]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[build] `py2exe`: Migrate to freeze API (#5149)
[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',
d1c4f6d4 372 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 373 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 374 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
375 r'(?:www\.)?watch\.whatever\.social',
376 r'(?:www\.)?piped\.garudalinux\.org',
377 r'(?:www\.)?piped\.rivo\.lol',
378 r'(?:www\.)?piped-libre\.kavin\.rocks',
379 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 380 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
381 r'(?:www\.)?il\.ax',
382 r'(?:www\.)?piped\.esmailelbob\.xyz',
383 r'(?:www\.)?piped\.projectsegfau\.lt',
384 r'(?:www\.)?piped\.privacydev\.net',
385 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
386 r'(?:www\.)?piped\.smnz\.de',
387 r'(?:www\.)?piped\.adminforge\.de',
388 r'(?:www\.)?watch\.whatevertinfoil\.de',
389 r'(?:www\.)?piped\.qdi\.fi',
d9190e44
RH
390 )
391
c26f9b99 392 # extracted from account/account_menu ep
393 # XXX: These are the supported YouTube UI and API languages,
394 # which is slightly different from languages supported for translation in YouTube studio
395 _SUPPORTED_LANG_CODES = [
396 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
397 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
398 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
399 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
400 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
401 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
402 ]
403
a057779d 404 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
405
c26f9b99 406 @functools.cached_property
407 def _preferred_lang(self):
408 """
409 Returns a language code supported by YouTube for the user preferred language.
410 Returns None if no preferred language set.
411 """
412 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
413 if not preferred_lang:
414 return
415 if preferred_lang not in self._SUPPORTED_LANG_CODES:
416 raise ExtractorError(
417 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
418 expected=True)
419 elif preferred_lang != 'en':
420 self.report_warning(
421 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
422 return preferred_lang
423
cce889b9 424 def _initialize_consent(self):
425 cookies = self._get_cookies('https://www.youtube.com/')
426 if cookies.get('__Secure-3PSID'):
427 return
428 consent_id = None
429 consent = cookies.get('CONSENT')
430 if consent:
431 if 'YES' in consent.value:
432 return
433 consent_id = self._search_regex(
434 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
435 if not consent_id:
436 consent_id = random.randint(100, 999)
437 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 438
f3aa3c3f 439 def _initialize_pref(self):
440 cookies = self._get_cookies('https://www.youtube.com/')
441 pref_cookie = cookies.get('PREF')
442 pref = {}
443 if pref_cookie:
444 try:
14f25df2 445 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 446 except ValueError:
447 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 448 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 449 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 450
b2e8bc1b 451 def _real_initialize(self):
f3aa3c3f 452 self._initialize_pref()
cce889b9 453 self._initialize_consent()
a25bca9f 454 self._check_login_required()
455
456 def _check_login_required(self):
24146491 457 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 458 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 459
b7c47b74 460 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
461 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 462
000c15a4 463 def _get_default_ytcfg(self, client='web'):
464 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 465
000c15a4 466 def _get_innertube_host(self, client='web'):
467 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 468
000c15a4 469 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 470 # try_get but with fallback to default ytcfg client values when present
471 _func = lambda y: try_get(y, getter, expected_type)
472 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
473
000c15a4 474 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 475 return self._ytcfg_get_safe(
476 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 477 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 478
000c15a4 479 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 480 return self._ytcfg_get_safe(
481 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 482 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 483
2ae778b8 484 def _select_api_hostname(self, req_api_hostname, default_client=None):
485 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
486 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
487
000c15a4 488 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 489 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 490
000c15a4 491 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 492 context = get_first(
493 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 494 # Enforce language and tz for extraction
495 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 496 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 497 return context
498
cf87314d 499 _SAPISID = None
500
109dd3b2 501 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 502 time_now = round(time.time())
cf87314d 503 if self._SAPISID is None:
504 yt_cookies = self._get_cookies('https://www.youtube.com')
505 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
506 # See: https://github.com/yt-dlp/yt-dlp/issues/393
507 sapisid_cookie = dict_get(
508 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
509 if sapisid_cookie and sapisid_cookie.value:
510 self._SAPISID = sapisid_cookie.value
511 self.write_debug('Extracted SAPISID cookie')
512 # SAPISID cookie is required if not already present
513 if not yt_cookies.get('SAPISID'):
514 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
515 self._set_cookie(
516 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
517 else:
518 self._SAPISID = False
519 if not self._SAPISID:
520 return None
1974e99f 521 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
522 sapisidhash = hashlib.sha1(
86e5f3ed 523 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 524 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
525
526 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 527 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 528 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 529
109dd3b2 530 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 531 data.update(query)
11f9be09 532 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 533 real_headers.update({'content-type': 'application/json'})
534 if headers:
535 real_headers.update(headers)
2ae778b8 536 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
537 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 538 return self._download_json(
2ae778b8 539 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 540 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 541 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 542 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 543
65141660 544 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
545 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 546
99e9e001 547 @staticmethod
548 def _extract_session_index(*data):
549 """
550 Index of current account in account list.
551 See: https://github.com/yt-dlp/yt-dlp/pull/519
552 """
553 for ytcfg in data:
554 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
555 if session_index is not None:
556 return session_index
557
558 # Deprecated?
559 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 560 if ytcfg:
14f25df2 561 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
562 if token:
563 return token
99e9e001 564 if webpage:
565 return self._search_regex(
566 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
567 'identity token', default=None, fatal=False)
a1c5d2ca
M
568
569 @staticmethod
fe93e2c4 570 def _extract_account_syncid(*args):
8ea3f7b9 571 """
572 Extract syncId required to download private playlists of secondary channels
fe93e2c4 573 @params response and/or ytcfg
8ea3f7b9 574 """
fe93e2c4 575 for data in args:
576 # ytcfg includes channel_syncid if on secondary channel
14f25df2 577 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 578 if delegated_sid:
579 return delegated_sid
580 sync_ids = (try_get(
581 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 582 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 583 if len(sync_ids) >= 2 and sync_ids[1]:
584 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
585 # and just "user_syncid||" for primary channel. We only want the channel_syncid
586 return sync_ids[0]
a1c5d2ca 587
ac56cf38 588 @staticmethod
589 def _extract_visitor_data(*args):
590 """
591 Extracts visitorData from an API response or ytcfg
592 Appears to be used to track session state
593 """
9222c381 594 return get_first(
6c73052c 595 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 596 expected_type=str)
ac56cf38 597
2762dbb1 598 @functools.cached_property
99e9e001 599 def is_authenticated(self):
600 return bool(self._generate_sapisidhash_header())
601
11f9be09 602 def extract_ytcfg(self, video_id, webpage):
8c54a305 603 if not webpage:
604 return {}
29f7c58a 605 return self._parse_json(
606 self._search_regex(
607 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 608 default='{}'), video_id, fatal=False) or {}
609
11f9be09 610 def generate_api_headers(
99e9e001 611 self, *, ytcfg=None, account_syncid=None, session_index=None,
612 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
613
2ae778b8 614 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 615 headers = {
14f25df2 616 'X-YouTube-Client-Name': str(
11f9be09 617 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
618 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 619 'Origin': origin,
620 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
621 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 622 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
623 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 624 }
625 if session_index is None:
314ee305 626 session_index = self._extract_session_index(ytcfg)
627 if account_syncid or session_index is not None:
628 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 629
109dd3b2 630 auth = self._generate_sapisidhash_header(origin)
f4f751af 631 if auth is not None:
632 headers['Authorization'] = auth
109dd3b2 633 headers['X-Origin'] = origin
7a32c70d 634 return filter_dict(headers)
29f7c58a 635
a25bca9f 636 def _download_ytcfg(self, client, video_id):
637 url = {
638 'web': 'https://www.youtube.com',
639 'web_music': 'https://music.youtube.com',
640 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
641 }.get(client)
642 if not url:
643 return {}
644 webpage = self._download_webpage(
645 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
646 return self.extract_ytcfg(video_id, webpage) or {}
647
2d6659b9 648 @staticmethod
649 def _build_api_continuation_query(continuation, ctp=None):
650 query = {
651 'continuation': continuation
652 }
653 # TODO: Inconsistency with clickTrackingParams.
654 # Currently we have a fixed ctp contained within context (from ytcfg)
655 # and a ctp in root query for continuation.
656 if ctp:
657 query['clickTracking'] = {'clickTrackingParams': ctp}
658 return query
659
2d6659b9 660 @classmethod
661 def _extract_next_continuation_data(cls, renderer):
662 next_continuation = try_get(
663 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
664 lambda x: x['continuation']['reloadContinuationData']), dict)
665 if not next_continuation:
666 return
667 continuation = next_continuation.get('continuation')
668 if not continuation:
669 return
670 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 671 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 672
673 @classmethod
674 def _extract_continuation_ep_data(cls, continuation_ep: dict):
675 if isinstance(continuation_ep, dict):
676 continuation = try_get(
14f25df2 677 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 678 if not continuation:
679 return
680 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 681 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 682
683 @classmethod
684 def _extract_continuation(cls, renderer):
685 next_continuation = cls._extract_next_continuation_data(renderer)
686 if next_continuation:
687 return next_continuation
fe93e2c4 688
7a32c70d 689 return traverse_obj(renderer, (
690 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
691 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
692 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 693
fe93e2c4 694 @classmethod
695 def _extract_alerts(cls, data):
109dd3b2 696 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
697 if not isinstance(alert_dict, dict):
698 continue
699 for alert in alert_dict.values():
700 alert_type = alert.get('type')
701 if not alert_type:
702 continue
052e1350 703 message = cls._get_text(alert, 'text')
109dd3b2 704 if message:
705 yield alert_type, message
706
c0ac49bc 707 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 708 errors, warnings = [], []
109dd3b2 709 for alert_type, alert_message in alerts:
641ad5d8 710 if alert_type.lower() == 'error' and fatal:
109dd3b2 711 errors.append([alert_type, alert_message])
a057779d 712 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 713 warnings.append([alert_type, alert_message])
714
715 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 716 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 717 if errors:
718 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
719
720 def _extract_and_report_alerts(self, data, *args, **kwargs):
721 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
722
47193e02 723 def _extract_badges(self, renderer: dict):
c26f9b99 724 privacy_icon_map = {
725 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
726 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
727 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
728 }
729
730 badge_style_map = {
731 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
732 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
733 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
734 }
735
736 label_map = {
737 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
738 'private': BadgeType.AVAILABILITY_PRIVATE,
739 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
740 'live': BadgeType.LIVE_NOW,
741 'premium': BadgeType.AVAILABILITY_PREMIUM
742 }
743
744 badges = []
745 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer'), default=[]):
746 badge_type = (
747 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
748 or badge_style_map.get(traverse_obj(badge, 'style'))
749 )
750 if badge_type:
751 badges.append({'type': badge_type})
752 continue
753
754 # fallback, won't work in some languages
755 label = traverse_obj(badge, 'label', expected_type=str, default='')
756 for match, label_badge_type in label_map.items():
757 if match in label.lower():
758 badges.append({'type': badge_type})
759 continue
760
47193e02 761 return badges
762
c26f9b99 763 @staticmethod
764 def _has_badge(badges, badge_type):
765 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
766
47193e02 767 @staticmethod
052e1350 768 def _get_text(data, *path_list, max_runs=None):
769 for path in path_list or [None]:
770 if path is None:
771 obj = [data]
772 else:
773 obj = traverse_obj(data, path, default=[])
774 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
775 obj = [obj]
776 for item in obj:
14f25df2 777 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 778 if text:
779 return text
780 runs = try_get(item, lambda x: x['runs'], list) or []
781 if not runs and isinstance(item, list):
782 runs = item
783
784 runs = runs[:min(len(runs), max_runs or len(runs))]
785 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
786 if text:
787 return text
47193e02 788
f0d785d3 789 def _get_count(self, data, *path_list):
790 count_text = self._get_text(data, *path_list) or ''
791 count = parse_count(count_text)
792 if count is None:
793 count = str_to_int(
794 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
795 return count
796
a709d873 797 @staticmethod
798 def _extract_thumbnails(data, *path_list):
799 """
800 Extract thumbnails from thumbnails dict
801 @param path_list: path list to level that contains 'thumbnails' key
802 """
803 thumbnails = []
804 for path in path_list or [()]:
805 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
806 thumbnail_url = url_or_none(thumbnail.get('url'))
807 if not thumbnail_url:
808 continue
809 # Sometimes youtube gives a wrong thumbnail URL. See:
810 # https://github.com/yt-dlp/yt-dlp/issues/233
811 # https://github.com/ytdl-org/youtube-dl/issues/28023
812 if 'maxresdefault' in thumbnail_url:
813 thumbnail_url = thumbnail_url.split('?')[0]
814 thumbnails.append({
815 'url': thumbnail_url,
816 'height': int_or_none(thumbnail.get('height')),
817 'width': int_or_none(thumbnail.get('width')),
818 })
819 return thumbnails
820
f3aa3c3f 821 @staticmethod
822 def extract_relative_time(relative_time_text):
823 """
824 Extracts a relative time from string and converts to dt object
f0d785d3 825 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 826 """
f0d785d3 827 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 828 if mobj:
f0d785d3 829 start = mobj.group('start')
830 if start:
831 return datetime_from_str(start)
f3aa3c3f 832 try:
f0d785d3 833 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 834 except ValueError:
835 return None
836
c26f9b99 837 def _parse_time_text(self, text):
838 if not text:
839 return
f3aa3c3f 840 dt = self.extract_relative_time(text)
841 timestamp = None
842 if isinstance(dt, datetime.datetime):
843 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 844
845 if timestamp is None:
846 timestamp = (
847 unified_timestamp(text) or unified_timestamp(
848 self._search_regex(
17322130 849 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 850 text.lower(), 'time text', default=None)))
f0d785d3 851
c26f9b99 852 if text and timestamp is None and self._preferred_lang in (None, 'en'):
853 self.report_warning(
854 f'Cannot parse localized time text "{text}"', only_once=True)
855 return timestamp
f3aa3c3f 856
109dd3b2 857 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
858 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 859 default_client='web'):
be5c1ae8 860 for retry in self.RetryManager():
109dd3b2 861 try:
862 response = self._call_api(
863 ep=ep, fatal=True, headers=headers,
be5c1ae8 864 video_id=item_id, query=query, note=note,
109dd3b2 865 context=self._extract_context(ytcfg, default_client),
866 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 867 api_hostname=api_hostname, default_client=default_client)
109dd3b2 868 except ExtractorError as e:
be5c1ae8 869 if not isinstance(e.cause, network_exceptions):
870 return self._error_or_warning(e, fatal=fatal)
871 elif not isinstance(e.cause, urllib.error.HTTPError):
872 retry.error = e
873 continue
109dd3b2 874
be5c1ae8 875 first_bytes = e.cause.read(512)
876 if not is_html(first_bytes):
877 yt_error = try_get(
878 self._parse_json(
879 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
880 lambda x: x['error']['message'], str)
881 if yt_error:
882 self._report_alerts([('ERROR', yt_error)], fatal=False)
883 # Downloading page may result in intermittent 5xx HTTP error
884 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
885 # We also want to catch all other network exceptions since errors in later pages can be troublesome
886 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
887 if e.cause.code not in (403, 429):
888 retry.error = e
889 continue
890 return self._error_or_warning(e, fatal=fatal)
891
892 try:
893 self._extract_and_report_alerts(response, only_once=True)
894 except ExtractorError as e:
895 # YouTube servers may return errors we want to retry on in a 200 OK response
896 # See: https://github.com/yt-dlp/yt-dlp/issues/839
897 if 'unknown error' in e.msg.lower():
898 retry.error = e
899 continue
900 return self._error_or_warning(e, fatal=fatal)
901 # Youtube sometimes sends incomplete data
902 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
903 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 904 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 905 continue
906
907 return response
109dd3b2 908
9297939e 909 @staticmethod
910 def is_music_url(url):
911 return re.match(r'https?://music\.youtube\.com/', url) is not None
912
30a074c2 913 def _extract_video(self, renderer):
914 video_id = renderer.get('videoId')
4dc23a80
M
915
916 reel_header_renderer = traverse_obj(renderer, (
917 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
918 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
919
920 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 921 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
922
923 duration = int_or_none(renderer.get('lengthSeconds'))
924 if duration is None:
925 duration = parse_duration(self._get_text(
926 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 927 if duration is None:
4dc23a80 928 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 929 duration = parse_duration(self._search_regex(
930 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
931 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
932 video_id, default=None, group='duration'))
933
f3aa3c3f 934 channel_id = traverse_obj(
a44ca5a4 935 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
936 expected_type=str, get_all=False)
4dc23a80
M
937 if not channel_id:
938 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
939
f3aa3c3f 940 overlay_style = traverse_obj(
a44ca5a4 941 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
942 get_all=False, expected_type=str)
f3aa3c3f 943 badges = self._extract_badges(renderer)
4dc23a80 944
fd2ad7cb 945 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 946 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
947 expected_type=str)) or ''
fd2ad7cb 948 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 949 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 950 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 951
4dc23a80
M
952 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
953 or self._get_text(reel_header_renderer, 'timestampText') or '')
954 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
955
867c66ff
M
956 live_status = (
957 'is_upcoming' if scheduled_timestamp is not None
958 else 'was_live' if 'streamed' in time_text.lower()
959 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
960 else None)
961
4dc23a80
M
962 # videoInfo is a string like '50K views • 10 years ago'.
963 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
964 view_count = (0 if 'no views' in view_count_text.lower()
965 else self._get_count({'simpleText': view_count_text}))
966 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
967
30a074c2 968 return {
39ed931e 969 '_type': 'url',
30a074c2 970 'ie_key': YoutubeIE.ie_key(),
971 'id': video_id,
fd2ad7cb 972 'url': url,
30a074c2 973 'title': title,
974 'description': description,
975 'duration': duration,
f3aa3c3f 976 'channel_id': channel_id,
4dc23a80
M
977 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
978 or self._get_text(reel_header_renderer, 'channelTitleText')),
979 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
980 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 981 'timestamp': (self._parse_time_text(time_text)
982 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
983 else None),
f3aa3c3f 984 'release_timestamp': scheduled_timestamp,
c26f9b99 985 'availability':
986 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
987 else self._availability(
988 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
989 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
990 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 991 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 992 view_count_field: view_count,
e63faa10 993 'live_status': live_status
30a074c2 994 }
995
0c148415 996
360e1ca5 997class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 998 IE_DESC = 'YouTube'
cb7dfeea 999 _VALID_URL = r"""(?x)^
c5e8d7af 1000 (
edb53e2d 1001 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1002 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1003 (?:www\.)?deturl\.com/www\.youtube\.com|
1004 (?:www\.)?pwnyoutube\.com|
1005 (?:www\.)?hooktube\.com|
1006 (?:www\.)?yourepeat\.com|
1007 tube\.majestyc\.net|
1008 %(invidious)s|
1009 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1010 (?:.*?\#/)? # handle anchor (#/) redirect urls
1011 (?: # the various things that can precede the ID:
b6ce9bb0 1012 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1013 |(?: # or the v= param in all its forms
f7000f3a 1014 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1015 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1016 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1017 v=
1018 )
f4b05232 1019 ))
cbaed4bb
S
1020 |(?:
1021 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1022 vid\.plus| # or vid.plus/xxxx
1023 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1024 %(invidious)s
cbaed4bb 1025 )/
edb53e2d 1026 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1027 )
c5e8d7af 1028 )? # all until now is optional -> you can pass the naked ID
201c1459 1029 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1030 (?(1).+)? # if we found the ID, everything can follow
9297939e 1031 (?:\#|$)""" % {
d9190e44 1032 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1033 }
7c6eb424 1034 _EMBED_REGEX = [
1035 r'''(?x)
1036 (?:
0ca0f881 1037 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1038 data-video-url=|
1039 <embed[^>]+?src=|
1040 embedSWF\(?:\s*|
1041 <object[^>]+data=|
1042 new\s+SWFObject\(
1043 )
1044 (["\'])
1045 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1046 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1047 \1''',
1048 # https://wordpress.org/plugins/lazy-load-for-videos/
1049 r'''(?xs)
1050 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1051 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1052 ]
1053
e40c758c 1054 _PLAYER_INFO_RE = (
cc2db878 1055 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1056 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$',
545cc85d 1057 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1058 )
2c62dc26 1059 _formats = {
c2d3cb4c 1060 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1061 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1062 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1063 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1064 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1065 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1066 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1067 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1068 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1069 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1070 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1071 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1072 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1073 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1074 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1075 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1076 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1077 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1078
1079
1080 # 3D videos
c2d3cb4c 1081 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1082 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1083 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1084 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1085 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1086 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1087 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1088
96fb5605 1089 # Apple HTTP Live Streaming
11f12195 1090 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1091 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1092 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1093 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1094 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1095 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1096 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1097 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1098
1099 # DASH mp4 video
d23028a8
S
1100 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1101 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1102 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1103 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1104 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1105 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1106 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1107 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1108 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1109 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1110 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1111 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1112
f6f1fc92 1113 # Dash mp4 audio
d23028a8
S
1114 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1115 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1116 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1117 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1118 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1119 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1120 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1121
1122 # Dash webm
d23028a8
S
1123 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1124 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1125 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1126 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1127 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1128 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1129 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1130 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1131 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1132 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1133 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1134 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1135 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1136 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1137 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1138 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1139 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1140 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1141 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1142 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1143 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1144 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1145
1146 # Dash webm audio
d23028a8
S
1147 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1148 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1149
0857baad 1150 # Dash webm audio with opus inside
d23028a8
S
1151 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1152 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1153 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1154
ce6b9a2d
PH
1155 # RTMP (unnamed)
1156 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1157
1158 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1159 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1160 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1161 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1162 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1163 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1164 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1165 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1166 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1167 }
29f7c58a 1168 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1169
fd5c4aab
S
1170 _GEO_BYPASS = False
1171
78caa52a 1172 IE_NAME = 'youtube'
2eb88d95
PH
1173 _TESTS = [
1174 {
2d3d2997 1175 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1176 'info_dict': {
1177 'id': 'BaW_jenozKc',
1178 'ext': 'mp4',
3867038a 1179 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1180 'uploader': 'Philipp Hagemeister',
1181 'uploader_id': 'phihag',
ec85ded8 1182 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1183 'channel': 'Philipp Hagemeister',
dd4c4492
S
1184 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1185 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1186 'upload_date': '20121002',
ff9f925b 1187 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1188 'categories': ['Science & Technology'],
3867038a 1189 'tags': ['youtube-dl'],
556dbe7f 1190 'duration': 10,
dbdaaa23 1191 'view_count': int,
3e7c1224 1192 'like_count': int,
ff9f925b 1193 'availability': 'public',
1194 'playable_in_embed': True,
1195 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1196 'live_status': 'not_live',
1197 'age_limit': 0,
7c80519c 1198 'start_time': 1,
297a564b 1199 'end_time': 9,
12a1b225 1200 'comment_count': int,
6c73052c 1201 'channel_follower_count': int
2eb88d95 1202 }
0e853ca4 1203 },
fccd3771 1204 {
4bc3a23e
PH
1205 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1206 'note': 'Embed-only video (#1746)',
1207 'info_dict': {
1208 'id': 'yZIXLfi8CZQ',
1209 'ext': 'mp4',
1210 'upload_date': '20120608',
1211 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1212 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1213 'uploader': 'SET India',
94bfcd23 1214 'uploader_id': 'setindia',
ec85ded8 1215 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1216 'age_limit': 18,
545cc85d 1217 },
1218 'skip': 'Private video',
fccd3771 1219 },
11b56058 1220 {
8bdd16b4 1221 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1222 'note': 'Use the first video ID in the URL',
1223 'info_dict': {
1224 'id': 'BaW_jenozKc',
1225 'ext': 'mp4',
3867038a 1226 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1227 'uploader': 'Philipp Hagemeister',
1228 'uploader_id': 'phihag',
ec85ded8 1229 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1230 'channel': 'Philipp Hagemeister',
1231 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1232 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1233 'upload_date': '20121002',
976ae3ea 1234 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1235 'categories': ['Science & Technology'],
3867038a 1236 'tags': ['youtube-dl'],
556dbe7f 1237 'duration': 10,
dbdaaa23 1238 'view_count': int,
11b56058 1239 'like_count': int,
976ae3ea 1240 'availability': 'public',
1241 'playable_in_embed': True,
1242 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1243 'live_status': 'not_live',
1244 'age_limit': 0,
12a1b225 1245 'comment_count': int,
6c73052c 1246 'channel_follower_count': int
34a7de29
S
1247 },
1248 'params': {
1249 'skip_download': True,
1250 },
11b56058 1251 },
dd27fd17 1252 {
2d3d2997 1253 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1254 'note': '256k DASH audio (format 141) via DASH manifest',
1255 'info_dict': {
1256 'id': 'a9LDPn-MO4I',
1257 'ext': 'm4a',
1258 'upload_date': '20121002',
1259 'uploader_id': '8KVIDEO',
ec85ded8 1260 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1261 'description': '',
1262 'uploader': '8KVIDEO',
1263 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1264 },
4bc3a23e
PH
1265 'params': {
1266 'youtube_include_dash_manifest': True,
1267 'format': '141',
4919603f 1268 },
de3c7fe0 1269 'skip': 'format 141 not served anymore',
dd27fd17 1270 },
8bdd16b4 1271 # DASH manifest with encrypted signature
1272 {
1273 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1274 'info_dict': {
1275 'id': 'IB3lcPjvWLA',
1276 'ext': 'm4a',
1277 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1278 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1279 'duration': 244,
1280 'uploader': 'AfrojackVEVO',
1281 'uploader_id': 'AfrojackVEVO',
1282 'upload_date': '20131011',
cc2db878 1283 'abr': 129.495,
976ae3ea 1284 'like_count': int,
1285 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1286 'playable_in_embed': True,
1287 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1288 'view_count': int,
1289 'track': 'The Spark',
1290 'live_status': 'not_live',
1291 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1292 'channel': 'Afrojack',
1293 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1294 'tags': 'count:19',
1295 'availability': 'public',
1296 'categories': ['Music'],
1297 'age_limit': 0,
1298 'alt_title': 'The Spark',
6c73052c 1299 'channel_follower_count': int
8bdd16b4 1300 },
1301 'params': {
1302 'youtube_include_dash_manifest': True,
1303 'format': '141/bestaudio[ext=m4a]',
1304 },
1305 },
65c2fde2 1306 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1307 {
65c2fde2 1308 'note': 'Embed allowed age-gate video',
2d3d2997 1309 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1310 'info_dict': {
1311 'id': 'HtVdAasjOgU',
1312 'ext': 'mp4',
1313 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1314 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1315 'duration': 142,
c522adb1
JMF
1316 'uploader': 'The Witcher',
1317 'uploader_id': 'WitcherGame',
ec85ded8 1318 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1319 'upload_date': '20140605',
34952f09 1320 'age_limit': 18,
976ae3ea 1321 'categories': ['Gaming'],
1322 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1323 'availability': 'needs_auth',
1324 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1325 'like_count': int,
1326 'channel': 'The Witcher',
1327 'live_status': 'not_live',
1328 'tags': 'count:17',
1329 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1330 'playable_in_embed': True,
1331 'view_count': int,
6c73052c 1332 'channel_follower_count': int
c522adb1
JMF
1333 },
1334 },
65c2fde2 1335 {
1336 'note': 'Age-gate video with embed allowed in public site',
1337 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1338 'info_dict': {
1339 'id': 'HsUATh_Nc2U',
1340 'ext': 'mp4',
1341 'title': 'Godzilla 2 (Official Video)',
1342 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1343 'upload_date': '20200408',
1344 'uploader_id': 'FlyingKitty900',
1345 'uploader': 'FlyingKitty',
1346 'age_limit': 18,
976ae3ea 1347 'availability': 'needs_auth',
1348 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1349 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1350 'channel': 'FlyingKitty',
1351 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1352 'view_count': int,
1353 'categories': ['Entertainment'],
1354 'live_status': 'not_live',
1355 'tags': ['Flyingkitty', 'godzilla 2'],
1356 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1357 'like_count': int,
1358 'duration': 177,
1359 'playable_in_embed': True,
6c73052c 1360 'channel_follower_count': int
65c2fde2 1361 },
1362 },
1363 {
1364 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1365 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1366 'info_dict': {
1367 'id': 'Tq92D6wQ1mg',
1368 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1369 'ext': 'mp4',
17322130 1370 'upload_date': '20191228',
65c2fde2 1371 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1372 'uploader': 'Projekt Melody',
1373 'description': 'md5:17eccca93a786d51bc67646756894066',
1374 'age_limit': 18,
976ae3ea 1375 'like_count': int,
1376 'availability': 'needs_auth',
1377 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1378 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1379 'view_count': int,
1380 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1381 'channel': 'Projekt Melody',
1382 'live_status': 'not_live',
1383 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1384 'playable_in_embed': True,
1385 'categories': ['Entertainment'],
1386 'duration': 106,
1387 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1388 'comment_count': int,
6c73052c 1389 'channel_follower_count': int
65c2fde2 1390 },
1391 },
1392 {
1393 'note': 'Non-Agegated non-embeddable video',
1394 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1395 'info_dict': {
1396 'id': 'MeJVWBSsPAY',
1397 'ext': 'mp4',
1398 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1399 'uploader': 'Herr Lurik',
1400 'uploader_id': 'st3in234',
1401 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1402 'upload_date': '20130730',
976ae3ea 1403 'track': 'Such mich find mich',
1404 'age_limit': 0,
1405 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1406 'like_count': int,
1407 'playable_in_embed': False,
1408 'creator': 'OOMPH!',
1409 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1410 'view_count': int,
1411 'alt_title': 'Such mich find mich',
1412 'duration': 210,
1413 'channel': 'Herr Lurik',
1414 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1415 'categories': ['Music'],
1416 'availability': 'public',
1417 'uploader_url': 'http://www.youtube.com/user/st3in234',
1418 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1419 'live_status': 'not_live',
1420 'artist': 'OOMPH!',
6c73052c 1421 'channel_follower_count': int
65c2fde2 1422 },
1423 },
1424 {
1425 'note': 'Non-bypassable age-gated video',
1426 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1427 'only_matching': True,
1428 },
8bdd16b4 1429 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1430 # YouTube Red ad is not captured for creator
1431 {
1432 'url': '__2ABJjxzNo',
1433 'info_dict': {
1434 'id': '__2ABJjxzNo',
1435 'ext': 'mp4',
1436 'duration': 266,
1437 'upload_date': '20100430',
1438 'uploader_id': 'deadmau5',
1439 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1440 'creator': 'deadmau5',
1441 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1442 'uploader': 'deadmau5',
1443 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1444 'alt_title': 'Some Chords',
976ae3ea 1445 'availability': 'public',
1446 'tags': 'count:14',
1447 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1448 'view_count': int,
1449 'live_status': 'not_live',
1450 'channel': 'deadmau5',
1451 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1452 'like_count': int,
1453 'track': 'Some Chords',
1454 'artist': 'deadmau5',
1455 'playable_in_embed': True,
1456 'age_limit': 0,
1457 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1458 'categories': ['Music'],
1459 'album': 'Some Chords',
6c73052c 1460 'channel_follower_count': int
8bdd16b4 1461 },
1462 'expected_warnings': [
1463 'DASH manifest missing',
1464 ]
1465 },
067aa17e 1466 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1467 {
1468 'url': 'lqQg6PlCWgI',
1469 'info_dict': {
1470 'id': 'lqQg6PlCWgI',
1471 'ext': 'mp4',
556dbe7f 1472 'duration': 6085,
90227264 1473 'upload_date': '20150827',
cbe2bd91 1474 'uploader_id': 'olympic',
ec85ded8 1475 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1476 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1477 'uploader': 'Olympics',
cbe2bd91 1478 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1479 'like_count': int,
1480 'release_timestamp': 1343767800,
1481 'playable_in_embed': True,
1482 'categories': ['Sports'],
1483 'release_date': '20120731',
1484 'channel': 'Olympics',
1485 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1486 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1487 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1488 'age_limit': 0,
1489 'availability': 'public',
1490 'live_status': 'was_live',
1491 'view_count': int,
1492 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1493 'channel_follower_count': int
cbe2bd91
PH
1494 },
1495 'params': {
1496 'skip_download': 'requires avconv',
e52a40ab 1497 }
cbe2bd91 1498 },
6271f1ca
PH
1499 # Non-square pixels
1500 {
1501 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1502 'info_dict': {
1503 'id': '_b-2C3KPAM0',
1504 'ext': 'mp4',
1505 'stretched_ratio': 16 / 9.,
556dbe7f 1506 'duration': 85,
6271f1ca
PH
1507 'upload_date': '20110310',
1508 'uploader_id': 'AllenMeow',
ec85ded8 1509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1510 '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 1511 'uploader': '孫ᄋᄅ',
6271f1ca 1512 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1513 'playable_in_embed': True,
1514 'channel': '孫ᄋᄅ',
1515 'age_limit': 0,
1516 'tags': 'count:11',
1517 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1518 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1519 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1520 'view_count': int,
1521 'categories': ['People & Blogs'],
1522 'like_count': int,
1523 'live_status': 'not_live',
1524 'availability': 'unlisted',
12a1b225 1525 'comment_count': int,
6c73052c 1526 'channel_follower_count': int
6271f1ca 1527 },
06b491eb
S
1528 },
1529 # url_encoded_fmt_stream_map is empty string
1530 {
1531 'url': 'qEJwOuvDf7I',
1532 'info_dict': {
1533 'id': 'qEJwOuvDf7I',
f57b7835 1534 'ext': 'webm',
06b491eb
S
1535 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1536 'description': '',
1537 'upload_date': '20150404',
1538 'uploader_id': 'spbelect',
1539 'uploader': 'Наблюдатели Петербурга',
1540 },
1541 'params': {
1542 'skip_download': 'requires avconv',
e323cf3f
S
1543 },
1544 'skip': 'This live event has ended.',
06b491eb 1545 },
067aa17e 1546 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1547 {
1548 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1549 'info_dict': {
1550 'id': 'FIl7x6_3R5Y',
eb6793ba 1551 'ext': 'webm',
da77d856
S
1552 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1553 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1554 'duration': 220,
da77d856
S
1555 'upload_date': '20150625',
1556 'uploader_id': 'dorappi2000',
ec85ded8 1557 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1558 'uploader': 'dorappi2000',
eb6793ba 1559 'formats': 'mincount:31',
da77d856 1560 },
eb6793ba 1561 'skip': 'not actual anymore',
2ee8f5d8 1562 },
8a1a26ce
YCH
1563 # DASH manifest with segment_list
1564 {
1565 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1566 'md5': '8ce563a1d667b599d21064e982ab9e31',
1567 'info_dict': {
1568 'id': 'CsmdDsKjzN8',
1569 'ext': 'mp4',
17ee98e1 1570 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1571 'uploader': 'Airtek',
1572 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1573 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1574 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1575 },
1576 'params': {
1577 'youtube_include_dash_manifest': True,
1578 'format': '135', # bestvideo
be49068d
S
1579 },
1580 'skip': 'This live event has ended.',
2ee8f5d8 1581 },
cf7e015f
S
1582 {
1583 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1584 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1585 'info_dict': {
545cc85d 1586 'id': 'jvGDaLqkpTg',
1587 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1588 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1589 },
1590 'playlist': [{
1591 'info_dict': {
545cc85d 1592 'id': 'jvGDaLqkpTg',
cf7e015f 1593 'ext': 'mp4',
545cc85d 1594 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1595 'description': 'md5:e03b909557865076822aa169218d6a5d',
1596 'duration': 10643,
1597 'upload_date': '20161111',
1598 'uploader': 'Team PGP',
1599 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1600 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1601 },
1602 }, {
1603 'info_dict': {
545cc85d 1604 'id': '3AKt1R1aDnw',
cf7e015f 1605 'ext': 'mp4',
545cc85d 1606 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1607 'description': 'md5:e03b909557865076822aa169218d6a5d',
1608 'duration': 10991,
1609 'upload_date': '20161111',
1610 'uploader': 'Team PGP',
1611 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1612 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1613 },
1614 }, {
1615 'info_dict': {
545cc85d 1616 'id': 'RtAMM00gpVc',
cf7e015f 1617 'ext': 'mp4',
545cc85d 1618 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1619 'description': 'md5:e03b909557865076822aa169218d6a5d',
1620 'duration': 10995,
1621 'upload_date': '20161111',
1622 'uploader': 'Team PGP',
1623 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1624 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1625 },
1626 }, {
1627 'info_dict': {
545cc85d 1628 'id': '6N2fdlP3C5U',
cf7e015f 1629 'ext': 'mp4',
545cc85d 1630 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1631 'description': 'md5:e03b909557865076822aa169218d6a5d',
1632 'duration': 10990,
1633 'upload_date': '20161111',
1634 'uploader': 'Team PGP',
1635 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1636 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1637 },
1638 }],
1639 'params': {
1640 'skip_download': True,
1641 },
65c2fde2 1642 'skip': 'Not multifeed anymore',
cbaed4bb 1643 },
f9f49d87 1644 {
067aa17e 1645 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1646 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1647 'info_dict': {
1648 'id': 'gVfLd0zydlo',
1649 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1650 },
1651 'playlist_count': 2,
be49068d 1652 'skip': 'Not multifeed anymore',
f9f49d87 1653 },
cbaed4bb 1654 {
2d3d2997 1655 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1656 'only_matching': True,
0e49d9a6 1657 },
6d4fc66b 1658 {
2d3d2997 1659 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1660 'only_matching': True,
1661 },
0e49d9a6 1662 {
067aa17e 1663 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1664 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1665 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1666 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1667 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1668 'info_dict': {
1669 'id': 'lsguqyKfVQg',
1670 'ext': 'mp4',
1671 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1672 'alt_title': 'Dark Walk',
0e49d9a6 1673 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1674 'duration': 133,
0e49d9a6
LL
1675 'upload_date': '20151119',
1676 'uploader_id': 'IronSoulElf',
ec85ded8 1677 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1678 'uploader': 'IronSoulElf',
11f9be09 1679 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1680 'track': 'Dark Walk',
1681 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1682 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1683 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1684 'categories': ['Film & Animation'],
1685 'view_count': int,
1686 'live_status': 'not_live',
1687 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1688 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1689 'tags': 'count:13',
1690 'availability': 'public',
1691 'channel': 'IronSoulElf',
1692 'playable_in_embed': True,
1693 'like_count': int,
1694 'age_limit': 0,
6c73052c 1695 'channel_follower_count': int
0e49d9a6
LL
1696 },
1697 'params': {
1698 'skip_download': True,
1699 },
1700 },
61f92af1 1701 {
067aa17e 1702 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1703 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1704 'only_matching': True,
1705 },
313dfc45
LL
1706 {
1707 # Video with yt:stretch=17:0
1708 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1709 'info_dict': {
1710 'id': 'Q39EVAstoRM',
1711 'ext': 'mp4',
1712 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1713 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1714 'upload_date': '20151107',
1715 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1716 'uploader': 'CH GAMER DROID',
1717 },
1718 'params': {
1719 'skip_download': True,
1720 },
be49068d 1721 'skip': 'This video does not exist.',
313dfc45 1722 },
201c1459 1723 {
1724 # Video with incomplete 'yt:stretch=16:'
1725 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1726 'only_matching': True,
1727 },
7caf9830
S
1728 {
1729 # Video licensed under Creative Commons
1730 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1731 'info_dict': {
1732 'id': 'M4gD1WSo5mA',
1733 'ext': 'mp4',
1734 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1735 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1736 'duration': 721,
17322130 1737 'upload_date': '20150128',
7caf9830 1738 'uploader_id': 'BerkmanCenter',
ec85ded8 1739 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1740 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1741 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1742 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1743 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1744 'like_count': int,
1745 'age_limit': 0,
1746 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1747 'channel': 'The Berkman Klein Center for Internet & Society',
1748 'availability': 'public',
1749 'view_count': int,
1750 'categories': ['Education'],
1751 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1752 'live_status': 'not_live',
1753 'playable_in_embed': True,
12a1b225 1754 'comment_count': int,
d5d1df8a 1755 'channel_follower_count': int,
1756 'chapters': list,
7caf9830
S
1757 },
1758 'params': {
1759 'skip_download': True,
1760 },
1761 },
fd050249
S
1762 {
1763 # Channel-like uploader_url
1764 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1765 'info_dict': {
1766 'id': 'eQcmzGIKrzg',
1767 'ext': 'mp4',
1768 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1769 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1770 'duration': 4060,
17322130 1771 'upload_date': '20151120',
eb6793ba 1772 'uploader': 'Bernie Sanders',
fd050249 1773 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1774 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1775 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1776 'playable_in_embed': True,
1777 'tags': 'count:12',
1778 'like_count': int,
1779 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1780 'age_limit': 0,
1781 'availability': 'public',
1782 'categories': ['News & Politics'],
1783 'channel': 'Bernie Sanders',
1784 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1785 'view_count': int,
1786 'live_status': 'not_live',
1787 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1788 'comment_count': int,
d5d1df8a 1789 'channel_follower_count': int,
1790 'chapters': list,
fd050249
S
1791 },
1792 'params': {
1793 'skip_download': True,
1794 },
1795 },
040ac686
S
1796 {
1797 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1798 'only_matching': True,
7f29cf54
S
1799 },
1800 {
067aa17e 1801 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1802 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1803 'only_matching': True,
6496ccb4
S
1804 },
1805 {
1806 # Rental video preview
1807 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1808 'info_dict': {
1809 'id': 'uGpuVWrhIzE',
1810 'ext': 'mp4',
1811 'title': 'Piku - Trailer',
1812 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1813 'upload_date': '20150811',
1814 'uploader': 'FlixMatrix',
1815 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1816 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1817 'license': 'Standard YouTube License',
1818 },
1819 'params': {
1820 'skip_download': True,
1821 },
eb6793ba 1822 'skip': 'This video is not available.',
022a5d66 1823 },
12afdc2a
S
1824 {
1825 # YouTube Red video with episode data
1826 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1827 'info_dict': {
1828 'id': 'iqKdEhx-dD4',
1829 'ext': 'mp4',
1830 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1831 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1832 'duration': 2085,
12afdc2a
S
1833 'upload_date': '20170118',
1834 'uploader': 'Vsauce',
1835 'uploader_id': 'Vsauce',
1836 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1837 'series': 'Mind Field',
1838 'season_number': 1,
1839 'episode_number': 1,
976ae3ea 1840 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1841 'tags': 'count:12',
1842 'view_count': int,
1843 'availability': 'public',
1844 'age_limit': 0,
1845 'channel': 'Vsauce',
1846 'episode': 'Episode 1',
1847 'categories': ['Entertainment'],
1848 'season': 'Season 1',
1849 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1850 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1851 'like_count': int,
1852 'playable_in_embed': True,
1853 'live_status': 'not_live',
6c73052c 1854 'channel_follower_count': int
12afdc2a
S
1855 },
1856 'params': {
1857 'skip_download': True,
1858 },
1859 'expected_warnings': [
1860 'Skipping DASH manifest',
1861 ],
1862 },
c7121fa7
S
1863 {
1864 # The following content has been identified by the YouTube community
1865 # as inappropriate or offensive to some audiences.
1866 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1867 'info_dict': {
1868 'id': '6SJNVb0GnPI',
1869 'ext': 'mp4',
1870 'title': 'Race Differences in Intelligence',
1871 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1872 'duration': 965,
1873 'upload_date': '20140124',
1874 'uploader': 'New Century Foundation',
1875 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1876 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1877 },
1878 'params': {
1879 'skip_download': True,
1880 },
545cc85d 1881 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1882 },
022a5d66
S
1883 {
1884 # itag 212
1885 'url': '1t24XAntNCY',
1886 'only_matching': True,
fd5c4aab
S
1887 },
1888 {
1889 # geo restricted to JP
1890 'url': 'sJL6WA-aGkQ',
1891 'only_matching': True,
1892 },
cd5a74a2
S
1893 {
1894 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1895 'only_matching': True,
1896 },
bc2ca1bb 1897 {
1898 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1899 'only_matching': True,
1900 },
1901 {
1902 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1903 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1904 'only_matching': True,
1905 },
825cd268
RA
1906 {
1907 # DRM protected
1908 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1909 'only_matching': True,
4fe54c12
S
1910 },
1911 {
1912 # Video with unsupported adaptive stream type formats
1913 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1914 'info_dict': {
1915 'id': 'Z4Vy8R84T1U',
1916 'ext': 'mp4',
1917 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1918 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1919 'duration': 433,
1920 'upload_date': '20130923',
1921 'uploader': 'Amelia Putri Harwita',
1922 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1923 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1924 'formats': 'maxcount:10',
1925 },
1926 'params': {
1927 'skip_download': True,
1928 'youtube_include_dash_manifest': False,
1929 },
5429d6a9 1930 'skip': 'not actual anymore',
5caabd3c 1931 },
1932 {
822b9d9c 1933 # Youtube Music Auto-generated description
5caabd3c 1934 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1935 'info_dict': {
1936 'id': 'MgNrAu2pzNs',
1937 'ext': 'mp4',
1938 'title': 'Voyeur Girl',
1939 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1940 'upload_date': '20190312',
5429d6a9
S
1941 'uploader': 'Stephen - Topic',
1942 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1943 'artist': 'Stephen',
1944 'track': 'Voyeur Girl',
1945 'album': 'it\'s too much love to know my dear',
1946 'release_date': '20190313',
1947 'release_year': 2019,
976ae3ea 1948 'alt_title': 'Voyeur Girl',
1949 'view_count': int,
1950 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1951 'playable_in_embed': True,
1952 'like_count': int,
1953 'categories': ['Music'],
1954 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1955 'channel': 'Stephen',
1956 'availability': 'public',
1957 'creator': 'Stephen',
1958 'duration': 169,
1959 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1960 'age_limit': 0,
1961 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1962 'tags': 'count:11',
1963 'live_status': 'not_live',
6c73052c 1964 'channel_follower_count': int
5caabd3c 1965 },
1966 'params': {
1967 'skip_download': True,
1968 },
1969 },
66b48727
RA
1970 {
1971 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1972 'only_matching': True,
1973 },
011e75e6
S
1974 {
1975 # invalid -> valid video id redirection
1976 'url': 'DJztXj2GPfl',
1977 'info_dict': {
1978 'id': 'DJztXj2GPfk',
1979 'ext': 'mp4',
1980 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1981 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1982 'upload_date': '20090125',
1983 'uploader': 'Prochorowka',
1984 'uploader_id': 'Prochorowka',
1985 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1986 'artist': 'Panjabi MC',
1987 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1988 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1989 },
1990 'params': {
1991 'skip_download': True,
1992 },
545cc85d 1993 'skip': 'Video unavailable',
ea74e00b
DP
1994 },
1995 {
1996 # empty description results in an empty string
1997 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1998 'info_dict': {
1999 'id': 'x41yOUIvK2k',
2000 'ext': 'mp4',
2001 'title': 'IMG 3456',
2002 'description': '',
2003 'upload_date': '20170613',
2004 'uploader_id': 'ElevageOrVert',
2005 'uploader': 'ElevageOrVert',
976ae3ea 2006 'view_count': int,
2007 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2008 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2009 'like_count': int,
2010 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2011 'tags': [],
2012 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2013 'availability': 'public',
2014 'age_limit': 0,
2015 'categories': ['Pets & Animals'],
2016 'duration': 7,
2017 'playable_in_embed': True,
2018 'live_status': 'not_live',
2019 'channel': 'ElevageOrVert',
6c73052c 2020 'channel_follower_count': int
ea74e00b
DP
2021 },
2022 'params': {
2023 'skip_download': True,
2024 },
2025 },
a0566bbf 2026 {
29f7c58a 2027 # with '};' inside yt initial data (see [1])
2028 # see [2] for an example with '};' inside ytInitialPlayerResponse
2029 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2030 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2031 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2032 'info_dict': {
2033 'id': 'CHqg6qOn4no',
2034 'ext': 'mp4',
2035 'title': 'Part 77 Sort a list of simple types in c#',
2036 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2037 'upload_date': '20130831',
2038 'uploader_id': 'kudvenkat',
2039 'uploader': 'kudvenkat',
976ae3ea 2040 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2041 'like_count': int,
2042 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2043 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2044 'live_status': 'not_live',
2045 'categories': ['Education'],
2046 'availability': 'public',
2047 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2048 'tags': 'count:12',
2049 'playable_in_embed': True,
2050 'age_limit': 0,
2051 'view_count': int,
2052 'duration': 522,
2053 'channel': 'kudvenkat',
12a1b225 2054 'comment_count': int,
d5d1df8a 2055 'channel_follower_count': int,
2056 'chapters': list,
a0566bbf 2057 },
2058 'params': {
2059 'skip_download': True,
2060 },
2061 },
29f7c58a 2062 {
2063 # another example of '};' in ytInitialData
2064 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2065 'only_matching': True,
2066 },
2067 {
2068 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2069 'only_matching': True,
2070 },
545cc85d 2071 {
cc2db878 2072 # https://github.com/ytdl-org/youtube-dl/pull/28094
2073 'url': 'OtqTfy26tG0',
2074 'info_dict': {
2075 'id': 'OtqTfy26tG0',
2076 'ext': 'mp4',
2077 'title': 'Burn Out',
2078 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2079 'upload_date': '20141120',
2080 'uploader': 'The Cinematic Orchestra - Topic',
2081 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2082 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2083 'artist': 'The Cinematic Orchestra',
2084 'track': 'Burn Out',
2085 'album': 'Every Day',
976ae3ea 2086 'like_count': int,
2087 'live_status': 'not_live',
2088 'alt_title': 'Burn Out',
2089 'duration': 614,
2090 'age_limit': 0,
2091 'view_count': int,
2092 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2093 'creator': 'The Cinematic Orchestra',
2094 'channel': 'The Cinematic Orchestra',
2095 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2096 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2097 'availability': 'public',
2098 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2099 'categories': ['Music'],
2100 'playable_in_embed': True,
6c73052c 2101 'channel_follower_count': int
cc2db878 2102 },
2103 'params': {
2104 'skip_download': True,
2105 },
545cc85d 2106 },
bc2ca1bb 2107 {
2108 # controversial video, only works with bpctr when authenticated with cookies
2109 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2110 'only_matching': True,
2111 },
a1a7907b 2112 {
2113 # controversial video, requires bpctr/contentCheckOk
2114 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2115 'info_dict': {
2116 'id': 'SZJvDhaSDnc',
2117 'ext': 'mp4',
2118 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2119 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2120 'uploader': 'CBS Mornings',
11f9be09 2121 'uploader_id': 'CBSThisMorning',
a1a7907b 2122 'upload_date': '20140716',
976ae3ea 2123 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2124 'duration': 170,
2125 'categories': ['News & Politics'],
2126 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2127 'view_count': int,
2128 'channel': 'CBS Mornings',
2129 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2130 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2131 'age_limit': 18,
2132 'availability': 'needs_auth',
2133 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2134 'like_count': int,
2135 'live_status': 'not_live',
2136 'playable_in_embed': True,
6c73052c 2137 'channel_follower_count': int
a1a7907b 2138 }
2139 },
f7ad7160 2140 {
2141 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2142 'url': 'cBvYw8_A0vQ',
2143 'info_dict': {
2144 'id': 'cBvYw8_A0vQ',
2145 'ext': 'mp4',
2146 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2147 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2148 'upload_date': '20201120',
2149 'uploader': 'Walk around Japan',
2150 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2151 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2152 'duration': 1456,
2153 'categories': ['Travel & Events'],
2154 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2155 'view_count': int,
2156 'channel': 'Walk around Japan',
2157 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2158 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2159 'age_limit': 0,
2160 'availability': 'public',
2161 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2162 'live_status': 'not_live',
2163 'playable_in_embed': True,
6c73052c 2164 'channel_follower_count': int
f7ad7160 2165 },
2166 'params': {
2167 'skip_download': True,
2168 },
0fb983f6 2169 }, {
2170 # Has multiple audio streams
2171 'url': 'WaOKSUlf4TM',
2172 'only_matching': True
9297939e 2173 }, {
2174 # Requires Premium: has format 141 when requested using YTM url
2175 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2176 'only_matching': True
2177 }, {
120916da 2178 # multiple subtitles with same lang_code
2179 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2180 'only_matching': True,
109dd3b2 2181 }, {
2182 # Force use android client fallback
2183 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2184 'info_dict': {
2185 'id': 'YOelRv7fMxY',
11f9be09 2186 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2187 'ext': '3gp',
2188 'upload_date': '20210624',
2189 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2190 'uploader': 'colinfurze',
11f9be09 2191 'uploader_id': 'colinfurze',
109dd3b2 2192 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2193 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2194 'duration': 596,
2195 'categories': ['Entertainment'],
2196 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2197 'view_count': int,
2198 'channel': 'colinfurze',
2199 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2200 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2201 'age_limit': 0,
2202 'availability': 'public',
2203 'like_count': int,
2204 'live_status': 'not_live',
2205 'playable_in_embed': True,
d5d1df8a 2206 'channel_follower_count': int,
2207 'chapters': list,
109dd3b2 2208 },
2209 'params': {
2210 'format': '17', # 3gp format available on android
2211 'extractor_args': {'youtube': {'player_client': ['android']}},
2212 },
120916da 2213 },
109dd3b2 2214 {
2215 # Skip download of additional client configs (remix client config in this case)
2216 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2217 'only_matching': True,
2218 'params': {
2219 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2220 },
8fc54b12 2221 }, {
2222 # shorts
2223 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2224 'only_matching': True,
9222c381 2225 }, {
2226 'note': 'Storyboards',
2227 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2228 'info_dict': {
2229 'id': '5KLPxDtMqe8',
2230 'ext': 'mhtml',
2231 'format_id': 'sb0',
2232 'title': 'Your Brain is Plastic',
2233 'uploader_id': 'scishow',
2234 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2235 'upload_date': '20140324',
2236 'uploader': 'SciShow',
976ae3ea 2237 'like_count': int,
2238 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2239 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2240 'view_count': int,
2241 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2242 'playable_in_embed': True,
2243 'tags': 'count:12',
2244 'uploader_url': 'http://www.youtube.com/user/scishow',
2245 'availability': 'public',
2246 'channel': 'SciShow',
2247 'live_status': 'not_live',
2248 'duration': 248,
2249 'categories': ['Education'],
2250 'age_limit': 0,
d5d1df8a 2251 'channel_follower_count': int,
2252 'chapters': list,
9222c381 2253 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2254 }, {
2255 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2256 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2257 'info_dict': {
2258 'id': '2NUZ8W2llS4',
2259 'ext': 'mp4',
2260 'title': 'The NP that test your phone performance 🙂',
2261 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2262 'uploader': 'Leon Nguyen',
2263 'uploader_id': 'VNSXIII',
2264 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2265 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2266 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2267 'duration': 21,
2268 'view_count': int,
2269 'age_limit': 0,
2270 'categories': ['Gaming'],
2271 'tags': 'count:23',
2272 'playable_in_embed': True,
2273 'live_status': 'not_live',
2274 'upload_date': '20220103',
2275 'like_count': int,
2276 'availability': 'public',
2277 'channel': 'Leon Nguyen',
2278 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2279 'comment_count': int,
992f9a73 2280 'channel_follower_count': int
2281 }
1ff88b7a 2282 }, {
2283 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2284 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2285 'info_dict': {
2286 'id': '2NUZ8W2llS4',
2287 'ext': 'mp4',
2288 'title': 'The NP that test your phone performance 🙂',
2289 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2290 'uploader': 'Leon Nguyen',
2291 'uploader_id': 'VNSXIII',
2292 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2293 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2294 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2295 'duration': 21,
2296 'view_count': int,
2297 'age_limit': 0,
2298 'categories': ['Gaming'],
2299 'tags': 'count:23',
2300 'playable_in_embed': True,
2301 'live_status': 'not_live',
2302 'upload_date': '20220102',
2303 'like_count': int,
2304 'availability': 'public',
2305 'channel': 'Leon Nguyen',
2306 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2307 'comment_count': int,
2308 'channel_follower_count': int
2309 },
2310 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2311 }, {
2312 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2313 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2314 'info_dict': {
2315 'id': 'mzZzzBU6lrM',
2316 'ext': 'mp4',
2317 'title': 'I Met GeorgeNotFound In Real Life...',
2318 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2319 'uploader': 'Quackity',
2320 'uploader_id': 'QuackityHQ',
2321 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2322 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2323 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2324 'duration': 955,
2325 'view_count': int,
2326 'age_limit': 0,
2327 'categories': ['Entertainment'],
2328 'tags': 'count:26',
2329 'playable_in_embed': True,
2330 'live_status': 'not_live',
2331 'release_timestamp': 1641172509,
2332 'release_date': '20220103',
2333 'upload_date': '20220103',
2334 'like_count': int,
2335 'availability': 'public',
2336 'channel': 'Quackity',
2337 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2338 'channel_follower_count': int
2339 }
2340 },
2341 { # continuous livestream. Microformat upload date should be preferred.
2342 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2343 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2344 'info_dict': {
2345 'id': 'kgx4WGK0oNU',
2346 '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}',
2347 'ext': 'mp4',
2348 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2349 'availability': 'public',
2350 'age_limit': 0,
2351 'release_timestamp': 1637975704,
2352 'upload_date': '20210619',
2353 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2354 'live_status': 'is_live',
2355 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2356 'uploader': '阿鲍Abao',
2357 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2358 'channel': 'Abao in Tokyo',
2359 'channel_follower_count': int,
2360 'release_date': '20211127',
2361 'tags': 'count:39',
2362 'categories': ['People & Blogs'],
2363 'like_count': int,
2364 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2365 'view_count': int,
2366 'playable_in_embed': True,
2367 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2368 'concurrent_view_count': int,
992f9a73 2369 },
2370 'params': {'skip_download': True}
6e634cbe 2371 }, {
2372 # Story. Requires specific player params to work.
ee27297f 2373 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2374 'info_dict': {
ee27297f 2375 'id': 'vv8qTUWmulI',
6e634cbe 2376 'ext': 'mp4',
ee27297f 2377 'availability': 'unlisted',
2378 'view_count': int,
2379 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2380 'upload_date': '20220526',
2381 'categories': ['Education'],
2382 'title': 'Story',
2383 'channel': 'IT\'S HISTORY',
2384 'description': '',
2385 'uploader_id': 'BlastfromthePast',
2386 'duration': 12,
2387 'uploader': 'IT\'S HISTORY',
6e634cbe 2388 'playable_in_embed': True,
6e634cbe 2389 'age_limit': 0,
6e634cbe 2390 'live_status': 'not_live',
ee27297f 2391 'tags': [],
2392 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2393 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2394 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2395 },
2396 'skip': 'stories get removed after some period of time',
ee27297f 2397 }, {
2398 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2399 'info_dict': {
2400 'id': 'tjjjtzRLHvA',
2401 'ext': 'mp4',
2402 'title': 'ハッシュタグ無し };if window.ytcsi',
2403 'upload_date': '20220323',
2404 'like_count': int,
2405 'availability': 'unlisted',
2406 'channel': 'nao20010128nao',
2407 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2408 'age_limit': 0,
2409 'uploader': 'nao20010128nao',
2410 'uploader_id': 'nao20010128nao',
2411 'categories': ['Music'],
6e634cbe 2412 'view_count': int,
2413 'description': '',
ee27297f 2414 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2415 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2416 'live_status': 'not_live',
2417 'playable_in_embed': True,
2418 'channel_follower_count': int,
2419 'duration': 6,
2420 'tags': [],
2421 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2422 }
c26f9b99 2423 }, {
2424 # Prefer primary title+description language metadata by default
2425 # Do not prefer translated description if primary is empty
2426 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2427 'info_dict': {
2428 'id': 'el3E4MbxRqQ',
2429 'ext': 'mp4',
2430 'title': 'dlp test video 2 - primary sv no desc',
2431 'description': '',
2432 'channel': 'cole-dlp-test-acc',
2433 'tags': [],
2434 'view_count': int,
2435 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2436 'like_count': int,
2437 'playable_in_embed': True,
2438 'availability': 'unlisted',
2439 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2440 'age_limit': 0,
2441 'duration': 5,
2442 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2443 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2444 'live_status': 'not_live',
2445 'upload_date': '20220908',
2446 'categories': ['People & Blogs'],
2447 'uploader': 'cole-dlp-test-acc',
2448 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2449 },
2450 'params': {'skip_download': True}
2451 }, {
2452 # Extractor argument: prefer translated title+description
2453 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2454 'info_dict': {
2455 'id': 'gHKT4uU8Zng',
2456 'ext': 'mp4',
2457 'channel': 'cole-dlp-test-acc',
2458 'tags': [],
2459 'duration': 5,
2460 'live_status': 'not_live',
2461 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2462 'upload_date': '20220728',
2463 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2464 'view_count': int,
2465 'categories': ['People & Blogs'],
2466 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2467 'title': 'dlp test video title translated (fr)',
2468 'availability': 'public',
2469 'uploader': 'cole-dlp-test-acc',
2470 'age_limit': 0,
2471 'description': 'dlp test video description translated (fr)',
2472 'playable_in_embed': True,
2473 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2474 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2475 },
2476 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2477 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2478 }, {
2479 'note': '6 channel audio',
2480 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2481 'only_matching': True,
6e634cbe 2482 }
2eb88d95
PH
2483 ]
2484
f2e8dbcc 2485 _WEBPAGE_TESTS = [
2486 # YouTube <object> embed
2487 {
2488 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2489 'md5': '873c81d308b979f0e23ee7e620b312a3',
2490 'info_dict': {
2491 'id': 'msN87y-iEx0',
2492 'ext': 'mp4',
2493 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2494 'upload_date': '20080526',
2495 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2496 'uploader': 'Christopher Sykes',
2497 'uploader_id': 'ChristopherJSykes',
2498 'age_limit': 0,
2499 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2500 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2501 'playable_in_embed': True,
2502 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2503 'like_count': int,
2504 'comment_count': int,
2505 'channel': 'Christopher Sykes',
2506 'live_status': 'not_live',
2507 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2508 'availability': 'public',
2509 'duration': 195,
2510 'view_count': int,
2511 'categories': ['Science & Technology'],
2512 'channel_follower_count': int,
2513 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2514 },
2515 'params': {
2516 'skip_download': True,
2517 }
2518 },
2519 ]
2520
201c1459 2521 @classmethod
2522 def suitable(cls, url):
4dfbf869 2523 from ..utils import parse_qs
2524
201c1459 2525 qs = parse_qs(url)
2526 if qs.get('list', [None])[0]:
2527 return False
86e5f3ed 2528 return super().suitable(url)
201c1459 2529
e0df6211 2530 def __init__(self, *args, **kwargs):
86e5f3ed 2531 super().__init__(*args, **kwargs)
545cc85d 2532 self._code_cache = {}
83799698 2533 self._player_cache = {}
e0df6211 2534
4d37720a 2535 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2536 lock = threading.Lock()
185bf310 2537 start_time = time.time()
adbc4ec4
THD
2538 formats = [f for f in formats if f.get('is_from_start')]
2539
185bf310 2540 def refetch_manifest(format_id, delay):
2541 nonlocal formats, start_time, is_live
2542 if time.time() <= start_time + delay:
adbc4ec4
THD
2543 return
2544
2545 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2546 video_details = traverse_obj(
2547 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2548 microformats = traverse_obj(
2549 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2550 expected_type=dict, default=[])
4d37720a
L
2551 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2552 is_live = live_status == 'is_live'
185bf310 2553 start_time = time.time()
adbc4ec4 2554
185bf310 2555 def mpd_feed(format_id, delay):
adbc4ec4
THD
2556 """
2557 @returns (manifest_url, manifest_stream_number, is_live) or None
2558 """
2559 with lock:
185bf310 2560 refetch_manifest(format_id, delay)
adbc4ec4
THD
2561
2562 f = next((f for f in formats if f['format_id'] == format_id), None)
2563 if not f:
185bf310 2564 if not is_live:
2565 self.to_screen(f'{video_id}: Video is no longer live')
2566 else:
2567 self.report_warning(
2568 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2569 return None
2570 return f['manifest_url'], f['manifest_stream_number'], is_live
2571
2572 for f in formats:
4d37720a
L
2573 f['is_live'] = is_live
2574 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2575 live_start_time, mpd_feed, not is_live and f.copy())
2576 if is_live:
2577 f['fragments'] = gen
2578 f['protocol'] = 'http_dash_segments_generator'
2579 else:
2580 f['fragments'] = LazyList(gen({}))
2581 del f['is_from_start']
adbc4ec4 2582
4d37720a 2583 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2584 FETCH_SPAN, MAX_DURATION = 5, 432000
2585
2586 mpd_url, stream_number, is_live = None, None, True
2587
2588 begin_index = 0
2589 download_start_time = ctx.get('start') or time.time()
2590
2591 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2592 if lack_early_segments:
2593 self.report_warning(bug_reports_message(
2594 'Starting download from the last 120 hours of the live stream since '
2595 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2596 lack_early_segments = True
2597
2598 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2599 fragments, fragment_base_url = None, None
2600
a539f065 2601 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2602 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2603 # Obtain from MPD's maximum seq value
2604 old_mpd_url = mpd_url
185bf310 2605 last_error = ctx.pop('last_error', None)
14f25df2 2606 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2607 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2608 or (mpd_url, stream_number, False))
2609 if not refresh_sequence:
2610 if expire_fast and not is_live:
2611 return False, last_seq
2612 elif old_mpd_url == mpd_url:
2613 return True, last_seq
4d37720a
L
2614 if manifestless_orig_fmt:
2615 fmt_info = manifestless_orig_fmt
2616 else:
2617 try:
2618 fmts, _ = self._extract_mpd_formats_and_subtitles(
2619 mpd_url, None, note=False, errnote=False, fatal=False)
2620 except ExtractorError:
2621 fmts = None
2622 if not fmts:
2623 no_fragment_score += 2
2624 return False, last_seq
2625 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2626 fragments = fmt_info['fragments']
2627 fragment_base_url = fmt_info['fragment_base_url']
2628 assert fragment_base_url
2629
2630 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2631 return True, _last_seq
2632
4d37720a 2633 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2634 while is_live:
2635 fetch_time = time.time()
2636 if no_fragment_score > 30:
2637 return
2638 if last_segment_url:
2639 # Obtain from "X-Head-Seqnum" header value from each segment
2640 try:
2641 urlh = self._request_webpage(
2642 last_segment_url, None, note=False, errnote=False, fatal=False)
2643 except ExtractorError:
2644 urlh = None
2645 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2646 if last_seq is None:
a539f065 2647 no_fragment_score += 2
adbc4ec4
THD
2648 last_segment_url = None
2649 continue
2650 else:
a539f065
LNO
2651 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2652 no_fragment_score += 2
185bf310 2653 if not should_continue:
adbc4ec4
THD
2654 continue
2655
2656 if known_idx > last_seq:
2657 last_segment_url = None
2658 continue
2659
2660 last_seq += 1
2661
2662 if begin_index < 0 and known_idx < 0:
2663 # skip from the start when it's negative value
2664 known_idx = last_seq + begin_index
2665 if lack_early_segments:
2666 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2667 try:
2668 for idx in range(known_idx, last_seq):
2669 # do not update sequence here or you'll get skipped some part of it
a539f065 2670 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2671 if not should_continue:
adbc4ec4
THD
2672 known_idx = idx - 1
2673 raise ExtractorError('breaking out of outer loop')
2674 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2675 yield {
2676 'url': last_segment_url,
36195c44 2677 'fragment_count': last_seq,
adbc4ec4
THD
2678 }
2679 if known_idx == last_seq:
2680 no_fragment_score += 5
2681 else:
2682 no_fragment_score = 0
2683 known_idx = last_seq
2684 except ExtractorError:
2685 continue
2686
4d37720a
L
2687 if manifestless_orig_fmt:
2688 # Stop at the first iteration if running for post-live manifestless;
2689 # fragment count no longer increase since it starts
2690 break
2691
adbc4ec4
THD
2692 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2693
b6de707d 2694 def _extract_player_url(self, *ytcfgs, webpage=None):
2695 player_url = traverse_obj(
2696 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2697 get_all=False, expected_type=str)
11f9be09 2698 if not player_url:
b6de707d 2699 return
60f393e4 2700 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2701
b6de707d 2702 def _download_player_url(self, video_id, fatal=False):
2703 res = self._download_webpage(
2704 'https://www.youtube.com/iframe_api',
2705 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2706 if res:
2707 player_version = self._search_regex(
2708 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2709 if player_version:
2710 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2711
60064c53
PH
2712 def _signature_cache_id(self, example_sig):
2713 """ Return a string representation of a signature """
14f25df2 2714 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2715
e40c758c
S
2716 @classmethod
2717 def _extract_player_info(cls, player_url):
2718 for player_re in cls._PLAYER_INFO_RE:
2719 id_m = re.search(player_re, player_url)
2720 if id_m:
2721 break
2722 else:
c081b35c 2723 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2724 return id_m.group('id')
e40c758c 2725
404f611f 2726 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2727 player_id = self._extract_player_info(player_url)
2728 if player_id not in self._code_cache:
1276a43a 2729 code = self._download_webpage(
109dd3b2 2730 player_url, video_id, fatal=fatal,
2731 note='Downloading player ' + player_id,
2732 errnote='Download of %s failed' % player_url)
1276a43a 2733 if code:
2734 self._code_cache[player_id] = code
404f611f 2735 return self._code_cache.get(player_id)
109dd3b2 2736
e40c758c 2737 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2738 player_id = self._extract_player_info(player_url)
e0df6211 2739
c4417ddb 2740 # Read from filesystem cache
86e5f3ed 2741 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2742 assert os.path.basename(func_id) == func_id
a0e07d31 2743
ae61d108 2744 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2745 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2746
580ce007 2747 if not cache_spec:
2748 code = self._load_player(video_id, player_url)
404f611f 2749 if code:
109dd3b2 2750 res = self._parse_sig_js(code)
ac668111 2751 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2752 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2753 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2754
2755 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2756
60064c53 2757 def _print_sig_code(self, func, example_sig):
404f611f 2758 if not self.get_param('youtube_print_sig_code'):
2759 return
2760
edf3e38e
PH
2761 def gen_sig_code(idxs):
2762 def _genslice(start, end, step):
78caa52a 2763 starts = '' if start == 0 else str(start)
8bcc8756 2764 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2765 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2766 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2767
2768 step = None
7af808a5
PH
2769 # Quelch pyflakes warnings - start will be set when step is set
2770 start = '(Never used)'
edf3e38e
PH
2771 for i, prev in zip(idxs[1:], idxs[:-1]):
2772 if step is not None:
2773 if i - prev == step:
2774 continue
2775 yield _genslice(start, prev, step)
2776 step = None
2777 continue
2778 if i - prev in [-1, 1]:
2779 step = i - prev
2780 start = prev
2781 continue
2782 else:
78caa52a 2783 yield 's[%d]' % prev
edf3e38e 2784 if step is None:
78caa52a 2785 yield 's[%d]' % i
edf3e38e
PH
2786 else:
2787 yield _genslice(start, i, step)
2788
ac668111 2789 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2790 cache_res = func(test_string)
edf3e38e 2791 cache_spec = [ord(c) for c in cache_res]
78caa52a 2792 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2793 signature_id_tuple = '(%s)' % (
14f25df2 2794 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2795 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2796 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2797 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2798
e0df6211
PH
2799 def _parse_sig_js(self, jscode):
2800 funcname = self._search_regex(
abefc03f
S
2801 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2802 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
2803 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2804 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2805 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}\(a,\d+\)',
2806 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 2807 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2808 # Obsolete patterns
2809 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2810 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2811 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2812 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2813 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2814 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2815 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2816 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2817 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2818
2819 jsi = JSInterpreter(jscode)
2820 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2821 return lambda s: initial_function([s])
2822
580ce007 2823 def _cached(self, func, *cache_id):
2824 def inner(*args, **kwargs):
2825 if cache_id not in self._player_cache:
2826 try:
2827 self._player_cache[cache_id] = func(*args, **kwargs)
2828 except ExtractorError as e:
2829 self._player_cache[cache_id] = e
2830 except Exception as e:
2831 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2832
2833 ret = self._player_cache[cache_id]
2834 if isinstance(ret, Exception):
2835 raise ret
2836 return ret
2837 return inner
2838
545cc85d 2839 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2840 """Turn the encrypted s field into a working signature"""
580ce007 2841 extract_sig = self._cached(
2842 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2843 func = extract_sig(video_id, player_url, s)
2844 self._print_sig_code(func, s)
2845 return func(s)
404f611f 2846
2847 def _decrypt_nsig(self, s, video_id, player_url):
2848 """Turn the encrypted n field into a working signature"""
2849 if player_url is None:
2850 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2851 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2852
b505e851 2853 try:
2854 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2855 except ExtractorError as e:
2856 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 2857 if self.get_param('youtube_print_sig_code'):
2858 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2859
25836db6 2860 try:
2861 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2862 ret = extract_nsig(jsi, func_code)(s)
2863 except JSInterpreter.Exception as e:
2864 try:
992dc6b4 2865 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 2866 except ExtractorError:
2867 raise e
2868 self.report_warning(
2869 f'Native nsig extraction failed: Trying with PhantomJS\n'
2870 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 2871 self.write_debug(e, only_once=True)
25836db6 2872
2873 args, func_body = func_code
2874 ret = jsi.execute(
2875 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2876 video_id=video_id, note='Executing signature code').strip()
580ce007 2877
2878 self.write_debug(f'Decrypted nsig {s} => {ret}')
2879 return ret
2880
90a1df30 2881 def _extract_n_function_name(self, jscode):
2882 funcname, idx = self._search_regex(
2883 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2884 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2885 if not idx:
2886 return funcname
2887
2888 return json.loads(js_to_json(self._search_regex(
2889 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2890 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2891
580ce007 2892 def _extract_n_function_code(self, video_id, player_url):
404f611f 2893 player_id = self._extract_player_info(player_url)
05deb747 2894 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 2895 jscode = func_code or self._load_player(video_id, player_url)
2896 jsi = JSInterpreter(jscode)
404f611f 2897
2898 if func_code:
580ce007 2899 return jsi, player_id, func_code
404f611f 2900
b505e851 2901 func_name = self._extract_n_function_name(jscode)
2902
2903 # For redundancy
2904 func_code = self._search_regex(
2905 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
2906 # NB: The end of the regex is intentionally kept strict
2907 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
2908 jscode, 'nsig function', group=('var', 'code'), default=None)
2909 if func_code:
2910 func_code = ([func_code[0]], func_code[1])
2911 else:
2912 self.write_debug('Extracting nsig function with jsinterp')
2913 func_code = jsi.extract_function_code(func_name)
2914
580ce007 2915 self.cache.store('youtube-nsig', player_id, func_code)
2916 return jsi, player_id, func_code
2917
2918 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 2919 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2920
580ce007 2921 def extract_nsig(s):
25836db6 2922 try:
2923 ret = func([s])
2924 except JSInterpreter.Exception:
2925 raise
2926 except Exception as e:
2927 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2928
f6ca640b 2929 if ret.startswith('enhanced_except_'):
25836db6 2930 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 2931 return ret
580ce007 2932
2933 return extract_nsig
e0df6211 2934
109dd3b2 2935 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2936 """
2937 Extract signatureTimestamp (sts)
2938 Required to tell API what sig/player version is in use.
2939 """
2940 sts = None
2941 if isinstance(ytcfg, dict):
2942 sts = int_or_none(ytcfg.get('STS'))
2943
2944 if not sts:
2945 # Attempt to extract from player
2946 if player_url is None:
2947 error_msg = 'Cannot extract signature timestamp without player_url.'
2948 if fatal:
2949 raise ExtractorError(error_msg)
2950 self.report_warning(error_msg)
2951 return
404f611f 2952 code = self._load_player(video_id, player_url, fatal=fatal)
2953 if code:
109dd3b2 2954 sts = int_or_none(self._search_regex(
2955 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2956 'JS player signature timestamp', group='sts', fatal=fatal))
2957 return sts
2958
11f9be09 2959 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2960 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2961 label = 'fully ' if is_full else ''
2962 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2963 expected_type=url_or_none)
2964 if not url:
2965 self.report_warning(f'Unable to mark {label}watched')
2966 return
14f25df2 2967 parsed_url = urllib.parse.urlparse(url)
2968 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2969
2970 # cpn generation algorithm is reverse engineered from base.js.
2971 # In fact it works even with dummy cpn.
2972 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2973 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2974
2975 # # more consistent results setting it to right before the end
2976 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2977
2978 qs.update({
2979 'ver': ['2'],
2980 'cpn': [cpn],
2981 'cmt': video_length,
2982 'el': 'detailpage', # otherwise defaults to "shorts"
2983 })
2984
2985 if is_full:
2986 # these seem to mark watchtime "history" in the real world
2987 # they're required, so send in a single value
2988 qs.update({
5318156f 2989 'st': 0,
06cc8f10
B
2990 'et': video_length,
2991 })
2992
14f25df2 2993 url = urllib.parse.urlunparse(
2994 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2995
2996 self._download_webpage(
2997 url, video_id, f'Marking {label}watched',
2998 'Unable to mark watched', fatal=False)
d77ab8e2 2999
bfd973ec 3000 @classmethod
3001 def _extract_from_webpage(cls, url, webpage):
3002 # Invidious Instances
3003 # https://github.com/yt-dlp/yt-dlp/issues/195
3004 # https://github.com/iv-org/invidious/pull/1730
3005 mobj = re.search(
3006 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3007 webpage)
3008 if mobj:
3009 yield cls.url_result(mobj.group('url'), cls)
3010 raise cls.StopExtraction()
3011
3012 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3013
3014 # lazyYT YouTube embed
bfd973ec 3015 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3016 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3017
3018 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3019 for m in re.findall(r'''(?x)<div[^>]+
3020 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3021 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3022 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3023
97665381
PH
3024 @classmethod
3025 def extract_id(cls, url):
ae61d108 3026 video_id = cls.get_temp_id(url)
3027 if not video_id:
3028 raise ExtractorError(f'Invalid URL: {url}')
3029 return video_id
c5e8d7af 3030
7c365c21 3031 def _extract_chapters_from_json(self, data, duration):
3032 chapter_list = traverse_obj(
3033 data, (
3034 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3035 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3036 ), expected_type=list)
3037
3038 return self._extract_chapters(
3039 chapter_list,
3040 chapter_time=lambda chapter: float_or_none(
3041 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3042 chapter_title=lambda chapter: traverse_obj(
3043 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3044 duration=duration)
3045
3046 def _extract_chapters_from_engagement_panel(self, data, duration):
3047 content_list = traverse_obj(
8bdd16b4 3048 data,
7c365c21 3049 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 3050 expected_type=list, default=[])
052e1350 3051 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3052 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3053
1890fc63 3054 return next(filter(None, (
3055 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3056 chapter_time, chapter_title, duration)
3057 for contents in content_list)), [])
7c365c21 3058
1890fc63 3059 def _extract_chapters_from_description(self, description, duration):
2e30b46f 3060 duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
3061 sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
1890fc63 3062 return self._extract_chapters(
2e30b46f 3063 re.findall(sep_re % (duration_re, r'.+?'), description or ''),
1890fc63 3064 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2e30b46f 3065 duration=duration, strict=False) or self._extract_chapters(
3066 re.findall(sep_re % (r'.+?', duration_re), description or ''),
3067 chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
1890fc63 3068 duration=duration, strict=False)
84213ea8 3069
1890fc63 3070 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3071 if not duration:
3072 return
3073 chapter_list = [{
3074 'start_time': chapter_time(chapter),
3075 'title': chapter_title(chapter),
3076 } for chapter in chapter_list or []]
3077 if not strict:
3078 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3079
a3976e07 3080 chapters = [{'start_time': 0}]
1890fc63 3081 for idx, chapter in enumerate(chapter_list):
a3976e07 3082 if chapter['start_time'] is None:
1890fc63 3083 self.report_warning(f'Incomplete chapter {idx}')
3084 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3085 chapters.append(chapter)
709ee214 3086 elif chapter not in chapters:
3087 self.report_warning(
3088 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3089 return chapters[1:]
84213ea8 3090
a1c5d2ca
M
3091 def _extract_comment(self, comment_renderer, parent=None):
3092 comment_id = comment_renderer.get('commentId')
3093 if not comment_id:
3094 return
fe93e2c4 3095
052e1350 3096 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3097
c26f9b99 3098 # Timestamp is an estimate calculated from the current time and time_text
3099 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3100 timestamp = self._parse_time_text(time_text)
3101
052e1350 3102 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3103 author_id = try_get(comment_renderer,
14f25df2 3104 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3105
49bd8c66 3106 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3107 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3108 author_thumbnail = try_get(comment_renderer,
14f25df2 3109 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3110
3111 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3112 is_favorited = 'creatorHeart' in (try_get(
3113 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3114 return {
3115 'id': comment_id,
3116 'text': text,
d92f5d5a 3117 'timestamp': timestamp,
a1c5d2ca
M
3118 'time_text': time_text,
3119 'like_count': votes,
97524332 3120 'is_favorited': is_favorited,
a1c5d2ca
M
3121 'author': author,
3122 'author_id': author_id,
3123 'author_thumbnail': author_thumbnail,
3124 'author_is_uploader': author_is_uploader,
3125 'parent': parent or 'root'
3126 }
3127
46383212 3128 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3129
3130 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3131
3132 def extract_header(contents):
2d6659b9 3133 _continuation = None
3134 for content in contents:
46383212 3135 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3136 expected_comment_count = self._get_count(
3137 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3138
2d6659b9 3139 if expected_comment_count:
46383212 3140 tracker['est_total'] = expected_comment_count
3141 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3142 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3143
3144 sort_menu_item = try_get(
3145 comments_header_renderer,
3146 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3147 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3148
3149 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3150 if not _continuation:
3151 continue
3152
46383212 3153 sort_text = str_or_none(sort_menu_item.get('title'))
3154 if not sort_text:
2d6659b9 3155 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3156 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3157 break
a2160aa4 3158 return _continuation
a1c5d2ca 3159
2d6659b9 3160 def extract_thread(contents):
a1c5d2ca 3161 if not parent:
46383212 3162 tracker['current_page_thread'] = 0
a1c5d2ca 3163 for content in contents:
46383212 3164 if not parent and tracker['total_parent_comments'] >= max_parents:
3165 yield
a1c5d2ca 3166 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3167 comment_renderer = get_first(
3168 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3169 expected_type=dict, default={})
a1c5d2ca 3170
a1c5d2ca
M
3171 comment = self._extract_comment(comment_renderer, parent)
3172 if not comment:
3173 continue
46383212 3174
3175 tracker['running_total'] += 1
3176 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3177 yield comment
46383212 3178
a1c5d2ca
M
3179 # Attempt to get the replies
3180 comment_replies_renderer = try_get(
3181 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3182
3183 if comment_replies_renderer:
46383212 3184 tracker['current_page_thread'] += 1
a1c5d2ca 3185 comment_entries_iter = self._comment_entries(
99e9e001 3186 comment_replies_renderer, ytcfg, video_id,
46383212 3187 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3188 yield from itertools.islice(comment_entries_iter, min(
3189 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3190
46383212 3191 # Keeps track of counts across recursive calls
3192 if not tracker:
3193 tracker = dict(
3194 running_total=0,
3195 est_total=0,
3196 current_page_thread=0,
3197 total_parent_comments=0,
3198 total_reply_comments=0)
3199
3200 # TODO: Deprecated
2d6659b9 3201 # YouTube comments have a max depth of 2
46383212 3202 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3203 if max_depth:
da4db748 3204 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3205 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3206 if max_depth == 1 and parent:
3207 return
a1c5d2ca 3208
46383212 3209 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3210 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3211
46383212 3212 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3213
46383212 3214 response = None
6e634cbe 3215 is_forced_continuation = False
2d6659b9 3216 is_first_continuation = parent is None
6e634cbe 3217 if is_first_continuation and not continuation:
3218 # Sometimes you can get comments by generating the continuation yourself,
3219 # even if YouTube initially reports them being disabled - e.g. stories comments.
3220 # Note: if the comment section is actually disabled, YouTube may return a response with
3221 # required check_get_keys missing. So we will disable that check initially in this case.
3222 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3223 is_forced_continuation = True
a1c5d2ca
M
3224
3225 for page_num in itertools.count(0):
3226 if not continuation:
3227 break
46383212 3228 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3229 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3230 if page_num == 0:
3231 if is_first_continuation:
3232 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3233 else:
2d6659b9 3234 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3235 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3236 else:
3237 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3238 ' ' if parent else '', ' replies' if parent else '',
3239 page_num, comment_prog_str)
3240
3241 response = self._extract_response(
fe93e2c4 3242 item_id=None, query=continuation,
2d6659b9 3243 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 3244 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3245 is_forced_continuation = False
46383212 3246 continuation_contents = traverse_obj(
3247 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3248
2d6659b9 3249 continuation = None
46383212 3250 for continuation_section in continuation_contents:
3251 continuation_items = traverse_obj(
3252 continuation_section,
3253 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3254 get_all=False, expected_type=list) or []
3255 if is_first_continuation:
3256 continuation = extract_header(continuation_items)
3257 is_first_continuation = False
2d6659b9 3258 if continuation:
a1c5d2ca 3259 break
46383212 3260 continue
a1c5d2ca 3261
46383212 3262 for entry in extract_thread(continuation_items):
3263 if not entry:
3264 return
3265 yield entry
3266 continuation = self._extract_continuation({'contents': continuation_items})
3267 if continuation:
2d6659b9 3268 break
a1c5d2ca 3269
6e634cbe 3270 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3271 if message and not parent and tracker['running_total'] == 0:
3272 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3273
3274 @staticmethod
3275 def _generate_comment_continuation(video_id):
3276 """
3277 Generates initial comment section continuation token from given video id
3278 """
3279 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3280 return base64.b64encode(token.encode()).decode()
3281
a2160aa4 3282 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3283 """Entry for comment extraction"""
2d6659b9 3284 def _real_comment_extract(contents):
aae16f6e 3285 renderer = next((
3286 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3287 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3288 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3289
a2160aa4 3290 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3291 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3292
109dd3b2 3293 @staticmethod
99e9e001 3294 def _get_checkok_params():
3295 return {'contentCheckOk': True, 'racyCheckOk': True}
3296
3297 @classmethod
3298 def _generate_player_context(cls, sts=None):
109dd3b2 3299 context = {
3300 'html5Preference': 'HTML5_PREF_WANTS',
3301 }
3302 if sts is not None:
3303 context['signatureTimestamp'] = sts
3304 return {
3305 'playbackContext': {
3306 'contentPlaybackContext': context
a1a7907b 3307 },
99e9e001 3308 **cls._get_checkok_params()
109dd3b2 3309 }
3310
e7e94f2a
D
3311 @staticmethod
3312 def _is_agegated(player_response):
3313 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3314 return True
e7e94f2a
D
3315
3316 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3317 AGE_GATE_REASONS = (
3318 'confirm your age', 'age-restricted', 'inappropriate', # reason
3319 'age_verification_required', 'age_check_required', # status
3320 )
3321 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3322
3323 @staticmethod
3324 def _is_unplayable(player_response):
3325 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3326
50ac0e54 3327 _STORY_PLAYER_PARAMS = '8AEB'
3328
3329 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3330
11f9be09 3331 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3332 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3333 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3334 headers = self.generate_api_headers(
99e9e001 3335 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3336
6e634cbe 3337 yt_query = {
3338 'videoId': video_id,
6e634cbe 3339 }
50ac0e54 3340 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3341 yt_query['params'] = self._STORY_PLAYER_PARAMS
3342
11f9be09 3343 yt_query.update(self._generate_player_context(sts))
3344 return self._extract_response(
3345 item_id=video_id, ep='player', query=yt_query,
379e44ed 3346 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3347 default_client=client,
11f9be09 3348 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3349 ) or None
3350
11f9be09 3351 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3352 requested_clients = []
d0d012d4 3353 default = ['android', 'web']
000c15a4 3354 allowed_clients = sorted(
86e5f3ed 3355 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3356 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3357 for client in self._configuration_arg('player_client'):
3358 if client in allowed_clients:
3359 requested_clients.append(client)
d0d012d4 3360 elif client == 'default':
3361 requested_clients.extend(default)
b4c055ba 3362 elif client == 'all':
3363 requested_clients.extend(allowed_clients)
3364 else:
3365 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3366 if not requested_clients:
d0d012d4 3367 requested_clients = default
cf7e015f 3368
11f9be09 3369 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3370 requested_clients.extend(
e7e94f2a 3371 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3372
11f9be09 3373 return orderedSet(requested_clients)
cf7e015f 3374
50ac0e54 3375 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3376 initial_pr = None
3377 if webpage:
b7c47b74 3378 initial_pr = self._search_json(
3379 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3380
ae729626 3381 all_clients = set(clients)
c0bc527b 3382 clients = clients[::-1]
b6de707d 3383 prs = []
e7e94f2a 3384
ae729626 3385 def append_client(*client_names):
e7870111 3386 """ Append the first client name that exists but not already used """
ae729626 3387 for client_name in client_names:
e7870111
D
3388 actual_client = _split_innertube_client(client_name)[0]
3389 if actual_client in INNERTUBE_CLIENTS:
3390 if actual_client not in all_clients:
ae729626 3391 clients.append(client_name)
e7870111
D
3392 all_clients.add(actual_client)
3393 return
e7e94f2a 3394
379e44ed 3395 # Android player_response does not have microFormats which are needed for
3396 # extraction of some data. So we return the initial_pr with formats
3397 # stripped out even if not requested by the user
3398 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3399 if initial_pr:
3400 pr = dict(initial_pr)
3401 pr['streamingData'] = None
b6de707d 3402 prs.append(pr)
379e44ed 3403
3404 last_error = None
b6de707d 3405 tried_iframe_fallback = False
3406 player_url = None
c0bc527b 3407 while clients:
e7870111 3408 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3409 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3410 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3411 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3412
b6de707d 3413 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3414 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3415 if 'js' in self._configuration_arg('player_skip'):
3416 require_js_player = False
3417 player_url = None
3418
3419 if not player_url and not tried_iframe_fallback and require_js_player:
3420 player_url = self._download_player_url(video_id)
3421 tried_iframe_fallback = True
3422
379e44ed 3423 try:
3424 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3425 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3426 except ExtractorError as e:
3427 if last_error:
3428 self.report_warning(last_error)
3429 last_error = e
3430 continue
3431
11f9be09 3432 if pr:
a3e96421 3433 # YouTube may return a different video player response than expected.
3434 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3435 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3436 if pr_video_id and pr_video_id != video_id:
3437 self.report_warning(
c7dcf0b3 3438 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3439 else:
3440 prs.append(pr)
c0bc527b 3441
e7e94f2a 3442 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3443 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3444 append_client(f'{base_client}_creator')
e7e94f2a 3445 elif self._is_agegated(pr):
e7870111
D
3446 if variant == 'tv_embedded':
3447 append_client(f'{base_client}_embedded')
3448 elif not variant:
3449 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3450
379e44ed 3451 if last_error:
b6de707d 3452 if not len(prs):
379e44ed 3453 raise last_error
3454 self.report_warning(last_error)
b6de707d 3455 return prs, player_url
11f9be09 3456
4d37720a
L
3457 def _needs_live_processing(self, live_status, duration):
3458 if (live_status == 'is_live' and self.get_param('live_from_start')
3459 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3460 return live_status
3461
3462 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a0bb6ce5 3463 itags, stream_ids = {}, []
b25cac65 3464 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3465 q = qualities([
2a9c6dcd 3466 # Normally tiny is the smallest video-only formats. But
3467 # audio-only formats with unknown quality may get tagged as tiny
3468 'tiny',
3469 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3470 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3471 ])
11f9be09 3472 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3473
545cc85d 3474 for fmt in streaming_formats:
727029c5 3475 if fmt.get('targetDurationSec'):
545cc85d 3476 continue
321bf820 3477
cc2db878 3478 itag = str_or_none(fmt.get('itag'))
9297939e 3479 audio_track = fmt.get('audioTrack') or {}
3480 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3481 if stream_id in stream_ids:
3482 continue
3483
cc2db878 3484 quality = fmt.get('quality')
2a9c6dcd 3485 height = int_or_none(fmt.get('height'))
d3fc8074 3486 if quality == 'tiny' or not quality:
3487 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3488 # The 3gp format (17) in android client has a quality of "small",
3489 # but is actually worse than other formats
3490 if itag == '17':
3491 quality = 'tiny'
3492 if quality:
3493 if itag:
3494 itag_qualities[itag] = quality
3495 if height:
3496 res_qualities[height] = quality
cc2db878 3497 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3498 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3499 # number of fragment that would subsequently requested with (`&sq=N`)
3500 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3501 continue
3502
545cc85d 3503 fmt_url = fmt.get('url')
3504 if not fmt_url:
14f25df2 3505 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3506 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3507 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3508 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3509 continue
52023f12 3510 try:
3511 fmt_url += '&%s=%s' % (
3512 traverse_obj(sc, ('sp', -1)) or 'signature',
3513 self._decrypt_signature(encrypted_sig, video_id, player_url)
3514 )
3515 except ExtractorError as e:
580ce007 3516 self.report_warning('Signature extraction failed: Some formats may be missing',
3517 video_id=video_id, only_once=True)
52023f12 3518 self.write_debug(e, only_once=True)
201e9eaa 3519 continue
545cc85d 3520
404f611f 3521 query = parse_qs(fmt_url)
3522 throttled = False
b2916526 3523 if query.get('n'):
404f611f 3524 try:
580ce007 3525 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3526 fmt_url = update_url_query(fmt_url, {
580ce007 3527 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3528 })
404f611f 3529 except ExtractorError as e:
25836db6 3530 phantomjs_hint = ''
3531 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3532 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3533 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3534 if player_url:
3535 self.report_warning(
3536 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3537 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3538 self.write_debug(e, only_once=True)
3539 else:
3540 self.report_warning(
3541 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3542 video_id=video_id, only_once=True)
404f611f 3543 throttled = True
3544
545cc85d 3545 if itag:
a0bb6ce5 3546 itags[itag] = 'https'
9297939e 3547 stream_ids.append(stream_id)
3548
0ad92dfb 3549 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3550 language_preference = (
3551 10 if audio_track.get('audioIsDefault') and 10
3552 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3553 else -1)
0ad92dfb 3554 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3555 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3556 # Make sure to avoid false positives with small duration differences.
62b58c09 3557 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3558 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3559 if is_damaged:
0f06bcd7 3560 self.report_warning(
3561 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3562 dct = {
3563 'asr': int_or_none(fmt.get('audioSampleRate')),
3564 'filesize': int_or_none(fmt.get('contentLength')),
3565 'format_id': itag,
34921b43 3566 'format_note': join_nonempty(
26e8e044 3567 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3568 ' (default)' if language_preference > 0 else ''),
404f611f 3569 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3570 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3571 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3572 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3573 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3574 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3575 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3576 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3577 'height': height,
dca3ff4a 3578 'quality': q(quality),
727029c5 3579 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3580 'tbr': tbr,
545cc85d 3581 'url': fmt_url,
2a9c6dcd 3582 'width': int_or_none(fmt.get('width')),
ab6df717 3583 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3584 'desc' if language_preference < -1 else ''),
3585 'language_preference': language_preference,
a405b38f 3586 # Strictly de-prioritize damaged and 3gp formats
3587 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3588 }
60bdb7bd 3589 mime_mobj = re.match(
3590 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3591 if mime_mobj:
3592 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3593 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3594 no_audio = dct.get('acodec') == 'none'
3595 no_video = dct.get('vcodec') == 'none'
3596 if no_audio:
3597 dct['vbr'] = tbr
3598 if no_video:
3599 dct['abr'] = tbr
3600 if no_audio or no_video:
545cc85d 3601 dct['downloader_options'] = {
3602 # Youtube throttles chunks >~10M
3603 'http_chunk_size': 10485760,
bf1317d2 3604 }
7c60c33e 3605 if dct.get('ext'):
3606 dct['container'] = dct['ext'] + '_dash'
11f9be09 3607 yield dct
545cc85d 3608
4d37720a
L
3609 needs_live_processing = self._needs_live_processing(live_status, duration)
3610 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3611
3612 skip_manifests = set(self._configuration_arg('skip'))
3613 if (not self.get_param('youtube_include_hls_manifest', True)
3614 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3615 or needs_live_processing and skip_bad_formats):
3616 skip_manifests.add('hls')
3617
0f06bcd7 3618 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3619 skip_manifests.add('dash')
3620 if self._configuration_arg('include_live_dash'):
3621 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3622 'Use include_incomplete_formats extractor argument instead')
3623 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3624 skip_manifests.add('dash')
5d3a0e79 3625
a0bb6ce5 3626 def process_manifest_format(f, proto, itag):
3627 if itag in itags:
3628 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3629 return False
3630 itag = f'{itag}-{proto}'
3631 if itag:
3632 f['format_id'] = itag
3633 itags[itag] = proto
3634
b25cac65 3635 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3636 if f['quality'] == -1 and f.get('height'):
3637 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3638 return True
2a9c6dcd 3639
c646d76f 3640 subtitles = {}
11f9be09 3641 for sd in streaming_data:
4d37720a 3642 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3643 if hls_manifest_url:
4d37720a
L
3644 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3645 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3646 subtitles = self._merge_subtitles(subs, subtitles)
3647 for f in fmts:
a0bb6ce5 3648 if process_manifest_format(f, 'hls', self._search_regex(
3649 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3650 yield f
545cc85d 3651
4d37720a 3652 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3653 if dash_manifest_url:
c646d76f 3654 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3655 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3656 for f in formats:
a0bb6ce5 3657 if process_manifest_format(f, 'dash', f['format_id']):
3658 f['filesize'] = int_or_none(self._search_regex(
3659 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3660 if needs_live_processing:
adbc4ec4
THD
3661 f['is_from_start'] = True
3662
a0bb6ce5 3663 yield f
c646d76f 3664 yield subtitles
11f9be09 3665
720c3099 3666 def _extract_storyboard(self, player_responses, duration):
3667 spec = get_first(
3668 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3669 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3670 if not base_url:
720c3099 3671 return
720c3099 3672 L = len(spec) - 1
3673 for i, args in enumerate(spec):
3674 args = args.split('#')
3675 counts = list(map(int_or_none, args[:5]))
3676 if len(args) != 8 or not all(counts):
3677 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3678 continue
3679 width, height, frame_count, cols, rows = counts
3680 N, sigh = args[6:]
3681
3682 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3683 fragment_count = frame_count / (cols * rows)
3684 fragment_duration = duration / fragment_count
3685 yield {
3686 'format_id': f'sb{i}',
3687 'format_note': 'storyboard',
3688 'ext': 'mhtml',
3689 'protocol': 'mhtml',
3690 'acodec': 'none',
3691 'vcodec': 'none',
3692 'url': url,
3693 'width': width,
3694 'height': height,
45e8a04e 3695 'fps': frame_count / duration,
3696 'rows': rows,
3697 'columns': cols,
720c3099 3698 'fragments': [{
b3edc806 3699 'url': url.replace('$M', str(j)),
720c3099 3700 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3701 } for j in range(math.ceil(fragment_count))],
3702 }
3703
adbc4ec4 3704 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3705 webpage = None
3706 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3707 query = {'bpctr': '9999999999', 'has_verified': '1'}
3708 if smuggled_data.get('is_story'):
3709 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3710 webpage = self._download_webpage(
50ac0e54 3711 webpage_url, video_id, fatal=False, query=query)
11f9be09 3712
3713 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3714
b6de707d 3715 player_responses, player_url = self._extract_player_responses(
11f9be09 3716 self._get_requested_clients(url, smuggled_data),
50ac0e54 3717 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3718
adbc4ec4
THD
3719 return webpage, master_ytcfg, player_responses, player_url
3720
a1b2d843 3721 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3722 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3723 is_live = get_first(video_details, 'isLive')
3724 if is_live is None:
3725 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3726 live_content = get_first(video_details, 'isLiveContent')
3727 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3728 post_live = get_first(video_details, 'isPostLiveDvr')
3729 live_status = ('post_live' if post_live
3730 else 'is_live' if is_live
3731 else 'is_upcoming' if is_upcoming
6678a4f0 3732 else 'was_live' if live_content
3733 else 'not_live' if False in (is_live, live_content)
3734 else None)
adbc4ec4 3735 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3736 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3737
4d37720a 3738 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3739
3740 def _real_extract(self, url):
3741 url, smuggled_data = unsmuggle_url(url, {})
3742 video_id = self._match_id(url)
3743
3744 base_url = self.http_scheme() + '//www.youtube.com/'
3745 webpage_url = base_url + 'watch?v=' + video_id
3746
3747 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3748
11f9be09 3749 playability_statuses = traverse_obj(
3750 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3751
3752 trailer_video_id = get_first(
3753 playability_statuses,
3754 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3755 expected_type=str)
3756 if trailer_video_id:
3757 return self.url_result(
3758 trailer_video_id, self.ie_key(), trailer_video_id)
3759
3760 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3761 if webpage else (lambda x: None))
3762
3763 video_details = traverse_obj(
3764 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3765 microformats = traverse_obj(
3766 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3767 expected_type=dict, default=[])
c26f9b99 3768
3769 translated_title = self._get_text(microformats, (..., 'title'))
3770 video_title = (self._preferred_lang and translated_title
3771 or get_first(video_details, 'title') # primary
3772 or translated_title
3773 or search_meta(['og:title', 'twitter:title', 'title']))
3774 translated_description = self._get_text(microformats, (..., 'description'))
3775 original_description = get_first(video_details, 'shortDescription')
3776 video_description = (
3777 self._preferred_lang and translated_description
3778 # If original description is blank, it will be an empty string.
3779 # Do not prefer translated description in this case.
3780 or original_description if original_description is not None else translated_description)
11f9be09 3781
d89257f3 3782 multifeed_metadata_list = get_first(
3783 player_responses,
3784 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3785 expected_type=str)
3786 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3787 if self.get_param('noplaylist'):
11f9be09 3788 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3789 else:
3790 entries = []
3791 feed_ids = []
3792 for feed in multifeed_metadata_list.split(','):
3793 # Unquote should take place before split on comma (,) since textual
3794 # fields may contain comma as well (see
3795 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3796 feed_data = urllib.parse.parse_qs(
ac668111 3797 urllib.parse.unquote_plus(feed))
d89257f3 3798
3799 def feed_entry(name):
3800 return try_get(
14f25df2 3801 feed_data, lambda x: x[name][0], str)
d89257f3 3802
3803 feed_id = feed_entry('id')
3804 if not feed_id:
3805 continue
3806 feed_title = feed_entry('title')
3807 title = video_title
3808 if feed_title:
3809 title += ' (%s)' % feed_title
3810 entries.append({
3811 '_type': 'url_transparent',
3812 'ie_key': 'Youtube',
3813 'url': smuggle_url(
3814 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3815 {'force_singlefeed': True}),
3816 'title': title,
3817 })
3818 feed_ids.append(feed_id)
3819 self.to_screen(
3820 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3821 % (', '.join(feed_ids), video_id))
3822 return self.playlist_result(
3823 entries, video_id, video_title, video_description)
11f9be09 3824
9da6612b 3825 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
3826 or int_or_none(get_first(microformats, 'lengthSeconds'))
3827 or parse_duration(search_meta('duration')) or None)
a1b2d843 3828
4d37720a
L
3829 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3830 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3831 if live_status == 'post_live':
3832 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3833
545cc85d 3834 if not formats:
11f9be09 3835 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3836 self.report_drm(video_id)
11f9be09 3837 pemr = get_first(
3838 playability_statuses,
3839 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3840 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3841 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3842 if subreason:
545cc85d 3843 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3844 countries = get_first(microformats, 'availableCountries')
545cc85d 3845 if not countries:
3846 regions_allowed = search_meta('regionsAllowed')
3847 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3848 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3849 reason += f'. {subreason}'
545cc85d 3850 if reason:
b7da73eb 3851 self.raise_no_formats(reason, expected=True)
bf1317d2 3852
11f9be09 3853 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3854 if not keywords and webpage:
3855 keywords = [
3856 unescapeHTML(m.group('content'))
3857 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3858 for keyword in keywords:
3859 if keyword.startswith('yt:stretch='):
201c1459 3860 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3861 if mobj:
3862 # NB: float is intentional for forcing float division
3863 w, h = (float(v) for v in mobj.groups())
3864 if w > 0 and h > 0:
3865 ratio = w / h
3866 for f in formats:
3867 if f.get('vcodec') != 'none':
3868 f['stretched_ratio'] = ratio
3869 break
a709d873 3870 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3871 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3872 if thumbnail_url:
3873 thumbnails.append({
3874 'url': thumbnail_url,
ff2751ac 3875 })
fccf5021 3876 original_thumbnails = thumbnails.copy()
3877
0ba692ac 3878 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3879 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3880 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3881 thumbnail_names = [
962ffcf8 3882 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3883 # in resolution, these are not the custom thumbnail. So de-prioritize them
3884 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3885 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3886 ]
cca80fe6 3887 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3888 thumbnails.extend({
3889 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3890 video_id=video_id, name=name, ext=ext,
4d37720a 3891 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 3892 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3893 for thumb in thumbnails:
cca80fe6 3894 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3895 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3896 self._remove_duplicate_formats(thumbnails)
fccf5021 3897 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3898
7ea65411 3899 category = get_first(microformats, 'category') or search_meta('genre')
3900 channel_id = str_or_none(
3901 get_first(video_details, 'channelId')
3902 or get_first(microformats, 'externalChannelId')
3903 or search_meta('channelId'))
7ea65411 3904 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3905
adbc4ec4
THD
3906 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3907 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3908 if not duration and live_end_time and live_start_time:
3909 duration = live_end_time - live_start_time
3910
4d37720a
L
3911 needs_live_processing = self._needs_live_processing(live_status, duration)
3912
3913 def is_bad_format(fmt):
3914 if needs_live_processing and not fmt.get('is_from_start'):
3915 return True
3916 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
3917 and fmt.get('protocol') == 'http_dash_segments'):
3918 return True
3919
3920 for fmt in filter(is_bad_format, formats):
3921 fmt['preference'] = (fmt.get('preference') or -1) - 10
3922 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
3923
3924 if needs_live_processing:
3925 self._prepare_live_from_start_formats(
3926 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 3927
720c3099 3928 formats.extend(self._extract_storyboard(player_responses, duration))
3929
31b532a1 3930 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3931 self._sort_formats(formats, (
3932 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3933
545cc85d 3934 info = {
3935 'id': video_id,
39ca3b5c 3936 'title': video_title,
545cc85d 3937 'formats': formats,
3938 'thumbnails': thumbnails,
fccf5021 3939 # The best thumbnail that we are sure exists. Prevents unnecessary
3940 # URL checking if user don't care about getting the best possible thumbnail
3941 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3942 'description': video_description,
11f9be09 3943 'uploader': get_first(video_details, 'author'),
545cc85d 3944 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3945 'uploader_url': owner_profile_url,
3946 'channel_id': channel_id,
a70635b8 3947 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3948 'duration': duration,
3949 'view_count': int_or_none(
11f9be09 3950 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3951 or search_meta('interactionCount')),
11f9be09 3952 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3953 'age_limit': 18 if (
11f9be09 3954 get_first(microformats, 'isFamilySafe') is False
545cc85d 3955 or search_meta('isFamilyFriendly') == 'false'
3956 or search_meta('og:restrictions:age') == '18+') else 0,
3957 'webpage_url': webpage_url,
3958 'categories': [category] if category else None,
3959 'tags': keywords,
11f9be09 3960 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 3961 'live_status': live_status,
adbc4ec4 3962 'release_timestamp': live_start_time,
545cc85d 3963 }
b477fc13 3964
c646d76f 3965 subtitles = {}
3944e7af 3966 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3967 if pctr:
ecdc9049 3968 def get_lang_code(track):
3969 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3970 or track.get('languageCode'))
3971
3972 # Converted into dicts to remove duplicates
3973 captions = {
3974 get_lang_code(sub): sub
3975 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3976 translation_languages = {
3977 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3978 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3979
774d79cc 3980 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3981 lang_subs = container.setdefault(lang_code, [])
545cc85d 3982 for fmt in self._SUBTITLE_FORMATS:
3983 query.update({
3984 'fmt': fmt,
3985 })
3986 lang_subs.append({
3987 'ext': fmt,
60f393e4 3988 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3989 'name': sub_name,
545cc85d 3990 })
7e72694b 3991
07b47084 3992 # NB: Constructing the full subtitle dictionary is slow
3993 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3994 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3995 for lang_code, caption_track in captions.items():
3996 base_url = caption_track.get('baseUrl')
1235d333 3997 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3998 if not base_url:
3999 continue
ecdc9049 4000 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4001 if caption_track.get('kind') != 'asr':
545cc85d 4002 if not lang_code:
4003 continue
4004 process_language(
ecdc9049 4005 subtitles, base_url, lang_code, lang_name, {})
4006 if not caption_track.get('isTranslatable'):
4007 continue
3944e7af 4008 for trans_code, trans_name in translation_languages.items():
4009 if not trans_code:
545cc85d 4010 continue
1235d333 4011 orig_trans_code = trans_code
ecdc9049 4012 if caption_track.get('kind') != 'asr':
07b47084 4013 if not get_translated_subs:
18e49408 4014 continue
ecdc9049 4015 trans_code += f'-{lang_code}'
a70635b8 4016 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 4017 # Add an "-orig" label to the original language so that it can be distinguished.
4018 # The subs are returned without "-orig" as well for compatibility
1235d333 4019 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 4020 process_language(
d49669ac 4021 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4022 # Setting tlang=lang returns damaged subtitles.
d49669ac 4023 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4024 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4025
4026 info['automatic_captions'] = automatic_captions
4027 info['subtitles'] = subtitles
7e72694b 4028
14f25df2 4029 parsed_url = urllib.parse.urlparse(url)
545cc85d 4030 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4031 query = urllib.parse.parse_qs(component)
545cc85d 4032 for k, v in query.items():
4033 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4034 d_k += '_time'
4035 if d_k not in info and k in s_ks:
4036 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4037
4038 # Youtube Music Auto-generated description
822b9d9c 4039 if video_description:
1890fc63 4040 mobj = re.search(
4041 r'''(?xs)
4042 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4043 (?P<album>[^\n]+)
4044 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4045 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4046 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4047 .+\nAuto-generated\ by\ YouTube\.\s*$
4048 ''', video_description)
822b9d9c 4049 if mobj:
822b9d9c
RA
4050 release_year = mobj.group('release_year')
4051 release_date = mobj.group('release_date')
4052 if release_date:
4053 release_date = release_date.replace('-', '')
4054 if not release_year:
545cc85d 4055 release_year = release_date[:4]
4056 info.update({
4057 'album': mobj.group('album'.strip()),
4058 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4059 'track': mobj.group('track').strip(),
4060 'release_date': release_date,
cc2db878 4061 'release_year': int_or_none(release_year),
545cc85d 4062 })
7e72694b 4063
545cc85d 4064 initial_data = None
4065 if webpage:
56ba69e4 4066 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4067 if not initial_data:
99e9e001 4068 query = {'videoId': video_id}
4069 query.update(self._get_checkok_params())
109dd3b2 4070 initial_data = self._extract_response(
4071 item_id=video_id, ep='next', fatal=False,
99e9e001 4072 ytcfg=master_ytcfg, query=query,
4073 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4074 note='Downloading initial data API JSON')
545cc85d 4075
0df111a3 4076 info['comment_count'] = traverse_obj(initial_data, (
4077 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4078 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4079 ), (
4080 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4081 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4082 ), expected_type=int_or_none, get_all=False)
4083
19a03940 4084 try: # This will error if there is no livechat
c60ee3a2 4085 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4086 except (KeyError, IndexError, TypeError):
4087 pass
4088 else:
ecdc9049 4089 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4090 # url is needed to set cookies
4091 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4092 'video_id': video_id,
4093 'ext': 'json',
4d37720a
L
4094 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4095 else 'youtube_live_chat_replay'),
c60ee3a2 4096 }]
545cc85d 4097
4098 if initial_data:
7c365c21 4099 info['chapters'] = (
4100 self._extract_chapters_from_json(initial_data, duration)
4101 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4102 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4103 or None)
545cc85d 4104
17322130 4105 contents = traverse_obj(
4106 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4107 expected_type=list, default=[])
4108
4109 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4110 if vpir:
4111 stl = vpir.get('superTitleLink')
4112 if stl:
4113 stl = self._get_text(stl)
4114 if try_get(
4115 vpir,
4116 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4117 info['location'] = stl
4118 else:
affc4fef 4119 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4120 if mobj:
545cc85d 4121 info.update({
17322130 4122 'series': mobj.group(1),
4123 'season_number': int(mobj.group(2)),
4124 'episode_number': int(mobj.group(3)),
545cc85d 4125 })
17322130 4126 for tlb in (try_get(
4127 vpir,
4128 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4129 list) or []):
3ffb2f5b 4130 tbrs = variadic(
4131 traverse_obj(
4132 tlb, 'toggleButtonRenderer',
4133 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4134 default=[]))
4135 for tbr in tbrs:
4136 for getter, regex in [(
4137 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4138 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4139 lambda x: x['accessibility'],
4140 lambda x: x['accessibilityData']['accessibilityData'],
4141 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4142 label = (try_get(tbr, getter, dict) or {}).get('label')
4143 if label:
4144 mobj = re.match(regex, label)
4145 if mobj:
4146 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4147 break
17322130 4148 sbr_tooltip = try_get(
4149 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4150 if sbr_tooltip:
4151 like_count, dislike_count = sbr_tooltip.split(' / ')
4152 info.update({
4153 'like_count': str_to_int(like_count),
4154 'dislike_count': str_to_int(dislike_count),
4155 })
867c66ff
M
4156 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4157 if vcr:
4158 vc = self._get_count(vcr, 'viewCount')
4159 # Upcoming premieres with waiting count are treated as live here
4160 if vcr.get('isLive'):
4161 info['concurrent_view_count'] = vc
4162 elif info.get('view_count') is None:
4163 info['view_count'] = vc
4164
17322130 4165 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4166 if vsir:
4167 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4168 info.update({
4169 'channel': self._get_text(vor, 'title'),
4170 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4171
4172 rows = try_get(
4173 vsir,
4174 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4175 list) or []
4176 multiple_songs = False
4177 for row in rows:
4178 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4179 multiple_songs = True
4180 break
4181 for row in rows:
4182 mrr = row.get('metadataRowRenderer') or {}
4183 mrr_title = mrr.get('title')
4184 if not mrr_title:
4185 continue
4186 mrr_title = self._get_text(mrr, 'title')
4187 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4188 if mrr_title == 'License':
4189 info['license'] = mrr_contents_text
4190 elif not multiple_songs:
4191 if mrr_title == 'Album':
4192 info['album'] = mrr_contents_text
4193 elif mrr_title == 'Artist':
4194 info['artist'] = mrr_contents_text
4195 elif mrr_title == 'Song':
4196 info['track'] = mrr_contents_text
545cc85d 4197
4198 fallbacks = {
4199 'channel': 'uploader',
4200 'channel_id': 'uploader_id',
4201 'channel_url': 'uploader_url',
4202 }
992f9a73 4203
17322130 4204 # The upload date for scheduled, live and past live streams / premieres in microformats
4205 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4206 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4207 upload_date = (
4208 unified_strdate(get_first(microformats, 'uploadDate'))
4209 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4210 if not upload_date or (
4d37720a 4211 live_status in ('not_live', None)
1ff88b7a 4212 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4213 ):
c26f9b99 4214 upload_date = strftime_or_none(
4215 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4216 info['upload_date'] = upload_date
992f9a73 4217
545cc85d 4218 for to, frm in fallbacks.items():
4219 if not info.get(to):
4220 info[to] = info.get(frm)
4221
4222 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4223 v = info.get(s_k)
4224 if v:
4225 info[d_k] = v
b84071c0 4226
c26f9b99 4227 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4228
4229 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4230 or get_first(video_details, 'isPrivate', expected_type=bool))
4231
4232 info['availability'] = (
4233 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4234 else self._availability(
4235 is_private=is_private,
4236 needs_premium=(
4237 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4238 or False if initial_data and is_private is not None else None),
4239 needs_subscription=(
4240 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4241 or False if initial_data and is_private is not None else None),
4242 needs_auth=info['age_limit'] >= 18,
4243 is_unlisted=None if is_private is None else (
4244 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4245 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4246
a2160aa4 4247 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4248
11f9be09 4249 self.mark_watched(video_id, player_responses)
d77ab8e2 4250
545cc85d 4251 return info
c5e8d7af 4252
a61fd4cf 4253
a6213a49 4254class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 4255
182bda88 4256 @staticmethod
4257 def passthrough_smuggled_data(func):
4258 def _smuggle(entries, smuggled_data):
4259 for entry in entries:
4260 # TODO: Convert URL to music.youtube instead.
4261 # Do we need to passthrough any other smuggled_data?
4262 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4263 yield entry
4264
4265 @functools.wraps(func)
4266 def wrapper(self, url):
4267 url, smuggled_data = unsmuggle_url(url, {})
4268 if self.is_music_url(url):
4269 smuggled_data['is_music_url'] = True
4270 info_dict = func(self, url, smuggled_data)
4271 if smuggled_data and info_dict.get('entries'):
4272 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4273 return info_dict
4274 return wrapper
4275
a6213a49 4276 def _extract_channel_id(self, webpage):
4277 channel_id = self._html_search_meta(
4278 'channelId', webpage, 'channel id', default=None)
4279 if channel_id:
4280 return channel_id
4281 channel_url = self._html_search_meta(
4282 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4283 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4284 'twitter:app:url:googleplay'), webpage, 'channel url')
4285 return self._search_regex(
4286 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4287 channel_url, 'channel id')
15f6397c 4288
8bdd16b4 4289 @staticmethod
cd7c66cf 4290 def _extract_basic_item_renderer(item):
4291 # Modified from _extract_grid_item_renderer
201c1459 4292 known_basic_renderers = (
a17526e4 4293 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4294 )
4295 for key, renderer in item.items():
201c1459 4296 if not isinstance(renderer, dict):
cd7c66cf 4297 continue
201c1459 4298 elif key in known_basic_renderers:
4299 return renderer
4300 elif key.startswith('grid') and key.endswith('Renderer'):
4301 return renderer
8bdd16b4 4302
8bdd16b4 4303 def _grid_entries(self, grid_renderer):
4304 for item in grid_renderer['items']:
4305 if not isinstance(item, dict):
39b62db1 4306 continue
cd7c66cf 4307 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4308 if not isinstance(renderer, dict):
4309 continue
052e1350 4310 title = self._get_text(renderer, 'title')
fe93e2c4 4311
8bdd16b4 4312 # playlist
4313 playlist_id = renderer.get('playlistId')
4314 if playlist_id:
4315 yield self.url_result(
4316 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4317 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4318 video_title=title)
201c1459 4319 continue
8bdd16b4 4320 # video
4321 video_id = renderer.get('videoId')
4322 if video_id:
4323 yield self._extract_video(renderer)
201c1459 4324 continue
8bdd16b4 4325 # channel
4326 channel_id = renderer.get('channelId')
4327 if channel_id:
8bdd16b4 4328 yield self.url_result(
4329 'https://www.youtube.com/channel/%s' % channel_id,
4330 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4331 continue
4332 # generic endpoint URL support
4333 ep_url = urljoin('https://www.youtube.com/', try_get(
4334 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4335 str))
201c1459 4336 if ep_url:
4337 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4338 if ie.suitable(ep_url):
4339 yield self.url_result(
4340 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4341 break
8bdd16b4 4342
16aa9ea4 4343 def _music_reponsive_list_entry(self, renderer):
4344 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4345 if video_id:
4346 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4347 ie=YoutubeIE.ie_key(), video_id=video_id)
4348 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4349 if playlist_id:
4350 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4351 if video_id:
4352 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4353 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4354 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4355 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4356 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4357 if browse_id:
4358 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4359 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4360
3d3dddc9 4361 def _shelf_entries_from_content(self, shelf_renderer):
4362 content = shelf_renderer.get('content')
4363 if not isinstance(content, dict):
8bdd16b4 4364 return
cd7c66cf 4365 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4366 if renderer:
4367 # TODO: add support for nested playlists so each shelf is processed
4368 # as separate playlist
4369 # TODO: this includes only first N items
86e5f3ed 4370 yield from self._grid_entries(renderer)
3d3dddc9 4371 renderer = content.get('horizontalListRenderer')
4372 if renderer:
4373 # TODO
4374 pass
8bdd16b4 4375
29f7c58a 4376 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4377 ep = try_get(
4378 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4379 str)
8bdd16b4 4380 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4381 if shelf_url:
29f7c58a 4382 # Skipping links to another channels, note that checking for
4383 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4384 # will not work
4385 if skip_channels and '/channels?' in shelf_url:
4386 return
052e1350 4387 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4388 yield self.url_result(shelf_url, video_title=title)
4389 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4390 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4391
8bdd16b4 4392 def _playlist_entries(self, video_list_renderer):
4393 for content in video_list_renderer['contents']:
4394 if not isinstance(content, dict):
4395 continue
4396 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4397 if not isinstance(renderer, dict):
4398 continue
4399 video_id = renderer.get('videoId')
4400 if not video_id:
4401 continue
4402 yield self._extract_video(renderer)
07aeced6 4403
3462ffa8 4404 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4405 renderer = traverse_obj(
4406 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4407 video_id = renderer.get('videoId')
4408 if not video_id:
4409 return
4410 yield self._extract_video(renderer)
4411
8bdd16b4 4412 def _video_entry(self, video_renderer):
4413 video_id = video_renderer.get('videoId')
4414 if video_id:
4415 return self._extract_video(video_renderer)
dacb3a86 4416
ad210f4f 4417 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4418 url = urljoin('https://youtube.com', traverse_obj(
4419 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4420 if url:
4421 return self.url_result(
4422 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4423
8bdd16b4 4424 def _post_thread_entries(self, post_thread_renderer):
4425 post_renderer = try_get(
4426 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4427 if not post_renderer:
4428 return
4429 # video attachment
4430 video_renderer = try_get(
895b0931 4431 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4432 video_id = video_renderer.get('videoId')
4433 if video_id:
4434 entry = self._extract_video(video_renderer)
8bdd16b4 4435 if entry:
4436 yield entry
895b0931 4437 # playlist attachment
4438 playlist_id = try_get(
14f25df2 4439 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4440 if playlist_id:
4441 yield self.url_result(
e28f1c0a 4442 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4443 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4444 # inline video links
4445 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4446 for run in runs:
4447 if not isinstance(run, dict):
4448 continue
4449 ep_url = try_get(
14f25df2 4450 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4451 if not ep_url:
4452 continue
4453 if not YoutubeIE.suitable(ep_url):
4454 continue
4455 ep_video_id = YoutubeIE._match_id(ep_url)
4456 if video_id == ep_video_id:
4457 continue
895b0931 4458 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4459
8bdd16b4 4460 def _post_thread_continuation_entries(self, post_thread_continuation):
4461 contents = post_thread_continuation.get('contents')
4462 if not isinstance(contents, list):
4463 return
4464 for content in contents:
4465 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4466 if isinstance(renderer, dict):
4467 yield from self._post_thread_entries(renderer)
8bdd16b4 4468 continue
6b0b0a28 4469 renderer = content.get('videoRenderer')
4470 if isinstance(renderer, dict):
4471 yield self._video_entry(renderer)
07aeced6 4472
39ed931e 4473 r''' # unused
4474 def _rich_grid_entries(self, contents):
4475 for content in contents:
4476 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4477 if video_renderer:
4478 entry = self._video_entry(video_renderer)
4479 if entry:
4480 yield entry
4481 '''
52efa4b3 4482
0a5095fe 4483 def _report_history_entries(self, renderer):
4484 for url in traverse_obj(renderer, (
7a32c70d 4485 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4486 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4487 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4488 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4489
a6213a49 4490 def _extract_entries(self, parent_renderer, continuation_list):
4491 # continuation_list is modified in-place with continuation_list = [continuation_token]
4492 continuation_list[:] = [None]
4493 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4494 for content in contents:
4495 if not isinstance(content, dict):
4496 continue
16aa9ea4 4497 is_renderer = traverse_obj(
4498 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4499 expected_type=dict)
a6213a49 4500 if not is_renderer:
0a5095fe 4501 if content.get('richItemRenderer'):
4502 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4503 yield entry
4504 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4505 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4506 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4507 yield from self._report_history_entries(table)
4508 continuation_list[0] = self._extract_continuation(table)
a6213a49 4509 continue
0a5095fe 4510
a6213a49 4511 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4512 for isr_content in isr_contents:
4513 if not isinstance(isr_content, dict):
8bdd16b4 4514 continue
69184e41 4515
a6213a49 4516 known_renderers = {
4517 'playlistVideoListRenderer': self._playlist_entries,
4518 'gridRenderer': self._grid_entries,
a17526e4 4519 'reelShelfRenderer': self._grid_entries,
4520 'shelfRenderer': self._shelf_entries,
16aa9ea4 4521 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4522 'backstagePostThreadRenderer': self._post_thread_entries,
4523 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4524 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4525 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4526 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4527 }
4528 for key, renderer in isr_content.items():
4529 if key not in known_renderers:
4530 continue
4531 for entry in known_renderers[key](renderer):
4532 if entry:
4533 yield entry
4534 continuation_list[0] = self._extract_continuation(renderer)
4535 break
70d5c17b 4536
4537 if not continuation_list[0]:
a6213a49 4538 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4539
a6213a49 4540 if not continuation_list[0]:
4541 continuation_list[0] = self._extract_continuation(parent_renderer)
4542
4543 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4544 continuation_list = [None]
4545 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4546 tab_content = try_get(tab, lambda x: x['content'], dict)
4547 if not tab_content:
4548 return
3462ffa8 4549 parent_renderer = (
29f7c58a 4550 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4551 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4552 yield from extract_entries(parent_renderer)
3462ffa8 4553 continuation = continuation_list[0]
d069eca7 4554
8bdd16b4 4555 for page_num in itertools.count(1):
4556 if not continuation:
4557 break
99e9e001 4558 headers = self.generate_api_headers(
4559 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4560 response = self._extract_response(
86e5f3ed 4561 item_id=f'{item_id} page {page_num}',
fe93e2c4 4562 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4563 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4564
4565 if not response:
8bdd16b4 4566 break
ac56cf38 4567 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4568 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4569 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4570
a1b535bd 4571 known_renderers = {
e4b98809 4572 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4573 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4574 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4575 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4576 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4577 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4578 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4579 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4580 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4581 'playlistVideoListContinuation': (self._playlist_entries, None),
4582 'gridContinuation': (self._grid_entries, None),
4583 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4584 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4585 }
1fb53b94 4586
4587 continuation_items = traverse_obj(response, (
4588 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4589 'appendContinuationItemsAction', 'continuationItems'
4590 ), 'continuationContents', get_all=False)
4591 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4592
a1b535bd 4593 video_items_renderer = None
1fb53b94 4594 for key in continuation_item.keys():
a1b535bd 4595 if key not in known_renderers:
8bdd16b4 4596 continue
1fb53b94 4597 func, parent_key = known_renderers[key]
4598 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4599 continuation_list = [None]
1fb53b94 4600 yield from func(video_items_renderer)
9ba5705a 4601 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4602
4603 if not video_items_renderer:
a1b535bd 4604 break
9558dcec 4605
8bdd16b4 4606 @staticmethod
7c219ea6 4607 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4608 for tab_renderer in tabs:
4609 if tab_renderer.get('selected'):
4610 return tab_renderer
4611 if fatal:
4612 raise ExtractorError('Unable to find selected tab')
4613
4614 @staticmethod
4615 def _extract_tab_renderers(response):
4616 return traverse_obj(
4617 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4618
ac56cf38 4619 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4620 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4621 tags = []
b60419c5 4622
8bdd16b4 4623 selected_tab = self._extract_selected_tab(tabs)
6141346d 4624 # Deprecated - remove when layout discontinued
f0d785d3 4625 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
6141346d
M
4626 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4627 metadata_renderer = try_get(
8bdd16b4 4628 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
6141346d
M
4629 if metadata_renderer:
4630 channel_name = metadata_renderer.get('title')
4631 channel_url = metadata_renderer.get('channelUrl')
4632 channel_id = metadata_renderer.get('externalId')
39ed931e 4633 else:
6141346d 4634 metadata_renderer = try_get(
64c0d954 4635 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4636
6141346d
M
4637 if metadata_renderer:
4638 title = metadata_renderer.get('title')
4639 description = metadata_renderer.get('description', '')
b60419c5 4640 playlist_id = channel_id
6141346d 4641 tags = metadata_renderer.get('keywords', '').split()
b60419c5 4642
301d07fc 4643 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4644 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4645 def _get_uncropped(url):
4646 return url_or_none((url or '').split('=')[0] + '=s0')
4647
6141346d 4648 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 4649 if avatar_thumbnails:
4650 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4651 if uncropped_avatar:
4652 avatar_thumbnails.append({
4653 'url': uncropped_avatar,
4654 'id': 'avatar_uncropped',
4655 'preference': 1
4656 })
4657
4658 channel_banners = self._extract_thumbnails(
4659 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4660 for banner in channel_banners:
4661 banner['preference'] = -10
4662
4663 if channel_banners:
4664 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4665 if uncropped_banner:
4666 channel_banners.append({
4667 'url': uncropped_banner,
4668 'id': 'banner_uncropped',
4669 'preference': -5
4670 })
4671
6141346d 4672 # Deprecated - remove when old layout is discontinued
301d07fc 4673 primary_thumbnails = self._extract_thumbnails(
a17526e4 4674 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4675
6141346d
M
4676 playlist_thumbnails = self._extract_thumbnails(
4677 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4678
3462ffa8 4679 if playlist_id is None:
70d5c17b 4680 playlist_id = item_id
f0d785d3 4681
6141346d
M
4682 # Deprecated - remove primary_sidebar_renderer when old layout discontinued
4683 # Playlist stats is a text runs array containing [video count, view count, last updated].
4684 # last updated or (view count and last updated) may be missing.
4685 playlist_stats = get_first(
4686 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'),))
4687 last_updated_unix = self._parse_time_text(
4688 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4689 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4690
4691 view_count = self._get_count(playlist_stats, 1)
4692 if view_count is None:
4693 view_count = self._get_count(playlist_header_renderer, 'viewCountText')
4694
4695 playlist_count = self._get_count(playlist_stats, 0)
4696 if playlist_count is None:
4697 playlist_count = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4698
70d5c17b 4699 if title is None:
f0d785d3 4700 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4701 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4702 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4703
b60419c5 4704 metadata = {
4705 'playlist_id': playlist_id,
4706 'playlist_title': title,
4707 'playlist_description': description,
4708 'uploader': channel_name,
4709 'uploader_id': channel_id,
4710 'uploader_url': channel_url,
6141346d 4711 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
b60419c5 4712 'tags': tags,
6141346d 4713 'view_count': view_count,
f0d785d3 4714 'availability': self._extract_availability(data),
4715 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6141346d 4716 'playlist_count': playlist_count,
6c73052c 4717 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4718 }
4719 if not channel_id:
6141346d
M
4720 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4721 if not owner:
4722 # Deprecated
4723 owner = traverse_obj(
4724 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4725 ('videoOwner', 'videoOwnerRenderer', 'title'))
4726 owner_text = self._get_text(owner)
4727 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4728 metadata.update(filter_dict({
4729 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4730 'uploader_id': browse_ep.get('browseId'),
4731 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4732 }))
4733
b60419c5 4734 metadata.update({
4735 'channel': metadata['uploader'],
4736 'channel_id': metadata['uploader_id'],
4737 'channel_url': metadata['uploader_url']})
4738 return self.playlist_result(
d069eca7 4739 self._entries(
ac56cf38 4740 selected_tab, playlist_id, ytcfg,
4741 self._extract_account_syncid(ytcfg, data),
4742 self._extract_visitor_data(data, ytcfg)),
b60419c5 4743 **metadata)
73c4ac2c 4744
6e634cbe 4745 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4746 first_id = last_id = response = None
2be71994 4747 for page_num in itertools.count(1):
cd7c66cf 4748 videos = list(self._playlist_entries(playlist))
4749 if not videos:
4750 return
2be71994 4751 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4752 if start >= len(videos):
4753 return
24146491 4754 yield from videos[start:]
2be71994 4755 first_id = first_id or videos[0]['id']
4756 last_id = videos[-1]['id']
79360d99 4757 watch_endpoint = try_get(
4758 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4759 headers = self.generate_api_headers(
4760 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4761 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4762 query = {
4763 'playlistId': playlist_id,
4764 'videoId': watch_endpoint.get('videoId') or last_id,
4765 'index': watch_endpoint.get('index') or len(videos),
4766 'params': watch_endpoint.get('params') or 'OAE%3D'
4767 }
4768 response = self._extract_response(
4769 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4770 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4771 check_get_keys='contents'
4772 )
cd7c66cf 4773 playlist = try_get(
79360d99 4774 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4775
ac56cf38 4776 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4777 title = playlist.get('title') or try_get(
14f25df2 4778 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4779 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4780
4781 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4782 playlist_url = urljoin(url, try_get(
4783 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4784 str))
6e634cbe 4785
4786 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4787 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4788 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4789
4790 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4791 return self.url_result(
4792 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4793 video_title=title)
cd7c66cf 4794
8bdd16b4 4795 return self.playlist_result(
6e634cbe 4796 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4797 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4798
47193e02 4799 def _extract_availability(self, data):
4800 """
4801 Gets the availability of a given playlist/tab.
4802 Note: Unless YouTube tells us explicitly, we do not assume it is public
4803 @param data: response
4804 """
6141346d
M
4805 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4806 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4807 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 4808
6141346d 4809 badges = self._extract_badges(sidebar_renderer)
47193e02 4810
4811 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
4812 privacy_setting_icon = get_first(
4813 (playlist_header_renderer, sidebar_renderer),
4814 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4815 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4816 expected_type=str)
4817
4818 microformats_is_unlisted = traverse_obj(
4819 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 4820
c26f9b99 4821 return (
4822 'public' if (
4823 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4824 or player_header_privacy == 'PUBLIC'
4825 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4826 else self._availability(
4827 is_private=(
4828 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4829 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4830 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4831 is_unlisted=(
4832 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4833 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
4834 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
4835 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 4836 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4837 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4838 needs_auth=False))
47193e02 4839
4840 @staticmethod
4841 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4842 sidebar_renderer = try_get(
4843 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4844 for item in sidebar_renderer:
4845 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4846 if renderer:
4847 return renderer
4848
ac56cf38 4849 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4850 """
6141346d 4851 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 4852 """
6141346d
M
4853 is_playlist = bool(traverse_obj(
4854 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
4855 if not is_playlist:
47193e02 4856 return
11f9be09 4857 headers = self.generate_api_headers(
99e9e001 4858 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4859 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4860 query = {
6141346d
M
4861 'params': 'wgYCCAA=',
4862 'browseId': f'VL{item_id}'
47193e02 4863 }
4864 return self._extract_response(
4865 item_id=item_id, headers=headers, query=query,
fe93e2c4 4866 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 4867 note='Redownloading playlist API JSON with unavailable videos')
358de58c 4868
2762dbb1 4869 @functools.cached_property
a25bca9f 4870 def skip_webpage(self):
4871 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4872
ac56cf38 4873 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4874 webpage, data = None, None
4875 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4876 try:
be5c1ae8 4877 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4878 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4879 except ExtractorError as e:
4880 if isinstance(e.cause, network_exceptions):
14f25df2 4881 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4882 retry.error = e
4883 continue
4884 self._error_or_warning(e, fatal=fatal)
14fdfea9 4885 break
ac56cf38 4886
be5c1ae8 4887 try:
4888 self._extract_and_report_alerts(data)
4889 except ExtractorError as e:
4890 self._error_or_warning(e, fatal=fatal)
4891 break
ac56cf38 4892
be5c1ae8 4893 # Sometimes youtube returns a webpage with incomplete ytInitialData
4894 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4895 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4896 retry.error = ExtractorError('Incomplete yt initial data received')
4897 continue
ac56cf38 4898
cd7c66cf 4899 return webpage, data
4900
a25bca9f 4901 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4902 """Use if failed to extract ytcfg (and data) from initial webpage"""
4903 if not ytcfg and self.is_authenticated:
4904 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4905 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4906 raise ExtractorError(
4907 f'{msg}. If you are not downloading private content, or '
4908 'your cookies are only for the first account and channel,'
4909 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4910 expected=True)
4911 self.report_warning(msg, only_once=True)
4912
ac56cf38 4913 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4914 data = None
a25bca9f 4915 if not self.skip_webpage:
ac56cf38 4916 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4917 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4918 # Reject webpage data if redirected to home page without explicitly requesting
86973308 4919 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 4920 if (url != 'https://www.youtube.com/feed/recommended'
4921 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4922 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4923 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4924 if fatal:
4925 raise ExtractorError(msg, expected=True)
4926 self.report_warning(msg, only_once=True)
ac56cf38 4927 if not data:
a25bca9f 4928 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4929 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4930 return data, ytcfg
4931
4932 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4933 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4934 resolve_response = self._extract_response(
4935 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4936 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4937 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4938 for ep_key, ep in endpoints.items():
4939 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4940 if params:
4941 return self._extract_response(
4942 item_id=item_id, query=params, ep=ep, headers=headers,
4943 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4944 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4945 err_note = 'Failed to resolve url (does the playlist exist?)'
4946 if fatal:
4947 raise ExtractorError(err_note, expected=True)
4948 self.report_warning(err_note, item_id)
4949
a6213a49 4950 _SEARCH_PARAMS = None
4951
af5c1c55 4952 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4953 data = {'query': query}
4954 if params is NO_DEFAULT:
4955 params = self._SEARCH_PARAMS
4956 if params:
4957 data['params'] = params
16aa9ea4 4958
4959 content_keys = (
4960 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4961 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4962 # ytmusic search
4963 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4964 ('continuationContents', ),
4965 )
a25bca9f 4966 display_id = f'query "{query}"'
86e5f3ed 4967 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4968 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4969 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4970
a61fd4cf 4971 continuation_list = [None]
a25bca9f 4972 search = None
a6213a49 4973 for page_num in itertools.count(1):
a61fd4cf 4974 data.update(continuation_list[0] or {})
a25bca9f 4975 headers = self.generate_api_headers(
4976 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4977 search = self._extract_response(
a25bca9f 4978 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4979 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4980 slr_contents = traverse_obj(search, *content_keys)
4981 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4982 if not continuation_list[0]:
a6213a49 4983 break
4984
4985
4986class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4987 IE_DESC = 'YouTube Tabs'
4988 _VALID_URL = r'''(?x:
4989 https?://
4990 (?:\w+\.)?
4991 (?:
4992 youtube(?:kids)?\.com|
4993 %(invidious)s
4994 )/
4995 (?:
4996 (?P<channel_type>channel|c|user|browse)/|
4997 (?P<not_channel>
4998 feed/|hashtag/|
4999 (?:playlist|watch)\?.*?\blist=
5000 )|
5001 (?!(?:%(reserved_names)s)\b) # Direct URLs
5002 )
5003 (?P<id>[^/?\#&]+)
5004 )''' % {
5005 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5006 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5007 }
5008 IE_NAME = 'youtube:tab'
5009
5010 _TESTS = [{
5011 'note': 'playlists, multipage',
5012 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5013 'playlist_mincount': 94,
5014 'info_dict': {
5015 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5016 'title': 'Igor Kleiner - Playlists',
a6213a49 5017 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5018 'uploader': 'Igor Kleiner',
a6213a49 5019 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5020 'channel': 'Igor Kleiner',
5021 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5022 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5023 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5024 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5025 'channel_follower_count': int
a6213a49 5026 },
5027 }, {
5028 'note': 'playlists, multipage, different order',
5029 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5030 'playlist_mincount': 94,
5031 'info_dict': {
5032 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5033 'title': 'Igor Kleiner - Playlists',
a6213a49 5034 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5035 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5036 'uploader': 'Igor Kleiner',
5037 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5038 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5039 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5040 'channel': 'Igor Kleiner',
5041 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5042 'channel_follower_count': int
a6213a49 5043 },
5044 }, {
5045 'note': 'playlists, series',
5046 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5047 'playlist_mincount': 5,
5048 'info_dict': {
5049 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5050 'title': '3Blue1Brown - Playlists',
5051 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5052 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5053 'uploader': '3Blue1Brown',
976ae3ea 5054 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5055 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5056 'channel': '3Blue1Brown',
5057 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5058 'tags': ['Mathematics'],
6c73052c 5059 'channel_follower_count': int
a6213a49 5060 },
5061 }, {
5062 'note': 'playlists, singlepage',
5063 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5064 'playlist_mincount': 4,
5065 'info_dict': {
5066 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5067 'title': 'ThirstForScience - Playlists',
5068 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5069 'uploader': 'ThirstForScience',
5070 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5071 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5072 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5073 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5074 'tags': 'count:13',
5075 'channel': 'ThirstForScience',
6c73052c 5076 'channel_follower_count': int
a6213a49 5077 }
5078 }, {
5079 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5080 'only_matching': True,
5081 }, {
5082 'note': 'basic, single video playlist',
5083 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5084 'info_dict': {
5085 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5086 'uploader': 'Sergey M.',
5087 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5088 'title': 'youtube-dl public playlist',
976ae3ea 5089 'description': '',
5090 'tags': [],
5091 'view_count': int,
5092 'modified_date': '20201130',
5093 'channel': 'Sergey M.',
5094 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5095 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5096 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5097 'availability': 'public',
a6213a49 5098 },
5099 'playlist_count': 1,
5100 }, {
5101 'note': 'empty playlist',
5102 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5103 'info_dict': {
5104 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5105 'uploader': 'Sergey M.',
5106 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5107 'title': 'youtube-dl empty playlist',
976ae3ea 5108 'tags': [],
5109 'channel': 'Sergey M.',
5110 'description': '',
5111 'modified_date': '20160902',
5112 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5113 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5114 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5115 'availability': 'public',
a6213a49 5116 },
5117 'playlist_count': 0,
5118 }, {
5119 'note': 'Home tab',
5120 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5121 'info_dict': {
5122 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5123 'title': 'lex will - Home',
5124 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5125 'uploader': 'lex will',
5126 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5127 'channel': 'lex will',
5128 'tags': ['bible', 'history', 'prophesy'],
5129 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5130 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5131 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5132 'channel_follower_count': int
a6213a49 5133 },
5134 'playlist_mincount': 2,
5135 }, {
5136 'note': 'Videos tab',
5137 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5138 'info_dict': {
5139 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5140 'title': 'lex will - Videos',
5141 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5142 'uploader': 'lex will',
5143 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5144 'tags': ['bible', 'history', 'prophesy'],
5145 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5146 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5147 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5148 'channel': 'lex will',
6c73052c 5149 'channel_follower_count': int
a6213a49 5150 },
5151 'playlist_mincount': 975,
5152 }, {
5153 'note': 'Videos tab, sorted by popular',
5154 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5155 'info_dict': {
5156 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5157 'title': 'lex will - Videos',
5158 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5159 'uploader': 'lex will',
5160 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5161 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5162 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5163 'channel': 'lex will',
5164 'tags': ['bible', 'history', 'prophesy'],
5165 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5166 'channel_follower_count': int
a6213a49 5167 },
5168 'playlist_mincount': 199,
5169 }, {
5170 'note': 'Playlists tab',
5171 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5172 'info_dict': {
5173 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5174 'title': 'lex will - Playlists',
5175 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5176 'uploader': 'lex will',
5177 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5178 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5179 'channel': 'lex will',
5180 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5181 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5182 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5183 'channel_follower_count': int
a6213a49 5184 },
5185 'playlist_mincount': 17,
5186 }, {
5187 'note': 'Community tab',
5188 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5189 'info_dict': {
5190 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5191 'title': 'lex will - Community',
5192 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5193 'uploader': 'lex will',
5194 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5195 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5196 'channel': 'lex will',
5197 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5198 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5199 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5200 'channel_follower_count': int
a6213a49 5201 },
5202 'playlist_mincount': 18,
5203 }, {
5204 'note': 'Channels tab',
5205 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5206 'info_dict': {
5207 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5208 'title': 'lex will - Channels',
5209 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5210 'uploader': 'lex will',
5211 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5212 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5213 'channel': 'lex will',
5214 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5215 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5216 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5217 'channel_follower_count': int
a6213a49 5218 },
5219 'playlist_mincount': 12,
5220 }, {
5221 'note': 'Search tab',
5222 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5223 'playlist_mincount': 40,
5224 'info_dict': {
5225 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5226 'title': '3Blue1Brown - Search - linear algebra',
5227 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5228 'uploader': '3Blue1Brown',
5229 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5230 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5231 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5232 'tags': ['Mathematics'],
5233 'channel': '3Blue1Brown',
5234 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5235 'channel_follower_count': int
a6213a49 5236 },
5237 }, {
5238 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5239 'only_matching': True,
5240 }, {
5241 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5242 'only_matching': True,
5243 }, {
5244 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5245 'only_matching': True,
5246 }, {
5247 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5248 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5249 'info_dict': {
5250 'title': '29C3: Not my department',
5251 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5252 'uploader': 'Christiaan008',
5253 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5254 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5255 'tags': [],
5256 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5257 'view_count': int,
5258 'modified_date': '20150605',
5259 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5260 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5261 'channel': 'Christiaan008',
c26f9b99 5262 'availability': 'public',
a6213a49 5263 },
5264 'playlist_count': 96,
5265 }, {
5266 'note': 'Large playlist',
5267 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5268 'info_dict': {
5269 'title': 'Uploads from Cauchemar',
5270 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5271 'uploader': 'Cauchemar',
5272 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5273 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5274 'tags': [],
5275 'modified_date': r're:\d{8}',
5276 'channel': 'Cauchemar',
5277 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5278 'view_count': int,
5279 'description': '',
5280 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5281 'availability': 'public',
a6213a49 5282 },
5283 'playlist_mincount': 1123,
976ae3ea 5284 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5285 }, {
5286 'note': 'even larger playlist, 8832 videos',
5287 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5288 'only_matching': True,
5289 }, {
5290 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5291 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5292 'info_dict': {
5293 'title': 'Uploads from Interstellar Movie',
5294 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5295 'uploader': 'Interstellar Movie',
5296 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5297 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5298 'tags': [],
5299 'view_count': int,
5300 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5301 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5302 'channel': 'Interstellar Movie',
5303 'description': '',
5304 'modified_date': r're:\d{8}',
c26f9b99 5305 'availability': 'public',
a6213a49 5306 },
5307 'playlist_mincount': 21,
5308 }, {
5309 'note': 'Playlist with "show unavailable videos" button',
5310 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5311 'info_dict': {
5312 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5313 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5314 'uploader': 'Phim Siêu Nhân Nhật Bản',
5315 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5316 'view_count': int,
5317 'channel': 'Phim Siêu Nhân Nhật Bản',
5318 'tags': [],
5319 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5320 'description': '',
5321 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5322 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5323 'modified_date': r're:\d{8}',
c26f9b99 5324 'availability': 'public',
a6213a49 5325 },
5326 'playlist_mincount': 200,
976ae3ea 5327 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5328 }, {
5329 'note': 'Playlist with unavailable videos in page 7',
5330 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5331 'info_dict': {
5332 'title': 'Uploads from BlankTV',
5333 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5334 'uploader': 'BlankTV',
5335 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5336 'channel': 'BlankTV',
5337 'channel_url': 'https://www.youtube.com/c/blanktv',
5338 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5339 'view_count': int,
5340 'tags': [],
5341 'uploader_url': 'https://www.youtube.com/c/blanktv',
5342 'modified_date': r're:\d{8}',
5343 'description': '',
c26f9b99 5344 'availability': 'public',
a6213a49 5345 },
5346 'playlist_mincount': 1000,
976ae3ea 5347 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5348 }, {
5349 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5350 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5351 'info_dict': {
5352 'title': 'Data Analysis with Dr Mike Pound',
5353 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5354 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5355 'uploader': 'Computerphile',
5356 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5357 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5358 'tags': [],
5359 'view_count': int,
5360 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5361 'channel_url': 'https://www.youtube.com/user/Computerphile',
5362 'channel': 'Computerphile',
c26f9b99 5363 'availability': 'public',
6141346d 5364 'modified_date': '20190712',
a6213a49 5365 },
5366 'playlist_mincount': 11,
5367 }, {
5368 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5369 'only_matching': True,
5370 }, {
5371 'note': 'Playlist URL that does not actually serve a playlist',
5372 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5373 'info_dict': {
5374 'id': 'FqZTN594JQw',
5375 'ext': 'webm',
5376 'title': "Smiley's People 01 detective, Adventure Series, Action",
5377 'uploader': 'STREEM',
5378 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5379 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5380 'upload_date': '20150526',
5381 'license': 'Standard YouTube License',
5382 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5383 'categories': ['People & Blogs'],
5384 'tags': list,
5385 'view_count': int,
5386 'like_count': int,
a6213a49 5387 },
5388 'params': {
5389 'skip_download': True,
5390 },
5391 'skip': 'This video is not available.',
5392 'add_ie': [YoutubeIE.ie_key()],
5393 }, {
5394 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5395 'only_matching': True,
5396 }, {
5397 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5398 'only_matching': True,
5399 }, {
5400 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5401 'info_dict': {
12a1b225 5402 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5403 'ext': 'mp4',
976ae3ea 5404 'title': str,
a6213a49 5405 'uploader': 'Sky News',
5406 'uploader_id': 'skynews',
5407 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5408 'upload_date': r're:\d{8}',
976ae3ea 5409 'description': str,
a6213a49 5410 'categories': ['News & Politics'],
5411 'tags': list,
5412 'like_count': int,
86973308 5413 'release_timestamp': int,
976ae3ea 5414 'channel': 'Sky News',
5415 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5416 'age_limit': 0,
5417 'view_count': int,
86973308 5418 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5419 'playable_in_embed': True,
86973308 5420 'release_date': r're:\d+',
976ae3ea 5421 'availability': 'public',
5422 'live_status': 'is_live',
5423 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5424 'channel_follower_count': int,
5425 'concurrent_view_count': int,
a6213a49 5426 },
5427 'params': {
5428 'skip_download': True,
5429 },
976ae3ea 5430 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5431 }, {
5432 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5433 'info_dict': {
5434 'id': 'a48o2S1cPoo',
5435 'ext': 'mp4',
5436 'title': 'The Young Turks - Live Main Show',
5437 'uploader': 'The Young Turks',
5438 'uploader_id': 'TheYoungTurks',
5439 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5440 'upload_date': '20150715',
5441 'license': 'Standard YouTube License',
5442 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5443 'categories': ['News & Politics'],
5444 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5445 'like_count': int,
a6213a49 5446 },
5447 'params': {
5448 'skip_download': True,
5449 },
5450 'only_matching': True,
5451 }, {
5452 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5453 'only_matching': True,
5454 }, {
5455 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5456 'only_matching': True,
5457 }, {
5458 'note': 'A channel that is not live. Should raise error',
5459 'url': 'https://www.youtube.com/user/numberphile/live',
5460 'only_matching': True,
5461 }, {
5462 'url': 'https://www.youtube.com/feed/trending',
5463 'only_matching': True,
5464 }, {
5465 'url': 'https://www.youtube.com/feed/library',
5466 'only_matching': True,
5467 }, {
5468 'url': 'https://www.youtube.com/feed/history',
5469 'only_matching': True,
5470 }, {
5471 'url': 'https://www.youtube.com/feed/subscriptions',
5472 'only_matching': True,
5473 }, {
5474 'url': 'https://www.youtube.com/feed/watch_later',
5475 'only_matching': True,
5476 }, {
5477 'note': 'Recommended - redirects to home page.',
5478 'url': 'https://www.youtube.com/feed/recommended',
5479 'only_matching': True,
5480 }, {
5481 'note': 'inline playlist with not always working continuations',
5482 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5483 'only_matching': True,
5484 }, {
5485 'url': 'https://www.youtube.com/course',
5486 'only_matching': True,
5487 }, {
5488 'url': 'https://www.youtube.com/zsecurity',
5489 'only_matching': True,
5490 }, {
5491 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5492 'only_matching': True,
5493 }, {
5494 'url': 'https://www.youtube.com/TheYoungTurks/live',
5495 'only_matching': True,
5496 }, {
5497 'url': 'https://www.youtube.com/hashtag/cctv9',
5498 'info_dict': {
5499 'id': 'cctv9',
5500 'title': '#cctv9',
976ae3ea 5501 'tags': [],
a6213a49 5502 },
4dc23a80 5503 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5504 }, {
5505 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5506 'only_matching': True,
5507 }, {
5508 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5509 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5510 'only_matching': True
5511 }, {
5512 'note': '/browse/ should redirect to /channel/',
5513 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5514 'only_matching': True
5515 }, {
5516 'note': 'VLPL, should redirect to playlist?list=PL...',
5517 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5518 'info_dict': {
5519 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5520 'uploader': 'NoCopyrightSounds',
5521 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5522 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5523 'title': 'NCS : All Releases 💿',
976ae3ea 5524 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5525 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5526 'modified_date': r're:\d{8}',
5527 'view_count': int,
5528 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5529 'tags': [],
5530 'channel': 'NoCopyrightSounds',
c26f9b99 5531 'availability': 'public',
a6213a49 5532 },
5533 'playlist_mincount': 166,
976ae3ea 5534 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5535 }, {
5536 'note': 'Topic, should redirect to playlist?list=UU...',
5537 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5538 'info_dict': {
5539 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5540 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5541 'title': 'Uploads from Royalty Free Music - Topic',
5542 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5543 'tags': [],
5544 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5545 'channel': 'Royalty Free Music - Topic',
5546 'view_count': int,
5547 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5548 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5549 'modified_date': r're:\d{8}',
5550 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5551 'description': '',
c26f9b99 5552 'availability': 'public',
a6213a49 5553 },
5554 'expected_warnings': [
a6213a49 5555 'The URL does not have a videos tab',
976ae3ea 5556 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5557 ],
5558 'playlist_mincount': 101,
5559 }, {
86973308
M
5560 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5561 # Treat as a general feed
a6213a49 5562 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5563 'info_dict': {
5564 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5565 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5566 'tags': [],
a6213a49 5567 },
a6213a49 5568 'playlist_mincount': 9,
5569 }, {
5570 'note': 'Youtube music Album',
5571 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5572 'info_dict': {
5573 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5574 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5575 'tags': [],
5576 'view_count': int,
5577 'description': '',
5578 'availability': 'unlisted',
5579 'modified_date': r're:\d{8}',
a6213a49 5580 },
5581 'playlist_count': 50,
5582 }, {
5583 'note': 'unlisted single video playlist',
5584 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5585 'info_dict': {
5586 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5587 'uploader': 'colethedj',
5588 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5589 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5590 'availability': 'unlisted',
5591 'tags': [],
12a1b225 5592 'modified_date': '20220418',
976ae3ea 5593 'channel': 'colethedj',
5594 'view_count': int,
5595 'description': '',
5596 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5597 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5598 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5599 },
5600 'playlist_count': 1,
5601 }, {
5602 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5603 'url': 'https://www.youtube.com/feed/recommended',
5604 'info_dict': {
5605 'id': 'recommended',
5606 'title': 'recommended',
6c73052c 5607 'tags': [],
a6213a49 5608 },
5609 'playlist_mincount': 50,
5610 'params': {
5611 'skip_download': True,
5612 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5613 },
5614 }, {
5615 'note': 'API Fallback: /videos tab, sorted by oldest first',
5616 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5617 'info_dict': {
5618 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5619 'title': 'Cody\'sLab - Videos',
5620 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5621 'uploader': 'Cody\'sLab',
5622 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5623 'channel': 'Cody\'sLab',
5624 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5625 'tags': [],
5626 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5627 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5628 'channel_follower_count': int
a6213a49 5629 },
5630 'playlist_mincount': 650,
5631 'params': {
5632 'skip_download': True,
5633 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5634 },
86973308 5635 'skip': 'Query for sorting no longer works',
a6213a49 5636 }, {
5637 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5638 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5639 'info_dict': {
5640 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5641 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5642 'title': 'Uploads from Royalty Free Music - Topic',
5643 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5644 'modified_date': r're:\d{8}',
5645 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5646 'description': '',
5647 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5648 'tags': [],
5649 'channel': 'Royalty Free Music - Topic',
5650 'view_count': int,
5651 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5652 'availability': 'public',
a6213a49 5653 },
a6213a49 5654 'playlist_mincount': 101,
5655 'params': {
5656 'skip_download': True,
5657 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5658 },
7c219ea6 5659 }, {
5660 'note': 'non-standard redirect to regional channel',
5661 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5662 'only_matching': True
61d3665d 5663 }, {
5664 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5665 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5666 'info_dict': {
5667 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5668 'modified_date': '20220407',
5669 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5670 'tags': [],
5671 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5672 'uploader': 'pukkandan',
5673 'availability': 'unlisted',
5674 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5675 'channel': 'pukkandan',
5676 'description': 'Test for collaborative playlist',
5677 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5678 'view_count': int,
61d3665d 5679 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5680 },
5681 'playlist_mincount': 2
c26f9b99 5682 }, {
5683 'note': 'translated tab name',
5684 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5685 'info_dict': {
5686 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5687 'tags': [],
5688 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5689 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 5690 'description': 'test description',
c26f9b99 5691 'title': 'cole-dlp-test-acc - 再生リスト',
5692 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5693 'uploader': 'cole-dlp-test-acc',
5694 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5695 'channel': 'cole-dlp-test-acc',
6141346d 5696 'channel_follower_count': int,
c26f9b99 5697 },
5698 'playlist_mincount': 1,
5699 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5700 'expected_warnings': ['Preferring "ja"'],
5701 }, {
5702 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5703 'note': 'preferred lang set with playlist with translated video titles',
5704 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5705 'info_dict': {
5706 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5707 'tags': [],
5708 'view_count': int,
5709 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5710 'uploader': 'cole-dlp-test-acc',
5711 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5712 'channel': 'cole-dlp-test-acc',
5713 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5714 'description': 'test',
5715 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5716 'title': 'dlp test playlist',
5717 'availability': 'public',
5718 },
5719 'playlist_mincount': 1,
5720 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5721 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5722 }, {
5723 # shorts audio pivot for 2GtVksBMYFM.
5724 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5725 'info_dict': {
5726 'id': 'sfv_audio_pivot',
5727 'title': 'sfv_audio_pivot',
5728 'tags': [],
5729 },
5730 'playlist_mincount': 50,
5731
86973308
M
5732 }, {
5733 # Channel with a real live tab (not to be mistaken with streams tab)
5734 # Do not treat like it should redirect to live stream
5735 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5736 'info_dict': {
5737 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5738 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5739 'tags': [],
5740 },
5741 'playlist_mincount': 20,
5742 }, {
5743 # Tab name is not the same as tab id
5744 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5745 'info_dict': {
5746 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5747 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5748 'tags': [],
5749 },
5750 'playlist_mincount': 8,
5751 }, {
5752 # Home tab id is literally home. Not to get mistaken with featured
5753 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5754 'info_dict': {
5755 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5756 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5757 'tags': [],
5758 },
5759 'playlist_mincount': 8,
5760 }, {
5761 # Should get three playlists for videos, shorts and streams tabs
5762 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5763 'info_dict': {
5764 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5765 'title': 'Uploads for UCK9V2B22uJYu3N7eR_BT9QA'
5766 },
5767 'playlist_count': 3,
5768 }, {
5769 # Shorts tab with channel with handle
5770 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5771 'info_dict': {
5772 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5773 'title': 'Not Just Bikes - Shorts',
5774 'tags': 'count:12',
5775 'uploader': 'Not Just Bikes',
5776 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5777 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5778 'channel_follower_count': int,
5779 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5780 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5781 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5782 'channel': 'Not Just Bikes',
5783 },
5784 'playlist_mincount': 10,
5785 }, {
5786 # Streams tab
5787 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5788 'info_dict': {
5789 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5790 'title': '中村悠一 - Live',
5791 'tags': 'count:7',
5792 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5793 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5794 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5795 'channel': '中村悠一',
5796 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5797 'channel_follower_count': int,
5798 'uploader': '中村悠一',
5799 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5800 },
5801 'playlist_mincount': 60,
5802 }, {
5803 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5804 # See test_youtube_lists
5805 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5806 'only_matching': True,
5807 }, {
5808 # No uploads and no UCID given. Should fail with no uploads error
5809 # See test_youtube_lists
5810 'url': 'https://www.youtube.com/news',
5811 'only_matching': True
5812 }, {
5813 # No videos tab but has a shorts tab
5814 'url': 'https://www.youtube.com/c/TKFShorts',
5815 'info_dict': {
5816 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5817 'title': 'Shorts Break - Shorts',
5818 'tags': 'count:32',
5819 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5820 'channel': 'Shorts Break',
5821 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5822 'uploader': 'Shorts Break',
5823 'channel_follower_count': int,
5824 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5825 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5826 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5827 },
5828 'playlist_mincount': 30,
5829 }, {
5830 # Trending Now Tab. tab id is empty
5831 'url': 'https://www.youtube.com/feed/trending',
5832 'info_dict': {
5833 'id': 'trending',
5834 'title': 'trending - Now',
5835 'tags': [],
5836 },
5837 'playlist_mincount': 30,
5838 }, {
5839 # Trending Gaming Tab. tab id is empty
5840 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
5841 'info_dict': {
5842 'id': 'trending',
5843 'title': 'trending - Gaming',
5844 'tags': [],
5845 },
5846 'playlist_mincount': 30,
4dc23a80
M
5847 }, {
5848 # Shorts url result in shorts tab
5849 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
5850 'info_dict': {
5851 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5852 'title': 'cole-dlp-test-acc - Shorts',
5853 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5854 'channel': 'cole-dlp-test-acc',
5855 'channel_follower_count': int,
5856 'description': 'test description',
5857 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5858 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5859 'tags': [],
5860 'uploader': 'cole-dlp-test-acc',
5861 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5862
5863 },
5864 'playlist': [{
5865 'info_dict': {
5866 '_type': 'url',
5867 'ie_key': 'Youtube',
5868 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
5869 'id': 'sSM9J5YH_60',
5870 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5871 'title': 'SHORT short',
5872 'channel': 'cole-dlp-test-acc',
5873 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5874 'view_count': int,
5875 'thumbnails': list,
5876 }
5877 }],
5878 'params': {'extract_flat': True},
5879 }, {
5880 # Live video status should be extracted
5881 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
5882 'info_dict': {
5883 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5884 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
5885 'tags': []
5886 },
5887 'playlist': [{
5888 'info_dict': {
5889 '_type': 'url',
5890 'ie_key': 'Youtube',
5891 'url': 'startswith:https://www.youtube.com/watch?v=',
5892 'id': str,
5893 'title': str,
5894 'live_status': 'is_live',
5895 'channel_id': str,
5896 'channel_url': str,
5897 'concurrent_view_count': int,
5898 'channel': str,
5899 }
5900 }],
5901 'params': {'extract_flat': True},
5902 'playlist_mincount': 1
a6213a49 5903 }]
5904
5905 @classmethod
5906 def suitable(cls, url):
86e5f3ed 5907 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5908
86973308
M
5909 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
5910
5911 def _get_url_mobj(self, url):
5912 mobj = self._URL_RE.match(url).groupdict()
5913 mobj.update((k, '') for k, v in mobj.items() if v is None)
5914 return mobj
5915
5916 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
5917 tab_name = (tab.get('title') or '').lower()
5918 tab_url = urljoin(base_url, traverse_obj(
5919 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5920
5921 tab_id = (traverse_obj(tab, 'tabIdentifier', expected_type=str)
5922 or tab_url and self._get_url_mobj(tab_url)['tab'][1:])
5923 if tab_id:
5924 return tab_id, tab_name
5925
5926 # Fallback to tab name if we cannot get the tab id.
5927 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
5928 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
5929 self.write_debug(f'Falling back to selected tab name: {tab_name}')
5930 return {
5931 'home': 'featured',
5932 'live': 'streams',
5933 }.get(tab_name, tab_name), tab_name
5934
5935 def _has_tab(self, tabs, tab_id):
5936 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 5937
182bda88 5938 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5939 def _real_extract(self, url, smuggled_data):
cd7c66cf 5940 item_id = self._match_id(url)
14f25df2 5941 url = urllib.parse.urlunparse(
5942 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5943 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5944
86973308
M
5945 mobj = self._get_url_mobj(url)
5946 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
fe03a6cd 5947 if is_channel:
5948 if smuggled_data.get('is_music_url'):
37e57a9f 5949 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5950 item_id = item_id[2:]
37e57a9f 5951 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5952 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5953 mdata = self._extract_tab_endpoint(
37e57a9f 5954 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5955 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5956 get_all=False, expected_type=str)
ac56cf38 5957 if not murl:
37e57a9f 5958 raise ExtractorError('Failed to resolve album to playlist')
86973308 5959 return self.url_result(murl, YoutubeTabIE)
37e57a9f 5960 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5961 pre = f'https://www.youtube.com/channel/{item_id}'
5962
86973308 5963 original_tab_id = tab[1:]
fe03a6cd 5964 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
fe03a6cd 5965 tab = '/videos'
5966
5967 url = ''.join((pre, tab, post))
86973308 5968 mobj = self._get_url_mobj(url)
cd7c66cf 5969
5970 # Handle both video/playlist URLs
201c1459 5971 qs = parse_qs(url)
86e5f3ed 5972 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5973
fe03a6cd 5974 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5975 if not playlist_id:
fe03a6cd 5976 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5977 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5978 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5979 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5980 url = f'https://www.youtube.com/playlist?list={playlist_id}'
86973308 5981 mobj = self._get_url_mobj(url)
cd7c66cf 5982
86973308
M
5983 if not self._yes_playlist(playlist_id, video_id):
5984 return self.url_result(
5985 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 5986
ac56cf38 5987 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5988
7c219ea6 5989 # YouTube may provide a non-standard redirect to the regional channel
5990 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 5991 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 5992 redirect_url = traverse_obj(
5993 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5994 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5995 redirect_url = ''.join((
5996 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
86973308
M
5997 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
5998 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 5999
86973308
M
6000 tab_results = []
6001 tabs = self._extract_tab_renderers(data)
6002 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6003 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6004 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6005 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6006
6007 if not original_tab_id and selected_tab_name:
6008 self.to_screen('Channel URLs download all uploads of the channel. '
6009 'To download only the videos in a specific tab, pass the tab\'s URL')
6010 if self._has_tab(tabs, 'streams'):
6011 tab_results.append(self.url_result(''.join((pre, '/streams', post))))
6012 if self._has_tab(tabs, 'shorts'):
6013 tab_results.append(self.url_result(''.join((pre, '/shorts', post))))
6014 # XXX: Members-only tab should also be extracted
6015
6016 if not tab_results and selected_tab_id != 'videos':
6017 # Channel does not have streams, shorts or videos tabs
6018 if item_id[:2] != 'UC':
6019 raise ExtractorError('This channel has no uploads', expected=True)
6020
6021 # Topic channels don't have /videos. Use the equivalent playlist instead
6022 pl_id = f'UU{item_id[2:]}'
6023 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6024 try:
6025 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6026 except ExtractorError:
6027 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6028 else:
86973308
M
6029 item_id, url = pl_id, pl_url
6030 self.to_screen(
6031 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6032
6033 elif tab_results and selected_tab_id != 'videos':
6034 # When there are shorts/live tabs but not videos tab
6035 url, data = ''.join((pre, post)), None
6036
6037 elif (original_tab_id or 'videos') != selected_tab_id:
6038 if original_tab_id == 'live':
6039 # Live tab should have redirected to the video
6040 # Except in the case the channel has an actual live tab
6041 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6042 raise UserNotLive(video_id=mobj['id'])
6043 elif selected_tab_name:
6044 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6045
6046 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6047 url = f'{pre}{post}'
18db7548 6048
37e57a9f 6049 self.write_debug(f'Final URL: {url}')
18db7548 6050
358de58c 6051 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6052 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 6053 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 6054 self._extract_and_report_alerts(data, only_once=True)
86973308
M
6055
6056 tabs = self._extract_tab_renderers(data)
8bdd16b4 6057 if tabs:
86973308
M
6058 tab_results[:0] = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6059 tab_results[0].update({
6060 'extractor_key': YoutubeTabIE.ie_key(),
6061 'extractor': YoutubeTabIE.IE_NAME,
6062 'webpage_url': url,
6063 })
6064
6065 if len(tab_results) == 1:
6066 return tab_results[0]
6067 elif len(tab_results) > 1:
6068 return self.playlist_result(tab_results, item_id, title=f'Uploads for {item_id}')
cd7c66cf 6069
37e57a9f 6070 playlist = traverse_obj(
6071 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6072 if playlist:
ac56cf38 6073 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6074
37e57a9f 6075 video_id = traverse_obj(
6076 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6077 if video_id:
09f1580e 6078 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 6079 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6080 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6081
8bdd16b4 6082 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6083
c5e8d7af 6084
8bdd16b4 6085class YoutubePlaylistIE(InfoExtractor):
96565c7e 6086 IE_DESC = 'YouTube playlists'
8bdd16b4 6087 _VALID_URL = r'''(?x)(?:
6088 (?:https?://)?
6089 (?:\w+\.)?
6090 (?:
6091 (?:
6092 youtube(?:kids)?\.com|
d9190e44 6093 %(invidious)s
8bdd16b4 6094 )
6095 /.*?\?.*?\blist=
6096 )?
6097 (?P<id>%(playlist_id)s)
d9190e44
RH
6098 )''' % {
6099 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6100 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6101 }
8bdd16b4 6102 IE_NAME = 'youtube:playlist'
cdc628a4 6103 _TESTS = [{
8bdd16b4 6104 'note': 'issue #673',
6105 'url': 'PLBB231211A4F62143',
cdc628a4 6106 'info_dict': {
8bdd16b4 6107 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6108 'id': 'PLBB231211A4F62143',
976ae3ea 6109 'uploader': 'Wickman',
8bdd16b4 6110 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 6111 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6112 'view_count': int,
86973308 6113 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
976ae3ea 6114 'modified_date': r're:\d{8}',
6115 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6116 'channel': 'Wickman',
6117 'tags': [],
86973308
M
6118 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6119 'availability': 'public',
8bdd16b4 6120 },
6121 'playlist_mincount': 29,
6122 }, {
6123 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6124 'info_dict': {
6125 'title': 'YDL_safe_search',
6126 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6127 },
6128 'playlist_count': 2,
6129 'skip': 'This playlist is private',
9558dcec 6130 }, {
8bdd16b4 6131 'note': 'embedded',
6132 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6133 'playlist_count': 4,
9558dcec 6134 'info_dict': {
8bdd16b4 6135 'title': 'JODA15',
6136 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6137 'uploader': 'milan',
6138 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 6139 'description': '',
6140 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6141 'tags': [],
6142 'modified_date': '20140919',
6143 'view_count': int,
6144 'channel': 'milan',
6145 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6146 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 6147 'availability': 'public',
976ae3ea 6148 },
86973308 6149 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6150 }, {
8bdd16b4 6151 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6152 'playlist_mincount': 455,
8bdd16b4 6153 'info_dict': {
6154 'title': '2018 Chinese New Singles (11/6 updated)',
6155 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6156 'uploader': 'LBK',
6157 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 6158 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6159 'channel': 'LBK',
6160 'view_count': int,
6161 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6162 'tags': [],
6163 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6164 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6165 'modified_date': r're:\d{8}',
c26f9b99 6166 'availability': 'public',
976ae3ea 6167 },
6168 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6169 }, {
29f7c58a 6170 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6171 'only_matching': True,
6172 }, {
6173 # music album playlist
6174 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6175 'only_matching': True,
6176 }]
6177
6178 @classmethod
6179 def suitable(cls, url):
201c1459 6180 if YoutubeTabIE.suitable(url):
6181 return False
49a57e70 6182 from ..utils import parse_qs
201c1459 6183 qs = parse_qs(url)
6184 if qs.get('v', [None])[0]:
6185 return False
86e5f3ed 6186 return super().suitable(url)
29f7c58a 6187
6188 def _real_extract(self, url):
6189 playlist_id = self._match_id(url)
46953e7e 6190 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6191 url = update_url_query(
6192 'https://www.youtube.com/playlist',
6193 parse_qs(url) or {'list': playlist_id})
6194 if is_music_url:
6195 url = smuggle_url(url, {'is_music_url': True})
6196 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6197
6198
6199class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6200 IE_DESC = 'youtu.be'
29f7c58a 6201 _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}
6202 _TESTS = [{
8bdd16b4 6203 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6204 'info_dict': {
6205 'id': 'yeWKywCrFtk',
6206 'ext': 'mp4',
6207 'title': 'Small Scale Baler and Braiding Rugs',
6208 'uploader': 'Backus-Page House Museum',
6209 'uploader_id': 'backuspagemuseum',
6210 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6211 'upload_date': '20161008',
6212 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6213 'categories': ['Nonprofits & Activism'],
6214 'tags': list,
6215 'like_count': int,
976ae3ea 6216 'age_limit': 0,
6217 'playable_in_embed': True,
6218 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6219 'channel': 'Backus-Page House Museum',
6220 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6221 'live_status': 'not_live',
6222 'view_count': int,
6223 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6224 'availability': 'public',
6225 'duration': 59,
12a1b225
A
6226 'comment_count': int,
6227 'channel_follower_count': int
8bdd16b4 6228 },
6229 'params': {
6230 'noplaylist': True,
6231 'skip_download': True,
6232 },
39e7107d 6233 }, {
8bdd16b4 6234 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6235 'only_matching': True,
cdc628a4
PH
6236 }]
6237
8bdd16b4 6238 def _real_extract(self, url):
5ad28e7f 6239 mobj = self._match_valid_url(url)
29f7c58a 6240 video_id = mobj.group('id')
6241 playlist_id = mobj.group('playlist_id')
8bdd16b4 6242 return self.url_result(
29f7c58a 6243 update_url_query('https://www.youtube.com/watch', {
6244 'v': video_id,
6245 'list': playlist_id,
6246 'feature': 'youtu.be',
6247 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6248
6249
b6ce9bb0 6250class YoutubeLivestreamEmbedIE(InfoExtractor):
6251 IE_DESC = 'YouTube livestream embeds'
6252 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6253 _TESTS = [{
6254 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6255 'only_matching': True,
6256 }]
6257
6258 def _real_extract(self, url):
6259 channel_id = self._match_id(url)
6260 return self.url_result(
6261 f'https://www.youtube.com/channel/{channel_id}/live',
6262 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6263
6264
8bdd16b4 6265class YoutubeYtUserIE(InfoExtractor):
96565c7e 6266 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6267 IE_NAME = 'youtube:user'
8bdd16b4 6268 _VALID_URL = r'ytuser:(?P<id>.+)'
6269 _TESTS = [{
6270 'url': 'ytuser:phihag',
6271 'only_matching': True,
6272 }]
6273
6274 def _real_extract(self, url):
6275 user_id = self._match_id(url)
6276 return self.url_result(
c586f9e8 6277 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 6278 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 6279
b05654f0 6280
3d3dddc9 6281class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6282 IE_NAME = 'youtube:favorites'
96565c7e 6283 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6284 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6285 _LOGIN_REQUIRED = True
6286 _TESTS = [{
6287 'url': ':ytfav',
6288 'only_matching': True,
6289 }, {
6290 'url': ':ytfavorites',
6291 'only_matching': True,
6292 }]
6293
6294 def _real_extract(self, url):
6295 return self.url_result(
6296 'https://www.youtube.com/playlist?list=LL',
6297 ie=YoutubeTabIE.ie_key())
6298
6299
ca5300c7 6300class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6301 IE_NAME = 'youtube:notif'
6302 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6303 _VALID_URL = r':ytnotif(?:ication)?s?'
6304 _LOGIN_REQUIRED = True
6305 _TESTS = [{
6306 'url': ':ytnotif',
6307 'only_matching': True,
6308 }, {
6309 'url': ':ytnotifications',
6310 'only_matching': True,
6311 }]
6312
6313 def _extract_notification_menu(self, response, continuation_list):
6314 notification_list = traverse_obj(
6315 response,
6316 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6317 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6318 expected_type=list) or []
6319 continuation_list[0] = None
6320 for item in notification_list:
6321 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6322 if entry:
6323 yield entry
6324 continuation = item.get('continuationItemRenderer')
6325 if continuation:
6326 continuation_list[0] = continuation
6327
6328 def _extract_notification_renderer(self, notification):
6329 video_id = traverse_obj(
6330 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6331 url = f'https://www.youtube.com/watch?v={video_id}'
6332 channel_id = None
6333 if not video_id:
6334 browse_ep = traverse_obj(
6335 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6336 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6337 post_id = self._search_regex(
6338 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6339 'post id', default=None)
6340 if not channel_id or not post_id:
6341 return
6342 # The direct /post url redirects to this in the browser
6343 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6344
6345 channel = traverse_obj(
6346 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6347 expected_type=str)
c7a7baaa 6348 notification_title = self._get_text(notification, 'shortMessage')
6349 if notification_title:
6350 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6351 # TODO: handle recommended videos
ca5300c7 6352 title = self._search_regex(
c7a7baaa 6353 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6354 'video title', default=None)
5225df50 6355 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6356 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6357 else None)
ca5300c7 6358 return {
6359 '_type': 'url',
6360 'url': url,
6361 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6362 'video_id': video_id,
6363 'title': title,
6364 'channel_id': channel_id,
6365 'channel': channel,
6366 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6367 'timestamp': timestamp,
ca5300c7 6368 }
6369
6370 def _notification_menu_entries(self, ytcfg):
6371 continuation_list = [None]
6372 response = None
6373 for page in itertools.count(1):
6374 ctoken = traverse_obj(
6375 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6376 response = self._extract_response(
6377 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6378 ep='notification/get_notification_menu', check_get_keys='actions',
6379 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6380 yield from self._extract_notification_menu(response, continuation_list)
6381 if not continuation_list[0]:
6382 break
6383
6384 def _real_extract(self, url):
6385 display_id = 'notifications'
6386 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6387 self._report_playlist_authcheck(ytcfg)
6388 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6389
6390
a6213a49 6391class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6392 IE_DESC = 'YouTube search'
78caa52a 6393 IE_NAME = 'youtube:search'
b05654f0 6394 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6395 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6396 _TESTS = [{
6397 'url': 'ytsearch5:youtube-dl test video',
6398 'playlist_count': 5,
6399 'info_dict': {
6400 'id': 'youtube-dl test video',
6401 'title': 'youtube-dl test video',
6402 }
6403 }]
b05654f0 6404
a61fd4cf 6405
5f7cb91a 6406class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6407 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6408 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6409 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6410 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6411 _TESTS = [{
6412 'url': 'ytsearchdate5:youtube-dl test video',
6413 'playlist_count': 5,
6414 'info_dict': {
6415 'id': 'youtube-dl test video',
6416 'title': 'youtube-dl test video',
6417 }
6418 }]
75dff0ee 6419
c9ae7b95 6420
a6213a49 6421class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6422 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6423 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6424 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6425 _TESTS = [{
6426 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6427 'playlist_mincount': 5,
6428 'info_dict': {
11f9be09 6429 'id': 'youtube-dl test video',
3462ffa8 6430 'title': 'youtube-dl test video',
6431 }
a61fd4cf 6432 }, {
6433 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6434 'playlist_mincount': 5,
6435 'info_dict': {
6436 'id': 'python',
6437 'title': 'python',
6438 }
ad210f4f 6439 }, {
6440 'url': 'https://www.youtube.com/results?search_query=%23cats',
6441 'playlist_mincount': 1,
6442 'info_dict': {
6443 'id': '#cats',
6444 'title': '#cats',
12a1b225
A
6445 # The test suite does not have support for nested playlists
6446 # 'entries': [{
6447 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6448 # 'title': '#cats',
6449 # }],
ad210f4f 6450 },
3462ffa8 6451 }, {
6452 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6453 'only_matching': True,
6454 }]
6455
6456 def _real_extract(self, url):
4dfbf869 6457 qs = parse_qs(url)
386e1dd9 6458 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6459 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6460
6461
16aa9ea4 6462class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6463 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6464 IE_NAME = 'youtube:music:search_url'
6465 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6466 _TESTS = [{
6467 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6468 'playlist_count': 16,
6469 'info_dict': {
6470 'id': 'royalty free music',
6471 'title': 'royalty free music',
6472 }
6473 }, {
6474 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6475 'playlist_mincount': 30,
6476 'info_dict': {
6477 'id': 'royalty free music - songs',
6478 'title': 'royalty free music - songs',
6479 },
6480 'params': {'extract_flat': 'in_playlist'}
6481 }, {
6482 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6483 'playlist_mincount': 30,
6484 'info_dict': {
6485 'id': 'royalty free music - community playlists',
6486 'title': 'royalty free music - community playlists',
6487 },
6488 'params': {'extract_flat': 'in_playlist'}
6489 }]
6490
6491 _SECTIONS = {
6492 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6493 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6494 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6495 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6496 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6497 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6498 }
6499
6500 def _real_extract(self, url):
6501 qs = parse_qs(url)
6502 query = (qs.get('search_query') or qs.get('q'))[0]
6503 params = qs.get('sp', (None,))[0]
6504 if params:
6505 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6506 else:
ac668111 6507 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6508 params = self._SECTIONS.get(section)
6509 if not params:
6510 section = None
6511 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6512 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6513
6514
182bda88 6515class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6516 """
25f14e9f 6517 Base class for feed extractors
82d02080 6518 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6519 """
b2e8bc1b 6520 _LOGIN_REQUIRED = True
82d02080 6521 _FEED_NAME = 'feeds'
a25bca9f 6522
6523 def _real_initialize(self):
6524 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6525
82d02080 6526 @classproperty
d7ae0639 6527 def IE_NAME(self):
82d02080 6528 return f'youtube:{self._FEED_NAME}'
04cc9617 6529
3853309f 6530 def _real_extract(self, url):
3d3dddc9 6531 return self.url_result(
182bda88 6532 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6533
6534
ef2f3c7f 6535class YoutubeWatchLaterIE(InfoExtractor):
6536 IE_NAME = 'youtube:watchlater'
96565c7e 6537 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6538 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6539 _TESTS = [{
8bdd16b4 6540 'url': ':ytwatchlater',
bc7a9cd8
S
6541 'only_matching': True,
6542 }]
25f14e9f
S
6543
6544 def _real_extract(self, url):
ef2f3c7f 6545 return self.url_result(
6546 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6547
6548
25f14e9f 6549class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6550 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6551 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6552 _FEED_NAME = 'recommended'
45db527f 6553 _LOGIN_REQUIRED = False
3d3dddc9 6554 _TESTS = [{
6555 'url': ':ytrec',
6556 'only_matching': True,
6557 }, {
6558 'url': ':ytrecommended',
6559 'only_matching': True,
6560 }, {
6561 'url': 'https://youtube.com',
6562 'only_matching': True,
6563 }]
1ed5b5c9 6564
1ed5b5c9 6565
25f14e9f 6566class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6567 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6568 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6569 _FEED_NAME = 'subscriptions'
3d3dddc9 6570 _TESTS = [{
6571 'url': ':ytsubs',
6572 'only_matching': True,
6573 }, {
6574 'url': ':ytsubscriptions',
6575 'only_matching': True,
6576 }]
1ed5b5c9 6577
1ed5b5c9 6578
25f14e9f 6579class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6580 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6581 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6582 _FEED_NAME = 'history'
3d3dddc9 6583 _TESTS = [{
6584 'url': ':ythistory',
6585 'only_matching': True,
6586 }]
1ed5b5c9
JMF
6587
6588
6e634cbe 6589class YoutubeStoriesIE(InfoExtractor):
6590 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6591 IE_NAME = 'youtube:stories'
6592 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6593 _TESTS = [{
6594 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6595 'only_matching': True,
6596 }]
6597
6598 def _real_extract(self, url):
6599 playlist_id = f'RLTD{self._match_id(url)}'
6600 return self.url_result(
50ac0e54 6601 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6602 ie=YoutubeTabIE, video_id=playlist_id)
6603
6604
80eb0bd9 6605class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6606 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6607 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6608 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6609 _TESTS = [{
1dd18a88 6610 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6611 'only_matching': True,
6612 }]
6613
6614 @staticmethod
6615 def _generate_audio_pivot_params(video_id):
6616 """
6617 Generates sfv_audio_pivot browse params for this video id
6618 """
6619 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6620 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6621
6622 def _real_extract(self, url):
6623 video_id = self._match_id(url)
6624 return self.url_result(
6625 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6626 ie=YoutubeTabIE)
6627
6628
15870e90
PH
6629class YoutubeTruncatedURLIE(InfoExtractor):
6630 IE_NAME = 'youtube:truncated_url'
6631 IE_DESC = False # Do not list
975d35db 6632 _VALID_URL = r'''(?x)
b95aab84
PH
6633 (?:https?://)?
6634 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6635 (?:watch\?(?:
c4808c60 6636 feature=[a-z_]+|
b95aab84
PH
6637 annotation_id=annotation_[^&]+|
6638 x-yt-cl=[0-9]+|
c1708b89 6639 hl=[^&]*|
287be8c6 6640 t=[0-9]+
b95aab84
PH
6641 )?
6642 |
6643 attribution_link\?a=[^&]+
6644 )
6645 $
975d35db 6646 '''
15870e90 6647
c4808c60 6648 _TESTS = [{
2d3d2997 6649 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6650 'only_matching': True,
dc2fc736 6651 }, {
2d3d2997 6652 'url': 'https://www.youtube.com/watch?',
dc2fc736 6653 'only_matching': True,
b95aab84
PH
6654 }, {
6655 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6656 'only_matching': True,
6657 }, {
6658 'url': 'https://www.youtube.com/watch?feature=foo',
6659 'only_matching': True,
c1708b89
PH
6660 }, {
6661 'url': 'https://www.youtube.com/watch?hl=en-GB',
6662 'only_matching': True,
287be8c6
PH
6663 }, {
6664 'url': 'https://www.youtube.com/watch?t=2372',
6665 'only_matching': True,
c4808c60
PH
6666 }]
6667
15870e90
PH
6668 def _real_extract(self, url):
6669 raise ExtractorError(
78caa52a
PH
6670 'Did you forget to quote the URL? Remember that & is a meta '
6671 'character in most shells, so you want to put the URL in quotes, '
3867038a 6672 'like youtube-dl '
2d3d2997 6673 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6674 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6675 expected=True)
772fd5cc
PH
6676
6677
471d0367 6678class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6679 IE_NAME = 'youtube:clip'
471d0367 6680 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6681 _TESTS = [{
6682 # FIXME: Other metadata should be extracted from the clip, not from the base video
6683 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6684 'info_dict': {
6685 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6686 'ext': 'mp4',
6687 'section_start': 29.0,
6688 'section_end': 39.7,
6689 'duration': 10.7,
12a1b225
A
6690 'age_limit': 0,
6691 'availability': 'public',
6692 'categories': ['Gaming'],
6693 'channel': 'Scott The Woz',
6694 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6695 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6696 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6697 'like_count': int,
6698 'playable_in_embed': True,
6699 'tags': 'count:17',
6700 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6701 'title': 'Mobile Games on Console - Scott The Woz',
6702 'upload_date': '20210920',
6703 'uploader': 'Scott The Woz',
6704 'uploader_id': 'scottthewoz',
6705 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6706 'view_count': int,
6707 'live_status': 'not_live',
6708 'channel_follower_count': int
471d0367 6709 }
6710 }]
3cd786db 6711
6712 def _real_extract(self, url):
471d0367 6713 clip_id = self._match_id(url)
6714 _, data = self._extract_webpage(url, clip_id)
6715
6716 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6717 if not video_id:
6718 raise ExtractorError('Unable to find video ID')
6719
6720 clip_data = traverse_obj(data, (
6721 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6722 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6723 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6724 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6725
6726 return {
6727 '_type': 'url_transparent',
6728 'url': f'https://www.youtube.com/watch?v={video_id}',
6729 'ie_key': YoutubeIE.ie_key(),
6730 'id': clip_id,
6731 'section_start': int(clip_data['startTimeMs']) / 1000,
6732 'section_end': int(clip_data['endTimeMs']) / 1000,
6733 }
3cd786db 6734
6735
772fd5cc
PH
6736class YoutubeTruncatedIDIE(InfoExtractor):
6737 IE_NAME = 'youtube:truncated_id'
6738 IE_DESC = False # Do not list
b95aab84 6739 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6740
6741 _TESTS = [{
6742 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6743 'only_matching': True,
6744 }]
6745
6746 def _real_extract(self, url):
6747 video_id = self._match_id(url)
6748 raise ExtractorError(
86e5f3ed 6749 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6750 expected=True)