]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/youtube] Differentiate between no and disabled comments (#5491)
[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)
0cf643b2 3273 raise self.CommentsDisabled
6e634cbe 3274
3275 @staticmethod
3276 def _generate_comment_continuation(video_id):
3277 """
3278 Generates initial comment section continuation token from given video id
3279 """
3280 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3281 return base64.b64encode(token.encode()).decode()
3282
a2160aa4 3283 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3284 """Entry for comment extraction"""
2d6659b9 3285 def _real_comment_extract(contents):
aae16f6e 3286 renderer = next((
3287 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3288 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3289 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3290
a2160aa4 3291 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3292 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3293
109dd3b2 3294 @staticmethod
99e9e001 3295 def _get_checkok_params():
3296 return {'contentCheckOk': True, 'racyCheckOk': True}
3297
3298 @classmethod
3299 def _generate_player_context(cls, sts=None):
109dd3b2 3300 context = {
3301 'html5Preference': 'HTML5_PREF_WANTS',
3302 }
3303 if sts is not None:
3304 context['signatureTimestamp'] = sts
3305 return {
3306 'playbackContext': {
3307 'contentPlaybackContext': context
a1a7907b 3308 },
99e9e001 3309 **cls._get_checkok_params()
109dd3b2 3310 }
3311
e7e94f2a
D
3312 @staticmethod
3313 def _is_agegated(player_response):
3314 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3315 return True
e7e94f2a
D
3316
3317 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3318 AGE_GATE_REASONS = (
3319 'confirm your age', 'age-restricted', 'inappropriate', # reason
3320 'age_verification_required', 'age_check_required', # status
3321 )
3322 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3323
3324 @staticmethod
3325 def _is_unplayable(player_response):
3326 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3327
50ac0e54 3328 _STORY_PLAYER_PARAMS = '8AEB'
3329
3330 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3331
11f9be09 3332 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3333 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3334 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3335 headers = self.generate_api_headers(
99e9e001 3336 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3337
6e634cbe 3338 yt_query = {
3339 'videoId': video_id,
6e634cbe 3340 }
50ac0e54 3341 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3342 yt_query['params'] = self._STORY_PLAYER_PARAMS
3343
11f9be09 3344 yt_query.update(self._generate_player_context(sts))
3345 return self._extract_response(
3346 item_id=video_id, ep='player', query=yt_query,
379e44ed 3347 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3348 default_client=client,
11f9be09 3349 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3350 ) or None
3351
11f9be09 3352 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3353 requested_clients = []
d0d012d4 3354 default = ['android', 'web']
000c15a4 3355 allowed_clients = sorted(
86e5f3ed 3356 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3357 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3358 for client in self._configuration_arg('player_client'):
3359 if client in allowed_clients:
3360 requested_clients.append(client)
d0d012d4 3361 elif client == 'default':
3362 requested_clients.extend(default)
b4c055ba 3363 elif client == 'all':
3364 requested_clients.extend(allowed_clients)
3365 else:
3366 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3367 if not requested_clients:
d0d012d4 3368 requested_clients = default
cf7e015f 3369
11f9be09 3370 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3371 requested_clients.extend(
e7e94f2a 3372 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3373
11f9be09 3374 return orderedSet(requested_clients)
cf7e015f 3375
50ac0e54 3376 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3377 initial_pr = None
3378 if webpage:
b7c47b74 3379 initial_pr = self._search_json(
3380 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3381
ae729626 3382 all_clients = set(clients)
c0bc527b 3383 clients = clients[::-1]
b6de707d 3384 prs = []
e7e94f2a 3385
ae729626 3386 def append_client(*client_names):
e7870111 3387 """ Append the first client name that exists but not already used """
ae729626 3388 for client_name in client_names:
e7870111
D
3389 actual_client = _split_innertube_client(client_name)[0]
3390 if actual_client in INNERTUBE_CLIENTS:
3391 if actual_client not in all_clients:
ae729626 3392 clients.append(client_name)
e7870111
D
3393 all_clients.add(actual_client)
3394 return
e7e94f2a 3395
379e44ed 3396 # Android player_response does not have microFormats which are needed for
3397 # extraction of some data. So we return the initial_pr with formats
3398 # stripped out even if not requested by the user
3399 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3400 if initial_pr:
3401 pr = dict(initial_pr)
3402 pr['streamingData'] = None
b6de707d 3403 prs.append(pr)
379e44ed 3404
3405 last_error = None
b6de707d 3406 tried_iframe_fallback = False
3407 player_url = None
c0bc527b 3408 while clients:
e7870111 3409 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3410 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3411 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3412 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3413
b6de707d 3414 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3415 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3416 if 'js' in self._configuration_arg('player_skip'):
3417 require_js_player = False
3418 player_url = None
3419
3420 if not player_url and not tried_iframe_fallback and require_js_player:
3421 player_url = self._download_player_url(video_id)
3422 tried_iframe_fallback = True
3423
379e44ed 3424 try:
3425 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3426 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3427 except ExtractorError as e:
3428 if last_error:
3429 self.report_warning(last_error)
3430 last_error = e
3431 continue
3432
11f9be09 3433 if pr:
a3e96421 3434 # YouTube may return a different video player response than expected.
3435 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3436 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3437 if pr_video_id and pr_video_id != video_id:
3438 self.report_warning(
c7dcf0b3 3439 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3440 else:
3441 prs.append(pr)
c0bc527b 3442
e7e94f2a 3443 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3444 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3445 append_client(f'{base_client}_creator')
e7e94f2a 3446 elif self._is_agegated(pr):
e7870111
D
3447 if variant == 'tv_embedded':
3448 append_client(f'{base_client}_embedded')
3449 elif not variant:
3450 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3451
379e44ed 3452 if last_error:
b6de707d 3453 if not len(prs):
379e44ed 3454 raise last_error
3455 self.report_warning(last_error)
b6de707d 3456 return prs, player_url
11f9be09 3457
4d37720a
L
3458 def _needs_live_processing(self, live_status, duration):
3459 if (live_status == 'is_live' and self.get_param('live_from_start')
3460 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3461 return live_status
3462
3463 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a0bb6ce5 3464 itags, stream_ids = {}, []
b25cac65 3465 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3466 q = qualities([
2a9c6dcd 3467 # Normally tiny is the smallest video-only formats. But
3468 # audio-only formats with unknown quality may get tagged as tiny
3469 'tiny',
3470 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3471 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3472 ])
11f9be09 3473 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3474
545cc85d 3475 for fmt in streaming_formats:
727029c5 3476 if fmt.get('targetDurationSec'):
545cc85d 3477 continue
321bf820 3478
cc2db878 3479 itag = str_or_none(fmt.get('itag'))
9297939e 3480 audio_track = fmt.get('audioTrack') or {}
3481 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3482 if stream_id in stream_ids:
3483 continue
3484
cc2db878 3485 quality = fmt.get('quality')
2a9c6dcd 3486 height = int_or_none(fmt.get('height'))
d3fc8074 3487 if quality == 'tiny' or not quality:
3488 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3489 # The 3gp format (17) in android client has a quality of "small",
3490 # but is actually worse than other formats
3491 if itag == '17':
3492 quality = 'tiny'
3493 if quality:
3494 if itag:
3495 itag_qualities[itag] = quality
3496 if height:
3497 res_qualities[height] = quality
cc2db878 3498 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3499 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3500 # number of fragment that would subsequently requested with (`&sq=N`)
3501 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3502 continue
3503
545cc85d 3504 fmt_url = fmt.get('url')
3505 if not fmt_url:
14f25df2 3506 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3507 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3508 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3509 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3510 continue
52023f12 3511 try:
3512 fmt_url += '&%s=%s' % (
3513 traverse_obj(sc, ('sp', -1)) or 'signature',
3514 self._decrypt_signature(encrypted_sig, video_id, player_url)
3515 )
3516 except ExtractorError as e:
580ce007 3517 self.report_warning('Signature extraction failed: Some formats may be missing',
3518 video_id=video_id, only_once=True)
52023f12 3519 self.write_debug(e, only_once=True)
201e9eaa 3520 continue
545cc85d 3521
404f611f 3522 query = parse_qs(fmt_url)
3523 throttled = False
b2916526 3524 if query.get('n'):
404f611f 3525 try:
580ce007 3526 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3527 fmt_url = update_url_query(fmt_url, {
580ce007 3528 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3529 })
404f611f 3530 except ExtractorError as e:
25836db6 3531 phantomjs_hint = ''
3532 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3533 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3534 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3535 if player_url:
3536 self.report_warning(
3537 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3538 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3539 self.write_debug(e, only_once=True)
3540 else:
3541 self.report_warning(
3542 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3543 video_id=video_id, only_once=True)
404f611f 3544 throttled = True
3545
545cc85d 3546 if itag:
a0bb6ce5 3547 itags[itag] = 'https'
9297939e 3548 stream_ids.append(stream_id)
3549
0ad92dfb 3550 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3551 language_preference = (
3552 10 if audio_track.get('audioIsDefault') and 10
3553 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3554 else -1)
0ad92dfb 3555 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3556 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3557 # Make sure to avoid false positives with small duration differences.
62b58c09 3558 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3559 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3560 if is_damaged:
0f06bcd7 3561 self.report_warning(
3562 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3563 dct = {
3564 'asr': int_or_none(fmt.get('audioSampleRate')),
3565 'filesize': int_or_none(fmt.get('contentLength')),
3566 'format_id': itag,
34921b43 3567 'format_note': join_nonempty(
26e8e044 3568 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3569 ' (default)' if language_preference > 0 else ''),
404f611f 3570 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3571 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3572 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3573 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3574 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3575 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3576 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3577 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3578 'height': height,
dca3ff4a 3579 'quality': q(quality),
727029c5 3580 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3581 'tbr': tbr,
545cc85d 3582 'url': fmt_url,
2a9c6dcd 3583 'width': int_or_none(fmt.get('width')),
ab6df717 3584 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3585 'desc' if language_preference < -1 else ''),
3586 'language_preference': language_preference,
a405b38f 3587 # Strictly de-prioritize damaged and 3gp formats
3588 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3589 }
60bdb7bd 3590 mime_mobj = re.match(
3591 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3592 if mime_mobj:
3593 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3594 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3595 no_audio = dct.get('acodec') == 'none'
3596 no_video = dct.get('vcodec') == 'none'
3597 if no_audio:
3598 dct['vbr'] = tbr
3599 if no_video:
3600 dct['abr'] = tbr
3601 if no_audio or no_video:
545cc85d 3602 dct['downloader_options'] = {
3603 # Youtube throttles chunks >~10M
3604 'http_chunk_size': 10485760,
bf1317d2 3605 }
7c60c33e 3606 if dct.get('ext'):
3607 dct['container'] = dct['ext'] + '_dash'
11f9be09 3608 yield dct
545cc85d 3609
4d37720a
L
3610 needs_live_processing = self._needs_live_processing(live_status, duration)
3611 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3612
3613 skip_manifests = set(self._configuration_arg('skip'))
3614 if (not self.get_param('youtube_include_hls_manifest', True)
3615 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3616 or needs_live_processing and skip_bad_formats):
3617 skip_manifests.add('hls')
3618
0f06bcd7 3619 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3620 skip_manifests.add('dash')
3621 if self._configuration_arg('include_live_dash'):
3622 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3623 'Use include_incomplete_formats extractor argument instead')
3624 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3625 skip_manifests.add('dash')
5d3a0e79 3626
a0bb6ce5 3627 def process_manifest_format(f, proto, itag):
3628 if itag in itags:
3629 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3630 return False
3631 itag = f'{itag}-{proto}'
3632 if itag:
3633 f['format_id'] = itag
3634 itags[itag] = proto
3635
b25cac65 3636 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3637 if f['quality'] == -1 and f.get('height'):
3638 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3639 return True
2a9c6dcd 3640
c646d76f 3641 subtitles = {}
11f9be09 3642 for sd in streaming_data:
4d37720a 3643 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3644 if hls_manifest_url:
4d37720a
L
3645 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3646 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3647 subtitles = self._merge_subtitles(subs, subtitles)
3648 for f in fmts:
a0bb6ce5 3649 if process_manifest_format(f, 'hls', self._search_regex(
3650 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3651 yield f
545cc85d 3652
4d37720a 3653 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3654 if dash_manifest_url:
c646d76f 3655 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3656 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3657 for f in formats:
a0bb6ce5 3658 if process_manifest_format(f, 'dash', f['format_id']):
3659 f['filesize'] = int_or_none(self._search_regex(
3660 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3661 if needs_live_processing:
adbc4ec4
THD
3662 f['is_from_start'] = True
3663
a0bb6ce5 3664 yield f
c646d76f 3665 yield subtitles
11f9be09 3666
720c3099 3667 def _extract_storyboard(self, player_responses, duration):
3668 spec = get_first(
3669 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3670 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3671 if not base_url:
720c3099 3672 return
720c3099 3673 L = len(spec) - 1
3674 for i, args in enumerate(spec):
3675 args = args.split('#')
3676 counts = list(map(int_or_none, args[:5]))
3677 if len(args) != 8 or not all(counts):
3678 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3679 continue
3680 width, height, frame_count, cols, rows = counts
3681 N, sigh = args[6:]
3682
3683 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3684 fragment_count = frame_count / (cols * rows)
3685 fragment_duration = duration / fragment_count
3686 yield {
3687 'format_id': f'sb{i}',
3688 'format_note': 'storyboard',
3689 'ext': 'mhtml',
3690 'protocol': 'mhtml',
3691 'acodec': 'none',
3692 'vcodec': 'none',
3693 'url': url,
3694 'width': width,
3695 'height': height,
45e8a04e 3696 'fps': frame_count / duration,
3697 'rows': rows,
3698 'columns': cols,
720c3099 3699 'fragments': [{
b3edc806 3700 'url': url.replace('$M', str(j)),
720c3099 3701 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3702 } for j in range(math.ceil(fragment_count))],
3703 }
3704
adbc4ec4 3705 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3706 webpage = None
3707 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3708 query = {'bpctr': '9999999999', 'has_verified': '1'}
3709 if smuggled_data.get('is_story'):
3710 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3711 webpage = self._download_webpage(
50ac0e54 3712 webpage_url, video_id, fatal=False, query=query)
11f9be09 3713
3714 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3715
b6de707d 3716 player_responses, player_url = self._extract_player_responses(
11f9be09 3717 self._get_requested_clients(url, smuggled_data),
50ac0e54 3718 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3719
adbc4ec4
THD
3720 return webpage, master_ytcfg, player_responses, player_url
3721
a1b2d843 3722 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3723 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3724 is_live = get_first(video_details, 'isLive')
3725 if is_live is None:
3726 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3727 live_content = get_first(video_details, 'isLiveContent')
3728 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3729 post_live = get_first(video_details, 'isPostLiveDvr')
3730 live_status = ('post_live' if post_live
3731 else 'is_live' if is_live
3732 else 'is_upcoming' if is_upcoming
6678a4f0 3733 else 'was_live' if live_content
3734 else 'not_live' if False in (is_live, live_content)
3735 else None)
adbc4ec4 3736 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
4d37720a 3737 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3738
4d37720a 3739 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3740
3741 def _real_extract(self, url):
3742 url, smuggled_data = unsmuggle_url(url, {})
3743 video_id = self._match_id(url)
3744
3745 base_url = self.http_scheme() + '//www.youtube.com/'
3746 webpage_url = base_url + 'watch?v=' + video_id
3747
3748 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3749
11f9be09 3750 playability_statuses = traverse_obj(
3751 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3752
3753 trailer_video_id = get_first(
3754 playability_statuses,
3755 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3756 expected_type=str)
3757 if trailer_video_id:
3758 return self.url_result(
3759 trailer_video_id, self.ie_key(), trailer_video_id)
3760
3761 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3762 if webpage else (lambda x: None))
3763
3764 video_details = traverse_obj(
3765 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3766 microformats = traverse_obj(
3767 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3768 expected_type=dict, default=[])
c26f9b99 3769
3770 translated_title = self._get_text(microformats, (..., 'title'))
3771 video_title = (self._preferred_lang and translated_title
3772 or get_first(video_details, 'title') # primary
3773 or translated_title
3774 or search_meta(['og:title', 'twitter:title', 'title']))
3775 translated_description = self._get_text(microformats, (..., 'description'))
3776 original_description = get_first(video_details, 'shortDescription')
3777 video_description = (
3778 self._preferred_lang and translated_description
3779 # If original description is blank, it will be an empty string.
3780 # Do not prefer translated description in this case.
3781 or original_description if original_description is not None else translated_description)
11f9be09 3782
d89257f3 3783 multifeed_metadata_list = get_first(
3784 player_responses,
3785 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3786 expected_type=str)
3787 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3788 if self.get_param('noplaylist'):
11f9be09 3789 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3790 else:
3791 entries = []
3792 feed_ids = []
3793 for feed in multifeed_metadata_list.split(','):
3794 # Unquote should take place before split on comma (,) since textual
3795 # fields may contain comma as well (see
3796 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3797 feed_data = urllib.parse.parse_qs(
ac668111 3798 urllib.parse.unquote_plus(feed))
d89257f3 3799
3800 def feed_entry(name):
3801 return try_get(
14f25df2 3802 feed_data, lambda x: x[name][0], str)
d89257f3 3803
3804 feed_id = feed_entry('id')
3805 if not feed_id:
3806 continue
3807 feed_title = feed_entry('title')
3808 title = video_title
3809 if feed_title:
3810 title += ' (%s)' % feed_title
3811 entries.append({
3812 '_type': 'url_transparent',
3813 'ie_key': 'Youtube',
3814 'url': smuggle_url(
3815 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3816 {'force_singlefeed': True}),
3817 'title': title,
3818 })
3819 feed_ids.append(feed_id)
3820 self.to_screen(
3821 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3822 % (', '.join(feed_ids), video_id))
3823 return self.playlist_result(
3824 entries, video_id, video_title, video_description)
11f9be09 3825
9da6612b 3826 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
3827 or int_or_none(get_first(microformats, 'lengthSeconds'))
3828 or parse_duration(search_meta('duration')) or None)
a1b2d843 3829
4d37720a
L
3830 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
3831 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
3832 if live_status == 'post_live':
3833 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 3834
545cc85d 3835 if not formats:
11f9be09 3836 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3837 self.report_drm(video_id)
11f9be09 3838 pemr = get_first(
3839 playability_statuses,
3840 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3841 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3842 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3843 if subreason:
545cc85d 3844 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3845 countries = get_first(microformats, 'availableCountries')
545cc85d 3846 if not countries:
3847 regions_allowed = search_meta('regionsAllowed')
3848 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3849 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3850 reason += f'. {subreason}'
545cc85d 3851 if reason:
b7da73eb 3852 self.raise_no_formats(reason, expected=True)
bf1317d2 3853
11f9be09 3854 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3855 if not keywords and webpage:
3856 keywords = [
3857 unescapeHTML(m.group('content'))
3858 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3859 for keyword in keywords:
3860 if keyword.startswith('yt:stretch='):
201c1459 3861 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3862 if mobj:
3863 # NB: float is intentional for forcing float division
3864 w, h = (float(v) for v in mobj.groups())
3865 if w > 0 and h > 0:
3866 ratio = w / h
3867 for f in formats:
3868 if f.get('vcodec') != 'none':
3869 f['stretched_ratio'] = ratio
3870 break
a709d873 3871 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3872 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3873 if thumbnail_url:
3874 thumbnails.append({
3875 'url': thumbnail_url,
ff2751ac 3876 })
fccf5021 3877 original_thumbnails = thumbnails.copy()
3878
0ba692ac 3879 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3880 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3881 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3882 thumbnail_names = [
962ffcf8 3883 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3884 # in resolution, these are not the custom thumbnail. So de-prioritize them
3885 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3886 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3887 ]
cca80fe6 3888 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3889 thumbnails.extend({
3890 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3891 video_id=video_id, name=name, ext=ext,
4d37720a 3892 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 3893 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3894 for thumb in thumbnails:
cca80fe6 3895 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3896 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3897 self._remove_duplicate_formats(thumbnails)
fccf5021 3898 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3899
7ea65411 3900 category = get_first(microformats, 'category') or search_meta('genre')
3901 channel_id = str_or_none(
3902 get_first(video_details, 'channelId')
3903 or get_first(microformats, 'externalChannelId')
3904 or search_meta('channelId'))
7ea65411 3905 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3906
adbc4ec4
THD
3907 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3908 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3909 if not duration and live_end_time and live_start_time:
3910 duration = live_end_time - live_start_time
3911
4d37720a
L
3912 needs_live_processing = self._needs_live_processing(live_status, duration)
3913
3914 def is_bad_format(fmt):
3915 if needs_live_processing and not fmt.get('is_from_start'):
3916 return True
3917 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
3918 and fmt.get('protocol') == 'http_dash_segments'):
3919 return True
3920
3921 for fmt in filter(is_bad_format, formats):
3922 fmt['preference'] = (fmt.get('preference') or -1) - 10
3923 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
3924
3925 if needs_live_processing:
3926 self._prepare_live_from_start_formats(
3927 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 3928
720c3099 3929 formats.extend(self._extract_storyboard(player_responses, duration))
3930
31b532a1 3931 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3932 self._sort_formats(formats, (
3933 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3934
545cc85d 3935 info = {
3936 'id': video_id,
39ca3b5c 3937 'title': video_title,
545cc85d 3938 'formats': formats,
3939 'thumbnails': thumbnails,
fccf5021 3940 # The best thumbnail that we are sure exists. Prevents unnecessary
3941 # URL checking if user don't care about getting the best possible thumbnail
3942 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3943 'description': video_description,
11f9be09 3944 'uploader': get_first(video_details, 'author'),
545cc85d 3945 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3946 'uploader_url': owner_profile_url,
3947 'channel_id': channel_id,
a70635b8 3948 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3949 'duration': duration,
3950 'view_count': int_or_none(
11f9be09 3951 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3952 or search_meta('interactionCount')),
11f9be09 3953 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3954 'age_limit': 18 if (
11f9be09 3955 get_first(microformats, 'isFamilySafe') is False
545cc85d 3956 or search_meta('isFamilyFriendly') == 'false'
3957 or search_meta('og:restrictions:age') == '18+') else 0,
3958 'webpage_url': webpage_url,
3959 'categories': [category] if category else None,
3960 'tags': keywords,
11f9be09 3961 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 3962 'live_status': live_status,
adbc4ec4 3963 'release_timestamp': live_start_time,
545cc85d 3964 }
b477fc13 3965
c646d76f 3966 subtitles = {}
3944e7af 3967 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3968 if pctr:
ecdc9049 3969 def get_lang_code(track):
3970 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3971 or track.get('languageCode'))
3972
3973 # Converted into dicts to remove duplicates
3974 captions = {
3975 get_lang_code(sub): sub
3976 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3977 translation_languages = {
3978 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3979 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3980
774d79cc 3981 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3982 lang_subs = container.setdefault(lang_code, [])
545cc85d 3983 for fmt in self._SUBTITLE_FORMATS:
3984 query.update({
3985 'fmt': fmt,
3986 })
3987 lang_subs.append({
3988 'ext': fmt,
60f393e4 3989 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3990 'name': sub_name,
545cc85d 3991 })
7e72694b 3992
07b47084 3993 # NB: Constructing the full subtitle dictionary is slow
3994 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3995 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3996 for lang_code, caption_track in captions.items():
3997 base_url = caption_track.get('baseUrl')
1235d333 3998 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3999 if not base_url:
4000 continue
ecdc9049 4001 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4002 if caption_track.get('kind') != 'asr':
545cc85d 4003 if not lang_code:
4004 continue
4005 process_language(
ecdc9049 4006 subtitles, base_url, lang_code, lang_name, {})
4007 if not caption_track.get('isTranslatable'):
4008 continue
3944e7af 4009 for trans_code, trans_name in translation_languages.items():
4010 if not trans_code:
545cc85d 4011 continue
1235d333 4012 orig_trans_code = trans_code
ecdc9049 4013 if caption_track.get('kind') != 'asr':
07b47084 4014 if not get_translated_subs:
18e49408 4015 continue
ecdc9049 4016 trans_code += f'-{lang_code}'
a70635b8 4017 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 4018 # Add an "-orig" label to the original language so that it can be distinguished.
4019 # The subs are returned without "-orig" as well for compatibility
1235d333 4020 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 4021 process_language(
d49669ac 4022 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4023 # Setting tlang=lang returns damaged subtitles.
d49669ac 4024 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4025 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4026
4027 info['automatic_captions'] = automatic_captions
4028 info['subtitles'] = subtitles
7e72694b 4029
14f25df2 4030 parsed_url = urllib.parse.urlparse(url)
545cc85d 4031 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4032 query = urllib.parse.parse_qs(component)
545cc85d 4033 for k, v in query.items():
4034 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4035 d_k += '_time'
4036 if d_k not in info and k in s_ks:
4037 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4038
4039 # Youtube Music Auto-generated description
822b9d9c 4040 if video_description:
1890fc63 4041 mobj = re.search(
4042 r'''(?xs)
4043 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4044 (?P<album>[^\n]+)
4045 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4046 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4047 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4048 .+\nAuto-generated\ by\ YouTube\.\s*$
4049 ''', video_description)
822b9d9c 4050 if mobj:
822b9d9c
RA
4051 release_year = mobj.group('release_year')
4052 release_date = mobj.group('release_date')
4053 if release_date:
4054 release_date = release_date.replace('-', '')
4055 if not release_year:
545cc85d 4056 release_year = release_date[:4]
4057 info.update({
4058 'album': mobj.group('album'.strip()),
4059 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4060 'track': mobj.group('track').strip(),
4061 'release_date': release_date,
cc2db878 4062 'release_year': int_or_none(release_year),
545cc85d 4063 })
7e72694b 4064
545cc85d 4065 initial_data = None
4066 if webpage:
56ba69e4 4067 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4068 if not initial_data:
99e9e001 4069 query = {'videoId': video_id}
4070 query.update(self._get_checkok_params())
109dd3b2 4071 initial_data = self._extract_response(
4072 item_id=video_id, ep='next', fatal=False,
99e9e001 4073 ytcfg=master_ytcfg, query=query,
4074 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4075 note='Downloading initial data API JSON')
545cc85d 4076
0df111a3 4077 info['comment_count'] = traverse_obj(initial_data, (
4078 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4079 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4080 ), (
4081 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4082 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4083 ), expected_type=int_or_none, get_all=False)
4084
19a03940 4085 try: # This will error if there is no livechat
c60ee3a2 4086 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4087 except (KeyError, IndexError, TypeError):
4088 pass
4089 else:
ecdc9049 4090 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4091 # url is needed to set cookies
4092 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4093 'video_id': video_id,
4094 'ext': 'json',
4d37720a
L
4095 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4096 else 'youtube_live_chat_replay'),
c60ee3a2 4097 }]
545cc85d 4098
4099 if initial_data:
7c365c21 4100 info['chapters'] = (
4101 self._extract_chapters_from_json(initial_data, duration)
4102 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4103 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4104 or None)
545cc85d 4105
17322130 4106 contents = traverse_obj(
4107 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4108 expected_type=list, default=[])
4109
4110 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4111 if vpir:
4112 stl = vpir.get('superTitleLink')
4113 if stl:
4114 stl = self._get_text(stl)
4115 if try_get(
4116 vpir,
4117 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4118 info['location'] = stl
4119 else:
affc4fef 4120 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4121 if mobj:
545cc85d 4122 info.update({
17322130 4123 'series': mobj.group(1),
4124 'season_number': int(mobj.group(2)),
4125 'episode_number': int(mobj.group(3)),
545cc85d 4126 })
17322130 4127 for tlb in (try_get(
4128 vpir,
4129 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4130 list) or []):
3ffb2f5b 4131 tbrs = variadic(
4132 traverse_obj(
4133 tlb, 'toggleButtonRenderer',
4134 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4135 default=[]))
4136 for tbr in tbrs:
4137 for getter, regex in [(
4138 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4139 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4140 lambda x: x['accessibility'],
4141 lambda x: x['accessibilityData']['accessibilityData'],
4142 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4143 label = (try_get(tbr, getter, dict) or {}).get('label')
4144 if label:
4145 mobj = re.match(regex, label)
4146 if mobj:
4147 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4148 break
17322130 4149 sbr_tooltip = try_get(
4150 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4151 if sbr_tooltip:
4152 like_count, dislike_count = sbr_tooltip.split(' / ')
4153 info.update({
4154 'like_count': str_to_int(like_count),
4155 'dislike_count': str_to_int(dislike_count),
4156 })
867c66ff
M
4157 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4158 if vcr:
4159 vc = self._get_count(vcr, 'viewCount')
4160 # Upcoming premieres with waiting count are treated as live here
4161 if vcr.get('isLive'):
4162 info['concurrent_view_count'] = vc
4163 elif info.get('view_count') is None:
4164 info['view_count'] = vc
4165
17322130 4166 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4167 if vsir:
4168 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4169 info.update({
4170 'channel': self._get_text(vor, 'title'),
4171 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4172
4173 rows = try_get(
4174 vsir,
4175 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4176 list) or []
4177 multiple_songs = False
4178 for row in rows:
4179 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4180 multiple_songs = True
4181 break
4182 for row in rows:
4183 mrr = row.get('metadataRowRenderer') or {}
4184 mrr_title = mrr.get('title')
4185 if not mrr_title:
4186 continue
4187 mrr_title = self._get_text(mrr, 'title')
4188 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4189 if mrr_title == 'License':
4190 info['license'] = mrr_contents_text
4191 elif not multiple_songs:
4192 if mrr_title == 'Album':
4193 info['album'] = mrr_contents_text
4194 elif mrr_title == 'Artist':
4195 info['artist'] = mrr_contents_text
4196 elif mrr_title == 'Song':
4197 info['track'] = mrr_contents_text
545cc85d 4198
4199 fallbacks = {
4200 'channel': 'uploader',
4201 'channel_id': 'uploader_id',
4202 'channel_url': 'uploader_url',
4203 }
992f9a73 4204
17322130 4205 # The upload date for scheduled, live and past live streams / premieres in microformats
4206 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4207 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4208 upload_date = (
4209 unified_strdate(get_first(microformats, 'uploadDate'))
4210 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4211 if not upload_date or (
4d37720a 4212 live_status in ('not_live', None)
1ff88b7a 4213 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4214 ):
c26f9b99 4215 upload_date = strftime_or_none(
4216 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4217 info['upload_date'] = upload_date
992f9a73 4218
545cc85d 4219 for to, frm in fallbacks.items():
4220 if not info.get(to):
4221 info[to] = info.get(frm)
4222
4223 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4224 v = info.get(s_k)
4225 if v:
4226 info[d_k] = v
b84071c0 4227
c26f9b99 4228 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4229
4230 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4231 or get_first(video_details, 'isPrivate', expected_type=bool))
4232
4233 info['availability'] = (
4234 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4235 else self._availability(
4236 is_private=is_private,
4237 needs_premium=(
4238 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4239 or False if initial_data and is_private is not None else None),
4240 needs_subscription=(
4241 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4242 or False if initial_data and is_private is not None else None),
4243 needs_auth=info['age_limit'] >= 18,
4244 is_unlisted=None if is_private is None else (
4245 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4246 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4247
a2160aa4 4248 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4249
11f9be09 4250 self.mark_watched(video_id, player_responses)
d77ab8e2 4251
545cc85d 4252 return info
c5e8d7af 4253
a61fd4cf 4254
a6213a49 4255class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 4256
182bda88 4257 @staticmethod
4258 def passthrough_smuggled_data(func):
4259 def _smuggle(entries, smuggled_data):
4260 for entry in entries:
4261 # TODO: Convert URL to music.youtube instead.
4262 # Do we need to passthrough any other smuggled_data?
4263 entry['url'] = smuggle_url(entry['url'], smuggled_data)
4264 yield entry
4265
4266 @functools.wraps(func)
4267 def wrapper(self, url):
4268 url, smuggled_data = unsmuggle_url(url, {})
4269 if self.is_music_url(url):
4270 smuggled_data['is_music_url'] = True
4271 info_dict = func(self, url, smuggled_data)
4272 if smuggled_data and info_dict.get('entries'):
4273 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
4274 return info_dict
4275 return wrapper
4276
a6213a49 4277 def _extract_channel_id(self, webpage):
4278 channel_id = self._html_search_meta(
4279 'channelId', webpage, 'channel id', default=None)
4280 if channel_id:
4281 return channel_id
4282 channel_url = self._html_search_meta(
4283 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4284 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4285 'twitter:app:url:googleplay'), webpage, 'channel url')
4286 return self._search_regex(
4287 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4288 channel_url, 'channel id')
15f6397c 4289
8bdd16b4 4290 @staticmethod
cd7c66cf 4291 def _extract_basic_item_renderer(item):
4292 # Modified from _extract_grid_item_renderer
201c1459 4293 known_basic_renderers = (
a17526e4 4294 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4295 )
4296 for key, renderer in item.items():
201c1459 4297 if not isinstance(renderer, dict):
cd7c66cf 4298 continue
201c1459 4299 elif key in known_basic_renderers:
4300 return renderer
4301 elif key.startswith('grid') and key.endswith('Renderer'):
4302 return renderer
8bdd16b4 4303
8bdd16b4 4304 def _grid_entries(self, grid_renderer):
4305 for item in grid_renderer['items']:
4306 if not isinstance(item, dict):
39b62db1 4307 continue
cd7c66cf 4308 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4309 if not isinstance(renderer, dict):
4310 continue
052e1350 4311 title = self._get_text(renderer, 'title')
fe93e2c4 4312
8bdd16b4 4313 # playlist
4314 playlist_id = renderer.get('playlistId')
4315 if playlist_id:
4316 yield self.url_result(
4317 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4318 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4319 video_title=title)
201c1459 4320 continue
8bdd16b4 4321 # video
4322 video_id = renderer.get('videoId')
4323 if video_id:
4324 yield self._extract_video(renderer)
201c1459 4325 continue
8bdd16b4 4326 # channel
4327 channel_id = renderer.get('channelId')
4328 if channel_id:
8bdd16b4 4329 yield self.url_result(
4330 'https://www.youtube.com/channel/%s' % channel_id,
4331 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4332 continue
4333 # generic endpoint URL support
4334 ep_url = urljoin('https://www.youtube.com/', try_get(
4335 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4336 str))
201c1459 4337 if ep_url:
4338 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4339 if ie.suitable(ep_url):
4340 yield self.url_result(
4341 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4342 break
8bdd16b4 4343
16aa9ea4 4344 def _music_reponsive_list_entry(self, renderer):
4345 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4346 if video_id:
4347 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4348 ie=YoutubeIE.ie_key(), video_id=video_id)
4349 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4350 if playlist_id:
4351 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4352 if video_id:
4353 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4354 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4355 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4356 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4357 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4358 if browse_id:
4359 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4360 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4361
3d3dddc9 4362 def _shelf_entries_from_content(self, shelf_renderer):
4363 content = shelf_renderer.get('content')
4364 if not isinstance(content, dict):
8bdd16b4 4365 return
cd7c66cf 4366 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4367 if renderer:
4368 # TODO: add support for nested playlists so each shelf is processed
4369 # as separate playlist
4370 # TODO: this includes only first N items
86e5f3ed 4371 yield from self._grid_entries(renderer)
3d3dddc9 4372 renderer = content.get('horizontalListRenderer')
4373 if renderer:
4374 # TODO
4375 pass
8bdd16b4 4376
29f7c58a 4377 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4378 ep = try_get(
4379 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4380 str)
8bdd16b4 4381 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4382 if shelf_url:
29f7c58a 4383 # Skipping links to another channels, note that checking for
4384 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4385 # will not work
4386 if skip_channels and '/channels?' in shelf_url:
4387 return
052e1350 4388 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4389 yield self.url_result(shelf_url, video_title=title)
4390 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4391 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4392
8bdd16b4 4393 def _playlist_entries(self, video_list_renderer):
4394 for content in video_list_renderer['contents']:
4395 if not isinstance(content, dict):
4396 continue
4397 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4398 if not isinstance(renderer, dict):
4399 continue
4400 video_id = renderer.get('videoId')
4401 if not video_id:
4402 continue
4403 yield self._extract_video(renderer)
07aeced6 4404
3462ffa8 4405 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4406 renderer = traverse_obj(
4407 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4408 video_id = renderer.get('videoId')
4409 if not video_id:
4410 return
4411 yield self._extract_video(renderer)
4412
8bdd16b4 4413 def _video_entry(self, video_renderer):
4414 video_id = video_renderer.get('videoId')
4415 if video_id:
4416 return self._extract_video(video_renderer)
dacb3a86 4417
ad210f4f 4418 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4419 url = urljoin('https://youtube.com', traverse_obj(
4420 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4421 if url:
4422 return self.url_result(
4423 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4424
8bdd16b4 4425 def _post_thread_entries(self, post_thread_renderer):
4426 post_renderer = try_get(
4427 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4428 if not post_renderer:
4429 return
4430 # video attachment
4431 video_renderer = try_get(
895b0931 4432 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4433 video_id = video_renderer.get('videoId')
4434 if video_id:
4435 entry = self._extract_video(video_renderer)
8bdd16b4 4436 if entry:
4437 yield entry
895b0931 4438 # playlist attachment
4439 playlist_id = try_get(
14f25df2 4440 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4441 if playlist_id:
4442 yield self.url_result(
e28f1c0a 4443 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4444 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4445 # inline video links
4446 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4447 for run in runs:
4448 if not isinstance(run, dict):
4449 continue
4450 ep_url = try_get(
14f25df2 4451 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4452 if not ep_url:
4453 continue
4454 if not YoutubeIE.suitable(ep_url):
4455 continue
4456 ep_video_id = YoutubeIE._match_id(ep_url)
4457 if video_id == ep_video_id:
4458 continue
895b0931 4459 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4460
8bdd16b4 4461 def _post_thread_continuation_entries(self, post_thread_continuation):
4462 contents = post_thread_continuation.get('contents')
4463 if not isinstance(contents, list):
4464 return
4465 for content in contents:
4466 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4467 if isinstance(renderer, dict):
4468 yield from self._post_thread_entries(renderer)
8bdd16b4 4469 continue
6b0b0a28 4470 renderer = content.get('videoRenderer')
4471 if isinstance(renderer, dict):
4472 yield self._video_entry(renderer)
07aeced6 4473
39ed931e 4474 r''' # unused
4475 def _rich_grid_entries(self, contents):
4476 for content in contents:
4477 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4478 if video_renderer:
4479 entry = self._video_entry(video_renderer)
4480 if entry:
4481 yield entry
4482 '''
52efa4b3 4483
0a5095fe 4484 def _report_history_entries(self, renderer):
4485 for url in traverse_obj(renderer, (
7a32c70d 4486 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4487 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4488 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4489 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4490
a6213a49 4491 def _extract_entries(self, parent_renderer, continuation_list):
4492 # continuation_list is modified in-place with continuation_list = [continuation_token]
4493 continuation_list[:] = [None]
4494 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4495 for content in contents:
4496 if not isinstance(content, dict):
4497 continue
16aa9ea4 4498 is_renderer = traverse_obj(
4499 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4500 expected_type=dict)
a6213a49 4501 if not is_renderer:
0a5095fe 4502 if content.get('richItemRenderer'):
4503 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4504 yield entry
4505 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4506 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4507 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4508 yield from self._report_history_entries(table)
4509 continuation_list[0] = self._extract_continuation(table)
a6213a49 4510 continue
0a5095fe 4511
a6213a49 4512 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4513 for isr_content in isr_contents:
4514 if not isinstance(isr_content, dict):
8bdd16b4 4515 continue
69184e41 4516
a6213a49 4517 known_renderers = {
4518 'playlistVideoListRenderer': self._playlist_entries,
4519 'gridRenderer': self._grid_entries,
a17526e4 4520 'reelShelfRenderer': self._grid_entries,
4521 'shelfRenderer': self._shelf_entries,
16aa9ea4 4522 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4523 'backstagePostThreadRenderer': self._post_thread_entries,
4524 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4525 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4526 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4527 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4528 }
4529 for key, renderer in isr_content.items():
4530 if key not in known_renderers:
4531 continue
4532 for entry in known_renderers[key](renderer):
4533 if entry:
4534 yield entry
4535 continuation_list[0] = self._extract_continuation(renderer)
4536 break
70d5c17b 4537
4538 if not continuation_list[0]:
a6213a49 4539 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4540
a6213a49 4541 if not continuation_list[0]:
4542 continuation_list[0] = self._extract_continuation(parent_renderer)
4543
4544 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4545 continuation_list = [None]
4546 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4547 tab_content = try_get(tab, lambda x: x['content'], dict)
4548 if not tab_content:
4549 return
3462ffa8 4550 parent_renderer = (
29f7c58a 4551 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4552 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4553 yield from extract_entries(parent_renderer)
3462ffa8 4554 continuation = continuation_list[0]
d069eca7 4555
8bdd16b4 4556 for page_num in itertools.count(1):
4557 if not continuation:
4558 break
99e9e001 4559 headers = self.generate_api_headers(
4560 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4561 response = self._extract_response(
86e5f3ed 4562 item_id=f'{item_id} page {page_num}',
fe93e2c4 4563 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4564 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4565
4566 if not response:
8bdd16b4 4567 break
ac56cf38 4568 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4569 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4570 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4571
a1b535bd 4572 known_renderers = {
e4b98809 4573 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4574 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4575 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4576 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4577 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4578 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4579 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4580 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4581 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4582 'playlistVideoListContinuation': (self._playlist_entries, None),
4583 'gridContinuation': (self._grid_entries, None),
4584 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4585 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4586 }
1fb53b94 4587
4588 continuation_items = traverse_obj(response, (
4589 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4590 'appendContinuationItemsAction', 'continuationItems'
4591 ), 'continuationContents', get_all=False)
4592 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4593
a1b535bd 4594 video_items_renderer = None
1fb53b94 4595 for key in continuation_item.keys():
a1b535bd 4596 if key not in known_renderers:
8bdd16b4 4597 continue
1fb53b94 4598 func, parent_key = known_renderers[key]
4599 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4600 continuation_list = [None]
1fb53b94 4601 yield from func(video_items_renderer)
9ba5705a 4602 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4603
4604 if not video_items_renderer:
a1b535bd 4605 break
9558dcec 4606
8bdd16b4 4607 @staticmethod
7c219ea6 4608 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4609 for tab_renderer in tabs:
4610 if tab_renderer.get('selected'):
4611 return tab_renderer
4612 if fatal:
4613 raise ExtractorError('Unable to find selected tab')
4614
4615 @staticmethod
4616 def _extract_tab_renderers(response):
4617 return traverse_obj(
4618 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4619
ac56cf38 4620 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4621 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4622 tags = []
b60419c5 4623
8bdd16b4 4624 selected_tab = self._extract_selected_tab(tabs)
6141346d 4625 # Deprecated - remove when layout discontinued
f0d785d3 4626 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
6141346d
M
4627 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4628 metadata_renderer = try_get(
8bdd16b4 4629 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
6141346d
M
4630 if metadata_renderer:
4631 channel_name = metadata_renderer.get('title')
4632 channel_url = metadata_renderer.get('channelUrl')
4633 channel_id = metadata_renderer.get('externalId')
39ed931e 4634 else:
6141346d 4635 metadata_renderer = try_get(
64c0d954 4636 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4637
6141346d
M
4638 if metadata_renderer:
4639 title = metadata_renderer.get('title')
4640 description = metadata_renderer.get('description', '')
b60419c5 4641 playlist_id = channel_id
6141346d 4642 tags = metadata_renderer.get('keywords', '').split()
b60419c5 4643
301d07fc 4644 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4645 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4646 def _get_uncropped(url):
4647 return url_or_none((url or '').split('=')[0] + '=s0')
4648
6141346d 4649 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 4650 if avatar_thumbnails:
4651 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4652 if uncropped_avatar:
4653 avatar_thumbnails.append({
4654 'url': uncropped_avatar,
4655 'id': 'avatar_uncropped',
4656 'preference': 1
4657 })
4658
4659 channel_banners = self._extract_thumbnails(
4660 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4661 for banner in channel_banners:
4662 banner['preference'] = -10
4663
4664 if channel_banners:
4665 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4666 if uncropped_banner:
4667 channel_banners.append({
4668 'url': uncropped_banner,
4669 'id': 'banner_uncropped',
4670 'preference': -5
4671 })
4672
6141346d 4673 # Deprecated - remove when old layout is discontinued
301d07fc 4674 primary_thumbnails = self._extract_thumbnails(
a17526e4 4675 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4676
6141346d
M
4677 playlist_thumbnails = self._extract_thumbnails(
4678 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4679
3462ffa8 4680 if playlist_id is None:
70d5c17b 4681 playlist_id = item_id
f0d785d3 4682
6141346d
M
4683 # Deprecated - remove primary_sidebar_renderer when old layout discontinued
4684 # Playlist stats is a text runs array containing [video count, view count, last updated].
4685 # last updated or (view count and last updated) may be missing.
4686 playlist_stats = get_first(
4687 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'),))
4688 last_updated_unix = self._parse_time_text(
4689 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4690 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
4691
4692 view_count = self._get_count(playlist_stats, 1)
4693 if view_count is None:
4694 view_count = self._get_count(playlist_header_renderer, 'viewCountText')
4695
4696 playlist_count = self._get_count(playlist_stats, 0)
4697 if playlist_count is None:
4698 playlist_count = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4699
70d5c17b 4700 if title is None:
f0d785d3 4701 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4702 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4703 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4704
b60419c5 4705 metadata = {
4706 'playlist_id': playlist_id,
4707 'playlist_title': title,
4708 'playlist_description': description,
4709 'uploader': channel_name,
4710 'uploader_id': channel_id,
4711 'uploader_url': channel_url,
6141346d 4712 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
b60419c5 4713 'tags': tags,
6141346d 4714 'view_count': view_count,
f0d785d3 4715 'availability': self._extract_availability(data),
4716 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6141346d 4717 'playlist_count': playlist_count,
6c73052c 4718 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4719 }
4720 if not channel_id:
6141346d
M
4721 owner = traverse_obj(playlist_header_renderer, 'ownerText')
4722 if not owner:
4723 # Deprecated
4724 owner = traverse_obj(
4725 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4726 ('videoOwner', 'videoOwnerRenderer', 'title'))
4727 owner_text = self._get_text(owner)
4728 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4729 metadata.update(filter_dict({
4730 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4731 'uploader_id': browse_ep.get('browseId'),
4732 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
4733 }))
4734
b60419c5 4735 metadata.update({
4736 'channel': metadata['uploader'],
4737 'channel_id': metadata['uploader_id'],
4738 'channel_url': metadata['uploader_url']})
4739 return self.playlist_result(
d069eca7 4740 self._entries(
ac56cf38 4741 selected_tab, playlist_id, ytcfg,
4742 self._extract_account_syncid(ytcfg, data),
4743 self._extract_visitor_data(data, ytcfg)),
b60419c5 4744 **metadata)
73c4ac2c 4745
6e634cbe 4746 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4747 first_id = last_id = response = None
2be71994 4748 for page_num in itertools.count(1):
cd7c66cf 4749 videos = list(self._playlist_entries(playlist))
4750 if not videos:
4751 return
2be71994 4752 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4753 if start >= len(videos):
4754 return
24146491 4755 yield from videos[start:]
2be71994 4756 first_id = first_id or videos[0]['id']
4757 last_id = videos[-1]['id']
79360d99 4758 watch_endpoint = try_get(
4759 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4760 headers = self.generate_api_headers(
4761 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4762 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4763 query = {
4764 'playlistId': playlist_id,
4765 'videoId': watch_endpoint.get('videoId') or last_id,
4766 'index': watch_endpoint.get('index') or len(videos),
4767 'params': watch_endpoint.get('params') or 'OAE%3D'
4768 }
4769 response = self._extract_response(
4770 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4771 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4772 check_get_keys='contents'
4773 )
cd7c66cf 4774 playlist = try_get(
79360d99 4775 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4776
ac56cf38 4777 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4778 title = playlist.get('title') or try_get(
14f25df2 4779 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4780 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4781
4782 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4783 playlist_url = urljoin(url, try_get(
4784 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4785 str))
6e634cbe 4786
4787 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4788 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4789 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4790
4791 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4792 return self.url_result(
4793 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4794 video_title=title)
cd7c66cf 4795
8bdd16b4 4796 return self.playlist_result(
6e634cbe 4797 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4798 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4799
47193e02 4800 def _extract_availability(self, data):
4801 """
4802 Gets the availability of a given playlist/tab.
4803 Note: Unless YouTube tells us explicitly, we do not assume it is public
4804 @param data: response
4805 """
6141346d
M
4806 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4807 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4808 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 4809
6141346d 4810 badges = self._extract_badges(sidebar_renderer)
47193e02 4811
4812 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
4813 privacy_setting_icon = get_first(
4814 (playlist_header_renderer, sidebar_renderer),
4815 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4816 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4817 expected_type=str)
4818
4819 microformats_is_unlisted = traverse_obj(
4820 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 4821
c26f9b99 4822 return (
4823 'public' if (
4824 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4825 or player_header_privacy == 'PUBLIC'
4826 or privacy_setting_icon == 'PRIVACY_PUBLIC')
4827 else self._availability(
4828 is_private=(
4829 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4830 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
4831 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
4832 is_unlisted=(
4833 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4834 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
4835 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
4836 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 4837 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
4838 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
4839 needs_auth=False))
47193e02 4840
4841 @staticmethod
4842 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4843 sidebar_renderer = try_get(
4844 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4845 for item in sidebar_renderer:
4846 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4847 if renderer:
4848 return renderer
4849
ac56cf38 4850 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4851 """
6141346d 4852 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 4853 """
6141346d
M
4854 is_playlist = bool(traverse_obj(
4855 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
4856 if not is_playlist:
47193e02 4857 return
11f9be09 4858 headers = self.generate_api_headers(
99e9e001 4859 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4860 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4861 query = {
6141346d
M
4862 'params': 'wgYCCAA=',
4863 'browseId': f'VL{item_id}'
47193e02 4864 }
4865 return self._extract_response(
4866 item_id=item_id, headers=headers, query=query,
fe93e2c4 4867 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 4868 note='Redownloading playlist API JSON with unavailable videos')
358de58c 4869
2762dbb1 4870 @functools.cached_property
a25bca9f 4871 def skip_webpage(self):
4872 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4873
ac56cf38 4874 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4875 webpage, data = None, None
4876 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4877 try:
be5c1ae8 4878 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4879 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4880 except ExtractorError as e:
4881 if isinstance(e.cause, network_exceptions):
14f25df2 4882 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4883 retry.error = e
4884 continue
4885 self._error_or_warning(e, fatal=fatal)
14fdfea9 4886 break
ac56cf38 4887
be5c1ae8 4888 try:
4889 self._extract_and_report_alerts(data)
4890 except ExtractorError as e:
4891 self._error_or_warning(e, fatal=fatal)
4892 break
ac56cf38 4893
be5c1ae8 4894 # Sometimes youtube returns a webpage with incomplete ytInitialData
4895 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4896 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4897 retry.error = ExtractorError('Incomplete yt initial data received')
4898 continue
ac56cf38 4899
cd7c66cf 4900 return webpage, data
4901
a25bca9f 4902 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4903 """Use if failed to extract ytcfg (and data) from initial webpage"""
4904 if not ytcfg and self.is_authenticated:
4905 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4906 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4907 raise ExtractorError(
4908 f'{msg}. If you are not downloading private content, or '
4909 'your cookies are only for the first account and channel,'
4910 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4911 expected=True)
4912 self.report_warning(msg, only_once=True)
4913
ac56cf38 4914 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4915 data = None
a25bca9f 4916 if not self.skip_webpage:
ac56cf38 4917 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4918 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4919 # Reject webpage data if redirected to home page without explicitly requesting
86973308 4920 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 4921 if (url != 'https://www.youtube.com/feed/recommended'
4922 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4923 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4924 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4925 if fatal:
4926 raise ExtractorError(msg, expected=True)
4927 self.report_warning(msg, only_once=True)
ac56cf38 4928 if not data:
a25bca9f 4929 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4930 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4931 return data, ytcfg
4932
4933 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4934 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4935 resolve_response = self._extract_response(
4936 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4937 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4938 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4939 for ep_key, ep in endpoints.items():
4940 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4941 if params:
4942 return self._extract_response(
4943 item_id=item_id, query=params, ep=ep, headers=headers,
4944 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4945 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4946 err_note = 'Failed to resolve url (does the playlist exist?)'
4947 if fatal:
4948 raise ExtractorError(err_note, expected=True)
4949 self.report_warning(err_note, item_id)
4950
a6213a49 4951 _SEARCH_PARAMS = None
4952
af5c1c55 4953 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4954 data = {'query': query}
4955 if params is NO_DEFAULT:
4956 params = self._SEARCH_PARAMS
4957 if params:
4958 data['params'] = params
16aa9ea4 4959
4960 content_keys = (
4961 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4962 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4963 # ytmusic search
4964 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4965 ('continuationContents', ),
4966 )
a25bca9f 4967 display_id = f'query "{query}"'
86e5f3ed 4968 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4969 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4970 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4971
a61fd4cf 4972 continuation_list = [None]
a25bca9f 4973 search = None
a6213a49 4974 for page_num in itertools.count(1):
a61fd4cf 4975 data.update(continuation_list[0] or {})
a25bca9f 4976 headers = self.generate_api_headers(
4977 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4978 search = self._extract_response(
a25bca9f 4979 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4980 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4981 slr_contents = traverse_obj(search, *content_keys)
4982 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4983 if not continuation_list[0]:
a6213a49 4984 break
4985
4986
4987class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4988 IE_DESC = 'YouTube Tabs'
4989 _VALID_URL = r'''(?x:
4990 https?://
4991 (?:\w+\.)?
4992 (?:
4993 youtube(?:kids)?\.com|
4994 %(invidious)s
4995 )/
4996 (?:
4997 (?P<channel_type>channel|c|user|browse)/|
4998 (?P<not_channel>
4999 feed/|hashtag/|
5000 (?:playlist|watch)\?.*?\blist=
5001 )|
5002 (?!(?:%(reserved_names)s)\b) # Direct URLs
5003 )
5004 (?P<id>[^/?\#&]+)
5005 )''' % {
5006 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5007 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5008 }
5009 IE_NAME = 'youtube:tab'
5010
5011 _TESTS = [{
5012 'note': 'playlists, multipage',
5013 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5014 'playlist_mincount': 94,
5015 'info_dict': {
5016 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5017 'title': 'Igor Kleiner - Playlists',
a6213a49 5018 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5019 'uploader': 'Igor Kleiner',
a6213a49 5020 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5021 'channel': 'Igor Kleiner',
5022 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5023 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5024 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5025 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5026 'channel_follower_count': int
a6213a49 5027 },
5028 }, {
5029 'note': 'playlists, multipage, different order',
5030 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5031 'playlist_mincount': 94,
5032 'info_dict': {
5033 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5034 'title': 'Igor Kleiner - Playlists',
a6213a49 5035 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5036 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5037 'uploader': 'Igor Kleiner',
5038 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5039 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5040 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5041 'channel': 'Igor Kleiner',
5042 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5043 'channel_follower_count': int
a6213a49 5044 },
5045 }, {
5046 'note': 'playlists, series',
5047 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5048 'playlist_mincount': 5,
5049 'info_dict': {
5050 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5051 'title': '3Blue1Brown - Playlists',
5052 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5053 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5054 'uploader': '3Blue1Brown',
976ae3ea 5055 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5056 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5057 'channel': '3Blue1Brown',
5058 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5059 'tags': ['Mathematics'],
6c73052c 5060 'channel_follower_count': int
a6213a49 5061 },
5062 }, {
5063 'note': 'playlists, singlepage',
5064 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5065 'playlist_mincount': 4,
5066 'info_dict': {
5067 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5068 'title': 'ThirstForScience - Playlists',
5069 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5070 'uploader': 'ThirstForScience',
5071 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5072 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5073 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5074 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5075 'tags': 'count:13',
5076 'channel': 'ThirstForScience',
6c73052c 5077 'channel_follower_count': int
a6213a49 5078 }
5079 }, {
5080 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5081 'only_matching': True,
5082 }, {
5083 'note': 'basic, single video playlist',
5084 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5085 'info_dict': {
5086 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5087 'uploader': 'Sergey M.',
5088 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5089 'title': 'youtube-dl public playlist',
976ae3ea 5090 'description': '',
5091 'tags': [],
5092 'view_count': int,
5093 'modified_date': '20201130',
5094 'channel': 'Sergey M.',
5095 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5096 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5097 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5098 'availability': 'public',
a6213a49 5099 },
5100 'playlist_count': 1,
5101 }, {
5102 'note': 'empty playlist',
5103 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5104 'info_dict': {
5105 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5106 'uploader': 'Sergey M.',
5107 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5108 'title': 'youtube-dl empty playlist',
976ae3ea 5109 'tags': [],
5110 'channel': 'Sergey M.',
5111 'description': '',
5112 'modified_date': '20160902',
5113 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5114 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5115 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5116 'availability': 'public',
a6213a49 5117 },
5118 'playlist_count': 0,
5119 }, {
5120 'note': 'Home tab',
5121 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5122 'info_dict': {
5123 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5124 'title': 'lex will - Home',
5125 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5126 'uploader': 'lex will',
5127 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5128 'channel': 'lex will',
5129 'tags': ['bible', 'history', 'prophesy'],
5130 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5131 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5132 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5133 'channel_follower_count': int
a6213a49 5134 },
5135 'playlist_mincount': 2,
5136 }, {
5137 'note': 'Videos tab',
5138 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5139 'info_dict': {
5140 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5141 'title': 'lex will - Videos',
5142 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5143 'uploader': 'lex will',
5144 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5145 'tags': ['bible', 'history', 'prophesy'],
5146 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5147 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5148 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5149 'channel': 'lex will',
6c73052c 5150 'channel_follower_count': int
a6213a49 5151 },
5152 'playlist_mincount': 975,
5153 }, {
5154 'note': 'Videos tab, sorted by popular',
5155 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5156 'info_dict': {
5157 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5158 'title': 'lex will - Videos',
5159 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5160 'uploader': 'lex will',
5161 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5162 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5163 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5164 'channel': 'lex will',
5165 'tags': ['bible', 'history', 'prophesy'],
5166 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5167 'channel_follower_count': int
a6213a49 5168 },
5169 'playlist_mincount': 199,
5170 }, {
5171 'note': 'Playlists tab',
5172 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5173 'info_dict': {
5174 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5175 'title': 'lex will - Playlists',
5176 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5177 'uploader': 'lex will',
5178 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5179 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5180 'channel': 'lex will',
5181 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5182 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5183 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5184 'channel_follower_count': int
a6213a49 5185 },
5186 'playlist_mincount': 17,
5187 }, {
5188 'note': 'Community tab',
5189 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5190 'info_dict': {
5191 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5192 'title': 'lex will - Community',
5193 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5194 'uploader': 'lex will',
5195 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5196 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5197 'channel': 'lex will',
5198 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5199 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5200 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5201 'channel_follower_count': int
a6213a49 5202 },
5203 'playlist_mincount': 18,
5204 }, {
5205 'note': 'Channels tab',
5206 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5207 'info_dict': {
5208 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5209 'title': 'lex will - Channels',
5210 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5211 'uploader': 'lex will',
5212 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5213 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5214 'channel': 'lex will',
5215 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5216 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5217 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5218 'channel_follower_count': int
a6213a49 5219 },
5220 'playlist_mincount': 12,
5221 }, {
5222 'note': 'Search tab',
5223 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5224 'playlist_mincount': 40,
5225 'info_dict': {
5226 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5227 'title': '3Blue1Brown - Search - linear algebra',
5228 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5229 'uploader': '3Blue1Brown',
5230 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5231 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5232 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5233 'tags': ['Mathematics'],
5234 'channel': '3Blue1Brown',
5235 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5236 'channel_follower_count': int
a6213a49 5237 },
5238 }, {
5239 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5240 'only_matching': True,
5241 }, {
5242 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5243 'only_matching': True,
5244 }, {
5245 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5246 'only_matching': True,
5247 }, {
5248 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5249 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5250 'info_dict': {
5251 'title': '29C3: Not my department',
5252 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5253 'uploader': 'Christiaan008',
5254 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5255 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5256 'tags': [],
5257 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5258 'view_count': int,
5259 'modified_date': '20150605',
5260 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5261 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5262 'channel': 'Christiaan008',
c26f9b99 5263 'availability': 'public',
a6213a49 5264 },
5265 'playlist_count': 96,
5266 }, {
5267 'note': 'Large playlist',
5268 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5269 'info_dict': {
5270 'title': 'Uploads from Cauchemar',
5271 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5272 'uploader': 'Cauchemar',
5273 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5274 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5275 'tags': [],
5276 'modified_date': r're:\d{8}',
5277 'channel': 'Cauchemar',
5278 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5279 'view_count': int,
5280 'description': '',
5281 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5282 'availability': 'public',
a6213a49 5283 },
5284 'playlist_mincount': 1123,
976ae3ea 5285 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5286 }, {
5287 'note': 'even larger playlist, 8832 videos',
5288 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5289 'only_matching': True,
5290 }, {
5291 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5292 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5293 'info_dict': {
5294 'title': 'Uploads from Interstellar Movie',
5295 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5296 'uploader': 'Interstellar Movie',
5297 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5298 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5299 'tags': [],
5300 'view_count': int,
5301 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5302 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5303 'channel': 'Interstellar Movie',
5304 'description': '',
5305 'modified_date': r're:\d{8}',
c26f9b99 5306 'availability': 'public',
a6213a49 5307 },
5308 'playlist_mincount': 21,
5309 }, {
5310 'note': 'Playlist with "show unavailable videos" button',
5311 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5312 'info_dict': {
5313 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5314 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5315 'uploader': 'Phim Siêu Nhân Nhật Bản',
5316 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5317 'view_count': int,
5318 'channel': 'Phim Siêu Nhân Nhật Bản',
5319 'tags': [],
5320 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5321 'description': '',
5322 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5323 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5324 'modified_date': r're:\d{8}',
c26f9b99 5325 'availability': 'public',
a6213a49 5326 },
5327 'playlist_mincount': 200,
976ae3ea 5328 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5329 }, {
5330 'note': 'Playlist with unavailable videos in page 7',
5331 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5332 'info_dict': {
5333 'title': 'Uploads from BlankTV',
5334 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5335 'uploader': 'BlankTV',
5336 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5337 'channel': 'BlankTV',
5338 'channel_url': 'https://www.youtube.com/c/blanktv',
5339 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5340 'view_count': int,
5341 'tags': [],
5342 'uploader_url': 'https://www.youtube.com/c/blanktv',
5343 'modified_date': r're:\d{8}',
5344 'description': '',
c26f9b99 5345 'availability': 'public',
a6213a49 5346 },
5347 'playlist_mincount': 1000,
976ae3ea 5348 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5349 }, {
5350 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5351 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5352 'info_dict': {
5353 'title': 'Data Analysis with Dr Mike Pound',
5354 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5355 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5356 'uploader': 'Computerphile',
5357 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5358 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5359 'tags': [],
5360 'view_count': int,
5361 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5362 'channel_url': 'https://www.youtube.com/user/Computerphile',
5363 'channel': 'Computerphile',
c26f9b99 5364 'availability': 'public',
6141346d 5365 'modified_date': '20190712',
a6213a49 5366 },
5367 'playlist_mincount': 11,
5368 }, {
5369 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5370 'only_matching': True,
5371 }, {
5372 'note': 'Playlist URL that does not actually serve a playlist',
5373 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5374 'info_dict': {
5375 'id': 'FqZTN594JQw',
5376 'ext': 'webm',
5377 'title': "Smiley's People 01 detective, Adventure Series, Action",
5378 'uploader': 'STREEM',
5379 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5380 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5381 'upload_date': '20150526',
5382 'license': 'Standard YouTube License',
5383 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5384 'categories': ['People & Blogs'],
5385 'tags': list,
5386 'view_count': int,
5387 'like_count': int,
a6213a49 5388 },
5389 'params': {
5390 'skip_download': True,
5391 },
5392 'skip': 'This video is not available.',
5393 'add_ie': [YoutubeIE.ie_key()],
5394 }, {
5395 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5396 'only_matching': True,
5397 }, {
5398 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5399 'only_matching': True,
5400 }, {
5401 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5402 'info_dict': {
12a1b225 5403 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5404 'ext': 'mp4',
976ae3ea 5405 'title': str,
a6213a49 5406 'uploader': 'Sky News',
5407 'uploader_id': 'skynews',
5408 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5409 'upload_date': r're:\d{8}',
976ae3ea 5410 'description': str,
a6213a49 5411 'categories': ['News & Politics'],
5412 'tags': list,
5413 'like_count': int,
86973308 5414 'release_timestamp': int,
976ae3ea 5415 'channel': 'Sky News',
5416 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5417 'age_limit': 0,
5418 'view_count': int,
86973308 5419 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5420 'playable_in_embed': True,
86973308 5421 'release_date': r're:\d+',
976ae3ea 5422 'availability': 'public',
5423 'live_status': 'is_live',
5424 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5425 'channel_follower_count': int,
5426 'concurrent_view_count': int,
a6213a49 5427 },
5428 'params': {
5429 'skip_download': True,
5430 },
976ae3ea 5431 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5432 }, {
5433 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5434 'info_dict': {
5435 'id': 'a48o2S1cPoo',
5436 'ext': 'mp4',
5437 'title': 'The Young Turks - Live Main Show',
5438 'uploader': 'The Young Turks',
5439 'uploader_id': 'TheYoungTurks',
5440 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5441 'upload_date': '20150715',
5442 'license': 'Standard YouTube License',
5443 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5444 'categories': ['News & Politics'],
5445 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5446 'like_count': int,
a6213a49 5447 },
5448 'params': {
5449 'skip_download': True,
5450 },
5451 'only_matching': True,
5452 }, {
5453 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5454 'only_matching': True,
5455 }, {
5456 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5457 'only_matching': True,
5458 }, {
5459 'note': 'A channel that is not live. Should raise error',
5460 'url': 'https://www.youtube.com/user/numberphile/live',
5461 'only_matching': True,
5462 }, {
5463 'url': 'https://www.youtube.com/feed/trending',
5464 'only_matching': True,
5465 }, {
5466 'url': 'https://www.youtube.com/feed/library',
5467 'only_matching': True,
5468 }, {
5469 'url': 'https://www.youtube.com/feed/history',
5470 'only_matching': True,
5471 }, {
5472 'url': 'https://www.youtube.com/feed/subscriptions',
5473 'only_matching': True,
5474 }, {
5475 'url': 'https://www.youtube.com/feed/watch_later',
5476 'only_matching': True,
5477 }, {
5478 'note': 'Recommended - redirects to home page.',
5479 'url': 'https://www.youtube.com/feed/recommended',
5480 'only_matching': True,
5481 }, {
5482 'note': 'inline playlist with not always working continuations',
5483 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5484 'only_matching': True,
5485 }, {
5486 'url': 'https://www.youtube.com/course',
5487 'only_matching': True,
5488 }, {
5489 'url': 'https://www.youtube.com/zsecurity',
5490 'only_matching': True,
5491 }, {
5492 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5493 'only_matching': True,
5494 }, {
5495 'url': 'https://www.youtube.com/TheYoungTurks/live',
5496 'only_matching': True,
5497 }, {
5498 'url': 'https://www.youtube.com/hashtag/cctv9',
5499 'info_dict': {
5500 'id': 'cctv9',
5501 'title': '#cctv9',
976ae3ea 5502 'tags': [],
a6213a49 5503 },
4dc23a80 5504 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5505 }, {
5506 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5507 'only_matching': True,
5508 }, {
5509 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5510 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5511 'only_matching': True
5512 }, {
5513 'note': '/browse/ should redirect to /channel/',
5514 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5515 'only_matching': True
5516 }, {
5517 'note': 'VLPL, should redirect to playlist?list=PL...',
5518 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5519 'info_dict': {
5520 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5521 'uploader': 'NoCopyrightSounds',
5522 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5523 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5524 'title': 'NCS : All Releases 💿',
976ae3ea 5525 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5526 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5527 'modified_date': r're:\d{8}',
5528 'view_count': int,
5529 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5530 'tags': [],
5531 'channel': 'NoCopyrightSounds',
c26f9b99 5532 'availability': 'public',
a6213a49 5533 },
5534 'playlist_mincount': 166,
976ae3ea 5535 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5536 }, {
5537 'note': 'Topic, should redirect to playlist?list=UU...',
5538 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5539 'info_dict': {
5540 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5541 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5542 'title': 'Uploads from Royalty Free Music - Topic',
5543 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5544 'tags': [],
5545 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5546 'channel': 'Royalty Free Music - Topic',
5547 'view_count': int,
5548 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5549 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5550 'modified_date': r're:\d{8}',
5551 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5552 'description': '',
c26f9b99 5553 'availability': 'public',
a6213a49 5554 },
5555 'expected_warnings': [
a6213a49 5556 'The URL does not have a videos tab',
976ae3ea 5557 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5558 ],
5559 'playlist_mincount': 101,
5560 }, {
86973308
M
5561 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5562 # Treat as a general feed
a6213a49 5563 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5564 'info_dict': {
5565 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5566 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5567 'tags': [],
a6213a49 5568 },
a6213a49 5569 'playlist_mincount': 9,
5570 }, {
5571 'note': 'Youtube music Album',
5572 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5573 'info_dict': {
5574 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5575 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5576 'tags': [],
5577 'view_count': int,
5578 'description': '',
5579 'availability': 'unlisted',
5580 'modified_date': r're:\d{8}',
a6213a49 5581 },
5582 'playlist_count': 50,
5583 }, {
5584 'note': 'unlisted single video playlist',
5585 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5586 'info_dict': {
5587 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5588 'uploader': 'colethedj',
5589 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5590 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5591 'availability': 'unlisted',
5592 'tags': [],
12a1b225 5593 'modified_date': '20220418',
976ae3ea 5594 'channel': 'colethedj',
5595 'view_count': int,
5596 'description': '',
5597 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5598 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5599 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5600 },
5601 'playlist_count': 1,
5602 }, {
5603 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5604 'url': 'https://www.youtube.com/feed/recommended',
5605 'info_dict': {
5606 'id': 'recommended',
5607 'title': 'recommended',
6c73052c 5608 'tags': [],
a6213a49 5609 },
5610 'playlist_mincount': 50,
5611 'params': {
5612 'skip_download': True,
5613 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5614 },
5615 }, {
5616 'note': 'API Fallback: /videos tab, sorted by oldest first',
5617 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5618 'info_dict': {
5619 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5620 'title': 'Cody\'sLab - Videos',
5621 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5622 'uploader': 'Cody\'sLab',
5623 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5624 'channel': 'Cody\'sLab',
5625 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5626 'tags': [],
5627 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5628 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5629 'channel_follower_count': int
a6213a49 5630 },
5631 'playlist_mincount': 650,
5632 'params': {
5633 'skip_download': True,
5634 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5635 },
86973308 5636 'skip': 'Query for sorting no longer works',
a6213a49 5637 }, {
5638 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5639 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5640 'info_dict': {
5641 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5642 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5643 'title': 'Uploads from Royalty Free Music - Topic',
5644 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5645 'modified_date': r're:\d{8}',
5646 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5647 'description': '',
5648 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5649 'tags': [],
5650 'channel': 'Royalty Free Music - Topic',
5651 'view_count': int,
5652 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5653 'availability': 'public',
a6213a49 5654 },
a6213a49 5655 'playlist_mincount': 101,
5656 'params': {
5657 'skip_download': True,
5658 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5659 },
7c219ea6 5660 }, {
5661 'note': 'non-standard redirect to regional channel',
5662 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5663 'only_matching': True
61d3665d 5664 }, {
5665 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5666 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5667 'info_dict': {
5668 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5669 'modified_date': '20220407',
5670 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5671 'tags': [],
5672 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5673 'uploader': 'pukkandan',
5674 'availability': 'unlisted',
5675 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5676 'channel': 'pukkandan',
5677 'description': 'Test for collaborative playlist',
5678 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5679 'view_count': int,
61d3665d 5680 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5681 },
5682 'playlist_mincount': 2
c26f9b99 5683 }, {
5684 'note': 'translated tab name',
5685 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5686 'info_dict': {
5687 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5688 'tags': [],
5689 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5690 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 5691 'description': 'test description',
c26f9b99 5692 'title': 'cole-dlp-test-acc - 再生リスト',
5693 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5694 'uploader': 'cole-dlp-test-acc',
5695 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5696 'channel': 'cole-dlp-test-acc',
6141346d 5697 'channel_follower_count': int,
c26f9b99 5698 },
5699 'playlist_mincount': 1,
5700 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5701 'expected_warnings': ['Preferring "ja"'],
5702 }, {
5703 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5704 'note': 'preferred lang set with playlist with translated video titles',
5705 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5706 'info_dict': {
5707 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5708 'tags': [],
5709 'view_count': int,
5710 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5711 'uploader': 'cole-dlp-test-acc',
5712 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5713 'channel': 'cole-dlp-test-acc',
5714 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5715 'description': 'test',
5716 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5717 'title': 'dlp test playlist',
5718 'availability': 'public',
5719 },
5720 'playlist_mincount': 1,
5721 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5722 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5723 }, {
5724 # shorts audio pivot for 2GtVksBMYFM.
5725 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5726 'info_dict': {
5727 'id': 'sfv_audio_pivot',
5728 'title': 'sfv_audio_pivot',
5729 'tags': [],
5730 },
5731 'playlist_mincount': 50,
5732
86973308
M
5733 }, {
5734 # Channel with a real live tab (not to be mistaken with streams tab)
5735 # Do not treat like it should redirect to live stream
5736 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5737 'info_dict': {
5738 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5739 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5740 'tags': [],
5741 },
5742 'playlist_mincount': 20,
5743 }, {
5744 # Tab name is not the same as tab id
5745 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5746 'info_dict': {
5747 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5748 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5749 'tags': [],
5750 },
5751 'playlist_mincount': 8,
5752 }, {
5753 # Home tab id is literally home. Not to get mistaken with featured
5754 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5755 'info_dict': {
5756 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5757 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5758 'tags': [],
5759 },
5760 'playlist_mincount': 8,
5761 }, {
5762 # Should get three playlists for videos, shorts and streams tabs
5763 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5764 'info_dict': {
5765 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5766 'title': 'Uploads for UCK9V2B22uJYu3N7eR_BT9QA'
5767 },
5768 'playlist_count': 3,
5769 }, {
5770 # Shorts tab with channel with handle
5771 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5772 'info_dict': {
5773 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5774 'title': 'Not Just Bikes - Shorts',
5775 'tags': 'count:12',
5776 'uploader': 'Not Just Bikes',
5777 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5778 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5779 'channel_follower_count': int,
5780 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5781 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5782 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5783 'channel': 'Not Just Bikes',
5784 },
5785 'playlist_mincount': 10,
5786 }, {
5787 # Streams tab
5788 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5789 'info_dict': {
5790 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5791 'title': '中村悠一 - Live',
5792 'tags': 'count:7',
5793 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5794 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5795 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5796 'channel': '中村悠一',
5797 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5798 'channel_follower_count': int,
5799 'uploader': '中村悠一',
5800 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5801 },
5802 'playlist_mincount': 60,
5803 }, {
5804 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5805 # See test_youtube_lists
5806 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5807 'only_matching': True,
5808 }, {
5809 # No uploads and no UCID given. Should fail with no uploads error
5810 # See test_youtube_lists
5811 'url': 'https://www.youtube.com/news',
5812 'only_matching': True
5813 }, {
5814 # No videos tab but has a shorts tab
5815 'url': 'https://www.youtube.com/c/TKFShorts',
5816 'info_dict': {
5817 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5818 'title': 'Shorts Break - Shorts',
5819 'tags': 'count:32',
5820 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5821 'channel': 'Shorts Break',
5822 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5823 'uploader': 'Shorts Break',
5824 'channel_follower_count': int,
5825 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5826 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5827 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5828 },
5829 'playlist_mincount': 30,
5830 }, {
5831 # Trending Now Tab. tab id is empty
5832 'url': 'https://www.youtube.com/feed/trending',
5833 'info_dict': {
5834 'id': 'trending',
5835 'title': 'trending - Now',
5836 'tags': [],
5837 },
5838 'playlist_mincount': 30,
5839 }, {
5840 # Trending Gaming Tab. tab id is empty
5841 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
5842 'info_dict': {
5843 'id': 'trending',
5844 'title': 'trending - Gaming',
5845 'tags': [],
5846 },
5847 'playlist_mincount': 30,
4dc23a80
M
5848 }, {
5849 # Shorts url result in shorts tab
5850 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
5851 'info_dict': {
5852 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5853 'title': 'cole-dlp-test-acc - Shorts',
5854 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5855 'channel': 'cole-dlp-test-acc',
5856 'channel_follower_count': int,
5857 'description': 'test description',
5858 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5859 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5860 'tags': [],
5861 'uploader': 'cole-dlp-test-acc',
5862 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5863
5864 },
5865 'playlist': [{
5866 'info_dict': {
5867 '_type': 'url',
5868 'ie_key': 'Youtube',
5869 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
5870 'id': 'sSM9J5YH_60',
5871 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5872 'title': 'SHORT short',
5873 'channel': 'cole-dlp-test-acc',
5874 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5875 'view_count': int,
5876 'thumbnails': list,
5877 }
5878 }],
5879 'params': {'extract_flat': True},
5880 }, {
5881 # Live video status should be extracted
5882 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
5883 'info_dict': {
5884 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5885 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
5886 'tags': []
5887 },
5888 'playlist': [{
5889 'info_dict': {
5890 '_type': 'url',
5891 'ie_key': 'Youtube',
5892 'url': 'startswith:https://www.youtube.com/watch?v=',
5893 'id': str,
5894 'title': str,
5895 'live_status': 'is_live',
5896 'channel_id': str,
5897 'channel_url': str,
5898 'concurrent_view_count': int,
5899 'channel': str,
5900 }
5901 }],
5902 'params': {'extract_flat': True},
5903 'playlist_mincount': 1
a6213a49 5904 }]
5905
5906 @classmethod
5907 def suitable(cls, url):
86e5f3ed 5908 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5909
86973308
M
5910 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
5911
5912 def _get_url_mobj(self, url):
5913 mobj = self._URL_RE.match(url).groupdict()
5914 mobj.update((k, '') for k, v in mobj.items() if v is None)
5915 return mobj
5916
5917 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
5918 tab_name = (tab.get('title') or '').lower()
5919 tab_url = urljoin(base_url, traverse_obj(
5920 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5921
5922 tab_id = (traverse_obj(tab, 'tabIdentifier', expected_type=str)
5923 or tab_url and self._get_url_mobj(tab_url)['tab'][1:])
5924 if tab_id:
5925 return tab_id, tab_name
5926
5927 # Fallback to tab name if we cannot get the tab id.
5928 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
5929 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
5930 self.write_debug(f'Falling back to selected tab name: {tab_name}')
5931 return {
5932 'home': 'featured',
5933 'live': 'streams',
5934 }.get(tab_name, tab_name), tab_name
5935
5936 def _has_tab(self, tabs, tab_id):
5937 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 5938
182bda88 5939 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5940 def _real_extract(self, url, smuggled_data):
cd7c66cf 5941 item_id = self._match_id(url)
14f25df2 5942 url = urllib.parse.urlunparse(
5943 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5944 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5945
86973308
M
5946 mobj = self._get_url_mobj(url)
5947 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
fe03a6cd 5948 if is_channel:
5949 if smuggled_data.get('is_music_url'):
37e57a9f 5950 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5951 item_id = item_id[2:]
37e57a9f 5952 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5953 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5954 mdata = self._extract_tab_endpoint(
37e57a9f 5955 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5956 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5957 get_all=False, expected_type=str)
ac56cf38 5958 if not murl:
37e57a9f 5959 raise ExtractorError('Failed to resolve album to playlist')
86973308 5960 return self.url_result(murl, YoutubeTabIE)
37e57a9f 5961 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5962 pre = f'https://www.youtube.com/channel/{item_id}'
5963
86973308 5964 original_tab_id = tab[1:]
fe03a6cd 5965 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
fe03a6cd 5966 tab = '/videos'
5967
5968 url = ''.join((pre, tab, post))
86973308 5969 mobj = self._get_url_mobj(url)
cd7c66cf 5970
5971 # Handle both video/playlist URLs
201c1459 5972 qs = parse_qs(url)
86e5f3ed 5973 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5974
fe03a6cd 5975 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5976 if not playlist_id:
fe03a6cd 5977 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5978 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5979 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5980 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5981 url = f'https://www.youtube.com/playlist?list={playlist_id}'
86973308 5982 mobj = self._get_url_mobj(url)
cd7c66cf 5983
86973308
M
5984 if not self._yes_playlist(playlist_id, video_id):
5985 return self.url_result(
5986 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 5987
ac56cf38 5988 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5989
7c219ea6 5990 # YouTube may provide a non-standard redirect to the regional channel
5991 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 5992 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 5993 redirect_url = traverse_obj(
5994 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5995 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5996 redirect_url = ''.join((
5997 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
86973308
M
5998 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
5999 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6000
86973308
M
6001 tab_results = []
6002 tabs = self._extract_tab_renderers(data)
6003 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6004 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6005 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6006 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6007
6008 if not original_tab_id and selected_tab_name:
6009 self.to_screen('Channel URLs download all uploads of the channel. '
6010 'To download only the videos in a specific tab, pass the tab\'s URL')
6011 if self._has_tab(tabs, 'streams'):
6012 tab_results.append(self.url_result(''.join((pre, '/streams', post))))
6013 if self._has_tab(tabs, 'shorts'):
6014 tab_results.append(self.url_result(''.join((pre, '/shorts', post))))
6015 # XXX: Members-only tab should also be extracted
6016
6017 if not tab_results and selected_tab_id != 'videos':
6018 # Channel does not have streams, shorts or videos tabs
6019 if item_id[:2] != 'UC':
6020 raise ExtractorError('This channel has no uploads', expected=True)
6021
6022 # Topic channels don't have /videos. Use the equivalent playlist instead
6023 pl_id = f'UU{item_id[2:]}'
6024 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6025 try:
6026 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6027 except ExtractorError:
6028 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6029 else:
86973308
M
6030 item_id, url = pl_id, pl_url
6031 self.to_screen(
6032 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6033
6034 elif tab_results and selected_tab_id != 'videos':
6035 # When there are shorts/live tabs but not videos tab
6036 url, data = ''.join((pre, post)), None
6037
6038 elif (original_tab_id or 'videos') != selected_tab_id:
6039 if original_tab_id == 'live':
6040 # Live tab should have redirected to the video
6041 # Except in the case the channel has an actual live tab
6042 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6043 raise UserNotLive(video_id=mobj['id'])
6044 elif selected_tab_name:
6045 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6046
6047 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6048 url = f'{pre}{post}'
18db7548 6049
37e57a9f 6050 self.write_debug(f'Final URL: {url}')
18db7548 6051
358de58c 6052 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6053 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 6054 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 6055 self._extract_and_report_alerts(data, only_once=True)
86973308
M
6056
6057 tabs = self._extract_tab_renderers(data)
8bdd16b4 6058 if tabs:
86973308
M
6059 tab_results[:0] = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6060 tab_results[0].update({
6061 'extractor_key': YoutubeTabIE.ie_key(),
6062 'extractor': YoutubeTabIE.IE_NAME,
6063 'webpage_url': url,
6064 })
6065
6066 if len(tab_results) == 1:
6067 return tab_results[0]
6068 elif len(tab_results) > 1:
6069 return self.playlist_result(tab_results, item_id, title=f'Uploads for {item_id}')
cd7c66cf 6070
37e57a9f 6071 playlist = traverse_obj(
6072 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6073 if playlist:
ac56cf38 6074 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6075
37e57a9f 6076 video_id = traverse_obj(
6077 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6078 if video_id:
09f1580e 6079 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 6080 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6081 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6082
8bdd16b4 6083 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6084
c5e8d7af 6085
8bdd16b4 6086class YoutubePlaylistIE(InfoExtractor):
96565c7e 6087 IE_DESC = 'YouTube playlists'
8bdd16b4 6088 _VALID_URL = r'''(?x)(?:
6089 (?:https?://)?
6090 (?:\w+\.)?
6091 (?:
6092 (?:
6093 youtube(?:kids)?\.com|
d9190e44 6094 %(invidious)s
8bdd16b4 6095 )
6096 /.*?\?.*?\blist=
6097 )?
6098 (?P<id>%(playlist_id)s)
d9190e44
RH
6099 )''' % {
6100 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6101 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6102 }
8bdd16b4 6103 IE_NAME = 'youtube:playlist'
cdc628a4 6104 _TESTS = [{
8bdd16b4 6105 'note': 'issue #673',
6106 'url': 'PLBB231211A4F62143',
cdc628a4 6107 'info_dict': {
8bdd16b4 6108 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6109 'id': 'PLBB231211A4F62143',
976ae3ea 6110 'uploader': 'Wickman',
8bdd16b4 6111 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 6112 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6113 'view_count': int,
86973308 6114 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
976ae3ea 6115 'modified_date': r're:\d{8}',
6116 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6117 'channel': 'Wickman',
6118 'tags': [],
86973308
M
6119 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6120 'availability': 'public',
8bdd16b4 6121 },
6122 'playlist_mincount': 29,
6123 }, {
6124 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6125 'info_dict': {
6126 'title': 'YDL_safe_search',
6127 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6128 },
6129 'playlist_count': 2,
6130 'skip': 'This playlist is private',
9558dcec 6131 }, {
8bdd16b4 6132 'note': 'embedded',
6133 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6134 'playlist_count': 4,
9558dcec 6135 'info_dict': {
8bdd16b4 6136 'title': 'JODA15',
6137 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6138 'uploader': 'milan',
6139 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 6140 'description': '',
6141 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6142 'tags': [],
6143 'modified_date': '20140919',
6144 'view_count': int,
6145 'channel': 'milan',
6146 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6147 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 6148 'availability': 'public',
976ae3ea 6149 },
86973308 6150 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6151 }, {
8bdd16b4 6152 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6153 'playlist_mincount': 455,
8bdd16b4 6154 'info_dict': {
6155 'title': '2018 Chinese New Singles (11/6 updated)',
6156 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6157 'uploader': 'LBK',
6158 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 6159 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6160 'channel': 'LBK',
6161 'view_count': int,
6162 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6163 'tags': [],
6164 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6165 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6166 'modified_date': r're:\d{8}',
c26f9b99 6167 'availability': 'public',
976ae3ea 6168 },
6169 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6170 }, {
29f7c58a 6171 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6172 'only_matching': True,
6173 }, {
6174 # music album playlist
6175 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6176 'only_matching': True,
6177 }]
6178
6179 @classmethod
6180 def suitable(cls, url):
201c1459 6181 if YoutubeTabIE.suitable(url):
6182 return False
49a57e70 6183 from ..utils import parse_qs
201c1459 6184 qs = parse_qs(url)
6185 if qs.get('v', [None])[0]:
6186 return False
86e5f3ed 6187 return super().suitable(url)
29f7c58a 6188
6189 def _real_extract(self, url):
6190 playlist_id = self._match_id(url)
46953e7e 6191 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6192 url = update_url_query(
6193 'https://www.youtube.com/playlist',
6194 parse_qs(url) or {'list': playlist_id})
6195 if is_music_url:
6196 url = smuggle_url(url, {'is_music_url': True})
6197 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6198
6199
6200class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6201 IE_DESC = 'youtu.be'
29f7c58a 6202 _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}
6203 _TESTS = [{
8bdd16b4 6204 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6205 'info_dict': {
6206 'id': 'yeWKywCrFtk',
6207 'ext': 'mp4',
6208 'title': 'Small Scale Baler and Braiding Rugs',
6209 'uploader': 'Backus-Page House Museum',
6210 'uploader_id': 'backuspagemuseum',
6211 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6212 'upload_date': '20161008',
6213 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6214 'categories': ['Nonprofits & Activism'],
6215 'tags': list,
6216 'like_count': int,
976ae3ea 6217 'age_limit': 0,
6218 'playable_in_embed': True,
6219 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6220 'channel': 'Backus-Page House Museum',
6221 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6222 'live_status': 'not_live',
6223 'view_count': int,
6224 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6225 'availability': 'public',
6226 'duration': 59,
12a1b225
A
6227 'comment_count': int,
6228 'channel_follower_count': int
8bdd16b4 6229 },
6230 'params': {
6231 'noplaylist': True,
6232 'skip_download': True,
6233 },
39e7107d 6234 }, {
8bdd16b4 6235 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6236 'only_matching': True,
cdc628a4
PH
6237 }]
6238
8bdd16b4 6239 def _real_extract(self, url):
5ad28e7f 6240 mobj = self._match_valid_url(url)
29f7c58a 6241 video_id = mobj.group('id')
6242 playlist_id = mobj.group('playlist_id')
8bdd16b4 6243 return self.url_result(
29f7c58a 6244 update_url_query('https://www.youtube.com/watch', {
6245 'v': video_id,
6246 'list': playlist_id,
6247 'feature': 'youtu.be',
6248 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6249
6250
b6ce9bb0 6251class YoutubeLivestreamEmbedIE(InfoExtractor):
6252 IE_DESC = 'YouTube livestream embeds'
6253 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6254 _TESTS = [{
6255 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6256 'only_matching': True,
6257 }]
6258
6259 def _real_extract(self, url):
6260 channel_id = self._match_id(url)
6261 return self.url_result(
6262 f'https://www.youtube.com/channel/{channel_id}/live',
6263 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6264
6265
8bdd16b4 6266class YoutubeYtUserIE(InfoExtractor):
96565c7e 6267 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6268 IE_NAME = 'youtube:user'
8bdd16b4 6269 _VALID_URL = r'ytuser:(?P<id>.+)'
6270 _TESTS = [{
6271 'url': 'ytuser:phihag',
6272 'only_matching': True,
6273 }]
6274
6275 def _real_extract(self, url):
6276 user_id = self._match_id(url)
6277 return self.url_result(
c586f9e8 6278 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 6279 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 6280
b05654f0 6281
3d3dddc9 6282class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6283 IE_NAME = 'youtube:favorites'
96565c7e 6284 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6285 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6286 _LOGIN_REQUIRED = True
6287 _TESTS = [{
6288 'url': ':ytfav',
6289 'only_matching': True,
6290 }, {
6291 'url': ':ytfavorites',
6292 'only_matching': True,
6293 }]
6294
6295 def _real_extract(self, url):
6296 return self.url_result(
6297 'https://www.youtube.com/playlist?list=LL',
6298 ie=YoutubeTabIE.ie_key())
6299
6300
ca5300c7 6301class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6302 IE_NAME = 'youtube:notif'
6303 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6304 _VALID_URL = r':ytnotif(?:ication)?s?'
6305 _LOGIN_REQUIRED = True
6306 _TESTS = [{
6307 'url': ':ytnotif',
6308 'only_matching': True,
6309 }, {
6310 'url': ':ytnotifications',
6311 'only_matching': True,
6312 }]
6313
6314 def _extract_notification_menu(self, response, continuation_list):
6315 notification_list = traverse_obj(
6316 response,
6317 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6318 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6319 expected_type=list) or []
6320 continuation_list[0] = None
6321 for item in notification_list:
6322 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6323 if entry:
6324 yield entry
6325 continuation = item.get('continuationItemRenderer')
6326 if continuation:
6327 continuation_list[0] = continuation
6328
6329 def _extract_notification_renderer(self, notification):
6330 video_id = traverse_obj(
6331 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6332 url = f'https://www.youtube.com/watch?v={video_id}'
6333 channel_id = None
6334 if not video_id:
6335 browse_ep = traverse_obj(
6336 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6337 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6338 post_id = self._search_regex(
6339 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6340 'post id', default=None)
6341 if not channel_id or not post_id:
6342 return
6343 # The direct /post url redirects to this in the browser
6344 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6345
6346 channel = traverse_obj(
6347 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6348 expected_type=str)
c7a7baaa 6349 notification_title = self._get_text(notification, 'shortMessage')
6350 if notification_title:
6351 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6352 # TODO: handle recommended videos
ca5300c7 6353 title = self._search_regex(
c7a7baaa 6354 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6355 'video title', default=None)
5225df50 6356 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6357 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6358 else None)
ca5300c7 6359 return {
6360 '_type': 'url',
6361 'url': url,
6362 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6363 'video_id': video_id,
6364 'title': title,
6365 'channel_id': channel_id,
6366 'channel': channel,
6367 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6368 'timestamp': timestamp,
ca5300c7 6369 }
6370
6371 def _notification_menu_entries(self, ytcfg):
6372 continuation_list = [None]
6373 response = None
6374 for page in itertools.count(1):
6375 ctoken = traverse_obj(
6376 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6377 response = self._extract_response(
6378 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6379 ep='notification/get_notification_menu', check_get_keys='actions',
6380 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6381 yield from self._extract_notification_menu(response, continuation_list)
6382 if not continuation_list[0]:
6383 break
6384
6385 def _real_extract(self, url):
6386 display_id = 'notifications'
6387 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6388 self._report_playlist_authcheck(ytcfg)
6389 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6390
6391
a6213a49 6392class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6393 IE_DESC = 'YouTube search'
78caa52a 6394 IE_NAME = 'youtube:search'
b05654f0 6395 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6396 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6397 _TESTS = [{
6398 'url': 'ytsearch5:youtube-dl test video',
6399 'playlist_count': 5,
6400 'info_dict': {
6401 'id': 'youtube-dl test video',
6402 'title': 'youtube-dl test video',
6403 }
6404 }]
b05654f0 6405
a61fd4cf 6406
5f7cb91a 6407class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6408 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6409 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6410 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6411 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6412 _TESTS = [{
6413 'url': 'ytsearchdate5:youtube-dl test video',
6414 'playlist_count': 5,
6415 'info_dict': {
6416 'id': 'youtube-dl test video',
6417 'title': 'youtube-dl test video',
6418 }
6419 }]
75dff0ee 6420
c9ae7b95 6421
a6213a49 6422class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6423 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6424 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6425 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6426 _TESTS = [{
6427 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6428 'playlist_mincount': 5,
6429 'info_dict': {
11f9be09 6430 'id': 'youtube-dl test video',
3462ffa8 6431 'title': 'youtube-dl test video',
6432 }
a61fd4cf 6433 }, {
6434 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6435 'playlist_mincount': 5,
6436 'info_dict': {
6437 'id': 'python',
6438 'title': 'python',
6439 }
ad210f4f 6440 }, {
6441 'url': 'https://www.youtube.com/results?search_query=%23cats',
6442 'playlist_mincount': 1,
6443 'info_dict': {
6444 'id': '#cats',
6445 'title': '#cats',
12a1b225
A
6446 # The test suite does not have support for nested playlists
6447 # 'entries': [{
6448 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6449 # 'title': '#cats',
6450 # }],
ad210f4f 6451 },
3462ffa8 6452 }, {
6453 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6454 'only_matching': True,
6455 }]
6456
6457 def _real_extract(self, url):
4dfbf869 6458 qs = parse_qs(url)
386e1dd9 6459 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6460 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6461
6462
16aa9ea4 6463class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6464 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6465 IE_NAME = 'youtube:music:search_url'
6466 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6467 _TESTS = [{
6468 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6469 'playlist_count': 16,
6470 'info_dict': {
6471 'id': 'royalty free music',
6472 'title': 'royalty free music',
6473 }
6474 }, {
6475 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6476 'playlist_mincount': 30,
6477 'info_dict': {
6478 'id': 'royalty free music - songs',
6479 'title': 'royalty free music - songs',
6480 },
6481 'params': {'extract_flat': 'in_playlist'}
6482 }, {
6483 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6484 'playlist_mincount': 30,
6485 'info_dict': {
6486 'id': 'royalty free music - community playlists',
6487 'title': 'royalty free music - community playlists',
6488 },
6489 'params': {'extract_flat': 'in_playlist'}
6490 }]
6491
6492 _SECTIONS = {
6493 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6494 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6495 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6496 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6497 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6498 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6499 }
6500
6501 def _real_extract(self, url):
6502 qs = parse_qs(url)
6503 query = (qs.get('search_query') or qs.get('q'))[0]
6504 params = qs.get('sp', (None,))[0]
6505 if params:
6506 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6507 else:
ac668111 6508 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6509 params = self._SECTIONS.get(section)
6510 if not params:
6511 section = None
6512 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6513 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6514
6515
182bda88 6516class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6517 """
25f14e9f 6518 Base class for feed extractors
82d02080 6519 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6520 """
b2e8bc1b 6521 _LOGIN_REQUIRED = True
82d02080 6522 _FEED_NAME = 'feeds'
a25bca9f 6523
6524 def _real_initialize(self):
6525 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6526
82d02080 6527 @classproperty
d7ae0639 6528 def IE_NAME(self):
82d02080 6529 return f'youtube:{self._FEED_NAME}'
04cc9617 6530
3853309f 6531 def _real_extract(self, url):
3d3dddc9 6532 return self.url_result(
182bda88 6533 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6534
6535
ef2f3c7f 6536class YoutubeWatchLaterIE(InfoExtractor):
6537 IE_NAME = 'youtube:watchlater'
96565c7e 6538 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6539 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6540 _TESTS = [{
8bdd16b4 6541 'url': ':ytwatchlater',
bc7a9cd8
S
6542 'only_matching': True,
6543 }]
25f14e9f
S
6544
6545 def _real_extract(self, url):
ef2f3c7f 6546 return self.url_result(
6547 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6548
6549
25f14e9f 6550class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6551 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6552 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6553 _FEED_NAME = 'recommended'
45db527f 6554 _LOGIN_REQUIRED = False
3d3dddc9 6555 _TESTS = [{
6556 'url': ':ytrec',
6557 'only_matching': True,
6558 }, {
6559 'url': ':ytrecommended',
6560 'only_matching': True,
6561 }, {
6562 'url': 'https://youtube.com',
6563 'only_matching': True,
6564 }]
1ed5b5c9 6565
1ed5b5c9 6566
25f14e9f 6567class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6568 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6569 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6570 _FEED_NAME = 'subscriptions'
3d3dddc9 6571 _TESTS = [{
6572 'url': ':ytsubs',
6573 'only_matching': True,
6574 }, {
6575 'url': ':ytsubscriptions',
6576 'only_matching': True,
6577 }]
1ed5b5c9 6578
1ed5b5c9 6579
25f14e9f 6580class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6581 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6582 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6583 _FEED_NAME = 'history'
3d3dddc9 6584 _TESTS = [{
6585 'url': ':ythistory',
6586 'only_matching': True,
6587 }]
1ed5b5c9
JMF
6588
6589
6e634cbe 6590class YoutubeStoriesIE(InfoExtractor):
6591 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6592 IE_NAME = 'youtube:stories'
6593 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6594 _TESTS = [{
6595 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6596 'only_matching': True,
6597 }]
6598
6599 def _real_extract(self, url):
6600 playlist_id = f'RLTD{self._match_id(url)}'
6601 return self.url_result(
50ac0e54 6602 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6603 ie=YoutubeTabIE, video_id=playlist_id)
6604
6605
80eb0bd9 6606class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6607 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6608 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6609 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6610 _TESTS = [{
1dd18a88 6611 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6612 'only_matching': True,
6613 }]
6614
6615 @staticmethod
6616 def _generate_audio_pivot_params(video_id):
6617 """
6618 Generates sfv_audio_pivot browse params for this video id
6619 """
6620 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6621 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6622
6623 def _real_extract(self, url):
6624 video_id = self._match_id(url)
6625 return self.url_result(
6626 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6627 ie=YoutubeTabIE)
6628
6629
15870e90
PH
6630class YoutubeTruncatedURLIE(InfoExtractor):
6631 IE_NAME = 'youtube:truncated_url'
6632 IE_DESC = False # Do not list
975d35db 6633 _VALID_URL = r'''(?x)
b95aab84
PH
6634 (?:https?://)?
6635 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6636 (?:watch\?(?:
c4808c60 6637 feature=[a-z_]+|
b95aab84
PH
6638 annotation_id=annotation_[^&]+|
6639 x-yt-cl=[0-9]+|
c1708b89 6640 hl=[^&]*|
287be8c6 6641 t=[0-9]+
b95aab84
PH
6642 )?
6643 |
6644 attribution_link\?a=[^&]+
6645 )
6646 $
975d35db 6647 '''
15870e90 6648
c4808c60 6649 _TESTS = [{
2d3d2997 6650 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6651 'only_matching': True,
dc2fc736 6652 }, {
2d3d2997 6653 'url': 'https://www.youtube.com/watch?',
dc2fc736 6654 'only_matching': True,
b95aab84
PH
6655 }, {
6656 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6657 'only_matching': True,
6658 }, {
6659 'url': 'https://www.youtube.com/watch?feature=foo',
6660 'only_matching': True,
c1708b89
PH
6661 }, {
6662 'url': 'https://www.youtube.com/watch?hl=en-GB',
6663 'only_matching': True,
287be8c6
PH
6664 }, {
6665 'url': 'https://www.youtube.com/watch?t=2372',
6666 'only_matching': True,
c4808c60
PH
6667 }]
6668
15870e90
PH
6669 def _real_extract(self, url):
6670 raise ExtractorError(
78caa52a
PH
6671 'Did you forget to quote the URL? Remember that & is a meta '
6672 'character in most shells, so you want to put the URL in quotes, '
3867038a 6673 'like youtube-dl '
2d3d2997 6674 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6675 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6676 expected=True)
772fd5cc
PH
6677
6678
471d0367 6679class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6680 IE_NAME = 'youtube:clip'
471d0367 6681 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6682 _TESTS = [{
6683 # FIXME: Other metadata should be extracted from the clip, not from the base video
6684 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6685 'info_dict': {
6686 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6687 'ext': 'mp4',
6688 'section_start': 29.0,
6689 'section_end': 39.7,
6690 'duration': 10.7,
12a1b225
A
6691 'age_limit': 0,
6692 'availability': 'public',
6693 'categories': ['Gaming'],
6694 'channel': 'Scott The Woz',
6695 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6696 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6697 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6698 'like_count': int,
6699 'playable_in_embed': True,
6700 'tags': 'count:17',
6701 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6702 'title': 'Mobile Games on Console - Scott The Woz',
6703 'upload_date': '20210920',
6704 'uploader': 'Scott The Woz',
6705 'uploader_id': 'scottthewoz',
6706 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6707 'view_count': int,
6708 'live_status': 'not_live',
6709 'channel_follower_count': int
471d0367 6710 }
6711 }]
3cd786db 6712
6713 def _real_extract(self, url):
471d0367 6714 clip_id = self._match_id(url)
6715 _, data = self._extract_webpage(url, clip_id)
6716
6717 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6718 if not video_id:
6719 raise ExtractorError('Unable to find video ID')
6720
6721 clip_data = traverse_obj(data, (
6722 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6723 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6724 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6725 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6726
6727 return {
6728 '_type': 'url_transparent',
6729 'url': f'https://www.youtube.com/watch?v={video_id}',
6730 'ie_key': YoutubeIE.ie_key(),
6731 'id': clip_id,
6732 'section_start': int(clip_data['startTimeMs']) / 1000,
6733 'section_end': int(clip_data['endTimeMs']) / 1000,
6734 }
3cd786db 6735
6736
772fd5cc
PH
6737class YoutubeTruncatedIDIE(InfoExtractor):
6738 IE_NAME = 'youtube:truncated_id'
6739 IE_DESC = False # Do not list
b95aab84 6740 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6741
6742 _TESTS = [{
6743 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6744 'only_matching': True,
6745 }]
6746
6747 def _real_extract(self, url):
6748 video_id = self._match_id(url)
6749 raise ExtractorError(
86e5f3ed 6750 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6751 expected=True)