]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
Handle float in `--wait-for-video`
[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,
ff91cf74 42 get_first,
dd27fd17 43 int_or_none,
641ad5d8 44 is_html,
34921b43 45 join_nonempty,
48416bc4 46 js_to_json,
94278f72 47 mimetype2ext,
9c0d7f49 48 network_exceptions,
a6213a49 49 NO_DEFAULT,
11f9be09 50 orderedSet,
6310acf5 51 parse_codecs,
49bd8c66 52 parse_count,
7c80519c 53 parse_duration,
7ea65411 54 parse_iso8601,
4dfbf869 55 parse_qs,
dca3ff4a 56 qualities,
c0ac49bc 57 remove_end,
3995d37d 58 remove_start,
cf7e015f 59 smuggle_url,
dbdaaa23 60 str_or_none,
c93d53f5 61 str_to_int,
f3aa3c3f 62 strftime_or_none,
7c365c21 63 traverse_obj,
556dbe7f 64 try_get,
c5e8d7af
PH
65 unescapeHTML,
66 unified_strdate,
f0d785d3 67 unified_timestamp,
cf7e015f 68 unsmuggle_url,
8bdd16b4 69 update_url_query,
21c340b8 70 url_or_none,
fe93e2c4 71 urljoin,
7c365c21 72 variadic,
c5e8d7af
PH
73)
74
5f6a1245 75
000c15a4 76# any clients starting with _ cannot be explicity requested by the user
77INNERTUBE_CLIENTS = {
78 'web': {
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
81 'client': {
82 'clientName': 'WEB',
18c7683d 83 'clientVersion': '2.20211221.00.00',
000c15a4 84 }
85 },
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
87 },
88 'web_embedded': {
89 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 93 'clientVersion': '1.20211215.00.01',
000c15a4 94 },
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
97 },
98 'web_music': {
99 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
100 'INNERTUBE_HOST': 'music.youtube.com',
101 'INNERTUBE_CONTEXT': {
102 'client': {
103 'clientName': 'WEB_REMIX',
18c7683d 104 'clientVersion': '1.20211213.00.00',
000c15a4 105 }
106 },
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
108 },
e7e94f2a 109 'web_creator': {
18c7683d 110 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
111 'INNERTUBE_CONTEXT': {
112 'client': {
113 'clientName': 'WEB_CREATOR',
18c7683d 114 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
115 }
116 },
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
118 },
000c15a4 119 'android': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID',
18c7683d 124 'clientVersion': '16.49',
000c15a4 125 }
126 },
127 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 128 'REQUIRE_JS_PLAYER': False
000c15a4 129 },
130 'android_embedded': {
18c7683d 131 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 132 'INNERTUBE_CONTEXT': {
133 'client': {
134 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 135 'clientVersion': '16.49',
000c15a4 136 },
137 },
b6de707d 138 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
139 'REQUIRE_JS_PLAYER': False
000c15a4 140 },
141 'android_music': {
18c7683d 142 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_MUSIC',
18c7683d 146 'clientVersion': '4.57',
000c15a4 147 }
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 150 'REQUIRE_JS_PLAYER': False
000c15a4 151 },
e7e94f2a 152 'android_creator': {
18c7683d 153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
154 'INNERTUBE_CONTEXT': {
155 'client': {
156 'clientName': 'ANDROID_CREATOR',
18c7683d 157 'clientVersion': '21.47',
e7e94f2a
D
158 },
159 },
b6de707d 160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
e7e94f2a 162 },
18c7683d 163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 165 'ios': {
18c7683d 166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS',
18c7683d 170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
000c15a4 172 }
173 },
b6de707d 174 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
175 'REQUIRE_JS_PLAYER': False
000c15a4 176 },
177 'ios_embedded': {
000c15a4 178 'INNERTUBE_CONTEXT': {
179 'client': {
180 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 181 'clientVersion': '16.46',
182 'deviceModel': 'iPhone14,3',
000c15a4 183 },
184 },
b6de707d 185 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
186 'REQUIRE_JS_PLAYER': False
000c15a4 187 },
188 'ios_music': {
18c7683d 189 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 190 'INNERTUBE_CONTEXT': {
191 'client': {
192 'clientName': 'IOS_MUSIC',
18c7683d 193 'clientVersion': '4.57',
000c15a4 194 },
195 },
b6de707d 196 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
197 'REQUIRE_JS_PLAYER': False
000c15a4 198 },
e7e94f2a
D
199 'ios_creator': {
200 'INNERTUBE_CONTEXT': {
201 'client': {
202 'clientName': 'IOS_CREATOR',
18c7683d 203 'clientVersion': '21.47',
e7e94f2a
D
204 },
205 },
b6de707d 206 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
207 'REQUIRE_JS_PLAYER': False
e7e94f2a 208 },
3619f78d 209 # mweb has 'ultralow' formats
210 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 211 'mweb': {
18c7683d 212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 213 'INNERTUBE_CONTEXT': {
214 'client': {
215 'clientName': 'MWEB',
18c7683d 216 'clientVersion': '2.20211221.01.00',
000c15a4 217 }
218 },
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
18c7683d 220 }
000c15a4 221}
222
223
224def build_innertube_clients():
2e4cacd0 225 THIRD_PARTY = {
65c2fde2 226 'embedUrl': 'https://google.com', # Can be any valid URL
227 }
2e4cacd0 228 BASE_CLIENTS = ('android', 'web', 'ios', 'mweb')
229 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 230
231 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 232 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 233 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 234 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 235 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 236
2e4cacd0 237 base_client, *variant = client.split('_')
238 ytcfg['priority'] = 10 * priority(base_client)
239
e48b3875 240 if not variant:
241 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
000c15a4 242 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
e48b3875 243 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 244 agegate_ytcfg['priority'] -= 1
e48b3875 245 elif variant == ['embedded']:
246 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 247 ytcfg['priority'] -= 2
e48b3875 248 else:
000c15a4 249 ytcfg['priority'] -= 3
250
251
252build_innertube_clients()
253
254
de7f3446 255class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 256 """Provide base functions for Youtube extractors"""
e00eb564 257
3462ffa8 258 _RESERVED_NAMES = (
3cd786db 259 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 260 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 261 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 262 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 263
3619f78d 264 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
265
b2e8bc1b 266 _NETRC_MACHINE = 'youtube'
3619f78d 267
b2e8bc1b
JMF
268 # If True it will raise an error if no login info is provided
269 _LOGIN_REQUIRED = False
270
d9190e44
RH
271 _INVIDIOUS_SITES = (
272 # invidious-redirect websites
273 r'(?:www\.)?redirect\.invidious\.io',
274 r'(?:(?:www|dev)\.)?invidio\.us',
275 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
276 r'(?:www\.)?invidious\.pussthecat\.org',
277 r'(?:www\.)?invidious\.zee\.li',
278 r'(?:www\.)?invidious\.ethibox\.fr',
279 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
280 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
281 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
282 # youtube-dl invidious instances list
283 r'(?:(?:www|no)\.)?invidiou\.sh',
284 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
285 r'(?:www\.)?invidious\.kabi\.tk',
286 r'(?:www\.)?invidious\.mastodon\.host',
287 r'(?:www\.)?invidious\.zapashcanon\.fr',
288 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
289 r'(?:www\.)?invidious\.tinfoil-hat\.net',
290 r'(?:www\.)?invidious\.himiko\.cloud',
291 r'(?:www\.)?invidious\.reallyancient\.tech',
292 r'(?:www\.)?invidious\.tube',
293 r'(?:www\.)?invidiou\.site',
294 r'(?:www\.)?invidious\.site',
295 r'(?:www\.)?invidious\.xyz',
296 r'(?:www\.)?invidious\.nixnet\.xyz',
297 r'(?:www\.)?invidious\.048596\.xyz',
298 r'(?:www\.)?invidious\.drycat\.fr',
299 r'(?:www\.)?inv\.skyn3t\.in',
300 r'(?:www\.)?tube\.poal\.co',
301 r'(?:www\.)?tube\.connect\.cafe',
302 r'(?:www\.)?vid\.wxzm\.sx',
303 r'(?:www\.)?vid\.mint\.lgbt',
304 r'(?:www\.)?vid\.puffyan\.us',
305 r'(?:www\.)?yewtu\.be',
306 r'(?:www\.)?yt\.elukerio\.org',
307 r'(?:www\.)?yt\.lelux\.fi',
308 r'(?:www\.)?invidious\.ggc-project\.de',
309 r'(?:www\.)?yt\.maisputain\.ovh',
310 r'(?:www\.)?ytprivate\.com',
311 r'(?:www\.)?invidious\.13ad\.de',
312 r'(?:www\.)?invidious\.toot\.koeln',
313 r'(?:www\.)?invidious\.fdn\.fr',
314 r'(?:www\.)?watch\.nettohikari\.com',
315 r'(?:www\.)?invidious\.namazso\.eu',
316 r'(?:www\.)?invidious\.silkky\.cloud',
317 r'(?:www\.)?invidious\.exonip\.de',
318 r'(?:www\.)?invidious\.riverside\.rocks',
319 r'(?:www\.)?invidious\.blamefran\.net',
320 r'(?:www\.)?invidious\.moomoo\.de',
321 r'(?:www\.)?ytb\.trom\.tf',
322 r'(?:www\.)?yt\.cyberhost\.uk',
323 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
324 r'(?:www\.)?qklhadlycap4cnod\.onion',
325 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
326 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
327 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
328 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
329 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
330 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
331 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
332 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
333 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
334 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
335 )
336
b2e8bc1b 337 def _login(self):
83317f69 338 """
339 Attempt to log in to YouTube.
83317f69 340 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
341 """
9d5d4d64 342
982ee69a
MB
343 if (self._LOGIN_REQUIRED
344 and self.get_param('cookiefile') is None
345 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 346 self.raise_login_required(
347 'Login details are needed to download this content', method='cookies')
68217024 348 username, password = self._get_login_info()
9d5d4d64 349 if username:
24b0a72b 350 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
b2e8bc1b 351
cce889b9 352 def _initialize_consent(self):
353 cookies = self._get_cookies('https://www.youtube.com/')
354 if cookies.get('__Secure-3PSID'):
355 return
356 consent_id = None
357 consent = cookies.get('CONSENT')
358 if consent:
359 if 'YES' in consent.value:
360 return
361 consent_id = self._search_regex(
362 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
363 if not consent_id:
364 consent_id = random.randint(100, 999)
365 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 366
f3aa3c3f 367 def _initialize_pref(self):
368 cookies = self._get_cookies('https://www.youtube.com/')
369 pref_cookie = cookies.get('PREF')
370 pref = {}
371 if pref_cookie:
372 try:
373 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
374 except ValueError:
375 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 376 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 377 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
378
b2e8bc1b 379 def _real_initialize(self):
f3aa3c3f 380 self._initialize_pref()
cce889b9 381 self._initialize_consent()
24b0a72b 382 self._login()
c5e8d7af 383
a0566bbf 384 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 385 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 387
000c15a4 388 def _get_default_ytcfg(self, client='web'):
389 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 390
000c15a4 391 def _get_innertube_host(self, client='web'):
392 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 393
000c15a4 394 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 395 # try_get but with fallback to default ytcfg client values when present
396 _func = lambda y: try_get(y, getter, expected_type)
397 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
398
000c15a4 399 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 400 return self._ytcfg_get_safe(
401 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
402 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 403
000c15a4 404 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 405 return self._ytcfg_get_safe(
406 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
407 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 408
000c15a4 409 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 410 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
411
000c15a4 412 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 413 context = get_first(
414 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 415 # Enforce language and tz for extraction
416 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
417 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 418 return context
419
cf87314d 420 _SAPISID = None
421
109dd3b2 422 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 423 time_now = round(time.time())
cf87314d 424 if self._SAPISID is None:
425 yt_cookies = self._get_cookies('https://www.youtube.com')
426 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
427 # See: https://github.com/yt-dlp/yt-dlp/issues/393
428 sapisid_cookie = dict_get(
429 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
430 if sapisid_cookie and sapisid_cookie.value:
431 self._SAPISID = sapisid_cookie.value
432 self.write_debug('Extracted SAPISID cookie')
433 # SAPISID cookie is required if not already present
434 if not yt_cookies.get('SAPISID'):
435 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
436 self._set_cookie(
437 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
438 else:
439 self._SAPISID = False
440 if not self._SAPISID:
441 return None
1974e99f 442 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
443 sapisidhash = hashlib.sha1(
cf87314d 444 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 445 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
446
447 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 448 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 449 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 450
109dd3b2 451 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 452 data.update(query)
11f9be09 453 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 454 real_headers.update({'content-type': 'application/json'})
455 if headers:
456 real_headers.update(headers)
545cc85d 457 return self._download_json(
109dd3b2 458 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 459 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 460 data=json.dumps(data).encode('utf8'), headers=real_headers,
5dbc77df 461 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
f4f751af 462
ac56cf38 463 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
464 data = self._search_regex(
465 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
466 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
467 if data:
468 return self._parse_json(data, item_id, fatal=fatal)
0c148415 469
99e9e001 470 @staticmethod
471 def _extract_session_index(*data):
472 """
473 Index of current account in account list.
474 See: https://github.com/yt-dlp/yt-dlp/pull/519
475 """
476 for ytcfg in data:
477 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
478 if session_index is not None:
479 return session_index
480
481 # Deprecated?
482 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
483 if ytcfg:
484 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
485 if token:
486 return token
99e9e001 487 if webpage:
488 return self._search_regex(
489 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
490 'identity token', default=None, fatal=False)
a1c5d2ca
M
491
492 @staticmethod
fe93e2c4 493 def _extract_account_syncid(*args):
8ea3f7b9 494 """
495 Extract syncId required to download private playlists of secondary channels
fe93e2c4 496 @params response and/or ytcfg
8ea3f7b9 497 """
fe93e2c4 498 for data in args:
499 # ytcfg includes channel_syncid if on secondary channel
500 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
501 if delegated_sid:
502 return delegated_sid
503 sync_ids = (try_get(
504 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 505 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 506 if len(sync_ids) >= 2 and sync_ids[1]:
507 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
508 # and just "user_syncid||" for primary channel. We only want the channel_syncid
509 return sync_ids[0]
a1c5d2ca 510
ac56cf38 511 @staticmethod
512 def _extract_visitor_data(*args):
513 """
514 Extracts visitorData from an API response or ytcfg
515 Appears to be used to track session state
516 """
9222c381 517 return get_first(
6c73052c 518 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 519 expected_type=str)
ac56cf38 520
99e9e001 521 @property
522 def is_authenticated(self):
523 return bool(self._generate_sapisidhash_header())
524
11f9be09 525 def extract_ytcfg(self, video_id, webpage):
8c54a305 526 if not webpage:
527 return {}
29f7c58a 528 return self._parse_json(
529 self._search_regex(
530 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 531 default='{}'), video_id, fatal=False) or {}
532
11f9be09 533 def generate_api_headers(
99e9e001 534 self, *, ytcfg=None, account_syncid=None, session_index=None,
535 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
536
11f9be09 537 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 538 headers = {
109dd3b2 539 'X-YouTube-Client-Name': compat_str(
11f9be09 540 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
541 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 542 'Origin': origin,
543 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
544 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 545 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 546 }
547 if session_index is None:
314ee305 548 session_index = self._extract_session_index(ytcfg)
549 if account_syncid or session_index is not None:
550 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 551
109dd3b2 552 auth = self._generate_sapisidhash_header(origin)
f4f751af 553 if auth is not None:
554 headers['Authorization'] = auth
109dd3b2 555 headers['X-Origin'] = origin
99e9e001 556 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 557
2d6659b9 558 @staticmethod
559 def _build_api_continuation_query(continuation, ctp=None):
560 query = {
561 'continuation': continuation
562 }
563 # TODO: Inconsistency with clickTrackingParams.
564 # Currently we have a fixed ctp contained within context (from ytcfg)
565 # and a ctp in root query for continuation.
566 if ctp:
567 query['clickTracking'] = {'clickTrackingParams': ctp}
568 return query
569
2d6659b9 570 @classmethod
571 def _extract_next_continuation_data(cls, renderer):
572 next_continuation = try_get(
573 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
574 lambda x: x['continuation']['reloadContinuationData']), dict)
575 if not next_continuation:
576 return
577 continuation = next_continuation.get('continuation')
578 if not continuation:
579 return
580 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 581 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 582
583 @classmethod
584 def _extract_continuation_ep_data(cls, continuation_ep: dict):
585 if isinstance(continuation_ep, dict):
586 continuation = try_get(
587 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
588 if not continuation:
589 return
590 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 591 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 592
593 @classmethod
594 def _extract_continuation(cls, renderer):
595 next_continuation = cls._extract_next_continuation_data(renderer)
596 if next_continuation:
597 return next_continuation
fe93e2c4 598
2d6659b9 599 contents = []
600 for key in ('contents', 'items'):
601 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 602
2d6659b9 603 for content in contents:
604 if not isinstance(content, dict):
605 continue
606 continuation_ep = try_get(
607 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
608 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
609 dict)
610 continuation = cls._extract_continuation_ep_data(continuation_ep)
611 if continuation:
612 return continuation
613
fe93e2c4 614 @classmethod
615 def _extract_alerts(cls, data):
109dd3b2 616 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
617 if not isinstance(alert_dict, dict):
618 continue
619 for alert in alert_dict.values():
620 alert_type = alert.get('type')
621 if not alert_type:
622 continue
052e1350 623 message = cls._get_text(alert, 'text')
109dd3b2 624 if message:
625 yield alert_type, message
626
c0ac49bc 627 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 628 errors = []
629 warnings = []
630 for alert_type, alert_message in alerts:
641ad5d8 631 if alert_type.lower() == 'error' and fatal:
109dd3b2 632 errors.append([alert_type, alert_message])
633 else:
634 warnings.append([alert_type, alert_message])
635
636 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 637 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 638 if errors:
639 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
640
641 def _extract_and_report_alerts(self, data, *args, **kwargs):
642 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
643
47193e02 644 def _extract_badges(self, renderer: dict):
645 badges = set()
646 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
647 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
648 if label:
649 badges.add(label.lower())
650 return badges
651
652 @staticmethod
052e1350 653 def _get_text(data, *path_list, max_runs=None):
654 for path in path_list or [None]:
655 if path is None:
656 obj = [data]
657 else:
658 obj = traverse_obj(data, path, default=[])
659 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
660 obj = [obj]
661 for item in obj:
662 text = try_get(item, lambda x: x['simpleText'], compat_str)
663 if text:
664 return text
665 runs = try_get(item, lambda x: x['runs'], list) or []
666 if not runs and isinstance(item, list):
667 runs = item
668
669 runs = runs[:min(len(runs), max_runs or len(runs))]
670 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
671 if text:
672 return text
47193e02 673
f0d785d3 674 def _get_count(self, data, *path_list):
675 count_text = self._get_text(data, *path_list) or ''
676 count = parse_count(count_text)
677 if count is None:
678 count = str_to_int(
679 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
680 return count
681
a709d873 682 @staticmethod
683 def _extract_thumbnails(data, *path_list):
684 """
685 Extract thumbnails from thumbnails dict
686 @param path_list: path list to level that contains 'thumbnails' key
687 """
688 thumbnails = []
689 for path in path_list or [()]:
690 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
691 thumbnail_url = url_or_none(thumbnail.get('url'))
692 if not thumbnail_url:
693 continue
694 # Sometimes youtube gives a wrong thumbnail URL. See:
695 # https://github.com/yt-dlp/yt-dlp/issues/233
696 # https://github.com/ytdl-org/youtube-dl/issues/28023
697 if 'maxresdefault' in thumbnail_url:
698 thumbnail_url = thumbnail_url.split('?')[0]
699 thumbnails.append({
700 'url': thumbnail_url,
701 'height': int_or_none(thumbnail.get('height')),
702 'width': int_or_none(thumbnail.get('width')),
703 })
704 return thumbnails
705
f3aa3c3f 706 @staticmethod
707 def extract_relative_time(relative_time_text):
708 """
709 Extracts a relative time from string and converts to dt object
f0d785d3 710 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 711 """
f0d785d3 712 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 713 if mobj:
f0d785d3 714 start = mobj.group('start')
715 if start:
716 return datetime_from_str(start)
f3aa3c3f 717 try:
f0d785d3 718 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 719 except ValueError:
720 return None
721
722 def _extract_time_text(self, renderer, *path_list):
723 text = self._get_text(renderer, *path_list) or ''
724 dt = self.extract_relative_time(text)
725 timestamp = None
726 if isinstance(dt, datetime.datetime):
727 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 728
729 if timestamp is None:
730 timestamp = (
731 unified_timestamp(text) or unified_timestamp(
732 self._search_regex(
17322130 733 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 734 text.lower(), 'time text', default=None)))
f0d785d3 735
f3aa3c3f 736 if text and timestamp is None:
17322130 737 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 738 return timestamp, text
739
109dd3b2 740 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
741 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 742 default_client='web'):
109dd3b2 743 response = None
744 last_error = None
745 count = -1
746 retries = self.get_param('extractor_retries', 3)
747 if check_get_keys is None:
748 check_get_keys = []
749 while count < retries:
750 count += 1
751 if last_error:
c0ac49bc 752 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 753 try:
754 response = self._call_api(
755 ep=ep, fatal=True, headers=headers,
756 video_id=item_id, query=query,
757 context=self._extract_context(ytcfg, default_client),
758 api_key=self._extract_api_key(ytcfg, default_client),
759 api_hostname=api_hostname, default_client=default_client,
760 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
761 except ExtractorError as e:
9c0d7f49 762 if isinstance(e.cause, network_exceptions):
87e8e8a7 763 if isinstance(e.cause, compat_HTTPError):
764 first_bytes = e.cause.read(512)
765 if not is_html(first_bytes):
766 yt_error = try_get(
767 self._parse_json(
768 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
769 lambda x: x['error']['message'], compat_str)
770 if yt_error:
771 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 772 # Downloading page may result in intermittent 5xx HTTP error
773 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 774 # We also want to catch all other network exceptions since errors in later pages can be troublesome
775 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
776 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 777 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 778 if count < retries:
779 continue
109dd3b2 780 if fatal:
781 raise
782 else:
783 self.report_warning(error_to_compat_str(e))
784 return
785
786 else:
109dd3b2 787 try:
ac56cf38 788 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 789 except ExtractorError as e:
c0ac49bc 790 # YouTube servers may return errors we want to retry on in a 200 OK response
791 # See: https://github.com/yt-dlp/yt-dlp/issues/839
792 if 'unknown error' in e.msg.lower():
793 last_error = e.msg
794 continue
109dd3b2 795 if fatal:
796 raise
797 self.report_warning(error_to_compat_str(e))
798 return
799 if not check_get_keys or dict_get(response, check_get_keys):
800 break
801 # Youtube sometimes sends incomplete data
802 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
803 last_error = 'Incomplete data received'
804 if count >= retries:
805 if fatal:
806 raise ExtractorError(last_error)
807 else:
808 self.report_warning(last_error)
809 return
810 return response
811
9297939e 812 @staticmethod
813 def is_music_url(url):
814 return re.match(r'https?://music\.youtube\.com/', url) is not None
815
30a074c2 816 def _extract_video(self, renderer):
817 video_id = renderer.get('videoId')
052e1350 818 title = self._get_text(renderer, 'title')
819 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 820 duration = parse_duration(self._get_text(
821 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
f0d785d3 822 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 823
052e1350 824 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 825 channel_id = traverse_obj(
826 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
827 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
828 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
829 overlay_style = traverse_obj(
830 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
831 badges = self._extract_badges(renderer)
a709d873 832 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
833
30a074c2 834 return {
39ed931e 835 '_type': 'url',
30a074c2 836 'ie_key': YoutubeIE.ie_key(),
837 'id': video_id,
5e3f2f8f 838 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 839 'title': title,
840 'description': description,
841 'duration': duration,
842 'view_count': view_count,
843 'uploader': uploader,
f3aa3c3f 844 'channel_id': channel_id,
a709d873 845 'thumbnails': thumbnails,
a30a6ed3 846 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 847 'live_status': ('is_upcoming' if scheduled_timestamp is not None
848 else 'was_live' if 'streamed' in time_text.lower()
849 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
850 else None),
851 'release_timestamp': scheduled_timestamp,
852 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 853 }
854
0c148415 855
360e1ca5 856class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 857 IE_DESC = 'YouTube'
cb7dfeea 858 _VALID_URL = r"""(?x)^
c5e8d7af 859 (
edb53e2d 860 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 861 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
862 (?:www\.)?deturl\.com/www\.youtube\.com|
863 (?:www\.)?pwnyoutube\.com|
864 (?:www\.)?hooktube\.com|
865 (?:www\.)?yourepeat\.com|
866 tube\.majestyc\.net|
867 %(invidious)s|
868 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
869 (?:.*?\#/)? # handle anchor (#/) redirect urls
870 (?: # the various things that can precede the ID:
b6ce9bb0 871 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 872 |(?: # or the v= param in all its forms
f7000f3a 873 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 874 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 875 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
876 v=
877 )
f4b05232 878 ))
cbaed4bb
S
879 |(?:
880 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
881 vid\.plus| # or vid.plus/xxxx
882 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 883 %(invidious)s
cbaed4bb 884 )/
edb53e2d 885 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 886 )
c5e8d7af 887 )? # all until now is optional -> you can pass the naked ID
201c1459 888 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 889 (?(1).+)? # if we found the ID, everything can follow
9297939e 890 (?:\#|$)""" % {
d9190e44 891 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 892 }
e40c758c 893 _PLAYER_INFO_RE = (
cc2db878 894 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
895 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 896 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 897 )
2c62dc26 898 _formats = {
c2d3cb4c 899 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
900 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
901 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
902 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
903 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
904 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
905 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
906 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 907 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 908 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
909 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
910 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
911 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
912 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
913 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 914 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 915 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
916 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 917
918
919 # 3D videos
c2d3cb4c 920 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
921 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
922 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
923 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 924 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
925 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
926 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 927
96fb5605 928 # Apple HTTP Live Streaming
11f12195 929 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 930 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
931 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
932 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
933 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
934 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 935 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
936 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
937
938 # DASH mp4 video
d23028a8
S
939 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
940 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
942 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
943 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 944 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
945 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
946 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
947 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
948 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
949 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
950 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 951
f6f1fc92 952 # Dash mp4 audio
d23028a8
S
953 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
954 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
955 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
956 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
957 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
958 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
959 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
960
961 # Dash webm
d23028a8
S
962 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
963 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
967 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
968 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
969 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
970 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
975 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
976 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 977 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
978 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
979 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
980 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
981 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
982 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
983 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
984
985 # Dash webm audio
d23028a8
S
986 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
987 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 988
0857baad 989 # Dash webm audio with opus inside
d23028a8
S
990 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
991 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
992 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 993
ce6b9a2d
PH
994 # RTMP (unnamed)
995 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
996
997 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
998 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
999 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1000 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1001 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1002 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1003 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1004 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1005 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1006 }
29f7c58a 1007 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1008
fd5c4aab
S
1009 _GEO_BYPASS = False
1010
78caa52a 1011 IE_NAME = 'youtube'
2eb88d95
PH
1012 _TESTS = [
1013 {
2d3d2997 1014 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1015 'info_dict': {
1016 'id': 'BaW_jenozKc',
1017 'ext': 'mp4',
3867038a 1018 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1019 'uploader': 'Philipp Hagemeister',
1020 'uploader_id': 'phihag',
ec85ded8 1021 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1022 'channel': 'Philipp Hagemeister',
dd4c4492
S
1023 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1024 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1025 'upload_date': '20121002',
ff9f925b 1026 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1027 'categories': ['Science & Technology'],
3867038a 1028 'tags': ['youtube-dl'],
556dbe7f 1029 'duration': 10,
dbdaaa23 1030 'view_count': int,
3e7c1224 1031 'like_count': int,
ff9f925b 1032 'availability': 'public',
1033 'playable_in_embed': True,
1034 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1035 'live_status': 'not_live',
1036 'age_limit': 0,
7c80519c 1037 'start_time': 1,
297a564b 1038 'end_time': 9,
6c73052c 1039 'channel_follower_count': int
2eb88d95 1040 }
0e853ca4 1041 },
fccd3771 1042 {
4bc3a23e
PH
1043 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1044 'note': 'Embed-only video (#1746)',
1045 'info_dict': {
1046 'id': 'yZIXLfi8CZQ',
1047 'ext': 'mp4',
1048 'upload_date': '20120608',
1049 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1050 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1051 'uploader': 'SET India',
94bfcd23 1052 'uploader_id': 'setindia',
ec85ded8 1053 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1054 'age_limit': 18,
545cc85d 1055 },
1056 'skip': 'Private video',
fccd3771 1057 },
11b56058 1058 {
8bdd16b4 1059 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1060 'note': 'Use the first video ID in the URL',
1061 'info_dict': {
1062 'id': 'BaW_jenozKc',
1063 'ext': 'mp4',
3867038a 1064 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1065 'uploader': 'Philipp Hagemeister',
1066 'uploader_id': 'phihag',
ec85ded8 1067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1068 'channel': 'Philipp Hagemeister',
1069 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1070 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1071 'upload_date': '20121002',
976ae3ea 1072 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1073 'categories': ['Science & Technology'],
3867038a 1074 'tags': ['youtube-dl'],
556dbe7f 1075 'duration': 10,
dbdaaa23 1076 'view_count': int,
11b56058 1077 'like_count': int,
976ae3ea 1078 'availability': 'public',
1079 'playable_in_embed': True,
1080 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1081 'live_status': 'not_live',
1082 'age_limit': 0,
6c73052c 1083 'channel_follower_count': int
34a7de29
S
1084 },
1085 'params': {
1086 'skip_download': True,
1087 },
11b56058 1088 },
dd27fd17 1089 {
2d3d2997 1090 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1091 'note': '256k DASH audio (format 141) via DASH manifest',
1092 'info_dict': {
1093 'id': 'a9LDPn-MO4I',
1094 'ext': 'm4a',
1095 'upload_date': '20121002',
1096 'uploader_id': '8KVIDEO',
ec85ded8 1097 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1098 'description': '',
1099 'uploader': '8KVIDEO',
1100 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1101 },
4bc3a23e
PH
1102 'params': {
1103 'youtube_include_dash_manifest': True,
1104 'format': '141',
4919603f 1105 },
de3c7fe0 1106 'skip': 'format 141 not served anymore',
dd27fd17 1107 },
8bdd16b4 1108 # DASH manifest with encrypted signature
1109 {
1110 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1111 'info_dict': {
1112 'id': 'IB3lcPjvWLA',
1113 'ext': 'm4a',
1114 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1115 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1116 'duration': 244,
1117 'uploader': 'AfrojackVEVO',
1118 'uploader_id': 'AfrojackVEVO',
1119 'upload_date': '20131011',
cc2db878 1120 'abr': 129.495,
976ae3ea 1121 'like_count': int,
1122 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1123 'playable_in_embed': True,
1124 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1125 'view_count': int,
1126 'track': 'The Spark',
1127 'live_status': 'not_live',
1128 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1129 'channel': 'Afrojack',
1130 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1131 'tags': 'count:19',
1132 'availability': 'public',
1133 'categories': ['Music'],
1134 'age_limit': 0,
1135 'alt_title': 'The Spark',
6c73052c 1136 'channel_follower_count': int
8bdd16b4 1137 },
1138 'params': {
1139 'youtube_include_dash_manifest': True,
1140 'format': '141/bestaudio[ext=m4a]',
1141 },
1142 },
65c2fde2 1143 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1144 {
65c2fde2 1145 'note': 'Embed allowed age-gate video',
2d3d2997 1146 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1147 'info_dict': {
1148 'id': 'HtVdAasjOgU',
1149 'ext': 'mp4',
1150 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1151 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1152 'duration': 142,
c522adb1
JMF
1153 'uploader': 'The Witcher',
1154 'uploader_id': 'WitcherGame',
ec85ded8 1155 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1156 'upload_date': '20140605',
34952f09 1157 'age_limit': 18,
976ae3ea 1158 'categories': ['Gaming'],
1159 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1160 'availability': 'needs_auth',
1161 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1162 'like_count': int,
1163 'channel': 'The Witcher',
1164 'live_status': 'not_live',
1165 'tags': 'count:17',
1166 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1167 'playable_in_embed': True,
1168 'view_count': int,
6c73052c 1169 'channel_follower_count': int
c522adb1
JMF
1170 },
1171 },
65c2fde2 1172 {
1173 'note': 'Age-gate video with embed allowed in public site',
1174 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1175 'info_dict': {
1176 'id': 'HsUATh_Nc2U',
1177 'ext': 'mp4',
1178 'title': 'Godzilla 2 (Official Video)',
1179 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1180 'upload_date': '20200408',
1181 'uploader_id': 'FlyingKitty900',
1182 'uploader': 'FlyingKitty',
1183 'age_limit': 18,
976ae3ea 1184 'availability': 'needs_auth',
1185 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1186 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1187 'channel': 'FlyingKitty',
1188 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1189 'view_count': int,
1190 'categories': ['Entertainment'],
1191 'live_status': 'not_live',
1192 'tags': ['Flyingkitty', 'godzilla 2'],
1193 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1194 'like_count': int,
1195 'duration': 177,
1196 'playable_in_embed': True,
6c73052c 1197 'channel_follower_count': int
65c2fde2 1198 },
1199 },
1200 {
1201 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1202 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1203 'info_dict': {
1204 'id': 'Tq92D6wQ1mg',
1205 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1206 'ext': 'mp4',
17322130 1207 'upload_date': '20191228',
65c2fde2 1208 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1209 'uploader': 'Projekt Melody',
1210 'description': 'md5:17eccca93a786d51bc67646756894066',
1211 'age_limit': 18,
976ae3ea 1212 'like_count': int,
1213 'availability': 'needs_auth',
1214 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1215 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1216 'view_count': int,
1217 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1218 'channel': 'Projekt Melody',
1219 'live_status': 'not_live',
1220 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1221 'playable_in_embed': True,
1222 'categories': ['Entertainment'],
1223 'duration': 106,
1224 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1225 'channel_follower_count': int
65c2fde2 1226 },
1227 },
1228 {
1229 'note': 'Non-Agegated non-embeddable video',
1230 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1231 'info_dict': {
1232 'id': 'MeJVWBSsPAY',
1233 'ext': 'mp4',
1234 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1235 'uploader': 'Herr Lurik',
1236 'uploader_id': 'st3in234',
1237 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1238 'upload_date': '20130730',
976ae3ea 1239 'track': 'Such mich find mich',
1240 'age_limit': 0,
1241 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1242 'like_count': int,
1243 'playable_in_embed': False,
1244 'creator': 'OOMPH!',
1245 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1246 'view_count': int,
1247 'alt_title': 'Such mich find mich',
1248 'duration': 210,
1249 'channel': 'Herr Lurik',
1250 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1251 'categories': ['Music'],
1252 'availability': 'public',
1253 'uploader_url': 'http://www.youtube.com/user/st3in234',
1254 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1255 'live_status': 'not_live',
1256 'artist': 'OOMPH!',
6c73052c 1257 'channel_follower_count': int
65c2fde2 1258 },
1259 },
1260 {
1261 'note': 'Non-bypassable age-gated video',
1262 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1263 'only_matching': True,
1264 },
8bdd16b4 1265 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1266 # YouTube Red ad is not captured for creator
1267 {
1268 'url': '__2ABJjxzNo',
1269 'info_dict': {
1270 'id': '__2ABJjxzNo',
1271 'ext': 'mp4',
1272 'duration': 266,
1273 'upload_date': '20100430',
1274 'uploader_id': 'deadmau5',
1275 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1276 'creator': 'deadmau5',
1277 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1278 'uploader': 'deadmau5',
1279 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1280 'alt_title': 'Some Chords',
976ae3ea 1281 'availability': 'public',
1282 'tags': 'count:14',
1283 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1284 'view_count': int,
1285 'live_status': 'not_live',
1286 'channel': 'deadmau5',
1287 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1288 'like_count': int,
1289 'track': 'Some Chords',
1290 'artist': 'deadmau5',
1291 'playable_in_embed': True,
1292 'age_limit': 0,
1293 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1294 'categories': ['Music'],
1295 'album': 'Some Chords',
6c73052c 1296 'channel_follower_count': int
8bdd16b4 1297 },
1298 'expected_warnings': [
1299 'DASH manifest missing',
1300 ]
1301 },
067aa17e 1302 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1303 {
1304 'url': 'lqQg6PlCWgI',
1305 'info_dict': {
1306 'id': 'lqQg6PlCWgI',
1307 'ext': 'mp4',
556dbe7f 1308 'duration': 6085,
90227264 1309 'upload_date': '20150827',
cbe2bd91 1310 'uploader_id': 'olympic',
ec85ded8 1311 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1312 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1313 'uploader': 'Olympics',
cbe2bd91 1314 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1315 'like_count': int,
1316 'release_timestamp': 1343767800,
1317 'playable_in_embed': True,
1318 'categories': ['Sports'],
1319 'release_date': '20120731',
1320 'channel': 'Olympics',
1321 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1322 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1323 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1324 'age_limit': 0,
1325 'availability': 'public',
1326 'live_status': 'was_live',
1327 'view_count': int,
1328 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1329 'channel_follower_count': int
cbe2bd91
PH
1330 },
1331 'params': {
1332 'skip_download': 'requires avconv',
e52a40ab 1333 }
cbe2bd91 1334 },
6271f1ca
PH
1335 # Non-square pixels
1336 {
1337 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1338 'info_dict': {
1339 'id': '_b-2C3KPAM0',
1340 'ext': 'mp4',
1341 'stretched_ratio': 16 / 9.,
556dbe7f 1342 'duration': 85,
6271f1ca
PH
1343 'upload_date': '20110310',
1344 'uploader_id': 'AllenMeow',
ec85ded8 1345 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1346 '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 1347 'uploader': '孫ᄋᄅ',
6271f1ca 1348 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1349 'playable_in_embed': True,
1350 'channel': '孫ᄋᄅ',
1351 'age_limit': 0,
1352 'tags': 'count:11',
1353 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1354 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1355 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1356 'view_count': int,
1357 'categories': ['People & Blogs'],
1358 'like_count': int,
1359 'live_status': 'not_live',
1360 'availability': 'unlisted',
6c73052c 1361 'channel_follower_count': int
6271f1ca 1362 },
06b491eb
S
1363 },
1364 # url_encoded_fmt_stream_map is empty string
1365 {
1366 'url': 'qEJwOuvDf7I',
1367 'info_dict': {
1368 'id': 'qEJwOuvDf7I',
f57b7835 1369 'ext': 'webm',
06b491eb
S
1370 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1371 'description': '',
1372 'upload_date': '20150404',
1373 'uploader_id': 'spbelect',
1374 'uploader': 'Наблюдатели Петербурга',
1375 },
1376 'params': {
1377 'skip_download': 'requires avconv',
e323cf3f
S
1378 },
1379 'skip': 'This live event has ended.',
06b491eb 1380 },
067aa17e 1381 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1382 {
1383 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1384 'info_dict': {
1385 'id': 'FIl7x6_3R5Y',
eb6793ba 1386 'ext': 'webm',
da77d856
S
1387 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1388 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1389 'duration': 220,
da77d856
S
1390 'upload_date': '20150625',
1391 'uploader_id': 'dorappi2000',
ec85ded8 1392 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1393 'uploader': 'dorappi2000',
eb6793ba 1394 'formats': 'mincount:31',
da77d856 1395 },
eb6793ba 1396 'skip': 'not actual anymore',
2ee8f5d8 1397 },
8a1a26ce
YCH
1398 # DASH manifest with segment_list
1399 {
1400 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1401 'md5': '8ce563a1d667b599d21064e982ab9e31',
1402 'info_dict': {
1403 'id': 'CsmdDsKjzN8',
1404 'ext': 'mp4',
17ee98e1 1405 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1406 'uploader': 'Airtek',
1407 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1408 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1409 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1410 },
1411 'params': {
1412 'youtube_include_dash_manifest': True,
1413 'format': '135', # bestvideo
be49068d
S
1414 },
1415 'skip': 'This live event has ended.',
2ee8f5d8 1416 },
cf7e015f
S
1417 {
1418 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1419 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1420 'info_dict': {
545cc85d 1421 'id': 'jvGDaLqkpTg',
1422 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1423 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1424 },
1425 'playlist': [{
1426 'info_dict': {
545cc85d 1427 'id': 'jvGDaLqkpTg',
cf7e015f 1428 'ext': 'mp4',
545cc85d 1429 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1430 'description': 'md5:e03b909557865076822aa169218d6a5d',
1431 'duration': 10643,
1432 'upload_date': '20161111',
1433 'uploader': 'Team PGP',
1434 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1435 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1436 },
1437 }, {
1438 'info_dict': {
545cc85d 1439 'id': '3AKt1R1aDnw',
cf7e015f 1440 'ext': 'mp4',
545cc85d 1441 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1442 'description': 'md5:e03b909557865076822aa169218d6a5d',
1443 'duration': 10991,
1444 'upload_date': '20161111',
1445 'uploader': 'Team PGP',
1446 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1447 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1448 },
1449 }, {
1450 'info_dict': {
545cc85d 1451 'id': 'RtAMM00gpVc',
cf7e015f 1452 'ext': 'mp4',
545cc85d 1453 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1454 'description': 'md5:e03b909557865076822aa169218d6a5d',
1455 'duration': 10995,
1456 'upload_date': '20161111',
1457 'uploader': 'Team PGP',
1458 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1460 },
1461 }, {
1462 'info_dict': {
545cc85d 1463 'id': '6N2fdlP3C5U',
cf7e015f 1464 'ext': 'mp4',
545cc85d 1465 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1466 'description': 'md5:e03b909557865076822aa169218d6a5d',
1467 'duration': 10990,
1468 'upload_date': '20161111',
1469 'uploader': 'Team PGP',
1470 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1471 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1472 },
1473 }],
1474 'params': {
1475 'skip_download': True,
1476 },
65c2fde2 1477 'skip': 'Not multifeed anymore',
cbaed4bb 1478 },
f9f49d87 1479 {
067aa17e 1480 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1481 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1482 'info_dict': {
1483 'id': 'gVfLd0zydlo',
1484 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1485 },
1486 'playlist_count': 2,
be49068d 1487 'skip': 'Not multifeed anymore',
f9f49d87 1488 },
cbaed4bb 1489 {
2d3d2997 1490 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1491 'only_matching': True,
0e49d9a6 1492 },
6d4fc66b 1493 {
2d3d2997 1494 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1495 'only_matching': True,
1496 },
0e49d9a6 1497 {
067aa17e 1498 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1499 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1500 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1501 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1502 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1503 'info_dict': {
1504 'id': 'lsguqyKfVQg',
1505 'ext': 'mp4',
1506 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1507 'alt_title': 'Dark Walk',
0e49d9a6 1508 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1509 'duration': 133,
0e49d9a6
LL
1510 'upload_date': '20151119',
1511 'uploader_id': 'IronSoulElf',
ec85ded8 1512 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1513 'uploader': 'IronSoulElf',
11f9be09 1514 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1515 'track': 'Dark Walk',
1516 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1517 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1518 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1519 'categories': ['Film & Animation'],
1520 'view_count': int,
1521 'live_status': 'not_live',
1522 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1523 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1524 'tags': 'count:13',
1525 'availability': 'public',
1526 'channel': 'IronSoulElf',
1527 'playable_in_embed': True,
1528 'like_count': int,
1529 'age_limit': 0,
6c73052c 1530 'channel_follower_count': int
0e49d9a6
LL
1531 },
1532 'params': {
1533 'skip_download': True,
1534 },
1535 },
61f92af1 1536 {
067aa17e 1537 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1538 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1539 'only_matching': True,
1540 },
313dfc45
LL
1541 {
1542 # Video with yt:stretch=17:0
1543 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1544 'info_dict': {
1545 'id': 'Q39EVAstoRM',
1546 'ext': 'mp4',
1547 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1548 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1549 'upload_date': '20151107',
1550 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1551 'uploader': 'CH GAMER DROID',
1552 },
1553 'params': {
1554 'skip_download': True,
1555 },
be49068d 1556 'skip': 'This video does not exist.',
313dfc45 1557 },
201c1459 1558 {
1559 # Video with incomplete 'yt:stretch=16:'
1560 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1561 'only_matching': True,
1562 },
7caf9830
S
1563 {
1564 # Video licensed under Creative Commons
1565 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1566 'info_dict': {
1567 'id': 'M4gD1WSo5mA',
1568 'ext': 'mp4',
1569 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1570 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1571 'duration': 721,
17322130 1572 'upload_date': '20150128',
7caf9830 1573 'uploader_id': 'BerkmanCenter',
ec85ded8 1574 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1575 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1576 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1577 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1578 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1579 'like_count': int,
1580 'age_limit': 0,
1581 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1582 'channel': 'The Berkman Klein Center for Internet & Society',
1583 'availability': 'public',
1584 'view_count': int,
1585 'categories': ['Education'],
1586 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1587 'live_status': 'not_live',
1588 'playable_in_embed': True,
6c73052c 1589 'channel_follower_count': int
7caf9830
S
1590 },
1591 'params': {
1592 'skip_download': True,
1593 },
1594 },
fd050249
S
1595 {
1596 # Channel-like uploader_url
1597 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1598 'info_dict': {
1599 'id': 'eQcmzGIKrzg',
1600 'ext': 'mp4',
1601 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1602 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1603 'duration': 4060,
17322130 1604 'upload_date': '20151120',
eb6793ba 1605 'uploader': 'Bernie Sanders',
fd050249 1606 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1607 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1608 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1609 'playable_in_embed': True,
1610 'tags': 'count:12',
1611 'like_count': int,
1612 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1613 'age_limit': 0,
1614 'availability': 'public',
1615 'categories': ['News & Politics'],
1616 'channel': 'Bernie Sanders',
1617 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1618 'view_count': int,
1619 'live_status': 'not_live',
1620 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1621 'channel_follower_count': int
fd050249
S
1622 },
1623 'params': {
1624 'skip_download': True,
1625 },
1626 },
040ac686
S
1627 {
1628 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1629 'only_matching': True,
7f29cf54
S
1630 },
1631 {
067aa17e 1632 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1633 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1634 'only_matching': True,
6496ccb4
S
1635 },
1636 {
1637 # Rental video preview
1638 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1639 'info_dict': {
1640 'id': 'uGpuVWrhIzE',
1641 'ext': 'mp4',
1642 'title': 'Piku - Trailer',
1643 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1644 'upload_date': '20150811',
1645 'uploader': 'FlixMatrix',
1646 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1647 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1648 'license': 'Standard YouTube License',
1649 },
1650 'params': {
1651 'skip_download': True,
1652 },
eb6793ba 1653 'skip': 'This video is not available.',
022a5d66 1654 },
12afdc2a
S
1655 {
1656 # YouTube Red video with episode data
1657 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1658 'info_dict': {
1659 'id': 'iqKdEhx-dD4',
1660 'ext': 'mp4',
1661 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1662 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1663 'duration': 2085,
12afdc2a
S
1664 'upload_date': '20170118',
1665 'uploader': 'Vsauce',
1666 'uploader_id': 'Vsauce',
1667 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1668 'series': 'Mind Field',
1669 'season_number': 1,
1670 'episode_number': 1,
976ae3ea 1671 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1672 'tags': 'count:12',
1673 'view_count': int,
1674 'availability': 'public',
1675 'age_limit': 0,
1676 'channel': 'Vsauce',
1677 'episode': 'Episode 1',
1678 'categories': ['Entertainment'],
1679 'season': 'Season 1',
1680 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1681 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1682 'like_count': int,
1683 'playable_in_embed': True,
1684 'live_status': 'not_live',
6c73052c 1685 'channel_follower_count': int
12afdc2a
S
1686 },
1687 'params': {
1688 'skip_download': True,
1689 },
1690 'expected_warnings': [
1691 'Skipping DASH manifest',
1692 ],
1693 },
c7121fa7
S
1694 {
1695 # The following content has been identified by the YouTube community
1696 # as inappropriate or offensive to some audiences.
1697 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1698 'info_dict': {
1699 'id': '6SJNVb0GnPI',
1700 'ext': 'mp4',
1701 'title': 'Race Differences in Intelligence',
1702 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1703 'duration': 965,
1704 'upload_date': '20140124',
1705 'uploader': 'New Century Foundation',
1706 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1707 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1708 },
1709 'params': {
1710 'skip_download': True,
1711 },
545cc85d 1712 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1713 },
022a5d66
S
1714 {
1715 # itag 212
1716 'url': '1t24XAntNCY',
1717 'only_matching': True,
fd5c4aab
S
1718 },
1719 {
1720 # geo restricted to JP
1721 'url': 'sJL6WA-aGkQ',
1722 'only_matching': True,
1723 },
cd5a74a2
S
1724 {
1725 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1726 'only_matching': True,
1727 },
bc2ca1bb 1728 {
1729 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1730 'only_matching': True,
1731 },
1732 {
1733 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1734 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1735 'only_matching': True,
1736 },
825cd268
RA
1737 {
1738 # DRM protected
1739 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1740 'only_matching': True,
4fe54c12
S
1741 },
1742 {
1743 # Video with unsupported adaptive stream type formats
1744 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1745 'info_dict': {
1746 'id': 'Z4Vy8R84T1U',
1747 'ext': 'mp4',
1748 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1749 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1750 'duration': 433,
1751 'upload_date': '20130923',
1752 'uploader': 'Amelia Putri Harwita',
1753 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1754 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1755 'formats': 'maxcount:10',
1756 },
1757 'params': {
1758 'skip_download': True,
1759 'youtube_include_dash_manifest': False,
1760 },
5429d6a9 1761 'skip': 'not actual anymore',
5caabd3c 1762 },
1763 {
822b9d9c 1764 # Youtube Music Auto-generated description
5caabd3c 1765 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1766 'info_dict': {
1767 'id': 'MgNrAu2pzNs',
1768 'ext': 'mp4',
1769 'title': 'Voyeur Girl',
1770 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1771 'upload_date': '20190312',
5429d6a9
S
1772 'uploader': 'Stephen - Topic',
1773 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1774 'artist': 'Stephen',
1775 'track': 'Voyeur Girl',
1776 'album': 'it\'s too much love to know my dear',
1777 'release_date': '20190313',
1778 'release_year': 2019,
976ae3ea 1779 'alt_title': 'Voyeur Girl',
1780 'view_count': int,
1781 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1782 'playable_in_embed': True,
1783 'like_count': int,
1784 'categories': ['Music'],
1785 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1786 'channel': 'Stephen',
1787 'availability': 'public',
1788 'creator': 'Stephen',
1789 'duration': 169,
1790 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1791 'age_limit': 0,
1792 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1793 'tags': 'count:11',
1794 'live_status': 'not_live',
6c73052c 1795 'channel_follower_count': int
5caabd3c 1796 },
1797 'params': {
1798 'skip_download': True,
1799 },
1800 },
66b48727
RA
1801 {
1802 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1803 'only_matching': True,
1804 },
011e75e6
S
1805 {
1806 # invalid -> valid video id redirection
1807 'url': 'DJztXj2GPfl',
1808 'info_dict': {
1809 'id': 'DJztXj2GPfk',
1810 'ext': 'mp4',
1811 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1812 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1813 'upload_date': '20090125',
1814 'uploader': 'Prochorowka',
1815 'uploader_id': 'Prochorowka',
1816 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1817 'artist': 'Panjabi MC',
1818 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1819 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1820 },
1821 'params': {
1822 'skip_download': True,
1823 },
545cc85d 1824 'skip': 'Video unavailable',
ea74e00b
DP
1825 },
1826 {
1827 # empty description results in an empty string
1828 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1829 'info_dict': {
1830 'id': 'x41yOUIvK2k',
1831 'ext': 'mp4',
1832 'title': 'IMG 3456',
1833 'description': '',
1834 'upload_date': '20170613',
1835 'uploader_id': 'ElevageOrVert',
1836 'uploader': 'ElevageOrVert',
976ae3ea 1837 'view_count': int,
1838 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1839 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1840 'like_count': int,
1841 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1842 'tags': [],
1843 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1844 'availability': 'public',
1845 'age_limit': 0,
1846 'categories': ['Pets & Animals'],
1847 'duration': 7,
1848 'playable_in_embed': True,
1849 'live_status': 'not_live',
1850 'channel': 'ElevageOrVert',
6c73052c 1851 'channel_follower_count': int
ea74e00b
DP
1852 },
1853 'params': {
1854 'skip_download': True,
1855 },
1856 },
a0566bbf 1857 {
29f7c58a 1858 # with '};' inside yt initial data (see [1])
1859 # see [2] for an example with '};' inside ytInitialPlayerResponse
1860 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1861 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1862 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1863 'info_dict': {
1864 'id': 'CHqg6qOn4no',
1865 'ext': 'mp4',
1866 'title': 'Part 77 Sort a list of simple types in c#',
1867 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1868 'upload_date': '20130831',
1869 'uploader_id': 'kudvenkat',
1870 'uploader': 'kudvenkat',
976ae3ea 1871 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1872 'like_count': int,
1873 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1874 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1875 'live_status': 'not_live',
1876 'categories': ['Education'],
1877 'availability': 'public',
1878 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1879 'tags': 'count:12',
1880 'playable_in_embed': True,
1881 'age_limit': 0,
1882 'view_count': int,
1883 'duration': 522,
1884 'channel': 'kudvenkat',
6c73052c 1885 'channel_follower_count': int
a0566bbf 1886 },
1887 'params': {
1888 'skip_download': True,
1889 },
1890 },
29f7c58a 1891 {
1892 # another example of '};' in ytInitialData
1893 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1894 'only_matching': True,
1895 },
1896 {
1897 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1898 'only_matching': True,
1899 },
545cc85d 1900 {
cc2db878 1901 # https://github.com/ytdl-org/youtube-dl/pull/28094
1902 'url': 'OtqTfy26tG0',
1903 'info_dict': {
1904 'id': 'OtqTfy26tG0',
1905 'ext': 'mp4',
1906 'title': 'Burn Out',
1907 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1908 'upload_date': '20141120',
1909 'uploader': 'The Cinematic Orchestra - Topic',
1910 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1911 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1912 'artist': 'The Cinematic Orchestra',
1913 'track': 'Burn Out',
1914 'album': 'Every Day',
976ae3ea 1915 'like_count': int,
1916 'live_status': 'not_live',
1917 'alt_title': 'Burn Out',
1918 'duration': 614,
1919 'age_limit': 0,
1920 'view_count': int,
1921 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1922 'creator': 'The Cinematic Orchestra',
1923 'channel': 'The Cinematic Orchestra',
1924 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1925 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1926 'availability': 'public',
1927 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1928 'categories': ['Music'],
1929 'playable_in_embed': True,
6c73052c 1930 'channel_follower_count': int
cc2db878 1931 },
1932 'params': {
1933 'skip_download': True,
1934 },
545cc85d 1935 },
bc2ca1bb 1936 {
1937 # controversial video, only works with bpctr when authenticated with cookies
1938 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1939 'only_matching': True,
1940 },
a1a7907b 1941 {
1942 # controversial video, requires bpctr/contentCheckOk
1943 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1944 'info_dict': {
1945 'id': 'SZJvDhaSDnc',
1946 'ext': 'mp4',
1947 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1948 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1949 'uploader': 'CBS Mornings',
11f9be09 1950 'uploader_id': 'CBSThisMorning',
a1a7907b 1951 'upload_date': '20140716',
976ae3ea 1952 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1953 'duration': 170,
1954 'categories': ['News & Politics'],
1955 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1956 'view_count': int,
1957 'channel': 'CBS Mornings',
1958 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1959 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1960 'age_limit': 18,
1961 'availability': 'needs_auth',
1962 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1963 'like_count': int,
1964 'live_status': 'not_live',
1965 'playable_in_embed': True,
6c73052c 1966 'channel_follower_count': int
a1a7907b 1967 }
1968 },
f7ad7160 1969 {
1970 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1971 'url': 'cBvYw8_A0vQ',
1972 'info_dict': {
1973 'id': 'cBvYw8_A0vQ',
1974 'ext': 'mp4',
1975 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1976 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1977 'upload_date': '20201120',
1978 'uploader': 'Walk around Japan',
1979 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1980 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1981 'duration': 1456,
1982 'categories': ['Travel & Events'],
1983 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1984 'view_count': int,
1985 'channel': 'Walk around Japan',
1986 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1987 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1988 'age_limit': 0,
1989 'availability': 'public',
1990 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1991 'live_status': 'not_live',
1992 'playable_in_embed': True,
6c73052c 1993 'channel_follower_count': int
f7ad7160 1994 },
1995 'params': {
1996 'skip_download': True,
1997 },
0fb983f6 1998 }, {
1999 # Has multiple audio streams
2000 'url': 'WaOKSUlf4TM',
2001 'only_matching': True
9297939e 2002 }, {
2003 # Requires Premium: has format 141 when requested using YTM url
2004 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2005 'only_matching': True
2006 }, {
120916da 2007 # multiple subtitles with same lang_code
2008 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2009 'only_matching': True,
109dd3b2 2010 }, {
2011 # Force use android client fallback
2012 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2013 'info_dict': {
2014 'id': 'YOelRv7fMxY',
11f9be09 2015 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2016 'ext': '3gp',
2017 'upload_date': '20210624',
2018 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2019 'uploader': 'colinfurze',
11f9be09 2020 'uploader_id': 'colinfurze',
109dd3b2 2021 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2022 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2023 'duration': 596,
2024 'categories': ['Entertainment'],
2025 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2026 'view_count': int,
2027 'channel': 'colinfurze',
2028 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2029 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2030 'age_limit': 0,
2031 'availability': 'public',
2032 'like_count': int,
2033 'live_status': 'not_live',
2034 'playable_in_embed': True,
6c73052c 2035 'channel_follower_count': int
109dd3b2 2036 },
2037 'params': {
2038 'format': '17', # 3gp format available on android
2039 'extractor_args': {'youtube': {'player_client': ['android']}},
2040 },
120916da 2041 },
109dd3b2 2042 {
2043 # Skip download of additional client configs (remix client config in this case)
2044 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2045 'only_matching': True,
2046 'params': {
2047 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2048 },
8fc54b12 2049 }, {
2050 # shorts
2051 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2052 'only_matching': True,
9222c381 2053 }, {
2054 'note': 'Storyboards',
2055 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2056 'info_dict': {
2057 'id': '5KLPxDtMqe8',
2058 'ext': 'mhtml',
2059 'format_id': 'sb0',
2060 'title': 'Your Brain is Plastic',
2061 'uploader_id': 'scishow',
2062 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2063 'upload_date': '20140324',
2064 'uploader': 'SciShow',
976ae3ea 2065 'like_count': int,
2066 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2067 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2068 'view_count': int,
2069 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2070 'playable_in_embed': True,
2071 'tags': 'count:12',
2072 'uploader_url': 'http://www.youtube.com/user/scishow',
2073 'availability': 'public',
2074 'channel': 'SciShow',
2075 'live_status': 'not_live',
2076 'duration': 248,
2077 'categories': ['Education'],
2078 'age_limit': 0,
6c73052c 2079 'channel_follower_count': int
9222c381 2080 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2081 }, {
2082 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2083 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2084 'info_dict': {
2085 'id': '2NUZ8W2llS4',
2086 'ext': 'mp4',
2087 'title': 'The NP that test your phone performance 🙂',
2088 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2089 'uploader': 'Leon Nguyen',
2090 'uploader_id': 'VNSXIII',
2091 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2092 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2093 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2094 'duration': 21,
2095 'view_count': int,
2096 'age_limit': 0,
2097 'categories': ['Gaming'],
2098 'tags': 'count:23',
2099 'playable_in_embed': True,
2100 'live_status': 'not_live',
2101 'upload_date': '20220103',
2102 'like_count': int,
2103 'availability': 'public',
2104 'channel': 'Leon Nguyen',
2105 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2106 'channel_follower_count': int
2107 }
2108 }, {
2109 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2110 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2111 'info_dict': {
2112 'id': 'mzZzzBU6lrM',
2113 'ext': 'mp4',
2114 'title': 'I Met GeorgeNotFound In Real Life...',
2115 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2116 'uploader': 'Quackity',
2117 'uploader_id': 'QuackityHQ',
2118 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2119 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2120 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2121 'duration': 955,
2122 'view_count': int,
2123 'age_limit': 0,
2124 'categories': ['Entertainment'],
2125 'tags': 'count:26',
2126 'playable_in_embed': True,
2127 'live_status': 'not_live',
2128 'release_timestamp': 1641172509,
2129 'release_date': '20220103',
2130 'upload_date': '20220103',
2131 'like_count': int,
2132 'availability': 'public',
2133 'channel': 'Quackity',
2134 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2135 'channel_follower_count': int
2136 }
2137 },
2138 { # continuous livestream. Microformat upload date should be preferred.
2139 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2140 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2141 'info_dict': {
2142 'id': 'kgx4WGK0oNU',
2143 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2144 'ext': 'mp4',
2145 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2146 'availability': 'public',
2147 'age_limit': 0,
2148 'release_timestamp': 1637975704,
2149 'upload_date': '20210619',
2150 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2151 'live_status': 'is_live',
2152 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2153 'uploader': '阿鲍Abao',
2154 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2155 'channel': 'Abao in Tokyo',
2156 'channel_follower_count': int,
2157 'release_date': '20211127',
2158 'tags': 'count:39',
2159 'categories': ['People & Blogs'],
2160 'like_count': int,
2161 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2162 'view_count': int,
2163 'playable_in_embed': True,
2164 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2165 },
2166 'params': {'skip_download': True}
2167 },
2eb88d95
PH
2168 ]
2169
201c1459 2170 @classmethod
2171 def suitable(cls, url):
4dfbf869 2172 from ..utils import parse_qs
2173
201c1459 2174 qs = parse_qs(url)
2175 if qs.get('list', [None])[0]:
2176 return False
2177 return super(YoutubeIE, cls).suitable(url)
2178
e0df6211
PH
2179 def __init__(self, *args, **kwargs):
2180 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2181 self._code_cache = {}
83799698 2182 self._player_cache = {}
e0df6211 2183
adbc4ec4 2184 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2185 lock = threading.Lock()
2186
2187 is_live = True
185bf310 2188 start_time = time.time()
adbc4ec4
THD
2189 formats = [f for f in formats if f.get('is_from_start')]
2190
185bf310 2191 def refetch_manifest(format_id, delay):
2192 nonlocal formats, start_time, is_live
2193 if time.time() <= start_time + delay:
adbc4ec4
THD
2194 return
2195
2196 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2197 video_details = traverse_obj(
2198 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2199 microformats = traverse_obj(
2200 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2201 expected_type=dict, default=[])
2202 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2203 start_time = time.time()
adbc4ec4 2204
185bf310 2205 def mpd_feed(format_id, delay):
adbc4ec4
THD
2206 """
2207 @returns (manifest_url, manifest_stream_number, is_live) or None
2208 """
2209 with lock:
185bf310 2210 refetch_manifest(format_id, delay)
adbc4ec4
THD
2211
2212 f = next((f for f in formats if f['format_id'] == format_id), None)
2213 if not f:
185bf310 2214 if not is_live:
2215 self.to_screen(f'{video_id}: Video is no longer live')
2216 else:
2217 self.report_warning(
2218 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2219 return None
2220 return f['manifest_url'], f['manifest_stream_number'], is_live
2221
2222 for f in formats:
a539f065 2223 f['is_live'] = True
adbc4ec4
THD
2224 f['protocol'] = 'http_dash_segments_generator'
2225 f['fragments'] = functools.partial(
2226 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2227
2228 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2229 FETCH_SPAN, MAX_DURATION = 5, 432000
2230
2231 mpd_url, stream_number, is_live = None, None, True
2232
2233 begin_index = 0
2234 download_start_time = ctx.get('start') or time.time()
2235
2236 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2237 if lack_early_segments:
2238 self.report_warning(bug_reports_message(
2239 'Starting download from the last 120 hours of the live stream since '
2240 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2241 lack_early_segments = True
2242
2243 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2244 fragments, fragment_base_url = None, None
2245
a539f065 2246 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2247 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2248 # Obtain from MPD's maximum seq value
2249 old_mpd_url = mpd_url
185bf310 2250 last_error = ctx.pop('last_error', None)
a539f065 2251 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2252 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2253 or (mpd_url, stream_number, False))
2254 if not refresh_sequence:
2255 if expire_fast and not is_live:
2256 return False, last_seq
2257 elif old_mpd_url == mpd_url:
2258 return True, last_seq
adbc4ec4
THD
2259 try:
2260 fmts, _ = self._extract_mpd_formats_and_subtitles(
2261 mpd_url, None, note=False, errnote=False, fatal=False)
2262 except ExtractorError:
2263 fmts = None
2264 if not fmts:
a539f065 2265 no_fragment_score += 2
adbc4ec4
THD
2266 return False, last_seq
2267 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2268 fragments = fmt_info['fragments']
2269 fragment_base_url = fmt_info['fragment_base_url']
2270 assert fragment_base_url
2271
2272 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2273 return True, _last_seq
2274
2275 while is_live:
2276 fetch_time = time.time()
2277 if no_fragment_score > 30:
2278 return
2279 if last_segment_url:
2280 # Obtain from "X-Head-Seqnum" header value from each segment
2281 try:
2282 urlh = self._request_webpage(
2283 last_segment_url, None, note=False, errnote=False, fatal=False)
2284 except ExtractorError:
2285 urlh = None
2286 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2287 if last_seq is None:
a539f065 2288 no_fragment_score += 2
adbc4ec4
THD
2289 last_segment_url = None
2290 continue
2291 else:
a539f065
LNO
2292 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2293 no_fragment_score += 2
185bf310 2294 if not should_continue:
adbc4ec4
THD
2295 continue
2296
2297 if known_idx > last_seq:
2298 last_segment_url = None
2299 continue
2300
2301 last_seq += 1
2302
2303 if begin_index < 0 and known_idx < 0:
2304 # skip from the start when it's negative value
2305 known_idx = last_seq + begin_index
2306 if lack_early_segments:
2307 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2308 try:
2309 for idx in range(known_idx, last_seq):
2310 # do not update sequence here or you'll get skipped some part of it
a539f065 2311 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2312 if not should_continue:
adbc4ec4
THD
2313 known_idx = idx - 1
2314 raise ExtractorError('breaking out of outer loop')
2315 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2316 yield {
2317 'url': last_segment_url,
2318 }
2319 if known_idx == last_seq:
2320 no_fragment_score += 5
2321 else:
2322 no_fragment_score = 0
2323 known_idx = last_seq
2324 except ExtractorError:
2325 continue
2326
2327 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2328
b6de707d 2329 def _extract_player_url(self, *ytcfgs, webpage=None):
2330 player_url = traverse_obj(
2331 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2332 get_all=False, expected_type=compat_str)
11f9be09 2333 if not player_url:
b6de707d 2334 return
60f393e4 2335 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2336
b6de707d 2337 def _download_player_url(self, video_id, fatal=False):
2338 res = self._download_webpage(
2339 'https://www.youtube.com/iframe_api',
2340 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2341 if res:
2342 player_version = self._search_regex(
2343 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2344 if player_version:
2345 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2346
60064c53
PH
2347 def _signature_cache_id(self, example_sig):
2348 """ Return a string representation of a signature """
78caa52a 2349 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2350
e40c758c
S
2351 @classmethod
2352 def _extract_player_info(cls, player_url):
2353 for player_re in cls._PLAYER_INFO_RE:
2354 id_m = re.search(player_re, player_url)
2355 if id_m:
2356 break
2357 else:
c081b35c 2358 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2359 return id_m.group('id')
e40c758c 2360
404f611f 2361 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2362 player_id = self._extract_player_info(player_url)
2363 if player_id not in self._code_cache:
1276a43a 2364 code = self._download_webpage(
109dd3b2 2365 player_url, video_id, fatal=fatal,
2366 note='Downloading player ' + player_id,
2367 errnote='Download of %s failed' % player_url)
1276a43a 2368 if code:
2369 self._code_cache[player_id] = code
404f611f 2370 return self._code_cache.get(player_id)
109dd3b2 2371
e40c758c 2372 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2373 player_id = self._extract_player_info(player_url)
e0df6211 2374
c4417ddb 2375 # Read from filesystem cache
545cc85d 2376 func_id = 'js_%s_%s' % (
2377 player_id, self._signature_cache_id(example_sig))
c4417ddb 2378 assert os.path.basename(func_id) == func_id
a0e07d31 2379
69ea8ca4 2380 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2381 if cache_spec is not None:
78caa52a 2382 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2383
404f611f 2384 code = self._load_player(video_id, player_url)
2385 if code:
109dd3b2 2386 res = self._parse_sig_js(code)
e0df6211 2387
109dd3b2 2388 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2389 cache_res = res(test_string)
2390 cache_spec = [ord(c) for c in cache_res]
83799698 2391
109dd3b2 2392 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2393 return res
83799698 2394
60064c53 2395 def _print_sig_code(self, func, example_sig):
404f611f 2396 if not self.get_param('youtube_print_sig_code'):
2397 return
2398
edf3e38e
PH
2399 def gen_sig_code(idxs):
2400 def _genslice(start, end, step):
78caa52a 2401 starts = '' if start == 0 else str(start)
8bcc8756 2402 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2403 steps = '' if step == 1 else (':%d' % step)
78caa52a 2404 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2405
2406 step = None
7af808a5
PH
2407 # Quelch pyflakes warnings - start will be set when step is set
2408 start = '(Never used)'
edf3e38e
PH
2409 for i, prev in zip(idxs[1:], idxs[:-1]):
2410 if step is not None:
2411 if i - prev == step:
2412 continue
2413 yield _genslice(start, prev, step)
2414 step = None
2415 continue
2416 if i - prev in [-1, 1]:
2417 step = i - prev
2418 start = prev
2419 continue
2420 else:
78caa52a 2421 yield 's[%d]' % prev
edf3e38e 2422 if step is None:
78caa52a 2423 yield 's[%d]' % i
edf3e38e
PH
2424 else:
2425 yield _genslice(start, i, step)
2426
78caa52a 2427 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2428 cache_res = func(test_string)
edf3e38e 2429 cache_spec = [ord(c) for c in cache_res]
78caa52a 2430 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2431 signature_id_tuple = '(%s)' % (
2432 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2433 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2434 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2435 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2436
e0df6211
PH
2437 def _parse_sig_js(self, jscode):
2438 funcname = self._search_regex(
abefc03f
S
2439 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2440 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
2441 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2442 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2443 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}\(a,\d+\)',
2444 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 2445 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2446 # Obsolete patterns
2447 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2448 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2449 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2450 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2451 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2452 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2453 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2454 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2455 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2456
2457 jsi = JSInterpreter(jscode)
2458 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2459 return lambda s: initial_function([s])
2460
545cc85d 2461 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2462 """Turn the encrypted s field into a working signature"""
6b37f0be 2463
c8bf86d5 2464 if player_url is None:
69ea8ca4 2465 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2466
c8bf86d5 2467 try:
62af3a0e 2468 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2469 if player_id not in self._player_cache:
2470 func = self._extract_signature_function(
60064c53 2471 video_id, player_url, s
c8bf86d5
PH
2472 )
2473 self._player_cache[player_id] = func
2474 func = self._player_cache[player_id]
404f611f 2475 self._print_sig_code(func, s)
c8bf86d5
PH
2476 return func(s)
2477 except Exception as e:
404f611f 2478 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2479
2480 def _decrypt_nsig(self, s, video_id, player_url):
2481 """Turn the encrypted n field into a working signature"""
2482 if player_url is None:
2483 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2484 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2485
2486 sig_id = ('nsig_value', s)
2487 if sig_id in self._player_cache:
2488 return self._player_cache[sig_id]
2489
2490 try:
2491 player_id = ('nsig', player_url)
2492 if player_id not in self._player_cache:
2493 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2494 func = self._player_cache[player_id]
2495 self._player_cache[sig_id] = func(s)
2496 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2497 return self._player_cache[sig_id]
2498 except Exception as e:
aa9369a2 2499 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2500
2501 def _extract_n_function_name(self, jscode):
48416bc4 2502 nfunc, idx = self._search_regex(
c571b3a6 2503 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2504 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2505 if not idx:
2506 return nfunc
2507 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2508 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2509 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2510
2511 def _extract_n_function(self, video_id, player_url):
2512 player_id = self._extract_player_info(player_url)
2513 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2514
2515 if func_code:
2516 jsi = JSInterpreter(func_code)
2517 else:
2518 jscode = self._load_player(video_id, player_url)
2519 funcname = self._extract_n_function_name(jscode)
2520 jsi = JSInterpreter(jscode)
2521 func_code = jsi.extract_function_code(funcname)
2522 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2523
2524 if self.get_param('youtube_print_sig_code'):
2525 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2526
2527 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2528
109dd3b2 2529 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2530 """
2531 Extract signatureTimestamp (sts)
2532 Required to tell API what sig/player version is in use.
2533 """
2534 sts = None
2535 if isinstance(ytcfg, dict):
2536 sts = int_or_none(ytcfg.get('STS'))
2537
2538 if not sts:
2539 # Attempt to extract from player
2540 if player_url is None:
2541 error_msg = 'Cannot extract signature timestamp without player_url.'
2542 if fatal:
2543 raise ExtractorError(error_msg)
2544 self.report_warning(error_msg)
2545 return
404f611f 2546 code = self._load_player(video_id, player_url, fatal=fatal)
2547 if code:
109dd3b2 2548 sts = int_or_none(self._search_regex(
2549 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2550 'JS player signature timestamp', group='sts', fatal=fatal))
2551 return sts
2552
11f9be09 2553 def _mark_watched(self, video_id, player_responses):
9222c381 2554 playback_url = get_first(
2555 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2556 expected_type=url_or_none)
d77ab8e2 2557 if not playback_url:
352d63fd 2558 self.report_warning('Unable to mark watched')
d77ab8e2
S
2559 return
2560 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2561 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2562
2563 # cpn generation algorithm is reverse engineered from base.js.
2564 # In fact it works even with dummy cpn.
2565 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2566 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2567
2568 qs.update({
2569 'ver': ['2'],
2570 'cpn': [cpn],
2571 })
2572 playback_url = compat_urlparse.urlunparse(
15707c7e 2573 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2574
2575 self._download_webpage(
2576 playback_url, video_id, 'Marking watched',
2577 'Unable to mark watched', fatal=False)
2578
66c9fa36
S
2579 @staticmethod
2580 def _extract_urls(webpage):
2581 # Embedded YouTube player
2582 entries = [
2583 unescapeHTML(mobj.group('url'))
2584 for mobj in re.finditer(r'''(?x)
2585 (?:
2586 <iframe[^>]+?src=|
2587 data-video-url=|
2588 <embed[^>]+?src=|
2589 embedSWF\(?:\s*|
2590 <object[^>]+data=|
2591 new\s+SWFObject\(
2592 )
2593 (["\'])
2594 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2595 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2596 \1''', webpage)]
2597
2598 # lazyYT YouTube embed
2599 entries.extend(list(map(
2600 unescapeHTML,
2601 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2602
2603 # Wordpress "YouTube Video Importer" plugin
2604 matches = re.findall(r'''(?x)<div[^>]+
2605 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2606 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2607 entries.extend(m[-1] for m in matches)
2608
2609 return entries
2610
2611 @staticmethod
2612 def _extract_url(webpage):
2613 urls = YoutubeIE._extract_urls(webpage)
2614 return urls[0] if urls else None
2615
97665381
PH
2616 @classmethod
2617 def extract_id(cls, url):
2618 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2619 if mobj is None:
69ea8ca4 2620 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2621 return mobj.group('id')
c5e8d7af 2622
7c365c21 2623 def _extract_chapters_from_json(self, data, duration):
2624 chapter_list = traverse_obj(
2625 data, (
2626 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2627 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2628 ), expected_type=list)
2629
2630 return self._extract_chapters(
2631 chapter_list,
2632 chapter_time=lambda chapter: float_or_none(
2633 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2634 chapter_title=lambda chapter: traverse_obj(
2635 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2636 duration=duration)
2637
2638 def _extract_chapters_from_engagement_panel(self, data, duration):
2639 content_list = traverse_obj(
8bdd16b4 2640 data,
7c365c21 2641 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2642 expected_type=list, default=[])
052e1350 2643 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2644 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2645
2646 return next((
2647 filter(None, (
2648 self._extract_chapters(
2649 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2650 chapter_time, chapter_title, duration)
2651 for contents in content_list
2652 ))), [])
2653
2654 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2655 chapters = []
7c365c21 2656 last_chapter = {'start_time': 0}
2657 for idx, chapter in enumerate(chapter_list or []):
2658 title = chapter_title(chapter)
84213ea8
S
2659 start_time = chapter_time(chapter)
2660 if start_time is None:
2661 continue
7c365c21 2662 last_chapter['end_time'] = start_time
2663 if start_time < last_chapter['start_time']:
2664 if idx == 1:
2665 chapters.pop()
2666 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2667 else:
2668 self.report_warning(f'Invalid start time for chapter "{title}"')
2669 continue
2670 last_chapter = {'start_time': start_time, 'title': title}
2671 chapters.append(last_chapter)
2672 last_chapter['end_time'] = duration
84213ea8
S
2673 return chapters
2674
545cc85d 2675 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2676 return self._parse_json(self._search_regex(
2677 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2678 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2679
a1c5d2ca
M
2680 def _extract_comment(self, comment_renderer, parent=None):
2681 comment_id = comment_renderer.get('commentId')
2682 if not comment_id:
2683 return
fe93e2c4 2684
052e1350 2685 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2686
49bd8c66 2687 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2688 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2689 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2690 author_id = try_get(comment_renderer,
2691 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2692
49bd8c66 2693 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2694 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2695 author_thumbnail = try_get(comment_renderer,
2696 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2697
2698 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2699 is_favorited = 'creatorHeart' in (try_get(
2700 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2701 return {
2702 'id': comment_id,
2703 'text': text,
d92f5d5a 2704 'timestamp': timestamp,
a1c5d2ca
M
2705 'time_text': time_text,
2706 'like_count': votes,
97524332 2707 'is_favorited': is_favorited,
a1c5d2ca
M
2708 'author': author,
2709 'author_id': author_id,
2710 'author_thumbnail': author_thumbnail,
2711 'author_is_uploader': author_is_uploader,
2712 'parent': parent or 'root'
2713 }
2714
46383212 2715 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2716
2717 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2718
2719 def extract_header(contents):
2d6659b9 2720 _continuation = None
2721 for content in contents:
46383212 2722 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2723 expected_comment_count = self._get_count(
2724 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2725
2d6659b9 2726 if expected_comment_count:
46383212 2727 tracker['est_total'] = expected_comment_count
2728 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2729 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2730
2731 sort_menu_item = try_get(
2732 comments_header_renderer,
2733 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2734 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2735
2736 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2737 if not _continuation:
2738 continue
2739
46383212 2740 sort_text = str_or_none(sort_menu_item.get('title'))
2741 if not sort_text:
2d6659b9 2742 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2743 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2744 break
a2160aa4 2745 return _continuation
a1c5d2ca 2746
2d6659b9 2747 def extract_thread(contents):
a1c5d2ca 2748 if not parent:
46383212 2749 tracker['current_page_thread'] = 0
a1c5d2ca 2750 for content in contents:
46383212 2751 if not parent and tracker['total_parent_comments'] >= max_parents:
2752 yield
a1c5d2ca 2753 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2754 comment_renderer = get_first(
2755 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2756 expected_type=dict, default={})
a1c5d2ca 2757
a1c5d2ca
M
2758 comment = self._extract_comment(comment_renderer, parent)
2759 if not comment:
2760 continue
46383212 2761
2762 tracker['running_total'] += 1
2763 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2764 yield comment
46383212 2765
a1c5d2ca
M
2766 # Attempt to get the replies
2767 comment_replies_renderer = try_get(
2768 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2769
2770 if comment_replies_renderer:
46383212 2771 tracker['current_page_thread'] += 1
a1c5d2ca 2772 comment_entries_iter = self._comment_entries(
99e9e001 2773 comment_replies_renderer, ytcfg, video_id,
46383212 2774 parent=comment.get('id'), tracker=tracker)
2775 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2776 yield reply_comment
2777
46383212 2778 # Keeps track of counts across recursive calls
2779 if not tracker:
2780 tracker = dict(
2781 running_total=0,
2782 est_total=0,
2783 current_page_thread=0,
2784 total_parent_comments=0,
2785 total_reply_comments=0)
2786
2787 # TODO: Deprecated
2d6659b9 2788 # YouTube comments have a max depth of 2
46383212 2789 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2790 if max_depth:
2791 self._downloader.deprecation_warning(
2792 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2793 if max_depth == 1 and parent:
2794 return
a1c5d2ca 2795
46383212 2796 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2797 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2798
46383212 2799 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2800 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2801 if message and not parent:
2802 self.report_warning(message, video_id=video_id)
2803
46383212 2804 response = None
2d6659b9 2805 is_first_continuation = parent is None
a1c5d2ca
M
2806
2807 for page_num in itertools.count(0):
2808 if not continuation:
2809 break
46383212 2810 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2811 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2812 if page_num == 0:
2813 if is_first_continuation:
2814 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2815 else:
2d6659b9 2816 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2817 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2818 else:
2819 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2820 ' ' if parent else '', ' replies' if parent else '',
2821 page_num, comment_prog_str)
2822
2823 response = self._extract_response(
fe93e2c4 2824 item_id=None, query=continuation,
2d6659b9 2825 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2826 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2827
46383212 2828 continuation_contents = traverse_obj(
2829 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2830
2d6659b9 2831 continuation = None
46383212 2832 for continuation_section in continuation_contents:
2833 continuation_items = traverse_obj(
2834 continuation_section,
2835 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2836 get_all=False, expected_type=list) or []
2837 if is_first_continuation:
2838 continuation = extract_header(continuation_items)
2839 is_first_continuation = False
2d6659b9 2840 if continuation:
a1c5d2ca 2841 break
46383212 2842 continue
a1c5d2ca 2843
46383212 2844 for entry in extract_thread(continuation_items):
2845 if not entry:
2846 return
2847 yield entry
2848 continuation = self._extract_continuation({'contents': continuation_items})
2849 if continuation:
2d6659b9 2850 break
a1c5d2ca 2851
a2160aa4 2852 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2853 """Entry for comment extraction"""
2d6659b9 2854 def _real_comment_extract(contents):
aae16f6e 2855 renderer = next((
2856 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2857 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2858 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2859
a2160aa4 2860 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2861 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2862
109dd3b2 2863 @staticmethod
99e9e001 2864 def _get_checkok_params():
2865 return {'contentCheckOk': True, 'racyCheckOk': True}
2866
2867 @classmethod
2868 def _generate_player_context(cls, sts=None):
109dd3b2 2869 context = {
2870 'html5Preference': 'HTML5_PREF_WANTS',
2871 }
2872 if sts is not None:
2873 context['signatureTimestamp'] = sts
2874 return {
2875 'playbackContext': {
2876 'contentPlaybackContext': context
a1a7907b 2877 },
99e9e001 2878 **cls._get_checkok_params()
109dd3b2 2879 }
2880
e7e94f2a
D
2881 @staticmethod
2882 def _is_agegated(player_response):
2883 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2884 return True
e7e94f2a
D
2885
2886 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2887 AGE_GATE_REASONS = (
2888 'confirm your age', 'age-restricted', 'inappropriate', # reason
2889 'age_verification_required', 'age_check_required', # status
2890 )
2891 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2892
2893 @staticmethod
2894 def _is_unplayable(player_response):
2895 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2896
99e9e001 2897 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2898
11f9be09 2899 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2900 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2901 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2902 headers = self.generate_api_headers(
99e9e001 2903 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2904
11f9be09 2905 yt_query = {'videoId': video_id}
2906 yt_query.update(self._generate_player_context(sts))
2907 return self._extract_response(
2908 item_id=video_id, ep='player', query=yt_query,
379e44ed 2909 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2910 default_client=client,
11f9be09 2911 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2912 ) or None
2913
11f9be09 2914 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2915 requested_clients = []
d0d012d4 2916 default = ['android', 'web']
000c15a4 2917 allowed_clients = sorted(
2918 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2919 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2920 for client in self._configuration_arg('player_client'):
2921 if client in allowed_clients:
2922 requested_clients.append(client)
d0d012d4 2923 elif client == 'default':
2924 requested_clients.extend(default)
b4c055ba 2925 elif client == 'all':
2926 requested_clients.extend(allowed_clients)
2927 else:
2928 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2929 if not requested_clients:
d0d012d4 2930 requested_clients = default
cf7e015f 2931
11f9be09 2932 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2933 requested_clients.extend(
e7e94f2a 2934 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2935
11f9be09 2936 return orderedSet(requested_clients)
cf7e015f 2937
c0bc527b
M
2938 def _extract_player_ytcfg(self, client, video_id):
2939 url = {
2940 'web_music': 'https://music.youtube.com',
2941 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2942 }.get(client)
2943 if not url:
2944 return {}
18c7683d 2945 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2946 return self.extract_ytcfg(video_id, webpage) or {}
2947
99e9e001 2948 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2949 initial_pr = None
2950 if webpage:
2951 initial_pr = self._extract_yt_initial_variable(
2952 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2953 video_id, 'initial player response')
6b09401b 2954
c0bc527b
M
2955 original_clients = clients
2956 clients = clients[::-1]
b6de707d 2957 prs = []
e7e94f2a
D
2958
2959 def append_client(client_name):
2960 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2961 clients.append(client_name)
2962
379e44ed 2963 # Android player_response does not have microFormats which are needed for
2964 # extraction of some data. So we return the initial_pr with formats
2965 # stripped out even if not requested by the user
2966 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2967 if initial_pr:
2968 pr = dict(initial_pr)
2969 pr['streamingData'] = None
b6de707d 2970 prs.append(pr)
379e44ed 2971
2972 last_error = None
b6de707d 2973 tried_iframe_fallback = False
2974 player_url = None
c0bc527b
M
2975 while clients:
2976 client = clients.pop()
11f9be09 2977 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2978 if 'configs' not in self._configuration_arg('player_skip'):
2979 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2980
b6de707d 2981 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2982 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2983 if 'js' in self._configuration_arg('player_skip'):
2984 require_js_player = False
2985 player_url = None
2986
2987 if not player_url and not tried_iframe_fallback and require_js_player:
2988 player_url = self._download_player_url(video_id)
2989 tried_iframe_fallback = True
2990
379e44ed 2991 try:
2992 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2993 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2994 except ExtractorError as e:
2995 if last_error:
2996 self.report_warning(last_error)
2997 last_error = e
2998 continue
2999
11f9be09 3000 if pr:
b6de707d 3001 prs.append(pr)
c0bc527b 3002
e7e94f2a 3003 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 3004 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
3005 append_client(client.replace('_agegate', '_creator'))
3006 elif self._is_agegated(pr):
3007 append_client(f'{client}_agegate')
c0bc527b 3008
379e44ed 3009 if last_error:
b6de707d 3010 if not len(prs):
379e44ed 3011 raise last_error
3012 self.report_warning(last_error)
b6de707d 3013 return prs, player_url
11f9be09 3014
a1b2d843 3015 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3016 itags, stream_ids = {}, []
2a9c6dcd 3017 itag_qualities, res_qualities = {}, {}
d3fc8074 3018 q = qualities([
2a9c6dcd 3019 # Normally tiny is the smallest video-only formats. But
3020 # audio-only formats with unknown quality may get tagged as tiny
3021 'tiny',
3022 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3023 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3024 ])
11f9be09 3025 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3026
545cc85d 3027 for fmt in streaming_formats:
3028 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
3029 continue
321bf820 3030
cc2db878 3031 itag = str_or_none(fmt.get('itag'))
9297939e 3032 audio_track = fmt.get('audioTrack') or {}
3033 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3034 if stream_id in stream_ids:
3035 continue
3036
cc2db878 3037 quality = fmt.get('quality')
2a9c6dcd 3038 height = int_or_none(fmt.get('height'))
d3fc8074 3039 if quality == 'tiny' or not quality:
3040 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3041 # The 3gp format (17) in android client has a quality of "small",
3042 # but is actually worse than other formats
3043 if itag == '17':
3044 quality = 'tiny'
3045 if quality:
3046 if itag:
3047 itag_qualities[itag] = quality
3048 if height:
3049 res_qualities[height] = quality
cc2db878 3050 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3051 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3052 # number of fragment that would subsequently requested with (`&sq=N`)
3053 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3054 continue
3055
545cc85d 3056 fmt_url = fmt.get('url')
3057 if not fmt_url:
3058 sc = compat_parse_qs(fmt.get('signatureCipher'))
3059 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3060 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3061 if not (sc and fmt_url and encrypted_sig):
3062 continue
545cc85d 3063 if not player_url:
201e9eaa 3064 continue
545cc85d 3065 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3066 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3067 fmt_url += '&' + sp + '=' + signature
3068
404f611f 3069 query = parse_qs(fmt_url)
3070 throttled = False
b2916526 3071 if query.get('n'):
404f611f 3072 try:
3073 fmt_url = update_url_query(fmt_url, {
3074 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3075 except ExtractorError as e:
aa9369a2 3076 self.report_warning(
3077 f'nsig extraction failed: You may experience throttling for some formats\n'
3078 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3079 throttled = True
3080
545cc85d 3081 if itag:
a0bb6ce5 3082 itags[itag] = 'https'
9297939e 3083 stream_ids.append(stream_id)
3084
0ad92dfb 3085 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3086 language_preference = (
3087 10 if audio_track.get('audioIsDefault') and 10
3088 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3089 else -1)
0ad92dfb 3090 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3091 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3092 # Make sure to avoid false positives with small duration differences.
3093 # Eg: __2ABJjxzNo, ySuUZEjARPY
3094 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3095 if is_damaged:
3096 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3097 dct = {
3098 'asr': int_or_none(fmt.get('audioSampleRate')),
3099 'filesize': int_or_none(fmt.get('contentLength')),
3100 'format_id': itag,
34921b43 3101 'format_note': join_nonempty(
26e8e044 3102 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3103 ' (default)' if language_preference > 0 else ''),
404f611f 3104 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3105 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3106 'source_preference': -10 if throttled else -1,
a4211baf 3107 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3108 'height': height,
dca3ff4a 3109 'quality': q(quality),
cc2db878 3110 'tbr': tbr,
545cc85d 3111 'url': fmt_url,
2a9c6dcd 3112 'width': int_or_none(fmt.get('width')),
ab6df717 3113 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3114 'desc' if language_preference < -1 else ''),
3115 'language_preference': language_preference,
a405b38f 3116 # Strictly de-prioritize damaged and 3gp formats
3117 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3118 }
60bdb7bd 3119 mime_mobj = re.match(
3120 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3121 if mime_mobj:
3122 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3123 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3124 no_audio = dct.get('acodec') == 'none'
3125 no_video = dct.get('vcodec') == 'none'
3126 if no_audio:
3127 dct['vbr'] = tbr
3128 if no_video:
3129 dct['abr'] = tbr
3130 if no_audio or no_video:
545cc85d 3131 dct['downloader_options'] = {
3132 # Youtube throttles chunks >~10M
3133 'http_chunk_size': 10485760,
bf1317d2 3134 }
7c60c33e 3135 if dct.get('ext'):
3136 dct['container'] = dct['ext'] + '_dash'
11f9be09 3137 yield dct
545cc85d 3138
adbc4ec4 3139 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3140 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3141 if not self.get_param('youtube_include_hls_manifest', True):
3142 skip_manifests.append('hls')
3143 get_dash = 'dash' not in skip_manifests and (
3144 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3145 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3146
a0bb6ce5 3147 def process_manifest_format(f, proto, itag):
3148 if itag in itags:
3149 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3150 return False
3151 itag = f'{itag}-{proto}'
3152 if itag:
3153 f['format_id'] = itag
3154 itags[itag] = proto
3155
3156 f['quality'] = next((
3157 q(qdict[val])
e339d25a 3158 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3159 if val in qdict), -1)
3160 return True
2a9c6dcd 3161
11f9be09 3162 for sd in streaming_data:
5d3a0e79 3163 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3164 if hls_manifest_url:
2a9c6dcd 3165 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3166 if process_manifest_format(f, 'hls', self._search_regex(
3167 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3168 yield f
545cc85d 3169
5d3a0e79 3170 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3171 if dash_manifest_url:
2a9c6dcd 3172 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3173 if process_manifest_format(f, 'dash', f['format_id']):
3174 f['filesize'] = int_or_none(self._search_regex(
3175 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3176 if live_from_start:
3177 f['is_from_start'] = True
3178
a0bb6ce5 3179 yield f
11f9be09 3180
720c3099 3181 def _extract_storyboard(self, player_responses, duration):
3182 spec = get_first(
3183 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3184 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3185 if not base_url:
720c3099 3186 return
720c3099 3187 L = len(spec) - 1
3188 for i, args in enumerate(spec):
3189 args = args.split('#')
3190 counts = list(map(int_or_none, args[:5]))
3191 if len(args) != 8 or not all(counts):
3192 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3193 continue
3194 width, height, frame_count, cols, rows = counts
3195 N, sigh = args[6:]
3196
3197 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3198 fragment_count = frame_count / (cols * rows)
3199 fragment_duration = duration / fragment_count
3200 yield {
3201 'format_id': f'sb{i}',
3202 'format_note': 'storyboard',
3203 'ext': 'mhtml',
3204 'protocol': 'mhtml',
3205 'acodec': 'none',
3206 'vcodec': 'none',
3207 'url': url,
3208 'width': width,
3209 'height': height,
3210 'fragments': [{
b3edc806 3211 'url': url.replace('$M', str(j)),
720c3099 3212 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3213 } for j in range(math.ceil(fragment_count))],
3214 }
3215
adbc4ec4 3216 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3217 webpage = None
3218 if 'webpage' not in self._configuration_arg('player_skip'):
3219 webpage = self._download_webpage(
3220 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3221
3222 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3223
b6de707d 3224 player_responses, player_url = self._extract_player_responses(
11f9be09 3225 self._get_requested_clients(url, smuggled_data),
99e9e001 3226 video_id, webpage, master_ytcfg)
11f9be09 3227
adbc4ec4
THD
3228 return webpage, master_ytcfg, player_responses, player_url
3229
a1b2d843 3230 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3231 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3232 is_live = get_first(video_details, 'isLive')
3233 if is_live is None:
3234 is_live = get_first(live_broadcast_details, 'isLiveNow')
3235
3236 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3237 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3238
3239 return live_broadcast_details, is_live, streaming_data, formats
3240
3241 def _real_extract(self, url):
3242 url, smuggled_data = unsmuggle_url(url, {})
3243 video_id = self._match_id(url)
3244
3245 base_url = self.http_scheme() + '//www.youtube.com/'
3246 webpage_url = base_url + 'watch?v=' + video_id
3247
3248 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3249
11f9be09 3250 playability_statuses = traverse_obj(
3251 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3252
3253 trailer_video_id = get_first(
3254 playability_statuses,
3255 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3256 expected_type=str)
3257 if trailer_video_id:
3258 return self.url_result(
3259 trailer_video_id, self.ie_key(), trailer_video_id)
3260
3261 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3262 if webpage else (lambda x: None))
3263
3264 video_details = traverse_obj(
3265 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3266 microformats = traverse_obj(
3267 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3268 expected_type=dict, default=[])
3269 video_title = (
3270 get_first(video_details, 'title')
3271 or self._get_text(microformats, (..., 'title'))
3272 or search_meta(['og:title', 'twitter:title', 'title']))
3273 video_description = get_first(video_details, 'shortDescription')
3274
d89257f3 3275 multifeed_metadata_list = get_first(
3276 player_responses,
3277 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3278 expected_type=str)
3279 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3280 if self.get_param('noplaylist'):
11f9be09 3281 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3282 else:
3283 entries = []
3284 feed_ids = []
3285 for feed in multifeed_metadata_list.split(','):
3286 # Unquote should take place before split on comma (,) since textual
3287 # fields may contain comma as well (see
3288 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3289 feed_data = compat_parse_qs(
3290 compat_urllib_parse_unquote_plus(feed))
3291
3292 def feed_entry(name):
3293 return try_get(
3294 feed_data, lambda x: x[name][0], compat_str)
3295
3296 feed_id = feed_entry('id')
3297 if not feed_id:
3298 continue
3299 feed_title = feed_entry('title')
3300 title = video_title
3301 if feed_title:
3302 title += ' (%s)' % feed_title
3303 entries.append({
3304 '_type': 'url_transparent',
3305 'ie_key': 'Youtube',
3306 'url': smuggle_url(
3307 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3308 {'force_singlefeed': True}),
3309 'title': title,
3310 })
3311 feed_ids.append(feed_id)
3312 self.to_screen(
3313 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3314 % (', '.join(feed_ids), video_id))
3315 return self.playlist_result(
3316 entries, video_id, video_title, video_description)
11f9be09 3317
a1b2d843 3318 duration = int_or_none(
3319 get_first(video_details, 'lengthSeconds')
3320 or get_first(microformats, 'lengthSeconds')
3321 or parse_duration(search_meta('duration'))) or None
3322
3323 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3324 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3325
545cc85d 3326 if not formats:
11f9be09 3327 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3328 self.report_drm(video_id)
11f9be09 3329 pemr = get_first(
3330 playability_statuses,
3331 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3332 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3333 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3334 if subreason:
545cc85d 3335 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3336 countries = get_first(microformats, 'availableCountries')
545cc85d 3337 if not countries:
3338 regions_allowed = search_meta('regionsAllowed')
3339 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3340 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3341 reason += f'. {subreason}'
545cc85d 3342 if reason:
b7da73eb 3343 self.raise_no_formats(reason, expected=True)
bf1317d2 3344
11f9be09 3345 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3346 if not keywords and webpage:
3347 keywords = [
3348 unescapeHTML(m.group('content'))
3349 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3350 for keyword in keywords:
3351 if keyword.startswith('yt:stretch='):
201c1459 3352 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3353 if mobj:
3354 # NB: float is intentional for forcing float division
3355 w, h = (float(v) for v in mobj.groups())
3356 if w > 0 and h > 0:
3357 ratio = w / h
3358 for f in formats:
3359 if f.get('vcodec') != 'none':
3360 f['stretched_ratio'] = ratio
3361 break
a709d873 3362 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3363 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3364 if thumbnail_url:
3365 thumbnails.append({
3366 'url': thumbnail_url,
ff2751ac 3367 })
fccf5021 3368 original_thumbnails = thumbnails.copy()
3369
0ba692ac 3370 # The best resolution thumbnails sometimes does not appear in the webpage
3371 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3372 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3373 thumbnail_names = [
3374 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3375 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3376 'mqdefault', 'mq1', 'mq2', 'mq3',
3377 'default', '1', '2', '3'
3378 ]
cca80fe6 3379 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3380 thumbnails.extend({
3381 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3382 video_id=video_id, name=name, ext=ext,
3383 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3384 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3385 for thumb in thumbnails:
cca80fe6 3386 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3387 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3388 self._remove_duplicate_formats(thumbnails)
fccf5021 3389 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3390
7ea65411 3391 category = get_first(microformats, 'category') or search_meta('genre')
3392 channel_id = str_or_none(
3393 get_first(video_details, 'channelId')
3394 or get_first(microformats, 'externalChannelId')
3395 or search_meta('channelId'))
7ea65411 3396 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3397
3398 live_content = get_first(video_details, 'isLiveContent')
3399 is_upcoming = get_first(video_details, 'isUpcoming')
3400 if is_live is None:
3401 if is_upcoming or live_content is False:
3402 is_live = False
3403 if is_upcoming is None and (live_content or is_live):
3404 is_upcoming = False
adbc4ec4
THD
3405 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3406 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3407 if not duration and live_end_time and live_start_time:
3408 duration = live_end_time - live_start_time
3409
3410 if is_live and self.get_param('live_from_start'):
3411 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3412
720c3099 3413 formats.extend(self._extract_storyboard(player_responses, duration))
3414
3415 # Source is given priority since formats that throttle are given lower source_preference
3416 # When throttling issue is fully fixed, remove this
3417 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3418
545cc85d 3419 info = {
3420 'id': video_id,
39ca3b5c 3421 'title': video_title,
545cc85d 3422 'formats': formats,
3423 'thumbnails': thumbnails,
fccf5021 3424 # The best thumbnail that we are sure exists. Prevents unnecessary
3425 # URL checking if user don't care about getting the best possible thumbnail
3426 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3427 'description': video_description,
11f9be09 3428 'uploader': get_first(video_details, 'author'),
545cc85d 3429 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3430 'uploader_url': owner_profile_url,
3431 'channel_id': channel_id,
e0ddbd02 3432 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3433 'duration': duration,
3434 'view_count': int_or_none(
11f9be09 3435 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3436 or search_meta('interactionCount')),
11f9be09 3437 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3438 'age_limit': 18 if (
11f9be09 3439 get_first(microformats, 'isFamilySafe') is False
545cc85d 3440 or search_meta('isFamilyFriendly') == 'false'
3441 or search_meta('og:restrictions:age') == '18+') else 0,
3442 'webpage_url': webpage_url,
3443 'categories': [category] if category else None,
3444 'tags': keywords,
11f9be09 3445 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3446 'is_live': is_live,
3447 'was_live': (False if is_live or is_upcoming or live_content is False
3448 else None if is_live is None or is_upcoming is None
3449 else live_content),
3450 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3451 'release_timestamp': live_start_time,
545cc85d 3452 }
b477fc13 3453
3944e7af 3454 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3455 if pctr:
ecdc9049 3456 def get_lang_code(track):
3457 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3458 or track.get('languageCode'))
3459
3460 # Converted into dicts to remove duplicates
3461 captions = {
3462 get_lang_code(sub): sub
3463 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3464 translation_languages = {
3465 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3466 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3467
774d79cc 3468 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3469 lang_subs = container.setdefault(lang_code, [])
545cc85d 3470 for fmt in self._SUBTITLE_FORMATS:
3471 query.update({
3472 'fmt': fmt,
3473 })
3474 lang_subs.append({
3475 'ext': fmt,
60f393e4 3476 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3477 'name': sub_name,
545cc85d 3478 })
7e72694b 3479
ecdc9049 3480 subtitles, automatic_captions = {}, {}
3481 for lang_code, caption_track in captions.items():
3482 base_url = caption_track.get('baseUrl')
545cc85d 3483 if not base_url:
3484 continue
ecdc9049 3485 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3486 if caption_track.get('kind') != 'asr':
545cc85d 3487 if not lang_code:
3488 continue
3489 process_language(
ecdc9049 3490 subtitles, base_url, lang_code, lang_name, {})
3491 if not caption_track.get('isTranslatable'):
3492 continue
3944e7af 3493 for trans_code, trans_name in translation_languages.items():
3494 if not trans_code:
545cc85d 3495 continue
ecdc9049 3496 if caption_track.get('kind') != 'asr':
3497 trans_code += f'-{lang_code}'
3498 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3499 # Add an "-orig" label to the original language so that it can be distinguished.
3500 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 3501 if lang_code == f'a-{trans_code}':
3502 process_language(
d49669ac 3503 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3504 # Setting tlang=lang returns damaged subtitles.
3505 # Not using lang_code == f'a-{trans_code}' here for future-proofing
3506 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3507 process_language(automatic_captions, base_url, trans_code, trans_name,
3508 {} if orig_lang == trans_code else {'tlang': trans_code})
ecdc9049 3509 info['automatic_captions'] = automatic_captions
3510 info['subtitles'] = subtitles
7e72694b 3511
545cc85d 3512 parsed_url = compat_urllib_parse_urlparse(url)
3513 for component in [parsed_url.fragment, parsed_url.query]:
3514 query = compat_parse_qs(component)
3515 for k, v in query.items():
3516 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3517 d_k += '_time'
3518 if d_k not in info and k in s_ks:
3519 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3520
3521 # Youtube Music Auto-generated description
822b9d9c 3522 if video_description:
38d70284 3523 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 3524 if mobj:
822b9d9c
RA
3525 release_year = mobj.group('release_year')
3526 release_date = mobj.group('release_date')
3527 if release_date:
3528 release_date = release_date.replace('-', '')
3529 if not release_year:
545cc85d 3530 release_year = release_date[:4]
3531 info.update({
3532 'album': mobj.group('album'.strip()),
3533 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3534 'track': mobj.group('track').strip(),
3535 'release_date': release_date,
cc2db878 3536 'release_year': int_or_none(release_year),
545cc85d 3537 })
7e72694b 3538
545cc85d 3539 initial_data = None
3540 if webpage:
3541 initial_data = self._extract_yt_initial_variable(
3542 webpage, self._YT_INITIAL_DATA_RE, video_id,
3543 'yt initial data')
3544 if not initial_data:
99e9e001 3545 query = {'videoId': video_id}
3546 query.update(self._get_checkok_params())
109dd3b2 3547 initial_data = self._extract_response(
3548 item_id=video_id, ep='next', fatal=False,
99e9e001 3549 ytcfg=master_ytcfg, query=query,
3550 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3551 note='Downloading initial data API JSON')
545cc85d 3552
c60ee3a2 3553 try:
3554 # This will error if there is no livechat
3555 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3556 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3557 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3558 'video_id': video_id,
3559 'ext': 'json',
f6745c49 3560 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3561 }]
3562 except (KeyError, IndexError, TypeError):
3563 pass
545cc85d 3564
3565 if initial_data:
7c365c21 3566 info['chapters'] = (
3567 self._extract_chapters_from_json(initial_data, duration)
3568 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3569 or None)
545cc85d 3570
17322130 3571 contents = traverse_obj(
3572 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3573 expected_type=list, default=[])
3574
3575 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3576 if vpir:
3577 stl = vpir.get('superTitleLink')
3578 if stl:
3579 stl = self._get_text(stl)
3580 if try_get(
3581 vpir,
3582 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3583 info['location'] = stl
3584 else:
3585 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3586 if mobj:
545cc85d 3587 info.update({
17322130 3588 'series': mobj.group(1),
3589 'season_number': int(mobj.group(2)),
3590 'episode_number': int(mobj.group(3)),
545cc85d 3591 })
17322130 3592 for tlb in (try_get(
3593 vpir,
3594 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3595 list) or []):
3596 tbr = tlb.get('toggleButtonRenderer') or {}
3597 for getter, regex in [(
3598 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3599 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3600 lambda x: x['accessibility'],
3601 lambda x: x['accessibilityData']['accessibilityData'],
3602 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3603 label = (try_get(tbr, getter, dict) or {}).get('label')
3604 if label:
3605 mobj = re.match(regex, label)
3606 if mobj:
3607 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3608 break
17322130 3609 sbr_tooltip = try_get(
3610 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3611 if sbr_tooltip:
3612 like_count, dislike_count = sbr_tooltip.split(' / ')
3613 info.update({
3614 'like_count': str_to_int(like_count),
3615 'dislike_count': str_to_int(dislike_count),
3616 })
3617 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3618 if vsir:
3619 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3620 info.update({
3621 'channel': self._get_text(vor, 'title'),
3622 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3623
3624 rows = try_get(
3625 vsir,
3626 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3627 list) or []
3628 multiple_songs = False
3629 for row in rows:
3630 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3631 multiple_songs = True
3632 break
3633 for row in rows:
3634 mrr = row.get('metadataRowRenderer') or {}
3635 mrr_title = mrr.get('title')
3636 if not mrr_title:
3637 continue
3638 mrr_title = self._get_text(mrr, 'title')
3639 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3640 if mrr_title == 'License':
3641 info['license'] = mrr_contents_text
3642 elif not multiple_songs:
3643 if mrr_title == 'Album':
3644 info['album'] = mrr_contents_text
3645 elif mrr_title == 'Artist':
3646 info['artist'] = mrr_contents_text
3647 elif mrr_title == 'Song':
3648 info['track'] = mrr_contents_text
545cc85d 3649
3650 fallbacks = {
3651 'channel': 'uploader',
3652 'channel_id': 'uploader_id',
3653 'channel_url': 'uploader_url',
3654 }
992f9a73 3655
17322130 3656 # The upload date for scheduled, live and past live streams / premieres in microformats
3657 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3658 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3659 upload_date = (
3660 unified_strdate(get_first(microformats, 'uploadDate'))
3661 or unified_strdate(search_meta('uploadDate')))
3662 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3663 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3664 info['upload_date'] = upload_date
992f9a73 3665
545cc85d 3666 for to, frm in fallbacks.items():
3667 if not info.get(to):
3668 info[to] = info.get(frm)
3669
3670 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3671 v = info.get(s_k)
3672 if v:
3673 info[d_k] = v
b84071c0 3674
11f9be09 3675 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3676 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3677 is_membersonly = None
b28f8d24 3678 is_premium = None
c224251a
M
3679 if initial_data and is_private is not None:
3680 is_membersonly = False
b28f8d24 3681 is_premium = False
47193e02 3682 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3683 badge_labels = set()
3684 for content in contents:
3685 if not isinstance(content, dict):
3686 continue
3687 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3688 for badge_label in badge_labels:
3689 if badge_label.lower() == 'members only':
3690 is_membersonly = True
3691 elif badge_label.lower() == 'premium':
3692 is_premium = True
3693 elif badge_label.lower() == 'unlisted':
3694 is_unlisted = True
c224251a 3695
c224251a
M
3696 info['availability'] = self._availability(
3697 is_private=is_private,
b28f8d24 3698 needs_premium=is_premium,
c224251a
M
3699 needs_subscription=is_membersonly,
3700 needs_auth=info['age_limit'] >= 18,
3701 is_unlisted=None if is_private is None else is_unlisted)
3702
a2160aa4 3703 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3704
11f9be09 3705 self.mark_watched(video_id, player_responses)
d77ab8e2 3706
545cc85d 3707 return info
c5e8d7af 3708
a61fd4cf 3709
a6213a49 3710class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3711
182bda88 3712 @staticmethod
3713 def passthrough_smuggled_data(func):
3714 def _smuggle(entries, smuggled_data):
3715 for entry in entries:
3716 # TODO: Convert URL to music.youtube instead.
3717 # Do we need to passthrough any other smuggled_data?
3718 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3719 yield entry
3720
3721 @functools.wraps(func)
3722 def wrapper(self, url):
3723 url, smuggled_data = unsmuggle_url(url, {})
3724 if self.is_music_url(url):
3725 smuggled_data['is_music_url'] = True
3726 info_dict = func(self, url, smuggled_data)
3727 if smuggled_data and info_dict.get('entries'):
3728 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3729 return info_dict
3730 return wrapper
3731
a6213a49 3732 def _extract_channel_id(self, webpage):
3733 channel_id = self._html_search_meta(
3734 'channelId', webpage, 'channel id', default=None)
3735 if channel_id:
3736 return channel_id
3737 channel_url = self._html_search_meta(
3738 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3739 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3740 'twitter:app:url:googleplay'), webpage, 'channel url')
3741 return self._search_regex(
3742 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3743 channel_url, 'channel id')
15f6397c 3744
8bdd16b4 3745 @staticmethod
cd7c66cf 3746 def _extract_basic_item_renderer(item):
3747 # Modified from _extract_grid_item_renderer
201c1459 3748 known_basic_renderers = (
3749 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3750 )
3751 for key, renderer in item.items():
201c1459 3752 if not isinstance(renderer, dict):
cd7c66cf 3753 continue
201c1459 3754 elif key in known_basic_renderers:
3755 return renderer
3756 elif key.startswith('grid') and key.endswith('Renderer'):
3757 return renderer
8bdd16b4 3758
8bdd16b4 3759 def _grid_entries(self, grid_renderer):
3760 for item in grid_renderer['items']:
3761 if not isinstance(item, dict):
39b62db1 3762 continue
cd7c66cf 3763 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3764 if not isinstance(renderer, dict):
3765 continue
052e1350 3766 title = self._get_text(renderer, 'title')
fe93e2c4 3767
8bdd16b4 3768 # playlist
3769 playlist_id = renderer.get('playlistId')
3770 if playlist_id:
3771 yield self.url_result(
3772 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3773 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3774 video_title=title)
201c1459 3775 continue
8bdd16b4 3776 # video
3777 video_id = renderer.get('videoId')
3778 if video_id:
3779 yield self._extract_video(renderer)
201c1459 3780 continue
8bdd16b4 3781 # channel
3782 channel_id = renderer.get('channelId')
3783 if channel_id:
8bdd16b4 3784 yield self.url_result(
3785 'https://www.youtube.com/channel/%s' % channel_id,
3786 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3787 continue
3788 # generic endpoint URL support
3789 ep_url = urljoin('https://www.youtube.com/', try_get(
3790 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3791 compat_str))
3792 if ep_url:
3793 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3794 if ie.suitable(ep_url):
3795 yield self.url_result(
3796 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3797 break
8bdd16b4 3798
16aa9ea4 3799 def _music_reponsive_list_entry(self, renderer):
3800 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3801 if video_id:
3802 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3803 ie=YoutubeIE.ie_key(), video_id=video_id)
3804 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3805 if playlist_id:
3806 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3807 if video_id:
3808 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3809 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3810 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3811 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3812 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3813 if browse_id:
3814 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3815 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3816
3d3dddc9 3817 def _shelf_entries_from_content(self, shelf_renderer):
3818 content = shelf_renderer.get('content')
3819 if not isinstance(content, dict):
8bdd16b4 3820 return
cd7c66cf 3821 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3822 if renderer:
3823 # TODO: add support for nested playlists so each shelf is processed
3824 # as separate playlist
3825 # TODO: this includes only first N items
3826 for entry in self._grid_entries(renderer):
3827 yield entry
3828 renderer = content.get('horizontalListRenderer')
3829 if renderer:
3830 # TODO
3831 pass
8bdd16b4 3832
29f7c58a 3833 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3834 ep = try_get(
3835 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3836 compat_str)
3837 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3838 if shelf_url:
29f7c58a 3839 # Skipping links to another channels, note that checking for
3840 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3841 # will not work
3842 if skip_channels and '/channels?' in shelf_url:
3843 return
052e1350 3844 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3845 yield self.url_result(shelf_url, video_title=title)
3846 # Shelf may not contain shelf URL, fallback to extraction from content
3847 for entry in self._shelf_entries_from_content(shelf_renderer):
3848 yield entry
c5e8d7af 3849
8bdd16b4 3850 def _playlist_entries(self, video_list_renderer):
3851 for content in video_list_renderer['contents']:
3852 if not isinstance(content, dict):
3853 continue
3854 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3855 if not isinstance(renderer, dict):
3856 continue
3857 video_id = renderer.get('videoId')
3858 if not video_id:
3859 continue
3860 yield self._extract_video(renderer)
07aeced6 3861
3462ffa8 3862 def _rich_entries(self, rich_grid_renderer):
3863 renderer = try_get(
70d5c17b 3864 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3865 video_id = renderer.get('videoId')
3866 if not video_id:
3867 return
3868 yield self._extract_video(renderer)
3869
8bdd16b4 3870 def _video_entry(self, video_renderer):
3871 video_id = video_renderer.get('videoId')
3872 if video_id:
3873 return self._extract_video(video_renderer)
dacb3a86 3874
8bdd16b4 3875 def _post_thread_entries(self, post_thread_renderer):
3876 post_renderer = try_get(
3877 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3878 if not post_renderer:
3879 return
3880 # video attachment
3881 video_renderer = try_get(
895b0931 3882 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3883 video_id = video_renderer.get('videoId')
3884 if video_id:
3885 entry = self._extract_video(video_renderer)
8bdd16b4 3886 if entry:
3887 yield entry
895b0931 3888 # playlist attachment
3889 playlist_id = try_get(
3890 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3891 if playlist_id:
3892 yield self.url_result(
e28f1c0a 3893 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3894 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3895 # inline video links
3896 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3897 for run in runs:
3898 if not isinstance(run, dict):
3899 continue
3900 ep_url = try_get(
3901 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3902 if not ep_url:
3903 continue
3904 if not YoutubeIE.suitable(ep_url):
3905 continue
3906 ep_video_id = YoutubeIE._match_id(ep_url)
3907 if video_id == ep_video_id:
3908 continue
895b0931 3909 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3910
8bdd16b4 3911 def _post_thread_continuation_entries(self, post_thread_continuation):
3912 contents = post_thread_continuation.get('contents')
3913 if not isinstance(contents, list):
3914 return
3915 for content in contents:
3916 renderer = content.get('backstagePostThreadRenderer')
3917 if not isinstance(renderer, dict):
3918 continue
3919 for entry in self._post_thread_entries(renderer):
3920 yield entry
07aeced6 3921
39ed931e 3922 r''' # unused
3923 def _rich_grid_entries(self, contents):
3924 for content in contents:
3925 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3926 if video_renderer:
3927 entry = self._video_entry(video_renderer)
3928 if entry:
3929 yield entry
3930 '''
a6213a49 3931 def _extract_entries(self, parent_renderer, continuation_list):
3932 # continuation_list is modified in-place with continuation_list = [continuation_token]
3933 continuation_list[:] = [None]
3934 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3935 for content in contents:
3936 if not isinstance(content, dict):
3937 continue
16aa9ea4 3938 is_renderer = traverse_obj(
3939 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3940 expected_type=dict)
a6213a49 3941 if not is_renderer:
3942 renderer = content.get('richItemRenderer')
3943 if renderer:
3944 for entry in self._rich_entries(renderer):
3945 yield entry
3946 continuation_list[0] = self._extract_continuation(parent_renderer)
3947 continue
3948 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3949 for isr_content in isr_contents:
3950 if not isinstance(isr_content, dict):
8bdd16b4 3951 continue
69184e41 3952
a6213a49 3953 known_renderers = {
3954 'playlistVideoListRenderer': self._playlist_entries,
3955 'gridRenderer': self._grid_entries,
3956 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3957 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3958 'backstagePostThreadRenderer': self._post_thread_entries,
3959 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3960 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3961 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3962 }
3963 for key, renderer in isr_content.items():
3964 if key not in known_renderers:
3965 continue
3966 for entry in known_renderers[key](renderer):
3967 if entry:
3968 yield entry
3969 continuation_list[0] = self._extract_continuation(renderer)
3970 break
70d5c17b 3971
3972 if not continuation_list[0]:
a6213a49 3973 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3974
a6213a49 3975 if not continuation_list[0]:
3976 continuation_list[0] = self._extract_continuation(parent_renderer)
3977
3978 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3979 continuation_list = [None]
3980 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3981 tab_content = try_get(tab, lambda x: x['content'], dict)
3982 if not tab_content:
3983 return
3462ffa8 3984 parent_renderer = (
29f7c58a 3985 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3986 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3987 for entry in extract_entries(parent_renderer):
3988 yield entry
3462ffa8 3989 continuation = continuation_list[0]
d069eca7 3990
8bdd16b4 3991 for page_num in itertools.count(1):
3992 if not continuation:
3993 break
99e9e001 3994 headers = self.generate_api_headers(
3995 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3996 response = self._extract_response(
3997 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3998 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3999 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4000
4001 if not response:
8bdd16b4 4002 break
ac56cf38 4003 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4004 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4005 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4006
69184e41 4007 known_continuation_renderers = {
4008 'playlistVideoListContinuation': self._playlist_entries,
4009 'gridContinuation': self._grid_entries,
4010 'itemSectionContinuation': self._post_thread_continuation_entries,
4011 'sectionListContinuation': extract_entries, # for feeds
4012 }
8bdd16b4 4013 continuation_contents = try_get(
69184e41 4014 response, lambda x: x['continuationContents'], dict) or {}
4015 continuation_renderer = None
4016 for key, value in continuation_contents.items():
4017 if key not in known_continuation_renderers:
3462ffa8 4018 continue
69184e41 4019 continuation_renderer = value
4020 continuation_list = [None]
4021 for entry in known_continuation_renderers[key](continuation_renderer):
4022 yield entry
4023 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4024 break
4025 if continuation_renderer:
4026 continue
c5e8d7af 4027
a1b535bd 4028 known_renderers = {
4029 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4030 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4031 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4032 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4033 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4034 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4035 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4036 }
cce889b9 4037 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4038 continuation_items = try_get(
cce889b9 4039 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4040 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4041 video_items_renderer = None
4042 for key, value in continuation_item.items():
4043 if key not in known_renderers:
8bdd16b4 4044 continue
a1b535bd 4045 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4046 continuation_list = [None]
a1b535bd 4047 for entry in known_renderers[key][0](video_items_renderer):
4048 yield entry
9ba5705a 4049 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4050 break
4051 if video_items_renderer:
4052 continue
8bdd16b4 4053 break
9558dcec 4054
8bdd16b4 4055 @staticmethod
7c219ea6 4056 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4057 for tab in tabs:
cd684175 4058 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4059 if renderer.get('selected') is True:
4060 return renderer
2b3c2546 4061 else:
7c219ea6 4062 if fatal:
4063 raise ExtractorError('Unable to find selected tab')
b82f815f 4064
47193e02 4065 @classmethod
4066 def _extract_uploader(cls, data):
8bdd16b4 4067 uploader = {}
47193e02 4068 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4069 owner = try_get(
4070 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4071 if owner:
4072 uploader['uploader'] = owner.get('text')
4073 uploader['uploader_id'] = try_get(
4074 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4075 uploader['uploader_url'] = urljoin(
4076 'https://www.youtube.com/',
4077 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4078 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4079
ac56cf38 4080 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4081 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4082 tags = []
b60419c5 4083
8bdd16b4 4084 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4085 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4086 renderer = try_get(
4087 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4088 if renderer:
b60419c5 4089 channel_name = renderer.get('title')
4090 channel_url = renderer.get('channelUrl')
4091 channel_id = renderer.get('externalId')
39ed931e 4092 else:
64c0d954 4093 renderer = try_get(
4094 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4095
8bdd16b4 4096 if renderer:
4097 title = renderer.get('title')
ecc97af3 4098 description = renderer.get('description', '')
b60419c5 4099 playlist_id = channel_id
4100 tags = renderer.get('keywords', '').split()
b60419c5 4101
301d07fc 4102 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4103 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4104 def _get_uncropped(url):
4105 return url_or_none((url or '').split('=')[0] + '=s0')
4106
4107 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4108 if avatar_thumbnails:
4109 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4110 if uncropped_avatar:
4111 avatar_thumbnails.append({
4112 'url': uncropped_avatar,
4113 'id': 'avatar_uncropped',
4114 'preference': 1
4115 })
4116
4117 channel_banners = self._extract_thumbnails(
4118 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4119 for banner in channel_banners:
4120 banner['preference'] = -10
4121
4122 if channel_banners:
4123 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4124 if uncropped_banner:
4125 channel_banners.append({
4126 'url': uncropped_banner,
4127 'id': 'banner_uncropped',
4128 'preference': -5
4129 })
4130
4131 primary_thumbnails = self._extract_thumbnails(
4132 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4133
3462ffa8 4134 if playlist_id is None:
70d5c17b 4135 playlist_id = item_id
f0d785d3 4136
4137 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4138 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4139 if title is None:
f0d785d3 4140 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4141 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4142 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4143
b60419c5 4144 metadata = {
4145 'playlist_id': playlist_id,
4146 'playlist_title': title,
4147 'playlist_description': description,
4148 'uploader': channel_name,
4149 'uploader_id': channel_id,
4150 'uploader_url': channel_url,
301d07fc 4151 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4152 'tags': tags,
f0d785d3 4153 'view_count': self._get_count(playlist_stats, 1),
4154 'availability': self._extract_availability(data),
4155 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4156 'playlist_count': self._get_count(playlist_stats, 0),
4157 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4158 }
4159 if not channel_id:
4160 metadata.update(self._extract_uploader(data))
4161 metadata.update({
4162 'channel': metadata['uploader'],
4163 'channel_id': metadata['uploader_id'],
4164 'channel_url': metadata['uploader_url']})
4165 return self.playlist_result(
d069eca7 4166 self._entries(
ac56cf38 4167 selected_tab, playlist_id, ytcfg,
4168 self._extract_account_syncid(ytcfg, data),
4169 self._extract_visitor_data(data, ytcfg)),
b60419c5 4170 **metadata)
73c4ac2c 4171
ac56cf38 4172 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4173 first_id = last_id = response = None
2be71994 4174 for page_num in itertools.count(1):
cd7c66cf 4175 videos = list(self._playlist_entries(playlist))
4176 if not videos:
4177 return
2be71994 4178 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4179 if start >= len(videos):
4180 return
4181 for video in videos[start:]:
4182 if video['id'] == first_id:
4183 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4184 return
4185 yield video
4186 first_id = first_id or videos[0]['id']
4187 last_id = videos[-1]['id']
79360d99 4188 watch_endpoint = try_get(
4189 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4190 headers = self.generate_api_headers(
4191 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4192 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4193 query = {
4194 'playlistId': playlist_id,
4195 'videoId': watch_endpoint.get('videoId') or last_id,
4196 'index': watch_endpoint.get('index') or len(videos),
4197 'params': watch_endpoint.get('params') or 'OAE%3D'
4198 }
4199 response = self._extract_response(
4200 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4201 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4202 check_get_keys='contents'
4203 )
cd7c66cf 4204 playlist = try_get(
79360d99 4205 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4206
ac56cf38 4207 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4208 title = playlist.get('title') or try_get(
4209 data, lambda x: x['titleText']['simpleText'], compat_str)
4210 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4211
4212 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4213 playlist_url = urljoin(url, try_get(
4214 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4215 compat_str))
4216 if playlist_url and playlist_url != url:
4217 return self.url_result(
4218 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4219 video_title=title)
cd7c66cf 4220
8bdd16b4 4221 return self.playlist_result(
ac56cf38 4222 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4223 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4224
47193e02 4225 def _extract_availability(self, data):
4226 """
4227 Gets the availability of a given playlist/tab.
4228 Note: Unless YouTube tells us explicitly, we do not assume it is public
4229 @param data: response
4230 """
4231 is_private = is_unlisted = None
4232 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4233 badge_labels = self._extract_badges(renderer)
4234
4235 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4236 privacy_dropdown_entries = try_get(
4237 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4238 for renderer_dict in privacy_dropdown_entries:
4239 is_selected = try_get(
4240 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4241 if not is_selected:
4242 continue
052e1350 4243 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4244 if label:
4245 badge_labels.add(label.lower())
4246 break
4247
4248 for badge_label in badge_labels:
4249 if badge_label == 'unlisted':
4250 is_unlisted = True
4251 elif badge_label == 'private':
4252 is_private = True
4253 elif badge_label == 'public':
4254 is_unlisted = is_private = False
4255 return self._availability(is_private, False, False, False, is_unlisted)
4256
4257 @staticmethod
4258 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4259 sidebar_renderer = try_get(
4260 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4261 for item in sidebar_renderer:
4262 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4263 if renderer:
4264 return renderer
4265
ac56cf38 4266 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4267 """
4268 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4269 """
5d342002 4270 browse_id = params = None
47193e02 4271 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4272 if not renderer:
4273 return
4274 menu_renderer = try_get(
4275 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4276 for menu_item in menu_renderer:
4277 if not isinstance(menu_item, dict):
358de58c 4278 continue
47193e02 4279 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4280 text = try_get(
4281 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4282 if not text or text.lower() != 'show unavailable videos':
4283 continue
4284 browse_endpoint = try_get(
4285 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4286 browse_id = browse_endpoint.get('browseId')
4287 params = browse_endpoint.get('params')
4288 break
5d342002 4289
11f9be09 4290 headers = self.generate_api_headers(
99e9e001 4291 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4292 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4293 query = {
4294 'params': params or 'wgYCCAA=',
4295 'browseId': browse_id or 'VL%s' % item_id
4296 }
4297 return self._extract_response(
4298 item_id=item_id, headers=headers, query=query,
fe93e2c4 4299 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4300 note='Downloading API JSON with unavailable videos')
358de58c 4301
ac56cf38 4302 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4303 retries = self.get_param('extractor_retries', 3)
62bff2c1 4304 count = -1
ac56cf38 4305 webpage = data = last_error = None
14fdfea9 4306 while count < retries:
62bff2c1 4307 count += 1
14fdfea9 4308 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4309 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4310 if last_error:
c705177d 4311 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4312 try:
4313 webpage = self._download_webpage(
4314 url, item_id,
4315 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4316 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4317 except ExtractorError as e:
4318 if isinstance(e.cause, network_exceptions):
4319 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4320 last_error = error_to_compat_str(e.cause or e.msg)
4321 if count < retries:
4322 continue
4323 if fatal:
4324 raise
4325 self.report_warning(error_to_compat_str(e))
14fdfea9 4326 break
ac56cf38 4327 else:
4328 try:
4329 self._extract_and_report_alerts(data)
4330 except ExtractorError as e:
4331 if fatal:
4332 raise
4333 self.report_warning(error_to_compat_str(e))
4334 break
4335
7c219ea6 4336 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4337 break
4338
4339 last_error = 'Incomplete yt initial data received'
4340 if count >= retries:
4341 if fatal:
4342 raise ExtractorError(last_error)
4343 self.report_warning(last_error)
4344 break
4345
cd7c66cf 4346 return webpage, data
4347
ac56cf38 4348 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4349 data = None
4350 if 'webpage' not in self._configuration_arg('skip'):
4351 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4352 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4353 # Reject webpage data if redirected to home page without explicitly requesting
4354 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4355 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4356 if (url != 'https://www.youtube.com/feed/recommended'
4357 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4358 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4359 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4360 if fatal:
4361 raise ExtractorError(msg, expected=True)
4362 self.report_warning(msg, only_once=True)
ac56cf38 4363 if not data:
4364 if not ytcfg and self.is_authenticated:
4365 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4366 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4367 raise ExtractorError(
4368 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4369 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4370 expected=True)
4371 self.report_warning(msg, only_once=True)
4372 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4373 return data, ytcfg
4374
4375 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4376 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4377 resolve_response = self._extract_response(
4378 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4379 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4380 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4381 for ep_key, ep in endpoints.items():
4382 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4383 if params:
4384 return self._extract_response(
4385 item_id=item_id, query=params, ep=ep, headers=headers,
4386 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4387 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4388 err_note = 'Failed to resolve url (does the playlist exist?)'
4389 if fatal:
4390 raise ExtractorError(err_note, expected=True)
4391 self.report_warning(err_note, item_id)
4392
a6213a49 4393 _SEARCH_PARAMS = None
4394
af5c1c55 4395 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4396 data = {'query': query}
4397 if params is NO_DEFAULT:
4398 params = self._SEARCH_PARAMS
4399 if params:
4400 data['params'] = params
16aa9ea4 4401
4402 content_keys = (
4403 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4404 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4405 # ytmusic search
4406 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4407 ('continuationContents', ),
4408 )
4409 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4410
a61fd4cf 4411 continuation_list = [None]
a6213a49 4412 for page_num in itertools.count(1):
a61fd4cf 4413 data.update(continuation_list[0] or {})
a6213a49 4414 search = self._extract_response(
4415 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4416 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4417 slr_contents = traverse_obj(search, *content_keys)
4418 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4419 if not continuation_list[0]:
a6213a49 4420 break
4421
4422
4423class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4424 IE_DESC = 'YouTube Tabs'
4425 _VALID_URL = r'''(?x:
4426 https?://
4427 (?:\w+\.)?
4428 (?:
4429 youtube(?:kids)?\.com|
4430 %(invidious)s
4431 )/
4432 (?:
4433 (?P<channel_type>channel|c|user|browse)/|
4434 (?P<not_channel>
4435 feed/|hashtag/|
4436 (?:playlist|watch)\?.*?\blist=
4437 )|
4438 (?!(?:%(reserved_names)s)\b) # Direct URLs
4439 )
4440 (?P<id>[^/?\#&]+)
4441 )''' % {
4442 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4443 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4444 }
4445 IE_NAME = 'youtube:tab'
4446
4447 _TESTS = [{
4448 'note': 'playlists, multipage',
4449 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4450 'playlist_mincount': 94,
4451 'info_dict': {
4452 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4453 'title': 'Igor Kleiner - Playlists',
a6213a49 4454 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4455 'uploader': 'Igor Kleiner',
a6213a49 4456 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4457 'channel': 'Igor Kleiner',
4458 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4459 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4460 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4461 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4462 'channel_follower_count': int
a6213a49 4463 },
4464 }, {
4465 'note': 'playlists, multipage, different order',
4466 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4467 'playlist_mincount': 94,
4468 'info_dict': {
4469 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4470 'title': 'Igor Kleiner - Playlists',
a6213a49 4471 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4472 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4473 'uploader': 'Igor Kleiner',
4474 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4475 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4476 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4477 'channel': 'Igor Kleiner',
4478 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4479 'channel_follower_count': int
a6213a49 4480 },
4481 }, {
4482 'note': 'playlists, series',
4483 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4484 'playlist_mincount': 5,
4485 'info_dict': {
4486 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4487 'title': '3Blue1Brown - Playlists',
4488 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4489 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4490 'uploader': '3Blue1Brown',
976ae3ea 4491 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4492 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4493 'channel': '3Blue1Brown',
4494 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4495 'tags': ['Mathematics'],
6c73052c 4496 'channel_follower_count': int
a6213a49 4497 },
4498 }, {
4499 'note': 'playlists, singlepage',
4500 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4501 'playlist_mincount': 4,
4502 'info_dict': {
4503 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4504 'title': 'ThirstForScience - Playlists',
4505 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4506 'uploader': 'ThirstForScience',
4507 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4508 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4509 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4510 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4511 'tags': 'count:13',
4512 'channel': 'ThirstForScience',
6c73052c 4513 'channel_follower_count': int
a6213a49 4514 }
4515 }, {
4516 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4517 'only_matching': True,
4518 }, {
4519 'note': 'basic, single video playlist',
4520 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4521 'info_dict': {
4522 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4523 'uploader': 'Sergey M.',
4524 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4525 'title': 'youtube-dl public playlist',
976ae3ea 4526 'description': '',
4527 'tags': [],
4528 'view_count': int,
4529 'modified_date': '20201130',
4530 'channel': 'Sergey M.',
4531 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4532 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4533 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4534 },
4535 'playlist_count': 1,
4536 }, {
4537 'note': 'empty playlist',
4538 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4539 'info_dict': {
4540 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4541 'uploader': 'Sergey M.',
4542 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4543 'title': 'youtube-dl empty playlist',
976ae3ea 4544 'tags': [],
4545 'channel': 'Sergey M.',
4546 'description': '',
4547 'modified_date': '20160902',
4548 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4549 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4550 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4551 },
4552 'playlist_count': 0,
4553 }, {
4554 'note': 'Home tab',
4555 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4556 'info_dict': {
4557 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4558 'title': 'lex will - Home',
4559 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4560 'uploader': 'lex will',
4561 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4562 'channel': 'lex will',
4563 'tags': ['bible', 'history', 'prophesy'],
4564 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4565 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4566 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4567 'channel_follower_count': int
a6213a49 4568 },
4569 'playlist_mincount': 2,
4570 }, {
4571 'note': 'Videos tab',
4572 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4573 'info_dict': {
4574 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4575 'title': 'lex will - Videos',
4576 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4577 'uploader': 'lex will',
4578 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4579 'tags': ['bible', 'history', 'prophesy'],
4580 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4581 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4582 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4583 'channel': 'lex will',
6c73052c 4584 'channel_follower_count': int
a6213a49 4585 },
4586 'playlist_mincount': 975,
4587 }, {
4588 'note': 'Videos tab, sorted by popular',
4589 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4590 'info_dict': {
4591 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4592 'title': 'lex will - Videos',
4593 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4594 'uploader': 'lex will',
4595 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4596 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4597 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4598 'channel': 'lex will',
4599 'tags': ['bible', 'history', 'prophesy'],
4600 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4601 'channel_follower_count': int
a6213a49 4602 },
4603 'playlist_mincount': 199,
4604 }, {
4605 'note': 'Playlists tab',
4606 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4607 'info_dict': {
4608 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4609 'title': 'lex will - Playlists',
4610 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4611 'uploader': 'lex will',
4612 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4613 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4614 'channel': 'lex will',
4615 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4616 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4617 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4618 'channel_follower_count': int
a6213a49 4619 },
4620 'playlist_mincount': 17,
4621 }, {
4622 'note': 'Community tab',
4623 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4624 'info_dict': {
4625 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4626 'title': 'lex will - Community',
4627 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4628 'uploader': 'lex will',
4629 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4630 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4631 'channel': 'lex will',
4632 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4633 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4634 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4635 'channel_follower_count': int
a6213a49 4636 },
4637 'playlist_mincount': 18,
4638 }, {
4639 'note': 'Channels tab',
4640 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4641 'info_dict': {
4642 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4643 'title': 'lex will - Channels',
4644 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4645 'uploader': 'lex will',
4646 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4647 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4648 'channel': 'lex will',
4649 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4650 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4651 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4652 'channel_follower_count': int
a6213a49 4653 },
4654 'playlist_mincount': 12,
4655 }, {
4656 'note': 'Search tab',
4657 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4658 'playlist_mincount': 40,
4659 'info_dict': {
4660 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4661 'title': '3Blue1Brown - Search - linear algebra',
4662 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4663 'uploader': '3Blue1Brown',
4664 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4665 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4666 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4667 'tags': ['Mathematics'],
4668 'channel': '3Blue1Brown',
4669 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4670 'channel_follower_count': int
a6213a49 4671 },
4672 }, {
4673 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4674 'only_matching': True,
4675 }, {
4676 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4677 'only_matching': True,
4678 }, {
4679 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4680 'only_matching': True,
4681 }, {
4682 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4683 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4684 'info_dict': {
4685 'title': '29C3: Not my department',
4686 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4687 'uploader': 'Christiaan008',
4688 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4689 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4690 'tags': [],
4691 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4692 'view_count': int,
4693 'modified_date': '20150605',
4694 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4695 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4696 'channel': 'Christiaan008',
a6213a49 4697 },
4698 'playlist_count': 96,
4699 }, {
4700 'note': 'Large playlist',
4701 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4702 'info_dict': {
4703 'title': 'Uploads from Cauchemar',
4704 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4705 'uploader': 'Cauchemar',
4706 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4707 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4708 'tags': [],
4709 'modified_date': r're:\d{8}',
4710 'channel': 'Cauchemar',
4711 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4712 'view_count': int,
4713 'description': '',
4714 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4715 },
4716 'playlist_mincount': 1123,
976ae3ea 4717 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4718 }, {
4719 'note': 'even larger playlist, 8832 videos',
4720 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4721 'only_matching': True,
4722 }, {
4723 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4724 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4725 'info_dict': {
4726 'title': 'Uploads from Interstellar Movie',
4727 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4728 'uploader': 'Interstellar Movie',
4729 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4730 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4731 'tags': [],
4732 'view_count': int,
4733 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4734 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4735 'channel': 'Interstellar Movie',
4736 'description': '',
4737 'modified_date': r're:\d{8}',
a6213a49 4738 },
4739 'playlist_mincount': 21,
4740 }, {
4741 'note': 'Playlist with "show unavailable videos" button',
4742 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4743 'info_dict': {
4744 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4745 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4746 'uploader': 'Phim Siêu Nhân Nhật Bản',
4747 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4748 'view_count': int,
4749 'channel': 'Phim Siêu Nhân Nhật Bản',
4750 'tags': [],
4751 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4752 'description': '',
4753 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4754 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4755 'modified_date': r're:\d{8}',
a6213a49 4756 },
4757 'playlist_mincount': 200,
976ae3ea 4758 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4759 }, {
4760 'note': 'Playlist with unavailable videos in page 7',
4761 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4762 'info_dict': {
4763 'title': 'Uploads from BlankTV',
4764 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4765 'uploader': 'BlankTV',
4766 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4767 'channel': 'BlankTV',
4768 'channel_url': 'https://www.youtube.com/c/blanktv',
4769 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4770 'view_count': int,
4771 'tags': [],
4772 'uploader_url': 'https://www.youtube.com/c/blanktv',
4773 'modified_date': r're:\d{8}',
4774 'description': '',
a6213a49 4775 },
4776 'playlist_mincount': 1000,
976ae3ea 4777 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4778 }, {
4779 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4780 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4781 'info_dict': {
4782 'title': 'Data Analysis with Dr Mike Pound',
4783 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4784 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4785 'uploader': 'Computerphile',
4786 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4787 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4788 'tags': [],
4789 'view_count': int,
4790 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4791 'channel_url': 'https://www.youtube.com/user/Computerphile',
4792 'channel': 'Computerphile',
a6213a49 4793 },
4794 'playlist_mincount': 11,
4795 }, {
4796 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4797 'only_matching': True,
4798 }, {
4799 'note': 'Playlist URL that does not actually serve a playlist',
4800 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4801 'info_dict': {
4802 'id': 'FqZTN594JQw',
4803 'ext': 'webm',
4804 'title': "Smiley's People 01 detective, Adventure Series, Action",
4805 'uploader': 'STREEM',
4806 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4807 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4808 'upload_date': '20150526',
4809 'license': 'Standard YouTube License',
4810 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4811 'categories': ['People & Blogs'],
4812 'tags': list,
4813 'view_count': int,
4814 'like_count': int,
a6213a49 4815 },
4816 'params': {
4817 'skip_download': True,
4818 },
4819 'skip': 'This video is not available.',
4820 'add_ie': [YoutubeIE.ie_key()],
4821 }, {
4822 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4823 'only_matching': True,
4824 }, {
4825 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4826 'only_matching': True,
4827 }, {
4828 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4829 'info_dict': {
6c73052c 4830 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4831 'ext': 'mp4',
976ae3ea 4832 'title': str,
a6213a49 4833 'uploader': 'Sky News',
4834 'uploader_id': 'skynews',
4835 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4836 'upload_date': r're:\d{8}',
976ae3ea 4837 'description': str,
a6213a49 4838 'categories': ['News & Politics'],
4839 'tags': list,
4840 'like_count': int,
6c73052c 4841 'release_timestamp': 1642502819,
976ae3ea 4842 'channel': 'Sky News',
4843 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4844 'age_limit': 0,
4845 'view_count': int,
6c73052c 4846 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4847 'playable_in_embed': True,
6c73052c 4848 'release_date': '20220118',
976ae3ea 4849 'availability': 'public',
4850 'live_status': 'is_live',
4851 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4852 'channel_follower_count': int
a6213a49 4853 },
4854 'params': {
4855 'skip_download': True,
4856 },
976ae3ea 4857 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4858 }, {
4859 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4860 'info_dict': {
4861 'id': 'a48o2S1cPoo',
4862 'ext': 'mp4',
4863 'title': 'The Young Turks - Live Main Show',
4864 'uploader': 'The Young Turks',
4865 'uploader_id': 'TheYoungTurks',
4866 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4867 'upload_date': '20150715',
4868 'license': 'Standard YouTube License',
4869 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4870 'categories': ['News & Politics'],
4871 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4872 'like_count': int,
a6213a49 4873 },
4874 'params': {
4875 'skip_download': True,
4876 },
4877 'only_matching': True,
4878 }, {
4879 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4880 'only_matching': True,
4881 }, {
4882 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4883 'only_matching': True,
4884 }, {
4885 'note': 'A channel that is not live. Should raise error',
4886 'url': 'https://www.youtube.com/user/numberphile/live',
4887 'only_matching': True,
4888 }, {
4889 'url': 'https://www.youtube.com/feed/trending',
4890 'only_matching': True,
4891 }, {
4892 'url': 'https://www.youtube.com/feed/library',
4893 'only_matching': True,
4894 }, {
4895 'url': 'https://www.youtube.com/feed/history',
4896 'only_matching': True,
4897 }, {
4898 'url': 'https://www.youtube.com/feed/subscriptions',
4899 'only_matching': True,
4900 }, {
4901 'url': 'https://www.youtube.com/feed/watch_later',
4902 'only_matching': True,
4903 }, {
4904 'note': 'Recommended - redirects to home page.',
4905 'url': 'https://www.youtube.com/feed/recommended',
4906 'only_matching': True,
4907 }, {
4908 'note': 'inline playlist with not always working continuations',
4909 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4910 'only_matching': True,
4911 }, {
4912 'url': 'https://www.youtube.com/course',
4913 'only_matching': True,
4914 }, {
4915 'url': 'https://www.youtube.com/zsecurity',
4916 'only_matching': True,
4917 }, {
4918 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4919 'only_matching': True,
4920 }, {
4921 'url': 'https://www.youtube.com/TheYoungTurks/live',
4922 'only_matching': True,
4923 }, {
4924 'url': 'https://www.youtube.com/hashtag/cctv9',
4925 'info_dict': {
4926 'id': 'cctv9',
4927 'title': '#cctv9',
976ae3ea 4928 'tags': [],
a6213a49 4929 },
4930 'playlist_mincount': 350,
4931 }, {
4932 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4933 'only_matching': True,
4934 }, {
4935 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4936 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4937 'only_matching': True
4938 }, {
4939 'note': '/browse/ should redirect to /channel/',
4940 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4941 'only_matching': True
4942 }, {
4943 'note': 'VLPL, should redirect to playlist?list=PL...',
4944 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4945 'info_dict': {
4946 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4947 'uploader': 'NoCopyrightSounds',
4948 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4949 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4950 'title': 'NCS Releases',
976ae3ea 4951 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4952 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4953 'modified_date': r're:\d{8}',
4954 'view_count': int,
4955 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4956 'tags': [],
4957 'channel': 'NoCopyrightSounds',
a6213a49 4958 },
4959 'playlist_mincount': 166,
976ae3ea 4960 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4961 }, {
4962 'note': 'Topic, should redirect to playlist?list=UU...',
4963 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4964 'info_dict': {
4965 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4966 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4967 'title': 'Uploads from Royalty Free Music - Topic',
4968 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4969 'tags': [],
4970 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4971 'channel': 'Royalty Free Music - Topic',
4972 'view_count': int,
4973 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4974 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4975 'modified_date': r're:\d{8}',
4976 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4977 'description': '',
a6213a49 4978 },
4979 'expected_warnings': [
a6213a49 4980 'The URL does not have a videos tab',
976ae3ea 4981 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4982 ],
4983 'playlist_mincount': 101,
4984 }, {
4985 'note': 'Topic without a UU playlist',
4986 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4987 'info_dict': {
4988 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4989 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4990 'tags': [],
a6213a49 4991 },
4992 'expected_warnings': [
976ae3ea 4993 'the playlist redirect gave error',
a6213a49 4994 ],
4995 'playlist_mincount': 9,
4996 }, {
4997 'note': 'Youtube music Album',
4998 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4999 'info_dict': {
5000 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5001 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5002 'tags': [],
5003 'view_count': int,
5004 'description': '',
5005 'availability': 'unlisted',
5006 'modified_date': r're:\d{8}',
a6213a49 5007 },
5008 'playlist_count': 50,
5009 }, {
5010 'note': 'unlisted single video playlist',
5011 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5012 'info_dict': {
5013 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5014 'uploader': 'colethedj',
5015 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5016 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5017 'availability': 'unlisted',
5018 'tags': [],
5019 'modified_date': '20211208',
5020 'channel': 'colethedj',
5021 'view_count': int,
5022 'description': '',
5023 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5024 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5025 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5026 },
5027 'playlist_count': 1,
5028 }, {
5029 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5030 'url': 'https://www.youtube.com/feed/recommended',
5031 'info_dict': {
5032 'id': 'recommended',
5033 'title': 'recommended',
6c73052c 5034 'tags': [],
a6213a49 5035 },
5036 'playlist_mincount': 50,
5037 'params': {
5038 'skip_download': True,
5039 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5040 },
5041 }, {
5042 'note': 'API Fallback: /videos tab, sorted by oldest first',
5043 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5044 'info_dict': {
5045 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5046 'title': 'Cody\'sLab - Videos',
5047 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5048 'uploader': 'Cody\'sLab',
5049 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5050 'channel': 'Cody\'sLab',
5051 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5052 'tags': [],
5053 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5054 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5055 'channel_follower_count': int
a6213a49 5056 },
5057 'playlist_mincount': 650,
5058 'params': {
5059 'skip_download': True,
5060 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5061 },
5062 }, {
5063 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5064 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5065 'info_dict': {
5066 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5067 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5068 'title': 'Uploads from Royalty Free Music - Topic',
5069 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5070 'modified_date': r're:\d{8}',
5071 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5072 'description': '',
5073 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5074 'tags': [],
5075 'channel': 'Royalty Free Music - Topic',
5076 'view_count': int,
5077 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5078 },
5079 'expected_warnings': [
976ae3ea 5080 'does not have a videos tab',
5081 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5082 ],
5083 'playlist_mincount': 101,
5084 'params': {
5085 'skip_download': True,
5086 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5087 },
7c219ea6 5088 }, {
5089 'note': 'non-standard redirect to regional channel',
5090 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5091 'only_matching': True
a6213a49 5092 }]
5093
5094 @classmethod
5095 def suitable(cls, url):
5096 return False if YoutubeIE.suitable(url) else super(
5097 YoutubeTabIE, cls).suitable(url)
9297939e 5098
64f36541 5099 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5100
182bda88 5101 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5102 def _real_extract(self, url, smuggled_data):
cd7c66cf 5103 item_id = self._match_id(url)
5104 url = compat_urlparse.urlunparse(
5105 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5106 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5107
fe03a6cd 5108 def get_mobj(url):
37e57a9f 5109 mobj = self._URL_RE.match(url).groupdict()
07cce701 5110 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5111 return mobj
5112
37e57a9f 5113 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5114 # Youtube returns incomplete data if tabname is not lower case
5115 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5116 if is_channel:
5117 if smuggled_data.get('is_music_url'):
37e57a9f 5118 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5119 item_id = item_id[2:]
37e57a9f 5120 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5121 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5122 mdata = self._extract_tab_endpoint(
37e57a9f 5123 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5124 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5125 get_all=False, expected_type=compat_str)
ac56cf38 5126 if not murl:
37e57a9f 5127 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5128 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5129 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5130 pre = f'https://www.youtube.com/channel/{item_id}'
5131
64f36541 5132 original_tab_name = tab
fe03a6cd 5133 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5134 # Home URLs should redirect to /videos/
37e57a9f 5135 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5136 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5137 tab = '/videos'
5138
5139 url = ''.join((pre, tab, post))
5140 mobj = get_mobj(url)
cd7c66cf 5141
5142 # Handle both video/playlist URLs
201c1459 5143 qs = parse_qs(url)
37e57a9f 5144 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5145
fe03a6cd 5146 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5147 if not playlist_id:
fe03a6cd 5148 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5149 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5150 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5151 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5152 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5153 mobj = get_mobj(url)
cd7c66cf 5154
5155 if video_id and playlist_id:
a06916d9 5156 if self.get_param('noplaylist'):
37e57a9f 5157 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5158 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5159 ie=YoutubeIE.ie_key(), video_id=video_id)
5160 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5161
ac56cf38 5162 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5163
7c219ea6 5164 # YouTube may provide a non-standard redirect to the regional channel
5165 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5166 redirect_url = traverse_obj(
5167 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5168 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5169 redirect_url = ''.join((
5170 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5171 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5172 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5173
37e57a9f 5174 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5175 if tabs:
5176 selected_tab = self._extract_selected_tab(tabs)
64f36541 5177 selected_tab_name = selected_tab.get('title', '').lower()
5178 if selected_tab_name == 'home':
5179 selected_tab_name = 'featured'
5180 requested_tab_name = mobj['tab'][1:]
09f1580e 5181 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5182 if requested_tab_name == 'live':
09f1580e 5183 # Live tab should have redirected to the video
5184 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5185 if requested_tab_name not in ('', selected_tab_name):
5186 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5187 if not original_tab_name:
5188 if item_id[:2] == 'UC':
5189 # Topic channels don't have /videos. Use the equivalent playlist instead
5190 pl_id = f'UU{item_id[2:]}'
5191 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5192 try:
5193 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5194 except ExtractorError:
5195 redirect_warning += ' and the playlist redirect gave error'
5196 else:
5197 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5198 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5199 if selected_tab_name and selected_tab_name != requested_tab_name:
5200 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5201 else:
5202 raise ExtractorError(redirect_warning, expected=True)
18db7548 5203
37e57a9f 5204 if redirect_warning:
64f36541 5205 self.to_screen(redirect_warning)
37e57a9f 5206 self.write_debug(f'Final URL: {url}')
18db7548 5207
358de58c 5208 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5209 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5210 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5211 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5212 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5213 if tabs:
ac56cf38 5214 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5215
37e57a9f 5216 playlist = traverse_obj(
5217 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5218 if playlist:
ac56cf38 5219 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5220
37e57a9f 5221 video_id = traverse_obj(
5222 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5223 if video_id:
09f1580e 5224 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5225 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5226 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5227 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5228
8bdd16b4 5229 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5230
c5e8d7af 5231
8bdd16b4 5232class YoutubePlaylistIE(InfoExtractor):
96565c7e 5233 IE_DESC = 'YouTube playlists'
8bdd16b4 5234 _VALID_URL = r'''(?x)(?:
5235 (?:https?://)?
5236 (?:\w+\.)?
5237 (?:
5238 (?:
5239 youtube(?:kids)?\.com|
d9190e44 5240 %(invidious)s
8bdd16b4 5241 )
5242 /.*?\?.*?\blist=
5243 )?
5244 (?P<id>%(playlist_id)s)
d9190e44
RH
5245 )''' % {
5246 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5247 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5248 }
8bdd16b4 5249 IE_NAME = 'youtube:playlist'
cdc628a4 5250 _TESTS = [{
8bdd16b4 5251 'note': 'issue #673',
5252 'url': 'PLBB231211A4F62143',
cdc628a4 5253 'info_dict': {
8bdd16b4 5254 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5255 'id': 'PLBB231211A4F62143',
976ae3ea 5256 'uploader': 'Wickman',
8bdd16b4 5257 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5258 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5259 'view_count': int,
5260 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5261 'modified_date': r're:\d{8}',
5262 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5263 'channel': 'Wickman',
5264 'tags': [],
5265 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5266 },
5267 'playlist_mincount': 29,
5268 }, {
5269 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5270 'info_dict': {
5271 'title': 'YDL_safe_search',
5272 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5273 },
5274 'playlist_count': 2,
5275 'skip': 'This playlist is private',
9558dcec 5276 }, {
8bdd16b4 5277 'note': 'embedded',
5278 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5279 'playlist_count': 4,
9558dcec 5280 'info_dict': {
8bdd16b4 5281 'title': 'JODA15',
5282 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5283 'uploader': 'milan',
5284 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5285 'description': '',
5286 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5287 'tags': [],
5288 'modified_date': '20140919',
5289 'view_count': int,
5290 'channel': 'milan',
5291 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5292 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5293 },
5294 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5295 }, {
8bdd16b4 5296 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5297 'playlist_mincount': 654,
8bdd16b4 5298 'info_dict': {
5299 'title': '2018 Chinese New Singles (11/6 updated)',
5300 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5301 'uploader': 'LBK',
5302 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5303 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5304 'channel': 'LBK',
5305 'view_count': int,
5306 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5307 'tags': [],
5308 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5309 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5310 'modified_date': r're:\d{8}',
5311 },
5312 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5313 }, {
29f7c58a 5314 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5315 'only_matching': True,
5316 }, {
5317 # music album playlist
5318 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5319 'only_matching': True,
5320 }]
5321
5322 @classmethod
5323 def suitable(cls, url):
201c1459 5324 if YoutubeTabIE.suitable(url):
5325 return False
49a57e70 5326 from ..utils import parse_qs
201c1459 5327 qs = parse_qs(url)
5328 if qs.get('v', [None])[0]:
5329 return False
5330 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5331
5332 def _real_extract(self, url):
5333 playlist_id = self._match_id(url)
46953e7e 5334 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5335 url = update_url_query(
5336 'https://www.youtube.com/playlist',
5337 parse_qs(url) or {'list': playlist_id})
5338 if is_music_url:
5339 url = smuggle_url(url, {'is_music_url': True})
5340 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5341
5342
5343class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5344 IE_DESC = 'youtu.be'
29f7c58a 5345 _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}
5346 _TESTS = [{
8bdd16b4 5347 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5348 'info_dict': {
5349 'id': 'yeWKywCrFtk',
5350 'ext': 'mp4',
5351 'title': 'Small Scale Baler and Braiding Rugs',
5352 'uploader': 'Backus-Page House Museum',
5353 'uploader_id': 'backuspagemuseum',
5354 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5355 'upload_date': '20161008',
5356 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5357 'categories': ['Nonprofits & Activism'],
5358 'tags': list,
5359 'like_count': int,
976ae3ea 5360 'age_limit': 0,
5361 'playable_in_embed': True,
5362 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5363 'channel': 'Backus-Page House Museum',
5364 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5365 'live_status': 'not_live',
5366 'view_count': int,
5367 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5368 'availability': 'public',
5369 'duration': 59,
8bdd16b4 5370 },
5371 'params': {
5372 'noplaylist': True,
5373 'skip_download': True,
5374 },
39e7107d 5375 }, {
8bdd16b4 5376 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5377 'only_matching': True,
cdc628a4
PH
5378 }]
5379
8bdd16b4 5380 def _real_extract(self, url):
5ad28e7f 5381 mobj = self._match_valid_url(url)
29f7c58a 5382 video_id = mobj.group('id')
5383 playlist_id = mobj.group('playlist_id')
8bdd16b4 5384 return self.url_result(
29f7c58a 5385 update_url_query('https://www.youtube.com/watch', {
5386 'v': video_id,
5387 'list': playlist_id,
5388 'feature': 'youtu.be',
5389 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5390
5391
b6ce9bb0 5392class YoutubeLivestreamEmbedIE(InfoExtractor):
5393 IE_DESC = 'YouTube livestream embeds'
5394 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5395 _TESTS = [{
5396 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5397 'only_matching': True,
5398 }]
5399
5400 def _real_extract(self, url):
5401 channel_id = self._match_id(url)
5402 return self.url_result(
5403 f'https://www.youtube.com/channel/{channel_id}/live',
5404 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5405
5406
8bdd16b4 5407class YoutubeYtUserIE(InfoExtractor):
96565c7e 5408 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5409 IE_NAME = 'youtube:user'
8bdd16b4 5410 _VALID_URL = r'ytuser:(?P<id>.+)'
5411 _TESTS = [{
5412 'url': 'ytuser:phihag',
5413 'only_matching': True,
5414 }]
5415
5416 def _real_extract(self, url):
5417 user_id = self._match_id(url)
5418 return self.url_result(
c586f9e8 5419 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5420 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5421
b05654f0 5422
3d3dddc9 5423class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5424 IE_NAME = 'youtube:favorites'
96565c7e 5425 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5426 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5427 _LOGIN_REQUIRED = True
5428 _TESTS = [{
5429 'url': ':ytfav',
5430 'only_matching': True,
5431 }, {
5432 'url': ':ytfavorites',
5433 'only_matching': True,
5434 }]
5435
5436 def _real_extract(self, url):
5437 return self.url_result(
5438 'https://www.youtube.com/playlist?list=LL',
5439 ie=YoutubeTabIE.ie_key())
5440
5441
a6213a49 5442class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5443 IE_DESC = 'YouTube search'
78caa52a 5444 IE_NAME = 'youtube:search'
b05654f0 5445 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5446 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5447 _TESTS = [{
5448 'url': 'ytsearch5:youtube-dl test video',
5449 'playlist_count': 5,
5450 'info_dict': {
5451 'id': 'youtube-dl test video',
5452 'title': 'youtube-dl test video',
5453 }
5454 }]
b05654f0 5455
a61fd4cf 5456
5f7cb91a 5457class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5458 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5459 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5460 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5461 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5462 _TESTS = [{
5463 'url': 'ytsearchdate5:youtube-dl test video',
5464 'playlist_count': 5,
5465 'info_dict': {
5466 'id': 'youtube-dl test video',
5467 'title': 'youtube-dl test video',
5468 }
5469 }]
75dff0ee 5470
c9ae7b95 5471
a6213a49 5472class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5473 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5474 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5475 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5476 _TESTS = [{
5477 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5478 'playlist_mincount': 5,
5479 'info_dict': {
11f9be09 5480 'id': 'youtube-dl test video',
3462ffa8 5481 'title': 'youtube-dl test video',
5482 }
a61fd4cf 5483 }, {
5484 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5485 'playlist_mincount': 5,
5486 'info_dict': {
5487 'id': 'python',
5488 'title': 'python',
5489 }
5490
3462ffa8 5491 }, {
5492 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5493 'only_matching': True,
5494 }]
5495
5496 def _real_extract(self, url):
4dfbf869 5497 qs = parse_qs(url)
386e1dd9 5498 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5499 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5500
5501
16aa9ea4 5502class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5503 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5504 IE_NAME = 'youtube:music:search_url'
5505 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5506 _TESTS = [{
5507 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5508 'playlist_count': 16,
5509 'info_dict': {
5510 'id': 'royalty free music',
5511 'title': 'royalty free music',
5512 }
5513 }, {
5514 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5515 'playlist_mincount': 30,
5516 'info_dict': {
5517 'id': 'royalty free music - songs',
5518 'title': 'royalty free music - songs',
5519 },
5520 'params': {'extract_flat': 'in_playlist'}
5521 }, {
5522 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5523 'playlist_mincount': 30,
5524 'info_dict': {
5525 'id': 'royalty free music - community playlists',
5526 'title': 'royalty free music - community playlists',
5527 },
5528 'params': {'extract_flat': 'in_playlist'}
5529 }]
5530
5531 _SECTIONS = {
5532 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5533 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5534 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5535 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5536 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5537 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5538 }
5539
5540 def _real_extract(self, url):
5541 qs = parse_qs(url)
5542 query = (qs.get('search_query') or qs.get('q'))[0]
5543 params = qs.get('sp', (None,))[0]
5544 if params:
5545 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5546 else:
5547 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5548 params = self._SECTIONS.get(section)
5549 if not params:
5550 section = None
5551 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5552 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5553
5554
182bda88 5555class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5556 """
25f14e9f 5557 Base class for feed extractors
3d3dddc9 5558 Subclasses must define the _FEED_NAME property.
d7ae0639 5559 """
b2e8bc1b 5560 _LOGIN_REQUIRED = True
ef2f3c7f 5561 _TESTS = []
d7ae0639
JMF
5562
5563 @property
5564 def IE_NAME(self):
78caa52a 5565 return 'youtube:%s' % self._FEED_NAME
04cc9617 5566
3853309f 5567 def _real_extract(self, url):
3d3dddc9 5568 return self.url_result(
182bda88 5569 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5570
5571
ef2f3c7f 5572class YoutubeWatchLaterIE(InfoExtractor):
5573 IE_NAME = 'youtube:watchlater'
96565c7e 5574 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5575 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5576 _TESTS = [{
8bdd16b4 5577 'url': ':ytwatchlater',
bc7a9cd8
S
5578 'only_matching': True,
5579 }]
25f14e9f
S
5580
5581 def _real_extract(self, url):
ef2f3c7f 5582 return self.url_result(
5583 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5584
5585
25f14e9f 5586class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5587 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5588 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5589 _FEED_NAME = 'recommended'
45db527f 5590 _LOGIN_REQUIRED = False
3d3dddc9 5591 _TESTS = [{
5592 'url': ':ytrec',
5593 'only_matching': True,
5594 }, {
5595 'url': ':ytrecommended',
5596 'only_matching': True,
5597 }, {
5598 'url': 'https://youtube.com',
5599 'only_matching': True,
5600 }]
1ed5b5c9 5601
1ed5b5c9 5602
25f14e9f 5603class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5604 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5605 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5606 _FEED_NAME = 'subscriptions'
3d3dddc9 5607 _TESTS = [{
5608 'url': ':ytsubs',
5609 'only_matching': True,
5610 }, {
5611 'url': ':ytsubscriptions',
5612 'only_matching': True,
5613 }]
1ed5b5c9 5614
1ed5b5c9 5615
25f14e9f 5616class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5617 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5618 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5619 _FEED_NAME = 'history'
3d3dddc9 5620 _TESTS = [{
5621 'url': ':ythistory',
5622 'only_matching': True,
5623 }]
1ed5b5c9
JMF
5624
5625
15870e90
PH
5626class YoutubeTruncatedURLIE(InfoExtractor):
5627 IE_NAME = 'youtube:truncated_url'
5628 IE_DESC = False # Do not list
975d35db 5629 _VALID_URL = r'''(?x)
b95aab84
PH
5630 (?:https?://)?
5631 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5632 (?:watch\?(?:
c4808c60 5633 feature=[a-z_]+|
b95aab84
PH
5634 annotation_id=annotation_[^&]+|
5635 x-yt-cl=[0-9]+|
c1708b89 5636 hl=[^&]*|
287be8c6 5637 t=[0-9]+
b95aab84
PH
5638 )?
5639 |
5640 attribution_link\?a=[^&]+
5641 )
5642 $
975d35db 5643 '''
15870e90 5644
c4808c60 5645 _TESTS = [{
2d3d2997 5646 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5647 'only_matching': True,
dc2fc736 5648 }, {
2d3d2997 5649 'url': 'https://www.youtube.com/watch?',
dc2fc736 5650 'only_matching': True,
b95aab84
PH
5651 }, {
5652 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5653 'only_matching': True,
5654 }, {
5655 'url': 'https://www.youtube.com/watch?feature=foo',
5656 'only_matching': True,
c1708b89
PH
5657 }, {
5658 'url': 'https://www.youtube.com/watch?hl=en-GB',
5659 'only_matching': True,
287be8c6
PH
5660 }, {
5661 'url': 'https://www.youtube.com/watch?t=2372',
5662 'only_matching': True,
c4808c60
PH
5663 }]
5664
15870e90
PH
5665 def _real_extract(self, url):
5666 raise ExtractorError(
78caa52a
PH
5667 'Did you forget to quote the URL? Remember that & is a meta '
5668 'character in most shells, so you want to put the URL in quotes, '
3867038a 5669 'like youtube-dl '
2d3d2997 5670 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5671 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5672 expected=True)
772fd5cc
PH
5673
5674
3cd786db 5675class YoutubeClipIE(InfoExtractor):
5676 IE_NAME = 'youtube:clip'
5677 IE_DESC = False # Do not list
5678 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5679
5680 def _real_extract(self, url):
5681 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5682 return self.url_result(url, 'Generic')
5683
5684
772fd5cc
PH
5685class YoutubeTruncatedIDIE(InfoExtractor):
5686 IE_NAME = 'youtube:truncated_id'
5687 IE_DESC = False # Do not list
b95aab84 5688 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5689
5690 _TESTS = [{
5691 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5692 'only_matching': True,
5693 }]
5694
5695 def _real_extract(self, url):
5696 video_id = self._match_id(url)
5697 raise ExtractorError(
5698 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5699 expected=True)