]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[youtube] Add extractor `YoutubeMusicSearchURLIE`
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
d92f5d5a 5import calendar
109dd3b2 6import copy
fe93e2c4 7import datetime
adbc4ec4 8import functools
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
720c3099 12import math
c4417ddb 13import os.path
d77ab8e2 14import random
c5e8d7af 15import re
46383212 16import sys
8a784c74 17import time
e0df6211 18import traceback
adbc4ec4 19import threading
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 22from ..compat import (
edf3e38e 23 compat_chr,
29f7c58a 24 compat_HTTPError,
c5e8d7af 25 compat_parse_qs,
545cc85d 26 compat_str,
7fd002c0 27 compat_urllib_parse_unquote_plus,
15707c7e 28 compat_urllib_parse_urlencode,
7c80519c 29 compat_urllib_parse_urlparse,
7c61bd36 30 compat_urlparse,
4bb4a188 31)
545cc85d 32from ..jsinterp import JSInterpreter
4bb4a188 33from ..utils import (
720c3099 34 bug_reports_message,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
c5e8d7af 39 ExtractorError,
2d30521a 40 float_or_none,
11f9be09 41 format_field,
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,
a6213a49 48 NO_DEFAULT,
11f9be09 49 orderedSet,
6310acf5 50 parse_codecs,
49bd8c66 51 parse_count,
7c80519c 52 parse_duration,
7ea65411 53 parse_iso8601,
4dfbf869 54 parse_qs,
dca3ff4a 55 qualities,
c0ac49bc 56 remove_end,
3995d37d 57 remove_start,
cf7e015f 58 smuggle_url,
dbdaaa23 59 str_or_none,
c93d53f5 60 str_to_int,
f3aa3c3f 61 strftime_or_none,
7c365c21 62 traverse_obj,
556dbe7f 63 try_get,
c5e8d7af
PH
64 unescapeHTML,
65 unified_strdate,
f0d785d3 66 unified_timestamp,
cf7e015f 67 unsmuggle_url,
8bdd16b4 68 update_url_query,
21c340b8 69 url_or_none,
fe93e2c4 70 urljoin,
7c365c21 71 variadic,
c5e8d7af
PH
72)
73
5f6a1245 74
720c3099 75def get_first(obj, keys, **kwargs):
76 return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
77
78
000c15a4 79# any clients starting with _ cannot be explicity requested by the user
80INNERTUBE_CLIENTS = {
81 'web': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB',
18c7683d 86 'clientVersion': '2.20211221.00.00',
000c15a4 87 }
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
90 },
91 'web_embedded': {
92 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
93 'INNERTUBE_CONTEXT': {
94 'client': {
95 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 96 'clientVersion': '1.20211215.00.01',
000c15a4 97 },
98 },
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
100 },
101 'web_music': {
102 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
103 'INNERTUBE_HOST': 'music.youtube.com',
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_REMIX',
18c7683d 107 'clientVersion': '1.20211213.00.00',
000c15a4 108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
111 },
e7e94f2a 112 'web_creator': {
18c7683d 113 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'WEB_CREATOR',
18c7683d 117 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
118 }
119 },
120 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
121 },
000c15a4 122 'android': {
18c7683d 123 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 124 'INNERTUBE_CONTEXT': {
125 'client': {
126 'clientName': 'ANDROID',
18c7683d 127 'clientVersion': '16.49',
000c15a4 128 }
129 },
130 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 131 'REQUIRE_JS_PLAYER': False
000c15a4 132 },
133 'android_embedded': {
18c7683d 134 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 135 'INNERTUBE_CONTEXT': {
136 'client': {
137 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 138 'clientVersion': '16.49',
000c15a4 139 },
140 },
b6de707d 141 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
142 'REQUIRE_JS_PLAYER': False
000c15a4 143 },
144 'android_music': {
18c7683d 145 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 146 'INNERTUBE_CONTEXT': {
147 'client': {
148 'clientName': 'ANDROID_MUSIC',
18c7683d 149 'clientVersion': '4.57',
000c15a4 150 }
151 },
152 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 153 'REQUIRE_JS_PLAYER': False
000c15a4 154 },
e7e94f2a 155 'android_creator': {
18c7683d 156 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
157 'INNERTUBE_CONTEXT': {
158 'client': {
159 'clientName': 'ANDROID_CREATOR',
18c7683d 160 'clientVersion': '21.47',
e7e94f2a
D
161 },
162 },
b6de707d 163 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
164 'REQUIRE_JS_PLAYER': False
e7e94f2a 165 },
18c7683d 166 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
167 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 168 'ios': {
18c7683d 169 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS',
18c7683d 173 'clientVersion': '16.46',
174 'deviceModel': 'iPhone14,3',
000c15a4 175 }
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_embedded': {
000c15a4 181 'INNERTUBE_CONTEXT': {
182 'client': {
183 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 184 'clientVersion': '16.46',
185 'deviceModel': 'iPhone14,3',
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
191 'ios_music': {
18c7683d 192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
18c7683d 196 'clientVersion': '4.57',
000c15a4 197 },
198 },
b6de707d 199 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
200 'REQUIRE_JS_PLAYER': False
000c15a4 201 },
e7e94f2a
D
202 'ios_creator': {
203 'INNERTUBE_CONTEXT': {
204 'client': {
205 'clientName': 'IOS_CREATOR',
18c7683d 206 'clientVersion': '21.47',
e7e94f2a
D
207 },
208 },
b6de707d 209 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
210 'REQUIRE_JS_PLAYER': False
e7e94f2a 211 },
3619f78d 212 # mweb has 'ultralow' formats
213 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 214 'mweb': {
18c7683d 215 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 216 'INNERTUBE_CONTEXT': {
217 'client': {
218 'clientName': 'MWEB',
18c7683d 219 'clientVersion': '2.20211221.01.00',
000c15a4 220 }
221 },
222 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
18c7683d 223 }
000c15a4 224}
225
226
227def build_innertube_clients():
65c2fde2 228 third_party = {
229 'embedUrl': 'https://google.com', # Can be any valid URL
230 }
000c15a4 231 base_clients = ('android', 'web', 'ios', 'mweb')
232 priority = qualities(base_clients[::-1])
233
234 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 235 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 236 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 237 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 238 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
239 ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
240
241 if client in base_clients:
242 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
243 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
65c2fde2 244 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 245 agegate_ytcfg['priority'] -= 1
246 elif client.endswith('_embedded'):
65c2fde2 247 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 248 ytcfg['priority'] -= 2
249 else:
250 ytcfg['priority'] -= 3
251
252
253build_innertube_clients()
254
255
de7f3446 256class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 257 """Provide base functions for Youtube extractors"""
e00eb564 258
3462ffa8 259 _RESERVED_NAMES = (
3cd786db 260 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
6970b600 261 r'shorts|movies|results|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 262 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 263 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 264
3619f78d 265 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
266
b2e8bc1b 267 _NETRC_MACHINE = 'youtube'
3619f78d 268
b2e8bc1b
JMF
269 # If True it will raise an error if no login info is provided
270 _LOGIN_REQUIRED = False
271
d9190e44
RH
272 _INVIDIOUS_SITES = (
273 # invidious-redirect websites
274 r'(?:www\.)?redirect\.invidious\.io',
275 r'(?:(?:www|dev)\.)?invidio\.us',
276 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
277 r'(?:www\.)?invidious\.pussthecat\.org',
278 r'(?:www\.)?invidious\.zee\.li',
279 r'(?:www\.)?invidious\.ethibox\.fr',
280 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
281 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
282 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
283 # youtube-dl invidious instances list
284 r'(?:(?:www|no)\.)?invidiou\.sh',
285 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
286 r'(?:www\.)?invidious\.kabi\.tk',
287 r'(?:www\.)?invidious\.mastodon\.host',
288 r'(?:www\.)?invidious\.zapashcanon\.fr',
289 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
290 r'(?:www\.)?invidious\.tinfoil-hat\.net',
291 r'(?:www\.)?invidious\.himiko\.cloud',
292 r'(?:www\.)?invidious\.reallyancient\.tech',
293 r'(?:www\.)?invidious\.tube',
294 r'(?:www\.)?invidiou\.site',
295 r'(?:www\.)?invidious\.site',
296 r'(?:www\.)?invidious\.xyz',
297 r'(?:www\.)?invidious\.nixnet\.xyz',
298 r'(?:www\.)?invidious\.048596\.xyz',
299 r'(?:www\.)?invidious\.drycat\.fr',
300 r'(?:www\.)?inv\.skyn3t\.in',
301 r'(?:www\.)?tube\.poal\.co',
302 r'(?:www\.)?tube\.connect\.cafe',
303 r'(?:www\.)?vid\.wxzm\.sx',
304 r'(?:www\.)?vid\.mint\.lgbt',
305 r'(?:www\.)?vid\.puffyan\.us',
306 r'(?:www\.)?yewtu\.be',
307 r'(?:www\.)?yt\.elukerio\.org',
308 r'(?:www\.)?yt\.lelux\.fi',
309 r'(?:www\.)?invidious\.ggc-project\.de',
310 r'(?:www\.)?yt\.maisputain\.ovh',
311 r'(?:www\.)?ytprivate\.com',
312 r'(?:www\.)?invidious\.13ad\.de',
313 r'(?:www\.)?invidious\.toot\.koeln',
314 r'(?:www\.)?invidious\.fdn\.fr',
315 r'(?:www\.)?watch\.nettohikari\.com',
316 r'(?:www\.)?invidious\.namazso\.eu',
317 r'(?:www\.)?invidious\.silkky\.cloud',
318 r'(?:www\.)?invidious\.exonip\.de',
319 r'(?:www\.)?invidious\.riverside\.rocks',
320 r'(?:www\.)?invidious\.blamefran\.net',
321 r'(?:www\.)?invidious\.moomoo\.de',
322 r'(?:www\.)?ytb\.trom\.tf',
323 r'(?:www\.)?yt\.cyberhost\.uk',
324 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
325 r'(?:www\.)?qklhadlycap4cnod\.onion',
326 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
327 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
328 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
329 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
330 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
331 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
332 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
333 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
334 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
335 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
336 )
337
b2e8bc1b 338 def _login(self):
83317f69 339 """
340 Attempt to log in to YouTube.
83317f69 341 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
342 """
9d5d4d64 343
982ee69a
MB
344 if (self._LOGIN_REQUIRED
345 and self.get_param('cookiefile') is None
346 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 347 self.raise_login_required(
348 'Login details are needed to download this content', method='cookies')
68217024 349 username, password = self._get_login_info()
9d5d4d64 350 if username:
24b0a72b 351 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
b2e8bc1b 352
cce889b9 353 def _initialize_consent(self):
354 cookies = self._get_cookies('https://www.youtube.com/')
355 if cookies.get('__Secure-3PSID'):
356 return
357 consent_id = None
358 consent = cookies.get('CONSENT')
359 if consent:
360 if 'YES' in consent.value:
361 return
362 consent_id = self._search_regex(
363 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
364 if not consent_id:
365 consent_id = random.randint(100, 999)
366 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 367
f3aa3c3f 368 def _initialize_pref(self):
369 cookies = self._get_cookies('https://www.youtube.com/')
370 pref_cookie = cookies.get('PREF')
371 pref = {}
372 if pref_cookie:
373 try:
374 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
375 except ValueError:
376 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 377 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 378 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
379
b2e8bc1b 380 def _real_initialize(self):
f3aa3c3f 381 self._initialize_pref()
cce889b9 382 self._initialize_consent()
24b0a72b 383 self._login()
c5e8d7af 384
a0566bbf 385 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 386 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
387 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 388
000c15a4 389 def _get_default_ytcfg(self, client='web'):
390 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 391
000c15a4 392 def _get_innertube_host(self, client='web'):
393 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 394
000c15a4 395 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 396 # try_get but with fallback to default ytcfg client values when present
397 _func = lambda y: try_get(y, getter, expected_type)
398 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
399
000c15a4 400 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 401 return self._ytcfg_get_safe(
402 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
403 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 404
000c15a4 405 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 406 return self._ytcfg_get_safe(
407 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
408 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 409
000c15a4 410 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 411 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
412
000c15a4 413 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 414 context = get_first(
415 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 416 # Enforce language and tz for extraction
417 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
418 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 419 return context
420
cf87314d 421 _SAPISID = None
422
109dd3b2 423 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 424 time_now = round(time.time())
cf87314d 425 if self._SAPISID is None:
426 yt_cookies = self._get_cookies('https://www.youtube.com')
427 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
428 # See: https://github.com/yt-dlp/yt-dlp/issues/393
429 sapisid_cookie = dict_get(
430 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
431 if sapisid_cookie and sapisid_cookie.value:
432 self._SAPISID = sapisid_cookie.value
433 self.write_debug('Extracted SAPISID cookie')
434 # SAPISID cookie is required if not already present
435 if not yt_cookies.get('SAPISID'):
436 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
437 self._set_cookie(
438 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
439 else:
440 self._SAPISID = False
441 if not self._SAPISID:
442 return None
1974e99f 443 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
444 sapisidhash = hashlib.sha1(
cf87314d 445 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 446 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
447
448 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 449 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 450 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 451
109dd3b2 452 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 453 data.update(query)
11f9be09 454 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 455 real_headers.update({'content-type': 'application/json'})
456 if headers:
457 real_headers.update(headers)
545cc85d 458 return self._download_json(
109dd3b2 459 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 460 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 461 data=json.dumps(data).encode('utf8'), headers=real_headers,
462 query={'key': api_key or self._extract_api_key()})
463
ac56cf38 464 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
465 data = self._search_regex(
466 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
467 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
468 if data:
469 return self._parse_json(data, item_id, fatal=fatal)
0c148415 470
99e9e001 471 @staticmethod
472 def _extract_session_index(*data):
473 """
474 Index of current account in account list.
475 See: https://github.com/yt-dlp/yt-dlp/pull/519
476 """
477 for ytcfg in data:
478 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
479 if session_index is not None:
480 return session_index
481
482 # Deprecated?
483 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
484 if ytcfg:
485 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
486 if token:
487 return token
99e9e001 488 if webpage:
489 return self._search_regex(
490 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
491 'identity token', default=None, fatal=False)
a1c5d2ca
M
492
493 @staticmethod
fe93e2c4 494 def _extract_account_syncid(*args):
8ea3f7b9 495 """
496 Extract syncId required to download private playlists of secondary channels
fe93e2c4 497 @params response and/or ytcfg
8ea3f7b9 498 """
fe93e2c4 499 for data in args:
500 # ytcfg includes channel_syncid if on secondary channel
501 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
502 if delegated_sid:
503 return delegated_sid
504 sync_ids = (try_get(
505 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 506 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 507 if len(sync_ids) >= 2 and sync_ids[1]:
508 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
509 # and just "user_syncid||" for primary channel. We only want the channel_syncid
510 return sync_ids[0]
a1c5d2ca 511
ac56cf38 512 @staticmethod
513 def _extract_visitor_data(*args):
514 """
515 Extracts visitorData from an API response or ytcfg
516 Appears to be used to track session state
517 """
9222c381 518 return get_first(
6c73052c 519 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 520 expected_type=str)
ac56cf38 521
99e9e001 522 @property
523 def is_authenticated(self):
524 return bool(self._generate_sapisidhash_header())
525
11f9be09 526 def extract_ytcfg(self, video_id, webpage):
8c54a305 527 if not webpage:
528 return {}
29f7c58a 529 return self._parse_json(
530 self._search_regex(
531 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 532 default='{}'), video_id, fatal=False) or {}
533
11f9be09 534 def generate_api_headers(
99e9e001 535 self, *, ytcfg=None, account_syncid=None, session_index=None,
536 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
537
11f9be09 538 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 539 headers = {
109dd3b2 540 'X-YouTube-Client-Name': compat_str(
11f9be09 541 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
542 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 543 'Origin': origin,
544 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
545 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 546 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 547 }
548 if session_index is None:
314ee305 549 session_index = self._extract_session_index(ytcfg)
550 if account_syncid or session_index is not None:
551 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 552
109dd3b2 553 auth = self._generate_sapisidhash_header(origin)
f4f751af 554 if auth is not None:
555 headers['Authorization'] = auth
109dd3b2 556 headers['X-Origin'] = origin
99e9e001 557 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 558
2d6659b9 559 @staticmethod
560 def _build_api_continuation_query(continuation, ctp=None):
561 query = {
562 'continuation': continuation
563 }
564 # TODO: Inconsistency with clickTrackingParams.
565 # Currently we have a fixed ctp contained within context (from ytcfg)
566 # and a ctp in root query for continuation.
567 if ctp:
568 query['clickTracking'] = {'clickTrackingParams': ctp}
569 return query
570
2d6659b9 571 @classmethod
572 def _extract_next_continuation_data(cls, renderer):
573 next_continuation = try_get(
574 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
575 lambda x: x['continuation']['reloadContinuationData']), dict)
576 if not next_continuation:
577 return
578 continuation = next_continuation.get('continuation')
579 if not continuation:
580 return
581 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 582 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 583
584 @classmethod
585 def _extract_continuation_ep_data(cls, continuation_ep: dict):
586 if isinstance(continuation_ep, dict):
587 continuation = try_get(
588 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
589 if not continuation:
590 return
591 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 592 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 593
594 @classmethod
595 def _extract_continuation(cls, renderer):
596 next_continuation = cls._extract_next_continuation_data(renderer)
597 if next_continuation:
598 return next_continuation
fe93e2c4 599
2d6659b9 600 contents = []
601 for key in ('contents', 'items'):
602 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 603
2d6659b9 604 for content in contents:
605 if not isinstance(content, dict):
606 continue
607 continuation_ep = try_get(
608 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
609 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
610 dict)
611 continuation = cls._extract_continuation_ep_data(continuation_ep)
612 if continuation:
613 return continuation
614
fe93e2c4 615 @classmethod
616 def _extract_alerts(cls, data):
109dd3b2 617 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
618 if not isinstance(alert_dict, dict):
619 continue
620 for alert in alert_dict.values():
621 alert_type = alert.get('type')
622 if not alert_type:
623 continue
052e1350 624 message = cls._get_text(alert, 'text')
109dd3b2 625 if message:
626 yield alert_type, message
627
c0ac49bc 628 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 629 errors = []
630 warnings = []
631 for alert_type, alert_message in alerts:
641ad5d8 632 if alert_type.lower() == 'error' and fatal:
109dd3b2 633 errors.append([alert_type, alert_message])
634 else:
635 warnings.append([alert_type, alert_message])
636
637 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 638 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 639 if errors:
640 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
641
642 def _extract_and_report_alerts(self, data, *args, **kwargs):
643 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
644
47193e02 645 def _extract_badges(self, renderer: dict):
646 badges = set()
647 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
648 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
649 if label:
650 badges.add(label.lower())
651 return badges
652
653 @staticmethod
052e1350 654 def _get_text(data, *path_list, max_runs=None):
655 for path in path_list or [None]:
656 if path is None:
657 obj = [data]
658 else:
659 obj = traverse_obj(data, path, default=[])
660 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
661 obj = [obj]
662 for item in obj:
663 text = try_get(item, lambda x: x['simpleText'], compat_str)
664 if text:
665 return text
666 runs = try_get(item, lambda x: x['runs'], list) or []
667 if not runs and isinstance(item, list):
668 runs = item
669
670 runs = runs[:min(len(runs), max_runs or len(runs))]
671 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
672 if text:
673 return text
47193e02 674
f0d785d3 675 def _get_count(self, data, *path_list):
676 count_text = self._get_text(data, *path_list) or ''
677 count = parse_count(count_text)
678 if count is None:
679 count = str_to_int(
680 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
681 return count
682
a709d873 683 @staticmethod
684 def _extract_thumbnails(data, *path_list):
685 """
686 Extract thumbnails from thumbnails dict
687 @param path_list: path list to level that contains 'thumbnails' key
688 """
689 thumbnails = []
690 for path in path_list or [()]:
691 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
692 thumbnail_url = url_or_none(thumbnail.get('url'))
693 if not thumbnail_url:
694 continue
695 # Sometimes youtube gives a wrong thumbnail URL. See:
696 # https://github.com/yt-dlp/yt-dlp/issues/233
697 # https://github.com/ytdl-org/youtube-dl/issues/28023
698 if 'maxresdefault' in thumbnail_url:
699 thumbnail_url = thumbnail_url.split('?')[0]
700 thumbnails.append({
701 'url': thumbnail_url,
702 'height': int_or_none(thumbnail.get('height')),
703 'width': int_or_none(thumbnail.get('width')),
704 })
705 return thumbnails
706
f3aa3c3f 707 @staticmethod
708 def extract_relative_time(relative_time_text):
709 """
710 Extracts a relative time from string and converts to dt object
f0d785d3 711 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 712 """
f0d785d3 713 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 714 if mobj:
f0d785d3 715 start = mobj.group('start')
716 if start:
717 return datetime_from_str(start)
f3aa3c3f 718 try:
f0d785d3 719 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 720 except ValueError:
721 return None
722
723 def _extract_time_text(self, renderer, *path_list):
724 text = self._get_text(renderer, *path_list) or ''
725 dt = self.extract_relative_time(text)
726 timestamp = None
727 if isinstance(dt, datetime.datetime):
728 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 729
730 if timestamp is None:
731 timestamp = (
732 unified_timestamp(text) or unified_timestamp(
733 self._search_regex(
396a76f7 734 (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
735 text.lower(), 'time text', default=None)))
f0d785d3 736
f3aa3c3f 737 if text and timestamp is None:
738 self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
739 return timestamp, text
740
109dd3b2 741 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
742 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 743 default_client='web'):
109dd3b2 744 response = None
745 last_error = None
746 count = -1
747 retries = self.get_param('extractor_retries', 3)
748 if check_get_keys is None:
749 check_get_keys = []
750 while count < retries:
751 count += 1
752 if last_error:
c0ac49bc 753 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 754 try:
755 response = self._call_api(
756 ep=ep, fatal=True, headers=headers,
757 video_id=item_id, query=query,
758 context=self._extract_context(ytcfg, default_client),
759 api_key=self._extract_api_key(ytcfg, default_client),
760 api_hostname=api_hostname, default_client=default_client,
761 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
762 except ExtractorError as e:
9c0d7f49 763 if isinstance(e.cause, network_exceptions):
87e8e8a7 764 if isinstance(e.cause, compat_HTTPError):
765 first_bytes = e.cause.read(512)
766 if not is_html(first_bytes):
767 yt_error = try_get(
768 self._parse_json(
769 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
770 lambda x: x['error']['message'], compat_str)
771 if yt_error:
772 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 773 # Downloading page may result in intermittent 5xx HTTP error
774 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 775 # We also want to catch all other network exceptions since errors in later pages can be troublesome
776 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
777 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 778 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 779 if count < retries:
780 continue
109dd3b2 781 if fatal:
782 raise
783 else:
784 self.report_warning(error_to_compat_str(e))
785 return
786
787 else:
109dd3b2 788 try:
ac56cf38 789 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 790 except ExtractorError as e:
c0ac49bc 791 # YouTube servers may return errors we want to retry on in a 200 OK response
792 # See: https://github.com/yt-dlp/yt-dlp/issues/839
793 if 'unknown error' in e.msg.lower():
794 last_error = e.msg
795 continue
109dd3b2 796 if fatal:
797 raise
798 self.report_warning(error_to_compat_str(e))
799 return
800 if not check_get_keys or dict_get(response, check_get_keys):
801 break
802 # Youtube sometimes sends incomplete data
803 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
804 last_error = 'Incomplete data received'
805 if count >= retries:
806 if fatal:
807 raise ExtractorError(last_error)
808 else:
809 self.report_warning(last_error)
810 return
811 return response
812
9297939e 813 @staticmethod
814 def is_music_url(url):
815 return re.match(r'https?://music\.youtube\.com/', url) is not None
816
30a074c2 817 def _extract_video(self, renderer):
818 video_id = renderer.get('videoId')
052e1350 819 title = self._get_text(renderer, 'title')
820 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 821 duration = parse_duration(self._get_text(
822 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
f0d785d3 823 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 824
052e1350 825 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 826 channel_id = traverse_obj(
827 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
828 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
829 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
830 overlay_style = traverse_obj(
831 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
832 badges = self._extract_badges(renderer)
a709d873 833 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
834
30a074c2 835 return {
39ed931e 836 '_type': 'url',
30a074c2 837 'ie_key': YoutubeIE.ie_key(),
838 'id': video_id,
5e3f2f8f 839 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 840 'title': title,
841 'description': description,
842 'duration': duration,
843 'view_count': view_count,
844 'uploader': uploader,
f3aa3c3f 845 'channel_id': channel_id,
a709d873 846 'thumbnails': thumbnails,
66f7c6a3 847 # 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
f3aa3c3f 848 'live_status': ('is_upcoming' if scheduled_timestamp is not None
849 else 'was_live' if 'streamed' in time_text.lower()
850 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
851 else None),
852 'release_timestamp': scheduled_timestamp,
853 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 854 }
855
0c148415 856
360e1ca5 857class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 858 IE_DESC = 'YouTube'
cb7dfeea 859 _VALID_URL = r"""(?x)^
c5e8d7af 860 (
edb53e2d 861 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 862 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
863 (?:www\.)?deturl\.com/www\.youtube\.com|
864 (?:www\.)?pwnyoutube\.com|
865 (?:www\.)?hooktube\.com|
866 (?:www\.)?yourepeat\.com|
867 tube\.majestyc\.net|
868 %(invidious)s|
869 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
870 (?:.*?\#/)? # handle anchor (#/) redirect urls
871 (?: # the various things that can precede the ID:
b6ce9bb0 872 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 873 |(?: # or the v= param in all its forms
f7000f3a 874 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 875 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 876 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
877 v=
878 )
f4b05232 879 ))
cbaed4bb
S
880 |(?:
881 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
882 vid\.plus| # or vid.plus/xxxx
883 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 884 %(invidious)s
cbaed4bb 885 )/
edb53e2d 886 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 887 )
c5e8d7af 888 )? # all until now is optional -> you can pass the naked ID
201c1459 889 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 890 (?(1).+)? # if we found the ID, everything can follow
9297939e 891 (?:\#|$)""" % {
d9190e44 892 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 893 }
e40c758c 894 _PLAYER_INFO_RE = (
cc2db878 895 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
896 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 897 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 898 )
2c62dc26 899 _formats = {
c2d3cb4c 900 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
901 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
902 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
903 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
904 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
905 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
906 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
907 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 908 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 909 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
910 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
911 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
912 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
913 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
914 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 915 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 916 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
917 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 918
919
920 # 3D videos
c2d3cb4c 921 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
922 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
923 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
924 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 925 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
926 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
927 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 928
96fb5605 929 # Apple HTTP Live Streaming
11f12195 930 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 931 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
932 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
933 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
934 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
935 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 936 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
937 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
938
939 # DASH mp4 video
d23028a8
S
940 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
942 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
943 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
944 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 945 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
946 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
947 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
948 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
949 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
950 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
951 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 952
f6f1fc92 953 # Dash mp4 audio
d23028a8
S
954 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
955 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
956 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
957 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
958 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
959 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
960 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
961
962 # Dash webm
d23028a8
S
963 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
967 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
968 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
969 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
970 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
976 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
977 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 978 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
979 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
980 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
981 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
982 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
983 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
984 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
985
986 # Dash webm audio
d23028a8
S
987 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
988 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 989
0857baad 990 # Dash webm audio with opus inside
d23028a8
S
991 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
992 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
993 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 994
ce6b9a2d
PH
995 # RTMP (unnamed)
996 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
997
998 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
999 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1000 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1001 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1002 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1003 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1004 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1005 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1006 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1007 }
29f7c58a 1008 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1009
fd5c4aab
S
1010 _GEO_BYPASS = False
1011
78caa52a 1012 IE_NAME = 'youtube'
2eb88d95
PH
1013 _TESTS = [
1014 {
2d3d2997 1015 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1016 'info_dict': {
1017 'id': 'BaW_jenozKc',
1018 'ext': 'mp4',
3867038a 1019 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1020 'uploader': 'Philipp Hagemeister',
1021 'uploader_id': 'phihag',
ec85ded8 1022 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1023 'channel': 'Philipp Hagemeister',
dd4c4492
S
1024 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1025 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1026 'upload_date': '20121002',
ff9f925b 1027 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1028 'categories': ['Science & Technology'],
3867038a 1029 'tags': ['youtube-dl'],
556dbe7f 1030 'duration': 10,
dbdaaa23 1031 'view_count': int,
3e7c1224 1032 'like_count': int,
ff9f925b 1033 'availability': 'public',
1034 'playable_in_embed': True,
1035 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1036 'live_status': 'not_live',
1037 'age_limit': 0,
7c80519c 1038 'start_time': 1,
297a564b 1039 'end_time': 9,
6c73052c 1040 'channel_follower_count': int
2eb88d95 1041 }
0e853ca4 1042 },
fccd3771 1043 {
4bc3a23e
PH
1044 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1045 'note': 'Embed-only video (#1746)',
1046 'info_dict': {
1047 'id': 'yZIXLfi8CZQ',
1048 'ext': 'mp4',
1049 'upload_date': '20120608',
1050 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1051 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1052 'uploader': 'SET India',
94bfcd23 1053 'uploader_id': 'setindia',
ec85ded8 1054 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1055 'age_limit': 18,
545cc85d 1056 },
1057 'skip': 'Private video',
fccd3771 1058 },
11b56058 1059 {
8bdd16b4 1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1061 'note': 'Use the first video ID in the URL',
1062 'info_dict': {
1063 'id': 'BaW_jenozKc',
1064 'ext': 'mp4',
3867038a 1065 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1066 'uploader': 'Philipp Hagemeister',
1067 'uploader_id': 'phihag',
ec85ded8 1068 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1069 'channel': 'Philipp Hagemeister',
1070 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1071 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1072 'upload_date': '20121002',
976ae3ea 1073 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1074 'categories': ['Science & Technology'],
3867038a 1075 'tags': ['youtube-dl'],
556dbe7f 1076 'duration': 10,
dbdaaa23 1077 'view_count': int,
11b56058 1078 'like_count': int,
976ae3ea 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,
6c73052c 1084 'channel_follower_count': int
34a7de29
S
1085 },
1086 'params': {
1087 'skip_download': True,
1088 },
11b56058 1089 },
dd27fd17 1090 {
2d3d2997 1091 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1092 'note': '256k DASH audio (format 141) via DASH manifest',
1093 'info_dict': {
1094 'id': 'a9LDPn-MO4I',
1095 'ext': 'm4a',
1096 'upload_date': '20121002',
1097 'uploader_id': '8KVIDEO',
ec85ded8 1098 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1099 'description': '',
1100 'uploader': '8KVIDEO',
1101 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1102 },
4bc3a23e
PH
1103 'params': {
1104 'youtube_include_dash_manifest': True,
1105 'format': '141',
4919603f 1106 },
de3c7fe0 1107 'skip': 'format 141 not served anymore',
dd27fd17 1108 },
8bdd16b4 1109 # DASH manifest with encrypted signature
1110 {
1111 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1112 'info_dict': {
1113 'id': 'IB3lcPjvWLA',
1114 'ext': 'm4a',
1115 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1116 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1117 'duration': 244,
1118 'uploader': 'AfrojackVEVO',
1119 'uploader_id': 'AfrojackVEVO',
1120 'upload_date': '20131011',
cc2db878 1121 'abr': 129.495,
976ae3ea 1122 'like_count': int,
1123 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1124 'playable_in_embed': True,
1125 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1126 'view_count': int,
1127 'track': 'The Spark',
1128 'live_status': 'not_live',
1129 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1130 'channel': 'Afrojack',
1131 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1132 'tags': 'count:19',
1133 'availability': 'public',
1134 'categories': ['Music'],
1135 'age_limit': 0,
1136 'alt_title': 'The Spark',
6c73052c 1137 'channel_follower_count': int
8bdd16b4 1138 },
1139 'params': {
1140 'youtube_include_dash_manifest': True,
1141 'format': '141/bestaudio[ext=m4a]',
1142 },
1143 },
65c2fde2 1144 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1145 {
65c2fde2 1146 'note': 'Embed allowed age-gate video',
2d3d2997 1147 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1148 'info_dict': {
1149 'id': 'HtVdAasjOgU',
1150 'ext': 'mp4',
1151 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1152 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1153 'duration': 142,
c522adb1
JMF
1154 'uploader': 'The Witcher',
1155 'uploader_id': 'WitcherGame',
ec85ded8 1156 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1157 'upload_date': '20140605',
34952f09 1158 'age_limit': 18,
976ae3ea 1159 'categories': ['Gaming'],
1160 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1161 'availability': 'needs_auth',
1162 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1163 'like_count': int,
1164 'channel': 'The Witcher',
1165 'live_status': 'not_live',
1166 'tags': 'count:17',
1167 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1168 'playable_in_embed': True,
1169 'view_count': int,
6c73052c 1170 'channel_follower_count': int
c522adb1
JMF
1171 },
1172 },
65c2fde2 1173 {
1174 'note': 'Age-gate video with embed allowed in public site',
1175 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1176 'info_dict': {
1177 'id': 'HsUATh_Nc2U',
1178 'ext': 'mp4',
1179 'title': 'Godzilla 2 (Official Video)',
1180 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1181 'upload_date': '20200408',
1182 'uploader_id': 'FlyingKitty900',
1183 'uploader': 'FlyingKitty',
1184 'age_limit': 18,
976ae3ea 1185 'availability': 'needs_auth',
1186 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1187 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1188 'channel': 'FlyingKitty',
1189 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1190 'view_count': int,
1191 'categories': ['Entertainment'],
1192 'live_status': 'not_live',
1193 'tags': ['Flyingkitty', 'godzilla 2'],
1194 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1195 'like_count': int,
1196 'duration': 177,
1197 'playable_in_embed': True,
6c73052c 1198 'channel_follower_count': int
65c2fde2 1199 },
1200 },
1201 {
1202 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1203 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1204 'info_dict': {
1205 'id': 'Tq92D6wQ1mg',
1206 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1207 'ext': 'mp4',
1208 'upload_date': '20191227',
65c2fde2 1209 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1210 'uploader': 'Projekt Melody',
1211 'description': 'md5:17eccca93a786d51bc67646756894066',
1212 'age_limit': 18,
976ae3ea 1213 'like_count': int,
1214 'availability': 'needs_auth',
1215 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1216 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1217 'view_count': int,
1218 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1219 'channel': 'Projekt Melody',
1220 'live_status': 'not_live',
1221 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1222 'playable_in_embed': True,
1223 'categories': ['Entertainment'],
1224 'duration': 106,
1225 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1226 'channel_follower_count': int
65c2fde2 1227 },
1228 },
1229 {
1230 'note': 'Non-Agegated non-embeddable video',
1231 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1232 'info_dict': {
1233 'id': 'MeJVWBSsPAY',
1234 'ext': 'mp4',
1235 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1236 'uploader': 'Herr Lurik',
1237 'uploader_id': 'st3in234',
1238 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1239 'upload_date': '20130730',
976ae3ea 1240 'track': 'Such mich find mich',
1241 'age_limit': 0,
1242 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1243 'like_count': int,
1244 'playable_in_embed': False,
1245 'creator': 'OOMPH!',
1246 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1247 'view_count': int,
1248 'alt_title': 'Such mich find mich',
1249 'duration': 210,
1250 'channel': 'Herr Lurik',
1251 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1252 'categories': ['Music'],
1253 'availability': 'public',
1254 'uploader_url': 'http://www.youtube.com/user/st3in234',
1255 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1256 'live_status': 'not_live',
1257 'artist': 'OOMPH!',
6c73052c 1258 'channel_follower_count': int
65c2fde2 1259 },
1260 },
1261 {
1262 'note': 'Non-bypassable age-gated video',
1263 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1264 'only_matching': True,
1265 },
8bdd16b4 1266 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1267 # YouTube Red ad is not captured for creator
1268 {
1269 'url': '__2ABJjxzNo',
1270 'info_dict': {
1271 'id': '__2ABJjxzNo',
1272 'ext': 'mp4',
1273 'duration': 266,
1274 'upload_date': '20100430',
1275 'uploader_id': 'deadmau5',
1276 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1277 'creator': 'deadmau5',
1278 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1279 'uploader': 'deadmau5',
1280 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1281 'alt_title': 'Some Chords',
976ae3ea 1282 'availability': 'public',
1283 'tags': 'count:14',
1284 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1285 'view_count': int,
1286 'live_status': 'not_live',
1287 'channel': 'deadmau5',
1288 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1289 'like_count': int,
1290 'track': 'Some Chords',
1291 'artist': 'deadmau5',
1292 'playable_in_embed': True,
1293 'age_limit': 0,
1294 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1295 'categories': ['Music'],
1296 'album': 'Some Chords',
6c73052c 1297 'channel_follower_count': int
8bdd16b4 1298 },
1299 'expected_warnings': [
1300 'DASH manifest missing',
1301 ]
1302 },
067aa17e 1303 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1304 {
1305 'url': 'lqQg6PlCWgI',
1306 'info_dict': {
1307 'id': 'lqQg6PlCWgI',
1308 'ext': 'mp4',
556dbe7f 1309 'duration': 6085,
90227264 1310 'upload_date': '20150827',
cbe2bd91 1311 'uploader_id': 'olympic',
ec85ded8 1312 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1313 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1314 'uploader': 'Olympics',
cbe2bd91 1315 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1316 'like_count': int,
1317 'release_timestamp': 1343767800,
1318 'playable_in_embed': True,
1319 'categories': ['Sports'],
1320 'release_date': '20120731',
1321 'channel': 'Olympics',
1322 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1323 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1324 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1325 'age_limit': 0,
1326 'availability': 'public',
1327 'live_status': 'was_live',
1328 'view_count': int,
1329 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1330 'channel_follower_count': int
cbe2bd91
PH
1331 },
1332 'params': {
1333 'skip_download': 'requires avconv',
e52a40ab 1334 }
cbe2bd91 1335 },
6271f1ca
PH
1336 # Non-square pixels
1337 {
1338 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1339 'info_dict': {
1340 'id': '_b-2C3KPAM0',
1341 'ext': 'mp4',
1342 'stretched_ratio': 16 / 9.,
556dbe7f 1343 'duration': 85,
6271f1ca
PH
1344 'upload_date': '20110310',
1345 'uploader_id': 'AllenMeow',
ec85ded8 1346 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1347 '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 1348 'uploader': '孫ᄋᄅ',
6271f1ca 1349 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1350 'playable_in_embed': True,
1351 'channel': '孫ᄋᄅ',
1352 'age_limit': 0,
1353 'tags': 'count:11',
1354 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1355 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1356 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1357 'view_count': int,
1358 'categories': ['People & Blogs'],
1359 'like_count': int,
1360 'live_status': 'not_live',
1361 'availability': 'unlisted',
6c73052c 1362 'channel_follower_count': int
6271f1ca 1363 },
06b491eb
S
1364 },
1365 # url_encoded_fmt_stream_map is empty string
1366 {
1367 'url': 'qEJwOuvDf7I',
1368 'info_dict': {
1369 'id': 'qEJwOuvDf7I',
f57b7835 1370 'ext': 'webm',
06b491eb
S
1371 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1372 'description': '',
1373 'upload_date': '20150404',
1374 'uploader_id': 'spbelect',
1375 'uploader': 'Наблюдатели Петербурга',
1376 },
1377 'params': {
1378 'skip_download': 'requires avconv',
e323cf3f
S
1379 },
1380 'skip': 'This live event has ended.',
06b491eb 1381 },
067aa17e 1382 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1383 {
1384 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1385 'info_dict': {
1386 'id': 'FIl7x6_3R5Y',
eb6793ba 1387 'ext': 'webm',
da77d856
S
1388 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1389 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1390 'duration': 220,
da77d856
S
1391 'upload_date': '20150625',
1392 'uploader_id': 'dorappi2000',
ec85ded8 1393 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1394 'uploader': 'dorappi2000',
eb6793ba 1395 'formats': 'mincount:31',
da77d856 1396 },
eb6793ba 1397 'skip': 'not actual anymore',
2ee8f5d8 1398 },
8a1a26ce
YCH
1399 # DASH manifest with segment_list
1400 {
1401 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1402 'md5': '8ce563a1d667b599d21064e982ab9e31',
1403 'info_dict': {
1404 'id': 'CsmdDsKjzN8',
1405 'ext': 'mp4',
17ee98e1 1406 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1407 'uploader': 'Airtek',
1408 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1409 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1410 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1411 },
1412 'params': {
1413 'youtube_include_dash_manifest': True,
1414 'format': '135', # bestvideo
be49068d
S
1415 },
1416 'skip': 'This live event has ended.',
2ee8f5d8 1417 },
cf7e015f
S
1418 {
1419 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1420 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1421 'info_dict': {
545cc85d 1422 'id': 'jvGDaLqkpTg',
1423 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1424 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1425 },
1426 'playlist': [{
1427 'info_dict': {
545cc85d 1428 'id': 'jvGDaLqkpTg',
cf7e015f 1429 'ext': 'mp4',
545cc85d 1430 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1431 'description': 'md5:e03b909557865076822aa169218d6a5d',
1432 'duration': 10643,
1433 'upload_date': '20161111',
1434 'uploader': 'Team PGP',
1435 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1436 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1437 },
1438 }, {
1439 'info_dict': {
545cc85d 1440 'id': '3AKt1R1aDnw',
cf7e015f 1441 'ext': 'mp4',
545cc85d 1442 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1443 'description': 'md5:e03b909557865076822aa169218d6a5d',
1444 'duration': 10991,
1445 'upload_date': '20161111',
1446 'uploader': 'Team PGP',
1447 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1448 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1449 },
1450 }, {
1451 'info_dict': {
545cc85d 1452 'id': 'RtAMM00gpVc',
cf7e015f 1453 'ext': 'mp4',
545cc85d 1454 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1455 'description': 'md5:e03b909557865076822aa169218d6a5d',
1456 'duration': 10995,
1457 'upload_date': '20161111',
1458 'uploader': 'Team PGP',
1459 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1460 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1461 },
1462 }, {
1463 'info_dict': {
545cc85d 1464 'id': '6N2fdlP3C5U',
cf7e015f 1465 'ext': 'mp4',
545cc85d 1466 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1467 'description': 'md5:e03b909557865076822aa169218d6a5d',
1468 'duration': 10990,
1469 'upload_date': '20161111',
1470 'uploader': 'Team PGP',
1471 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1472 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1473 },
1474 }],
1475 'params': {
1476 'skip_download': True,
1477 },
65c2fde2 1478 'skip': 'Not multifeed anymore',
cbaed4bb 1479 },
f9f49d87 1480 {
067aa17e 1481 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1482 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1483 'info_dict': {
1484 'id': 'gVfLd0zydlo',
1485 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1486 },
1487 'playlist_count': 2,
be49068d 1488 'skip': 'Not multifeed anymore',
f9f49d87 1489 },
cbaed4bb 1490 {
2d3d2997 1491 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1492 'only_matching': True,
0e49d9a6 1493 },
6d4fc66b 1494 {
2d3d2997 1495 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1496 'only_matching': True,
1497 },
0e49d9a6 1498 {
067aa17e 1499 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1500 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1501 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1502 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1503 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1504 'info_dict': {
1505 'id': 'lsguqyKfVQg',
1506 'ext': 'mp4',
1507 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1508 'alt_title': 'Dark Walk',
0e49d9a6 1509 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1510 'duration': 133,
0e49d9a6
LL
1511 'upload_date': '20151119',
1512 'uploader_id': 'IronSoulElf',
ec85ded8 1513 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1514 'uploader': 'IronSoulElf',
11f9be09 1515 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1516 'track': 'Dark Walk',
1517 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1518 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1519 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1520 'categories': ['Film & Animation'],
1521 'view_count': int,
1522 'live_status': 'not_live',
1523 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1524 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1525 'tags': 'count:13',
1526 'availability': 'public',
1527 'channel': 'IronSoulElf',
1528 'playable_in_embed': True,
1529 'like_count': int,
1530 'age_limit': 0,
6c73052c 1531 'channel_follower_count': int
0e49d9a6
LL
1532 },
1533 'params': {
1534 'skip_download': True,
1535 },
1536 },
61f92af1 1537 {
067aa17e 1538 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1539 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1540 'only_matching': True,
1541 },
313dfc45
LL
1542 {
1543 # Video with yt:stretch=17:0
1544 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1545 'info_dict': {
1546 'id': 'Q39EVAstoRM',
1547 'ext': 'mp4',
1548 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1549 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1550 'upload_date': '20151107',
1551 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1552 'uploader': 'CH GAMER DROID',
1553 },
1554 'params': {
1555 'skip_download': True,
1556 },
be49068d 1557 'skip': 'This video does not exist.',
313dfc45 1558 },
201c1459 1559 {
1560 # Video with incomplete 'yt:stretch=16:'
1561 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1562 'only_matching': True,
1563 },
7caf9830
S
1564 {
1565 # Video licensed under Creative Commons
1566 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1567 'info_dict': {
1568 'id': 'M4gD1WSo5mA',
1569 'ext': 'mp4',
1570 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1571 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1572 'duration': 721,
7caf9830
S
1573 'upload_date': '20150127',
1574 'uploader_id': 'BerkmanCenter',
ec85ded8 1575 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1576 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1577 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1578 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1579 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1580 'like_count': int,
1581 'age_limit': 0,
1582 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1583 'channel': 'The Berkman Klein Center for Internet & Society',
1584 'availability': 'public',
1585 'view_count': int,
1586 'categories': ['Education'],
1587 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1588 'live_status': 'not_live',
1589 'playable_in_embed': True,
6c73052c 1590 'channel_follower_count': int
7caf9830
S
1591 },
1592 'params': {
1593 'skip_download': True,
1594 },
1595 },
fd050249
S
1596 {
1597 # Channel-like uploader_url
1598 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1599 'info_dict': {
1600 'id': 'eQcmzGIKrzg',
1601 'ext': 'mp4',
1602 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1603 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1604 'duration': 4060,
fd050249 1605 'upload_date': '20151119',
eb6793ba 1606 'uploader': 'Bernie Sanders',
fd050249 1607 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1609 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1610 'playable_in_embed': True,
1611 'tags': 'count:12',
1612 'like_count': int,
1613 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1614 'age_limit': 0,
1615 'availability': 'public',
1616 'categories': ['News & Politics'],
1617 'channel': 'Bernie Sanders',
1618 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1619 'view_count': int,
1620 'live_status': 'not_live',
1621 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1622 'channel_follower_count': int
fd050249
S
1623 },
1624 'params': {
1625 'skip_download': True,
1626 },
1627 },
040ac686
S
1628 {
1629 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1630 'only_matching': True,
7f29cf54
S
1631 },
1632 {
067aa17e 1633 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1634 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1635 'only_matching': True,
6496ccb4
S
1636 },
1637 {
1638 # Rental video preview
1639 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1640 'info_dict': {
1641 'id': 'uGpuVWrhIzE',
1642 'ext': 'mp4',
1643 'title': 'Piku - Trailer',
1644 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1645 'upload_date': '20150811',
1646 'uploader': 'FlixMatrix',
1647 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1648 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1649 'license': 'Standard YouTube License',
1650 },
1651 'params': {
1652 'skip_download': True,
1653 },
eb6793ba 1654 'skip': 'This video is not available.',
022a5d66 1655 },
12afdc2a
S
1656 {
1657 # YouTube Red video with episode data
1658 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1659 'info_dict': {
1660 'id': 'iqKdEhx-dD4',
1661 'ext': 'mp4',
1662 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1663 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1664 'duration': 2085,
12afdc2a
S
1665 'upload_date': '20170118',
1666 'uploader': 'Vsauce',
1667 'uploader_id': 'Vsauce',
1668 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1669 'series': 'Mind Field',
1670 'season_number': 1,
1671 'episode_number': 1,
976ae3ea 1672 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1673 'tags': 'count:12',
1674 'view_count': int,
1675 'availability': 'public',
1676 'age_limit': 0,
1677 'channel': 'Vsauce',
1678 'episode': 'Episode 1',
1679 'categories': ['Entertainment'],
1680 'season': 'Season 1',
1681 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1682 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1683 'like_count': int,
1684 'playable_in_embed': True,
1685 'live_status': 'not_live',
6c73052c 1686 'channel_follower_count': int
12afdc2a
S
1687 },
1688 'params': {
1689 'skip_download': True,
1690 },
1691 'expected_warnings': [
1692 'Skipping DASH manifest',
1693 ],
1694 },
c7121fa7
S
1695 {
1696 # The following content has been identified by the YouTube community
1697 # as inappropriate or offensive to some audiences.
1698 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1699 'info_dict': {
1700 'id': '6SJNVb0GnPI',
1701 'ext': 'mp4',
1702 'title': 'Race Differences in Intelligence',
1703 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1704 'duration': 965,
1705 'upload_date': '20140124',
1706 'uploader': 'New Century Foundation',
1707 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1709 },
1710 'params': {
1711 'skip_download': True,
1712 },
545cc85d 1713 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1714 },
022a5d66
S
1715 {
1716 # itag 212
1717 'url': '1t24XAntNCY',
1718 'only_matching': True,
fd5c4aab
S
1719 },
1720 {
1721 # geo restricted to JP
1722 'url': 'sJL6WA-aGkQ',
1723 'only_matching': True,
1724 },
cd5a74a2
S
1725 {
1726 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1727 'only_matching': True,
1728 },
bc2ca1bb 1729 {
1730 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1731 'only_matching': True,
1732 },
1733 {
1734 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1735 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1736 'only_matching': True,
1737 },
825cd268
RA
1738 {
1739 # DRM protected
1740 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1741 'only_matching': True,
4fe54c12
S
1742 },
1743 {
1744 # Video with unsupported adaptive stream type formats
1745 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1746 'info_dict': {
1747 'id': 'Z4Vy8R84T1U',
1748 'ext': 'mp4',
1749 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1750 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1751 'duration': 433,
1752 'upload_date': '20130923',
1753 'uploader': 'Amelia Putri Harwita',
1754 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1755 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1756 'formats': 'maxcount:10',
1757 },
1758 'params': {
1759 'skip_download': True,
1760 'youtube_include_dash_manifest': False,
1761 },
5429d6a9 1762 'skip': 'not actual anymore',
5caabd3c 1763 },
1764 {
822b9d9c 1765 # Youtube Music Auto-generated description
5caabd3c 1766 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1767 'info_dict': {
1768 'id': 'MgNrAu2pzNs',
1769 'ext': 'mp4',
1770 'title': 'Voyeur Girl',
1771 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1772 'upload_date': '20190312',
5429d6a9
S
1773 'uploader': 'Stephen - Topic',
1774 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1775 'artist': 'Stephen',
1776 'track': 'Voyeur Girl',
1777 'album': 'it\'s too much love to know my dear',
1778 'release_date': '20190313',
1779 'release_year': 2019,
976ae3ea 1780 'alt_title': 'Voyeur Girl',
1781 'view_count': int,
1782 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1783 'playable_in_embed': True,
1784 'like_count': int,
1785 'categories': ['Music'],
1786 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1787 'channel': 'Stephen',
1788 'availability': 'public',
1789 'creator': 'Stephen',
1790 'duration': 169,
1791 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1792 'age_limit': 0,
1793 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1794 'tags': 'count:11',
1795 'live_status': 'not_live',
6c73052c 1796 'channel_follower_count': int
5caabd3c 1797 },
1798 'params': {
1799 'skip_download': True,
1800 },
1801 },
66b48727
RA
1802 {
1803 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1804 'only_matching': True,
1805 },
011e75e6
S
1806 {
1807 # invalid -> valid video id redirection
1808 'url': 'DJztXj2GPfl',
1809 'info_dict': {
1810 'id': 'DJztXj2GPfk',
1811 'ext': 'mp4',
1812 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1813 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1814 'upload_date': '20090125',
1815 'uploader': 'Prochorowka',
1816 'uploader_id': 'Prochorowka',
1817 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1818 'artist': 'Panjabi MC',
1819 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1820 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1821 },
1822 'params': {
1823 'skip_download': True,
1824 },
545cc85d 1825 'skip': 'Video unavailable',
ea74e00b
DP
1826 },
1827 {
1828 # empty description results in an empty string
1829 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1830 'info_dict': {
1831 'id': 'x41yOUIvK2k',
1832 'ext': 'mp4',
1833 'title': 'IMG 3456',
1834 'description': '',
1835 'upload_date': '20170613',
1836 'uploader_id': 'ElevageOrVert',
1837 'uploader': 'ElevageOrVert',
976ae3ea 1838 'view_count': int,
1839 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1840 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1841 'like_count': int,
1842 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1843 'tags': [],
1844 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1845 'availability': 'public',
1846 'age_limit': 0,
1847 'categories': ['Pets & Animals'],
1848 'duration': 7,
1849 'playable_in_embed': True,
1850 'live_status': 'not_live',
1851 'channel': 'ElevageOrVert',
6c73052c 1852 'channel_follower_count': int
ea74e00b
DP
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
1857 },
a0566bbf 1858 {
29f7c58a 1859 # with '};' inside yt initial data (see [1])
1860 # see [2] for an example with '};' inside ytInitialPlayerResponse
1861 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1862 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1863 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1864 'info_dict': {
1865 'id': 'CHqg6qOn4no',
1866 'ext': 'mp4',
1867 'title': 'Part 77 Sort a list of simple types in c#',
1868 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1869 'upload_date': '20130831',
1870 'uploader_id': 'kudvenkat',
1871 'uploader': 'kudvenkat',
976ae3ea 1872 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1873 'like_count': int,
1874 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1875 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1876 'live_status': 'not_live',
1877 'categories': ['Education'],
1878 'availability': 'public',
1879 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1880 'tags': 'count:12',
1881 'playable_in_embed': True,
1882 'age_limit': 0,
1883 'view_count': int,
1884 'duration': 522,
1885 'channel': 'kudvenkat',
6c73052c 1886 'channel_follower_count': int
a0566bbf 1887 },
1888 'params': {
1889 'skip_download': True,
1890 },
1891 },
29f7c58a 1892 {
1893 # another example of '};' in ytInitialData
1894 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1895 'only_matching': True,
1896 },
1897 {
1898 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1899 'only_matching': True,
1900 },
545cc85d 1901 {
cc2db878 1902 # https://github.com/ytdl-org/youtube-dl/pull/28094
1903 'url': 'OtqTfy26tG0',
1904 'info_dict': {
1905 'id': 'OtqTfy26tG0',
1906 'ext': 'mp4',
1907 'title': 'Burn Out',
1908 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1909 'upload_date': '20141120',
1910 'uploader': 'The Cinematic Orchestra - Topic',
1911 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1912 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1913 'artist': 'The Cinematic Orchestra',
1914 'track': 'Burn Out',
1915 'album': 'Every Day',
976ae3ea 1916 'like_count': int,
1917 'live_status': 'not_live',
1918 'alt_title': 'Burn Out',
1919 'duration': 614,
1920 'age_limit': 0,
1921 'view_count': int,
1922 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1923 'creator': 'The Cinematic Orchestra',
1924 'channel': 'The Cinematic Orchestra',
1925 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1926 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1927 'availability': 'public',
1928 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1929 'categories': ['Music'],
1930 'playable_in_embed': True,
6c73052c 1931 'channel_follower_count': int
cc2db878 1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
545cc85d 1936 },
bc2ca1bb 1937 {
1938 # controversial video, only works with bpctr when authenticated with cookies
1939 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1940 'only_matching': True,
1941 },
a1a7907b 1942 {
1943 # controversial video, requires bpctr/contentCheckOk
1944 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1945 'info_dict': {
1946 'id': 'SZJvDhaSDnc',
1947 'ext': 'mp4',
1948 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1949 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1950 'uploader': 'CBS Mornings',
11f9be09 1951 'uploader_id': 'CBSThisMorning',
a1a7907b 1952 'upload_date': '20140716',
976ae3ea 1953 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1954 'duration': 170,
1955 'categories': ['News & Politics'],
1956 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1957 'view_count': int,
1958 'channel': 'CBS Mornings',
1959 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1960 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1961 'age_limit': 18,
1962 'availability': 'needs_auth',
1963 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1964 'like_count': int,
1965 'live_status': 'not_live',
1966 'playable_in_embed': True,
6c73052c 1967 'channel_follower_count': int
a1a7907b 1968 }
1969 },
f7ad7160 1970 {
1971 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1972 'url': 'cBvYw8_A0vQ',
1973 'info_dict': {
1974 'id': 'cBvYw8_A0vQ',
1975 'ext': 'mp4',
1976 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1977 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1978 'upload_date': '20201120',
1979 'uploader': 'Walk around Japan',
1980 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1981 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1982 'duration': 1456,
1983 'categories': ['Travel & Events'],
1984 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1985 'view_count': int,
1986 'channel': 'Walk around Japan',
1987 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1988 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1989 'age_limit': 0,
1990 'availability': 'public',
1991 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1992 'live_status': 'not_live',
1993 'playable_in_embed': True,
6c73052c 1994 'channel_follower_count': int
f7ad7160 1995 },
1996 'params': {
1997 'skip_download': True,
1998 },
0fb983f6 1999 }, {
2000 # Has multiple audio streams
2001 'url': 'WaOKSUlf4TM',
2002 'only_matching': True
9297939e 2003 }, {
2004 # Requires Premium: has format 141 when requested using YTM url
2005 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2006 'only_matching': True
2007 }, {
120916da 2008 # multiple subtitles with same lang_code
2009 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2010 'only_matching': True,
109dd3b2 2011 }, {
2012 # Force use android client fallback
2013 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2014 'info_dict': {
2015 'id': 'YOelRv7fMxY',
11f9be09 2016 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2017 'ext': '3gp',
2018 'upload_date': '20210624',
2019 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2020 'uploader': 'colinfurze',
11f9be09 2021 'uploader_id': 'colinfurze',
109dd3b2 2022 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2023 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2024 'duration': 596,
2025 'categories': ['Entertainment'],
2026 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2027 'view_count': int,
2028 'channel': 'colinfurze',
2029 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2030 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2031 'age_limit': 0,
2032 'availability': 'public',
2033 'like_count': int,
2034 'live_status': 'not_live',
2035 'playable_in_embed': True,
6c73052c 2036 'channel_follower_count': int
109dd3b2 2037 },
2038 'params': {
2039 'format': '17', # 3gp format available on android
2040 'extractor_args': {'youtube': {'player_client': ['android']}},
2041 },
120916da 2042 },
109dd3b2 2043 {
2044 # Skip download of additional client configs (remix client config in this case)
2045 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2046 'only_matching': True,
2047 'params': {
2048 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2049 },
8fc54b12 2050 }, {
2051 # shorts
2052 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2053 'only_matching': True,
9222c381 2054 }, {
2055 'note': 'Storyboards',
2056 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2057 'info_dict': {
2058 'id': '5KLPxDtMqe8',
2059 'ext': 'mhtml',
2060 'format_id': 'sb0',
2061 'title': 'Your Brain is Plastic',
2062 'uploader_id': 'scishow',
2063 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2064 'upload_date': '20140324',
2065 'uploader': 'SciShow',
976ae3ea 2066 'like_count': int,
2067 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2068 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2069 'view_count': int,
2070 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2071 'playable_in_embed': True,
2072 'tags': 'count:12',
2073 'uploader_url': 'http://www.youtube.com/user/scishow',
2074 'availability': 'public',
2075 'channel': 'SciShow',
2076 'live_status': 'not_live',
2077 'duration': 248,
2078 'categories': ['Education'],
2079 'age_limit': 0,
6c73052c 2080 'channel_follower_count': int
9222c381 2081 }, 'params': {'format': 'mhtml', 'skip_download': True}
2082 }
2eb88d95
PH
2083 ]
2084
201c1459 2085 @classmethod
2086 def suitable(cls, url):
4dfbf869 2087 from ..utils import parse_qs
2088
201c1459 2089 qs = parse_qs(url)
2090 if qs.get('list', [None])[0]:
2091 return False
2092 return super(YoutubeIE, cls).suitable(url)
2093
e0df6211
PH
2094 def __init__(self, *args, **kwargs):
2095 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2096 self._code_cache = {}
83799698 2097 self._player_cache = {}
e0df6211 2098
adbc4ec4 2099 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2100 lock = threading.Lock()
2101
2102 is_live = True
185bf310 2103 start_time = time.time()
adbc4ec4
THD
2104 formats = [f for f in formats if f.get('is_from_start')]
2105
185bf310 2106 def refetch_manifest(format_id, delay):
2107 nonlocal formats, start_time, is_live
2108 if time.time() <= start_time + delay:
adbc4ec4
THD
2109 return
2110
2111 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2112 video_details = traverse_obj(
2113 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2114 microformats = traverse_obj(
2115 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2116 expected_type=dict, default=[])
2117 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2118 start_time = time.time()
adbc4ec4 2119
185bf310 2120 def mpd_feed(format_id, delay):
adbc4ec4
THD
2121 """
2122 @returns (manifest_url, manifest_stream_number, is_live) or None
2123 """
2124 with lock:
185bf310 2125 refetch_manifest(format_id, delay)
adbc4ec4
THD
2126
2127 f = next((f for f in formats if f['format_id'] == format_id), None)
2128 if not f:
185bf310 2129 if not is_live:
2130 self.to_screen(f'{video_id}: Video is no longer live')
2131 else:
2132 self.report_warning(
2133 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2134 return None
2135 return f['manifest_url'], f['manifest_stream_number'], is_live
2136
2137 for f in formats:
2138 f['protocol'] = 'http_dash_segments_generator'
2139 f['fragments'] = functools.partial(
2140 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2141
2142 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2143 FETCH_SPAN, MAX_DURATION = 5, 432000
2144
2145 mpd_url, stream_number, is_live = None, None, True
2146
2147 begin_index = 0
2148 download_start_time = ctx.get('start') or time.time()
2149
2150 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2151 if lack_early_segments:
2152 self.report_warning(bug_reports_message(
2153 'Starting download from the last 120 hours of the live stream since '
2154 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2155 lack_early_segments = True
2156
2157 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2158 fragments, fragment_base_url = None, None
2159
2160 def _extract_sequence_from_mpd(refresh_sequence):
2161 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2162 # Obtain from MPD's maximum seq value
2163 old_mpd_url = mpd_url
185bf310 2164 last_error = ctx.pop('last_error', None)
2165 expire_fast = last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2166 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2167 or (mpd_url, stream_number, False))
2168 if not refresh_sequence:
2169 if expire_fast and not is_live:
2170 return False, last_seq
2171 elif old_mpd_url == mpd_url:
2172 return True, last_seq
adbc4ec4
THD
2173 try:
2174 fmts, _ = self._extract_mpd_formats_and_subtitles(
2175 mpd_url, None, note=False, errnote=False, fatal=False)
2176 except ExtractorError:
2177 fmts = None
2178 if not fmts:
2179 no_fragment_score += 1
2180 return False, last_seq
2181 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2182 fragments = fmt_info['fragments']
2183 fragment_base_url = fmt_info['fragment_base_url']
2184 assert fragment_base_url
2185
2186 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2187 return True, _last_seq
2188
2189 while is_live:
2190 fetch_time = time.time()
2191 if no_fragment_score > 30:
2192 return
2193 if last_segment_url:
2194 # Obtain from "X-Head-Seqnum" header value from each segment
2195 try:
2196 urlh = self._request_webpage(
2197 last_segment_url, None, note=False, errnote=False, fatal=False)
2198 except ExtractorError:
2199 urlh = None
2200 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2201 if last_seq is None:
2202 no_fragment_score += 1
2203 last_segment_url = None
2204 continue
2205 else:
185bf310 2206 should_continue, last_seq = _extract_sequence_from_mpd(True)
2207 if not should_continue:
adbc4ec4
THD
2208 continue
2209
2210 if known_idx > last_seq:
2211 last_segment_url = None
2212 continue
2213
2214 last_seq += 1
2215
2216 if begin_index < 0 and known_idx < 0:
2217 # skip from the start when it's negative value
2218 known_idx = last_seq + begin_index
2219 if lack_early_segments:
2220 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2221 try:
2222 for idx in range(known_idx, last_seq):
2223 # do not update sequence here or you'll get skipped some part of it
185bf310 2224 should_continue, _ = _extract_sequence_from_mpd(False)
2225 if not should_continue:
adbc4ec4
THD
2226 known_idx = idx - 1
2227 raise ExtractorError('breaking out of outer loop')
2228 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2229 yield {
2230 'url': last_segment_url,
2231 }
2232 if known_idx == last_seq:
2233 no_fragment_score += 5
2234 else:
2235 no_fragment_score = 0
2236 known_idx = last_seq
2237 except ExtractorError:
2238 continue
2239
2240 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2241
b6de707d 2242 def _extract_player_url(self, *ytcfgs, webpage=None):
2243 player_url = traverse_obj(
2244 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2245 get_all=False, expected_type=compat_str)
11f9be09 2246 if not player_url:
b6de707d 2247 return
109dd3b2 2248 if player_url.startswith('//'):
2249 player_url = 'https:' + player_url
2250 elif not re.match(r'https?://', player_url):
2251 player_url = compat_urlparse.urljoin(
2252 'https://www.youtube.com', player_url)
2253 return player_url
2254
b6de707d 2255 def _download_player_url(self, video_id, fatal=False):
2256 res = self._download_webpage(
2257 'https://www.youtube.com/iframe_api',
2258 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2259 if res:
2260 player_version = self._search_regex(
2261 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2262 if player_version:
2263 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2264
60064c53
PH
2265 def _signature_cache_id(self, example_sig):
2266 """ Return a string representation of a signature """
78caa52a 2267 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2268
e40c758c
S
2269 @classmethod
2270 def _extract_player_info(cls, player_url):
2271 for player_re in cls._PLAYER_INFO_RE:
2272 id_m = re.search(player_re, player_url)
2273 if id_m:
2274 break
2275 else:
c081b35c 2276 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2277 return id_m.group('id')
e40c758c 2278
404f611f 2279 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2280 player_id = self._extract_player_info(player_url)
2281 if player_id not in self._code_cache:
1276a43a 2282 code = self._download_webpage(
109dd3b2 2283 player_url, video_id, fatal=fatal,
2284 note='Downloading player ' + player_id,
2285 errnote='Download of %s failed' % player_url)
1276a43a 2286 if code:
2287 self._code_cache[player_id] = code
404f611f 2288 return self._code_cache.get(player_id)
109dd3b2 2289
e40c758c 2290 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2291 player_id = self._extract_player_info(player_url)
e0df6211 2292
c4417ddb 2293 # Read from filesystem cache
545cc85d 2294 func_id = 'js_%s_%s' % (
2295 player_id, self._signature_cache_id(example_sig))
c4417ddb 2296 assert os.path.basename(func_id) == func_id
a0e07d31 2297
69ea8ca4 2298 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2299 if cache_spec is not None:
78caa52a 2300 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2301
404f611f 2302 code = self._load_player(video_id, player_url)
2303 if code:
109dd3b2 2304 res = self._parse_sig_js(code)
e0df6211 2305
109dd3b2 2306 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2307 cache_res = res(test_string)
2308 cache_spec = [ord(c) for c in cache_res]
83799698 2309
109dd3b2 2310 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2311 return res
83799698 2312
60064c53 2313 def _print_sig_code(self, func, example_sig):
404f611f 2314 if not self.get_param('youtube_print_sig_code'):
2315 return
2316
edf3e38e
PH
2317 def gen_sig_code(idxs):
2318 def _genslice(start, end, step):
78caa52a 2319 starts = '' if start == 0 else str(start)
8bcc8756 2320 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2321 steps = '' if step == 1 else (':%d' % step)
78caa52a 2322 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2323
2324 step = None
7af808a5
PH
2325 # Quelch pyflakes warnings - start will be set when step is set
2326 start = '(Never used)'
edf3e38e
PH
2327 for i, prev in zip(idxs[1:], idxs[:-1]):
2328 if step is not None:
2329 if i - prev == step:
2330 continue
2331 yield _genslice(start, prev, step)
2332 step = None
2333 continue
2334 if i - prev in [-1, 1]:
2335 step = i - prev
2336 start = prev
2337 continue
2338 else:
78caa52a 2339 yield 's[%d]' % prev
edf3e38e 2340 if step is None:
78caa52a 2341 yield 's[%d]' % i
edf3e38e
PH
2342 else:
2343 yield _genslice(start, i, step)
2344
78caa52a 2345 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2346 cache_res = func(test_string)
edf3e38e 2347 cache_spec = [ord(c) for c in cache_res]
78caa52a 2348 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2349 signature_id_tuple = '(%s)' % (
2350 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2351 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2352 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2353 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2354
e0df6211
PH
2355 def _parse_sig_js(self, jscode):
2356 funcname = self._search_regex(
abefc03f
S
2357 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2358 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
2359 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2360 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2361 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}\(a,\d+\)',
2362 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 2363 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2364 # Obsolete patterns
2365 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2366 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2367 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2368 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2369 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2370 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2371 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2372 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2373 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2374
2375 jsi = JSInterpreter(jscode)
2376 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2377 return lambda s: initial_function([s])
2378
545cc85d 2379 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2380 """Turn the encrypted s field into a working signature"""
6b37f0be 2381
c8bf86d5 2382 if player_url is None:
69ea8ca4 2383 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2384
c8bf86d5 2385 try:
62af3a0e 2386 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2387 if player_id not in self._player_cache:
2388 func = self._extract_signature_function(
60064c53 2389 video_id, player_url, s
c8bf86d5
PH
2390 )
2391 self._player_cache[player_id] = func
2392 func = self._player_cache[player_id]
404f611f 2393 self._print_sig_code(func, s)
c8bf86d5
PH
2394 return func(s)
2395 except Exception as e:
404f611f 2396 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2397
2398 def _decrypt_nsig(self, s, video_id, player_url):
2399 """Turn the encrypted n field into a working signature"""
2400 if player_url is None:
2401 raise ExtractorError('Cannot decrypt nsig without player_url')
2402 if player_url.startswith('//'):
2403 player_url = 'https:' + player_url
2404 elif not re.match(r'https?://', player_url):
2405 player_url = compat_urlparse.urljoin(
2406 'https://www.youtube.com', player_url)
2407
2408 sig_id = ('nsig_value', s)
2409 if sig_id in self._player_cache:
2410 return self._player_cache[sig_id]
2411
2412 try:
2413 player_id = ('nsig', player_url)
2414 if player_id not in self._player_cache:
2415 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2416 func = self._player_cache[player_id]
2417 self._player_cache[sig_id] = func(s)
2418 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2419 return self._player_cache[sig_id]
2420 except Exception as e:
aa9369a2 2421 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2422
2423 def _extract_n_function_name(self, jscode):
48416bc4 2424 nfunc, idx = self._search_regex(
2425 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})(\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2426 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2427 if not idx:
2428 return nfunc
2429 return json.loads(js_to_json(self._search_regex(
2430 rf'var {nfunc}\s*=\s*(\[.+?\]);', jscode,
2431 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2432
2433 def _extract_n_function(self, video_id, player_url):
2434 player_id = self._extract_player_info(player_url)
2435 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2436
2437 if func_code:
2438 jsi = JSInterpreter(func_code)
2439 else:
2440 jscode = self._load_player(video_id, player_url)
2441 funcname = self._extract_n_function_name(jscode)
2442 jsi = JSInterpreter(jscode)
2443 func_code = jsi.extract_function_code(funcname)
2444 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2445
2446 if self.get_param('youtube_print_sig_code'):
2447 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2448
2449 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2450
109dd3b2 2451 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2452 """
2453 Extract signatureTimestamp (sts)
2454 Required to tell API what sig/player version is in use.
2455 """
2456 sts = None
2457 if isinstance(ytcfg, dict):
2458 sts = int_or_none(ytcfg.get('STS'))
2459
2460 if not sts:
2461 # Attempt to extract from player
2462 if player_url is None:
2463 error_msg = 'Cannot extract signature timestamp without player_url.'
2464 if fatal:
2465 raise ExtractorError(error_msg)
2466 self.report_warning(error_msg)
2467 return
404f611f 2468 code = self._load_player(video_id, player_url, fatal=fatal)
2469 if code:
109dd3b2 2470 sts = int_or_none(self._search_regex(
2471 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2472 'JS player signature timestamp', group='sts', fatal=fatal))
2473 return sts
2474
11f9be09 2475 def _mark_watched(self, video_id, player_responses):
9222c381 2476 playback_url = get_first(
2477 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2478 expected_type=url_or_none)
d77ab8e2 2479 if not playback_url:
352d63fd 2480 self.report_warning('Unable to mark watched')
d77ab8e2
S
2481 return
2482 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2483 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2484
2485 # cpn generation algorithm is reverse engineered from base.js.
2486 # In fact it works even with dummy cpn.
2487 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2488 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2489
2490 qs.update({
2491 'ver': ['2'],
2492 'cpn': [cpn],
2493 })
2494 playback_url = compat_urlparse.urlunparse(
15707c7e 2495 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2496
2497 self._download_webpage(
2498 playback_url, video_id, 'Marking watched',
2499 'Unable to mark watched', fatal=False)
2500
66c9fa36
S
2501 @staticmethod
2502 def _extract_urls(webpage):
2503 # Embedded YouTube player
2504 entries = [
2505 unescapeHTML(mobj.group('url'))
2506 for mobj in re.finditer(r'''(?x)
2507 (?:
2508 <iframe[^>]+?src=|
2509 data-video-url=|
2510 <embed[^>]+?src=|
2511 embedSWF\(?:\s*|
2512 <object[^>]+data=|
2513 new\s+SWFObject\(
2514 )
2515 (["\'])
2516 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2517 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2518 \1''', webpage)]
2519
2520 # lazyYT YouTube embed
2521 entries.extend(list(map(
2522 unescapeHTML,
2523 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2524
2525 # Wordpress "YouTube Video Importer" plugin
2526 matches = re.findall(r'''(?x)<div[^>]+
2527 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2528 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2529 entries.extend(m[-1] for m in matches)
2530
2531 return entries
2532
2533 @staticmethod
2534 def _extract_url(webpage):
2535 urls = YoutubeIE._extract_urls(webpage)
2536 return urls[0] if urls else None
2537
97665381
PH
2538 @classmethod
2539 def extract_id(cls, url):
2540 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2541 if mobj is None:
69ea8ca4 2542 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2543 return mobj.group('id')
c5e8d7af 2544
7c365c21 2545 def _extract_chapters_from_json(self, data, duration):
2546 chapter_list = traverse_obj(
2547 data, (
2548 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2549 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2550 ), expected_type=list)
2551
2552 return self._extract_chapters(
2553 chapter_list,
2554 chapter_time=lambda chapter: float_or_none(
2555 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2556 chapter_title=lambda chapter: traverse_obj(
2557 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2558 duration=duration)
2559
2560 def _extract_chapters_from_engagement_panel(self, data, duration):
2561 content_list = traverse_obj(
8bdd16b4 2562 data,
7c365c21 2563 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2564 expected_type=list, default=[])
052e1350 2565 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2566 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2567
2568 return next((
2569 filter(None, (
2570 self._extract_chapters(
2571 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2572 chapter_time, chapter_title, duration)
2573 for contents in content_list
2574 ))), [])
2575
2576 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2577 chapters = []
7c365c21 2578 last_chapter = {'start_time': 0}
2579 for idx, chapter in enumerate(chapter_list or []):
2580 title = chapter_title(chapter)
84213ea8
S
2581 start_time = chapter_time(chapter)
2582 if start_time is None:
2583 continue
7c365c21 2584 last_chapter['end_time'] = start_time
2585 if start_time < last_chapter['start_time']:
2586 if idx == 1:
2587 chapters.pop()
2588 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2589 else:
2590 self.report_warning(f'Invalid start time for chapter "{title}"')
2591 continue
2592 last_chapter = {'start_time': start_time, 'title': title}
2593 chapters.append(last_chapter)
2594 last_chapter['end_time'] = duration
84213ea8
S
2595 return chapters
2596
545cc85d 2597 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2598 return self._parse_json(self._search_regex(
2599 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2600 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2601
a1c5d2ca
M
2602 def _extract_comment(self, comment_renderer, parent=None):
2603 comment_id = comment_renderer.get('commentId')
2604 if not comment_id:
2605 return
fe93e2c4 2606
052e1350 2607 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2608
49bd8c66 2609 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2610 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2611 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2612 author_id = try_get(comment_renderer,
2613 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2614
49bd8c66 2615 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2616 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2617 author_thumbnail = try_get(comment_renderer,
2618 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2619
2620 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2621 is_favorited = 'creatorHeart' in (try_get(
2622 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2623 return {
2624 'id': comment_id,
2625 'text': text,
d92f5d5a 2626 'timestamp': timestamp,
a1c5d2ca
M
2627 'time_text': time_text,
2628 'like_count': votes,
97524332 2629 'is_favorited': is_favorited,
a1c5d2ca
M
2630 'author': author,
2631 'author_id': author_id,
2632 'author_thumbnail': author_thumbnail,
2633 'author_is_uploader': author_is_uploader,
2634 'parent': parent or 'root'
2635 }
2636
46383212 2637 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2638
2639 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2640
2641 def extract_header(contents):
2d6659b9 2642 _continuation = None
2643 for content in contents:
46383212 2644 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2645 expected_comment_count = self._get_count(
2646 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2647
2d6659b9 2648 if expected_comment_count:
46383212 2649 tracker['est_total'] = expected_comment_count
2650 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2651 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2652
2653 sort_menu_item = try_get(
2654 comments_header_renderer,
2655 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2656 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2657
2658 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2659 if not _continuation:
2660 continue
2661
46383212 2662 sort_text = str_or_none(sort_menu_item.get('title'))
2663 if not sort_text:
2d6659b9 2664 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2665 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2666 break
a2160aa4 2667 return _continuation
a1c5d2ca 2668
2d6659b9 2669 def extract_thread(contents):
a1c5d2ca 2670 if not parent:
46383212 2671 tracker['current_page_thread'] = 0
a1c5d2ca 2672 for content in contents:
46383212 2673 if not parent and tracker['total_parent_comments'] >= max_parents:
2674 yield
a1c5d2ca 2675 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2676 comment_renderer = get_first(
2677 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2678 expected_type=dict, default={})
a1c5d2ca 2679
a1c5d2ca
M
2680 comment = self._extract_comment(comment_renderer, parent)
2681 if not comment:
2682 continue
46383212 2683
2684 tracker['running_total'] += 1
2685 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2686 yield comment
46383212 2687
a1c5d2ca
M
2688 # Attempt to get the replies
2689 comment_replies_renderer = try_get(
2690 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2691
2692 if comment_replies_renderer:
46383212 2693 tracker['current_page_thread'] += 1
a1c5d2ca 2694 comment_entries_iter = self._comment_entries(
99e9e001 2695 comment_replies_renderer, ytcfg, video_id,
46383212 2696 parent=comment.get('id'), tracker=tracker)
2697 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2698 yield reply_comment
2699
46383212 2700 # Keeps track of counts across recursive calls
2701 if not tracker:
2702 tracker = dict(
2703 running_total=0,
2704 est_total=0,
2705 current_page_thread=0,
2706 total_parent_comments=0,
2707 total_reply_comments=0)
2708
2709 # TODO: Deprecated
2d6659b9 2710 # YouTube comments have a max depth of 2
46383212 2711 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2712 if max_depth:
2713 self._downloader.deprecation_warning(
2714 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2715 if max_depth == 1 and parent:
2716 return
a1c5d2ca 2717
46383212 2718 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2719 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2720
46383212 2721 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2722 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2723 if message and not parent:
2724 self.report_warning(message, video_id=video_id)
2725
46383212 2726 response = None
2d6659b9 2727 is_first_continuation = parent is None
a1c5d2ca
M
2728
2729 for page_num in itertools.count(0):
2730 if not continuation:
2731 break
46383212 2732 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2733 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2734 if page_num == 0:
2735 if is_first_continuation:
2736 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2737 else:
2d6659b9 2738 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2739 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2740 else:
2741 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2742 ' ' if parent else '', ' replies' if parent else '',
2743 page_num, comment_prog_str)
2744
2745 response = self._extract_response(
fe93e2c4 2746 item_id=None, query=continuation,
2d6659b9 2747 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2748 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2749
46383212 2750 continuation_contents = traverse_obj(
2751 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2752
2d6659b9 2753 continuation = None
46383212 2754 for continuation_section in continuation_contents:
2755 continuation_items = traverse_obj(
2756 continuation_section,
2757 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2758 get_all=False, expected_type=list) or []
2759 if is_first_continuation:
2760 continuation = extract_header(continuation_items)
2761 is_first_continuation = False
2d6659b9 2762 if continuation:
a1c5d2ca 2763 break
46383212 2764 continue
a1c5d2ca 2765
46383212 2766 for entry in extract_thread(continuation_items):
2767 if not entry:
2768 return
2769 yield entry
2770 continuation = self._extract_continuation({'contents': continuation_items})
2771 if continuation:
2d6659b9 2772 break
a1c5d2ca 2773
a2160aa4 2774 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2775 """Entry for comment extraction"""
2d6659b9 2776 def _real_comment_extract(contents):
aae16f6e 2777 renderer = next((
2778 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2779 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2780 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2781
a2160aa4 2782 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2783 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2784
109dd3b2 2785 @staticmethod
99e9e001 2786 def _get_checkok_params():
2787 return {'contentCheckOk': True, 'racyCheckOk': True}
2788
2789 @classmethod
2790 def _generate_player_context(cls, sts=None):
109dd3b2 2791 context = {
2792 'html5Preference': 'HTML5_PREF_WANTS',
2793 }
2794 if sts is not None:
2795 context['signatureTimestamp'] = sts
2796 return {
2797 'playbackContext': {
2798 'contentPlaybackContext': context
a1a7907b 2799 },
99e9e001 2800 **cls._get_checkok_params()
109dd3b2 2801 }
2802
e7e94f2a
D
2803 @staticmethod
2804 def _is_agegated(player_response):
2805 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2806 return True
e7e94f2a
D
2807
2808 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2809 AGE_GATE_REASONS = (
2810 'confirm your age', 'age-restricted', 'inappropriate', # reason
2811 'age_verification_required', 'age_check_required', # status
2812 )
2813 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2814
2815 @staticmethod
2816 def _is_unplayable(player_response):
2817 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2818
99e9e001 2819 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2820
11f9be09 2821 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2822 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2823 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2824 headers = self.generate_api_headers(
99e9e001 2825 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2826
11f9be09 2827 yt_query = {'videoId': video_id}
2828 yt_query.update(self._generate_player_context(sts))
2829 return self._extract_response(
2830 item_id=video_id, ep='player', query=yt_query,
379e44ed 2831 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2832 default_client=client,
11f9be09 2833 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2834 ) or None
2835
11f9be09 2836 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2837 requested_clients = []
d0d012d4 2838 default = ['android', 'web']
000c15a4 2839 allowed_clients = sorted(
2840 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2841 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2842 for client in self._configuration_arg('player_client'):
2843 if client in allowed_clients:
2844 requested_clients.append(client)
d0d012d4 2845 elif client == 'default':
2846 requested_clients.extend(default)
b4c055ba 2847 elif client == 'all':
2848 requested_clients.extend(allowed_clients)
2849 else:
2850 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2851 if not requested_clients:
d0d012d4 2852 requested_clients = default
cf7e015f 2853
11f9be09 2854 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2855 requested_clients.extend(
e7e94f2a 2856 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2857
11f9be09 2858 return orderedSet(requested_clients)
cf7e015f 2859
c0bc527b
M
2860 def _extract_player_ytcfg(self, client, video_id):
2861 url = {
2862 'web_music': 'https://music.youtube.com',
2863 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2864 }.get(client)
2865 if not url:
2866 return {}
18c7683d 2867 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2868 return self.extract_ytcfg(video_id, webpage) or {}
2869
99e9e001 2870 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2871 initial_pr = None
2872 if webpage:
2873 initial_pr = self._extract_yt_initial_variable(
2874 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2875 video_id, 'initial player response')
6b09401b 2876
c0bc527b
M
2877 original_clients = clients
2878 clients = clients[::-1]
b6de707d 2879 prs = []
e7e94f2a
D
2880
2881 def append_client(client_name):
2882 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2883 clients.append(client_name)
2884
379e44ed 2885 # Android player_response does not have microFormats which are needed for
2886 # extraction of some data. So we return the initial_pr with formats
2887 # stripped out even if not requested by the user
2888 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2889 if initial_pr:
2890 pr = dict(initial_pr)
2891 pr['streamingData'] = None
b6de707d 2892 prs.append(pr)
379e44ed 2893
2894 last_error = None
b6de707d 2895 tried_iframe_fallback = False
2896 player_url = None
c0bc527b
M
2897 while clients:
2898 client = clients.pop()
11f9be09 2899 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2900 if 'configs' not in self._configuration_arg('player_skip'):
2901 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2902
b6de707d 2903 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2904 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2905 if 'js' in self._configuration_arg('player_skip'):
2906 require_js_player = False
2907 player_url = None
2908
2909 if not player_url and not tried_iframe_fallback and require_js_player:
2910 player_url = self._download_player_url(video_id)
2911 tried_iframe_fallback = True
2912
379e44ed 2913 try:
2914 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2915 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2916 except ExtractorError as e:
2917 if last_error:
2918 self.report_warning(last_error)
2919 last_error = e
2920 continue
2921
11f9be09 2922 if pr:
b6de707d 2923 prs.append(pr)
c0bc527b 2924
e7e94f2a 2925 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 2926 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
2927 append_client(client.replace('_agegate', '_creator'))
2928 elif self._is_agegated(pr):
2929 append_client(f'{client}_agegate')
c0bc527b 2930
379e44ed 2931 if last_error:
b6de707d 2932 if not len(prs):
379e44ed 2933 raise last_error
2934 self.report_warning(last_error)
b6de707d 2935 return prs, player_url
11f9be09 2936
2937 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
a0bb6ce5 2938 itags, stream_ids = {}, []
2a9c6dcd 2939 itag_qualities, res_qualities = {}, {}
d3fc8074 2940 q = qualities([
2a9c6dcd 2941 # Normally tiny is the smallest video-only formats. But
2942 # audio-only formats with unknown quality may get tagged as tiny
2943 'tiny',
2944 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 2945 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2946 ])
11f9be09 2947 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 2948
545cc85d 2949 for fmt in streaming_formats:
2950 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2951 continue
321bf820 2952
cc2db878 2953 itag = str_or_none(fmt.get('itag'))
9297939e 2954 audio_track = fmt.get('audioTrack') or {}
2955 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2956 if stream_id in stream_ids:
2957 continue
2958
cc2db878 2959 quality = fmt.get('quality')
2a9c6dcd 2960 height = int_or_none(fmt.get('height'))
d3fc8074 2961 if quality == 'tiny' or not quality:
2962 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 2963 # The 3gp format (17) in android client has a quality of "small",
2964 # but is actually worse than other formats
2965 if itag == '17':
2966 quality = 'tiny'
2967 if quality:
2968 if itag:
2969 itag_qualities[itag] = quality
2970 if height:
2971 res_qualities[height] = quality
cc2db878 2972 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2973 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2974 # number of fragment that would subsequently requested with (`&sq=N`)
2975 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2976 continue
2977
545cc85d 2978 fmt_url = fmt.get('url')
2979 if not fmt_url:
2980 sc = compat_parse_qs(fmt.get('signatureCipher'))
2981 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2982 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2983 if not (sc and fmt_url and encrypted_sig):
2984 continue
545cc85d 2985 if not player_url:
201e9eaa 2986 continue
545cc85d 2987 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2988 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2989 fmt_url += '&' + sp + '=' + signature
2990
404f611f 2991 query = parse_qs(fmt_url)
2992 throttled = False
b2916526 2993 if query.get('n'):
404f611f 2994 try:
2995 fmt_url = update_url_query(fmt_url, {
2996 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2997 except ExtractorError as e:
aa9369a2 2998 self.report_warning(
2999 f'nsig extraction failed: You may experience throttling for some formats\n'
3000 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3001 throttled = True
3002
545cc85d 3003 if itag:
a0bb6ce5 3004 itags[itag] = 'https'
9297939e 3005 stream_ids.append(stream_id)
3006
cc2db878 3007 tbr = float_or_none(
3008 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
545cc85d 3009 dct = {
3010 'asr': int_or_none(fmt.get('audioSampleRate')),
3011 'filesize': int_or_none(fmt.get('contentLength')),
3012 'format_id': itag,
34921b43 3013 'format_note': join_nonempty(
26e8e044 3014 '%s%s' % (audio_track.get('displayName') or '',
3015 ' (default)' if audio_track.get('audioIsDefault') else ''),
404f611f 3016 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
34921b43 3017 throttled and 'THROTTLED', delim=', '),
c18d4482 3018 'source_preference': -10 if throttled else -1,
a4211baf 3019 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3020 'height': height,
dca3ff4a 3021 'quality': q(quality),
cc2db878 3022 'tbr': tbr,
545cc85d 3023 'url': fmt_url,
2a9c6dcd 3024 'width': int_or_none(fmt.get('width')),
0fb983f6 3025 'language': audio_track.get('id', '').split('.')[0],
26e8e044 3026 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
545cc85d 3027 }
60bdb7bd 3028 mime_mobj = re.match(
3029 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3030 if mime_mobj:
3031 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3032 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3033 no_audio = dct.get('acodec') == 'none'
3034 no_video = dct.get('vcodec') == 'none'
3035 if no_audio:
3036 dct['vbr'] = tbr
3037 if no_video:
3038 dct['abr'] = tbr
3039 if no_audio or no_video:
545cc85d 3040 dct['downloader_options'] = {
3041 # Youtube throttles chunks >~10M
3042 'http_chunk_size': 10485760,
bf1317d2 3043 }
7c60c33e 3044 if dct.get('ext'):
3045 dct['container'] = dct['ext'] + '_dash'
11f9be09 3046 yield dct
545cc85d 3047
adbc4ec4 3048 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3049 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3050 if not self.get_param('youtube_include_hls_manifest', True):
3051 skip_manifests.append('hls')
3052 get_dash = 'dash' not in skip_manifests and (
3053 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3054 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3055
a0bb6ce5 3056 def process_manifest_format(f, proto, itag):
3057 if itag in itags:
3058 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3059 return False
3060 itag = f'{itag}-{proto}'
3061 if itag:
3062 f['format_id'] = itag
3063 itags[itag] = proto
3064
3065 f['quality'] = next((
3066 q(qdict[val])
e339d25a 3067 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3068 if val in qdict), -1)
3069 return True
2a9c6dcd 3070
11f9be09 3071 for sd in streaming_data:
5d3a0e79 3072 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3073 if hls_manifest_url:
2a9c6dcd 3074 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3075 if process_manifest_format(f, 'hls', self._search_regex(
3076 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3077 yield f
545cc85d 3078
5d3a0e79 3079 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3080 if dash_manifest_url:
2a9c6dcd 3081 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3082 if process_manifest_format(f, 'dash', f['format_id']):
3083 f['filesize'] = int_or_none(self._search_regex(
3084 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3085 if live_from_start:
3086 f['is_from_start'] = True
3087
a0bb6ce5 3088 yield f
11f9be09 3089
720c3099 3090 def _extract_storyboard(self, player_responses, duration):
3091 spec = get_first(
3092 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3093 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3094 if not base_url:
720c3099 3095 return
720c3099 3096 L = len(spec) - 1
3097 for i, args in enumerate(spec):
3098 args = args.split('#')
3099 counts = list(map(int_or_none, args[:5]))
3100 if len(args) != 8 or not all(counts):
3101 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3102 continue
3103 width, height, frame_count, cols, rows = counts
3104 N, sigh = args[6:]
3105
3106 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3107 fragment_count = frame_count / (cols * rows)
3108 fragment_duration = duration / fragment_count
3109 yield {
3110 'format_id': f'sb{i}',
3111 'format_note': 'storyboard',
3112 'ext': 'mhtml',
3113 'protocol': 'mhtml',
3114 'acodec': 'none',
3115 'vcodec': 'none',
3116 'url': url,
3117 'width': width,
3118 'height': height,
3119 'fragments': [{
3120 'path': url.replace('$M', str(j)),
3121 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3122 } for j in range(math.ceil(fragment_count))],
3123 }
3124
adbc4ec4 3125 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3126 webpage = None
3127 if 'webpage' not in self._configuration_arg('player_skip'):
3128 webpage = self._download_webpage(
3129 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3130
3131 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3132
b6de707d 3133 player_responses, player_url = self._extract_player_responses(
11f9be09 3134 self._get_requested_clients(url, smuggled_data),
99e9e001 3135 video_id, webpage, master_ytcfg)
11f9be09 3136
adbc4ec4
THD
3137 return webpage, master_ytcfg, player_responses, player_url
3138
3139 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3140 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3141 is_live = get_first(video_details, 'isLive')
3142 if is_live is None:
3143 is_live = get_first(live_broadcast_details, 'isLiveNow')
3144
3145 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3146 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3147
3148 return live_broadcast_details, is_live, streaming_data, formats
3149
3150 def _real_extract(self, url):
3151 url, smuggled_data = unsmuggle_url(url, {})
3152 video_id = self._match_id(url)
3153
3154 base_url = self.http_scheme() + '//www.youtube.com/'
3155 webpage_url = base_url + 'watch?v=' + video_id
3156
3157 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3158
11f9be09 3159 playability_statuses = traverse_obj(
3160 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3161
3162 trailer_video_id = get_first(
3163 playability_statuses,
3164 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3165 expected_type=str)
3166 if trailer_video_id:
3167 return self.url_result(
3168 trailer_video_id, self.ie_key(), trailer_video_id)
3169
3170 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3171 if webpage else (lambda x: None))
3172
3173 video_details = traverse_obj(
3174 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3175 microformats = traverse_obj(
3176 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3177 expected_type=dict, default=[])
3178 video_title = (
3179 get_first(video_details, 'title')
3180 or self._get_text(microformats, (..., 'title'))
3181 or search_meta(['og:title', 'twitter:title', 'title']))
3182 video_description = get_first(video_details, 'shortDescription')
3183
d89257f3 3184 multifeed_metadata_list = get_first(
3185 player_responses,
3186 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3187 expected_type=str)
3188 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3189 if self.get_param('noplaylist'):
11f9be09 3190 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3191 else:
3192 entries = []
3193 feed_ids = []
3194 for feed in multifeed_metadata_list.split(','):
3195 # Unquote should take place before split on comma (,) since textual
3196 # fields may contain comma as well (see
3197 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3198 feed_data = compat_parse_qs(
3199 compat_urllib_parse_unquote_plus(feed))
3200
3201 def feed_entry(name):
3202 return try_get(
3203 feed_data, lambda x: x[name][0], compat_str)
3204
3205 feed_id = feed_entry('id')
3206 if not feed_id:
3207 continue
3208 feed_title = feed_entry('title')
3209 title = video_title
3210 if feed_title:
3211 title += ' (%s)' % feed_title
3212 entries.append({
3213 '_type': 'url_transparent',
3214 'ie_key': 'Youtube',
3215 'url': smuggle_url(
3216 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3217 {'force_singlefeed': True}),
3218 'title': title,
3219 })
3220 feed_ids.append(feed_id)
3221 self.to_screen(
3222 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3223 % (', '.join(feed_ids), video_id))
3224 return self.playlist_result(
3225 entries, video_id, video_title, video_description)
11f9be09 3226
adbc4ec4 3227 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3228
545cc85d 3229 if not formats:
11f9be09 3230 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3231 self.report_drm(video_id)
11f9be09 3232 pemr = get_first(
3233 playability_statuses,
3234 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3235 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3236 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3237 if subreason:
545cc85d 3238 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3239 countries = get_first(microformats, 'availableCountries')
545cc85d 3240 if not countries:
3241 regions_allowed = search_meta('regionsAllowed')
3242 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3243 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3244 reason += f'. {subreason}'
545cc85d 3245 if reason:
b7da73eb 3246 self.raise_no_formats(reason, expected=True)
bf1317d2 3247
11f9be09 3248 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3249 if not keywords and webpage:
3250 keywords = [
3251 unescapeHTML(m.group('content'))
3252 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3253 for keyword in keywords:
3254 if keyword.startswith('yt:stretch='):
201c1459 3255 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3256 if mobj:
3257 # NB: float is intentional for forcing float division
3258 w, h = (float(v) for v in mobj.groups())
3259 if w > 0 and h > 0:
3260 ratio = w / h
3261 for f in formats:
3262 if f.get('vcodec') != 'none':
3263 f['stretched_ratio'] = ratio
3264 break
a709d873 3265 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3266 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3267 if thumbnail_url:
3268 thumbnails.append({
3269 'url': thumbnail_url,
ff2751ac 3270 })
fccf5021 3271 original_thumbnails = thumbnails.copy()
3272
0ba692ac 3273 # The best resolution thumbnails sometimes does not appear in the webpage
3274 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3275 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3276 thumbnail_names = [
3277 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3278 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3279 'mqdefault', 'mq1', 'mq2', 'mq3',
3280 'default', '1', '2', '3'
3281 ]
cca80fe6 3282 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3283 thumbnails.extend({
3284 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3285 video_id=video_id, name=name, ext=ext,
3286 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3287 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3288 for thumb in thumbnails:
cca80fe6 3289 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3290 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3291 self._remove_duplicate_formats(thumbnails)
fccf5021 3292 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3293
7ea65411 3294 category = get_first(microformats, 'category') or search_meta('genre')
3295 channel_id = str_or_none(
3296 get_first(video_details, 'channelId')
3297 or get_first(microformats, 'externalChannelId')
3298 or search_meta('channelId'))
3299 duration = int_or_none(
3300 get_first(video_details, 'lengthSeconds')
3301 or get_first(microformats, 'lengthSeconds')
3302 or parse_duration(search_meta('duration'))) or None
3303 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3304
3305 live_content = get_first(video_details, 'isLiveContent')
3306 is_upcoming = get_first(video_details, 'isUpcoming')
3307 if is_live is None:
3308 if is_upcoming or live_content is False:
3309 is_live = False
3310 if is_upcoming is None and (live_content or is_live):
3311 is_upcoming = False
adbc4ec4
THD
3312 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3313 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3314 if not duration and live_end_time and live_start_time:
3315 duration = live_end_time - live_start_time
3316
3317 if is_live and self.get_param('live_from_start'):
3318 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3319
720c3099 3320 formats.extend(self._extract_storyboard(player_responses, duration))
3321
3322 # Source is given priority since formats that throttle are given lower source_preference
3323 # When throttling issue is fully fixed, remove this
3324 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3325
545cc85d 3326 info = {
3327 'id': video_id,
39ca3b5c 3328 'title': video_title,
545cc85d 3329 'formats': formats,
3330 'thumbnails': thumbnails,
fccf5021 3331 # The best thumbnail that we are sure exists. Prevents unnecessary
3332 # URL checking if user don't care about getting the best possible thumbnail
3333 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3334 'description': video_description,
3335 'upload_date': unified_strdate(
11f9be09 3336 get_first(microformats, 'uploadDate')
545cc85d 3337 or search_meta('uploadDate')),
11f9be09 3338 'uploader': get_first(video_details, 'author'),
545cc85d 3339 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3340 'uploader_url': owner_profile_url,
3341 'channel_id': channel_id,
e0ddbd02 3342 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3343 'duration': duration,
3344 'view_count': int_or_none(
11f9be09 3345 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3346 or search_meta('interactionCount')),
11f9be09 3347 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3348 'age_limit': 18 if (
11f9be09 3349 get_first(microformats, 'isFamilySafe') is False
545cc85d 3350 or search_meta('isFamilyFriendly') == 'false'
3351 or search_meta('og:restrictions:age') == '18+') else 0,
3352 'webpage_url': webpage_url,
3353 'categories': [category] if category else None,
3354 'tags': keywords,
11f9be09 3355 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3356 'is_live': is_live,
3357 'was_live': (False if is_live or is_upcoming or live_content is False
3358 else None if is_live is None or is_upcoming is None
3359 else live_content),
3360 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3361 'release_timestamp': live_start_time,
545cc85d 3362 }
b477fc13 3363
3944e7af 3364 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3365 if pctr:
ecdc9049 3366 def get_lang_code(track):
3367 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3368 or track.get('languageCode'))
3369
3370 # Converted into dicts to remove duplicates
3371 captions = {
3372 get_lang_code(sub): sub
3373 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3374 translation_languages = {
3375 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3376 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3377
774d79cc 3378 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3379 lang_subs = container.setdefault(lang_code, [])
545cc85d 3380 for fmt in self._SUBTITLE_FORMATS:
3381 query.update({
3382 'fmt': fmt,
3383 })
3384 lang_subs.append({
3385 'ext': fmt,
3386 'url': update_url_query(base_url, query),
774d79cc 3387 'name': sub_name,
545cc85d 3388 })
7e72694b 3389
ecdc9049 3390 subtitles, automatic_captions = {}, {}
3391 for lang_code, caption_track in captions.items():
3392 base_url = caption_track.get('baseUrl')
545cc85d 3393 if not base_url:
3394 continue
ecdc9049 3395 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3396 if caption_track.get('kind') != 'asr':
545cc85d 3397 if not lang_code:
3398 continue
3399 process_language(
ecdc9049 3400 subtitles, base_url, lang_code, lang_name, {})
3401 if not caption_track.get('isTranslatable'):
3402 continue
3944e7af 3403 for trans_code, trans_name in translation_languages.items():
3404 if not trans_code:
545cc85d 3405 continue
ecdc9049 3406 if caption_track.get('kind') != 'asr':
3407 trans_code += f'-{lang_code}'
3408 trans_name += format_field(lang_name, template=' from %s')
545cc85d 3409 process_language(
ecdc9049 3410 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3411 info['automatic_captions'] = automatic_captions
3412 info['subtitles'] = subtitles
7e72694b 3413
545cc85d 3414 parsed_url = compat_urllib_parse_urlparse(url)
3415 for component in [parsed_url.fragment, parsed_url.query]:
3416 query = compat_parse_qs(component)
3417 for k, v in query.items():
3418 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3419 d_k += '_time'
3420 if d_k not in info and k in s_ks:
3421 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3422
3423 # Youtube Music Auto-generated description
822b9d9c 3424 if video_description:
38d70284 3425 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 3426 if mobj:
822b9d9c
RA
3427 release_year = mobj.group('release_year')
3428 release_date = mobj.group('release_date')
3429 if release_date:
3430 release_date = release_date.replace('-', '')
3431 if not release_year:
545cc85d 3432 release_year = release_date[:4]
3433 info.update({
3434 'album': mobj.group('album'.strip()),
3435 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3436 'track': mobj.group('track').strip(),
3437 'release_date': release_date,
cc2db878 3438 'release_year': int_or_none(release_year),
545cc85d 3439 })
7e72694b 3440
545cc85d 3441 initial_data = None
3442 if webpage:
3443 initial_data = self._extract_yt_initial_variable(
3444 webpage, self._YT_INITIAL_DATA_RE, video_id,
3445 'yt initial data')
3446 if not initial_data:
99e9e001 3447 query = {'videoId': video_id}
3448 query.update(self._get_checkok_params())
109dd3b2 3449 initial_data = self._extract_response(
3450 item_id=video_id, ep='next', fatal=False,
99e9e001 3451 ytcfg=master_ytcfg, query=query,
3452 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3453 note='Downloading initial data API JSON')
545cc85d 3454
c60ee3a2 3455 try:
3456 # This will error if there is no livechat
3457 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3458 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3459 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3460 'video_id': video_id,
3461 'ext': 'json',
f6745c49 3462 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3463 }]
3464 except (KeyError, IndexError, TypeError):
3465 pass
545cc85d 3466
3467 if initial_data:
7c365c21 3468 info['chapters'] = (
3469 self._extract_chapters_from_json(initial_data, duration)
3470 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3471 or None)
545cc85d 3472
3473 contents = try_get(
3474 initial_data,
3475 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3476 list) or []
3477 for content in contents:
3478 vpir = content.get('videoPrimaryInfoRenderer')
3479 if vpir:
3480 stl = vpir.get('superTitleLink')
3481 if stl:
fe93e2c4 3482 stl = self._get_text(stl)
545cc85d 3483 if try_get(
3484 vpir,
3485 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3486 info['location'] = stl
3487 else:
3488 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3489 if mobj:
3490 info.update({
3491 'series': mobj.group(1),
3492 'season_number': int(mobj.group(2)),
3493 'episode_number': int(mobj.group(3)),
3494 })
3495 for tlb in (try_get(
3496 vpir,
3497 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3498 list) or []):
3499 tbr = tlb.get('toggleButtonRenderer') or {}
3500 for getter, regex in [(
3501 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3502 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3503 lambda x: x['accessibility'],
3504 lambda x: x['accessibilityData']['accessibilityData'],
3505 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3506 label = (try_get(tbr, getter, dict) or {}).get('label')
3507 if label:
3508 mobj = re.match(regex, label)
3509 if mobj:
3510 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3511 break
3512 sbr_tooltip = try_get(
3513 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3514 if sbr_tooltip:
3515 like_count, dislike_count = sbr_tooltip.split(' / ')
3516 info.update({
3517 'like_count': str_to_int(like_count),
3518 'dislike_count': str_to_int(dislike_count),
3519 })
3520 vsir = content.get('videoSecondaryInfoRenderer')
3521 if vsir:
6c73052c 3522 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3523 info.update({
3524 'channel': self._get_text(vor, 'title'),
3525 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3526
545cc85d 3527 rows = try_get(
3528 vsir,
3529 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3530 list) or []
3531 multiple_songs = False
3532 for row in rows:
3533 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3534 multiple_songs = True
3535 break
3536 for row in rows:
3537 mrr = row.get('metadataRowRenderer') or {}
3538 mrr_title = mrr.get('title')
3539 if not mrr_title:
3540 continue
052e1350 3541 mrr_title = self._get_text(mrr, 'title')
3542 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3543 if mrr_title == 'License':
3544 info['license'] = mrr_contents_text
3545 elif not multiple_songs:
3546 if mrr_title == 'Album':
3547 info['album'] = mrr_contents_text
3548 elif mrr_title == 'Artist':
3549 info['artist'] = mrr_contents_text
3550 elif mrr_title == 'Song':
3551 info['track'] = mrr_contents_text
3552
3553 fallbacks = {
3554 'channel': 'uploader',
3555 'channel_id': 'uploader_id',
3556 'channel_url': 'uploader_url',
3557 }
3558 for to, frm in fallbacks.items():
3559 if not info.get(to):
3560 info[to] = info.get(frm)
3561
3562 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3563 v = info.get(s_k)
3564 if v:
3565 info[d_k] = v
b84071c0 3566
11f9be09 3567 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3568 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3569 is_membersonly = None
b28f8d24 3570 is_premium = None
c224251a
M
3571 if initial_data and is_private is not None:
3572 is_membersonly = False
b28f8d24 3573 is_premium = False
47193e02 3574 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3575 badge_labels = set()
3576 for content in contents:
3577 if not isinstance(content, dict):
3578 continue
3579 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3580 for badge_label in badge_labels:
3581 if badge_label.lower() == 'members only':
3582 is_membersonly = True
3583 elif badge_label.lower() == 'premium':
3584 is_premium = True
3585 elif badge_label.lower() == 'unlisted':
3586 is_unlisted = True
c224251a 3587
c224251a
M
3588 info['availability'] = self._availability(
3589 is_private=is_private,
b28f8d24 3590 needs_premium=is_premium,
c224251a
M
3591 needs_subscription=is_membersonly,
3592 needs_auth=info['age_limit'] >= 18,
3593 is_unlisted=None if is_private is None else is_unlisted)
3594
a2160aa4 3595 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3596
11f9be09 3597 self.mark_watched(video_id, player_responses)
d77ab8e2 3598
545cc85d 3599 return info
c5e8d7af 3600
a61fd4cf 3601
a6213a49 3602class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3603
a6213a49 3604 def _extract_channel_id(self, webpage):
3605 channel_id = self._html_search_meta(
3606 'channelId', webpage, 'channel id', default=None)
3607 if channel_id:
3608 return channel_id
3609 channel_url = self._html_search_meta(
3610 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3611 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3612 'twitter:app:url:googleplay'), webpage, 'channel url')
3613 return self._search_regex(
3614 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3615 channel_url, 'channel id')
15f6397c 3616
8bdd16b4 3617 @staticmethod
cd7c66cf 3618 def _extract_basic_item_renderer(item):
3619 # Modified from _extract_grid_item_renderer
201c1459 3620 known_basic_renderers = (
3621 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3622 )
3623 for key, renderer in item.items():
201c1459 3624 if not isinstance(renderer, dict):
cd7c66cf 3625 continue
201c1459 3626 elif key in known_basic_renderers:
3627 return renderer
3628 elif key.startswith('grid') and key.endswith('Renderer'):
3629 return renderer
8bdd16b4 3630
8bdd16b4 3631 def _grid_entries(self, grid_renderer):
3632 for item in grid_renderer['items']:
3633 if not isinstance(item, dict):
39b62db1 3634 continue
cd7c66cf 3635 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3636 if not isinstance(renderer, dict):
3637 continue
052e1350 3638 title = self._get_text(renderer, 'title')
fe93e2c4 3639
8bdd16b4 3640 # playlist
3641 playlist_id = renderer.get('playlistId')
3642 if playlist_id:
3643 yield self.url_result(
3644 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3645 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3646 video_title=title)
201c1459 3647 continue
8bdd16b4 3648 # video
3649 video_id = renderer.get('videoId')
3650 if video_id:
3651 yield self._extract_video(renderer)
201c1459 3652 continue
8bdd16b4 3653 # channel
3654 channel_id = renderer.get('channelId')
3655 if channel_id:
8bdd16b4 3656 yield self.url_result(
3657 'https://www.youtube.com/channel/%s' % channel_id,
3658 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3659 continue
3660 # generic endpoint URL support
3661 ep_url = urljoin('https://www.youtube.com/', try_get(
3662 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3663 compat_str))
3664 if ep_url:
3665 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3666 if ie.suitable(ep_url):
3667 yield self.url_result(
3668 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3669 break
8bdd16b4 3670
16aa9ea4 3671 def _music_reponsive_list_entry(self, renderer):
3672 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3673 if video_id:
3674 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3675 ie=YoutubeIE.ie_key(), video_id=video_id)
3676 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3677 if playlist_id:
3678 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3679 if video_id:
3680 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3681 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3682 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3683 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3684 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3685 if browse_id:
3686 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3687 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3688
3d3dddc9 3689 def _shelf_entries_from_content(self, shelf_renderer):
3690 content = shelf_renderer.get('content')
3691 if not isinstance(content, dict):
8bdd16b4 3692 return
cd7c66cf 3693 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3694 if renderer:
3695 # TODO: add support for nested playlists so each shelf is processed
3696 # as separate playlist
3697 # TODO: this includes only first N items
3698 for entry in self._grid_entries(renderer):
3699 yield entry
3700 renderer = content.get('horizontalListRenderer')
3701 if renderer:
3702 # TODO
3703 pass
8bdd16b4 3704
29f7c58a 3705 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3706 ep = try_get(
3707 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3708 compat_str)
3709 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3710 if shelf_url:
29f7c58a 3711 # Skipping links to another channels, note that checking for
3712 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3713 # will not work
3714 if skip_channels and '/channels?' in shelf_url:
3715 return
052e1350 3716 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3717 yield self.url_result(shelf_url, video_title=title)
3718 # Shelf may not contain shelf URL, fallback to extraction from content
3719 for entry in self._shelf_entries_from_content(shelf_renderer):
3720 yield entry
c5e8d7af 3721
8bdd16b4 3722 def _playlist_entries(self, video_list_renderer):
3723 for content in video_list_renderer['contents']:
3724 if not isinstance(content, dict):
3725 continue
3726 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3727 if not isinstance(renderer, dict):
3728 continue
3729 video_id = renderer.get('videoId')
3730 if not video_id:
3731 continue
3732 yield self._extract_video(renderer)
07aeced6 3733
3462ffa8 3734 def _rich_entries(self, rich_grid_renderer):
3735 renderer = try_get(
70d5c17b 3736 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3737 video_id = renderer.get('videoId')
3738 if not video_id:
3739 return
3740 yield self._extract_video(renderer)
3741
8bdd16b4 3742 def _video_entry(self, video_renderer):
3743 video_id = video_renderer.get('videoId')
3744 if video_id:
3745 return self._extract_video(video_renderer)
dacb3a86 3746
8bdd16b4 3747 def _post_thread_entries(self, post_thread_renderer):
3748 post_renderer = try_get(
3749 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3750 if not post_renderer:
3751 return
3752 # video attachment
3753 video_renderer = try_get(
895b0931 3754 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3755 video_id = video_renderer.get('videoId')
3756 if video_id:
3757 entry = self._extract_video(video_renderer)
8bdd16b4 3758 if entry:
3759 yield entry
895b0931 3760 # playlist attachment
3761 playlist_id = try_get(
3762 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3763 if playlist_id:
3764 yield self.url_result(
e28f1c0a 3765 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3766 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3767 # inline video links
3768 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3769 for run in runs:
3770 if not isinstance(run, dict):
3771 continue
3772 ep_url = try_get(
3773 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3774 if not ep_url:
3775 continue
3776 if not YoutubeIE.suitable(ep_url):
3777 continue
3778 ep_video_id = YoutubeIE._match_id(ep_url)
3779 if video_id == ep_video_id:
3780 continue
895b0931 3781 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3782
8bdd16b4 3783 def _post_thread_continuation_entries(self, post_thread_continuation):
3784 contents = post_thread_continuation.get('contents')
3785 if not isinstance(contents, list):
3786 return
3787 for content in contents:
3788 renderer = content.get('backstagePostThreadRenderer')
3789 if not isinstance(renderer, dict):
3790 continue
3791 for entry in self._post_thread_entries(renderer):
3792 yield entry
07aeced6 3793
39ed931e 3794 r''' # unused
3795 def _rich_grid_entries(self, contents):
3796 for content in contents:
3797 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3798 if video_renderer:
3799 entry = self._video_entry(video_renderer)
3800 if entry:
3801 yield entry
3802 '''
a6213a49 3803 def _extract_entries(self, parent_renderer, continuation_list):
3804 # continuation_list is modified in-place with continuation_list = [continuation_token]
3805 continuation_list[:] = [None]
3806 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3807 for content in contents:
3808 if not isinstance(content, dict):
3809 continue
16aa9ea4 3810 is_renderer = traverse_obj(
3811 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3812 expected_type=dict)
a6213a49 3813 if not is_renderer:
3814 renderer = content.get('richItemRenderer')
3815 if renderer:
3816 for entry in self._rich_entries(renderer):
3817 yield entry
3818 continuation_list[0] = self._extract_continuation(parent_renderer)
3819 continue
3820 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3821 for isr_content in isr_contents:
3822 if not isinstance(isr_content, dict):
8bdd16b4 3823 continue
69184e41 3824
a6213a49 3825 known_renderers = {
3826 'playlistVideoListRenderer': self._playlist_entries,
3827 'gridRenderer': self._grid_entries,
3828 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3829 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3830 'backstagePostThreadRenderer': self._post_thread_entries,
3831 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3832 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3833 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3834 }
3835 for key, renderer in isr_content.items():
3836 if key not in known_renderers:
3837 continue
3838 for entry in known_renderers[key](renderer):
3839 if entry:
3840 yield entry
3841 continuation_list[0] = self._extract_continuation(renderer)
3842 break
70d5c17b 3843
3844 if not continuation_list[0]:
a6213a49 3845 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3846
a6213a49 3847 if not continuation_list[0]:
3848 continuation_list[0] = self._extract_continuation(parent_renderer)
3849
3850 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3851 continuation_list = [None]
3852 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3853 tab_content = try_get(tab, lambda x: x['content'], dict)
3854 if not tab_content:
3855 return
3462ffa8 3856 parent_renderer = (
29f7c58a 3857 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3858 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3859 for entry in extract_entries(parent_renderer):
3860 yield entry
3462ffa8 3861 continuation = continuation_list[0]
d069eca7 3862
8bdd16b4 3863 for page_num in itertools.count(1):
3864 if not continuation:
3865 break
99e9e001 3866 headers = self.generate_api_headers(
3867 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3868 response = self._extract_response(
3869 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3870 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3871 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3872
3873 if not response:
8bdd16b4 3874 break
ac56cf38 3875 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3876 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3877 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 3878
69184e41 3879 known_continuation_renderers = {
3880 'playlistVideoListContinuation': self._playlist_entries,
3881 'gridContinuation': self._grid_entries,
3882 'itemSectionContinuation': self._post_thread_continuation_entries,
3883 'sectionListContinuation': extract_entries, # for feeds
3884 }
8bdd16b4 3885 continuation_contents = try_get(
69184e41 3886 response, lambda x: x['continuationContents'], dict) or {}
3887 continuation_renderer = None
3888 for key, value in continuation_contents.items():
3889 if key not in known_continuation_renderers:
3462ffa8 3890 continue
69184e41 3891 continuation_renderer = value
3892 continuation_list = [None]
3893 for entry in known_continuation_renderers[key](continuation_renderer):
3894 yield entry
3895 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3896 break
3897 if continuation_renderer:
3898 continue
c5e8d7af 3899
a1b535bd 3900 known_renderers = {
3901 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3902 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3903 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3904 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3905 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3906 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3907 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3908 }
cce889b9 3909 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3910 continuation_items = try_get(
cce889b9 3911 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3912 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3913 video_items_renderer = None
3914 for key, value in continuation_item.items():
3915 if key not in known_renderers:
8bdd16b4 3916 continue
a1b535bd 3917 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3918 continuation_list = [None]
a1b535bd 3919 for entry in known_renderers[key][0](video_items_renderer):
3920 yield entry
9ba5705a 3921 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3922 break
3923 if video_items_renderer:
3924 continue
8bdd16b4 3925 break
9558dcec 3926
8bdd16b4 3927 @staticmethod
3928 def _extract_selected_tab(tabs):
3929 for tab in tabs:
cd684175 3930 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3931 if renderer.get('selected') is True:
3932 return renderer
2b3c2546 3933 else:
8bdd16b4 3934 raise ExtractorError('Unable to find selected tab')
b82f815f 3935
47193e02 3936 @classmethod
3937 def _extract_uploader(cls, data):
8bdd16b4 3938 uploader = {}
47193e02 3939 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3940 owner = try_get(
3941 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3942 if owner:
3943 uploader['uploader'] = owner.get('text')
3944 uploader['uploader_id'] = try_get(
3945 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3946 uploader['uploader_url'] = urljoin(
3947 'https://www.youtube.com/',
3948 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3949 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3950
ac56cf38 3951 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 3952 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 3953 tags = []
b60419c5 3954
8bdd16b4 3955 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 3956 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 3957 renderer = try_get(
3958 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3959 if renderer:
b60419c5 3960 channel_name = renderer.get('title')
3961 channel_url = renderer.get('channelUrl')
3962 channel_id = renderer.get('externalId')
39ed931e 3963 else:
64c0d954 3964 renderer = try_get(
3965 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3966
8bdd16b4 3967 if renderer:
3968 title = renderer.get('title')
ecc97af3 3969 description = renderer.get('description', '')
b60419c5 3970 playlist_id = channel_id
3971 tags = renderer.get('keywords', '').split()
b60419c5 3972
301d07fc 3973 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
3974 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
3975 def _get_uncropped(url):
3976 return url_or_none((url or '').split('=')[0] + '=s0')
3977
3978 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
3979 if avatar_thumbnails:
3980 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
3981 if uncropped_avatar:
3982 avatar_thumbnails.append({
3983 'url': uncropped_avatar,
3984 'id': 'avatar_uncropped',
3985 'preference': 1
3986 })
3987
3988 channel_banners = self._extract_thumbnails(
3989 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
3990 for banner in channel_banners:
3991 banner['preference'] = -10
3992
3993 if channel_banners:
3994 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
3995 if uncropped_banner:
3996 channel_banners.append({
3997 'url': uncropped_banner,
3998 'id': 'banner_uncropped',
3999 'preference': -5
4000 })
4001
4002 primary_thumbnails = self._extract_thumbnails(
4003 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4004
3462ffa8 4005 if playlist_id is None:
70d5c17b 4006 playlist_id = item_id
f0d785d3 4007
4008 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4009 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4010 if title is None:
f0d785d3 4011 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4012 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4013 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4014
b60419c5 4015 metadata = {
4016 'playlist_id': playlist_id,
4017 'playlist_title': title,
4018 'playlist_description': description,
4019 'uploader': channel_name,
4020 'uploader_id': channel_id,
4021 'uploader_url': channel_url,
301d07fc 4022 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4023 'tags': tags,
f0d785d3 4024 'view_count': self._get_count(playlist_stats, 1),
4025 'availability': self._extract_availability(data),
4026 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4027 'playlist_count': self._get_count(playlist_stats, 0),
4028 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4029 }
4030 if not channel_id:
4031 metadata.update(self._extract_uploader(data))
4032 metadata.update({
4033 'channel': metadata['uploader'],
4034 'channel_id': metadata['uploader_id'],
4035 'channel_url': metadata['uploader_url']})
4036 return self.playlist_result(
d069eca7 4037 self._entries(
ac56cf38 4038 selected_tab, playlist_id, ytcfg,
4039 self._extract_account_syncid(ytcfg, data),
4040 self._extract_visitor_data(data, ytcfg)),
b60419c5 4041 **metadata)
73c4ac2c 4042
ac56cf38 4043 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4044 first_id = last_id = response = None
2be71994 4045 for page_num in itertools.count(1):
cd7c66cf 4046 videos = list(self._playlist_entries(playlist))
4047 if not videos:
4048 return
2be71994 4049 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4050 if start >= len(videos):
4051 return
4052 for video in videos[start:]:
4053 if video['id'] == first_id:
4054 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4055 return
4056 yield video
4057 first_id = first_id or videos[0]['id']
4058 last_id = videos[-1]['id']
79360d99 4059 watch_endpoint = try_get(
4060 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4061 headers = self.generate_api_headers(
4062 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4063 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4064 query = {
4065 'playlistId': playlist_id,
4066 'videoId': watch_endpoint.get('videoId') or last_id,
4067 'index': watch_endpoint.get('index') or len(videos),
4068 'params': watch_endpoint.get('params') or 'OAE%3D'
4069 }
4070 response = self._extract_response(
4071 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4072 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4073 check_get_keys='contents'
4074 )
cd7c66cf 4075 playlist = try_get(
79360d99 4076 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4077
ac56cf38 4078 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4079 title = playlist.get('title') or try_get(
4080 data, lambda x: x['titleText']['simpleText'], compat_str)
4081 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4082
4083 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4084 playlist_url = urljoin(url, try_get(
4085 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4086 compat_str))
4087 if playlist_url and playlist_url != url:
4088 return self.url_result(
4089 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4090 video_title=title)
cd7c66cf 4091
8bdd16b4 4092 return self.playlist_result(
ac56cf38 4093 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4094 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4095
47193e02 4096 def _extract_availability(self, data):
4097 """
4098 Gets the availability of a given playlist/tab.
4099 Note: Unless YouTube tells us explicitly, we do not assume it is public
4100 @param data: response
4101 """
4102 is_private = is_unlisted = None
4103 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4104 badge_labels = self._extract_badges(renderer)
4105
4106 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4107 privacy_dropdown_entries = try_get(
4108 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4109 for renderer_dict in privacy_dropdown_entries:
4110 is_selected = try_get(
4111 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4112 if not is_selected:
4113 continue
052e1350 4114 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4115 if label:
4116 badge_labels.add(label.lower())
4117 break
4118
4119 for badge_label in badge_labels:
4120 if badge_label == 'unlisted':
4121 is_unlisted = True
4122 elif badge_label == 'private':
4123 is_private = True
4124 elif badge_label == 'public':
4125 is_unlisted = is_private = False
4126 return self._availability(is_private, False, False, False, is_unlisted)
4127
4128 @staticmethod
4129 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4130 sidebar_renderer = try_get(
4131 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4132 for item in sidebar_renderer:
4133 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4134 if renderer:
4135 return renderer
4136
ac56cf38 4137 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4138 """
4139 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4140 """
5d342002 4141 browse_id = params = None
47193e02 4142 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4143 if not renderer:
4144 return
4145 menu_renderer = try_get(
4146 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4147 for menu_item in menu_renderer:
4148 if not isinstance(menu_item, dict):
358de58c 4149 continue
47193e02 4150 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4151 text = try_get(
4152 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4153 if not text or text.lower() != 'show unavailable videos':
4154 continue
4155 browse_endpoint = try_get(
4156 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4157 browse_id = browse_endpoint.get('browseId')
4158 params = browse_endpoint.get('params')
4159 break
5d342002 4160
11f9be09 4161 headers = self.generate_api_headers(
99e9e001 4162 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4163 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4164 query = {
4165 'params': params or 'wgYCCAA=',
4166 'browseId': browse_id or 'VL%s' % item_id
4167 }
4168 return self._extract_response(
4169 item_id=item_id, headers=headers, query=query,
fe93e2c4 4170 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4171 note='Downloading API JSON with unavailable videos')
358de58c 4172
ac56cf38 4173 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4174 retries = self.get_param('extractor_retries', 3)
62bff2c1 4175 count = -1
ac56cf38 4176 webpage = data = last_error = None
14fdfea9 4177 while count < retries:
62bff2c1 4178 count += 1
14fdfea9 4179 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4180 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4181 if last_error:
c705177d 4182 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4183 try:
4184 webpage = self._download_webpage(
4185 url, item_id,
4186 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4187 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4188 except ExtractorError as e:
4189 if isinstance(e.cause, network_exceptions):
4190 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4191 last_error = error_to_compat_str(e.cause or e.msg)
4192 if count < retries:
4193 continue
4194 if fatal:
4195 raise
4196 self.report_warning(error_to_compat_str(e))
14fdfea9 4197 break
ac56cf38 4198 else:
4199 try:
4200 self._extract_and_report_alerts(data)
4201 except ExtractorError as e:
4202 if fatal:
4203 raise
4204 self.report_warning(error_to_compat_str(e))
4205 break
4206
4207 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4208 break
4209
4210 last_error = 'Incomplete yt initial data received'
4211 if count >= retries:
4212 if fatal:
4213 raise ExtractorError(last_error)
4214 self.report_warning(last_error)
4215 break
4216
cd7c66cf 4217 return webpage, data
4218
ac56cf38 4219 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4220 data = None
4221 if 'webpage' not in self._configuration_arg('skip'):
4222 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4223 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4224 if not data:
4225 if not ytcfg and self.is_authenticated:
4226 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4227 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4228 raise ExtractorError(
4229 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4230 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4231 expected=True)
4232 self.report_warning(msg, only_once=True)
4233 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4234 return data, ytcfg
4235
4236 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4237 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4238 resolve_response = self._extract_response(
4239 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4240 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4241 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4242 for ep_key, ep in endpoints.items():
4243 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4244 if params:
4245 return self._extract_response(
4246 item_id=item_id, query=params, ep=ep, headers=headers,
4247 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4248 check_get_keys=('contents', 'currentVideoEndpoint'))
4249 err_note = 'Failed to resolve url (does the playlist exist?)'
4250 if fatal:
4251 raise ExtractorError(err_note, expected=True)
4252 self.report_warning(err_note, item_id)
4253
a6213a49 4254 @staticmethod
4255 def _smuggle_data(entries, data):
4256 for entry in entries:
4257 if data:
4258 entry['url'] = smuggle_url(entry['url'], data)
4259 yield entry
4260
4261 _SEARCH_PARAMS = None
4262
16aa9ea4 4263 def _search_results(self, query, params=NO_DEFAULT, client=None):
a6213a49 4264 data = {'query': query}
4265 if params is NO_DEFAULT:
4266 params = self._SEARCH_PARAMS
4267 if params:
4268 data['params'] = params
16aa9ea4 4269
4270 content_keys = (
4271 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4272 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4273 # ytmusic search
4274 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4275 ('continuationContents', ),
4276 )
4277 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4278
a61fd4cf 4279 continuation_list = [None]
a6213a49 4280 for page_num in itertools.count(1):
a61fd4cf 4281 data.update(continuation_list[0] or {})
a6213a49 4282 search = self._extract_response(
4283 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
16aa9ea4 4284 default_client=client, check_get_keys=check_get_keys)
4285 slr_contents = traverse_obj(search, *content_keys)
4286 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4287 if not continuation_list[0]:
a6213a49 4288 break
4289
4290
4291class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4292 IE_DESC = 'YouTube Tabs'
4293 _VALID_URL = r'''(?x:
4294 https?://
4295 (?:\w+\.)?
4296 (?:
4297 youtube(?:kids)?\.com|
4298 %(invidious)s
4299 )/
4300 (?:
4301 (?P<channel_type>channel|c|user|browse)/|
4302 (?P<not_channel>
4303 feed/|hashtag/|
4304 (?:playlist|watch)\?.*?\blist=
4305 )|
4306 (?!(?:%(reserved_names)s)\b) # Direct URLs
4307 )
4308 (?P<id>[^/?\#&]+)
4309 )''' % {
4310 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4311 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4312 }
4313 IE_NAME = 'youtube:tab'
4314
4315 _TESTS = [{
4316 'note': 'playlists, multipage',
4317 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4318 'playlist_mincount': 94,
4319 'info_dict': {
4320 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4321 'title': 'Igor Kleiner - Playlists',
a6213a49 4322 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4323 'uploader': 'Igor Kleiner',
a6213a49 4324 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4325 'channel': 'Igor Kleiner',
4326 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4327 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4328 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4329 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4330 'channel_follower_count': int
a6213a49 4331 },
4332 }, {
4333 'note': 'playlists, multipage, different order',
4334 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4335 'playlist_mincount': 94,
4336 'info_dict': {
4337 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4338 'title': 'Igor Kleiner - Playlists',
a6213a49 4339 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4340 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4341 'uploader': 'Igor Kleiner',
4342 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4343 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4344 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4345 'channel': 'Igor Kleiner',
4346 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4347 'channel_follower_count': int
a6213a49 4348 },
4349 }, {
4350 'note': 'playlists, series',
4351 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4352 'playlist_mincount': 5,
4353 'info_dict': {
4354 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4355 'title': '3Blue1Brown - Playlists',
4356 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4357 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4358 'uploader': '3Blue1Brown',
976ae3ea 4359 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4360 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4361 'channel': '3Blue1Brown',
4362 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4363 'tags': ['Mathematics'],
6c73052c 4364 'channel_follower_count': int
a6213a49 4365 },
4366 }, {
4367 'note': 'playlists, singlepage',
4368 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4369 'playlist_mincount': 4,
4370 'info_dict': {
4371 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4372 'title': 'ThirstForScience - Playlists',
4373 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4374 'uploader': 'ThirstForScience',
4375 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4376 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4377 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4378 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4379 'tags': 'count:13',
4380 'channel': 'ThirstForScience',
6c73052c 4381 'channel_follower_count': int
a6213a49 4382 }
4383 }, {
4384 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4385 'only_matching': True,
4386 }, {
4387 'note': 'basic, single video playlist',
4388 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4389 'info_dict': {
4390 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4391 'uploader': 'Sergey M.',
4392 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4393 'title': 'youtube-dl public playlist',
976ae3ea 4394 'description': '',
4395 'tags': [],
4396 'view_count': int,
4397 'modified_date': '20201130',
4398 'channel': 'Sergey M.',
4399 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4400 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4401 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4402 },
4403 'playlist_count': 1,
4404 }, {
4405 'note': 'empty playlist',
4406 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4407 'info_dict': {
4408 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4409 'uploader': 'Sergey M.',
4410 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4411 'title': 'youtube-dl empty playlist',
976ae3ea 4412 'tags': [],
4413 'channel': 'Sergey M.',
4414 'description': '',
4415 'modified_date': '20160902',
4416 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4417 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4418 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4419 },
4420 'playlist_count': 0,
4421 }, {
4422 'note': 'Home tab',
4423 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4424 'info_dict': {
4425 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4426 'title': 'lex will - Home',
4427 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4428 'uploader': 'lex will',
4429 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4430 'channel': 'lex will',
4431 'tags': ['bible', 'history', 'prophesy'],
4432 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4433 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4434 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4435 'channel_follower_count': int
a6213a49 4436 },
4437 'playlist_mincount': 2,
4438 }, {
4439 'note': 'Videos tab',
4440 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4441 'info_dict': {
4442 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4443 'title': 'lex will - Videos',
4444 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4445 'uploader': 'lex will',
4446 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4447 'tags': ['bible', 'history', 'prophesy'],
4448 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4449 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4450 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4451 'channel': 'lex will',
6c73052c 4452 'channel_follower_count': int
a6213a49 4453 },
4454 'playlist_mincount': 975,
4455 }, {
4456 'note': 'Videos tab, sorted by popular',
4457 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4458 'info_dict': {
4459 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4460 'title': 'lex will - Videos',
4461 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4462 'uploader': 'lex will',
4463 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4464 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4465 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4466 'channel': 'lex will',
4467 'tags': ['bible', 'history', 'prophesy'],
4468 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4469 'channel_follower_count': int
a6213a49 4470 },
4471 'playlist_mincount': 199,
4472 }, {
4473 'note': 'Playlists tab',
4474 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4475 'info_dict': {
4476 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4477 'title': 'lex will - Playlists',
4478 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4479 'uploader': 'lex will',
4480 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4481 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4482 'channel': 'lex will',
4483 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4484 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4485 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4486 'channel_follower_count': int
a6213a49 4487 },
4488 'playlist_mincount': 17,
4489 }, {
4490 'note': 'Community tab',
4491 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4492 'info_dict': {
4493 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4494 'title': 'lex will - Community',
4495 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4496 'uploader': 'lex will',
4497 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4498 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4499 'channel': 'lex will',
4500 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4501 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4502 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4503 'channel_follower_count': int
a6213a49 4504 },
4505 'playlist_mincount': 18,
4506 }, {
4507 'note': 'Channels tab',
4508 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4509 'info_dict': {
4510 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4511 'title': 'lex will - Channels',
4512 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4513 'uploader': 'lex will',
4514 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4515 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4516 'channel': 'lex will',
4517 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4518 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4519 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4520 'channel_follower_count': int
a6213a49 4521 },
4522 'playlist_mincount': 12,
4523 }, {
4524 'note': 'Search tab',
4525 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4526 'playlist_mincount': 40,
4527 'info_dict': {
4528 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4529 'title': '3Blue1Brown - Search - linear algebra',
4530 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4531 'uploader': '3Blue1Brown',
4532 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4533 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4534 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4535 'tags': ['Mathematics'],
4536 'channel': '3Blue1Brown',
4537 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4538 'channel_follower_count': int
a6213a49 4539 },
4540 }, {
4541 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4542 'only_matching': True,
4543 }, {
4544 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4545 'only_matching': True,
4546 }, {
4547 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4548 'only_matching': True,
4549 }, {
4550 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4551 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4552 'info_dict': {
4553 'title': '29C3: Not my department',
4554 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4555 'uploader': 'Christiaan008',
4556 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4557 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4558 'tags': [],
4559 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4560 'view_count': int,
4561 'modified_date': '20150605',
4562 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4563 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4564 'channel': 'Christiaan008',
a6213a49 4565 },
4566 'playlist_count': 96,
4567 }, {
4568 'note': 'Large playlist',
4569 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4570 'info_dict': {
4571 'title': 'Uploads from Cauchemar',
4572 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4573 'uploader': 'Cauchemar',
4574 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4575 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4576 'tags': [],
4577 'modified_date': r're:\d{8}',
4578 'channel': 'Cauchemar',
4579 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4580 'view_count': int,
4581 'description': '',
4582 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4583 },
4584 'playlist_mincount': 1123,
976ae3ea 4585 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4586 }, {
4587 'note': 'even larger playlist, 8832 videos',
4588 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4589 'only_matching': True,
4590 }, {
4591 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4592 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4593 'info_dict': {
4594 'title': 'Uploads from Interstellar Movie',
4595 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4596 'uploader': 'Interstellar Movie',
4597 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4598 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4599 'tags': [],
4600 'view_count': int,
4601 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4602 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4603 'channel': 'Interstellar Movie',
4604 'description': '',
4605 'modified_date': r're:\d{8}',
a6213a49 4606 },
4607 'playlist_mincount': 21,
4608 }, {
4609 'note': 'Playlist with "show unavailable videos" button',
4610 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4611 'info_dict': {
4612 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4613 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4614 'uploader': 'Phim Siêu Nhân Nhật Bản',
4615 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4616 'view_count': int,
4617 'channel': 'Phim Siêu Nhân Nhật Bản',
4618 'tags': [],
4619 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4620 'description': '',
4621 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4622 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4623 'modified_date': r're:\d{8}',
a6213a49 4624 },
4625 'playlist_mincount': 200,
976ae3ea 4626 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4627 }, {
4628 'note': 'Playlist with unavailable videos in page 7',
4629 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4630 'info_dict': {
4631 'title': 'Uploads from BlankTV',
4632 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4633 'uploader': 'BlankTV',
4634 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4635 'channel': 'BlankTV',
4636 'channel_url': 'https://www.youtube.com/c/blanktv',
4637 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4638 'view_count': int,
4639 'tags': [],
4640 'uploader_url': 'https://www.youtube.com/c/blanktv',
4641 'modified_date': r're:\d{8}',
4642 'description': '',
a6213a49 4643 },
4644 'playlist_mincount': 1000,
976ae3ea 4645 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4646 }, {
4647 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4648 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4649 'info_dict': {
4650 'title': 'Data Analysis with Dr Mike Pound',
4651 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4652 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4653 'uploader': 'Computerphile',
4654 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4655 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4656 'tags': [],
4657 'view_count': int,
4658 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4659 'channel_url': 'https://www.youtube.com/user/Computerphile',
4660 'channel': 'Computerphile',
a6213a49 4661 },
4662 'playlist_mincount': 11,
4663 }, {
4664 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4665 'only_matching': True,
4666 }, {
4667 'note': 'Playlist URL that does not actually serve a playlist',
4668 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4669 'info_dict': {
4670 'id': 'FqZTN594JQw',
4671 'ext': 'webm',
4672 'title': "Smiley's People 01 detective, Adventure Series, Action",
4673 'uploader': 'STREEM',
4674 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4675 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4676 'upload_date': '20150526',
4677 'license': 'Standard YouTube License',
4678 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4679 'categories': ['People & Blogs'],
4680 'tags': list,
4681 'view_count': int,
4682 'like_count': int,
a6213a49 4683 },
4684 'params': {
4685 'skip_download': True,
4686 },
4687 'skip': 'This video is not available.',
4688 'add_ie': [YoutubeIE.ie_key()],
4689 }, {
4690 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4691 'only_matching': True,
4692 }, {
4693 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4694 'only_matching': True,
4695 }, {
4696 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4697 'info_dict': {
6c73052c 4698 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4699 'ext': 'mp4',
976ae3ea 4700 'title': str,
a6213a49 4701 'uploader': 'Sky News',
4702 'uploader_id': 'skynews',
4703 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4704 'upload_date': r're:\d{8}',
976ae3ea 4705 'description': str,
a6213a49 4706 'categories': ['News & Politics'],
4707 'tags': list,
4708 'like_count': int,
6c73052c 4709 'release_timestamp': 1642502819,
976ae3ea 4710 'channel': 'Sky News',
4711 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4712 'age_limit': 0,
4713 'view_count': int,
6c73052c 4714 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4715 'playable_in_embed': True,
6c73052c 4716 'release_date': '20220118',
976ae3ea 4717 'availability': 'public',
4718 'live_status': 'is_live',
4719 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4720 'channel_follower_count': int
a6213a49 4721 },
4722 'params': {
4723 'skip_download': True,
4724 },
976ae3ea 4725 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4726 }, {
4727 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4728 'info_dict': {
4729 'id': 'a48o2S1cPoo',
4730 'ext': 'mp4',
4731 'title': 'The Young Turks - Live Main Show',
4732 'uploader': 'The Young Turks',
4733 'uploader_id': 'TheYoungTurks',
4734 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4735 'upload_date': '20150715',
4736 'license': 'Standard YouTube License',
4737 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4738 'categories': ['News & Politics'],
4739 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4740 'like_count': int,
a6213a49 4741 },
4742 'params': {
4743 'skip_download': True,
4744 },
4745 'only_matching': True,
4746 }, {
4747 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4748 'only_matching': True,
4749 }, {
4750 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4751 'only_matching': True,
4752 }, {
4753 'note': 'A channel that is not live. Should raise error',
4754 'url': 'https://www.youtube.com/user/numberphile/live',
4755 'only_matching': True,
4756 }, {
4757 'url': 'https://www.youtube.com/feed/trending',
4758 'only_matching': True,
4759 }, {
4760 'url': 'https://www.youtube.com/feed/library',
4761 'only_matching': True,
4762 }, {
4763 'url': 'https://www.youtube.com/feed/history',
4764 'only_matching': True,
4765 }, {
4766 'url': 'https://www.youtube.com/feed/subscriptions',
4767 'only_matching': True,
4768 }, {
4769 'url': 'https://www.youtube.com/feed/watch_later',
4770 'only_matching': True,
4771 }, {
4772 'note': 'Recommended - redirects to home page.',
4773 'url': 'https://www.youtube.com/feed/recommended',
4774 'only_matching': True,
4775 }, {
4776 'note': 'inline playlist with not always working continuations',
4777 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4778 'only_matching': True,
4779 }, {
4780 'url': 'https://www.youtube.com/course',
4781 'only_matching': True,
4782 }, {
4783 'url': 'https://www.youtube.com/zsecurity',
4784 'only_matching': True,
4785 }, {
4786 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4787 'only_matching': True,
4788 }, {
4789 'url': 'https://www.youtube.com/TheYoungTurks/live',
4790 'only_matching': True,
4791 }, {
4792 'url': 'https://www.youtube.com/hashtag/cctv9',
4793 'info_dict': {
4794 'id': 'cctv9',
4795 'title': '#cctv9',
976ae3ea 4796 'tags': [],
a6213a49 4797 },
4798 'playlist_mincount': 350,
4799 }, {
4800 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4801 'only_matching': True,
4802 }, {
4803 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4804 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4805 'only_matching': True
4806 }, {
4807 'note': '/browse/ should redirect to /channel/',
4808 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4809 'only_matching': True
4810 }, {
4811 'note': 'VLPL, should redirect to playlist?list=PL...',
4812 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4813 'info_dict': {
4814 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4815 'uploader': 'NoCopyrightSounds',
4816 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4817 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4818 'title': 'NCS Releases',
976ae3ea 4819 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4820 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4821 'modified_date': r're:\d{8}',
4822 'view_count': int,
4823 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4824 'tags': [],
4825 'channel': 'NoCopyrightSounds',
a6213a49 4826 },
4827 'playlist_mincount': 166,
976ae3ea 4828 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4829 }, {
4830 'note': 'Topic, should redirect to playlist?list=UU...',
4831 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4832 'info_dict': {
4833 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4834 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4835 'title': 'Uploads from Royalty Free Music - Topic',
4836 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4837 'tags': [],
4838 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4839 'channel': 'Royalty Free Music - Topic',
4840 'view_count': int,
4841 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4842 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4843 'modified_date': r're:\d{8}',
4844 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4845 'description': '',
a6213a49 4846 },
4847 'expected_warnings': [
a6213a49 4848 'The URL does not have a videos tab',
976ae3ea 4849 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4850 ],
4851 'playlist_mincount': 101,
4852 }, {
4853 'note': 'Topic without a UU playlist',
4854 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4855 'info_dict': {
4856 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4857 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4858 'tags': [],
a6213a49 4859 },
4860 'expected_warnings': [
976ae3ea 4861 'the playlist redirect gave error',
a6213a49 4862 ],
4863 'playlist_mincount': 9,
4864 }, {
4865 'note': 'Youtube music Album',
4866 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4867 'info_dict': {
4868 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4869 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 4870 'tags': [],
4871 'view_count': int,
4872 'description': '',
4873 'availability': 'unlisted',
4874 'modified_date': r're:\d{8}',
a6213a49 4875 },
4876 'playlist_count': 50,
4877 }, {
4878 'note': 'unlisted single video playlist',
4879 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4880 'info_dict': {
4881 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4882 'uploader': 'colethedj',
4883 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4884 'title': 'yt-dlp unlisted playlist test',
976ae3ea 4885 'availability': 'unlisted',
4886 'tags': [],
4887 'modified_date': '20211208',
4888 'channel': 'colethedj',
4889 'view_count': int,
4890 'description': '',
4891 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4892 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4893 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 4894 },
4895 'playlist_count': 1,
4896 }, {
4897 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4898 'url': 'https://www.youtube.com/feed/recommended',
4899 'info_dict': {
4900 'id': 'recommended',
4901 'title': 'recommended',
6c73052c 4902 'tags': [],
a6213a49 4903 },
4904 'playlist_mincount': 50,
4905 'params': {
4906 'skip_download': True,
4907 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4908 },
4909 }, {
4910 'note': 'API Fallback: /videos tab, sorted by oldest first',
4911 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4912 'info_dict': {
4913 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4914 'title': 'Cody\'sLab - Videos',
4915 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4916 'uploader': 'Cody\'sLab',
4917 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 4918 'channel': 'Cody\'sLab',
4919 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4920 'tags': [],
4921 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4922 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 4923 'channel_follower_count': int
a6213a49 4924 },
4925 'playlist_mincount': 650,
4926 'params': {
4927 'skip_download': True,
4928 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4929 },
4930 }, {
4931 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4932 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4933 'info_dict': {
4934 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4935 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4936 'title': 'Uploads from Royalty Free Music - Topic',
4937 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4938 'modified_date': r're:\d{8}',
4939 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4940 'description': '',
4941 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4942 'tags': [],
4943 'channel': 'Royalty Free Music - Topic',
4944 'view_count': int,
4945 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 4946 },
4947 'expected_warnings': [
976ae3ea 4948 'does not have a videos tab',
4949 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4950 ],
4951 'playlist_mincount': 101,
4952 'params': {
4953 'skip_download': True,
4954 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4955 },
4956 }]
4957
4958 @classmethod
4959 def suitable(cls, url):
4960 return False if YoutubeIE.suitable(url) else super(
4961 YoutubeTabIE, cls).suitable(url)
9297939e 4962
cd7c66cf 4963 def _real_extract(self, url):
9297939e 4964 url, smuggled_data = unsmuggle_url(url, {})
4965 if self.is_music_url(url):
4966 smuggled_data['is_music_url'] = True
fe03a6cd 4967 info_dict = self.__real_extract(url, smuggled_data)
9297939e 4968 if info_dict.get('entries'):
4969 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4970 return info_dict
4971
64f36541 4972 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 4973
4974 def __real_extract(self, url, smuggled_data):
cd7c66cf 4975 item_id = self._match_id(url)
4976 url = compat_urlparse.urlunparse(
4977 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 4978 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 4979
fe03a6cd 4980 def get_mobj(url):
37e57a9f 4981 mobj = self._URL_RE.match(url).groupdict()
07cce701 4982 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 4983 return mobj
4984
37e57a9f 4985 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 4986 # Youtube returns incomplete data if tabname is not lower case
4987 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 4988 if is_channel:
4989 if smuggled_data.get('is_music_url'):
37e57a9f 4990 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 4991 item_id = item_id[2:]
37e57a9f 4992 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
4993 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 4994 mdata = self._extract_tab_endpoint(
37e57a9f 4995 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
4996 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
4997 get_all=False, expected_type=compat_str)
ac56cf38 4998 if not murl:
37e57a9f 4999 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5000 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5001 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5002 pre = f'https://www.youtube.com/channel/{item_id}'
5003
64f36541 5004 original_tab_name = tab
fe03a6cd 5005 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5006 # Home URLs should redirect to /videos/
37e57a9f 5007 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5008 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5009 tab = '/videos'
5010
5011 url = ''.join((pre, tab, post))
5012 mobj = get_mobj(url)
cd7c66cf 5013
5014 # Handle both video/playlist URLs
201c1459 5015 qs = parse_qs(url)
37e57a9f 5016 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5017
fe03a6cd 5018 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5019 if not playlist_id:
fe03a6cd 5020 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5021 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5022 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5023 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5024 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5025 mobj = get_mobj(url)
cd7c66cf 5026
5027 if video_id and playlist_id:
a06916d9 5028 if self.get_param('noplaylist'):
37e57a9f 5029 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5030 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5031 ie=YoutubeIE.ie_key(), video_id=video_id)
5032 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5033
ac56cf38 5034 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5035
37e57a9f 5036 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5037 if tabs:
5038 selected_tab = self._extract_selected_tab(tabs)
64f36541 5039 selected_tab_name = selected_tab.get('title', '').lower()
5040 if selected_tab_name == 'home':
5041 selected_tab_name = 'featured'
5042 requested_tab_name = mobj['tab'][1:]
09f1580e 5043 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5044 if requested_tab_name == 'live':
09f1580e 5045 # Live tab should have redirected to the video
5046 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5047 if requested_tab_name not in ('', selected_tab_name):
5048 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5049 if not original_tab_name:
5050 if item_id[:2] == 'UC':
5051 # Topic channels don't have /videos. Use the equivalent playlist instead
5052 pl_id = f'UU{item_id[2:]}'
5053 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5054 try:
5055 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5056 except ExtractorError:
5057 redirect_warning += ' and the playlist redirect gave error'
5058 else:
5059 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5060 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5061 if selected_tab_name and selected_tab_name != requested_tab_name:
5062 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5063 else:
5064 raise ExtractorError(redirect_warning, expected=True)
18db7548 5065
37e57a9f 5066 if redirect_warning:
64f36541 5067 self.to_screen(redirect_warning)
37e57a9f 5068 self.write_debug(f'Final URL: {url}')
18db7548 5069
358de58c 5070 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5071 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5072 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5073 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5074 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5075 if tabs:
ac56cf38 5076 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5077
37e57a9f 5078 playlist = traverse_obj(
5079 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5080 if playlist:
ac56cf38 5081 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5082
37e57a9f 5083 video_id = traverse_obj(
5084 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5085 if video_id:
09f1580e 5086 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5087 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5088 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5089 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5090
8bdd16b4 5091 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5092
c5e8d7af 5093
8bdd16b4 5094class YoutubePlaylistIE(InfoExtractor):
96565c7e 5095 IE_DESC = 'YouTube playlists'
8bdd16b4 5096 _VALID_URL = r'''(?x)(?:
5097 (?:https?://)?
5098 (?:\w+\.)?
5099 (?:
5100 (?:
5101 youtube(?:kids)?\.com|
d9190e44 5102 %(invidious)s
8bdd16b4 5103 )
5104 /.*?\?.*?\blist=
5105 )?
5106 (?P<id>%(playlist_id)s)
d9190e44
RH
5107 )''' % {
5108 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5109 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5110 }
8bdd16b4 5111 IE_NAME = 'youtube:playlist'
cdc628a4 5112 _TESTS = [{
8bdd16b4 5113 'note': 'issue #673',
5114 'url': 'PLBB231211A4F62143',
cdc628a4 5115 'info_dict': {
8bdd16b4 5116 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5117 'id': 'PLBB231211A4F62143',
976ae3ea 5118 'uploader': 'Wickman',
8bdd16b4 5119 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5120 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5121 'view_count': int,
5122 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5123 'modified_date': r're:\d{8}',
5124 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5125 'channel': 'Wickman',
5126 'tags': [],
5127 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5128 },
5129 'playlist_mincount': 29,
5130 }, {
5131 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5132 'info_dict': {
5133 'title': 'YDL_safe_search',
5134 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5135 },
5136 'playlist_count': 2,
5137 'skip': 'This playlist is private',
9558dcec 5138 }, {
8bdd16b4 5139 'note': 'embedded',
5140 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5141 'playlist_count': 4,
9558dcec 5142 'info_dict': {
8bdd16b4 5143 'title': 'JODA15',
5144 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5145 'uploader': 'milan',
5146 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5147 'description': '',
5148 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5149 'tags': [],
5150 'modified_date': '20140919',
5151 'view_count': int,
5152 'channel': 'milan',
5153 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5154 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5155 },
5156 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5157 }, {
8bdd16b4 5158 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5159 'playlist_mincount': 654,
8bdd16b4 5160 'info_dict': {
5161 'title': '2018 Chinese New Singles (11/6 updated)',
5162 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5163 'uploader': 'LBK',
5164 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5165 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5166 'channel': 'LBK',
5167 'view_count': int,
5168 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5169 'tags': [],
5170 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5171 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5172 'modified_date': r're:\d{8}',
5173 },
5174 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5175 }, {
29f7c58a 5176 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5177 'only_matching': True,
5178 }, {
5179 # music album playlist
5180 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5181 'only_matching': True,
5182 }]
5183
5184 @classmethod
5185 def suitable(cls, url):
201c1459 5186 if YoutubeTabIE.suitable(url):
5187 return False
49a57e70 5188 from ..utils import parse_qs
201c1459 5189 qs = parse_qs(url)
5190 if qs.get('v', [None])[0]:
5191 return False
5192 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5193
5194 def _real_extract(self, url):
5195 playlist_id = self._match_id(url)
46953e7e 5196 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5197 url = update_url_query(
5198 'https://www.youtube.com/playlist',
5199 parse_qs(url) or {'list': playlist_id})
5200 if is_music_url:
5201 url = smuggle_url(url, {'is_music_url': True})
5202 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5203
5204
5205class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5206 IE_DESC = 'youtu.be'
29f7c58a 5207 _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}
5208 _TESTS = [{
8bdd16b4 5209 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5210 'info_dict': {
5211 'id': 'yeWKywCrFtk',
5212 'ext': 'mp4',
5213 'title': 'Small Scale Baler and Braiding Rugs',
5214 'uploader': 'Backus-Page House Museum',
5215 'uploader_id': 'backuspagemuseum',
5216 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5217 'upload_date': '20161008',
5218 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5219 'categories': ['Nonprofits & Activism'],
5220 'tags': list,
5221 'like_count': int,
976ae3ea 5222 'age_limit': 0,
5223 'playable_in_embed': True,
5224 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5225 'channel': 'Backus-Page House Museum',
5226 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5227 'live_status': 'not_live',
5228 'view_count': int,
5229 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5230 'availability': 'public',
5231 'duration': 59,
8bdd16b4 5232 },
5233 'params': {
5234 'noplaylist': True,
5235 'skip_download': True,
5236 },
39e7107d 5237 }, {
8bdd16b4 5238 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5239 'only_matching': True,
cdc628a4
PH
5240 }]
5241
8bdd16b4 5242 def _real_extract(self, url):
5ad28e7f 5243 mobj = self._match_valid_url(url)
29f7c58a 5244 video_id = mobj.group('id')
5245 playlist_id = mobj.group('playlist_id')
8bdd16b4 5246 return self.url_result(
29f7c58a 5247 update_url_query('https://www.youtube.com/watch', {
5248 'v': video_id,
5249 'list': playlist_id,
5250 'feature': 'youtu.be',
5251 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5252
5253
b6ce9bb0 5254class YoutubeLivestreamEmbedIE(InfoExtractor):
5255 IE_DESC = 'YouTube livestream embeds'
5256 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5257 _TESTS = [{
5258 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5259 'only_matching': True,
5260 }]
5261
5262 def _real_extract(self, url):
5263 channel_id = self._match_id(url)
5264 return self.url_result(
5265 f'https://www.youtube.com/channel/{channel_id}/live',
5266 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5267
5268
8bdd16b4 5269class YoutubeYtUserIE(InfoExtractor):
96565c7e 5270 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5271 IE_NAME = 'youtube:user'
8bdd16b4 5272 _VALID_URL = r'ytuser:(?P<id>.+)'
5273 _TESTS = [{
5274 'url': 'ytuser:phihag',
5275 'only_matching': True,
5276 }]
5277
5278 def _real_extract(self, url):
5279 user_id = self._match_id(url)
5280 return self.url_result(
c586f9e8 5281 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5282 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5283
b05654f0 5284
3d3dddc9 5285class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5286 IE_NAME = 'youtube:favorites'
96565c7e 5287 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5288 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5289 _LOGIN_REQUIRED = True
5290 _TESTS = [{
5291 'url': ':ytfav',
5292 'only_matching': True,
5293 }, {
5294 'url': ':ytfavorites',
5295 'only_matching': True,
5296 }]
5297
5298 def _real_extract(self, url):
5299 return self.url_result(
5300 'https://www.youtube.com/playlist?list=LL',
5301 ie=YoutubeTabIE.ie_key())
5302
5303
a6213a49 5304class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5305 IE_DESC = 'YouTube search'
78caa52a 5306 IE_NAME = 'youtube:search'
b05654f0 5307 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5308 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
9dd8e46a 5309 _TESTS = []
b05654f0 5310
a61fd4cf 5311
5f7cb91a 5312class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5313 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5314 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5315 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5316 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
75dff0ee 5317
c9ae7b95 5318
a6213a49 5319class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5320 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5321 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5322 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
3462ffa8 5323 _TESTS = [{
5324 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5325 'playlist_mincount': 5,
5326 'info_dict': {
11f9be09 5327 'id': 'youtube-dl test video',
3462ffa8 5328 'title': 'youtube-dl test video',
5329 }
a61fd4cf 5330 }, {
5331 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5332 'playlist_mincount': 5,
5333 'info_dict': {
5334 'id': 'python',
5335 'title': 'python',
5336 }
5337
3462ffa8 5338 }, {
5339 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5340 'only_matching': True,
5341 }]
5342
5343 def _real_extract(self, url):
4dfbf869 5344 qs = parse_qs(url)
386e1dd9 5345 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5346 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5347
5348
16aa9ea4 5349class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5350 IE_DESC = 'YouTube music search URLs with sorting and filter support'
5351 IE_NAME = 'youtube:music:search_url'
5352 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5353 _TESTS = [{
5354 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5355 'playlist_count': 16,
5356 'info_dict': {
5357 'id': 'royalty free music',
5358 'title': 'royalty free music',
5359 }
5360 }, {
5361 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5362 'playlist_mincount': 30,
5363 'info_dict': {
5364 'id': 'royalty free music - songs',
5365 'title': 'royalty free music - songs',
5366 },
5367 'params': {'extract_flat': 'in_playlist'}
5368 }, {
5369 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5370 'playlist_mincount': 30,
5371 'info_dict': {
5372 'id': 'royalty free music - community playlists',
5373 'title': 'royalty free music - community playlists',
5374 },
5375 'params': {'extract_flat': 'in_playlist'}
5376 }]
5377
5378 _SECTIONS = {
5379 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5380 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5381 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5382 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5383 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5384 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5385 }
5386
5387 def _real_extract(self, url):
5388 qs = parse_qs(url)
5389 query = (qs.get('search_query') or qs.get('q'))[0]
5390 params = qs.get('sp', (None,))[0]
5391 if params:
5392 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5393 else:
5394 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5395 params = self._SECTIONS.get(section)
5396 if not params:
5397 section = None
5398 title = join_nonempty(query, section, delim=' - ')
5399 return self.playlist_result(self._search_results(query, params, client='web_music'), title, title)
5400
5401
3462ffa8 5402class YoutubeFeedsInfoExtractor(YoutubeTabIE):
d7ae0639 5403 """
25f14e9f 5404 Base class for feed extractors
3d3dddc9 5405 Subclasses must define the _FEED_NAME property.
d7ae0639 5406 """
b2e8bc1b 5407 _LOGIN_REQUIRED = True
ef2f3c7f 5408 _TESTS = []
d7ae0639
JMF
5409
5410 @property
5411 def IE_NAME(self):
78caa52a 5412 return 'youtube:%s' % self._FEED_NAME
04cc9617 5413
3853309f 5414 def _real_extract(self, url):
3d3dddc9 5415 return self.url_result(
5416 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
5417 ie=YoutubeTabIE.ie_key())
25f14e9f
S
5418
5419
ef2f3c7f 5420class YoutubeWatchLaterIE(InfoExtractor):
5421 IE_NAME = 'youtube:watchlater'
96565c7e 5422 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5423 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5424 _TESTS = [{
8bdd16b4 5425 'url': ':ytwatchlater',
bc7a9cd8
S
5426 'only_matching': True,
5427 }]
25f14e9f
S
5428
5429 def _real_extract(self, url):
ef2f3c7f 5430 return self.url_result(
5431 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5432
5433
25f14e9f 5434class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5435 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5436 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5437 _FEED_NAME = 'recommended'
45db527f 5438 _LOGIN_REQUIRED = False
3d3dddc9 5439 _TESTS = [{
5440 'url': ':ytrec',
5441 'only_matching': True,
5442 }, {
5443 'url': ':ytrecommended',
5444 'only_matching': True,
5445 }, {
5446 'url': 'https://youtube.com',
5447 'only_matching': True,
5448 }]
1ed5b5c9 5449
1ed5b5c9 5450
25f14e9f 5451class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5452 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5453 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5454 _FEED_NAME = 'subscriptions'
3d3dddc9 5455 _TESTS = [{
5456 'url': ':ytsubs',
5457 'only_matching': True,
5458 }, {
5459 'url': ':ytsubscriptions',
5460 'only_matching': True,
5461 }]
1ed5b5c9 5462
1ed5b5c9 5463
25f14e9f 5464class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5465 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5466 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5467 _FEED_NAME = 'history'
3d3dddc9 5468 _TESTS = [{
5469 'url': ':ythistory',
5470 'only_matching': True,
5471 }]
1ed5b5c9
JMF
5472
5473
15870e90
PH
5474class YoutubeTruncatedURLIE(InfoExtractor):
5475 IE_NAME = 'youtube:truncated_url'
5476 IE_DESC = False # Do not list
975d35db 5477 _VALID_URL = r'''(?x)
b95aab84
PH
5478 (?:https?://)?
5479 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5480 (?:watch\?(?:
c4808c60 5481 feature=[a-z_]+|
b95aab84
PH
5482 annotation_id=annotation_[^&]+|
5483 x-yt-cl=[0-9]+|
c1708b89 5484 hl=[^&]*|
287be8c6 5485 t=[0-9]+
b95aab84
PH
5486 )?
5487 |
5488 attribution_link\?a=[^&]+
5489 )
5490 $
975d35db 5491 '''
15870e90 5492
c4808c60 5493 _TESTS = [{
2d3d2997 5494 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5495 'only_matching': True,
dc2fc736 5496 }, {
2d3d2997 5497 'url': 'https://www.youtube.com/watch?',
dc2fc736 5498 'only_matching': True,
b95aab84
PH
5499 }, {
5500 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5501 'only_matching': True,
5502 }, {
5503 'url': 'https://www.youtube.com/watch?feature=foo',
5504 'only_matching': True,
c1708b89
PH
5505 }, {
5506 'url': 'https://www.youtube.com/watch?hl=en-GB',
5507 'only_matching': True,
287be8c6
PH
5508 }, {
5509 'url': 'https://www.youtube.com/watch?t=2372',
5510 'only_matching': True,
c4808c60
PH
5511 }]
5512
15870e90
PH
5513 def _real_extract(self, url):
5514 raise ExtractorError(
78caa52a
PH
5515 'Did you forget to quote the URL? Remember that & is a meta '
5516 'character in most shells, so you want to put the URL in quotes, '
3867038a 5517 'like youtube-dl '
2d3d2997 5518 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5519 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5520 expected=True)
772fd5cc
PH
5521
5522
3cd786db 5523class YoutubeClipIE(InfoExtractor):
5524 IE_NAME = 'youtube:clip'
5525 IE_DESC = False # Do not list
5526 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5527
5528 def _real_extract(self, url):
5529 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5530 return self.url_result(url, 'Generic')
5531
5532
772fd5cc
PH
5533class YoutubeTruncatedIDIE(InfoExtractor):
5534 IE_NAME = 'youtube:truncated_id'
5535 IE_DESC = False # Do not list
b95aab84 5536 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5537
5538 _TESTS = [{
5539 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5540 'only_matching': True,
5541 }]
5542
5543 def _real_extract(self, url):
5544 video_id = self._match_id(url)
5545 raise ExtractorError(
5546 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5547 expected=True)