]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[Hotstar] Bugfix for a1ddaa899ca8693f31f34770f7263ace7e8c8841
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
adbc4ec4 5import functools
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
c5e8d7af 17
b05654f0 18from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 19from ..compat import (
edf3e38e 20 compat_chr,
29f7c58a 21 compat_HTTPError,
c5e8d7af 22 compat_parse_qs,
545cc85d 23 compat_str,
7fd002c0 24 compat_urllib_parse_unquote_plus,
15707c7e 25 compat_urllib_parse_urlencode,
7c80519c 26 compat_urllib_parse_urlparse,
7c61bd36 27 compat_urlparse,
4bb4a188 28)
545cc85d 29from ..jsinterp import JSInterpreter
4bb4a188 30from ..utils import (
f8271158 31 NO_DEFAULT,
32 ExtractorError,
720c3099 33 bug_reports_message,
82d02080 34 classproperty,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
2d30521a 39 float_or_none,
11f9be09 40 format_field,
ff91cf74 41 get_first,
dd27fd17 42 int_or_none,
641ad5d8 43 is_html,
34921b43 44 join_nonempty,
48416bc4 45 js_to_json,
94278f72 46 mimetype2ext,
9c0d7f49 47 network_exceptions,
11f9be09 48 orderedSet,
6310acf5 49 parse_codecs,
49bd8c66 50 parse_count,
7c80519c 51 parse_duration,
7ea65411 52 parse_iso8601,
4dfbf869 53 parse_qs,
dca3ff4a 54 qualities,
c0ac49bc 55 remove_end,
3995d37d 56 remove_start,
cf7e015f 57 smuggle_url,
dbdaaa23 58 str_or_none,
c93d53f5 59 str_to_int,
f3aa3c3f 60 strftime_or_none,
7c365c21 61 traverse_obj,
556dbe7f 62 try_get,
c5e8d7af
PH
63 unescapeHTML,
64 unified_strdate,
f0d785d3 65 unified_timestamp,
cf7e015f 66 unsmuggle_url,
8bdd16b4 67 update_url_query,
21c340b8 68 url_or_none,
fe93e2c4 69 urljoin,
7c365c21 70 variadic,
c5e8d7af
PH
71)
72
000c15a4 73# any clients starting with _ cannot be explicity requested by the user
74INNERTUBE_CLIENTS = {
75 'web': {
76 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
77 'INNERTUBE_CONTEXT': {
78 'client': {
79 'clientName': 'WEB',
18c7683d 80 'clientVersion': '2.20211221.00.00',
000c15a4 81 }
82 },
83 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
84 },
85 'web_embedded': {
86 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
87 'INNERTUBE_CONTEXT': {
88 'client': {
89 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 90 'clientVersion': '1.20211215.00.01',
000c15a4 91 },
92 },
93 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
94 },
95 'web_music': {
96 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
97 'INNERTUBE_HOST': 'music.youtube.com',
98 'INNERTUBE_CONTEXT': {
99 'client': {
100 'clientName': 'WEB_REMIX',
18c7683d 101 'clientVersion': '1.20211213.00.00',
000c15a4 102 }
103 },
104 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
105 },
e7e94f2a 106 'web_creator': {
18c7683d 107 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
108 'INNERTUBE_CONTEXT': {
109 'client': {
110 'clientName': 'WEB_CREATOR',
18c7683d 111 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
112 }
113 },
114 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
115 },
000c15a4 116 'android': {
18c7683d 117 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 118 'INNERTUBE_CONTEXT': {
119 'client': {
120 'clientName': 'ANDROID',
18c7683d 121 'clientVersion': '16.49',
000c15a4 122 }
123 },
124 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 125 'REQUIRE_JS_PLAYER': False
000c15a4 126 },
127 'android_embedded': {
18c7683d 128 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 129 'INNERTUBE_CONTEXT': {
130 'client': {
131 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 132 'clientVersion': '16.49',
000c15a4 133 },
134 },
b6de707d 135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
000c15a4 137 },
138 'android_music': {
18c7683d 139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 140 'INNERTUBE_CONTEXT': {
141 'client': {
142 'clientName': 'ANDROID_MUSIC',
18c7683d 143 'clientVersion': '4.57',
000c15a4 144 }
145 },
146 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 147 'REQUIRE_JS_PLAYER': False
000c15a4 148 },
e7e94f2a 149 'android_creator': {
18c7683d 150 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
151 'INNERTUBE_CONTEXT': {
152 'client': {
153 'clientName': 'ANDROID_CREATOR',
18c7683d 154 'clientVersion': '21.47',
e7e94f2a
D
155 },
156 },
b6de707d 157 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
158 'REQUIRE_JS_PLAYER': False
e7e94f2a 159 },
18c7683d 160 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
161 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 162 'ios': {
18c7683d 163 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 164 'INNERTUBE_CONTEXT': {
165 'client': {
166 'clientName': 'IOS',
18c7683d 167 'clientVersion': '16.46',
168 'deviceModel': 'iPhone14,3',
000c15a4 169 }
170 },
b6de707d 171 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
172 'REQUIRE_JS_PLAYER': False
000c15a4 173 },
174 'ios_embedded': {
000c15a4 175 'INNERTUBE_CONTEXT': {
176 'client': {
177 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 178 'clientVersion': '16.46',
179 'deviceModel': 'iPhone14,3',
000c15a4 180 },
181 },
b6de707d 182 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
183 'REQUIRE_JS_PLAYER': False
000c15a4 184 },
185 'ios_music': {
18c7683d 186 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 187 'INNERTUBE_CONTEXT': {
188 'client': {
189 'clientName': 'IOS_MUSIC',
18c7683d 190 'clientVersion': '4.57',
000c15a4 191 },
192 },
b6de707d 193 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
194 'REQUIRE_JS_PLAYER': False
000c15a4 195 },
e7e94f2a
D
196 'ios_creator': {
197 'INNERTUBE_CONTEXT': {
198 'client': {
199 'clientName': 'IOS_CREATOR',
18c7683d 200 'clientVersion': '21.47',
e7e94f2a
D
201 },
202 },
b6de707d 203 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
204 'REQUIRE_JS_PLAYER': False
e7e94f2a 205 },
3619f78d 206 # mweb has 'ultralow' formats
207 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 208 'mweb': {
18c7683d 209 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 210 'INNERTUBE_CONTEXT': {
211 'client': {
212 'clientName': 'MWEB',
18c7683d 213 'clientVersion': '2.20211221.01.00',
000c15a4 214 }
215 },
216 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
217 },
218 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
219 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
220 'tv_embedded': {
221 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
222 'INNERTUBE_CONTEXT': {
223 'client': {
224 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
225 'clientVersion': '2.0',
226 },
227 },
228 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
229 },
000c15a4 230}
231
232
e7870111
D
233def _split_innertube_client(client_name):
234 variant, *base = client_name.rsplit('.', 1)
235 if base:
236 return variant, base[0], variant
237 base, *variant = client_name.split('_', 1)
238 return client_name, base, variant[0] if variant else None
239
240
000c15a4 241def build_innertube_clients():
2e4cacd0 242 THIRD_PARTY = {
e7870111 243 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 244 }
e7870111 245 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 246 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 247
248 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 249 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 250 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 251 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 252 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 253
e7870111 254 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 255 ytcfg['priority'] = 10 * priority(base_client)
256
e48b3875 257 if not variant:
e7870111
D
258 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
259 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
260 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
261 embedscreen['priority'] -= 3
262 elif variant == 'embedded':
e48b3875 263 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 264 ytcfg['priority'] -= 2
e48b3875 265 else:
000c15a4 266 ytcfg['priority'] -= 3
267
268
269build_innertube_clients()
270
271
de7f3446 272class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 273 """Provide base functions for Youtube extractors"""
e00eb564 274
3462ffa8 275 _RESERVED_NAMES = (
3cd786db 276 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 277 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 278 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 279 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 280
3619f78d 281 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
282
52efa4b3 283 # _NETRC_MACHINE = 'youtube'
3619f78d 284
b2e8bc1b
JMF
285 # If True it will raise an error if no login info is provided
286 _LOGIN_REQUIRED = False
287
d9190e44
RH
288 _INVIDIOUS_SITES = (
289 # invidious-redirect websites
290 r'(?:www\.)?redirect\.invidious\.io',
291 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 292 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
293 r'(?:www\.)?invidious\.pussthecat\.org',
294 r'(?:www\.)?invidious\.zee\.li',
295 r'(?:www\.)?invidious\.ethibox\.fr',
296 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
297 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
298 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
299 # youtube-dl invidious instances list
300 r'(?:(?:www|no)\.)?invidiou\.sh',
301 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
302 r'(?:www\.)?invidious\.kabi\.tk',
303 r'(?:www\.)?invidious\.mastodon\.host',
304 r'(?:www\.)?invidious\.zapashcanon\.fr',
305 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
306 r'(?:www\.)?invidious\.tinfoil-hat\.net',
307 r'(?:www\.)?invidious\.himiko\.cloud',
308 r'(?:www\.)?invidious\.reallyancient\.tech',
309 r'(?:www\.)?invidious\.tube',
310 r'(?:www\.)?invidiou\.site',
311 r'(?:www\.)?invidious\.site',
312 r'(?:www\.)?invidious\.xyz',
313 r'(?:www\.)?invidious\.nixnet\.xyz',
314 r'(?:www\.)?invidious\.048596\.xyz',
315 r'(?:www\.)?invidious\.drycat\.fr',
316 r'(?:www\.)?inv\.skyn3t\.in',
317 r'(?:www\.)?tube\.poal\.co',
318 r'(?:www\.)?tube\.connect\.cafe',
319 r'(?:www\.)?vid\.wxzm\.sx',
320 r'(?:www\.)?vid\.mint\.lgbt',
321 r'(?:www\.)?vid\.puffyan\.us',
322 r'(?:www\.)?yewtu\.be',
323 r'(?:www\.)?yt\.elukerio\.org',
324 r'(?:www\.)?yt\.lelux\.fi',
325 r'(?:www\.)?invidious\.ggc-project\.de',
326 r'(?:www\.)?yt\.maisputain\.ovh',
327 r'(?:www\.)?ytprivate\.com',
328 r'(?:www\.)?invidious\.13ad\.de',
329 r'(?:www\.)?invidious\.toot\.koeln',
330 r'(?:www\.)?invidious\.fdn\.fr',
331 r'(?:www\.)?watch\.nettohikari\.com',
332 r'(?:www\.)?invidious\.namazso\.eu',
333 r'(?:www\.)?invidious\.silkky\.cloud',
334 r'(?:www\.)?invidious\.exonip\.de',
335 r'(?:www\.)?invidious\.riverside\.rocks',
336 r'(?:www\.)?invidious\.blamefran\.net',
337 r'(?:www\.)?invidious\.moomoo\.de',
338 r'(?:www\.)?ytb\.trom\.tf',
339 r'(?:www\.)?yt\.cyberhost\.uk',
340 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
341 r'(?:www\.)?qklhadlycap4cnod\.onion',
342 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
343 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
344 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
345 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
346 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
347 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
348 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
349 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
350 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
351 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
352 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
353 r'(?:www\.)?piped\.kavin\.rocks',
354 r'(?:www\.)?piped\.silkky\.cloud',
355 r'(?:www\.)?piped\.tokhmi\.xyz',
356 r'(?:www\.)?piped\.moomoo\.me',
357 r'(?:www\.)?il\.ax',
358 r'(?:www\.)?piped\.syncpundit\.com',
359 r'(?:www\.)?piped\.mha\.fi',
360 r'(?:www\.)?piped\.mint\.lgbt',
361 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
362 )
363
cce889b9 364 def _initialize_consent(self):
365 cookies = self._get_cookies('https://www.youtube.com/')
366 if cookies.get('__Secure-3PSID'):
367 return
368 consent_id = None
369 consent = cookies.get('CONSENT')
370 if consent:
371 if 'YES' in consent.value:
372 return
373 consent_id = self._search_regex(
374 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
375 if not consent_id:
376 consent_id = random.randint(100, 999)
377 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 378
f3aa3c3f 379 def _initialize_pref(self):
380 cookies = self._get_cookies('https://www.youtube.com/')
381 pref_cookie = cookies.get('PREF')
382 pref = {}
383 if pref_cookie:
384 try:
385 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
386 except ValueError:
387 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 388 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 389 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
390
b2e8bc1b 391 def _real_initialize(self):
f3aa3c3f 392 self._initialize_pref()
cce889b9 393 self._initialize_consent()
a25bca9f 394 self._check_login_required()
395
396 def _check_login_required(self):
52efa4b3 397 if (self._LOGIN_REQUIRED
398 and self.get_param('cookiefile') is None
399 and self.get_param('cookiesfrombrowser') is None):
400 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 401
a0566bbf 402 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 403 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
404 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 405
000c15a4 406 def _get_default_ytcfg(self, client='web'):
407 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 408
000c15a4 409 def _get_innertube_host(self, client='web'):
410 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 411
000c15a4 412 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 413 # try_get but with fallback to default ytcfg client values when present
414 _func = lambda y: try_get(y, getter, expected_type)
415 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
416
000c15a4 417 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 418 return self._ytcfg_get_safe(
419 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
420 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 421
000c15a4 422 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 423 return self._ytcfg_get_safe(
424 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
425 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 426
000c15a4 427 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 428 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
429
000c15a4 430 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 431 context = get_first(
432 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 433 # Enforce language and tz for extraction
434 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
435 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 436 return context
437
cf87314d 438 _SAPISID = None
439
109dd3b2 440 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 441 time_now = round(time.time())
cf87314d 442 if self._SAPISID is None:
443 yt_cookies = self._get_cookies('https://www.youtube.com')
444 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
445 # See: https://github.com/yt-dlp/yt-dlp/issues/393
446 sapisid_cookie = dict_get(
447 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
448 if sapisid_cookie and sapisid_cookie.value:
449 self._SAPISID = sapisid_cookie.value
450 self.write_debug('Extracted SAPISID cookie')
451 # SAPISID cookie is required if not already present
452 if not yt_cookies.get('SAPISID'):
453 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
454 self._set_cookie(
455 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
456 else:
457 self._SAPISID = False
458 if not self._SAPISID:
459 return None
1974e99f 460 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
461 sapisidhash = hashlib.sha1(
86e5f3ed 462 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 463 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
464
465 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 466 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 467 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 468
109dd3b2 469 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 470 data.update(query)
11f9be09 471 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 472 real_headers.update({'content-type': 'application/json'})
473 if headers:
474 real_headers.update(headers)
545cc85d 475 return self._download_json(
86e5f3ed 476 f'https://{api_hostname or self._get_innertube_host(default_client)}/youtubei/v1/{ep}',
a5c56234 477 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 478 data=json.dumps(data).encode('utf8'), headers=real_headers,
5dbc77df 479 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
f4f751af 480
ac56cf38 481 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
482 data = self._search_regex(
86e5f3ed 483 (fr'{self._YT_INITIAL_DATA_RE}\s*{self._YT_INITIAL_BOUNDARY_RE}',
ac56cf38 484 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
485 if data:
486 return self._parse_json(data, item_id, fatal=fatal)
0c148415 487
99e9e001 488 @staticmethod
489 def _extract_session_index(*data):
490 """
491 Index of current account in account list.
492 See: https://github.com/yt-dlp/yt-dlp/pull/519
493 """
494 for ytcfg in data:
495 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
496 if session_index is not None:
497 return session_index
498
499 # Deprecated?
500 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
501 if ytcfg:
502 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
503 if token:
504 return token
99e9e001 505 if webpage:
506 return self._search_regex(
507 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
508 'identity token', default=None, fatal=False)
a1c5d2ca
M
509
510 @staticmethod
fe93e2c4 511 def _extract_account_syncid(*args):
8ea3f7b9 512 """
513 Extract syncId required to download private playlists of secondary channels
fe93e2c4 514 @params response and/or ytcfg
8ea3f7b9 515 """
fe93e2c4 516 for data in args:
517 # ytcfg includes channel_syncid if on secondary channel
518 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
519 if delegated_sid:
520 return delegated_sid
521 sync_ids = (try_get(
522 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 523 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 524 if len(sync_ids) >= 2 and sync_ids[1]:
525 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
526 # and just "user_syncid||" for primary channel. We only want the channel_syncid
527 return sync_ids[0]
a1c5d2ca 528
ac56cf38 529 @staticmethod
530 def _extract_visitor_data(*args):
531 """
532 Extracts visitorData from an API response or ytcfg
533 Appears to be used to track session state
534 """
9222c381 535 return get_first(
6c73052c 536 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 537 expected_type=str)
ac56cf38 538
99e9e001 539 @property
540 def is_authenticated(self):
541 return bool(self._generate_sapisidhash_header())
542
11f9be09 543 def extract_ytcfg(self, video_id, webpage):
8c54a305 544 if not webpage:
545 return {}
29f7c58a 546 return self._parse_json(
547 self._search_regex(
548 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 549 default='{}'), video_id, fatal=False) or {}
550
11f9be09 551 def generate_api_headers(
99e9e001 552 self, *, ytcfg=None, account_syncid=None, session_index=None,
553 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
554
11f9be09 555 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 556 headers = {
109dd3b2 557 'X-YouTube-Client-Name': compat_str(
11f9be09 558 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
559 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 560 'Origin': origin,
561 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
562 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 563 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 564 }
565 if session_index is None:
314ee305 566 session_index = self._extract_session_index(ytcfg)
567 if account_syncid or session_index is not None:
568 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 569
109dd3b2 570 auth = self._generate_sapisidhash_header(origin)
f4f751af 571 if auth is not None:
572 headers['Authorization'] = auth
109dd3b2 573 headers['X-Origin'] = origin
99e9e001 574 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 575
a25bca9f 576 def _download_ytcfg(self, client, video_id):
577 url = {
578 'web': 'https://www.youtube.com',
579 'web_music': 'https://music.youtube.com',
580 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
581 }.get(client)
582 if not url:
583 return {}
584 webpage = self._download_webpage(
585 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
586 return self.extract_ytcfg(video_id, webpage) or {}
587
2d6659b9 588 @staticmethod
589 def _build_api_continuation_query(continuation, ctp=None):
590 query = {
591 'continuation': continuation
592 }
593 # TODO: Inconsistency with clickTrackingParams.
594 # Currently we have a fixed ctp contained within context (from ytcfg)
595 # and a ctp in root query for continuation.
596 if ctp:
597 query['clickTracking'] = {'clickTrackingParams': ctp}
598 return query
599
2d6659b9 600 @classmethod
601 def _extract_next_continuation_data(cls, renderer):
602 next_continuation = try_get(
603 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
604 lambda x: x['continuation']['reloadContinuationData']), dict)
605 if not next_continuation:
606 return
607 continuation = next_continuation.get('continuation')
608 if not continuation:
609 return
610 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 611 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 612
613 @classmethod
614 def _extract_continuation_ep_data(cls, continuation_ep: dict):
615 if isinstance(continuation_ep, dict):
616 continuation = try_get(
617 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
618 if not continuation:
619 return
620 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 621 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 622
623 @classmethod
624 def _extract_continuation(cls, renderer):
625 next_continuation = cls._extract_next_continuation_data(renderer)
626 if next_continuation:
627 return next_continuation
fe93e2c4 628
2d6659b9 629 contents = []
630 for key in ('contents', 'items'):
631 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 632
2d6659b9 633 for content in contents:
634 if not isinstance(content, dict):
635 continue
636 continuation_ep = try_get(
637 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
638 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
639 dict)
640 continuation = cls._extract_continuation_ep_data(continuation_ep)
641 if continuation:
642 return continuation
643
fe93e2c4 644 @classmethod
645 def _extract_alerts(cls, data):
109dd3b2 646 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
647 if not isinstance(alert_dict, dict):
648 continue
649 for alert in alert_dict.values():
650 alert_type = alert.get('type')
651 if not alert_type:
652 continue
052e1350 653 message = cls._get_text(alert, 'text')
109dd3b2 654 if message:
655 yield alert_type, message
656
c0ac49bc 657 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 658 errors = []
659 warnings = []
660 for alert_type, alert_message in alerts:
641ad5d8 661 if alert_type.lower() == 'error' and fatal:
109dd3b2 662 errors.append([alert_type, alert_message])
663 else:
664 warnings.append([alert_type, alert_message])
665
666 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 667 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 668 if errors:
669 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
670
671 def _extract_and_report_alerts(self, data, *args, **kwargs):
672 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
673
47193e02 674 def _extract_badges(self, renderer: dict):
675 badges = set()
676 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
677 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
678 if label:
679 badges.add(label.lower())
680 return badges
681
682 @staticmethod
052e1350 683 def _get_text(data, *path_list, max_runs=None):
684 for path in path_list or [None]:
685 if path is None:
686 obj = [data]
687 else:
688 obj = traverse_obj(data, path, default=[])
689 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
690 obj = [obj]
691 for item in obj:
692 text = try_get(item, lambda x: x['simpleText'], compat_str)
693 if text:
694 return text
695 runs = try_get(item, lambda x: x['runs'], list) or []
696 if not runs and isinstance(item, list):
697 runs = item
698
699 runs = runs[:min(len(runs), max_runs or len(runs))]
700 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
701 if text:
702 return text
47193e02 703
f0d785d3 704 def _get_count(self, data, *path_list):
705 count_text = self._get_text(data, *path_list) or ''
706 count = parse_count(count_text)
707 if count is None:
708 count = str_to_int(
709 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
710 return count
711
a709d873 712 @staticmethod
713 def _extract_thumbnails(data, *path_list):
714 """
715 Extract thumbnails from thumbnails dict
716 @param path_list: path list to level that contains 'thumbnails' key
717 """
718 thumbnails = []
719 for path in path_list or [()]:
720 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
721 thumbnail_url = url_or_none(thumbnail.get('url'))
722 if not thumbnail_url:
723 continue
724 # Sometimes youtube gives a wrong thumbnail URL. See:
725 # https://github.com/yt-dlp/yt-dlp/issues/233
726 # https://github.com/ytdl-org/youtube-dl/issues/28023
727 if 'maxresdefault' in thumbnail_url:
728 thumbnail_url = thumbnail_url.split('?')[0]
729 thumbnails.append({
730 'url': thumbnail_url,
731 'height': int_or_none(thumbnail.get('height')),
732 'width': int_or_none(thumbnail.get('width')),
733 })
734 return thumbnails
735
f3aa3c3f 736 @staticmethod
737 def extract_relative_time(relative_time_text):
738 """
739 Extracts a relative time from string and converts to dt object
f0d785d3 740 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 741 """
f0d785d3 742 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 743 if mobj:
f0d785d3 744 start = mobj.group('start')
745 if start:
746 return datetime_from_str(start)
f3aa3c3f 747 try:
f0d785d3 748 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 749 except ValueError:
750 return None
751
752 def _extract_time_text(self, renderer, *path_list):
a25bca9f 753 """@returns (timestamp, time_text)"""
f3aa3c3f 754 text = self._get_text(renderer, *path_list) or ''
755 dt = self.extract_relative_time(text)
756 timestamp = None
757 if isinstance(dt, datetime.datetime):
758 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 759
760 if timestamp is None:
761 timestamp = (
762 unified_timestamp(text) or unified_timestamp(
763 self._search_regex(
17322130 764 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 765 text.lower(), 'time text', default=None)))
f0d785d3 766
f3aa3c3f 767 if text and timestamp is None:
17322130 768 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 769 return timestamp, text
770
109dd3b2 771 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
772 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 773 default_client='web'):
109dd3b2 774 response = None
775 last_error = None
776 count = -1
777 retries = self.get_param('extractor_retries', 3)
778 if check_get_keys is None:
779 check_get_keys = []
780 while count < retries:
781 count += 1
782 if last_error:
c0ac49bc 783 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 784 try:
785 response = self._call_api(
786 ep=ep, fatal=True, headers=headers,
787 video_id=item_id, query=query,
788 context=self._extract_context(ytcfg, default_client),
789 api_key=self._extract_api_key(ytcfg, default_client),
790 api_hostname=api_hostname, default_client=default_client,
791 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
792 except ExtractorError as e:
9c0d7f49 793 if isinstance(e.cause, network_exceptions):
87e8e8a7 794 if isinstance(e.cause, compat_HTTPError):
795 first_bytes = e.cause.read(512)
796 if not is_html(first_bytes):
797 yt_error = try_get(
798 self._parse_json(
799 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
800 lambda x: x['error']['message'], compat_str)
801 if yt_error:
802 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 803 # Downloading page may result in intermittent 5xx HTTP error
804 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 805 # We also want to catch all other network exceptions since errors in later pages can be troublesome
806 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
807 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 808 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 809 if count < retries:
810 continue
109dd3b2 811 if fatal:
812 raise
813 else:
814 self.report_warning(error_to_compat_str(e))
815 return
816
817 else:
109dd3b2 818 try:
ac56cf38 819 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 820 except ExtractorError as e:
c0ac49bc 821 # YouTube servers may return errors we want to retry on in a 200 OK response
822 # See: https://github.com/yt-dlp/yt-dlp/issues/839
823 if 'unknown error' in e.msg.lower():
824 last_error = e.msg
825 continue
109dd3b2 826 if fatal:
827 raise
828 self.report_warning(error_to_compat_str(e))
829 return
830 if not check_get_keys or dict_get(response, check_get_keys):
831 break
832 # Youtube sometimes sends incomplete data
833 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
834 last_error = 'Incomplete data received'
835 if count >= retries:
836 if fatal:
837 raise ExtractorError(last_error)
838 else:
839 self.report_warning(last_error)
840 return
841 return response
842
9297939e 843 @staticmethod
844 def is_music_url(url):
845 return re.match(r'https?://music\.youtube\.com/', url) is not None
846
30a074c2 847 def _extract_video(self, renderer):
848 video_id = renderer.get('videoId')
052e1350 849 title = self._get_text(renderer, 'title')
850 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 851 duration = parse_duration(self._get_text(
852 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 853 if duration is None:
854 duration = parse_duration(self._search_regex(
855 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
856 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
857 video_id, default=None, group='duration'))
858
f0d785d3 859 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 860
052e1350 861 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 862 channel_id = traverse_obj(
a44ca5a4 863 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
864 expected_type=str, get_all=False)
f3aa3c3f 865 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
866 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
867 overlay_style = traverse_obj(
a44ca5a4 868 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
869 get_all=False, expected_type=str)
f3aa3c3f 870 badges = self._extract_badges(renderer)
a709d873 871 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 872 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 873 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
874 expected_type=str)) or ''
fd2ad7cb 875 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 876 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 877 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 878
30a074c2 879 return {
39ed931e 880 '_type': 'url',
30a074c2 881 'ie_key': YoutubeIE.ie_key(),
882 'id': video_id,
fd2ad7cb 883 'url': url,
30a074c2 884 'title': title,
885 'description': description,
886 'duration': duration,
887 'view_count': view_count,
888 'uploader': uploader,
f3aa3c3f 889 'channel_id': channel_id,
a709d873 890 'thumbnails': thumbnails,
a44ca5a4 891 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
892 if self._configuration_arg('approximate_date', ie_key='youtubetab')
893 else None),
f3aa3c3f 894 'live_status': ('is_upcoming' if scheduled_timestamp is not None
895 else 'was_live' if 'streamed' in time_text.lower()
896 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
897 else None),
898 'release_timestamp': scheduled_timestamp,
899 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 900 }
901
0c148415 902
360e1ca5 903class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 904 IE_DESC = 'YouTube'
cb7dfeea 905 _VALID_URL = r"""(?x)^
c5e8d7af 906 (
edb53e2d 907 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 908 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
909 (?:www\.)?deturl\.com/www\.youtube\.com|
910 (?:www\.)?pwnyoutube\.com|
911 (?:www\.)?hooktube\.com|
912 (?:www\.)?yourepeat\.com|
913 tube\.majestyc\.net|
914 %(invidious)s|
915 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
916 (?:.*?\#/)? # handle anchor (#/) redirect urls
917 (?: # the various things that can precede the ID:
b6ce9bb0 918 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 919 |(?: # or the v= param in all its forms
f7000f3a 920 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 921 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 922 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
923 v=
924 )
f4b05232 925 ))
cbaed4bb
S
926 |(?:
927 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
928 vid\.plus| # or vid.plus/xxxx
929 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 930 %(invidious)s
cbaed4bb 931 )/
edb53e2d 932 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 933 )
c5e8d7af 934 )? # all until now is optional -> you can pass the naked ID
201c1459 935 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 936 (?(1).+)? # if we found the ID, everything can follow
9297939e 937 (?:\#|$)""" % {
d9190e44 938 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 939 }
e40c758c 940 _PLAYER_INFO_RE = (
cc2db878 941 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
942 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$',
545cc85d 943 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 944 )
2c62dc26 945 _formats = {
c2d3cb4c 946 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
947 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
948 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
949 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
950 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
951 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
952 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
953 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 954 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 955 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
956 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
957 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
958 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
959 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
960 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 961 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 962 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
963 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 964
965
966 # 3D videos
c2d3cb4c 967 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
968 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
969 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
970 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 971 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
972 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
973 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 974
96fb5605 975 # Apple HTTP Live Streaming
11f12195 976 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 977 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
978 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
979 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
980 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
981 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 982 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
983 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
984
985 # DASH mp4 video
d23028a8
S
986 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
989 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
990 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 991 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
992 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
993 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
994 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
995 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
996 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
997 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 998
f6f1fc92 999 # Dash mp4 audio
d23028a8
S
1000 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1001 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1002 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1003 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1004 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1005 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1006 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1007
1008 # Dash webm
d23028a8
S
1009 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1010 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1011 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1012 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1013 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1014 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1015 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1016 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1019 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1020 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1023 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1024 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1025 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1026 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1027 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1028 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1029 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1030 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1031
1032 # Dash webm audio
d23028a8
S
1033 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1034 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1035
0857baad 1036 # Dash webm audio with opus inside
d23028a8
S
1037 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1038 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1039 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1040
ce6b9a2d
PH
1041 # RTMP (unnamed)
1042 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1043
1044 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1045 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1046 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1047 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1048 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1049 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1050 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1051 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1052 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1053 }
29f7c58a 1054 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1055
fd5c4aab
S
1056 _GEO_BYPASS = False
1057
78caa52a 1058 IE_NAME = 'youtube'
2eb88d95
PH
1059 _TESTS = [
1060 {
2d3d2997 1061 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1062 'info_dict': {
1063 'id': 'BaW_jenozKc',
1064 'ext': 'mp4',
3867038a 1065 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1066 'uploader': 'Philipp Hagemeister',
1067 'uploader_id': 'phihag',
ec85ded8 1068 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1069 'channel': 'Philipp Hagemeister',
dd4c4492
S
1070 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1071 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1072 'upload_date': '20121002',
ff9f925b 1073 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1074 'categories': ['Science & Technology'],
3867038a 1075 'tags': ['youtube-dl'],
556dbe7f 1076 'duration': 10,
dbdaaa23 1077 'view_count': int,
3e7c1224 1078 'like_count': int,
ff9f925b 1079 'availability': 'public',
1080 'playable_in_embed': True,
1081 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1082 'live_status': 'not_live',
1083 'age_limit': 0,
7c80519c 1084 'start_time': 1,
297a564b 1085 'end_time': 9,
6c73052c 1086 'channel_follower_count': int
2eb88d95 1087 }
0e853ca4 1088 },
fccd3771 1089 {
4bc3a23e
PH
1090 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1091 'note': 'Embed-only video (#1746)',
1092 'info_dict': {
1093 'id': 'yZIXLfi8CZQ',
1094 'ext': 'mp4',
1095 'upload_date': '20120608',
1096 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1097 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1098 'uploader': 'SET India',
94bfcd23 1099 'uploader_id': 'setindia',
ec85ded8 1100 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1101 'age_limit': 18,
545cc85d 1102 },
1103 'skip': 'Private video',
fccd3771 1104 },
11b56058 1105 {
8bdd16b4 1106 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1107 'note': 'Use the first video ID in the URL',
1108 'info_dict': {
1109 'id': 'BaW_jenozKc',
1110 'ext': 'mp4',
3867038a 1111 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1112 'uploader': 'Philipp Hagemeister',
1113 'uploader_id': 'phihag',
ec85ded8 1114 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1115 'channel': 'Philipp Hagemeister',
1116 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1117 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1118 'upload_date': '20121002',
976ae3ea 1119 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1120 'categories': ['Science & Technology'],
3867038a 1121 'tags': ['youtube-dl'],
556dbe7f 1122 'duration': 10,
dbdaaa23 1123 'view_count': int,
11b56058 1124 'like_count': int,
976ae3ea 1125 'availability': 'public',
1126 'playable_in_embed': True,
1127 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1128 'live_status': 'not_live',
1129 'age_limit': 0,
6c73052c 1130 'channel_follower_count': int
34a7de29
S
1131 },
1132 'params': {
1133 'skip_download': True,
1134 },
11b56058 1135 },
dd27fd17 1136 {
2d3d2997 1137 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1138 'note': '256k DASH audio (format 141) via DASH manifest',
1139 'info_dict': {
1140 'id': 'a9LDPn-MO4I',
1141 'ext': 'm4a',
1142 'upload_date': '20121002',
1143 'uploader_id': '8KVIDEO',
ec85ded8 1144 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1145 'description': '',
1146 'uploader': '8KVIDEO',
1147 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1148 },
4bc3a23e
PH
1149 'params': {
1150 'youtube_include_dash_manifest': True,
1151 'format': '141',
4919603f 1152 },
de3c7fe0 1153 'skip': 'format 141 not served anymore',
dd27fd17 1154 },
8bdd16b4 1155 # DASH manifest with encrypted signature
1156 {
1157 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1158 'info_dict': {
1159 'id': 'IB3lcPjvWLA',
1160 'ext': 'm4a',
1161 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1162 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1163 'duration': 244,
1164 'uploader': 'AfrojackVEVO',
1165 'uploader_id': 'AfrojackVEVO',
1166 'upload_date': '20131011',
cc2db878 1167 'abr': 129.495,
976ae3ea 1168 'like_count': int,
1169 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1170 'playable_in_embed': True,
1171 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1172 'view_count': int,
1173 'track': 'The Spark',
1174 'live_status': 'not_live',
1175 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1176 'channel': 'Afrojack',
1177 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1178 'tags': 'count:19',
1179 'availability': 'public',
1180 'categories': ['Music'],
1181 'age_limit': 0,
1182 'alt_title': 'The Spark',
6c73052c 1183 'channel_follower_count': int
8bdd16b4 1184 },
1185 'params': {
1186 'youtube_include_dash_manifest': True,
1187 'format': '141/bestaudio[ext=m4a]',
1188 },
1189 },
65c2fde2 1190 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1191 {
65c2fde2 1192 'note': 'Embed allowed age-gate video',
2d3d2997 1193 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1194 'info_dict': {
1195 'id': 'HtVdAasjOgU',
1196 'ext': 'mp4',
1197 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1198 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1199 'duration': 142,
c522adb1
JMF
1200 'uploader': 'The Witcher',
1201 'uploader_id': 'WitcherGame',
ec85ded8 1202 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1203 'upload_date': '20140605',
34952f09 1204 'age_limit': 18,
976ae3ea 1205 'categories': ['Gaming'],
1206 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1207 'availability': 'needs_auth',
1208 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1209 'like_count': int,
1210 'channel': 'The Witcher',
1211 'live_status': 'not_live',
1212 'tags': 'count:17',
1213 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1214 'playable_in_embed': True,
1215 'view_count': int,
6c73052c 1216 'channel_follower_count': int
c522adb1
JMF
1217 },
1218 },
65c2fde2 1219 {
1220 'note': 'Age-gate video with embed allowed in public site',
1221 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1222 'info_dict': {
1223 'id': 'HsUATh_Nc2U',
1224 'ext': 'mp4',
1225 'title': 'Godzilla 2 (Official Video)',
1226 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1227 'upload_date': '20200408',
1228 'uploader_id': 'FlyingKitty900',
1229 'uploader': 'FlyingKitty',
1230 'age_limit': 18,
976ae3ea 1231 'availability': 'needs_auth',
1232 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1233 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1234 'channel': 'FlyingKitty',
1235 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1236 'view_count': int,
1237 'categories': ['Entertainment'],
1238 'live_status': 'not_live',
1239 'tags': ['Flyingkitty', 'godzilla 2'],
1240 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1241 'like_count': int,
1242 'duration': 177,
1243 'playable_in_embed': True,
6c73052c 1244 'channel_follower_count': int
65c2fde2 1245 },
1246 },
1247 {
1248 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1249 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1250 'info_dict': {
1251 'id': 'Tq92D6wQ1mg',
1252 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1253 'ext': 'mp4',
17322130 1254 'upload_date': '20191228',
65c2fde2 1255 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1256 'uploader': 'Projekt Melody',
1257 'description': 'md5:17eccca93a786d51bc67646756894066',
1258 'age_limit': 18,
976ae3ea 1259 'like_count': int,
1260 'availability': 'needs_auth',
1261 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1262 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1263 'view_count': int,
1264 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1265 'channel': 'Projekt Melody',
1266 'live_status': 'not_live',
1267 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1268 'playable_in_embed': True,
1269 'categories': ['Entertainment'],
1270 'duration': 106,
1271 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1272 'channel_follower_count': int
65c2fde2 1273 },
1274 },
1275 {
1276 'note': 'Non-Agegated non-embeddable video',
1277 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1278 'info_dict': {
1279 'id': 'MeJVWBSsPAY',
1280 'ext': 'mp4',
1281 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1282 'uploader': 'Herr Lurik',
1283 'uploader_id': 'st3in234',
1284 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1285 'upload_date': '20130730',
976ae3ea 1286 'track': 'Such mich find mich',
1287 'age_limit': 0,
1288 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1289 'like_count': int,
1290 'playable_in_embed': False,
1291 'creator': 'OOMPH!',
1292 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1293 'view_count': int,
1294 'alt_title': 'Such mich find mich',
1295 'duration': 210,
1296 'channel': 'Herr Lurik',
1297 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1298 'categories': ['Music'],
1299 'availability': 'public',
1300 'uploader_url': 'http://www.youtube.com/user/st3in234',
1301 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1302 'live_status': 'not_live',
1303 'artist': 'OOMPH!',
6c73052c 1304 'channel_follower_count': int
65c2fde2 1305 },
1306 },
1307 {
1308 'note': 'Non-bypassable age-gated video',
1309 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1310 'only_matching': True,
1311 },
8bdd16b4 1312 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1313 # YouTube Red ad is not captured for creator
1314 {
1315 'url': '__2ABJjxzNo',
1316 'info_dict': {
1317 'id': '__2ABJjxzNo',
1318 'ext': 'mp4',
1319 'duration': 266,
1320 'upload_date': '20100430',
1321 'uploader_id': 'deadmau5',
1322 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1323 'creator': 'deadmau5',
1324 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1325 'uploader': 'deadmau5',
1326 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1327 'alt_title': 'Some Chords',
976ae3ea 1328 'availability': 'public',
1329 'tags': 'count:14',
1330 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1331 'view_count': int,
1332 'live_status': 'not_live',
1333 'channel': 'deadmau5',
1334 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1335 'like_count': int,
1336 'track': 'Some Chords',
1337 'artist': 'deadmau5',
1338 'playable_in_embed': True,
1339 'age_limit': 0,
1340 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1341 'categories': ['Music'],
1342 'album': 'Some Chords',
6c73052c 1343 'channel_follower_count': int
8bdd16b4 1344 },
1345 'expected_warnings': [
1346 'DASH manifest missing',
1347 ]
1348 },
067aa17e 1349 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1350 {
1351 'url': 'lqQg6PlCWgI',
1352 'info_dict': {
1353 'id': 'lqQg6PlCWgI',
1354 'ext': 'mp4',
556dbe7f 1355 'duration': 6085,
90227264 1356 'upload_date': '20150827',
cbe2bd91 1357 'uploader_id': 'olympic',
ec85ded8 1358 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1359 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1360 'uploader': 'Olympics',
cbe2bd91 1361 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1362 'like_count': int,
1363 'release_timestamp': 1343767800,
1364 'playable_in_embed': True,
1365 'categories': ['Sports'],
1366 'release_date': '20120731',
1367 'channel': 'Olympics',
1368 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1369 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1370 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1371 'age_limit': 0,
1372 'availability': 'public',
1373 'live_status': 'was_live',
1374 'view_count': int,
1375 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1376 'channel_follower_count': int
cbe2bd91
PH
1377 },
1378 'params': {
1379 'skip_download': 'requires avconv',
e52a40ab 1380 }
cbe2bd91 1381 },
6271f1ca
PH
1382 # Non-square pixels
1383 {
1384 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1385 'info_dict': {
1386 'id': '_b-2C3KPAM0',
1387 'ext': 'mp4',
1388 'stretched_ratio': 16 / 9.,
556dbe7f 1389 'duration': 85,
6271f1ca
PH
1390 'upload_date': '20110310',
1391 'uploader_id': 'AllenMeow',
ec85ded8 1392 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1393 '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 1394 'uploader': '孫ᄋᄅ',
6271f1ca 1395 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1396 'playable_in_embed': True,
1397 'channel': '孫ᄋᄅ',
1398 'age_limit': 0,
1399 'tags': 'count:11',
1400 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1401 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1402 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1403 'view_count': int,
1404 'categories': ['People & Blogs'],
1405 'like_count': int,
1406 'live_status': 'not_live',
1407 'availability': 'unlisted',
6c73052c 1408 'channel_follower_count': int
6271f1ca 1409 },
06b491eb
S
1410 },
1411 # url_encoded_fmt_stream_map is empty string
1412 {
1413 'url': 'qEJwOuvDf7I',
1414 'info_dict': {
1415 'id': 'qEJwOuvDf7I',
f57b7835 1416 'ext': 'webm',
06b491eb
S
1417 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1418 'description': '',
1419 'upload_date': '20150404',
1420 'uploader_id': 'spbelect',
1421 'uploader': 'Наблюдатели Петербурга',
1422 },
1423 'params': {
1424 'skip_download': 'requires avconv',
e323cf3f
S
1425 },
1426 'skip': 'This live event has ended.',
06b491eb 1427 },
067aa17e 1428 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1429 {
1430 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1431 'info_dict': {
1432 'id': 'FIl7x6_3R5Y',
eb6793ba 1433 'ext': 'webm',
da77d856
S
1434 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1435 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1436 'duration': 220,
da77d856
S
1437 'upload_date': '20150625',
1438 'uploader_id': 'dorappi2000',
ec85ded8 1439 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1440 'uploader': 'dorappi2000',
eb6793ba 1441 'formats': 'mincount:31',
da77d856 1442 },
eb6793ba 1443 'skip': 'not actual anymore',
2ee8f5d8 1444 },
8a1a26ce
YCH
1445 # DASH manifest with segment_list
1446 {
1447 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1448 'md5': '8ce563a1d667b599d21064e982ab9e31',
1449 'info_dict': {
1450 'id': 'CsmdDsKjzN8',
1451 'ext': 'mp4',
17ee98e1 1452 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1453 'uploader': 'Airtek',
1454 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1455 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1456 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1457 },
1458 'params': {
1459 'youtube_include_dash_manifest': True,
1460 'format': '135', # bestvideo
be49068d
S
1461 },
1462 'skip': 'This live event has ended.',
2ee8f5d8 1463 },
cf7e015f
S
1464 {
1465 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1466 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1467 'info_dict': {
545cc85d 1468 'id': 'jvGDaLqkpTg',
1469 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1470 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1471 },
1472 'playlist': [{
1473 'info_dict': {
545cc85d 1474 'id': 'jvGDaLqkpTg',
cf7e015f 1475 'ext': 'mp4',
545cc85d 1476 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1477 'description': 'md5:e03b909557865076822aa169218d6a5d',
1478 'duration': 10643,
1479 'upload_date': '20161111',
1480 'uploader': 'Team PGP',
1481 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1482 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1483 },
1484 }, {
1485 'info_dict': {
545cc85d 1486 'id': '3AKt1R1aDnw',
cf7e015f 1487 'ext': 'mp4',
545cc85d 1488 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1489 'description': 'md5:e03b909557865076822aa169218d6a5d',
1490 'duration': 10991,
1491 'upload_date': '20161111',
1492 'uploader': 'Team PGP',
1493 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1494 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1495 },
1496 }, {
1497 'info_dict': {
545cc85d 1498 'id': 'RtAMM00gpVc',
cf7e015f 1499 'ext': 'mp4',
545cc85d 1500 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1501 'description': 'md5:e03b909557865076822aa169218d6a5d',
1502 'duration': 10995,
1503 'upload_date': '20161111',
1504 'uploader': 'Team PGP',
1505 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1506 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1507 },
1508 }, {
1509 'info_dict': {
545cc85d 1510 'id': '6N2fdlP3C5U',
cf7e015f 1511 'ext': 'mp4',
545cc85d 1512 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1513 'description': 'md5:e03b909557865076822aa169218d6a5d',
1514 'duration': 10990,
1515 'upload_date': '20161111',
1516 'uploader': 'Team PGP',
1517 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1518 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1519 },
1520 }],
1521 'params': {
1522 'skip_download': True,
1523 },
65c2fde2 1524 'skip': 'Not multifeed anymore',
cbaed4bb 1525 },
f9f49d87 1526 {
067aa17e 1527 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1528 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1529 'info_dict': {
1530 'id': 'gVfLd0zydlo',
1531 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1532 },
1533 'playlist_count': 2,
be49068d 1534 'skip': 'Not multifeed anymore',
f9f49d87 1535 },
cbaed4bb 1536 {
2d3d2997 1537 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1538 'only_matching': True,
0e49d9a6 1539 },
6d4fc66b 1540 {
2d3d2997 1541 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1542 'only_matching': True,
1543 },
0e49d9a6 1544 {
067aa17e 1545 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1546 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1547 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1548 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1549 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1550 'info_dict': {
1551 'id': 'lsguqyKfVQg',
1552 'ext': 'mp4',
1553 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1554 'alt_title': 'Dark Walk',
0e49d9a6 1555 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1556 'duration': 133,
0e49d9a6
LL
1557 'upload_date': '20151119',
1558 'uploader_id': 'IronSoulElf',
ec85ded8 1559 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1560 'uploader': 'IronSoulElf',
11f9be09 1561 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1562 'track': 'Dark Walk',
1563 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1564 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1565 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1566 'categories': ['Film & Animation'],
1567 'view_count': int,
1568 'live_status': 'not_live',
1569 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1570 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1571 'tags': 'count:13',
1572 'availability': 'public',
1573 'channel': 'IronSoulElf',
1574 'playable_in_embed': True,
1575 'like_count': int,
1576 'age_limit': 0,
6c73052c 1577 'channel_follower_count': int
0e49d9a6
LL
1578 },
1579 'params': {
1580 'skip_download': True,
1581 },
1582 },
61f92af1 1583 {
067aa17e 1584 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1585 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1586 'only_matching': True,
1587 },
313dfc45
LL
1588 {
1589 # Video with yt:stretch=17:0
1590 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1591 'info_dict': {
1592 'id': 'Q39EVAstoRM',
1593 'ext': 'mp4',
1594 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1595 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1596 'upload_date': '20151107',
1597 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1598 'uploader': 'CH GAMER DROID',
1599 },
1600 'params': {
1601 'skip_download': True,
1602 },
be49068d 1603 'skip': 'This video does not exist.',
313dfc45 1604 },
201c1459 1605 {
1606 # Video with incomplete 'yt:stretch=16:'
1607 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1608 'only_matching': True,
1609 },
7caf9830
S
1610 {
1611 # Video licensed under Creative Commons
1612 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1613 'info_dict': {
1614 'id': 'M4gD1WSo5mA',
1615 'ext': 'mp4',
1616 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1617 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1618 'duration': 721,
17322130 1619 'upload_date': '20150128',
7caf9830 1620 'uploader_id': 'BerkmanCenter',
ec85ded8 1621 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1622 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1623 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1624 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1625 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1626 'like_count': int,
1627 'age_limit': 0,
1628 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1629 'channel': 'The Berkman Klein Center for Internet & Society',
1630 'availability': 'public',
1631 'view_count': int,
1632 'categories': ['Education'],
1633 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1634 'live_status': 'not_live',
1635 'playable_in_embed': True,
6c73052c 1636 'channel_follower_count': int
7caf9830
S
1637 },
1638 'params': {
1639 'skip_download': True,
1640 },
1641 },
fd050249
S
1642 {
1643 # Channel-like uploader_url
1644 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1645 'info_dict': {
1646 'id': 'eQcmzGIKrzg',
1647 'ext': 'mp4',
1648 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1649 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1650 'duration': 4060,
17322130 1651 'upload_date': '20151120',
eb6793ba 1652 'uploader': 'Bernie Sanders',
fd050249 1653 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1654 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1655 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1656 'playable_in_embed': True,
1657 'tags': 'count:12',
1658 'like_count': int,
1659 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1660 'age_limit': 0,
1661 'availability': 'public',
1662 'categories': ['News & Politics'],
1663 'channel': 'Bernie Sanders',
1664 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1665 'view_count': int,
1666 'live_status': 'not_live',
1667 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1668 'channel_follower_count': int
fd050249
S
1669 },
1670 'params': {
1671 'skip_download': True,
1672 },
1673 },
040ac686
S
1674 {
1675 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1676 'only_matching': True,
7f29cf54
S
1677 },
1678 {
067aa17e 1679 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1680 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1681 'only_matching': True,
6496ccb4
S
1682 },
1683 {
1684 # Rental video preview
1685 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1686 'info_dict': {
1687 'id': 'uGpuVWrhIzE',
1688 'ext': 'mp4',
1689 'title': 'Piku - Trailer',
1690 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1691 'upload_date': '20150811',
1692 'uploader': 'FlixMatrix',
1693 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1694 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1695 'license': 'Standard YouTube License',
1696 },
1697 'params': {
1698 'skip_download': True,
1699 },
eb6793ba 1700 'skip': 'This video is not available.',
022a5d66 1701 },
12afdc2a
S
1702 {
1703 # YouTube Red video with episode data
1704 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1705 'info_dict': {
1706 'id': 'iqKdEhx-dD4',
1707 'ext': 'mp4',
1708 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1709 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1710 'duration': 2085,
12afdc2a
S
1711 'upload_date': '20170118',
1712 'uploader': 'Vsauce',
1713 'uploader_id': 'Vsauce',
1714 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1715 'series': 'Mind Field',
1716 'season_number': 1,
1717 'episode_number': 1,
976ae3ea 1718 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1719 'tags': 'count:12',
1720 'view_count': int,
1721 'availability': 'public',
1722 'age_limit': 0,
1723 'channel': 'Vsauce',
1724 'episode': 'Episode 1',
1725 'categories': ['Entertainment'],
1726 'season': 'Season 1',
1727 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1728 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1729 'like_count': int,
1730 'playable_in_embed': True,
1731 'live_status': 'not_live',
6c73052c 1732 'channel_follower_count': int
12afdc2a
S
1733 },
1734 'params': {
1735 'skip_download': True,
1736 },
1737 'expected_warnings': [
1738 'Skipping DASH manifest',
1739 ],
1740 },
c7121fa7
S
1741 {
1742 # The following content has been identified by the YouTube community
1743 # as inappropriate or offensive to some audiences.
1744 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1745 'info_dict': {
1746 'id': '6SJNVb0GnPI',
1747 'ext': 'mp4',
1748 'title': 'Race Differences in Intelligence',
1749 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1750 'duration': 965,
1751 'upload_date': '20140124',
1752 'uploader': 'New Century Foundation',
1753 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1754 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1755 },
1756 'params': {
1757 'skip_download': True,
1758 },
545cc85d 1759 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1760 },
022a5d66
S
1761 {
1762 # itag 212
1763 'url': '1t24XAntNCY',
1764 'only_matching': True,
fd5c4aab
S
1765 },
1766 {
1767 # geo restricted to JP
1768 'url': 'sJL6WA-aGkQ',
1769 'only_matching': True,
1770 },
cd5a74a2
S
1771 {
1772 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1773 'only_matching': True,
1774 },
bc2ca1bb 1775 {
1776 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1777 'only_matching': True,
1778 },
1779 {
1780 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1781 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1782 'only_matching': True,
1783 },
825cd268
RA
1784 {
1785 # DRM protected
1786 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1787 'only_matching': True,
4fe54c12
S
1788 },
1789 {
1790 # Video with unsupported adaptive stream type formats
1791 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1792 'info_dict': {
1793 'id': 'Z4Vy8R84T1U',
1794 'ext': 'mp4',
1795 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1796 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1797 'duration': 433,
1798 'upload_date': '20130923',
1799 'uploader': 'Amelia Putri Harwita',
1800 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1801 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1802 'formats': 'maxcount:10',
1803 },
1804 'params': {
1805 'skip_download': True,
1806 'youtube_include_dash_manifest': False,
1807 },
5429d6a9 1808 'skip': 'not actual anymore',
5caabd3c 1809 },
1810 {
822b9d9c 1811 # Youtube Music Auto-generated description
5caabd3c 1812 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1813 'info_dict': {
1814 'id': 'MgNrAu2pzNs',
1815 'ext': 'mp4',
1816 'title': 'Voyeur Girl',
1817 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1818 'upload_date': '20190312',
5429d6a9
S
1819 'uploader': 'Stephen - Topic',
1820 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1821 'artist': 'Stephen',
1822 'track': 'Voyeur Girl',
1823 'album': 'it\'s too much love to know my dear',
1824 'release_date': '20190313',
1825 'release_year': 2019,
976ae3ea 1826 'alt_title': 'Voyeur Girl',
1827 'view_count': int,
1828 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1829 'playable_in_embed': True,
1830 'like_count': int,
1831 'categories': ['Music'],
1832 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1833 'channel': 'Stephen',
1834 'availability': 'public',
1835 'creator': 'Stephen',
1836 'duration': 169,
1837 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1838 'age_limit': 0,
1839 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1840 'tags': 'count:11',
1841 'live_status': 'not_live',
6c73052c 1842 'channel_follower_count': int
5caabd3c 1843 },
1844 'params': {
1845 'skip_download': True,
1846 },
1847 },
66b48727
RA
1848 {
1849 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1850 'only_matching': True,
1851 },
011e75e6
S
1852 {
1853 # invalid -> valid video id redirection
1854 'url': 'DJztXj2GPfl',
1855 'info_dict': {
1856 'id': 'DJztXj2GPfk',
1857 'ext': 'mp4',
1858 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1859 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1860 'upload_date': '20090125',
1861 'uploader': 'Prochorowka',
1862 'uploader_id': 'Prochorowka',
1863 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1864 'artist': 'Panjabi MC',
1865 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1866 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1867 },
1868 'params': {
1869 'skip_download': True,
1870 },
545cc85d 1871 'skip': 'Video unavailable',
ea74e00b
DP
1872 },
1873 {
1874 # empty description results in an empty string
1875 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1876 'info_dict': {
1877 'id': 'x41yOUIvK2k',
1878 'ext': 'mp4',
1879 'title': 'IMG 3456',
1880 'description': '',
1881 'upload_date': '20170613',
1882 'uploader_id': 'ElevageOrVert',
1883 'uploader': 'ElevageOrVert',
976ae3ea 1884 'view_count': int,
1885 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1886 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1887 'like_count': int,
1888 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1889 'tags': [],
1890 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1891 'availability': 'public',
1892 'age_limit': 0,
1893 'categories': ['Pets & Animals'],
1894 'duration': 7,
1895 'playable_in_embed': True,
1896 'live_status': 'not_live',
1897 'channel': 'ElevageOrVert',
6c73052c 1898 'channel_follower_count': int
ea74e00b
DP
1899 },
1900 'params': {
1901 'skip_download': True,
1902 },
1903 },
a0566bbf 1904 {
29f7c58a 1905 # with '};' inside yt initial data (see [1])
1906 # see [2] for an example with '};' inside ytInitialPlayerResponse
1907 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1908 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1909 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1910 'info_dict': {
1911 'id': 'CHqg6qOn4no',
1912 'ext': 'mp4',
1913 'title': 'Part 77 Sort a list of simple types in c#',
1914 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1915 'upload_date': '20130831',
1916 'uploader_id': 'kudvenkat',
1917 'uploader': 'kudvenkat',
976ae3ea 1918 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1919 'like_count': int,
1920 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1921 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1922 'live_status': 'not_live',
1923 'categories': ['Education'],
1924 'availability': 'public',
1925 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1926 'tags': 'count:12',
1927 'playable_in_embed': True,
1928 'age_limit': 0,
1929 'view_count': int,
1930 'duration': 522,
1931 'channel': 'kudvenkat',
6c73052c 1932 'channel_follower_count': int
a0566bbf 1933 },
1934 'params': {
1935 'skip_download': True,
1936 },
1937 },
29f7c58a 1938 {
1939 # another example of '};' in ytInitialData
1940 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1941 'only_matching': True,
1942 },
1943 {
1944 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1945 'only_matching': True,
1946 },
545cc85d 1947 {
cc2db878 1948 # https://github.com/ytdl-org/youtube-dl/pull/28094
1949 'url': 'OtqTfy26tG0',
1950 'info_dict': {
1951 'id': 'OtqTfy26tG0',
1952 'ext': 'mp4',
1953 'title': 'Burn Out',
1954 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1955 'upload_date': '20141120',
1956 'uploader': 'The Cinematic Orchestra - Topic',
1957 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1958 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1959 'artist': 'The Cinematic Orchestra',
1960 'track': 'Burn Out',
1961 'album': 'Every Day',
976ae3ea 1962 'like_count': int,
1963 'live_status': 'not_live',
1964 'alt_title': 'Burn Out',
1965 'duration': 614,
1966 'age_limit': 0,
1967 'view_count': int,
1968 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1969 'creator': 'The Cinematic Orchestra',
1970 'channel': 'The Cinematic Orchestra',
1971 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1972 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1973 'availability': 'public',
1974 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1975 'categories': ['Music'],
1976 'playable_in_embed': True,
6c73052c 1977 'channel_follower_count': int
cc2db878 1978 },
1979 'params': {
1980 'skip_download': True,
1981 },
545cc85d 1982 },
bc2ca1bb 1983 {
1984 # controversial video, only works with bpctr when authenticated with cookies
1985 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1986 'only_matching': True,
1987 },
a1a7907b 1988 {
1989 # controversial video, requires bpctr/contentCheckOk
1990 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1991 'info_dict': {
1992 'id': 'SZJvDhaSDnc',
1993 'ext': 'mp4',
1994 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1995 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1996 'uploader': 'CBS Mornings',
11f9be09 1997 'uploader_id': 'CBSThisMorning',
a1a7907b 1998 'upload_date': '20140716',
976ae3ea 1999 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2000 'duration': 170,
2001 'categories': ['News & Politics'],
2002 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2003 'view_count': int,
2004 'channel': 'CBS Mornings',
2005 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2006 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2007 'age_limit': 18,
2008 'availability': 'needs_auth',
2009 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2010 'like_count': int,
2011 'live_status': 'not_live',
2012 'playable_in_embed': True,
6c73052c 2013 'channel_follower_count': int
a1a7907b 2014 }
2015 },
f7ad7160 2016 {
2017 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2018 'url': 'cBvYw8_A0vQ',
2019 'info_dict': {
2020 'id': 'cBvYw8_A0vQ',
2021 'ext': 'mp4',
2022 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2023 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2024 'upload_date': '20201120',
2025 'uploader': 'Walk around Japan',
2026 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2027 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2028 'duration': 1456,
2029 'categories': ['Travel & Events'],
2030 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2031 'view_count': int,
2032 'channel': 'Walk around Japan',
2033 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2034 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2035 'age_limit': 0,
2036 'availability': 'public',
2037 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2038 'live_status': 'not_live',
2039 'playable_in_embed': True,
6c73052c 2040 'channel_follower_count': int
f7ad7160 2041 },
2042 'params': {
2043 'skip_download': True,
2044 },
0fb983f6 2045 }, {
2046 # Has multiple audio streams
2047 'url': 'WaOKSUlf4TM',
2048 'only_matching': True
9297939e 2049 }, {
2050 # Requires Premium: has format 141 when requested using YTM url
2051 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2052 'only_matching': True
2053 }, {
120916da 2054 # multiple subtitles with same lang_code
2055 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2056 'only_matching': True,
109dd3b2 2057 }, {
2058 # Force use android client fallback
2059 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2060 'info_dict': {
2061 'id': 'YOelRv7fMxY',
11f9be09 2062 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2063 'ext': '3gp',
2064 'upload_date': '20210624',
2065 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2066 'uploader': 'colinfurze',
11f9be09 2067 'uploader_id': 'colinfurze',
109dd3b2 2068 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2069 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2070 'duration': 596,
2071 'categories': ['Entertainment'],
2072 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2073 'view_count': int,
2074 'channel': 'colinfurze',
2075 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2076 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2077 'age_limit': 0,
2078 'availability': 'public',
2079 'like_count': int,
2080 'live_status': 'not_live',
2081 'playable_in_embed': True,
6c73052c 2082 'channel_follower_count': int
109dd3b2 2083 },
2084 'params': {
2085 'format': '17', # 3gp format available on android
2086 'extractor_args': {'youtube': {'player_client': ['android']}},
2087 },
120916da 2088 },
109dd3b2 2089 {
2090 # Skip download of additional client configs (remix client config in this case)
2091 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2092 'only_matching': True,
2093 'params': {
2094 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2095 },
8fc54b12 2096 }, {
2097 # shorts
2098 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2099 'only_matching': True,
9222c381 2100 }, {
2101 'note': 'Storyboards',
2102 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2103 'info_dict': {
2104 'id': '5KLPxDtMqe8',
2105 'ext': 'mhtml',
2106 'format_id': 'sb0',
2107 'title': 'Your Brain is Plastic',
2108 'uploader_id': 'scishow',
2109 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2110 'upload_date': '20140324',
2111 'uploader': 'SciShow',
976ae3ea 2112 'like_count': int,
2113 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2114 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2115 'view_count': int,
2116 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2117 'playable_in_embed': True,
2118 'tags': 'count:12',
2119 'uploader_url': 'http://www.youtube.com/user/scishow',
2120 'availability': 'public',
2121 'channel': 'SciShow',
2122 'live_status': 'not_live',
2123 'duration': 248,
2124 'categories': ['Education'],
2125 'age_limit': 0,
6c73052c 2126 'channel_follower_count': int
9222c381 2127 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2128 }, {
2129 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2130 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2131 'info_dict': {
2132 'id': '2NUZ8W2llS4',
2133 'ext': 'mp4',
2134 'title': 'The NP that test your phone performance 🙂',
2135 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2136 'uploader': 'Leon Nguyen',
2137 'uploader_id': 'VNSXIII',
2138 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2139 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2140 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2141 'duration': 21,
2142 'view_count': int,
2143 'age_limit': 0,
2144 'categories': ['Gaming'],
2145 'tags': 'count:23',
2146 'playable_in_embed': True,
2147 'live_status': 'not_live',
2148 'upload_date': '20220103',
2149 'like_count': int,
2150 'availability': 'public',
2151 'channel': 'Leon Nguyen',
2152 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2153 'channel_follower_count': int
2154 }
2155 }, {
2156 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2157 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2158 'info_dict': {
2159 'id': 'mzZzzBU6lrM',
2160 'ext': 'mp4',
2161 'title': 'I Met GeorgeNotFound In Real Life...',
2162 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2163 'uploader': 'Quackity',
2164 'uploader_id': 'QuackityHQ',
2165 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2166 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2167 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2168 'duration': 955,
2169 'view_count': int,
2170 'age_limit': 0,
2171 'categories': ['Entertainment'],
2172 'tags': 'count:26',
2173 'playable_in_embed': True,
2174 'live_status': 'not_live',
2175 'release_timestamp': 1641172509,
2176 'release_date': '20220103',
2177 'upload_date': '20220103',
2178 'like_count': int,
2179 'availability': 'public',
2180 'channel': 'Quackity',
2181 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2182 'channel_follower_count': int
2183 }
2184 },
2185 { # continuous livestream. Microformat upload date should be preferred.
2186 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2187 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2188 'info_dict': {
2189 'id': 'kgx4WGK0oNU',
2190 '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}',
2191 'ext': 'mp4',
2192 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2193 'availability': 'public',
2194 'age_limit': 0,
2195 'release_timestamp': 1637975704,
2196 'upload_date': '20210619',
2197 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2198 'live_status': 'is_live',
2199 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2200 'uploader': '阿鲍Abao',
2201 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2202 'channel': 'Abao in Tokyo',
2203 'channel_follower_count': int,
2204 'release_date': '20211127',
2205 'tags': 'count:39',
2206 'categories': ['People & Blogs'],
2207 'like_count': int,
2208 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2209 'view_count': int,
2210 'playable_in_embed': True,
2211 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2212 },
2213 'params': {'skip_download': True}
6e634cbe 2214 }, {
2215 # Story. Requires specific player params to work.
2216 # Note: stories get removed after some period of time
2217 'url': 'https://www.youtube.com/watch?v=yN3x1t3sieA',
2218 'info_dict': {
2219 'id': 'yN3x1t3sieA',
2220 'ext': 'mp4',
2221 'uploader': 'Linus Tech Tips',
2222 'duration': 13,
2223 'channel': 'Linus Tech Tips',
2224 'playable_in_embed': True,
2225 'tags': [],
2226 'age_limit': 0,
2227 'uploader_url': 'http://www.youtube.com/user/LinusTechTips',
2228 'upload_date': '20220402',
2229 'thumbnail': 'https://i.ytimg.com/vi_webp/yN3x1t3sieA/maxresdefault.webp',
2230 'title': 'Story',
2231 'live_status': 'not_live',
2232 'uploader_id': 'LinusTechTips',
2233 'view_count': int,
2234 'description': '',
2235 'channel_id': 'UCXuqSBlHAE6Xw-yeJA0Tunw',
2236 'categories': ['Science & Technology'],
2237 'channel_url': 'https://www.youtube.com/channel/UCXuqSBlHAE6Xw-yeJA0Tunw',
2238 'availability': 'unlisted',
2239 }
2240 }
2eb88d95
PH
2241 ]
2242
201c1459 2243 @classmethod
2244 def suitable(cls, url):
4dfbf869 2245 from ..utils import parse_qs
2246
201c1459 2247 qs = parse_qs(url)
2248 if qs.get('list', [None])[0]:
2249 return False
86e5f3ed 2250 return super().suitable(url)
201c1459 2251
e0df6211 2252 def __init__(self, *args, **kwargs):
86e5f3ed 2253 super().__init__(*args, **kwargs)
545cc85d 2254 self._code_cache = {}
83799698 2255 self._player_cache = {}
e0df6211 2256
adbc4ec4 2257 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2258 lock = threading.Lock()
2259
2260 is_live = True
185bf310 2261 start_time = time.time()
adbc4ec4
THD
2262 formats = [f for f in formats if f.get('is_from_start')]
2263
185bf310 2264 def refetch_manifest(format_id, delay):
2265 nonlocal formats, start_time, is_live
2266 if time.time() <= start_time + delay:
adbc4ec4
THD
2267 return
2268
2269 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2270 video_details = traverse_obj(
2271 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2272 microformats = traverse_obj(
2273 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2274 expected_type=dict, default=[])
2275 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2276 start_time = time.time()
adbc4ec4 2277
185bf310 2278 def mpd_feed(format_id, delay):
adbc4ec4
THD
2279 """
2280 @returns (manifest_url, manifest_stream_number, is_live) or None
2281 """
2282 with lock:
185bf310 2283 refetch_manifest(format_id, delay)
adbc4ec4
THD
2284
2285 f = next((f for f in formats if f['format_id'] == format_id), None)
2286 if not f:
185bf310 2287 if not is_live:
2288 self.to_screen(f'{video_id}: Video is no longer live')
2289 else:
2290 self.report_warning(
2291 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2292 return None
2293 return f['manifest_url'], f['manifest_stream_number'], is_live
2294
2295 for f in formats:
a539f065 2296 f['is_live'] = True
adbc4ec4
THD
2297 f['protocol'] = 'http_dash_segments_generator'
2298 f['fragments'] = functools.partial(
2299 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2300
2301 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2302 FETCH_SPAN, MAX_DURATION = 5, 432000
2303
2304 mpd_url, stream_number, is_live = None, None, True
2305
2306 begin_index = 0
2307 download_start_time = ctx.get('start') or time.time()
2308
2309 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2310 if lack_early_segments:
2311 self.report_warning(bug_reports_message(
2312 'Starting download from the last 120 hours of the live stream since '
2313 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2314 lack_early_segments = True
2315
2316 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2317 fragments, fragment_base_url = None, None
2318
a539f065 2319 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2320 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2321 # Obtain from MPD's maximum seq value
2322 old_mpd_url = mpd_url
185bf310 2323 last_error = ctx.pop('last_error', None)
a539f065 2324 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2325 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2326 or (mpd_url, stream_number, False))
2327 if not refresh_sequence:
2328 if expire_fast and not is_live:
2329 return False, last_seq
2330 elif old_mpd_url == mpd_url:
2331 return True, last_seq
adbc4ec4
THD
2332 try:
2333 fmts, _ = self._extract_mpd_formats_and_subtitles(
2334 mpd_url, None, note=False, errnote=False, fatal=False)
2335 except ExtractorError:
2336 fmts = None
2337 if not fmts:
a539f065 2338 no_fragment_score += 2
adbc4ec4
THD
2339 return False, last_seq
2340 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2341 fragments = fmt_info['fragments']
2342 fragment_base_url = fmt_info['fragment_base_url']
2343 assert fragment_base_url
2344
2345 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2346 return True, _last_seq
2347
2348 while is_live:
2349 fetch_time = time.time()
2350 if no_fragment_score > 30:
2351 return
2352 if last_segment_url:
2353 # Obtain from "X-Head-Seqnum" header value from each segment
2354 try:
2355 urlh = self._request_webpage(
2356 last_segment_url, None, note=False, errnote=False, fatal=False)
2357 except ExtractorError:
2358 urlh = None
2359 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2360 if last_seq is None:
a539f065 2361 no_fragment_score += 2
adbc4ec4
THD
2362 last_segment_url = None
2363 continue
2364 else:
a539f065
LNO
2365 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2366 no_fragment_score += 2
185bf310 2367 if not should_continue:
adbc4ec4
THD
2368 continue
2369
2370 if known_idx > last_seq:
2371 last_segment_url = None
2372 continue
2373
2374 last_seq += 1
2375
2376 if begin_index < 0 and known_idx < 0:
2377 # skip from the start when it's negative value
2378 known_idx = last_seq + begin_index
2379 if lack_early_segments:
2380 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2381 try:
2382 for idx in range(known_idx, last_seq):
2383 # do not update sequence here or you'll get skipped some part of it
a539f065 2384 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2385 if not should_continue:
adbc4ec4
THD
2386 known_idx = idx - 1
2387 raise ExtractorError('breaking out of outer loop')
2388 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2389 yield {
2390 'url': last_segment_url,
2391 }
2392 if known_idx == last_seq:
2393 no_fragment_score += 5
2394 else:
2395 no_fragment_score = 0
2396 known_idx = last_seq
2397 except ExtractorError:
2398 continue
2399
2400 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2401
b6de707d 2402 def _extract_player_url(self, *ytcfgs, webpage=None):
2403 player_url = traverse_obj(
2404 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2405 get_all=False, expected_type=compat_str)
11f9be09 2406 if not player_url:
b6de707d 2407 return
60f393e4 2408 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2409
b6de707d 2410 def _download_player_url(self, video_id, fatal=False):
2411 res = self._download_webpage(
2412 'https://www.youtube.com/iframe_api',
2413 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2414 if res:
2415 player_version = self._search_regex(
2416 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2417 if player_version:
2418 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2419
60064c53
PH
2420 def _signature_cache_id(self, example_sig):
2421 """ Return a string representation of a signature """
78caa52a 2422 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2423
e40c758c
S
2424 @classmethod
2425 def _extract_player_info(cls, player_url):
2426 for player_re in cls._PLAYER_INFO_RE:
2427 id_m = re.search(player_re, player_url)
2428 if id_m:
2429 break
2430 else:
c081b35c 2431 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2432 return id_m.group('id')
e40c758c 2433
404f611f 2434 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2435 player_id = self._extract_player_info(player_url)
2436 if player_id not in self._code_cache:
1276a43a 2437 code = self._download_webpage(
109dd3b2 2438 player_url, video_id, fatal=fatal,
2439 note='Downloading player ' + player_id,
2440 errnote='Download of %s failed' % player_url)
1276a43a 2441 if code:
2442 self._code_cache[player_id] = code
404f611f 2443 return self._code_cache.get(player_id)
109dd3b2 2444
e40c758c 2445 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2446 player_id = self._extract_player_info(player_url)
e0df6211 2447
c4417ddb 2448 # Read from filesystem cache
86e5f3ed 2449 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2450 assert os.path.basename(func_id) == func_id
a0e07d31 2451
69ea8ca4 2452 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2453 if cache_spec is not None:
78caa52a 2454 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2455
404f611f 2456 code = self._load_player(video_id, player_url)
2457 if code:
109dd3b2 2458 res = self._parse_sig_js(code)
e0df6211 2459
109dd3b2 2460 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2461 cache_res = res(test_string)
2462 cache_spec = [ord(c) for c in cache_res]
83799698 2463
109dd3b2 2464 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2465 return res
83799698 2466
60064c53 2467 def _print_sig_code(self, func, example_sig):
404f611f 2468 if not self.get_param('youtube_print_sig_code'):
2469 return
2470
edf3e38e
PH
2471 def gen_sig_code(idxs):
2472 def _genslice(start, end, step):
78caa52a 2473 starts = '' if start == 0 else str(start)
8bcc8756 2474 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2475 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2476 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2477
2478 step = None
7af808a5
PH
2479 # Quelch pyflakes warnings - start will be set when step is set
2480 start = '(Never used)'
edf3e38e
PH
2481 for i, prev in zip(idxs[1:], idxs[:-1]):
2482 if step is not None:
2483 if i - prev == step:
2484 continue
2485 yield _genslice(start, prev, step)
2486 step = None
2487 continue
2488 if i - prev in [-1, 1]:
2489 step = i - prev
2490 start = prev
2491 continue
2492 else:
78caa52a 2493 yield 's[%d]' % prev
edf3e38e 2494 if step is None:
78caa52a 2495 yield 's[%d]' % i
edf3e38e
PH
2496 else:
2497 yield _genslice(start, i, step)
2498
78caa52a 2499 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2500 cache_res = func(test_string)
edf3e38e 2501 cache_spec = [ord(c) for c in cache_res]
78caa52a 2502 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2503 signature_id_tuple = '(%s)' % (
2504 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2505 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2506 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2507 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2508
e0df6211
PH
2509 def _parse_sig_js(self, jscode):
2510 funcname = self._search_regex(
abefc03f
S
2511 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2512 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
2513 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2514 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2515 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}\(a,\d+\)',
2516 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 2517 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2518 # Obsolete patterns
2519 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2520 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2521 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2522 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2523 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2524 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2525 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2526 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2527 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2528
2529 jsi = JSInterpreter(jscode)
2530 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2531 return lambda s: initial_function([s])
2532
545cc85d 2533 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2534 """Turn the encrypted s field into a working signature"""
6b37f0be 2535
c8bf86d5 2536 if player_url is None:
69ea8ca4 2537 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2538
c8bf86d5 2539 try:
62af3a0e 2540 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2541 if player_id not in self._player_cache:
2542 func = self._extract_signature_function(
60064c53 2543 video_id, player_url, s
c8bf86d5
PH
2544 )
2545 self._player_cache[player_id] = func
2546 func = self._player_cache[player_id]
404f611f 2547 self._print_sig_code(func, s)
c8bf86d5
PH
2548 return func(s)
2549 except Exception as e:
404f611f 2550 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2551
2552 def _decrypt_nsig(self, s, video_id, player_url):
2553 """Turn the encrypted n field into a working signature"""
2554 if player_url is None:
2555 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2556 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2557
2558 sig_id = ('nsig_value', s)
2559 if sig_id in self._player_cache:
2560 return self._player_cache[sig_id]
2561
2562 try:
2563 player_id = ('nsig', player_url)
2564 if player_id not in self._player_cache:
2565 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2566 func = self._player_cache[player_id]
2567 self._player_cache[sig_id] = func(s)
2568 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2569 return self._player_cache[sig_id]
2570 except Exception as e:
aa9369a2 2571 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2572
2573 def _extract_n_function_name(self, jscode):
48416bc4 2574 nfunc, idx = self._search_regex(
c571b3a6 2575 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2576 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2577 if not idx:
2578 return nfunc
2579 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2580 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2581 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2582
2583 def _extract_n_function(self, video_id, player_url):
2584 player_id = self._extract_player_info(player_url)
2585 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2586
2587 if func_code:
2588 jsi = JSInterpreter(func_code)
2589 else:
2590 jscode = self._load_player(video_id, player_url)
2591 funcname = self._extract_n_function_name(jscode)
2592 jsi = JSInterpreter(jscode)
2593 func_code = jsi.extract_function_code(funcname)
2594 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2595
2596 if self.get_param('youtube_print_sig_code'):
2597 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2598
2599 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2600
109dd3b2 2601 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2602 """
2603 Extract signatureTimestamp (sts)
2604 Required to tell API what sig/player version is in use.
2605 """
2606 sts = None
2607 if isinstance(ytcfg, dict):
2608 sts = int_or_none(ytcfg.get('STS'))
2609
2610 if not sts:
2611 # Attempt to extract from player
2612 if player_url is None:
2613 error_msg = 'Cannot extract signature timestamp without player_url.'
2614 if fatal:
2615 raise ExtractorError(error_msg)
2616 self.report_warning(error_msg)
2617 return
404f611f 2618 code = self._load_player(video_id, player_url, fatal=fatal)
2619 if code:
109dd3b2 2620 sts = int_or_none(self._search_regex(
2621 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2622 'JS player signature timestamp', group='sts', fatal=fatal))
2623 return sts
2624
11f9be09 2625 def _mark_watched(self, video_id, player_responses):
9222c381 2626 playback_url = get_first(
2627 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2628 expected_type=url_or_none)
d77ab8e2 2629 if not playback_url:
352d63fd 2630 self.report_warning('Unable to mark watched')
d77ab8e2
S
2631 return
2632 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2633 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2634
2635 # cpn generation algorithm is reverse engineered from base.js.
2636 # In fact it works even with dummy cpn.
2637 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
86e5f3ed 2638 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
d77ab8e2
S
2639
2640 qs.update({
2641 'ver': ['2'],
2642 'cpn': [cpn],
2643 })
2644 playback_url = compat_urlparse.urlunparse(
15707c7e 2645 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2646
2647 self._download_webpage(
2648 playback_url, video_id, 'Marking watched',
2649 'Unable to mark watched', fatal=False)
2650
66c9fa36
S
2651 @staticmethod
2652 def _extract_urls(webpage):
2653 # Embedded YouTube player
2654 entries = [
2655 unescapeHTML(mobj.group('url'))
2656 for mobj in re.finditer(r'''(?x)
2657 (?:
2658 <iframe[^>]+?src=|
2659 data-video-url=|
2660 <embed[^>]+?src=|
2661 embedSWF\(?:\s*|
2662 <object[^>]+data=|
2663 new\s+SWFObject\(
2664 )
2665 (["\'])
2666 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2667 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2668 \1''', webpage)]
2669
2670 # lazyYT YouTube embed
2671 entries.extend(list(map(
2672 unescapeHTML,
2673 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2674
2675 # Wordpress "YouTube Video Importer" plugin
2676 matches = re.findall(r'''(?x)<div[^>]+
2677 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2678 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2679 entries.extend(m[-1] for m in matches)
2680
2681 return entries
2682
2683 @staticmethod
2684 def _extract_url(webpage):
2685 urls = YoutubeIE._extract_urls(webpage)
2686 return urls[0] if urls else None
2687
97665381
PH
2688 @classmethod
2689 def extract_id(cls, url):
2690 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2691 if mobj is None:
69ea8ca4 2692 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2693 return mobj.group('id')
c5e8d7af 2694
7c365c21 2695 def _extract_chapters_from_json(self, data, duration):
2696 chapter_list = traverse_obj(
2697 data, (
2698 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2699 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2700 ), expected_type=list)
2701
2702 return self._extract_chapters(
2703 chapter_list,
2704 chapter_time=lambda chapter: float_or_none(
2705 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2706 chapter_title=lambda chapter: traverse_obj(
2707 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2708 duration=duration)
2709
2710 def _extract_chapters_from_engagement_panel(self, data, duration):
2711 content_list = traverse_obj(
8bdd16b4 2712 data,
7c365c21 2713 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2714 expected_type=list, default=[])
052e1350 2715 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2716 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2717
2718 return next((
2719 filter(None, (
2720 self._extract_chapters(
2721 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2722 chapter_time, chapter_title, duration)
2723 for contents in content_list
2724 ))), [])
2725
2726 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2727 chapters = []
7c365c21 2728 last_chapter = {'start_time': 0}
2729 for idx, chapter in enumerate(chapter_list or []):
2730 title = chapter_title(chapter)
84213ea8
S
2731 start_time = chapter_time(chapter)
2732 if start_time is None:
2733 continue
7c365c21 2734 last_chapter['end_time'] = start_time
2735 if start_time < last_chapter['start_time']:
2736 if idx == 1:
2737 chapters.pop()
2738 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2739 else:
2740 self.report_warning(f'Invalid start time for chapter "{title}"')
2741 continue
2742 last_chapter = {'start_time': start_time, 'title': title}
2743 chapters.append(last_chapter)
2744 last_chapter['end_time'] = duration
84213ea8
S
2745 return chapters
2746
545cc85d 2747 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2748 return self._parse_json(self._search_regex(
86e5f3ed 2749 (fr'{regex}\s*{self._YT_INITIAL_BOUNDARY_RE}',
545cc85d 2750 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2751
a1c5d2ca
M
2752 def _extract_comment(self, comment_renderer, parent=None):
2753 comment_id = comment_renderer.get('commentId')
2754 if not comment_id:
2755 return
fe93e2c4 2756
052e1350 2757 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2758
49bd8c66 2759 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2760 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2761 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2762 author_id = try_get(comment_renderer,
2763 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2764
49bd8c66 2765 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2766 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2767 author_thumbnail = try_get(comment_renderer,
2768 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2769
2770 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2771 is_favorited = 'creatorHeart' in (try_get(
2772 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2773 return {
2774 'id': comment_id,
2775 'text': text,
d92f5d5a 2776 'timestamp': timestamp,
a1c5d2ca
M
2777 'time_text': time_text,
2778 'like_count': votes,
97524332 2779 'is_favorited': is_favorited,
a1c5d2ca
M
2780 'author': author,
2781 'author_id': author_id,
2782 'author_thumbnail': author_thumbnail,
2783 'author_is_uploader': author_is_uploader,
2784 'parent': parent or 'root'
2785 }
2786
46383212 2787 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2788
2789 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2790
2791 def extract_header(contents):
2d6659b9 2792 _continuation = None
2793 for content in contents:
46383212 2794 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2795 expected_comment_count = self._get_count(
2796 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2797
2d6659b9 2798 if expected_comment_count:
46383212 2799 tracker['est_total'] = expected_comment_count
2800 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2801 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2802
2803 sort_menu_item = try_get(
2804 comments_header_renderer,
2805 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2806 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2807
2808 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2809 if not _continuation:
2810 continue
2811
46383212 2812 sort_text = str_or_none(sort_menu_item.get('title'))
2813 if not sort_text:
2d6659b9 2814 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2815 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2816 break
a2160aa4 2817 return _continuation
a1c5d2ca 2818
2d6659b9 2819 def extract_thread(contents):
a1c5d2ca 2820 if not parent:
46383212 2821 tracker['current_page_thread'] = 0
a1c5d2ca 2822 for content in contents:
46383212 2823 if not parent and tracker['total_parent_comments'] >= max_parents:
2824 yield
a1c5d2ca 2825 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2826 comment_renderer = get_first(
2827 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2828 expected_type=dict, default={})
a1c5d2ca 2829
a1c5d2ca
M
2830 comment = self._extract_comment(comment_renderer, parent)
2831 if not comment:
2832 continue
46383212 2833
2834 tracker['running_total'] += 1
2835 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2836 yield comment
46383212 2837
a1c5d2ca
M
2838 # Attempt to get the replies
2839 comment_replies_renderer = try_get(
2840 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2841
2842 if comment_replies_renderer:
46383212 2843 tracker['current_page_thread'] += 1
a1c5d2ca 2844 comment_entries_iter = self._comment_entries(
99e9e001 2845 comment_replies_renderer, ytcfg, video_id,
46383212 2846 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2847 yield from itertools.islice(comment_entries_iter, min(
2848 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2849
46383212 2850 # Keeps track of counts across recursive calls
2851 if not tracker:
2852 tracker = dict(
2853 running_total=0,
2854 est_total=0,
2855 current_page_thread=0,
2856 total_parent_comments=0,
2857 total_reply_comments=0)
2858
2859 # TODO: Deprecated
2d6659b9 2860 # YouTube comments have a max depth of 2
46383212 2861 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2862 if max_depth:
2863 self._downloader.deprecation_warning(
2864 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2865 if max_depth == 1 and parent:
2866 return
a1c5d2ca 2867
46383212 2868 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2869 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2870
46383212 2871 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2872
46383212 2873 response = None
6e634cbe 2874 is_forced_continuation = False
2d6659b9 2875 is_first_continuation = parent is None
6e634cbe 2876 if is_first_continuation and not continuation:
2877 # Sometimes you can get comments by generating the continuation yourself,
2878 # even if YouTube initially reports them being disabled - e.g. stories comments.
2879 # Note: if the comment section is actually disabled, YouTube may return a response with
2880 # required check_get_keys missing. So we will disable that check initially in this case.
2881 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2882 is_forced_continuation = True
a1c5d2ca
M
2883
2884 for page_num in itertools.count(0):
2885 if not continuation:
2886 break
46383212 2887 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2888 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2889 if page_num == 0:
2890 if is_first_continuation:
2891 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2892 else:
2d6659b9 2893 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2894 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2895 else:
2896 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2897 ' ' if parent else '', ' replies' if parent else '',
2898 page_num, comment_prog_str)
2899
2900 response = self._extract_response(
fe93e2c4 2901 item_id=None, query=continuation,
2d6659b9 2902 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2903 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2904 is_forced_continuation = False
46383212 2905 continuation_contents = traverse_obj(
2906 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2907
2d6659b9 2908 continuation = None
46383212 2909 for continuation_section in continuation_contents:
2910 continuation_items = traverse_obj(
2911 continuation_section,
2912 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2913 get_all=False, expected_type=list) or []
2914 if is_first_continuation:
2915 continuation = extract_header(continuation_items)
2916 is_first_continuation = False
2d6659b9 2917 if continuation:
a1c5d2ca 2918 break
46383212 2919 continue
a1c5d2ca 2920
46383212 2921 for entry in extract_thread(continuation_items):
2922 if not entry:
2923 return
2924 yield entry
2925 continuation = self._extract_continuation({'contents': continuation_items})
2926 if continuation:
2d6659b9 2927 break
a1c5d2ca 2928
6e634cbe 2929 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2930 if message and not parent and tracker['running_total'] == 0:
2931 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2932
2933 @staticmethod
2934 def _generate_comment_continuation(video_id):
2935 """
2936 Generates initial comment section continuation token from given video id
2937 """
2938 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2939 return base64.b64encode(token.encode()).decode()
2940
a2160aa4 2941 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2942 """Entry for comment extraction"""
2d6659b9 2943 def _real_comment_extract(contents):
aae16f6e 2944 renderer = next((
2945 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2946 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2947 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2948
a2160aa4 2949 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2950 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2951
109dd3b2 2952 @staticmethod
99e9e001 2953 def _get_checkok_params():
2954 return {'contentCheckOk': True, 'racyCheckOk': True}
2955
2956 @classmethod
2957 def _generate_player_context(cls, sts=None):
109dd3b2 2958 context = {
2959 'html5Preference': 'HTML5_PREF_WANTS',
2960 }
2961 if sts is not None:
2962 context['signatureTimestamp'] = sts
2963 return {
2964 'playbackContext': {
2965 'contentPlaybackContext': context
a1a7907b 2966 },
99e9e001 2967 **cls._get_checkok_params()
109dd3b2 2968 }
2969
e7e94f2a
D
2970 @staticmethod
2971 def _is_agegated(player_response):
2972 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2973 return True
e7e94f2a
D
2974
2975 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2976 AGE_GATE_REASONS = (
2977 'confirm your age', 'age-restricted', 'inappropriate', # reason
2978 'age_verification_required', 'age_check_required', # status
2979 )
2980 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2981
2982 @staticmethod
2983 def _is_unplayable(player_response):
2984 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2985
99e9e001 2986 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2987
11f9be09 2988 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2989 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2990 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2991 headers = self.generate_api_headers(
99e9e001 2992 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2993
6e634cbe 2994 yt_query = {
2995 'videoId': video_id,
2996 'params': '8AEB' # enable stories
2997 }
11f9be09 2998 yt_query.update(self._generate_player_context(sts))
2999 return self._extract_response(
3000 item_id=video_id, ep='player', query=yt_query,
379e44ed 3001 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3002 default_client=client,
11f9be09 3003 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3004 ) or None
3005
11f9be09 3006 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3007 requested_clients = []
d0d012d4 3008 default = ['android', 'web']
000c15a4 3009 allowed_clients = sorted(
86e5f3ed 3010 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3011 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3012 for client in self._configuration_arg('player_client'):
3013 if client in allowed_clients:
3014 requested_clients.append(client)
d0d012d4 3015 elif client == 'default':
3016 requested_clients.extend(default)
b4c055ba 3017 elif client == 'all':
3018 requested_clients.extend(allowed_clients)
3019 else:
3020 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3021 if not requested_clients:
d0d012d4 3022 requested_clients = default
cf7e015f 3023
11f9be09 3024 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3025 requested_clients.extend(
e7e94f2a 3026 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3027
11f9be09 3028 return orderedSet(requested_clients)
cf7e015f 3029
99e9e001 3030 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3031 initial_pr = None
3032 if webpage:
3033 initial_pr = self._extract_yt_initial_variable(
3034 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
3035 video_id, 'initial player response')
6b09401b 3036
ae729626 3037 all_clients = set(clients)
c0bc527b 3038 clients = clients[::-1]
b6de707d 3039 prs = []
e7e94f2a 3040
ae729626 3041 def append_client(*client_names):
e7870111 3042 """ Append the first client name that exists but not already used """
ae729626 3043 for client_name in client_names:
e7870111
D
3044 actual_client = _split_innertube_client(client_name)[0]
3045 if actual_client in INNERTUBE_CLIENTS:
3046 if actual_client not in all_clients:
ae729626 3047 clients.append(client_name)
e7870111
D
3048 all_clients.add(actual_client)
3049 return
e7e94f2a 3050
379e44ed 3051 # Android player_response does not have microFormats which are needed for
3052 # extraction of some data. So we return the initial_pr with formats
3053 # stripped out even if not requested by the user
3054 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3055 if initial_pr:
3056 pr = dict(initial_pr)
3057 pr['streamingData'] = None
b6de707d 3058 prs.append(pr)
379e44ed 3059
3060 last_error = None
b6de707d 3061 tried_iframe_fallback = False
3062 player_url = None
c0bc527b 3063 while clients:
e7870111 3064 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3065 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3066 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3067 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3068
b6de707d 3069 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3070 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3071 if 'js' in self._configuration_arg('player_skip'):
3072 require_js_player = False
3073 player_url = None
3074
3075 if not player_url and not tried_iframe_fallback and require_js_player:
3076 player_url = self._download_player_url(video_id)
3077 tried_iframe_fallback = True
3078
379e44ed 3079 try:
3080 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3081 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3082 except ExtractorError as e:
3083 if last_error:
3084 self.report_warning(last_error)
3085 last_error = e
3086 continue
3087
11f9be09 3088 if pr:
b6de707d 3089 prs.append(pr)
c0bc527b 3090
e7e94f2a 3091 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3092 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3093 append_client(f'{base_client}_creator')
e7e94f2a 3094 elif self._is_agegated(pr):
e7870111
D
3095 if variant == 'tv_embedded':
3096 append_client(f'{base_client}_embedded')
3097 elif not variant:
3098 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3099
379e44ed 3100 if last_error:
b6de707d 3101 if not len(prs):
379e44ed 3102 raise last_error
3103 self.report_warning(last_error)
b6de707d 3104 return prs, player_url
11f9be09 3105
a1b2d843 3106 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3107 itags, stream_ids = {}, []
2a9c6dcd 3108 itag_qualities, res_qualities = {}, {}
d3fc8074 3109 q = qualities([
2a9c6dcd 3110 # Normally tiny is the smallest video-only formats. But
3111 # audio-only formats with unknown quality may get tagged as tiny
3112 'tiny',
3113 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3114 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3115 ])
11f9be09 3116 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3117
545cc85d 3118 for fmt in streaming_formats:
727029c5 3119 if fmt.get('targetDurationSec'):
545cc85d 3120 continue
321bf820 3121
cc2db878 3122 itag = str_or_none(fmt.get('itag'))
9297939e 3123 audio_track = fmt.get('audioTrack') or {}
3124 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3125 if stream_id in stream_ids:
3126 continue
3127
cc2db878 3128 quality = fmt.get('quality')
2a9c6dcd 3129 height = int_or_none(fmt.get('height'))
d3fc8074 3130 if quality == 'tiny' or not quality:
3131 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3132 # The 3gp format (17) in android client has a quality of "small",
3133 # but is actually worse than other formats
3134 if itag == '17':
3135 quality = 'tiny'
3136 if quality:
3137 if itag:
3138 itag_qualities[itag] = quality
3139 if height:
3140 res_qualities[height] = quality
cc2db878 3141 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3142 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3143 # number of fragment that would subsequently requested with (`&sq=N`)
3144 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3145 continue
3146
545cc85d 3147 fmt_url = fmt.get('url')
3148 if not fmt_url:
3149 sc = compat_parse_qs(fmt.get('signatureCipher'))
3150 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3151 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3152 if not (sc and fmt_url and encrypted_sig):
3153 continue
545cc85d 3154 if not player_url:
201e9eaa 3155 continue
545cc85d 3156 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3157 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3158 fmt_url += '&' + sp + '=' + signature
3159
404f611f 3160 query = parse_qs(fmt_url)
3161 throttled = False
b2916526 3162 if query.get('n'):
404f611f 3163 try:
3164 fmt_url = update_url_query(fmt_url, {
3165 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3166 except ExtractorError as e:
aa9369a2 3167 self.report_warning(
1d485a1a 3168 'nsig extraction failed: You may experience throttling for some formats\n'
aa9369a2 3169 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3170 throttled = True
3171
545cc85d 3172 if itag:
a0bb6ce5 3173 itags[itag] = 'https'
9297939e 3174 stream_ids.append(stream_id)
3175
0ad92dfb 3176 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3177 language_preference = (
3178 10 if audio_track.get('audioIsDefault') and 10
3179 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3180 else -1)
0ad92dfb 3181 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3182 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3183 # Make sure to avoid false positives with small duration differences.
3184 # Eg: __2ABJjxzNo, ySuUZEjARPY
3185 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3186 if is_damaged:
0f06bcd7 3187 self.report_warning(
3188 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3189 dct = {
3190 'asr': int_or_none(fmt.get('audioSampleRate')),
3191 'filesize': int_or_none(fmt.get('contentLength')),
3192 'format_id': itag,
34921b43 3193 'format_note': join_nonempty(
26e8e044 3194 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3195 ' (default)' if language_preference > 0 else ''),
404f611f 3196 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3197 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3198 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3199 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3200 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3201 'height': height,
dca3ff4a 3202 'quality': q(quality),
727029c5 3203 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3204 'tbr': tbr,
545cc85d 3205 'url': fmt_url,
2a9c6dcd 3206 'width': int_or_none(fmt.get('width')),
ab6df717 3207 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3208 'desc' if language_preference < -1 else ''),
3209 'language_preference': language_preference,
a405b38f 3210 # Strictly de-prioritize damaged and 3gp formats
3211 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3212 }
60bdb7bd 3213 mime_mobj = re.match(
3214 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3215 if mime_mobj:
3216 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3217 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3218 no_audio = dct.get('acodec') == 'none'
3219 no_video = dct.get('vcodec') == 'none'
3220 if no_audio:
3221 dct['vbr'] = tbr
3222 if no_video:
3223 dct['abr'] = tbr
3224 if no_audio or no_video:
545cc85d 3225 dct['downloader_options'] = {
3226 # Youtube throttles chunks >~10M
3227 'http_chunk_size': 10485760,
bf1317d2 3228 }
7c60c33e 3229 if dct.get('ext'):
3230 dct['container'] = dct['ext'] + '_dash'
11f9be09 3231 yield dct
545cc85d 3232
adbc4ec4 3233 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3234 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3235 if not self.get_param('youtube_include_hls_manifest', True):
3236 skip_manifests.append('hls')
0f06bcd7 3237 if not self.get_param('youtube_include_dash_manifest', True):
3238 skip_manifests.append('dash')
adbc4ec4
THD
3239 get_dash = 'dash' not in skip_manifests and (
3240 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3241 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3242
a0bb6ce5 3243 def process_manifest_format(f, proto, itag):
3244 if itag in itags:
3245 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3246 return False
3247 itag = f'{itag}-{proto}'
3248 if itag:
3249 f['format_id'] = itag
3250 itags[itag] = proto
3251
3252 f['quality'] = next((
3253 q(qdict[val])
e339d25a 3254 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3255 if val in qdict), -1)
3256 return True
2a9c6dcd 3257
11f9be09 3258 for sd in streaming_data:
5d3a0e79 3259 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3260 if hls_manifest_url:
2a9c6dcd 3261 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3262 if process_manifest_format(f, 'hls', self._search_regex(
3263 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3264 yield f
545cc85d 3265
5d3a0e79 3266 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3267 if dash_manifest_url:
2a9c6dcd 3268 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3269 if process_manifest_format(f, 'dash', f['format_id']):
3270 f['filesize'] = int_or_none(self._search_regex(
3271 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3272 if live_from_start:
3273 f['is_from_start'] = True
3274
a0bb6ce5 3275 yield f
11f9be09 3276
720c3099 3277 def _extract_storyboard(self, player_responses, duration):
3278 spec = get_first(
3279 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3280 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3281 if not base_url:
720c3099 3282 return
720c3099 3283 L = len(spec) - 1
3284 for i, args in enumerate(spec):
3285 args = args.split('#')
3286 counts = list(map(int_or_none, args[:5]))
3287 if len(args) != 8 or not all(counts):
3288 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3289 continue
3290 width, height, frame_count, cols, rows = counts
3291 N, sigh = args[6:]
3292
3293 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3294 fragment_count = frame_count / (cols * rows)
3295 fragment_duration = duration / fragment_count
3296 yield {
3297 'format_id': f'sb{i}',
3298 'format_note': 'storyboard',
3299 'ext': 'mhtml',
3300 'protocol': 'mhtml',
3301 'acodec': 'none',
3302 'vcodec': 'none',
3303 'url': url,
3304 'width': width,
3305 'height': height,
3306 'fragments': [{
b3edc806 3307 'url': url.replace('$M', str(j)),
720c3099 3308 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3309 } for j in range(math.ceil(fragment_count))],
3310 }
3311
adbc4ec4 3312 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3313 webpage = None
3314 if 'webpage' not in self._configuration_arg('player_skip'):
3315 webpage = self._download_webpage(
6e634cbe 3316 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3317
3318 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3319
b6de707d 3320 player_responses, player_url = self._extract_player_responses(
11f9be09 3321 self._get_requested_clients(url, smuggled_data),
99e9e001 3322 video_id, webpage, master_ytcfg)
11f9be09 3323
adbc4ec4
THD
3324 return webpage, master_ytcfg, player_responses, player_url
3325
a1b2d843 3326 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3327 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3328 is_live = get_first(video_details, 'isLive')
3329 if is_live is None:
3330 is_live = get_first(live_broadcast_details, 'isLiveNow')
3331
3332 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3333 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3334
3335 return live_broadcast_details, is_live, streaming_data, formats
3336
3337 def _real_extract(self, url):
3338 url, smuggled_data = unsmuggle_url(url, {})
3339 video_id = self._match_id(url)
3340
3341 base_url = self.http_scheme() + '//www.youtube.com/'
3342 webpage_url = base_url + 'watch?v=' + video_id
3343
3344 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3345
11f9be09 3346 playability_statuses = traverse_obj(
3347 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3348
3349 trailer_video_id = get_first(
3350 playability_statuses,
3351 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3352 expected_type=str)
3353 if trailer_video_id:
3354 return self.url_result(
3355 trailer_video_id, self.ie_key(), trailer_video_id)
3356
3357 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3358 if webpage else (lambda x: None))
3359
3360 video_details = traverse_obj(
3361 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3362 microformats = traverse_obj(
3363 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3364 expected_type=dict, default=[])
3365 video_title = (
3366 get_first(video_details, 'title')
3367 or self._get_text(microformats, (..., 'title'))
3368 or search_meta(['og:title', 'twitter:title', 'title']))
3369 video_description = get_first(video_details, 'shortDescription')
3370
d89257f3 3371 multifeed_metadata_list = get_first(
3372 player_responses,
3373 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3374 expected_type=str)
3375 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3376 if self.get_param('noplaylist'):
11f9be09 3377 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3378 else:
3379 entries = []
3380 feed_ids = []
3381 for feed in multifeed_metadata_list.split(','):
3382 # Unquote should take place before split on comma (,) since textual
3383 # fields may contain comma as well (see
3384 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3385 feed_data = compat_parse_qs(
3386 compat_urllib_parse_unquote_plus(feed))
3387
3388 def feed_entry(name):
3389 return try_get(
3390 feed_data, lambda x: x[name][0], compat_str)
3391
3392 feed_id = feed_entry('id')
3393 if not feed_id:
3394 continue
3395 feed_title = feed_entry('title')
3396 title = video_title
3397 if feed_title:
3398 title += ' (%s)' % feed_title
3399 entries.append({
3400 '_type': 'url_transparent',
3401 'ie_key': 'Youtube',
3402 'url': smuggle_url(
3403 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3404 {'force_singlefeed': True}),
3405 'title': title,
3406 })
3407 feed_ids.append(feed_id)
3408 self.to_screen(
3409 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3410 % (', '.join(feed_ids), video_id))
3411 return self.playlist_result(
3412 entries, video_id, video_title, video_description)
11f9be09 3413
a1b2d843 3414 duration = int_or_none(
3415 get_first(video_details, 'lengthSeconds')
3416 or get_first(microformats, 'lengthSeconds')
3417 or parse_duration(search_meta('duration'))) or None
3418
3419 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3420 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3421
545cc85d 3422 if not formats:
11f9be09 3423 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3424 self.report_drm(video_id)
11f9be09 3425 pemr = get_first(
3426 playability_statuses,
3427 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3428 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3429 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3430 if subreason:
545cc85d 3431 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3432 countries = get_first(microformats, 'availableCountries')
545cc85d 3433 if not countries:
3434 regions_allowed = search_meta('regionsAllowed')
3435 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3436 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3437 reason += f'. {subreason}'
545cc85d 3438 if reason:
b7da73eb 3439 self.raise_no_formats(reason, expected=True)
bf1317d2 3440
11f9be09 3441 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3442 if not keywords and webpage:
3443 keywords = [
3444 unescapeHTML(m.group('content'))
3445 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3446 for keyword in keywords:
3447 if keyword.startswith('yt:stretch='):
201c1459 3448 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3449 if mobj:
3450 # NB: float is intentional for forcing float division
3451 w, h = (float(v) for v in mobj.groups())
3452 if w > 0 and h > 0:
3453 ratio = w / h
3454 for f in formats:
3455 if f.get('vcodec') != 'none':
3456 f['stretched_ratio'] = ratio
3457 break
a709d873 3458 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3459 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3460 if thumbnail_url:
3461 thumbnails.append({
3462 'url': thumbnail_url,
ff2751ac 3463 })
fccf5021 3464 original_thumbnails = thumbnails.copy()
3465
0ba692ac 3466 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3467 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3468 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3469 thumbnail_names = [
bfec31be 3470 # While the *1,*2,*3 thumbnails are just below their correspnding "*default" variants
3471 # in resolution, these are not the custom thumbnail. So de-prioritize them
3472 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3473 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3474 ]
cca80fe6 3475 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3476 thumbnails.extend({
3477 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3478 video_id=video_id, name=name, ext=ext,
3479 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3480 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3481 for thumb in thumbnails:
cca80fe6 3482 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3483 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3484 self._remove_duplicate_formats(thumbnails)
fccf5021 3485 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3486
7ea65411 3487 category = get_first(microformats, 'category') or search_meta('genre')
3488 channel_id = str_or_none(
3489 get_first(video_details, 'channelId')
3490 or get_first(microformats, 'externalChannelId')
3491 or search_meta('channelId'))
7ea65411 3492 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3493
3494 live_content = get_first(video_details, 'isLiveContent')
3495 is_upcoming = get_first(video_details, 'isUpcoming')
3496 if is_live is None:
3497 if is_upcoming or live_content is False:
3498 is_live = False
3499 if is_upcoming is None and (live_content or is_live):
3500 is_upcoming = False
adbc4ec4
THD
3501 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3502 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3503 if not duration and live_end_time and live_start_time:
3504 duration = live_end_time - live_start_time
3505
3506 if is_live and self.get_param('live_from_start'):
3507 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3508
720c3099 3509 formats.extend(self._extract_storyboard(player_responses, duration))
3510
3511 # Source is given priority since formats that throttle are given lower source_preference
3512 # When throttling issue is fully fixed, remove this
3513 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3514
545cc85d 3515 info = {
3516 'id': video_id,
39ca3b5c 3517 'title': video_title,
545cc85d 3518 'formats': formats,
3519 'thumbnails': thumbnails,
fccf5021 3520 # The best thumbnail that we are sure exists. Prevents unnecessary
3521 # URL checking if user don't care about getting the best possible thumbnail
3522 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3523 'description': video_description,
11f9be09 3524 'uploader': get_first(video_details, 'author'),
545cc85d 3525 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3526 'uploader_url': owner_profile_url,
3527 'channel_id': channel_id,
e0ddbd02 3528 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3529 'duration': duration,
3530 'view_count': int_or_none(
11f9be09 3531 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3532 or search_meta('interactionCount')),
11f9be09 3533 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3534 'age_limit': 18 if (
11f9be09 3535 get_first(microformats, 'isFamilySafe') is False
545cc85d 3536 or search_meta('isFamilyFriendly') == 'false'
3537 or search_meta('og:restrictions:age') == '18+') else 0,
3538 'webpage_url': webpage_url,
3539 'categories': [category] if category else None,
3540 'tags': keywords,
11f9be09 3541 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3542 'is_live': is_live,
3543 'was_live': (False if is_live or is_upcoming or live_content is False
3544 else None if is_live is None or is_upcoming is None
3545 else live_content),
3546 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3547 'release_timestamp': live_start_time,
545cc85d 3548 }
b477fc13 3549
3944e7af 3550 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3551 if pctr:
ecdc9049 3552 def get_lang_code(track):
3553 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3554 or track.get('languageCode'))
3555
3556 # Converted into dicts to remove duplicates
3557 captions = {
3558 get_lang_code(sub): sub
3559 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3560 translation_languages = {
3561 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3562 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3563
774d79cc 3564 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3565 lang_subs = container.setdefault(lang_code, [])
545cc85d 3566 for fmt in self._SUBTITLE_FORMATS:
3567 query.update({
3568 'fmt': fmt,
3569 })
3570 lang_subs.append({
3571 'ext': fmt,
60f393e4 3572 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3573 'name': sub_name,
545cc85d 3574 })
7e72694b 3575
ecdc9049 3576 subtitles, automatic_captions = {}, {}
3577 for lang_code, caption_track in captions.items():
3578 base_url = caption_track.get('baseUrl')
1235d333 3579 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3580 if not base_url:
3581 continue
ecdc9049 3582 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3583 if caption_track.get('kind') != 'asr':
545cc85d 3584 if not lang_code:
3585 continue
3586 process_language(
ecdc9049 3587 subtitles, base_url, lang_code, lang_name, {})
3588 if not caption_track.get('isTranslatable'):
3589 continue
3944e7af 3590 for trans_code, trans_name in translation_languages.items():
3591 if not trans_code:
545cc85d 3592 continue
1235d333 3593 orig_trans_code = trans_code
ecdc9049 3594 if caption_track.get('kind') != 'asr':
18e49408 3595 if 'translated_subs' in self._configuration_arg('skip'):
3596 continue
ecdc9049 3597 trans_code += f'-{lang_code}'
3598 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3599 # Add an "-orig" label to the original language so that it can be distinguished.
3600 # The subs are returned without "-orig" as well for compatibility
1235d333 3601 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3602 process_language(
d49669ac 3603 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3604 # Setting tlang=lang returns damaged subtitles.
d49669ac 3605 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3606 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3607 info['automatic_captions'] = automatic_captions
3608 info['subtitles'] = subtitles
7e72694b 3609
545cc85d 3610 parsed_url = compat_urllib_parse_urlparse(url)
3611 for component in [parsed_url.fragment, parsed_url.query]:
3612 query = compat_parse_qs(component)
3613 for k, v in query.items():
3614 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3615 d_k += '_time'
3616 if d_k not in info and k in s_ks:
3617 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3618
3619 # Youtube Music Auto-generated description
822b9d9c 3620 if video_description:
38d70284 3621 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
822b9d9c 3622 if mobj:
822b9d9c
RA
3623 release_year = mobj.group('release_year')
3624 release_date = mobj.group('release_date')
3625 if release_date:
3626 release_date = release_date.replace('-', '')
3627 if not release_year:
545cc85d 3628 release_year = release_date[:4]
3629 info.update({
3630 'album': mobj.group('album'.strip()),
3631 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3632 'track': mobj.group('track').strip(),
3633 'release_date': release_date,
cc2db878 3634 'release_year': int_or_none(release_year),
545cc85d 3635 })
7e72694b 3636
545cc85d 3637 initial_data = None
3638 if webpage:
3639 initial_data = self._extract_yt_initial_variable(
3640 webpage, self._YT_INITIAL_DATA_RE, video_id,
3641 'yt initial data')
3642 if not initial_data:
99e9e001 3643 query = {'videoId': video_id}
3644 query.update(self._get_checkok_params())
109dd3b2 3645 initial_data = self._extract_response(
3646 item_id=video_id, ep='next', fatal=False,
99e9e001 3647 ytcfg=master_ytcfg, query=query,
3648 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3649 note='Downloading initial data API JSON')
545cc85d 3650
19a03940 3651 try: # This will error if there is no livechat
c60ee3a2 3652 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3653 except (KeyError, IndexError, TypeError):
3654 pass
3655 else:
ecdc9049 3656 info.setdefault('subtitles', {})['live_chat'] = [{
19a03940 3657 'url': f'https://www.youtube.com/watch?v={video_id}', # url is needed to set cookies
c60ee3a2 3658 'video_id': video_id,
3659 'ext': 'json',
f6745c49 3660 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3661 }]
545cc85d 3662
3663 if initial_data:
7c365c21 3664 info['chapters'] = (
3665 self._extract_chapters_from_json(initial_data, duration)
3666 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3667 or None)
545cc85d 3668
17322130 3669 contents = traverse_obj(
3670 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3671 expected_type=list, default=[])
3672
3673 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3674 if vpir:
3675 stl = vpir.get('superTitleLink')
3676 if stl:
3677 stl = self._get_text(stl)
3678 if try_get(
3679 vpir,
3680 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3681 info['location'] = stl
3682 else:
affc4fef 3683 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3684 if mobj:
545cc85d 3685 info.update({
17322130 3686 'series': mobj.group(1),
3687 'season_number': int(mobj.group(2)),
3688 'episode_number': int(mobj.group(3)),
545cc85d 3689 })
17322130 3690 for tlb in (try_get(
3691 vpir,
3692 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3693 list) or []):
3694 tbr = tlb.get('toggleButtonRenderer') or {}
3695 for getter, regex in [(
3696 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3697 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3698 lambda x: x['accessibility'],
3699 lambda x: x['accessibilityData']['accessibilityData'],
3700 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3701 label = (try_get(tbr, getter, dict) or {}).get('label')
3702 if label:
3703 mobj = re.match(regex, label)
3704 if mobj:
3705 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3706 break
17322130 3707 sbr_tooltip = try_get(
3708 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3709 if sbr_tooltip:
3710 like_count, dislike_count = sbr_tooltip.split(' / ')
3711 info.update({
3712 'like_count': str_to_int(like_count),
3713 'dislike_count': str_to_int(dislike_count),
3714 })
3715 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3716 if vsir:
3717 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3718 info.update({
3719 'channel': self._get_text(vor, 'title'),
3720 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3721
3722 rows = try_get(
3723 vsir,
3724 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3725 list) or []
3726 multiple_songs = False
3727 for row in rows:
3728 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3729 multiple_songs = True
3730 break
3731 for row in rows:
3732 mrr = row.get('metadataRowRenderer') or {}
3733 mrr_title = mrr.get('title')
3734 if not mrr_title:
3735 continue
3736 mrr_title = self._get_text(mrr, 'title')
3737 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3738 if mrr_title == 'License':
3739 info['license'] = mrr_contents_text
3740 elif not multiple_songs:
3741 if mrr_title == 'Album':
3742 info['album'] = mrr_contents_text
3743 elif mrr_title == 'Artist':
3744 info['artist'] = mrr_contents_text
3745 elif mrr_title == 'Song':
3746 info['track'] = mrr_contents_text
545cc85d 3747
3748 fallbacks = {
3749 'channel': 'uploader',
3750 'channel_id': 'uploader_id',
3751 'channel_url': 'uploader_url',
3752 }
992f9a73 3753
17322130 3754 # The upload date for scheduled, live and past live streams / premieres in microformats
3755 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3756 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3757 upload_date = (
3758 unified_strdate(get_first(microformats, 'uploadDate'))
3759 or unified_strdate(search_meta('uploadDate')))
3760 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3761 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3762 info['upload_date'] = upload_date
992f9a73 3763
545cc85d 3764 for to, frm in fallbacks.items():
3765 if not info.get(to):
3766 info[to] = info.get(frm)
3767
3768 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3769 v = info.get(s_k)
3770 if v:
3771 info[d_k] = v
b84071c0 3772
11f9be09 3773 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3774 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3775 is_membersonly = None
b28f8d24 3776 is_premium = None
c224251a
M
3777 if initial_data and is_private is not None:
3778 is_membersonly = False
b28f8d24 3779 is_premium = False
47193e02 3780 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3781 badge_labels = set()
3782 for content in contents:
3783 if not isinstance(content, dict):
3784 continue
3785 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3786 for badge_label in badge_labels:
3787 if badge_label.lower() == 'members only':
3788 is_membersonly = True
3789 elif badge_label.lower() == 'premium':
3790 is_premium = True
3791 elif badge_label.lower() == 'unlisted':
3792 is_unlisted = True
c224251a 3793
c224251a
M
3794 info['availability'] = self._availability(
3795 is_private=is_private,
b28f8d24 3796 needs_premium=is_premium,
c224251a
M
3797 needs_subscription=is_membersonly,
3798 needs_auth=info['age_limit'] >= 18,
3799 is_unlisted=None if is_private is None else is_unlisted)
3800
a2160aa4 3801 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3802
11f9be09 3803 self.mark_watched(video_id, player_responses)
d77ab8e2 3804
545cc85d 3805 return info
c5e8d7af 3806
a61fd4cf 3807
a6213a49 3808class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3809
182bda88 3810 @staticmethod
3811 def passthrough_smuggled_data(func):
3812 def _smuggle(entries, smuggled_data):
3813 for entry in entries:
3814 # TODO: Convert URL to music.youtube instead.
3815 # Do we need to passthrough any other smuggled_data?
3816 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3817 yield entry
3818
3819 @functools.wraps(func)
3820 def wrapper(self, url):
3821 url, smuggled_data = unsmuggle_url(url, {})
3822 if self.is_music_url(url):
3823 smuggled_data['is_music_url'] = True
3824 info_dict = func(self, url, smuggled_data)
3825 if smuggled_data and info_dict.get('entries'):
3826 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3827 return info_dict
3828 return wrapper
3829
a6213a49 3830 def _extract_channel_id(self, webpage):
3831 channel_id = self._html_search_meta(
3832 'channelId', webpage, 'channel id', default=None)
3833 if channel_id:
3834 return channel_id
3835 channel_url = self._html_search_meta(
3836 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3837 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3838 'twitter:app:url:googleplay'), webpage, 'channel url')
3839 return self._search_regex(
3840 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3841 channel_url, 'channel id')
15f6397c 3842
8bdd16b4 3843 @staticmethod
cd7c66cf 3844 def _extract_basic_item_renderer(item):
3845 # Modified from _extract_grid_item_renderer
201c1459 3846 known_basic_renderers = (
a17526e4 3847 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3848 )
3849 for key, renderer in item.items():
201c1459 3850 if not isinstance(renderer, dict):
cd7c66cf 3851 continue
201c1459 3852 elif key in known_basic_renderers:
3853 return renderer
3854 elif key.startswith('grid') and key.endswith('Renderer'):
3855 return renderer
8bdd16b4 3856
8bdd16b4 3857 def _grid_entries(self, grid_renderer):
3858 for item in grid_renderer['items']:
3859 if not isinstance(item, dict):
39b62db1 3860 continue
cd7c66cf 3861 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3862 if not isinstance(renderer, dict):
3863 continue
052e1350 3864 title = self._get_text(renderer, 'title')
fe93e2c4 3865
8bdd16b4 3866 # playlist
3867 playlist_id = renderer.get('playlistId')
3868 if playlist_id:
3869 yield self.url_result(
3870 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3871 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3872 video_title=title)
201c1459 3873 continue
8bdd16b4 3874 # video
3875 video_id = renderer.get('videoId')
3876 if video_id:
3877 yield self._extract_video(renderer)
201c1459 3878 continue
8bdd16b4 3879 # channel
3880 channel_id = renderer.get('channelId')
3881 if channel_id:
8bdd16b4 3882 yield self.url_result(
3883 'https://www.youtube.com/channel/%s' % channel_id,
3884 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3885 continue
3886 # generic endpoint URL support
3887 ep_url = urljoin('https://www.youtube.com/', try_get(
3888 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3889 compat_str))
3890 if ep_url:
3891 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3892 if ie.suitable(ep_url):
3893 yield self.url_result(
3894 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3895 break
8bdd16b4 3896
16aa9ea4 3897 def _music_reponsive_list_entry(self, renderer):
3898 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3899 if video_id:
3900 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3901 ie=YoutubeIE.ie_key(), video_id=video_id)
3902 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3903 if playlist_id:
3904 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3905 if video_id:
3906 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3907 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3908 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3909 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3910 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3911 if browse_id:
3912 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3913 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3914
3d3dddc9 3915 def _shelf_entries_from_content(self, shelf_renderer):
3916 content = shelf_renderer.get('content')
3917 if not isinstance(content, dict):
8bdd16b4 3918 return
cd7c66cf 3919 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3920 if renderer:
3921 # TODO: add support for nested playlists so each shelf is processed
3922 # as separate playlist
3923 # TODO: this includes only first N items
86e5f3ed 3924 yield from self._grid_entries(renderer)
3d3dddc9 3925 renderer = content.get('horizontalListRenderer')
3926 if renderer:
3927 # TODO
3928 pass
8bdd16b4 3929
29f7c58a 3930 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3931 ep = try_get(
3932 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3933 compat_str)
3934 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3935 if shelf_url:
29f7c58a 3936 # Skipping links to another channels, note that checking for
3937 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3938 # will not work
3939 if skip_channels and '/channels?' in shelf_url:
3940 return
052e1350 3941 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3942 yield self.url_result(shelf_url, video_title=title)
3943 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 3944 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 3945
8bdd16b4 3946 def _playlist_entries(self, video_list_renderer):
3947 for content in video_list_renderer['contents']:
3948 if not isinstance(content, dict):
3949 continue
3950 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3951 if not isinstance(renderer, dict):
3952 continue
3953 video_id = renderer.get('videoId')
3954 if not video_id:
3955 continue
3956 yield self._extract_video(renderer)
07aeced6 3957
3462ffa8 3958 def _rich_entries(self, rich_grid_renderer):
3959 renderer = try_get(
70d5c17b 3960 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3961 video_id = renderer.get('videoId')
3962 if not video_id:
3963 return
3964 yield self._extract_video(renderer)
3965
8bdd16b4 3966 def _video_entry(self, video_renderer):
3967 video_id = video_renderer.get('videoId')
3968 if video_id:
3969 return self._extract_video(video_renderer)
dacb3a86 3970
ad210f4f 3971 def _hashtag_tile_entry(self, hashtag_tile_renderer):
3972 url = urljoin('https://youtube.com', traverse_obj(
3973 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
3974 if url:
3975 return self.url_result(
3976 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
3977
8bdd16b4 3978 def _post_thread_entries(self, post_thread_renderer):
3979 post_renderer = try_get(
3980 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3981 if not post_renderer:
3982 return
3983 # video attachment
3984 video_renderer = try_get(
895b0931 3985 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3986 video_id = video_renderer.get('videoId')
3987 if video_id:
3988 entry = self._extract_video(video_renderer)
8bdd16b4 3989 if entry:
3990 yield entry
895b0931 3991 # playlist attachment
3992 playlist_id = try_get(
3993 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3994 if playlist_id:
3995 yield self.url_result(
e28f1c0a 3996 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3997 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3998 # inline video links
3999 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4000 for run in runs:
4001 if not isinstance(run, dict):
4002 continue
4003 ep_url = try_get(
4004 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
4005 if not ep_url:
4006 continue
4007 if not YoutubeIE.suitable(ep_url):
4008 continue
4009 ep_video_id = YoutubeIE._match_id(ep_url)
4010 if video_id == ep_video_id:
4011 continue
895b0931 4012 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4013
8bdd16b4 4014 def _post_thread_continuation_entries(self, post_thread_continuation):
4015 contents = post_thread_continuation.get('contents')
4016 if not isinstance(contents, list):
4017 return
4018 for content in contents:
4019 renderer = content.get('backstagePostThreadRenderer')
4020 if not isinstance(renderer, dict):
4021 continue
86e5f3ed 4022 yield from self._post_thread_entries(renderer)
07aeced6 4023
39ed931e 4024 r''' # unused
4025 def _rich_grid_entries(self, contents):
4026 for content in contents:
4027 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4028 if video_renderer:
4029 entry = self._video_entry(video_renderer)
4030 if entry:
4031 yield entry
4032 '''
52efa4b3 4033
a6213a49 4034 def _extract_entries(self, parent_renderer, continuation_list):
4035 # continuation_list is modified in-place with continuation_list = [continuation_token]
4036 continuation_list[:] = [None]
4037 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4038 for content in contents:
4039 if not isinstance(content, dict):
4040 continue
16aa9ea4 4041 is_renderer = traverse_obj(
4042 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4043 expected_type=dict)
a6213a49 4044 if not is_renderer:
4045 renderer = content.get('richItemRenderer')
4046 if renderer:
4047 for entry in self._rich_entries(renderer):
4048 yield entry
4049 continuation_list[0] = self._extract_continuation(parent_renderer)
4050 continue
4051 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4052 for isr_content in isr_contents:
4053 if not isinstance(isr_content, dict):
8bdd16b4 4054 continue
69184e41 4055
a6213a49 4056 known_renderers = {
4057 'playlistVideoListRenderer': self._playlist_entries,
4058 'gridRenderer': self._grid_entries,
a17526e4 4059 'reelShelfRenderer': self._grid_entries,
4060 'shelfRenderer': self._shelf_entries,
16aa9ea4 4061 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4062 'backstagePostThreadRenderer': self._post_thread_entries,
4063 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4064 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4065 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4066 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4067 }
4068 for key, renderer in isr_content.items():
4069 if key not in known_renderers:
4070 continue
4071 for entry in known_renderers[key](renderer):
4072 if entry:
4073 yield entry
4074 continuation_list[0] = self._extract_continuation(renderer)
4075 break
70d5c17b 4076
4077 if not continuation_list[0]:
a6213a49 4078 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4079
a6213a49 4080 if not continuation_list[0]:
4081 continuation_list[0] = self._extract_continuation(parent_renderer)
4082
4083 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4084 continuation_list = [None]
4085 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4086 tab_content = try_get(tab, lambda x: x['content'], dict)
4087 if not tab_content:
4088 return
3462ffa8 4089 parent_renderer = (
29f7c58a 4090 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4091 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4092 yield from extract_entries(parent_renderer)
3462ffa8 4093 continuation = continuation_list[0]
d069eca7 4094
8bdd16b4 4095 for page_num in itertools.count(1):
4096 if not continuation:
4097 break
99e9e001 4098 headers = self.generate_api_headers(
4099 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4100 response = self._extract_response(
86e5f3ed 4101 item_id=f'{item_id} page {page_num}',
fe93e2c4 4102 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4103 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4104
4105 if not response:
8bdd16b4 4106 break
ac56cf38 4107 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4108 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4109 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4110
69184e41 4111 known_continuation_renderers = {
4112 'playlistVideoListContinuation': self._playlist_entries,
4113 'gridContinuation': self._grid_entries,
4114 'itemSectionContinuation': self._post_thread_continuation_entries,
4115 'sectionListContinuation': extract_entries, # for feeds
4116 }
8bdd16b4 4117 continuation_contents = try_get(
69184e41 4118 response, lambda x: x['continuationContents'], dict) or {}
4119 continuation_renderer = None
4120 for key, value in continuation_contents.items():
4121 if key not in known_continuation_renderers:
3462ffa8 4122 continue
69184e41 4123 continuation_renderer = value
4124 continuation_list = [None]
86e5f3ed 4125 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4126 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4127 break
4128 if continuation_renderer:
4129 continue
c5e8d7af 4130
a1b535bd 4131 known_renderers = {
e4b98809 4132 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4133 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4134 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4135 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4136 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4137 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4138 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4139 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4140 }
cce889b9 4141 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4142 continuation_items = try_get(
cce889b9 4143 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4144 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4145 video_items_renderer = None
4146 for key, value in continuation_item.items():
4147 if key not in known_renderers:
8bdd16b4 4148 continue
a1b535bd 4149 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4150 continuation_list = [None]
86e5f3ed 4151 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4152 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4153 break
4154 if video_items_renderer:
4155 continue
8bdd16b4 4156 break
9558dcec 4157
8bdd16b4 4158 @staticmethod
7c219ea6 4159 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4160 for tab in tabs:
cd684175 4161 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4162 if renderer.get('selected') is True:
4163 return renderer
2b3c2546 4164 else:
7c219ea6 4165 if fatal:
4166 raise ExtractorError('Unable to find selected tab')
b82f815f 4167
61d3665d 4168 def _extract_uploader(self, data):
8bdd16b4 4169 uploader = {}
61d3665d 4170 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4171 owner = try_get(
4172 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4173 if owner:
61d3665d 4174 owner_text = owner.get('text')
4175 uploader['uploader'] = self._search_regex(
4176 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4177 uploader['uploader_id'] = try_get(
4178 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4179 uploader['uploader_url'] = urljoin(
4180 'https://www.youtube.com/',
4181 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4182 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4183
ac56cf38 4184 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4185 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4186 tags = []
b60419c5 4187
8bdd16b4 4188 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4189 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4190 renderer = try_get(
4191 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4192 if renderer:
b60419c5 4193 channel_name = renderer.get('title')
4194 channel_url = renderer.get('channelUrl')
4195 channel_id = renderer.get('externalId')
39ed931e 4196 else:
64c0d954 4197 renderer = try_get(
4198 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4199
8bdd16b4 4200 if renderer:
4201 title = renderer.get('title')
ecc97af3 4202 description = renderer.get('description', '')
b60419c5 4203 playlist_id = channel_id
4204 tags = renderer.get('keywords', '').split()
b60419c5 4205
301d07fc 4206 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4207 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4208 def _get_uncropped(url):
4209 return url_or_none((url or '').split('=')[0] + '=s0')
4210
4211 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4212 if avatar_thumbnails:
4213 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4214 if uncropped_avatar:
4215 avatar_thumbnails.append({
4216 'url': uncropped_avatar,
4217 'id': 'avatar_uncropped',
4218 'preference': 1
4219 })
4220
4221 channel_banners = self._extract_thumbnails(
4222 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4223 for banner in channel_banners:
4224 banner['preference'] = -10
4225
4226 if channel_banners:
4227 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4228 if uncropped_banner:
4229 channel_banners.append({
4230 'url': uncropped_banner,
4231 'id': 'banner_uncropped',
4232 'preference': -5
4233 })
4234
4235 primary_thumbnails = self._extract_thumbnails(
a17526e4 4236 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4237
3462ffa8 4238 if playlist_id is None:
70d5c17b 4239 playlist_id = item_id
f0d785d3 4240
4241 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4242 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4243 if title is None:
f0d785d3 4244 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4245 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4246 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4247
b60419c5 4248 metadata = {
4249 'playlist_id': playlist_id,
4250 'playlist_title': title,
4251 'playlist_description': description,
4252 'uploader': channel_name,
4253 'uploader_id': channel_id,
4254 'uploader_url': channel_url,
301d07fc 4255 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4256 'tags': tags,
f0d785d3 4257 'view_count': self._get_count(playlist_stats, 1),
4258 'availability': self._extract_availability(data),
4259 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4260 'playlist_count': self._get_count(playlist_stats, 0),
4261 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4262 }
4263 if not channel_id:
4264 metadata.update(self._extract_uploader(data))
4265 metadata.update({
4266 'channel': metadata['uploader'],
4267 'channel_id': metadata['uploader_id'],
4268 'channel_url': metadata['uploader_url']})
4269 return self.playlist_result(
d069eca7 4270 self._entries(
ac56cf38 4271 selected_tab, playlist_id, ytcfg,
4272 self._extract_account_syncid(ytcfg, data),
4273 self._extract_visitor_data(data, ytcfg)),
b60419c5 4274 **metadata)
73c4ac2c 4275
6e634cbe 4276 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4277 first_id = last_id = response = None
2be71994 4278 for page_num in itertools.count(1):
cd7c66cf 4279 videos = list(self._playlist_entries(playlist))
4280 if not videos:
4281 return
2be71994 4282 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4283 if start >= len(videos):
4284 return
4285 for video in videos[start:]:
2be71994 4286 yield video
4287 first_id = first_id or videos[0]['id']
4288 last_id = videos[-1]['id']
79360d99 4289 watch_endpoint = try_get(
4290 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4291 headers = self.generate_api_headers(
4292 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4293 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4294 query = {
4295 'playlistId': playlist_id,
4296 'videoId': watch_endpoint.get('videoId') or last_id,
4297 'index': watch_endpoint.get('index') or len(videos),
4298 'params': watch_endpoint.get('params') or 'OAE%3D'
4299 }
4300 response = self._extract_response(
4301 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4302 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4303 check_get_keys='contents'
4304 )
cd7c66cf 4305 playlist = try_get(
79360d99 4306 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4307
ac56cf38 4308 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4309 title = playlist.get('title') or try_get(
4310 data, lambda x: x['titleText']['simpleText'], compat_str)
4311 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4312
4313 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4314 playlist_url = urljoin(url, try_get(
4315 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4316 compat_str))
6e634cbe 4317
4318 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4319 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4320 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4321
4322 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4323 return self.url_result(
4324 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4325 video_title=title)
cd7c66cf 4326
8bdd16b4 4327 return self.playlist_result(
6e634cbe 4328 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4329 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4330
47193e02 4331 def _extract_availability(self, data):
4332 """
4333 Gets the availability of a given playlist/tab.
4334 Note: Unless YouTube tells us explicitly, we do not assume it is public
4335 @param data: response
4336 """
4337 is_private = is_unlisted = None
4338 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4339 badge_labels = self._extract_badges(renderer)
4340
4341 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4342 privacy_dropdown_entries = try_get(
4343 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4344 for renderer_dict in privacy_dropdown_entries:
4345 is_selected = try_get(
4346 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4347 if not is_selected:
4348 continue
052e1350 4349 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4350 if label:
4351 badge_labels.add(label.lower())
4352 break
4353
4354 for badge_label in badge_labels:
4355 if badge_label == 'unlisted':
4356 is_unlisted = True
4357 elif badge_label == 'private':
4358 is_private = True
4359 elif badge_label == 'public':
4360 is_unlisted = is_private = False
4361 return self._availability(is_private, False, False, False, is_unlisted)
4362
4363 @staticmethod
4364 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4365 sidebar_renderer = try_get(
4366 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4367 for item in sidebar_renderer:
4368 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4369 if renderer:
4370 return renderer
4371
ac56cf38 4372 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4373 """
4374 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4375 """
5d342002 4376 browse_id = params = None
47193e02 4377 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4378 if not renderer:
4379 return
4380 menu_renderer = try_get(
4381 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4382 for menu_item in menu_renderer:
4383 if not isinstance(menu_item, dict):
358de58c 4384 continue
47193e02 4385 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4386 text = try_get(
4387 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4388 if not text or text.lower() != 'show unavailable videos':
4389 continue
4390 browse_endpoint = try_get(
4391 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4392 browse_id = browse_endpoint.get('browseId')
4393 params = browse_endpoint.get('params')
4394 break
5d342002 4395
11f9be09 4396 headers = self.generate_api_headers(
99e9e001 4397 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4398 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4399 query = {
4400 'params': params or 'wgYCCAA=',
4401 'browseId': browse_id or 'VL%s' % item_id
4402 }
4403 return self._extract_response(
4404 item_id=item_id, headers=headers, query=query,
fe93e2c4 4405 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4406 note='Downloading API JSON with unavailable videos')
358de58c 4407
a25bca9f 4408 @property
4409 def skip_webpage(self):
4410 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4411
ac56cf38 4412 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4413 retries = self.get_param('extractor_retries', 3)
62bff2c1 4414 count = -1
ac56cf38 4415 webpage = data = last_error = None
14fdfea9 4416 while count < retries:
62bff2c1 4417 count += 1
14fdfea9 4418 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4419 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4420 if last_error:
c705177d 4421 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4422 try:
4423 webpage = self._download_webpage(
4424 url, item_id,
4425 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4426 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4427 except ExtractorError as e:
4428 if isinstance(e.cause, network_exceptions):
4429 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4430 last_error = error_to_compat_str(e.cause or e.msg)
4431 if count < retries:
4432 continue
4433 if fatal:
4434 raise
4435 self.report_warning(error_to_compat_str(e))
14fdfea9 4436 break
ac56cf38 4437 else:
4438 try:
4439 self._extract_and_report_alerts(data)
4440 except ExtractorError as e:
4441 if fatal:
4442 raise
4443 self.report_warning(error_to_compat_str(e))
4444 break
4445
7c219ea6 4446 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4447 break
4448
4449 last_error = 'Incomplete yt initial data received'
4450 if count >= retries:
4451 if fatal:
4452 raise ExtractorError(last_error)
4453 self.report_warning(last_error)
4454 break
4455
cd7c66cf 4456 return webpage, data
4457
a25bca9f 4458 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4459 """Use if failed to extract ytcfg (and data) from initial webpage"""
4460 if not ytcfg and self.is_authenticated:
4461 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4462 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4463 raise ExtractorError(
4464 f'{msg}. If you are not downloading private content, or '
4465 'your cookies are only for the first account and channel,'
4466 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4467 expected=True)
4468 self.report_warning(msg, only_once=True)
4469
ac56cf38 4470 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4471 data = None
a25bca9f 4472 if not self.skip_webpage:
ac56cf38 4473 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4474 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4475 # Reject webpage data if redirected to home page without explicitly requesting
4476 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4477 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4478 if (url != 'https://www.youtube.com/feed/recommended'
4479 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4480 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4481 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4482 if fatal:
4483 raise ExtractorError(msg, expected=True)
4484 self.report_warning(msg, only_once=True)
ac56cf38 4485 if not data:
a25bca9f 4486 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4487 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4488 return data, ytcfg
4489
4490 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4491 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4492 resolve_response = self._extract_response(
4493 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4494 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4495 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4496 for ep_key, ep in endpoints.items():
4497 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4498 if params:
4499 return self._extract_response(
4500 item_id=item_id, query=params, ep=ep, headers=headers,
4501 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4502 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4503 err_note = 'Failed to resolve url (does the playlist exist?)'
4504 if fatal:
4505 raise ExtractorError(err_note, expected=True)
4506 self.report_warning(err_note, item_id)
4507
a6213a49 4508 _SEARCH_PARAMS = None
4509
af5c1c55 4510 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4511 data = {'query': query}
4512 if params is NO_DEFAULT:
4513 params = self._SEARCH_PARAMS
4514 if params:
4515 data['params'] = params
16aa9ea4 4516
4517 content_keys = (
4518 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4519 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4520 # ytmusic search
4521 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4522 ('continuationContents', ),
4523 )
a25bca9f 4524 display_id = f'query "{query}"'
86e5f3ed 4525 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4526 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4527 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4528
a61fd4cf 4529 continuation_list = [None]
a25bca9f 4530 search = None
a6213a49 4531 for page_num in itertools.count(1):
a61fd4cf 4532 data.update(continuation_list[0] or {})
a25bca9f 4533 headers = self.generate_api_headers(
4534 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4535 search = self._extract_response(
a25bca9f 4536 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4537 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4538 slr_contents = traverse_obj(search, *content_keys)
4539 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4540 if not continuation_list[0]:
a6213a49 4541 break
4542
4543
4544class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4545 IE_DESC = 'YouTube Tabs'
4546 _VALID_URL = r'''(?x:
4547 https?://
4548 (?:\w+\.)?
4549 (?:
4550 youtube(?:kids)?\.com|
4551 %(invidious)s
4552 )/
4553 (?:
4554 (?P<channel_type>channel|c|user|browse)/|
4555 (?P<not_channel>
4556 feed/|hashtag/|
4557 (?:playlist|watch)\?.*?\blist=
4558 )|
4559 (?!(?:%(reserved_names)s)\b) # Direct URLs
4560 )
4561 (?P<id>[^/?\#&]+)
4562 )''' % {
4563 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4564 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4565 }
4566 IE_NAME = 'youtube:tab'
4567
4568 _TESTS = [{
4569 'note': 'playlists, multipage',
4570 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4571 'playlist_mincount': 94,
4572 'info_dict': {
4573 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4574 'title': 'Igor Kleiner - Playlists',
a6213a49 4575 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4576 'uploader': 'Igor Kleiner',
a6213a49 4577 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4578 'channel': 'Igor Kleiner',
4579 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4580 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4581 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4582 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4583 'channel_follower_count': int
a6213a49 4584 },
4585 }, {
4586 'note': 'playlists, multipage, different order',
4587 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4588 'playlist_mincount': 94,
4589 'info_dict': {
4590 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4591 'title': 'Igor Kleiner - Playlists',
a6213a49 4592 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4593 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4594 'uploader': 'Igor Kleiner',
4595 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4596 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4597 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4598 'channel': 'Igor Kleiner',
4599 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4600 'channel_follower_count': int
a6213a49 4601 },
4602 }, {
4603 'note': 'playlists, series',
4604 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4605 'playlist_mincount': 5,
4606 'info_dict': {
4607 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4608 'title': '3Blue1Brown - Playlists',
4609 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4610 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4611 'uploader': '3Blue1Brown',
976ae3ea 4612 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4613 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4614 'channel': '3Blue1Brown',
4615 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4616 'tags': ['Mathematics'],
6c73052c 4617 'channel_follower_count': int
a6213a49 4618 },
4619 }, {
4620 'note': 'playlists, singlepage',
4621 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4622 'playlist_mincount': 4,
4623 'info_dict': {
4624 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4625 'title': 'ThirstForScience - Playlists',
4626 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4627 'uploader': 'ThirstForScience',
4628 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4629 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4630 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4631 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4632 'tags': 'count:13',
4633 'channel': 'ThirstForScience',
6c73052c 4634 'channel_follower_count': int
a6213a49 4635 }
4636 }, {
4637 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4638 'only_matching': True,
4639 }, {
4640 'note': 'basic, single video playlist',
4641 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4642 'info_dict': {
4643 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4644 'uploader': 'Sergey M.',
4645 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4646 'title': 'youtube-dl public playlist',
976ae3ea 4647 'description': '',
4648 'tags': [],
4649 'view_count': int,
4650 'modified_date': '20201130',
4651 'channel': 'Sergey M.',
4652 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4653 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4654 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4655 },
4656 'playlist_count': 1,
4657 }, {
4658 'note': 'empty playlist',
4659 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4660 'info_dict': {
4661 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4662 'uploader': 'Sergey M.',
4663 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4664 'title': 'youtube-dl empty playlist',
976ae3ea 4665 'tags': [],
4666 'channel': 'Sergey M.',
4667 'description': '',
4668 'modified_date': '20160902',
4669 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4670 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4671 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4672 },
4673 'playlist_count': 0,
4674 }, {
4675 'note': 'Home tab',
4676 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4677 'info_dict': {
4678 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4679 'title': 'lex will - Home',
4680 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4681 'uploader': 'lex will',
4682 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4683 'channel': 'lex will',
4684 'tags': ['bible', 'history', 'prophesy'],
4685 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4686 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4687 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4688 'channel_follower_count': int
a6213a49 4689 },
4690 'playlist_mincount': 2,
4691 }, {
4692 'note': 'Videos tab',
4693 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4694 'info_dict': {
4695 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4696 'title': 'lex will - Videos',
4697 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4698 'uploader': 'lex will',
4699 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4700 'tags': ['bible', 'history', 'prophesy'],
4701 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4702 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4703 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4704 'channel': 'lex will',
6c73052c 4705 'channel_follower_count': int
a6213a49 4706 },
4707 'playlist_mincount': 975,
4708 }, {
4709 'note': 'Videos tab, sorted by popular',
4710 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4711 'info_dict': {
4712 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4713 'title': 'lex will - Videos',
4714 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4715 'uploader': 'lex will',
4716 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4717 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4718 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4719 'channel': 'lex will',
4720 'tags': ['bible', 'history', 'prophesy'],
4721 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4722 'channel_follower_count': int
a6213a49 4723 },
4724 'playlist_mincount': 199,
4725 }, {
4726 'note': 'Playlists tab',
4727 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4728 'info_dict': {
4729 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4730 'title': 'lex will - Playlists',
4731 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4732 'uploader': 'lex will',
4733 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4734 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4735 'channel': 'lex will',
4736 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4737 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4738 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4739 'channel_follower_count': int
a6213a49 4740 },
4741 'playlist_mincount': 17,
4742 }, {
4743 'note': 'Community tab',
4744 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4745 'info_dict': {
4746 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4747 'title': 'lex will - Community',
4748 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4749 'uploader': 'lex will',
4750 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4751 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4752 'channel': 'lex will',
4753 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4754 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4755 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4756 'channel_follower_count': int
a6213a49 4757 },
4758 'playlist_mincount': 18,
4759 }, {
4760 'note': 'Channels tab',
4761 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4762 'info_dict': {
4763 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4764 'title': 'lex will - Channels',
4765 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4766 'uploader': 'lex will',
4767 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4768 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4769 'channel': 'lex will',
4770 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4771 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4772 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4773 'channel_follower_count': int
a6213a49 4774 },
4775 'playlist_mincount': 12,
4776 }, {
4777 'note': 'Search tab',
4778 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4779 'playlist_mincount': 40,
4780 'info_dict': {
4781 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4782 'title': '3Blue1Brown - Search - linear algebra',
4783 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4784 'uploader': '3Blue1Brown',
4785 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4786 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4787 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4788 'tags': ['Mathematics'],
4789 'channel': '3Blue1Brown',
4790 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4791 'channel_follower_count': int
a6213a49 4792 },
4793 }, {
4794 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4795 'only_matching': True,
4796 }, {
4797 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4798 'only_matching': True,
4799 }, {
4800 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4801 'only_matching': True,
4802 }, {
4803 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4804 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4805 'info_dict': {
4806 'title': '29C3: Not my department',
4807 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4808 'uploader': 'Christiaan008',
4809 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4810 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4811 'tags': [],
4812 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4813 'view_count': int,
4814 'modified_date': '20150605',
4815 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4816 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4817 'channel': 'Christiaan008',
a6213a49 4818 },
4819 'playlist_count': 96,
4820 }, {
4821 'note': 'Large playlist',
4822 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4823 'info_dict': {
4824 'title': 'Uploads from Cauchemar',
4825 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4826 'uploader': 'Cauchemar',
4827 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4828 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4829 'tags': [],
4830 'modified_date': r're:\d{8}',
4831 'channel': 'Cauchemar',
4832 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4833 'view_count': int,
4834 'description': '',
4835 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4836 },
4837 'playlist_mincount': 1123,
976ae3ea 4838 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4839 }, {
4840 'note': 'even larger playlist, 8832 videos',
4841 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4842 'only_matching': True,
4843 }, {
4844 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4845 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4846 'info_dict': {
4847 'title': 'Uploads from Interstellar Movie',
4848 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4849 'uploader': 'Interstellar Movie',
4850 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4851 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4852 'tags': [],
4853 'view_count': int,
4854 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4855 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4856 'channel': 'Interstellar Movie',
4857 'description': '',
4858 'modified_date': r're:\d{8}',
a6213a49 4859 },
4860 'playlist_mincount': 21,
4861 }, {
4862 'note': 'Playlist with "show unavailable videos" button',
4863 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4864 'info_dict': {
4865 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4866 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4867 'uploader': 'Phim Siêu Nhân Nhật Bản',
4868 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4869 'view_count': int,
4870 'channel': 'Phim Siêu Nhân Nhật Bản',
4871 'tags': [],
4872 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4873 'description': '',
4874 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4875 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4876 'modified_date': r're:\d{8}',
a6213a49 4877 },
4878 'playlist_mincount': 200,
976ae3ea 4879 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4880 }, {
4881 'note': 'Playlist with unavailable videos in page 7',
4882 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4883 'info_dict': {
4884 'title': 'Uploads from BlankTV',
4885 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4886 'uploader': 'BlankTV',
4887 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4888 'channel': 'BlankTV',
4889 'channel_url': 'https://www.youtube.com/c/blanktv',
4890 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4891 'view_count': int,
4892 'tags': [],
4893 'uploader_url': 'https://www.youtube.com/c/blanktv',
4894 'modified_date': r're:\d{8}',
4895 'description': '',
a6213a49 4896 },
4897 'playlist_mincount': 1000,
976ae3ea 4898 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4899 }, {
4900 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4901 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4902 'info_dict': {
4903 'title': 'Data Analysis with Dr Mike Pound',
4904 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4905 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4906 'uploader': 'Computerphile',
4907 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4908 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4909 'tags': [],
4910 'view_count': int,
4911 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4912 'channel_url': 'https://www.youtube.com/user/Computerphile',
4913 'channel': 'Computerphile',
a6213a49 4914 },
4915 'playlist_mincount': 11,
4916 }, {
4917 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4918 'only_matching': True,
4919 }, {
4920 'note': 'Playlist URL that does not actually serve a playlist',
4921 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4922 'info_dict': {
4923 'id': 'FqZTN594JQw',
4924 'ext': 'webm',
4925 'title': "Smiley's People 01 detective, Adventure Series, Action",
4926 'uploader': 'STREEM',
4927 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4928 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4929 'upload_date': '20150526',
4930 'license': 'Standard YouTube License',
4931 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4932 'categories': ['People & Blogs'],
4933 'tags': list,
4934 'view_count': int,
4935 'like_count': int,
a6213a49 4936 },
4937 'params': {
4938 'skip_download': True,
4939 },
4940 'skip': 'This video is not available.',
4941 'add_ie': [YoutubeIE.ie_key()],
4942 }, {
4943 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4944 'only_matching': True,
4945 }, {
4946 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4947 'only_matching': True,
4948 }, {
4949 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4950 'info_dict': {
6c73052c 4951 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4952 'ext': 'mp4',
976ae3ea 4953 'title': str,
a6213a49 4954 'uploader': 'Sky News',
4955 'uploader_id': 'skynews',
4956 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4957 'upload_date': r're:\d{8}',
976ae3ea 4958 'description': str,
a6213a49 4959 'categories': ['News & Politics'],
4960 'tags': list,
4961 'like_count': int,
6c73052c 4962 'release_timestamp': 1642502819,
976ae3ea 4963 'channel': 'Sky News',
4964 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4965 'age_limit': 0,
4966 'view_count': int,
6c73052c 4967 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4968 'playable_in_embed': True,
6c73052c 4969 'release_date': '20220118',
976ae3ea 4970 'availability': 'public',
4971 'live_status': 'is_live',
4972 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4973 'channel_follower_count': int
a6213a49 4974 },
4975 'params': {
4976 'skip_download': True,
4977 },
976ae3ea 4978 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4979 }, {
4980 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4981 'info_dict': {
4982 'id': 'a48o2S1cPoo',
4983 'ext': 'mp4',
4984 'title': 'The Young Turks - Live Main Show',
4985 'uploader': 'The Young Turks',
4986 'uploader_id': 'TheYoungTurks',
4987 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4988 'upload_date': '20150715',
4989 'license': 'Standard YouTube License',
4990 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4991 'categories': ['News & Politics'],
4992 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4993 'like_count': int,
a6213a49 4994 },
4995 'params': {
4996 'skip_download': True,
4997 },
4998 'only_matching': True,
4999 }, {
5000 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5001 'only_matching': True,
5002 }, {
5003 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5004 'only_matching': True,
5005 }, {
5006 'note': 'A channel that is not live. Should raise error',
5007 'url': 'https://www.youtube.com/user/numberphile/live',
5008 'only_matching': True,
5009 }, {
5010 'url': 'https://www.youtube.com/feed/trending',
5011 'only_matching': True,
5012 }, {
5013 'url': 'https://www.youtube.com/feed/library',
5014 'only_matching': True,
5015 }, {
5016 'url': 'https://www.youtube.com/feed/history',
5017 'only_matching': True,
5018 }, {
5019 'url': 'https://www.youtube.com/feed/subscriptions',
5020 'only_matching': True,
5021 }, {
5022 'url': 'https://www.youtube.com/feed/watch_later',
5023 'only_matching': True,
5024 }, {
5025 'note': 'Recommended - redirects to home page.',
5026 'url': 'https://www.youtube.com/feed/recommended',
5027 'only_matching': True,
5028 }, {
5029 'note': 'inline playlist with not always working continuations',
5030 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5031 'only_matching': True,
5032 }, {
5033 'url': 'https://www.youtube.com/course',
5034 'only_matching': True,
5035 }, {
5036 'url': 'https://www.youtube.com/zsecurity',
5037 'only_matching': True,
5038 }, {
5039 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5040 'only_matching': True,
5041 }, {
5042 'url': 'https://www.youtube.com/TheYoungTurks/live',
5043 'only_matching': True,
5044 }, {
5045 'url': 'https://www.youtube.com/hashtag/cctv9',
5046 'info_dict': {
5047 'id': 'cctv9',
5048 'title': '#cctv9',
976ae3ea 5049 'tags': [],
a6213a49 5050 },
5051 'playlist_mincount': 350,
5052 }, {
5053 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5054 'only_matching': True,
5055 }, {
5056 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5057 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5058 'only_matching': True
5059 }, {
5060 'note': '/browse/ should redirect to /channel/',
5061 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5062 'only_matching': True
5063 }, {
5064 'note': 'VLPL, should redirect to playlist?list=PL...',
5065 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5066 'info_dict': {
5067 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5068 'uploader': 'NoCopyrightSounds',
5069 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5070 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5071 'title': 'NCS Releases',
976ae3ea 5072 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5073 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5074 'modified_date': r're:\d{8}',
5075 'view_count': int,
5076 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5077 'tags': [],
5078 'channel': 'NoCopyrightSounds',
a6213a49 5079 },
5080 'playlist_mincount': 166,
976ae3ea 5081 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5082 }, {
5083 'note': 'Topic, should redirect to playlist?list=UU...',
5084 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5085 'info_dict': {
5086 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5087 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5088 'title': 'Uploads from Royalty Free Music - Topic',
5089 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5090 'tags': [],
5091 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5092 'channel': 'Royalty Free Music - Topic',
5093 'view_count': int,
5094 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5095 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5096 'modified_date': r're:\d{8}',
5097 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5098 'description': '',
a6213a49 5099 },
5100 'expected_warnings': [
a6213a49 5101 'The URL does not have a videos tab',
976ae3ea 5102 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5103 ],
5104 'playlist_mincount': 101,
5105 }, {
5106 'note': 'Topic without a UU playlist',
5107 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5108 'info_dict': {
5109 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5110 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5111 'tags': [],
a6213a49 5112 },
5113 'expected_warnings': [
976ae3ea 5114 'the playlist redirect gave error',
a6213a49 5115 ],
5116 'playlist_mincount': 9,
5117 }, {
5118 'note': 'Youtube music Album',
5119 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5120 'info_dict': {
5121 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5122 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5123 'tags': [],
5124 'view_count': int,
5125 'description': '',
5126 'availability': 'unlisted',
5127 'modified_date': r're:\d{8}',
a6213a49 5128 },
5129 'playlist_count': 50,
5130 }, {
5131 'note': 'unlisted single video playlist',
5132 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5133 'info_dict': {
5134 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5135 'uploader': 'colethedj',
5136 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5137 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5138 'availability': 'unlisted',
5139 'tags': [],
5140 'modified_date': '20211208',
5141 'channel': 'colethedj',
5142 'view_count': int,
5143 'description': '',
5144 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5145 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5146 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5147 },
5148 'playlist_count': 1,
5149 }, {
5150 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5151 'url': 'https://www.youtube.com/feed/recommended',
5152 'info_dict': {
5153 'id': 'recommended',
5154 'title': 'recommended',
6c73052c 5155 'tags': [],
a6213a49 5156 },
5157 'playlist_mincount': 50,
5158 'params': {
5159 'skip_download': True,
5160 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5161 },
5162 }, {
5163 'note': 'API Fallback: /videos tab, sorted by oldest first',
5164 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5165 'info_dict': {
5166 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5167 'title': 'Cody\'sLab - Videos',
5168 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5169 'uploader': 'Cody\'sLab',
5170 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5171 'channel': 'Cody\'sLab',
5172 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5173 'tags': [],
5174 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5175 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5176 'channel_follower_count': int
a6213a49 5177 },
5178 'playlist_mincount': 650,
5179 'params': {
5180 'skip_download': True,
5181 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5182 },
5183 }, {
5184 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5185 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5186 'info_dict': {
5187 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5188 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5189 'title': 'Uploads from Royalty Free Music - Topic',
5190 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5191 'modified_date': r're:\d{8}',
5192 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5193 'description': '',
5194 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5195 'tags': [],
5196 'channel': 'Royalty Free Music - Topic',
5197 'view_count': int,
5198 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5199 },
5200 'expected_warnings': [
976ae3ea 5201 'does not have a videos tab',
5202 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5203 ],
5204 'playlist_mincount': 101,
5205 'params': {
5206 'skip_download': True,
5207 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5208 },
7c219ea6 5209 }, {
5210 'note': 'non-standard redirect to regional channel',
5211 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5212 'only_matching': True
61d3665d 5213 }, {
5214 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5215 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5216 'info_dict': {
5217 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5218 'modified_date': '20220407',
5219 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5220 'tags': [],
5221 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5222 'uploader': 'pukkandan',
5223 'availability': 'unlisted',
5224 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5225 'channel': 'pukkandan',
5226 'description': 'Test for collaborative playlist',
5227 'title': 'yt-dlp test - collaborative playlist',
5228 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5229 },
5230 'playlist_mincount': 2
a6213a49 5231 }]
5232
5233 @classmethod
5234 def suitable(cls, url):
86e5f3ed 5235 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5236
64f36541 5237 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5238
182bda88 5239 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5240 def _real_extract(self, url, smuggled_data):
cd7c66cf 5241 item_id = self._match_id(url)
5242 url = compat_urlparse.urlunparse(
5243 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5244 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5245
fe03a6cd 5246 def get_mobj(url):
37e57a9f 5247 mobj = self._URL_RE.match(url).groupdict()
07cce701 5248 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5249 return mobj
5250
37e57a9f 5251 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5252 # Youtube returns incomplete data if tabname is not lower case
5253 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5254 if is_channel:
5255 if smuggled_data.get('is_music_url'):
37e57a9f 5256 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5257 item_id = item_id[2:]
37e57a9f 5258 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5259 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5260 mdata = self._extract_tab_endpoint(
37e57a9f 5261 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5262 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5263 get_all=False, expected_type=compat_str)
ac56cf38 5264 if not murl:
37e57a9f 5265 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5266 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5267 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5268 pre = f'https://www.youtube.com/channel/{item_id}'
5269
64f36541 5270 original_tab_name = tab
fe03a6cd 5271 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5272 # Home URLs should redirect to /videos/
37e57a9f 5273 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5274 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5275 tab = '/videos'
5276
5277 url = ''.join((pre, tab, post))
5278 mobj = get_mobj(url)
cd7c66cf 5279
5280 # Handle both video/playlist URLs
201c1459 5281 qs = parse_qs(url)
86e5f3ed 5282 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5283
fe03a6cd 5284 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5285 if not playlist_id:
fe03a6cd 5286 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5287 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5288 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5289 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5290 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5291 mobj = get_mobj(url)
cd7c66cf 5292
5293 if video_id and playlist_id:
a06916d9 5294 if self.get_param('noplaylist'):
37e57a9f 5295 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5296 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5297 ie=YoutubeIE.ie_key(), video_id=video_id)
5298 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5299
ac56cf38 5300 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5301
7c219ea6 5302 # YouTube may provide a non-standard redirect to the regional channel
5303 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5304 redirect_url = traverse_obj(
5305 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5306 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5307 redirect_url = ''.join((
5308 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5309 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5310 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5311
37e57a9f 5312 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5313 if tabs:
5314 selected_tab = self._extract_selected_tab(tabs)
64f36541 5315 selected_tab_name = selected_tab.get('title', '').lower()
5316 if selected_tab_name == 'home':
5317 selected_tab_name = 'featured'
5318 requested_tab_name = mobj['tab'][1:]
09f1580e 5319 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5320 if requested_tab_name == 'live':
09f1580e 5321 # Live tab should have redirected to the video
5322 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5323 if requested_tab_name not in ('', selected_tab_name):
5324 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5325 if not original_tab_name:
5326 if item_id[:2] == 'UC':
5327 # Topic channels don't have /videos. Use the equivalent playlist instead
5328 pl_id = f'UU{item_id[2:]}'
5329 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5330 try:
5331 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5332 except ExtractorError:
5333 redirect_warning += ' and the playlist redirect gave error'
5334 else:
5335 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5336 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5337 if selected_tab_name and selected_tab_name != requested_tab_name:
5338 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5339 else:
5340 raise ExtractorError(redirect_warning, expected=True)
18db7548 5341
37e57a9f 5342 if redirect_warning:
64f36541 5343 self.to_screen(redirect_warning)
37e57a9f 5344 self.write_debug(f'Final URL: {url}')
18db7548 5345
358de58c 5346 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5347 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5348 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5349 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5350 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5351 if tabs:
ac56cf38 5352 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5353
37e57a9f 5354 playlist = traverse_obj(
5355 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5356 if playlist:
ac56cf38 5357 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5358
37e57a9f 5359 video_id = traverse_obj(
5360 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5361 if video_id:
09f1580e 5362 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5363 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5364 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5365 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5366
8bdd16b4 5367 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5368
c5e8d7af 5369
8bdd16b4 5370class YoutubePlaylistIE(InfoExtractor):
96565c7e 5371 IE_DESC = 'YouTube playlists'
8bdd16b4 5372 _VALID_URL = r'''(?x)(?:
5373 (?:https?://)?
5374 (?:\w+\.)?
5375 (?:
5376 (?:
5377 youtube(?:kids)?\.com|
d9190e44 5378 %(invidious)s
8bdd16b4 5379 )
5380 /.*?\?.*?\blist=
5381 )?
5382 (?P<id>%(playlist_id)s)
d9190e44
RH
5383 )''' % {
5384 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5385 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5386 }
8bdd16b4 5387 IE_NAME = 'youtube:playlist'
cdc628a4 5388 _TESTS = [{
8bdd16b4 5389 'note': 'issue #673',
5390 'url': 'PLBB231211A4F62143',
cdc628a4 5391 'info_dict': {
8bdd16b4 5392 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5393 'id': 'PLBB231211A4F62143',
976ae3ea 5394 'uploader': 'Wickman',
8bdd16b4 5395 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5396 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5397 'view_count': int,
5398 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5399 'modified_date': r're:\d{8}',
5400 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5401 'channel': 'Wickman',
5402 'tags': [],
5403 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5404 },
5405 'playlist_mincount': 29,
5406 }, {
5407 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5408 'info_dict': {
5409 'title': 'YDL_safe_search',
5410 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5411 },
5412 'playlist_count': 2,
5413 'skip': 'This playlist is private',
9558dcec 5414 }, {
8bdd16b4 5415 'note': 'embedded',
5416 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5417 'playlist_count': 4,
9558dcec 5418 'info_dict': {
8bdd16b4 5419 'title': 'JODA15',
5420 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5421 'uploader': 'milan',
5422 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5423 'description': '',
5424 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5425 'tags': [],
5426 'modified_date': '20140919',
5427 'view_count': int,
5428 'channel': 'milan',
5429 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5430 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5431 },
5432 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5433 }, {
8bdd16b4 5434 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5435 'playlist_mincount': 654,
8bdd16b4 5436 'info_dict': {
5437 'title': '2018 Chinese New Singles (11/6 updated)',
5438 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5439 'uploader': 'LBK',
5440 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5441 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5442 'channel': 'LBK',
5443 'view_count': int,
5444 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5445 'tags': [],
5446 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5447 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5448 'modified_date': r're:\d{8}',
5449 },
5450 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5451 }, {
29f7c58a 5452 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5453 'only_matching': True,
5454 }, {
5455 # music album playlist
5456 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5457 'only_matching': True,
5458 }]
5459
5460 @classmethod
5461 def suitable(cls, url):
201c1459 5462 if YoutubeTabIE.suitable(url):
5463 return False
49a57e70 5464 from ..utils import parse_qs
201c1459 5465 qs = parse_qs(url)
5466 if qs.get('v', [None])[0]:
5467 return False
86e5f3ed 5468 return super().suitable(url)
29f7c58a 5469
5470 def _real_extract(self, url):
5471 playlist_id = self._match_id(url)
46953e7e 5472 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5473 url = update_url_query(
5474 'https://www.youtube.com/playlist',
5475 parse_qs(url) or {'list': playlist_id})
5476 if is_music_url:
5477 url = smuggle_url(url, {'is_music_url': True})
5478 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5479
5480
5481class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5482 IE_DESC = 'youtu.be'
29f7c58a 5483 _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}
5484 _TESTS = [{
8bdd16b4 5485 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5486 'info_dict': {
5487 'id': 'yeWKywCrFtk',
5488 'ext': 'mp4',
5489 'title': 'Small Scale Baler and Braiding Rugs',
5490 'uploader': 'Backus-Page House Museum',
5491 'uploader_id': 'backuspagemuseum',
5492 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5493 'upload_date': '20161008',
5494 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5495 'categories': ['Nonprofits & Activism'],
5496 'tags': list,
5497 'like_count': int,
976ae3ea 5498 'age_limit': 0,
5499 'playable_in_embed': True,
5500 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5501 'channel': 'Backus-Page House Museum',
5502 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5503 'live_status': 'not_live',
5504 'view_count': int,
5505 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5506 'availability': 'public',
5507 'duration': 59,
8bdd16b4 5508 },
5509 'params': {
5510 'noplaylist': True,
5511 'skip_download': True,
5512 },
39e7107d 5513 }, {
8bdd16b4 5514 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5515 'only_matching': True,
cdc628a4
PH
5516 }]
5517
8bdd16b4 5518 def _real_extract(self, url):
5ad28e7f 5519 mobj = self._match_valid_url(url)
29f7c58a 5520 video_id = mobj.group('id')
5521 playlist_id = mobj.group('playlist_id')
8bdd16b4 5522 return self.url_result(
29f7c58a 5523 update_url_query('https://www.youtube.com/watch', {
5524 'v': video_id,
5525 'list': playlist_id,
5526 'feature': 'youtu.be',
5527 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5528
5529
b6ce9bb0 5530class YoutubeLivestreamEmbedIE(InfoExtractor):
5531 IE_DESC = 'YouTube livestream embeds'
5532 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5533 _TESTS = [{
5534 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5535 'only_matching': True,
5536 }]
5537
5538 def _real_extract(self, url):
5539 channel_id = self._match_id(url)
5540 return self.url_result(
5541 f'https://www.youtube.com/channel/{channel_id}/live',
5542 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5543
5544
8bdd16b4 5545class YoutubeYtUserIE(InfoExtractor):
96565c7e 5546 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5547 IE_NAME = 'youtube:user'
8bdd16b4 5548 _VALID_URL = r'ytuser:(?P<id>.+)'
5549 _TESTS = [{
5550 'url': 'ytuser:phihag',
5551 'only_matching': True,
5552 }]
5553
5554 def _real_extract(self, url):
5555 user_id = self._match_id(url)
5556 return self.url_result(
c586f9e8 5557 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5558 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5559
b05654f0 5560
3d3dddc9 5561class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5562 IE_NAME = 'youtube:favorites'
96565c7e 5563 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5564 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5565 _LOGIN_REQUIRED = True
5566 _TESTS = [{
5567 'url': ':ytfav',
5568 'only_matching': True,
5569 }, {
5570 'url': ':ytfavorites',
5571 'only_matching': True,
5572 }]
5573
5574 def _real_extract(self, url):
5575 return self.url_result(
5576 'https://www.youtube.com/playlist?list=LL',
5577 ie=YoutubeTabIE.ie_key())
5578
5579
ca5300c7 5580class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5581 IE_NAME = 'youtube:notif'
5582 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5583 _VALID_URL = r':ytnotif(?:ication)?s?'
5584 _LOGIN_REQUIRED = True
5585 _TESTS = [{
5586 'url': ':ytnotif',
5587 'only_matching': True,
5588 }, {
5589 'url': ':ytnotifications',
5590 'only_matching': True,
5591 }]
5592
5593 def _extract_notification_menu(self, response, continuation_list):
5594 notification_list = traverse_obj(
5595 response,
5596 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5597 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5598 expected_type=list) or []
5599 continuation_list[0] = None
5600 for item in notification_list:
5601 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5602 if entry:
5603 yield entry
5604 continuation = item.get('continuationItemRenderer')
5605 if continuation:
5606 continuation_list[0] = continuation
5607
5608 def _extract_notification_renderer(self, notification):
5609 video_id = traverse_obj(
5610 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5611 url = f'https://www.youtube.com/watch?v={video_id}'
5612 channel_id = None
5613 if not video_id:
5614 browse_ep = traverse_obj(
5615 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5616 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5617 post_id = self._search_regex(
5618 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5619 'post id', default=None)
5620 if not channel_id or not post_id:
5621 return
5622 # The direct /post url redirects to this in the browser
5623 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5624
5625 channel = traverse_obj(
5626 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5627 expected_type=str)
5628 title = self._search_regex(
5629 rf'{re.escape(channel)} [^:]+: (.+)', self._get_text(notification, 'shortMessage'),
5630 'video title', default=None)
5631 if title:
5632 title = title.replace('\xad', '') # remove soft hyphens
5633 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5634 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5635 else None)
5636 return {
5637 '_type': 'url',
5638 'url': url,
5639 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5640 'video_id': video_id,
5641 'title': title,
5642 'channel_id': channel_id,
5643 'channel': channel,
5644 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5645 'upload_date': upload_date,
5646 }
5647
5648 def _notification_menu_entries(self, ytcfg):
5649 continuation_list = [None]
5650 response = None
5651 for page in itertools.count(1):
5652 ctoken = traverse_obj(
5653 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5654 response = self._extract_response(
5655 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5656 ep='notification/get_notification_menu', check_get_keys='actions',
5657 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5658 yield from self._extract_notification_menu(response, continuation_list)
5659 if not continuation_list[0]:
5660 break
5661
5662 def _real_extract(self, url):
5663 display_id = 'notifications'
5664 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5665 self._report_playlist_authcheck(ytcfg)
5666 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5667
5668
a6213a49 5669class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5670 IE_DESC = 'YouTube search'
78caa52a 5671 IE_NAME = 'youtube:search'
b05654f0 5672 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5673 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5674 _TESTS = [{
5675 'url': 'ytsearch5:youtube-dl test video',
5676 'playlist_count': 5,
5677 'info_dict': {
5678 'id': 'youtube-dl test video',
5679 'title': 'youtube-dl test video',
5680 }
5681 }]
b05654f0 5682
a61fd4cf 5683
5f7cb91a 5684class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5685 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5686 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5687 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5688 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5689 _TESTS = [{
5690 'url': 'ytsearchdate5:youtube-dl test video',
5691 'playlist_count': 5,
5692 'info_dict': {
5693 'id': 'youtube-dl test video',
5694 'title': 'youtube-dl test video',
5695 }
5696 }]
75dff0ee 5697
c9ae7b95 5698
a6213a49 5699class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5700 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5701 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5702 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5703 _TESTS = [{
5704 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5705 'playlist_mincount': 5,
5706 'info_dict': {
11f9be09 5707 'id': 'youtube-dl test video',
3462ffa8 5708 'title': 'youtube-dl test video',
5709 }
a61fd4cf 5710 }, {
5711 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5712 'playlist_mincount': 5,
5713 'info_dict': {
5714 'id': 'python',
5715 'title': 'python',
5716 }
ad210f4f 5717 }, {
5718 'url': 'https://www.youtube.com/results?search_query=%23cats',
5719 'playlist_mincount': 1,
5720 'info_dict': {
5721 'id': '#cats',
5722 'title': '#cats',
5723 'entries': [{
5724 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5725 'title': '#cats',
5726 }],
5727 },
3462ffa8 5728 }, {
5729 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5730 'only_matching': True,
5731 }]
5732
5733 def _real_extract(self, url):
4dfbf869 5734 qs = parse_qs(url)
386e1dd9 5735 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5736 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5737
5738
16aa9ea4 5739class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5740 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5741 IE_NAME = 'youtube:music:search_url'
5742 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5743 _TESTS = [{
5744 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5745 'playlist_count': 16,
5746 'info_dict': {
5747 'id': 'royalty free music',
5748 'title': 'royalty free music',
5749 }
5750 }, {
5751 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5752 'playlist_mincount': 30,
5753 'info_dict': {
5754 'id': 'royalty free music - songs',
5755 'title': 'royalty free music - songs',
5756 },
5757 'params': {'extract_flat': 'in_playlist'}
5758 }, {
5759 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5760 'playlist_mincount': 30,
5761 'info_dict': {
5762 'id': 'royalty free music - community playlists',
5763 'title': 'royalty free music - community playlists',
5764 },
5765 'params': {'extract_flat': 'in_playlist'}
5766 }]
5767
5768 _SECTIONS = {
5769 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5770 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5771 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5772 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5773 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5774 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5775 }
5776
5777 def _real_extract(self, url):
5778 qs = parse_qs(url)
5779 query = (qs.get('search_query') or qs.get('q'))[0]
5780 params = qs.get('sp', (None,))[0]
5781 if params:
5782 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5783 else:
5784 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5785 params = self._SECTIONS.get(section)
5786 if not params:
5787 section = None
5788 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5789 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5790
5791
182bda88 5792class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5793 """
25f14e9f 5794 Base class for feed extractors
82d02080 5795 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5796 """
b2e8bc1b 5797 _LOGIN_REQUIRED = True
82d02080 5798 _FEED_NAME = 'feeds'
a25bca9f 5799
5800 def _real_initialize(self):
5801 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5802
82d02080 5803 @classproperty
d7ae0639 5804 def IE_NAME(self):
82d02080 5805 return f'youtube:{self._FEED_NAME}'
04cc9617 5806
3853309f 5807 def _real_extract(self, url):
3d3dddc9 5808 return self.url_result(
182bda88 5809 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5810
5811
ef2f3c7f 5812class YoutubeWatchLaterIE(InfoExtractor):
5813 IE_NAME = 'youtube:watchlater'
96565c7e 5814 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5815 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5816 _TESTS = [{
8bdd16b4 5817 'url': ':ytwatchlater',
bc7a9cd8
S
5818 'only_matching': True,
5819 }]
25f14e9f
S
5820
5821 def _real_extract(self, url):
ef2f3c7f 5822 return self.url_result(
5823 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5824
5825
25f14e9f 5826class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5827 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5828 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5829 _FEED_NAME = 'recommended'
45db527f 5830 _LOGIN_REQUIRED = False
3d3dddc9 5831 _TESTS = [{
5832 'url': ':ytrec',
5833 'only_matching': True,
5834 }, {
5835 'url': ':ytrecommended',
5836 'only_matching': True,
5837 }, {
5838 'url': 'https://youtube.com',
5839 'only_matching': True,
5840 }]
1ed5b5c9 5841
1ed5b5c9 5842
25f14e9f 5843class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5844 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5845 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5846 _FEED_NAME = 'subscriptions'
3d3dddc9 5847 _TESTS = [{
5848 'url': ':ytsubs',
5849 'only_matching': True,
5850 }, {
5851 'url': ':ytsubscriptions',
5852 'only_matching': True,
5853 }]
1ed5b5c9 5854
1ed5b5c9 5855
25f14e9f 5856class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5857 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5858 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5859 _FEED_NAME = 'history'
3d3dddc9 5860 _TESTS = [{
5861 'url': ':ythistory',
5862 'only_matching': True,
5863 }]
1ed5b5c9
JMF
5864
5865
6e634cbe 5866class YoutubeStoriesIE(InfoExtractor):
5867 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5868 IE_NAME = 'youtube:stories'
5869 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5870 _TESTS = [{
5871 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5872 'only_matching': True,
5873 }]
5874
5875 def _real_extract(self, url):
5876 playlist_id = f'RLTD{self._match_id(url)}'
5877 return self.url_result(
5878 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5879 ie=YoutubeTabIE, video_id=playlist_id)
5880
5881
15870e90
PH
5882class YoutubeTruncatedURLIE(InfoExtractor):
5883 IE_NAME = 'youtube:truncated_url'
5884 IE_DESC = False # Do not list
975d35db 5885 _VALID_URL = r'''(?x)
b95aab84
PH
5886 (?:https?://)?
5887 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5888 (?:watch\?(?:
c4808c60 5889 feature=[a-z_]+|
b95aab84
PH
5890 annotation_id=annotation_[^&]+|
5891 x-yt-cl=[0-9]+|
c1708b89 5892 hl=[^&]*|
287be8c6 5893 t=[0-9]+
b95aab84
PH
5894 )?
5895 |
5896 attribution_link\?a=[^&]+
5897 )
5898 $
975d35db 5899 '''
15870e90 5900
c4808c60 5901 _TESTS = [{
2d3d2997 5902 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5903 'only_matching': True,
dc2fc736 5904 }, {
2d3d2997 5905 'url': 'https://www.youtube.com/watch?',
dc2fc736 5906 'only_matching': True,
b95aab84
PH
5907 }, {
5908 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5909 'only_matching': True,
5910 }, {
5911 'url': 'https://www.youtube.com/watch?feature=foo',
5912 'only_matching': True,
c1708b89
PH
5913 }, {
5914 'url': 'https://www.youtube.com/watch?hl=en-GB',
5915 'only_matching': True,
287be8c6
PH
5916 }, {
5917 'url': 'https://www.youtube.com/watch?t=2372',
5918 'only_matching': True,
c4808c60
PH
5919 }]
5920
15870e90
PH
5921 def _real_extract(self, url):
5922 raise ExtractorError(
78caa52a
PH
5923 'Did you forget to quote the URL? Remember that & is a meta '
5924 'character in most shells, so you want to put the URL in quotes, '
3867038a 5925 'like youtube-dl '
2d3d2997 5926 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5927 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5928 expected=True)
772fd5cc
PH
5929
5930
3cd786db 5931class YoutubeClipIE(InfoExtractor):
5932 IE_NAME = 'youtube:clip'
5933 IE_DESC = False # Do not list
5934 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5935
5936 def _real_extract(self, url):
5937 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5938 return self.url_result(url, 'Generic')
5939
5940
772fd5cc
PH
5941class YoutubeTruncatedIDIE(InfoExtractor):
5942 IE_NAME = 'youtube:truncated_id'
5943 IE_DESC = False # Do not list
b95aab84 5944 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5945
5946 _TESTS = [{
5947 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5948 'only_matching': True,
5949 }]
5950
5951 def _real_extract(self, url):
5952 video_id = self._match_id(url)
5953 raise ExtractorError(
86e5f3ed 5954 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 5955 expected=True)