {
6480 '_type': 'url_transparent',
6481 'url': f'https://www.youtube.com/watch?v={video_id}',
6482 'ie_key': YoutubeIE.ie_key(),
6483 'id': clip_id,
6484 'section_start': int(clip_data['startTimeMs']) / 1000,
6485 'section_end': int(clip_data['endTimeMs']) / 1000,
6486 }
3cd786db 6487
6488
772fd5cc
PH
6489class YoutubeTruncatedIDIE(InfoExtractor):
6490 IE_NAME = 'youtube:truncated_id'
6491 IE_DESC = False # Do not list
b95aab84 6492 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6493
6494 _TESTS = [{
6495 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6496 'only_matching': True,
6497 }]
6498
6499 def _real_extract(self, url):
6500 video_id = self._match_id(url)
6501 raise ExtractorError(
86e5f3ed 6502 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6503 expected=True)