]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[outtmpl] Handle hard-coded file extension better
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
d92f5d5a 5import calendar
109dd3b2 6import copy
fe93e2c4 7import datetime
adbc4ec4 8import functools
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
720c3099 12import math
c4417ddb 13import os.path
d77ab8e2 14import random
c5e8d7af 15import re
46383212 16import sys
8a784c74 17import time
e0df6211 18import traceback
adbc4ec4 19import threading
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 22from ..compat import (
edf3e38e 23 compat_chr,
29f7c58a 24 compat_HTTPError,
c5e8d7af 25 compat_parse_qs,
545cc85d 26 compat_str,
7fd002c0 27 compat_urllib_parse_unquote_plus,
15707c7e 28 compat_urllib_parse_urlencode,
7c80519c 29 compat_urllib_parse_urlparse,
7c61bd36 30 compat_urlparse,
4bb4a188 31)
545cc85d 32from ..jsinterp import JSInterpreter
4bb4a188 33from ..utils import (
720c3099 34 bug_reports_message,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
c5e8d7af 39 ExtractorError,
2d30521a 40 float_or_none,
11f9be09 41 format_field,
dd27fd17 42 int_or_none,
641ad5d8 43 is_html,
34921b43 44 join_nonempty,
94278f72 45 mimetype2ext,
9c0d7f49 46 network_exceptions,
a6213a49 47 NO_DEFAULT,
11f9be09 48 orderedSet,
6310acf5 49 parse_codecs,
49bd8c66 50 parse_count,
7c80519c 51 parse_duration,
7ea65411 52 parse_iso8601,
4dfbf869 53 parse_qs,
dca3ff4a 54 qualities,
c0ac49bc 55 remove_end,
3995d37d 56 remove_start,
cf7e015f 57 smuggle_url,
dbdaaa23 58 str_or_none,
c93d53f5 59 str_to_int,
f3aa3c3f 60 strftime_or_none,
7c365c21 61 traverse_obj,
556dbe7f 62 try_get,
c5e8d7af
PH
63 unescapeHTML,
64 unified_strdate,
f0d785d3 65 unified_timestamp,
cf7e015f 66 unsmuggle_url,
8bdd16b4 67 update_url_query,
21c340b8 68 url_or_none,
fe93e2c4 69 urljoin,
7c365c21 70 variadic,
c5e8d7af
PH
71)
72
5f6a1245 73
720c3099 74def get_first(obj, keys, **kwargs):
75 return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
76
77
000c15a4 78# any clients starting with _ cannot be explicity requested by the user
79INNERTUBE_CLIENTS = {
80 'web': {
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
83 'client': {
84 'clientName': 'WEB',
18c7683d 85 'clientVersion': '2.20211221.00.00',
000c15a4 86 }
87 },
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
89 },
90 'web_embedded': {
91 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
92 'INNERTUBE_CONTEXT': {
93 'client': {
94 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 95 'clientVersion': '1.20211215.00.01',
000c15a4 96 },
97 },
98 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
99 },
100 'web_music': {
101 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
102 'INNERTUBE_HOST': 'music.youtube.com',
103 'INNERTUBE_CONTEXT': {
104 'client': {
105 'clientName': 'WEB_REMIX',
18c7683d 106 'clientVersion': '1.20211213.00.00',
000c15a4 107 }
108 },
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
110 },
e7e94f2a 111 'web_creator': {
18c7683d 112 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
113 'INNERTUBE_CONTEXT': {
114 'client': {
115 'clientName': 'WEB_CREATOR',
18c7683d 116 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
117 }
118 },
119 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
120 },
000c15a4 121 'android': {
18c7683d 122 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 123 'INNERTUBE_CONTEXT': {
124 'client': {
125 'clientName': 'ANDROID',
18c7683d 126 'clientVersion': '16.49',
000c15a4 127 }
128 },
129 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 130 'REQUIRE_JS_PLAYER': False
000c15a4 131 },
132 'android_embedded': {
18c7683d 133 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 134 'INNERTUBE_CONTEXT': {
135 'client': {
136 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 137 'clientVersion': '16.49',
000c15a4 138 },
139 },
b6de707d 140 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
141 'REQUIRE_JS_PLAYER': False
000c15a4 142 },
143 'android_music': {
18c7683d 144 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 145 'INNERTUBE_CONTEXT': {
146 'client': {
147 'clientName': 'ANDROID_MUSIC',
18c7683d 148 'clientVersion': '4.57',
000c15a4 149 }
150 },
151 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 152 'REQUIRE_JS_PLAYER': False
000c15a4 153 },
e7e94f2a 154 'android_creator': {
18c7683d 155 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
156 'INNERTUBE_CONTEXT': {
157 'client': {
158 'clientName': 'ANDROID_CREATOR',
18c7683d 159 'clientVersion': '21.47',
e7e94f2a
D
160 },
161 },
b6de707d 162 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
163 'REQUIRE_JS_PLAYER': False
e7e94f2a 164 },
18c7683d 165 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
166 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 167 'ios': {
18c7683d 168 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 169 'INNERTUBE_CONTEXT': {
170 'client': {
171 'clientName': 'IOS',
18c7683d 172 'clientVersion': '16.46',
173 'deviceModel': 'iPhone14,3',
000c15a4 174 }
175 },
b6de707d 176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
000c15a4 178 },
179 'ios_embedded': {
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 183 'clientVersion': '16.46',
184 'deviceModel': 'iPhone14,3',
000c15a4 185 },
186 },
b6de707d 187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
000c15a4 189 },
190 'ios_music': {
18c7683d 191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_MUSIC',
18c7683d 195 'clientVersion': '4.57',
000c15a4 196 },
197 },
b6de707d 198 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
199 'REQUIRE_JS_PLAYER': False
000c15a4 200 },
e7e94f2a
D
201 'ios_creator': {
202 'INNERTUBE_CONTEXT': {
203 'client': {
204 'clientName': 'IOS_CREATOR',
18c7683d 205 'clientVersion': '21.47',
e7e94f2a
D
206 },
207 },
b6de707d 208 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
209 'REQUIRE_JS_PLAYER': False
e7e94f2a 210 },
3619f78d 211 # mweb has 'ultralow' formats
212 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 213 'mweb': {
18c7683d 214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 215 'INNERTUBE_CONTEXT': {
216 'client': {
217 'clientName': 'MWEB',
18c7683d 218 'clientVersion': '2.20211221.01.00',
000c15a4 219 }
220 },
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
18c7683d 222 }
000c15a4 223}
224
225
226def build_innertube_clients():
65c2fde2 227 third_party = {
228 'embedUrl': 'https://google.com', # Can be any valid URL
229 }
000c15a4 230 base_clients = ('android', 'web', 'ios', 'mweb')
231 priority = qualities(base_clients[::-1])
232
233 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 234 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 235 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 236 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 237 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
238 ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
239
240 if client in base_clients:
241 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
242 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
65c2fde2 243 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 244 agegate_ytcfg['priority'] -= 1
245 elif client.endswith('_embedded'):
65c2fde2 246 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 247 ytcfg['priority'] -= 2
248 else:
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|'
6970b600 260 r'shorts|movies|results|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,
461 query={'key': api_key or self._extract_api_key()})
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(
396a76f7 733 (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
734 text.lower(), 'time text', default=None)))
f0d785d3 735
f3aa3c3f 736 if text and timestamp is None:
737 self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
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,
66f7c6a3 846 # 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
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',
1207 'upload_date': '20191227',
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,
7caf9830
S
1572 'upload_date': '20150127',
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,
fd050249 1604 'upload_date': '20151119',
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}
2081 }
2eb88d95
PH
2082 ]
2083
201c1459 2084 @classmethod
2085 def suitable(cls, url):
4dfbf869 2086 from ..utils import parse_qs
2087
201c1459 2088 qs = parse_qs(url)
2089 if qs.get('list', [None])[0]:
2090 return False
2091 return super(YoutubeIE, cls).suitable(url)
2092
e0df6211
PH
2093 def __init__(self, *args, **kwargs):
2094 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2095 self._code_cache = {}
83799698 2096 self._player_cache = {}
e0df6211 2097
adbc4ec4 2098 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2099 lock = threading.Lock()
2100
2101 is_live = True
185bf310 2102 start_time = time.time()
adbc4ec4
THD
2103 formats = [f for f in formats if f.get('is_from_start')]
2104
185bf310 2105 def refetch_manifest(format_id, delay):
2106 nonlocal formats, start_time, is_live
2107 if time.time() <= start_time + delay:
adbc4ec4
THD
2108 return
2109
2110 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2111 video_details = traverse_obj(
2112 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2113 microformats = traverse_obj(
2114 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2115 expected_type=dict, default=[])
2116 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2117 start_time = time.time()
adbc4ec4 2118
185bf310 2119 def mpd_feed(format_id, delay):
adbc4ec4
THD
2120 """
2121 @returns (manifest_url, manifest_stream_number, is_live) or None
2122 """
2123 with lock:
185bf310 2124 refetch_manifest(format_id, delay)
adbc4ec4
THD
2125
2126 f = next((f for f in formats if f['format_id'] == format_id), None)
2127 if not f:
185bf310 2128 if not is_live:
2129 self.to_screen(f'{video_id}: Video is no longer live')
2130 else:
2131 self.report_warning(
2132 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2133 return None
2134 return f['manifest_url'], f['manifest_stream_number'], is_live
2135
2136 for f in formats:
2137 f['protocol'] = 'http_dash_segments_generator'
2138 f['fragments'] = functools.partial(
2139 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2140
2141 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2142 FETCH_SPAN, MAX_DURATION = 5, 432000
2143
2144 mpd_url, stream_number, is_live = None, None, True
2145
2146 begin_index = 0
2147 download_start_time = ctx.get('start') or time.time()
2148
2149 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2150 if lack_early_segments:
2151 self.report_warning(bug_reports_message(
2152 'Starting download from the last 120 hours of the live stream since '
2153 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2154 lack_early_segments = True
2155
2156 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2157 fragments, fragment_base_url = None, None
2158
2159 def _extract_sequence_from_mpd(refresh_sequence):
2160 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2161 # Obtain from MPD's maximum seq value
2162 old_mpd_url = mpd_url
185bf310 2163 last_error = ctx.pop('last_error', None)
2164 expire_fast = last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2165 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2166 or (mpd_url, stream_number, False))
2167 if not refresh_sequence:
2168 if expire_fast and not is_live:
2169 return False, last_seq
2170 elif old_mpd_url == mpd_url:
2171 return True, last_seq
adbc4ec4
THD
2172 try:
2173 fmts, _ = self._extract_mpd_formats_and_subtitles(
2174 mpd_url, None, note=False, errnote=False, fatal=False)
2175 except ExtractorError:
2176 fmts = None
2177 if not fmts:
2178 no_fragment_score += 1
2179 return False, last_seq
2180 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2181 fragments = fmt_info['fragments']
2182 fragment_base_url = fmt_info['fragment_base_url']
2183 assert fragment_base_url
2184
2185 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2186 return True, _last_seq
2187
2188 while is_live:
2189 fetch_time = time.time()
2190 if no_fragment_score > 30:
2191 return
2192 if last_segment_url:
2193 # Obtain from "X-Head-Seqnum" header value from each segment
2194 try:
2195 urlh = self._request_webpage(
2196 last_segment_url, None, note=False, errnote=False, fatal=False)
2197 except ExtractorError:
2198 urlh = None
2199 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2200 if last_seq is None:
2201 no_fragment_score += 1
2202 last_segment_url = None
2203 continue
2204 else:
185bf310 2205 should_continue, last_seq = _extract_sequence_from_mpd(True)
2206 if not should_continue:
adbc4ec4
THD
2207 continue
2208
2209 if known_idx > last_seq:
2210 last_segment_url = None
2211 continue
2212
2213 last_seq += 1
2214
2215 if begin_index < 0 and known_idx < 0:
2216 # skip from the start when it's negative value
2217 known_idx = last_seq + begin_index
2218 if lack_early_segments:
2219 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2220 try:
2221 for idx in range(known_idx, last_seq):
2222 # do not update sequence here or you'll get skipped some part of it
185bf310 2223 should_continue, _ = _extract_sequence_from_mpd(False)
2224 if not should_continue:
adbc4ec4
THD
2225 known_idx = idx - 1
2226 raise ExtractorError('breaking out of outer loop')
2227 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2228 yield {
2229 'url': last_segment_url,
2230 }
2231 if known_idx == last_seq:
2232 no_fragment_score += 5
2233 else:
2234 no_fragment_score = 0
2235 known_idx = last_seq
2236 except ExtractorError:
2237 continue
2238
2239 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2240
b6de707d 2241 def _extract_player_url(self, *ytcfgs, webpage=None):
2242 player_url = traverse_obj(
2243 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2244 get_all=False, expected_type=compat_str)
11f9be09 2245 if not player_url:
b6de707d 2246 return
109dd3b2 2247 if player_url.startswith('//'):
2248 player_url = 'https:' + player_url
2249 elif not re.match(r'https?://', player_url):
2250 player_url = compat_urlparse.urljoin(
2251 'https://www.youtube.com', player_url)
2252 return player_url
2253
b6de707d 2254 def _download_player_url(self, video_id, fatal=False):
2255 res = self._download_webpage(
2256 'https://www.youtube.com/iframe_api',
2257 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2258 if res:
2259 player_version = self._search_regex(
2260 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2261 if player_version:
2262 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2263
60064c53
PH
2264 def _signature_cache_id(self, example_sig):
2265 """ Return a string representation of a signature """
78caa52a 2266 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2267
e40c758c
S
2268 @classmethod
2269 def _extract_player_info(cls, player_url):
2270 for player_re in cls._PLAYER_INFO_RE:
2271 id_m = re.search(player_re, player_url)
2272 if id_m:
2273 break
2274 else:
c081b35c 2275 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2276 return id_m.group('id')
e40c758c 2277
404f611f 2278 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2279 player_id = self._extract_player_info(player_url)
2280 if player_id not in self._code_cache:
1276a43a 2281 code = self._download_webpage(
109dd3b2 2282 player_url, video_id, fatal=fatal,
2283 note='Downloading player ' + player_id,
2284 errnote='Download of %s failed' % player_url)
1276a43a 2285 if code:
2286 self._code_cache[player_id] = code
404f611f 2287 return self._code_cache.get(player_id)
109dd3b2 2288
e40c758c 2289 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2290 player_id = self._extract_player_info(player_url)
e0df6211 2291
c4417ddb 2292 # Read from filesystem cache
545cc85d 2293 func_id = 'js_%s_%s' % (
2294 player_id, self._signature_cache_id(example_sig))
c4417ddb 2295 assert os.path.basename(func_id) == func_id
a0e07d31 2296
69ea8ca4 2297 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2298 if cache_spec is not None:
78caa52a 2299 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2300
404f611f 2301 code = self._load_player(video_id, player_url)
2302 if code:
109dd3b2 2303 res = self._parse_sig_js(code)
e0df6211 2304
109dd3b2 2305 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2306 cache_res = res(test_string)
2307 cache_spec = [ord(c) for c in cache_res]
83799698 2308
109dd3b2 2309 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2310 return res
83799698 2311
60064c53 2312 def _print_sig_code(self, func, example_sig):
404f611f 2313 if not self.get_param('youtube_print_sig_code'):
2314 return
2315
edf3e38e
PH
2316 def gen_sig_code(idxs):
2317 def _genslice(start, end, step):
78caa52a 2318 starts = '' if start == 0 else str(start)
8bcc8756 2319 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2320 steps = '' if step == 1 else (':%d' % step)
78caa52a 2321 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2322
2323 step = None
7af808a5
PH
2324 # Quelch pyflakes warnings - start will be set when step is set
2325 start = '(Never used)'
edf3e38e
PH
2326 for i, prev in zip(idxs[1:], idxs[:-1]):
2327 if step is not None:
2328 if i - prev == step:
2329 continue
2330 yield _genslice(start, prev, step)
2331 step = None
2332 continue
2333 if i - prev in [-1, 1]:
2334 step = i - prev
2335 start = prev
2336 continue
2337 else:
78caa52a 2338 yield 's[%d]' % prev
edf3e38e 2339 if step is None:
78caa52a 2340 yield 's[%d]' % i
edf3e38e
PH
2341 else:
2342 yield _genslice(start, i, step)
2343
78caa52a 2344 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2345 cache_res = func(test_string)
edf3e38e 2346 cache_spec = [ord(c) for c in cache_res]
78caa52a 2347 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2348 signature_id_tuple = '(%s)' % (
2349 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2350 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2351 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2352 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2353
e0df6211
PH
2354 def _parse_sig_js(self, jscode):
2355 funcname = self._search_regex(
abefc03f
S
2356 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2357 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
2358 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2359 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2360 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}\(a,\d+\)',
2361 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 2362 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2363 # Obsolete patterns
2364 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2365 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2366 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2367 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2368 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2369 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2370 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2371 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2372 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2373
2374 jsi = JSInterpreter(jscode)
2375 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2376 return lambda s: initial_function([s])
2377
545cc85d 2378 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2379 """Turn the encrypted s field into a working signature"""
6b37f0be 2380
c8bf86d5 2381 if player_url is None:
69ea8ca4 2382 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2383
c8bf86d5 2384 try:
62af3a0e 2385 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2386 if player_id not in self._player_cache:
2387 func = self._extract_signature_function(
60064c53 2388 video_id, player_url, s
c8bf86d5
PH
2389 )
2390 self._player_cache[player_id] = func
2391 func = self._player_cache[player_id]
404f611f 2392 self._print_sig_code(func, s)
c8bf86d5
PH
2393 return func(s)
2394 except Exception as e:
404f611f 2395 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2396
2397 def _decrypt_nsig(self, s, video_id, player_url):
2398 """Turn the encrypted n field into a working signature"""
2399 if player_url is None:
2400 raise ExtractorError('Cannot decrypt nsig without player_url')
2401 if player_url.startswith('//'):
2402 player_url = 'https:' + player_url
2403 elif not re.match(r'https?://', player_url):
2404 player_url = compat_urlparse.urljoin(
2405 'https://www.youtube.com', player_url)
2406
2407 sig_id = ('nsig_value', s)
2408 if sig_id in self._player_cache:
2409 return self._player_cache[sig_id]
2410
2411 try:
2412 player_id = ('nsig', player_url)
2413 if player_id not in self._player_cache:
2414 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2415 func = self._player_cache[player_id]
2416 self._player_cache[sig_id] = func(s)
2417 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2418 return self._player_cache[sig_id]
2419 except Exception as e:
aa9369a2 2420 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2421
2422 def _extract_n_function_name(self, jscode):
2423 return self._search_regex(
2424 (r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})\([a-zA-Z0-9]\)',),
2425 jscode, 'Initial JS player n function name', group='nfunc')
2426
2427 def _extract_n_function(self, video_id, player_url):
2428 player_id = self._extract_player_info(player_url)
2429 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2430
2431 if func_code:
2432 jsi = JSInterpreter(func_code)
2433 else:
2434 jscode = self._load_player(video_id, player_url)
2435 funcname = self._extract_n_function_name(jscode)
2436 jsi = JSInterpreter(jscode)
2437 func_code = jsi.extract_function_code(funcname)
2438 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2439
2440 if self.get_param('youtube_print_sig_code'):
2441 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2442
2443 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2444
109dd3b2 2445 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2446 """
2447 Extract signatureTimestamp (sts)
2448 Required to tell API what sig/player version is in use.
2449 """
2450 sts = None
2451 if isinstance(ytcfg, dict):
2452 sts = int_or_none(ytcfg.get('STS'))
2453
2454 if not sts:
2455 # Attempt to extract from player
2456 if player_url is None:
2457 error_msg = 'Cannot extract signature timestamp without player_url.'
2458 if fatal:
2459 raise ExtractorError(error_msg)
2460 self.report_warning(error_msg)
2461 return
404f611f 2462 code = self._load_player(video_id, player_url, fatal=fatal)
2463 if code:
109dd3b2 2464 sts = int_or_none(self._search_regex(
2465 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2466 'JS player signature timestamp', group='sts', fatal=fatal))
2467 return sts
2468
11f9be09 2469 def _mark_watched(self, video_id, player_responses):
9222c381 2470 playback_url = get_first(
2471 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2472 expected_type=url_or_none)
d77ab8e2 2473 if not playback_url:
352d63fd 2474 self.report_warning('Unable to mark watched')
d77ab8e2
S
2475 return
2476 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2477 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2478
2479 # cpn generation algorithm is reverse engineered from base.js.
2480 # In fact it works even with dummy cpn.
2481 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2482 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2483
2484 qs.update({
2485 'ver': ['2'],
2486 'cpn': [cpn],
2487 })
2488 playback_url = compat_urlparse.urlunparse(
15707c7e 2489 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2490
2491 self._download_webpage(
2492 playback_url, video_id, 'Marking watched',
2493 'Unable to mark watched', fatal=False)
2494
66c9fa36
S
2495 @staticmethod
2496 def _extract_urls(webpage):
2497 # Embedded YouTube player
2498 entries = [
2499 unescapeHTML(mobj.group('url'))
2500 for mobj in re.finditer(r'''(?x)
2501 (?:
2502 <iframe[^>]+?src=|
2503 data-video-url=|
2504 <embed[^>]+?src=|
2505 embedSWF\(?:\s*|
2506 <object[^>]+data=|
2507 new\s+SWFObject\(
2508 )
2509 (["\'])
2510 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2511 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2512 \1''', webpage)]
2513
2514 # lazyYT YouTube embed
2515 entries.extend(list(map(
2516 unescapeHTML,
2517 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2518
2519 # Wordpress "YouTube Video Importer" plugin
2520 matches = re.findall(r'''(?x)<div[^>]+
2521 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2522 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2523 entries.extend(m[-1] for m in matches)
2524
2525 return entries
2526
2527 @staticmethod
2528 def _extract_url(webpage):
2529 urls = YoutubeIE._extract_urls(webpage)
2530 return urls[0] if urls else None
2531
97665381
PH
2532 @classmethod
2533 def extract_id(cls, url):
2534 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2535 if mobj is None:
69ea8ca4 2536 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2537 return mobj.group('id')
c5e8d7af 2538
7c365c21 2539 def _extract_chapters_from_json(self, data, duration):
2540 chapter_list = traverse_obj(
2541 data, (
2542 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2543 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2544 ), expected_type=list)
2545
2546 return self._extract_chapters(
2547 chapter_list,
2548 chapter_time=lambda chapter: float_or_none(
2549 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2550 chapter_title=lambda chapter: traverse_obj(
2551 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2552 duration=duration)
2553
2554 def _extract_chapters_from_engagement_panel(self, data, duration):
2555 content_list = traverse_obj(
8bdd16b4 2556 data,
7c365c21 2557 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2558 expected_type=list, default=[])
052e1350 2559 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2560 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2561
2562 return next((
2563 filter(None, (
2564 self._extract_chapters(
2565 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2566 chapter_time, chapter_title, duration)
2567 for contents in content_list
2568 ))), [])
2569
2570 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2571 chapters = []
7c365c21 2572 last_chapter = {'start_time': 0}
2573 for idx, chapter in enumerate(chapter_list or []):
2574 title = chapter_title(chapter)
84213ea8
S
2575 start_time = chapter_time(chapter)
2576 if start_time is None:
2577 continue
7c365c21 2578 last_chapter['end_time'] = start_time
2579 if start_time < last_chapter['start_time']:
2580 if idx == 1:
2581 chapters.pop()
2582 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2583 else:
2584 self.report_warning(f'Invalid start time for chapter "{title}"')
2585 continue
2586 last_chapter = {'start_time': start_time, 'title': title}
2587 chapters.append(last_chapter)
2588 last_chapter['end_time'] = duration
84213ea8
S
2589 return chapters
2590
545cc85d 2591 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2592 return self._parse_json(self._search_regex(
2593 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2594 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2595
a1c5d2ca
M
2596 def _extract_comment(self, comment_renderer, parent=None):
2597 comment_id = comment_renderer.get('commentId')
2598 if not comment_id:
2599 return
fe93e2c4 2600
052e1350 2601 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2602
49bd8c66 2603 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2604 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2605 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2606 author_id = try_get(comment_renderer,
2607 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2608
49bd8c66 2609 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2610 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2611 author_thumbnail = try_get(comment_renderer,
2612 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2613
2614 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2615 is_favorited = 'creatorHeart' in (try_get(
2616 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2617 return {
2618 'id': comment_id,
2619 'text': text,
d92f5d5a 2620 'timestamp': timestamp,
a1c5d2ca
M
2621 'time_text': time_text,
2622 'like_count': votes,
97524332 2623 'is_favorited': is_favorited,
a1c5d2ca
M
2624 'author': author,
2625 'author_id': author_id,
2626 'author_thumbnail': author_thumbnail,
2627 'author_is_uploader': author_is_uploader,
2628 'parent': parent or 'root'
2629 }
2630
46383212 2631 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2632
2633 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2634
2635 def extract_header(contents):
2d6659b9 2636 _continuation = None
2637 for content in contents:
46383212 2638 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2639 expected_comment_count = self._get_count(
2640 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2641
2d6659b9 2642 if expected_comment_count:
46383212 2643 tracker['est_total'] = expected_comment_count
2644 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2645 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2646
2647 sort_menu_item = try_get(
2648 comments_header_renderer,
2649 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2650 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2651
2652 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2653 if not _continuation:
2654 continue
2655
46383212 2656 sort_text = str_or_none(sort_menu_item.get('title'))
2657 if not sort_text:
2d6659b9 2658 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2659 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2660 break
a2160aa4 2661 return _continuation
a1c5d2ca 2662
2d6659b9 2663 def extract_thread(contents):
a1c5d2ca 2664 if not parent:
46383212 2665 tracker['current_page_thread'] = 0
a1c5d2ca 2666 for content in contents:
46383212 2667 if not parent and tracker['total_parent_comments'] >= max_parents:
2668 yield
a1c5d2ca 2669 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2670 comment_renderer = get_first(
2671 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2672 expected_type=dict, default={})
a1c5d2ca 2673
a1c5d2ca
M
2674 comment = self._extract_comment(comment_renderer, parent)
2675 if not comment:
2676 continue
46383212 2677
2678 tracker['running_total'] += 1
2679 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2680 yield comment
46383212 2681
a1c5d2ca
M
2682 # Attempt to get the replies
2683 comment_replies_renderer = try_get(
2684 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2685
2686 if comment_replies_renderer:
46383212 2687 tracker['current_page_thread'] += 1
a1c5d2ca 2688 comment_entries_iter = self._comment_entries(
99e9e001 2689 comment_replies_renderer, ytcfg, video_id,
46383212 2690 parent=comment.get('id'), tracker=tracker)
2691 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2692 yield reply_comment
2693
46383212 2694 # Keeps track of counts across recursive calls
2695 if not tracker:
2696 tracker = dict(
2697 running_total=0,
2698 est_total=0,
2699 current_page_thread=0,
2700 total_parent_comments=0,
2701 total_reply_comments=0)
2702
2703 # TODO: Deprecated
2d6659b9 2704 # YouTube comments have a max depth of 2
46383212 2705 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2706 if max_depth:
2707 self._downloader.deprecation_warning(
2708 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2709 if max_depth == 1 and parent:
2710 return
a1c5d2ca 2711
46383212 2712 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2713 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2714
46383212 2715 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2716 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2717 if message and not parent:
2718 self.report_warning(message, video_id=video_id)
2719
46383212 2720 response = None
2d6659b9 2721 is_first_continuation = parent is None
a1c5d2ca
M
2722
2723 for page_num in itertools.count(0):
2724 if not continuation:
2725 break
46383212 2726 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2727 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2728 if page_num == 0:
2729 if is_first_continuation:
2730 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2731 else:
2d6659b9 2732 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2733 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2734 else:
2735 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2736 ' ' if parent else '', ' replies' if parent else '',
2737 page_num, comment_prog_str)
2738
2739 response = self._extract_response(
fe93e2c4 2740 item_id=None, query=continuation,
2d6659b9 2741 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2742 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2743
46383212 2744 continuation_contents = traverse_obj(
2745 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2746
2d6659b9 2747 continuation = None
46383212 2748 for continuation_section in continuation_contents:
2749 continuation_items = traverse_obj(
2750 continuation_section,
2751 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2752 get_all=False, expected_type=list) or []
2753 if is_first_continuation:
2754 continuation = extract_header(continuation_items)
2755 is_first_continuation = False
2d6659b9 2756 if continuation:
a1c5d2ca 2757 break
46383212 2758 continue
a1c5d2ca 2759
46383212 2760 for entry in extract_thread(continuation_items):
2761 if not entry:
2762 return
2763 yield entry
2764 continuation = self._extract_continuation({'contents': continuation_items})
2765 if continuation:
2d6659b9 2766 break
a1c5d2ca 2767
a2160aa4 2768 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2769 """Entry for comment extraction"""
2d6659b9 2770 def _real_comment_extract(contents):
aae16f6e 2771 renderer = next((
2772 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2773 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2774 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2775
a2160aa4 2776 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2777 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2778
109dd3b2 2779 @staticmethod
99e9e001 2780 def _get_checkok_params():
2781 return {'contentCheckOk': True, 'racyCheckOk': True}
2782
2783 @classmethod
2784 def _generate_player_context(cls, sts=None):
109dd3b2 2785 context = {
2786 'html5Preference': 'HTML5_PREF_WANTS',
2787 }
2788 if sts is not None:
2789 context['signatureTimestamp'] = sts
2790 return {
2791 'playbackContext': {
2792 'contentPlaybackContext': context
a1a7907b 2793 },
99e9e001 2794 **cls._get_checkok_params()
109dd3b2 2795 }
2796
e7e94f2a
D
2797 @staticmethod
2798 def _is_agegated(player_response):
2799 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2800 return True
e7e94f2a
D
2801
2802 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2803 AGE_GATE_REASONS = (
2804 'confirm your age', 'age-restricted', 'inappropriate', # reason
2805 'age_verification_required', 'age_check_required', # status
2806 )
2807 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2808
2809 @staticmethod
2810 def _is_unplayable(player_response):
2811 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2812
99e9e001 2813 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2814
11f9be09 2815 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2816 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2817 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2818 headers = self.generate_api_headers(
99e9e001 2819 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2820
11f9be09 2821 yt_query = {'videoId': video_id}
2822 yt_query.update(self._generate_player_context(sts))
2823 return self._extract_response(
2824 item_id=video_id, ep='player', query=yt_query,
379e44ed 2825 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2826 default_client=client,
11f9be09 2827 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2828 ) or None
2829
11f9be09 2830 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2831 requested_clients = []
d0d012d4 2832 default = ['android', 'web']
000c15a4 2833 allowed_clients = sorted(
2834 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2835 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2836 for client in self._configuration_arg('player_client'):
2837 if client in allowed_clients:
2838 requested_clients.append(client)
d0d012d4 2839 elif client == 'default':
2840 requested_clients.extend(default)
b4c055ba 2841 elif client == 'all':
2842 requested_clients.extend(allowed_clients)
2843 else:
2844 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2845 if not requested_clients:
d0d012d4 2846 requested_clients = default
cf7e015f 2847
11f9be09 2848 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2849 requested_clients.extend(
e7e94f2a 2850 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2851
11f9be09 2852 return orderedSet(requested_clients)
cf7e015f 2853
c0bc527b
M
2854 def _extract_player_ytcfg(self, client, video_id):
2855 url = {
2856 'web_music': 'https://music.youtube.com',
2857 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2858 }.get(client)
2859 if not url:
2860 return {}
18c7683d 2861 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2862 return self.extract_ytcfg(video_id, webpage) or {}
2863
99e9e001 2864 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2865 initial_pr = None
2866 if webpage:
2867 initial_pr = self._extract_yt_initial_variable(
2868 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2869 video_id, 'initial player response')
6b09401b 2870
c0bc527b
M
2871 original_clients = clients
2872 clients = clients[::-1]
b6de707d 2873 prs = []
e7e94f2a
D
2874
2875 def append_client(client_name):
2876 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2877 clients.append(client_name)
2878
379e44ed 2879 # Android player_response does not have microFormats which are needed for
2880 # extraction of some data. So we return the initial_pr with formats
2881 # stripped out even if not requested by the user
2882 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2883 if initial_pr:
2884 pr = dict(initial_pr)
2885 pr['streamingData'] = None
b6de707d 2886 prs.append(pr)
379e44ed 2887
2888 last_error = None
b6de707d 2889 tried_iframe_fallback = False
2890 player_url = None
c0bc527b
M
2891 while clients:
2892 client = clients.pop()
11f9be09 2893 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2894 if 'configs' not in self._configuration_arg('player_skip'):
2895 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2896
b6de707d 2897 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2898 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2899 if 'js' in self._configuration_arg('player_skip'):
2900 require_js_player = False
2901 player_url = None
2902
2903 if not player_url and not tried_iframe_fallback and require_js_player:
2904 player_url = self._download_player_url(video_id)
2905 tried_iframe_fallback = True
2906
379e44ed 2907 try:
2908 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2909 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2910 except ExtractorError as e:
2911 if last_error:
2912 self.report_warning(last_error)
2913 last_error = e
2914 continue
2915
11f9be09 2916 if pr:
b6de707d 2917 prs.append(pr)
c0bc527b 2918
e7e94f2a 2919 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 2920 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
2921 append_client(client.replace('_agegate', '_creator'))
2922 elif self._is_agegated(pr):
2923 append_client(f'{client}_agegate')
c0bc527b 2924
379e44ed 2925 if last_error:
b6de707d 2926 if not len(prs):
379e44ed 2927 raise last_error
2928 self.report_warning(last_error)
b6de707d 2929 return prs, player_url
11f9be09 2930
2931 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
a0bb6ce5 2932 itags, stream_ids = {}, []
2a9c6dcd 2933 itag_qualities, res_qualities = {}, {}
d3fc8074 2934 q = qualities([
2a9c6dcd 2935 # Normally tiny is the smallest video-only formats. But
2936 # audio-only formats with unknown quality may get tagged as tiny
2937 'tiny',
2938 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 2939 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2940 ])
11f9be09 2941 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 2942
545cc85d 2943 for fmt in streaming_formats:
2944 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2945 continue
321bf820 2946
cc2db878 2947 itag = str_or_none(fmt.get('itag'))
9297939e 2948 audio_track = fmt.get('audioTrack') or {}
2949 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2950 if stream_id in stream_ids:
2951 continue
2952
cc2db878 2953 quality = fmt.get('quality')
2a9c6dcd 2954 height = int_or_none(fmt.get('height'))
d3fc8074 2955 if quality == 'tiny' or not quality:
2956 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 2957 # The 3gp format (17) in android client has a quality of "small",
2958 # but is actually worse than other formats
2959 if itag == '17':
2960 quality = 'tiny'
2961 if quality:
2962 if itag:
2963 itag_qualities[itag] = quality
2964 if height:
2965 res_qualities[height] = quality
cc2db878 2966 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2967 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2968 # number of fragment that would subsequently requested with (`&sq=N`)
2969 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2970 continue
2971
545cc85d 2972 fmt_url = fmt.get('url')
2973 if not fmt_url:
2974 sc = compat_parse_qs(fmt.get('signatureCipher'))
2975 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2976 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2977 if not (sc and fmt_url and encrypted_sig):
2978 continue
545cc85d 2979 if not player_url:
201e9eaa 2980 continue
545cc85d 2981 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2982 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2983 fmt_url += '&' + sp + '=' + signature
2984
404f611f 2985 query = parse_qs(fmt_url)
2986 throttled = False
b2916526 2987 if query.get('n'):
404f611f 2988 try:
2989 fmt_url = update_url_query(fmt_url, {
2990 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2991 except ExtractorError as e:
aa9369a2 2992 self.report_warning(
2993 f'nsig extraction failed: You may experience throttling for some formats\n'
2994 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 2995 throttled = True
2996
545cc85d 2997 if itag:
a0bb6ce5 2998 itags[itag] = 'https'
9297939e 2999 stream_ids.append(stream_id)
3000
cc2db878 3001 tbr = float_or_none(
3002 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
545cc85d 3003 dct = {
3004 'asr': int_or_none(fmt.get('audioSampleRate')),
3005 'filesize': int_or_none(fmt.get('contentLength')),
3006 'format_id': itag,
34921b43 3007 'format_note': join_nonempty(
26e8e044 3008 '%s%s' % (audio_track.get('displayName') or '',
3009 ' (default)' if audio_track.get('audioIsDefault') else ''),
404f611f 3010 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
34921b43 3011 throttled and 'THROTTLED', delim=', '),
c18d4482 3012 'source_preference': -10 if throttled else -1,
a4211baf 3013 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3014 'height': height,
dca3ff4a 3015 'quality': q(quality),
cc2db878 3016 'tbr': tbr,
545cc85d 3017 'url': fmt_url,
2a9c6dcd 3018 'width': int_or_none(fmt.get('width')),
0fb983f6 3019 'language': audio_track.get('id', '').split('.')[0],
26e8e044 3020 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
545cc85d 3021 }
60bdb7bd 3022 mime_mobj = re.match(
3023 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3024 if mime_mobj:
3025 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3026 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3027 no_audio = dct.get('acodec') == 'none'
3028 no_video = dct.get('vcodec') == 'none'
3029 if no_audio:
3030 dct['vbr'] = tbr
3031 if no_video:
3032 dct['abr'] = tbr
3033 if no_audio or no_video:
545cc85d 3034 dct['downloader_options'] = {
3035 # Youtube throttles chunks >~10M
3036 'http_chunk_size': 10485760,
bf1317d2 3037 }
7c60c33e 3038 if dct.get('ext'):
3039 dct['container'] = dct['ext'] + '_dash'
11f9be09 3040 yield dct
545cc85d 3041
adbc4ec4 3042 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3043 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3044 if not self.get_param('youtube_include_hls_manifest', True):
3045 skip_manifests.append('hls')
3046 get_dash = 'dash' not in skip_manifests and (
3047 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3048 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3049
a0bb6ce5 3050 def process_manifest_format(f, proto, itag):
3051 if itag in itags:
3052 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3053 return False
3054 itag = f'{itag}-{proto}'
3055 if itag:
3056 f['format_id'] = itag
3057 itags[itag] = proto
3058
3059 f['quality'] = next((
3060 q(qdict[val])
e339d25a 3061 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3062 if val in qdict), -1)
3063 return True
2a9c6dcd 3064
11f9be09 3065 for sd in streaming_data:
5d3a0e79 3066 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3067 if hls_manifest_url:
2a9c6dcd 3068 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3069 if process_manifest_format(f, 'hls', self._search_regex(
3070 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3071 yield f
545cc85d 3072
5d3a0e79 3073 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3074 if dash_manifest_url:
2a9c6dcd 3075 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3076 if process_manifest_format(f, 'dash', f['format_id']):
3077 f['filesize'] = int_or_none(self._search_regex(
3078 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3079 if live_from_start:
3080 f['is_from_start'] = True
3081
a0bb6ce5 3082 yield f
11f9be09 3083
720c3099 3084 def _extract_storyboard(self, player_responses, duration):
3085 spec = get_first(
3086 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3087 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3088 if not base_url:
720c3099 3089 return
720c3099 3090 L = len(spec) - 1
3091 for i, args in enumerate(spec):
3092 args = args.split('#')
3093 counts = list(map(int_or_none, args[:5]))
3094 if len(args) != 8 or not all(counts):
3095 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3096 continue
3097 width, height, frame_count, cols, rows = counts
3098 N, sigh = args[6:]
3099
3100 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3101 fragment_count = frame_count / (cols * rows)
3102 fragment_duration = duration / fragment_count
3103 yield {
3104 'format_id': f'sb{i}',
3105 'format_note': 'storyboard',
3106 'ext': 'mhtml',
3107 'protocol': 'mhtml',
3108 'acodec': 'none',
3109 'vcodec': 'none',
3110 'url': url,
3111 'width': width,
3112 'height': height,
3113 'fragments': [{
3114 'path': url.replace('$M', str(j)),
3115 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3116 } for j in range(math.ceil(fragment_count))],
3117 }
3118
adbc4ec4 3119 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3120 webpage = None
3121 if 'webpage' not in self._configuration_arg('player_skip'):
3122 webpage = self._download_webpage(
3123 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3124
3125 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3126
b6de707d 3127 player_responses, player_url = self._extract_player_responses(
11f9be09 3128 self._get_requested_clients(url, smuggled_data),
99e9e001 3129 video_id, webpage, master_ytcfg)
11f9be09 3130
adbc4ec4
THD
3131 return webpage, master_ytcfg, player_responses, player_url
3132
3133 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3134 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3135 is_live = get_first(video_details, 'isLive')
3136 if is_live is None:
3137 is_live = get_first(live_broadcast_details, 'isLiveNow')
3138
3139 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3140 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3141
3142 return live_broadcast_details, is_live, streaming_data, formats
3143
3144 def _real_extract(self, url):
3145 url, smuggled_data = unsmuggle_url(url, {})
3146 video_id = self._match_id(url)
3147
3148 base_url = self.http_scheme() + '//www.youtube.com/'
3149 webpage_url = base_url + 'watch?v=' + video_id
3150
3151 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3152
11f9be09 3153 playability_statuses = traverse_obj(
3154 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3155
3156 trailer_video_id = get_first(
3157 playability_statuses,
3158 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3159 expected_type=str)
3160 if trailer_video_id:
3161 return self.url_result(
3162 trailer_video_id, self.ie_key(), trailer_video_id)
3163
3164 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3165 if webpage else (lambda x: None))
3166
3167 video_details = traverse_obj(
3168 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3169 microformats = traverse_obj(
3170 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3171 expected_type=dict, default=[])
3172 video_title = (
3173 get_first(video_details, 'title')
3174 or self._get_text(microformats, (..., 'title'))
3175 or search_meta(['og:title', 'twitter:title', 'title']))
3176 video_description = get_first(video_details, 'shortDescription')
3177
d89257f3 3178 multifeed_metadata_list = get_first(
3179 player_responses,
3180 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3181 expected_type=str)
3182 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3183 if self.get_param('noplaylist'):
11f9be09 3184 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3185 else:
3186 entries = []
3187 feed_ids = []
3188 for feed in multifeed_metadata_list.split(','):
3189 # Unquote should take place before split on comma (,) since textual
3190 # fields may contain comma as well (see
3191 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3192 feed_data = compat_parse_qs(
3193 compat_urllib_parse_unquote_plus(feed))
3194
3195 def feed_entry(name):
3196 return try_get(
3197 feed_data, lambda x: x[name][0], compat_str)
3198
3199 feed_id = feed_entry('id')
3200 if not feed_id:
3201 continue
3202 feed_title = feed_entry('title')
3203 title = video_title
3204 if feed_title:
3205 title += ' (%s)' % feed_title
3206 entries.append({
3207 '_type': 'url_transparent',
3208 'ie_key': 'Youtube',
3209 'url': smuggle_url(
3210 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3211 {'force_singlefeed': True}),
3212 'title': title,
3213 })
3214 feed_ids.append(feed_id)
3215 self.to_screen(
3216 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3217 % (', '.join(feed_ids), video_id))
3218 return self.playlist_result(
3219 entries, video_id, video_title, video_description)
11f9be09 3220
adbc4ec4 3221 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3222
545cc85d 3223 if not formats:
11f9be09 3224 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3225 self.report_drm(video_id)
11f9be09 3226 pemr = get_first(
3227 playability_statuses,
3228 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3229 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3230 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3231 if subreason:
545cc85d 3232 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3233 countries = get_first(microformats, 'availableCountries')
545cc85d 3234 if not countries:
3235 regions_allowed = search_meta('regionsAllowed')
3236 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3237 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3238 reason += f'. {subreason}'
545cc85d 3239 if reason:
b7da73eb 3240 self.raise_no_formats(reason, expected=True)
bf1317d2 3241
11f9be09 3242 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3243 if not keywords and webpage:
3244 keywords = [
3245 unescapeHTML(m.group('content'))
3246 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3247 for keyword in keywords:
3248 if keyword.startswith('yt:stretch='):
201c1459 3249 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3250 if mobj:
3251 # NB: float is intentional for forcing float division
3252 w, h = (float(v) for v in mobj.groups())
3253 if w > 0 and h > 0:
3254 ratio = w / h
3255 for f in formats:
3256 if f.get('vcodec') != 'none':
3257 f['stretched_ratio'] = ratio
3258 break
a709d873 3259 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3260 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3261 if thumbnail_url:
3262 thumbnails.append({
3263 'url': thumbnail_url,
ff2751ac 3264 })
fccf5021 3265 original_thumbnails = thumbnails.copy()
3266
0ba692ac 3267 # The best resolution thumbnails sometimes does not appear in the webpage
3268 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3269 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3270 thumbnail_names = [
3271 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3272 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3273 'mqdefault', 'mq1', 'mq2', 'mq3',
3274 'default', '1', '2', '3'
3275 ]
cca80fe6 3276 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3277 thumbnails.extend({
3278 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3279 video_id=video_id, name=name, ext=ext,
3280 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3281 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3282 for thumb in thumbnails:
cca80fe6 3283 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3284 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3285 self._remove_duplicate_formats(thumbnails)
fccf5021 3286 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3287
7ea65411 3288 category = get_first(microformats, 'category') or search_meta('genre')
3289 channel_id = str_or_none(
3290 get_first(video_details, 'channelId')
3291 or get_first(microformats, 'externalChannelId')
3292 or search_meta('channelId'))
3293 duration = int_or_none(
3294 get_first(video_details, 'lengthSeconds')
3295 or get_first(microformats, 'lengthSeconds')
3296 or parse_duration(search_meta('duration'))) or None
3297 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3298
3299 live_content = get_first(video_details, 'isLiveContent')
3300 is_upcoming = get_first(video_details, 'isUpcoming')
3301 if is_live is None:
3302 if is_upcoming or live_content is False:
3303 is_live = False
3304 if is_upcoming is None and (live_content or is_live):
3305 is_upcoming = False
adbc4ec4
THD
3306 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3307 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3308 if not duration and live_end_time and live_start_time:
3309 duration = live_end_time - live_start_time
3310
3311 if is_live and self.get_param('live_from_start'):
3312 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3313
720c3099 3314 formats.extend(self._extract_storyboard(player_responses, duration))
3315
3316 # Source is given priority since formats that throttle are given lower source_preference
3317 # When throttling issue is fully fixed, remove this
3318 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3319
545cc85d 3320 info = {
3321 'id': video_id,
39ca3b5c 3322 'title': video_title,
545cc85d 3323 'formats': formats,
3324 'thumbnails': thumbnails,
fccf5021 3325 # The best thumbnail that we are sure exists. Prevents unnecessary
3326 # URL checking if user don't care about getting the best possible thumbnail
3327 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3328 'description': video_description,
3329 'upload_date': unified_strdate(
11f9be09 3330 get_first(microformats, 'uploadDate')
545cc85d 3331 or search_meta('uploadDate')),
11f9be09 3332 'uploader': get_first(video_details, 'author'),
545cc85d 3333 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3334 'uploader_url': owner_profile_url,
3335 'channel_id': channel_id,
e0ddbd02 3336 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3337 'duration': duration,
3338 'view_count': int_or_none(
11f9be09 3339 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3340 or search_meta('interactionCount')),
11f9be09 3341 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3342 'age_limit': 18 if (
11f9be09 3343 get_first(microformats, 'isFamilySafe') is False
545cc85d 3344 or search_meta('isFamilyFriendly') == 'false'
3345 or search_meta('og:restrictions:age') == '18+') else 0,
3346 'webpage_url': webpage_url,
3347 'categories': [category] if category else None,
3348 'tags': keywords,
11f9be09 3349 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3350 'is_live': is_live,
3351 'was_live': (False if is_live or is_upcoming or live_content is False
3352 else None if is_live is None or is_upcoming is None
3353 else live_content),
3354 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3355 'release_timestamp': live_start_time,
545cc85d 3356 }
b477fc13 3357
3944e7af 3358 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3359 if pctr:
ecdc9049 3360 def get_lang_code(track):
3361 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3362 or track.get('languageCode'))
3363
3364 # Converted into dicts to remove duplicates
3365 captions = {
3366 get_lang_code(sub): sub
3367 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3368 translation_languages = {
3369 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3370 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3371
774d79cc 3372 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3373 lang_subs = container.setdefault(lang_code, [])
545cc85d 3374 for fmt in self._SUBTITLE_FORMATS:
3375 query.update({
3376 'fmt': fmt,
3377 })
3378 lang_subs.append({
3379 'ext': fmt,
3380 'url': update_url_query(base_url, query),
774d79cc 3381 'name': sub_name,
545cc85d 3382 })
7e72694b 3383
ecdc9049 3384 subtitles, automatic_captions = {}, {}
3385 for lang_code, caption_track in captions.items():
3386 base_url = caption_track.get('baseUrl')
545cc85d 3387 if not base_url:
3388 continue
ecdc9049 3389 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3390 if caption_track.get('kind') != 'asr':
545cc85d 3391 if not lang_code:
3392 continue
3393 process_language(
ecdc9049 3394 subtitles, base_url, lang_code, lang_name, {})
3395 if not caption_track.get('isTranslatable'):
3396 continue
3944e7af 3397 for trans_code, trans_name in translation_languages.items():
3398 if not trans_code:
545cc85d 3399 continue
ecdc9049 3400 if caption_track.get('kind') != 'asr':
3401 trans_code += f'-{lang_code}'
3402 trans_name += format_field(lang_name, template=' from %s')
545cc85d 3403 process_language(
ecdc9049 3404 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3405 info['automatic_captions'] = automatic_captions
3406 info['subtitles'] = subtitles
7e72694b 3407
545cc85d 3408 parsed_url = compat_urllib_parse_urlparse(url)
3409 for component in [parsed_url.fragment, parsed_url.query]:
3410 query = compat_parse_qs(component)
3411 for k, v in query.items():
3412 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3413 d_k += '_time'
3414 if d_k not in info and k in s_ks:
3415 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3416
3417 # Youtube Music Auto-generated description
822b9d9c 3418 if video_description:
38d70284 3419 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 3420 if mobj:
822b9d9c
RA
3421 release_year = mobj.group('release_year')
3422 release_date = mobj.group('release_date')
3423 if release_date:
3424 release_date = release_date.replace('-', '')
3425 if not release_year:
545cc85d 3426 release_year = release_date[:4]
3427 info.update({
3428 'album': mobj.group('album'.strip()),
3429 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3430 'track': mobj.group('track').strip(),
3431 'release_date': release_date,
cc2db878 3432 'release_year': int_or_none(release_year),
545cc85d 3433 })
7e72694b 3434
545cc85d 3435 initial_data = None
3436 if webpage:
3437 initial_data = self._extract_yt_initial_variable(
3438 webpage, self._YT_INITIAL_DATA_RE, video_id,
3439 'yt initial data')
3440 if not initial_data:
99e9e001 3441 query = {'videoId': video_id}
3442 query.update(self._get_checkok_params())
109dd3b2 3443 initial_data = self._extract_response(
3444 item_id=video_id, ep='next', fatal=False,
99e9e001 3445 ytcfg=master_ytcfg, query=query,
3446 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3447 note='Downloading initial data API JSON')
545cc85d 3448
c60ee3a2 3449 try:
3450 # This will error if there is no livechat
3451 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3452 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3453 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3454 'video_id': video_id,
3455 'ext': 'json',
f6745c49 3456 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3457 }]
3458 except (KeyError, IndexError, TypeError):
3459 pass
545cc85d 3460
3461 if initial_data:
7c365c21 3462 info['chapters'] = (
3463 self._extract_chapters_from_json(initial_data, duration)
3464 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3465 or None)
545cc85d 3466
3467 contents = try_get(
3468 initial_data,
3469 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3470 list) or []
3471 for content in contents:
3472 vpir = content.get('videoPrimaryInfoRenderer')
3473 if vpir:
3474 stl = vpir.get('superTitleLink')
3475 if stl:
fe93e2c4 3476 stl = self._get_text(stl)
545cc85d 3477 if try_get(
3478 vpir,
3479 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3480 info['location'] = stl
3481 else:
3482 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3483 if mobj:
3484 info.update({
3485 'series': mobj.group(1),
3486 'season_number': int(mobj.group(2)),
3487 'episode_number': int(mobj.group(3)),
3488 })
3489 for tlb in (try_get(
3490 vpir,
3491 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3492 list) or []):
3493 tbr = tlb.get('toggleButtonRenderer') or {}
3494 for getter, regex in [(
3495 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3496 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3497 lambda x: x['accessibility'],
3498 lambda x: x['accessibilityData']['accessibilityData'],
3499 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3500 label = (try_get(tbr, getter, dict) or {}).get('label')
3501 if label:
3502 mobj = re.match(regex, label)
3503 if mobj:
3504 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3505 break
3506 sbr_tooltip = try_get(
3507 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3508 if sbr_tooltip:
3509 like_count, dislike_count = sbr_tooltip.split(' / ')
3510 info.update({
3511 'like_count': str_to_int(like_count),
3512 'dislike_count': str_to_int(dislike_count),
3513 })
3514 vsir = content.get('videoSecondaryInfoRenderer')
3515 if vsir:
6c73052c 3516 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3517 info.update({
3518 'channel': self._get_text(vor, 'title'),
3519 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3520
545cc85d 3521 rows = try_get(
3522 vsir,
3523 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3524 list) or []
3525 multiple_songs = False
3526 for row in rows:
3527 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3528 multiple_songs = True
3529 break
3530 for row in rows:
3531 mrr = row.get('metadataRowRenderer') or {}
3532 mrr_title = mrr.get('title')
3533 if not mrr_title:
3534 continue
052e1350 3535 mrr_title = self._get_text(mrr, 'title')
3536 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3537 if mrr_title == 'License':
3538 info['license'] = mrr_contents_text
3539 elif not multiple_songs:
3540 if mrr_title == 'Album':
3541 info['album'] = mrr_contents_text
3542 elif mrr_title == 'Artist':
3543 info['artist'] = mrr_contents_text
3544 elif mrr_title == 'Song':
3545 info['track'] = mrr_contents_text
3546
3547 fallbacks = {
3548 'channel': 'uploader',
3549 'channel_id': 'uploader_id',
3550 'channel_url': 'uploader_url',
3551 }
3552 for to, frm in fallbacks.items():
3553 if not info.get(to):
3554 info[to] = info.get(frm)
3555
3556 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3557 v = info.get(s_k)
3558 if v:
3559 info[d_k] = v
b84071c0 3560
11f9be09 3561 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3562 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3563 is_membersonly = None
b28f8d24 3564 is_premium = None
c224251a
M
3565 if initial_data and is_private is not None:
3566 is_membersonly = False
b28f8d24 3567 is_premium = False
47193e02 3568 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3569 badge_labels = set()
3570 for content in contents:
3571 if not isinstance(content, dict):
3572 continue
3573 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3574 for badge_label in badge_labels:
3575 if badge_label.lower() == 'members only':
3576 is_membersonly = True
3577 elif badge_label.lower() == 'premium':
3578 is_premium = True
3579 elif badge_label.lower() == 'unlisted':
3580 is_unlisted = True
c224251a 3581
c224251a
M
3582 info['availability'] = self._availability(
3583 is_private=is_private,
b28f8d24 3584 needs_premium=is_premium,
c224251a
M
3585 needs_subscription=is_membersonly,
3586 needs_auth=info['age_limit'] >= 18,
3587 is_unlisted=None if is_private is None else is_unlisted)
3588
a2160aa4 3589 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3590
11f9be09 3591 self.mark_watched(video_id, player_responses)
d77ab8e2 3592
545cc85d 3593 return info
c5e8d7af 3594
a61fd4cf 3595
a6213a49 3596class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3597
a6213a49 3598 def _extract_channel_id(self, webpage):
3599 channel_id = self._html_search_meta(
3600 'channelId', webpage, 'channel id', default=None)
3601 if channel_id:
3602 return channel_id
3603 channel_url = self._html_search_meta(
3604 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3605 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3606 'twitter:app:url:googleplay'), webpage, 'channel url')
3607 return self._search_regex(
3608 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3609 channel_url, 'channel id')
15f6397c 3610
8bdd16b4 3611 @staticmethod
cd7c66cf 3612 def _extract_basic_item_renderer(item):
3613 # Modified from _extract_grid_item_renderer
201c1459 3614 known_basic_renderers = (
3615 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3616 )
3617 for key, renderer in item.items():
201c1459 3618 if not isinstance(renderer, dict):
cd7c66cf 3619 continue
201c1459 3620 elif key in known_basic_renderers:
3621 return renderer
3622 elif key.startswith('grid') and key.endswith('Renderer'):
3623 return renderer
8bdd16b4 3624
8bdd16b4 3625 def _grid_entries(self, grid_renderer):
3626 for item in grid_renderer['items']:
3627 if not isinstance(item, dict):
39b62db1 3628 continue
cd7c66cf 3629 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3630 if not isinstance(renderer, dict):
3631 continue
052e1350 3632 title = self._get_text(renderer, 'title')
fe93e2c4 3633
8bdd16b4 3634 # playlist
3635 playlist_id = renderer.get('playlistId')
3636 if playlist_id:
3637 yield self.url_result(
3638 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3639 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3640 video_title=title)
201c1459 3641 continue
8bdd16b4 3642 # video
3643 video_id = renderer.get('videoId')
3644 if video_id:
3645 yield self._extract_video(renderer)
201c1459 3646 continue
8bdd16b4 3647 # channel
3648 channel_id = renderer.get('channelId')
3649 if channel_id:
8bdd16b4 3650 yield self.url_result(
3651 'https://www.youtube.com/channel/%s' % channel_id,
3652 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3653 continue
3654 # generic endpoint URL support
3655 ep_url = urljoin('https://www.youtube.com/', try_get(
3656 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3657 compat_str))
3658 if ep_url:
3659 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3660 if ie.suitable(ep_url):
3661 yield self.url_result(
3662 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3663 break
8bdd16b4 3664
3d3dddc9 3665 def _shelf_entries_from_content(self, shelf_renderer):
3666 content = shelf_renderer.get('content')
3667 if not isinstance(content, dict):
8bdd16b4 3668 return
cd7c66cf 3669 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3670 if renderer:
3671 # TODO: add support for nested playlists so each shelf is processed
3672 # as separate playlist
3673 # TODO: this includes only first N items
3674 for entry in self._grid_entries(renderer):
3675 yield entry
3676 renderer = content.get('horizontalListRenderer')
3677 if renderer:
3678 # TODO
3679 pass
8bdd16b4 3680
29f7c58a 3681 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3682 ep = try_get(
3683 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3684 compat_str)
3685 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3686 if shelf_url:
29f7c58a 3687 # Skipping links to another channels, note that checking for
3688 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3689 # will not work
3690 if skip_channels and '/channels?' in shelf_url:
3691 return
052e1350 3692 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3693 yield self.url_result(shelf_url, video_title=title)
3694 # Shelf may not contain shelf URL, fallback to extraction from content
3695 for entry in self._shelf_entries_from_content(shelf_renderer):
3696 yield entry
c5e8d7af 3697
8bdd16b4 3698 def _playlist_entries(self, video_list_renderer):
3699 for content in video_list_renderer['contents']:
3700 if not isinstance(content, dict):
3701 continue
3702 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3703 if not isinstance(renderer, dict):
3704 continue
3705 video_id = renderer.get('videoId')
3706 if not video_id:
3707 continue
3708 yield self._extract_video(renderer)
07aeced6 3709
3462ffa8 3710 def _rich_entries(self, rich_grid_renderer):
3711 renderer = try_get(
70d5c17b 3712 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3713 video_id = renderer.get('videoId')
3714 if not video_id:
3715 return
3716 yield self._extract_video(renderer)
3717
8bdd16b4 3718 def _video_entry(self, video_renderer):
3719 video_id = video_renderer.get('videoId')
3720 if video_id:
3721 return self._extract_video(video_renderer)
dacb3a86 3722
8bdd16b4 3723 def _post_thread_entries(self, post_thread_renderer):
3724 post_renderer = try_get(
3725 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3726 if not post_renderer:
3727 return
3728 # video attachment
3729 video_renderer = try_get(
895b0931 3730 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3731 video_id = video_renderer.get('videoId')
3732 if video_id:
3733 entry = self._extract_video(video_renderer)
8bdd16b4 3734 if entry:
3735 yield entry
895b0931 3736 # playlist attachment
3737 playlist_id = try_get(
3738 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3739 if playlist_id:
3740 yield self.url_result(
e28f1c0a 3741 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3742 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3743 # inline video links
3744 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3745 for run in runs:
3746 if not isinstance(run, dict):
3747 continue
3748 ep_url = try_get(
3749 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3750 if not ep_url:
3751 continue
3752 if not YoutubeIE.suitable(ep_url):
3753 continue
3754 ep_video_id = YoutubeIE._match_id(ep_url)
3755 if video_id == ep_video_id:
3756 continue
895b0931 3757 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3758
8bdd16b4 3759 def _post_thread_continuation_entries(self, post_thread_continuation):
3760 contents = post_thread_continuation.get('contents')
3761 if not isinstance(contents, list):
3762 return
3763 for content in contents:
3764 renderer = content.get('backstagePostThreadRenderer')
3765 if not isinstance(renderer, dict):
3766 continue
3767 for entry in self._post_thread_entries(renderer):
3768 yield entry
07aeced6 3769
39ed931e 3770 r''' # unused
3771 def _rich_grid_entries(self, contents):
3772 for content in contents:
3773 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3774 if video_renderer:
3775 entry = self._video_entry(video_renderer)
3776 if entry:
3777 yield entry
3778 '''
a6213a49 3779 def _extract_entries(self, parent_renderer, continuation_list):
3780 # continuation_list is modified in-place with continuation_list = [continuation_token]
3781 continuation_list[:] = [None]
3782 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3783 for content in contents:
3784 if not isinstance(content, dict):
3785 continue
3786 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3787 if not is_renderer:
3788 renderer = content.get('richItemRenderer')
3789 if renderer:
3790 for entry in self._rich_entries(renderer):
3791 yield entry
3792 continuation_list[0] = self._extract_continuation(parent_renderer)
3793 continue
3794 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3795 for isr_content in isr_contents:
3796 if not isinstance(isr_content, dict):
8bdd16b4 3797 continue
69184e41 3798
a6213a49 3799 known_renderers = {
3800 'playlistVideoListRenderer': self._playlist_entries,
3801 'gridRenderer': self._grid_entries,
3802 'shelfRenderer': lambda x: self._shelf_entries(x),
3803 'backstagePostThreadRenderer': self._post_thread_entries,
3804 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3805 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3806 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3807 }
3808 for key, renderer in isr_content.items():
3809 if key not in known_renderers:
3810 continue
3811 for entry in known_renderers[key](renderer):
3812 if entry:
3813 yield entry
3814 continuation_list[0] = self._extract_continuation(renderer)
3815 break
70d5c17b 3816
3817 if not continuation_list[0]:
a6213a49 3818 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3819
a6213a49 3820 if not continuation_list[0]:
3821 continuation_list[0] = self._extract_continuation(parent_renderer)
3822
3823 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3824 continuation_list = [None]
3825 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3826 tab_content = try_get(tab, lambda x: x['content'], dict)
3827 if not tab_content:
3828 return
3462ffa8 3829 parent_renderer = (
29f7c58a 3830 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3831 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3832 for entry in extract_entries(parent_renderer):
3833 yield entry
3462ffa8 3834 continuation = continuation_list[0]
d069eca7 3835
8bdd16b4 3836 for page_num in itertools.count(1):
3837 if not continuation:
3838 break
99e9e001 3839 headers = self.generate_api_headers(
3840 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3841 response = self._extract_response(
3842 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3843 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3844 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3845
3846 if not response:
8bdd16b4 3847 break
ac56cf38 3848 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3849 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3850 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 3851
69184e41 3852 known_continuation_renderers = {
3853 'playlistVideoListContinuation': self._playlist_entries,
3854 'gridContinuation': self._grid_entries,
3855 'itemSectionContinuation': self._post_thread_continuation_entries,
3856 'sectionListContinuation': extract_entries, # for feeds
3857 }
8bdd16b4 3858 continuation_contents = try_get(
69184e41 3859 response, lambda x: x['continuationContents'], dict) or {}
3860 continuation_renderer = None
3861 for key, value in continuation_contents.items():
3862 if key not in known_continuation_renderers:
3462ffa8 3863 continue
69184e41 3864 continuation_renderer = value
3865 continuation_list = [None]
3866 for entry in known_continuation_renderers[key](continuation_renderer):
3867 yield entry
3868 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3869 break
3870 if continuation_renderer:
3871 continue
c5e8d7af 3872
a1b535bd 3873 known_renderers = {
3874 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3875 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3876 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3877 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3878 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3879 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3880 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3881 }
cce889b9 3882 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3883 continuation_items = try_get(
cce889b9 3884 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3885 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3886 video_items_renderer = None
3887 for key, value in continuation_item.items():
3888 if key not in known_renderers:
8bdd16b4 3889 continue
a1b535bd 3890 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3891 continuation_list = [None]
a1b535bd 3892 for entry in known_renderers[key][0](video_items_renderer):
3893 yield entry
9ba5705a 3894 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3895 break
3896 if video_items_renderer:
3897 continue
8bdd16b4 3898 break
9558dcec 3899
8bdd16b4 3900 @staticmethod
3901 def _extract_selected_tab(tabs):
3902 for tab in tabs:
cd684175 3903 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3904 if renderer.get('selected') is True:
3905 return renderer
2b3c2546 3906 else:
8bdd16b4 3907 raise ExtractorError('Unable to find selected tab')
b82f815f 3908
47193e02 3909 @classmethod
3910 def _extract_uploader(cls, data):
8bdd16b4 3911 uploader = {}
47193e02 3912 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3913 owner = try_get(
3914 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3915 if owner:
3916 uploader['uploader'] = owner.get('text')
3917 uploader['uploader_id'] = try_get(
3918 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3919 uploader['uploader_url'] = urljoin(
3920 'https://www.youtube.com/',
3921 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3922 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3923
ac56cf38 3924 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 3925 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 3926 tags = []
b60419c5 3927
8bdd16b4 3928 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 3929 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 3930 renderer = try_get(
3931 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3932 if renderer:
b60419c5 3933 channel_name = renderer.get('title')
3934 channel_url = renderer.get('channelUrl')
3935 channel_id = renderer.get('externalId')
39ed931e 3936 else:
64c0d954 3937 renderer = try_get(
3938 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3939
8bdd16b4 3940 if renderer:
3941 title = renderer.get('title')
ecc97af3 3942 description = renderer.get('description', '')
b60419c5 3943 playlist_id = channel_id
3944 tags = renderer.get('keywords', '').split()
b60419c5 3945
301d07fc 3946 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
3947 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
3948 def _get_uncropped(url):
3949 return url_or_none((url or '').split('=')[0] + '=s0')
3950
3951 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
3952 if avatar_thumbnails:
3953 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
3954 if uncropped_avatar:
3955 avatar_thumbnails.append({
3956 'url': uncropped_avatar,
3957 'id': 'avatar_uncropped',
3958 'preference': 1
3959 })
3960
3961 channel_banners = self._extract_thumbnails(
3962 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
3963 for banner in channel_banners:
3964 banner['preference'] = -10
3965
3966 if channel_banners:
3967 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
3968 if uncropped_banner:
3969 channel_banners.append({
3970 'url': uncropped_banner,
3971 'id': 'banner_uncropped',
3972 'preference': -5
3973 })
3974
3975 primary_thumbnails = self._extract_thumbnails(
3976 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 3977
3462ffa8 3978 if playlist_id is None:
70d5c17b 3979 playlist_id = item_id
f0d785d3 3980
3981 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
3982 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 3983 if title is None:
f0d785d3 3984 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 3985 title += format_field(selected_tab, 'title', ' - %s')
cd684175 3986 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 3987
b60419c5 3988 metadata = {
3989 'playlist_id': playlist_id,
3990 'playlist_title': title,
3991 'playlist_description': description,
3992 'uploader': channel_name,
3993 'uploader_id': channel_id,
3994 'uploader_url': channel_url,
301d07fc 3995 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 3996 'tags': tags,
f0d785d3 3997 'view_count': self._get_count(playlist_stats, 1),
3998 'availability': self._extract_availability(data),
3999 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4000 'playlist_count': self._get_count(playlist_stats, 0),
4001 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4002 }
4003 if not channel_id:
4004 metadata.update(self._extract_uploader(data))
4005 metadata.update({
4006 'channel': metadata['uploader'],
4007 'channel_id': metadata['uploader_id'],
4008 'channel_url': metadata['uploader_url']})
4009 return self.playlist_result(
d069eca7 4010 self._entries(
ac56cf38 4011 selected_tab, playlist_id, ytcfg,
4012 self._extract_account_syncid(ytcfg, data),
4013 self._extract_visitor_data(data, ytcfg)),
b60419c5 4014 **metadata)
73c4ac2c 4015
ac56cf38 4016 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4017 first_id = last_id = response = None
2be71994 4018 for page_num in itertools.count(1):
cd7c66cf 4019 videos = list(self._playlist_entries(playlist))
4020 if not videos:
4021 return
2be71994 4022 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4023 if start >= len(videos):
4024 return
4025 for video in videos[start:]:
4026 if video['id'] == first_id:
4027 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4028 return
4029 yield video
4030 first_id = first_id or videos[0]['id']
4031 last_id = videos[-1]['id']
79360d99 4032 watch_endpoint = try_get(
4033 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4034 headers = self.generate_api_headers(
4035 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4036 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4037 query = {
4038 'playlistId': playlist_id,
4039 'videoId': watch_endpoint.get('videoId') or last_id,
4040 'index': watch_endpoint.get('index') or len(videos),
4041 'params': watch_endpoint.get('params') or 'OAE%3D'
4042 }
4043 response = self._extract_response(
4044 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4045 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4046 check_get_keys='contents'
4047 )
cd7c66cf 4048 playlist = try_get(
79360d99 4049 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4050
ac56cf38 4051 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4052 title = playlist.get('title') or try_get(
4053 data, lambda x: x['titleText']['simpleText'], compat_str)
4054 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4055
4056 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4057 playlist_url = urljoin(url, try_get(
4058 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4059 compat_str))
4060 if playlist_url and playlist_url != url:
4061 return self.url_result(
4062 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4063 video_title=title)
cd7c66cf 4064
8bdd16b4 4065 return self.playlist_result(
ac56cf38 4066 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4067 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4068
47193e02 4069 def _extract_availability(self, data):
4070 """
4071 Gets the availability of a given playlist/tab.
4072 Note: Unless YouTube tells us explicitly, we do not assume it is public
4073 @param data: response
4074 """
4075 is_private = is_unlisted = None
4076 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4077 badge_labels = self._extract_badges(renderer)
4078
4079 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4080 privacy_dropdown_entries = try_get(
4081 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4082 for renderer_dict in privacy_dropdown_entries:
4083 is_selected = try_get(
4084 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4085 if not is_selected:
4086 continue
052e1350 4087 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4088 if label:
4089 badge_labels.add(label.lower())
4090 break
4091
4092 for badge_label in badge_labels:
4093 if badge_label == 'unlisted':
4094 is_unlisted = True
4095 elif badge_label == 'private':
4096 is_private = True
4097 elif badge_label == 'public':
4098 is_unlisted = is_private = False
4099 return self._availability(is_private, False, False, False, is_unlisted)
4100
4101 @staticmethod
4102 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4103 sidebar_renderer = try_get(
4104 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4105 for item in sidebar_renderer:
4106 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4107 if renderer:
4108 return renderer
4109
ac56cf38 4110 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4111 """
4112 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4113 """
5d342002 4114 browse_id = params = None
47193e02 4115 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4116 if not renderer:
4117 return
4118 menu_renderer = try_get(
4119 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4120 for menu_item in menu_renderer:
4121 if not isinstance(menu_item, dict):
358de58c 4122 continue
47193e02 4123 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4124 text = try_get(
4125 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4126 if not text or text.lower() != 'show unavailable videos':
4127 continue
4128 browse_endpoint = try_get(
4129 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4130 browse_id = browse_endpoint.get('browseId')
4131 params = browse_endpoint.get('params')
4132 break
5d342002 4133
11f9be09 4134 headers = self.generate_api_headers(
99e9e001 4135 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4136 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4137 query = {
4138 'params': params or 'wgYCCAA=',
4139 'browseId': browse_id or 'VL%s' % item_id
4140 }
4141 return self._extract_response(
4142 item_id=item_id, headers=headers, query=query,
fe93e2c4 4143 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4144 note='Downloading API JSON with unavailable videos')
358de58c 4145
ac56cf38 4146 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4147 retries = self.get_param('extractor_retries', 3)
62bff2c1 4148 count = -1
ac56cf38 4149 webpage = data = last_error = None
14fdfea9 4150 while count < retries:
62bff2c1 4151 count += 1
14fdfea9 4152 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4153 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4154 if last_error:
c705177d 4155 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4156 try:
4157 webpage = self._download_webpage(
4158 url, item_id,
4159 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4160 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4161 except ExtractorError as e:
4162 if isinstance(e.cause, network_exceptions):
4163 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4164 last_error = error_to_compat_str(e.cause or e.msg)
4165 if count < retries:
4166 continue
4167 if fatal:
4168 raise
4169 self.report_warning(error_to_compat_str(e))
14fdfea9 4170 break
ac56cf38 4171 else:
4172 try:
4173 self._extract_and_report_alerts(data)
4174 except ExtractorError as e:
4175 if fatal:
4176 raise
4177 self.report_warning(error_to_compat_str(e))
4178 break
4179
4180 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4181 break
4182
4183 last_error = 'Incomplete yt initial data received'
4184 if count >= retries:
4185 if fatal:
4186 raise ExtractorError(last_error)
4187 self.report_warning(last_error)
4188 break
4189
cd7c66cf 4190 return webpage, data
4191
ac56cf38 4192 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4193 data = None
4194 if 'webpage' not in self._configuration_arg('skip'):
4195 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4196 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4197 if not data:
4198 if not ytcfg and self.is_authenticated:
4199 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4200 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4201 raise ExtractorError(
4202 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4203 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4204 expected=True)
4205 self.report_warning(msg, only_once=True)
4206 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4207 return data, ytcfg
4208
4209 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4210 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4211 resolve_response = self._extract_response(
4212 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4213 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4214 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4215 for ep_key, ep in endpoints.items():
4216 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4217 if params:
4218 return self._extract_response(
4219 item_id=item_id, query=params, ep=ep, headers=headers,
4220 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4221 check_get_keys=('contents', 'currentVideoEndpoint'))
4222 err_note = 'Failed to resolve url (does the playlist exist?)'
4223 if fatal:
4224 raise ExtractorError(err_note, expected=True)
4225 self.report_warning(err_note, item_id)
4226
a6213a49 4227 @staticmethod
4228 def _smuggle_data(entries, data):
4229 for entry in entries:
4230 if data:
4231 entry['url'] = smuggle_url(entry['url'], data)
4232 yield entry
4233
4234 _SEARCH_PARAMS = None
4235
4236 def _search_results(self, query, params=NO_DEFAULT):
4237 data = {'query': query}
4238 if params is NO_DEFAULT:
4239 params = self._SEARCH_PARAMS
4240 if params:
4241 data['params'] = params
a61fd4cf 4242 continuation_list = [None]
a6213a49 4243 for page_num in itertools.count(1):
a61fd4cf 4244 data.update(continuation_list[0] or {})
a6213a49 4245 search = self._extract_response(
4246 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
a61fd4cf 4247 check_get_keys=('contents', 'onResponseReceivedCommands'))
a6213a49 4248 slr_contents = try_get(
4249 search,
4250 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4251 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4252 list)
a61fd4cf 4253 yield from self._extract_entries({'contents': slr_contents}, continuation_list)
4254 if not continuation_list[0]:
a6213a49 4255 break
4256
4257
4258class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4259 IE_DESC = 'YouTube Tabs'
4260 _VALID_URL = r'''(?x:
4261 https?://
4262 (?:\w+\.)?
4263 (?:
4264 youtube(?:kids)?\.com|
4265 %(invidious)s
4266 )/
4267 (?:
4268 (?P<channel_type>channel|c|user|browse)/|
4269 (?P<not_channel>
4270 feed/|hashtag/|
4271 (?:playlist|watch)\?.*?\blist=
4272 )|
4273 (?!(?:%(reserved_names)s)\b) # Direct URLs
4274 )
4275 (?P<id>[^/?\#&]+)
4276 )''' % {
4277 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4278 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4279 }
4280 IE_NAME = 'youtube:tab'
4281
4282 _TESTS = [{
4283 'note': 'playlists, multipage',
4284 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4285 'playlist_mincount': 94,
4286 'info_dict': {
4287 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4288 'title': 'Igor Kleiner - Playlists',
a6213a49 4289 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4290 'uploader': 'Igor Kleiner',
a6213a49 4291 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4292 'channel': 'Igor Kleiner',
4293 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4294 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4295 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4296 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4297 'channel_follower_count': int
a6213a49 4298 },
4299 }, {
4300 'note': 'playlists, multipage, different order',
4301 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4302 'playlist_mincount': 94,
4303 'info_dict': {
4304 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4305 'title': 'Igor Kleiner - Playlists',
a6213a49 4306 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4307 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4308 'uploader': 'Igor Kleiner',
4309 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4310 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4311 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4312 'channel': 'Igor Kleiner',
4313 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4314 'channel_follower_count': int
a6213a49 4315 },
4316 }, {
4317 'note': 'playlists, series',
4318 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4319 'playlist_mincount': 5,
4320 'info_dict': {
4321 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4322 'title': '3Blue1Brown - Playlists',
4323 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4324 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4325 'uploader': '3Blue1Brown',
976ae3ea 4326 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4327 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4328 'channel': '3Blue1Brown',
4329 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4330 'tags': ['Mathematics'],
6c73052c 4331 'channel_follower_count': int
a6213a49 4332 },
4333 }, {
4334 'note': 'playlists, singlepage',
4335 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4336 'playlist_mincount': 4,
4337 'info_dict': {
4338 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4339 'title': 'ThirstForScience - Playlists',
4340 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4341 'uploader': 'ThirstForScience',
4342 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4343 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4344 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4345 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4346 'tags': 'count:13',
4347 'channel': 'ThirstForScience',
6c73052c 4348 'channel_follower_count': int
a6213a49 4349 }
4350 }, {
4351 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4352 'only_matching': True,
4353 }, {
4354 'note': 'basic, single video playlist',
4355 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4356 'info_dict': {
4357 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4358 'uploader': 'Sergey M.',
4359 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4360 'title': 'youtube-dl public playlist',
976ae3ea 4361 'description': '',
4362 'tags': [],
4363 'view_count': int,
4364 'modified_date': '20201130',
4365 'channel': 'Sergey M.',
4366 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4367 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4368 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4369 },
4370 'playlist_count': 1,
4371 }, {
4372 'note': 'empty playlist',
4373 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4374 'info_dict': {
4375 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4376 'uploader': 'Sergey M.',
4377 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4378 'title': 'youtube-dl empty playlist',
976ae3ea 4379 'tags': [],
4380 'channel': 'Sergey M.',
4381 'description': '',
4382 'modified_date': '20160902',
4383 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4384 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4385 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4386 },
4387 'playlist_count': 0,
4388 }, {
4389 'note': 'Home tab',
4390 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4391 'info_dict': {
4392 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4393 'title': 'lex will - Home',
4394 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4395 'uploader': 'lex will',
4396 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4397 'channel': 'lex will',
4398 'tags': ['bible', 'history', 'prophesy'],
4399 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4400 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4401 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4402 'channel_follower_count': int
a6213a49 4403 },
4404 'playlist_mincount': 2,
4405 }, {
4406 'note': 'Videos tab',
4407 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4408 'info_dict': {
4409 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4410 'title': 'lex will - Videos',
4411 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4412 'uploader': 'lex will',
4413 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4414 'tags': ['bible', 'history', 'prophesy'],
4415 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4416 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4417 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4418 'channel': 'lex will',
6c73052c 4419 'channel_follower_count': int
a6213a49 4420 },
4421 'playlist_mincount': 975,
4422 }, {
4423 'note': 'Videos tab, sorted by popular',
4424 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4425 'info_dict': {
4426 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4427 'title': 'lex will - Videos',
4428 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4429 'uploader': 'lex will',
4430 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4431 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4432 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4433 'channel': 'lex will',
4434 'tags': ['bible', 'history', 'prophesy'],
4435 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4436 'channel_follower_count': int
a6213a49 4437 },
4438 'playlist_mincount': 199,
4439 }, {
4440 'note': 'Playlists tab',
4441 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4442 'info_dict': {
4443 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4444 'title': 'lex will - Playlists',
4445 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4446 'uploader': 'lex will',
4447 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4448 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4449 'channel': 'lex will',
4450 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4451 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4452 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4453 'channel_follower_count': int
a6213a49 4454 },
4455 'playlist_mincount': 17,
4456 }, {
4457 'note': 'Community tab',
4458 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4459 'info_dict': {
4460 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4461 'title': 'lex will - Community',
4462 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4463 'uploader': 'lex will',
4464 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4465 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4466 'channel': 'lex will',
4467 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4468 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4469 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4470 'channel_follower_count': int
a6213a49 4471 },
4472 'playlist_mincount': 18,
4473 }, {
4474 'note': 'Channels tab',
4475 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4476 'info_dict': {
4477 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4478 'title': 'lex will - Channels',
4479 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4480 'uploader': 'lex will',
4481 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4482 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4483 'channel': 'lex will',
4484 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4485 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4486 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4487 'channel_follower_count': int
a6213a49 4488 },
4489 'playlist_mincount': 12,
4490 }, {
4491 'note': 'Search tab',
4492 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4493 'playlist_mincount': 40,
4494 'info_dict': {
4495 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4496 'title': '3Blue1Brown - Search - linear algebra',
4497 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4498 'uploader': '3Blue1Brown',
4499 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4500 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4501 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4502 'tags': ['Mathematics'],
4503 'channel': '3Blue1Brown',
4504 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4505 'channel_follower_count': int
a6213a49 4506 },
4507 }, {
4508 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4509 'only_matching': True,
4510 }, {
4511 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4512 'only_matching': True,
4513 }, {
4514 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4515 'only_matching': True,
4516 }, {
4517 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4518 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4519 'info_dict': {
4520 'title': '29C3: Not my department',
4521 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4522 'uploader': 'Christiaan008',
4523 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4524 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4525 'tags': [],
4526 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4527 'view_count': int,
4528 'modified_date': '20150605',
4529 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4530 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4531 'channel': 'Christiaan008',
a6213a49 4532 },
4533 'playlist_count': 96,
4534 }, {
4535 'note': 'Large playlist',
4536 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4537 'info_dict': {
4538 'title': 'Uploads from Cauchemar',
4539 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4540 'uploader': 'Cauchemar',
4541 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4542 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4543 'tags': [],
4544 'modified_date': r're:\d{8}',
4545 'channel': 'Cauchemar',
4546 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4547 'view_count': int,
4548 'description': '',
4549 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4550 },
4551 'playlist_mincount': 1123,
976ae3ea 4552 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4553 }, {
4554 'note': 'even larger playlist, 8832 videos',
4555 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4556 'only_matching': True,
4557 }, {
4558 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4559 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4560 'info_dict': {
4561 'title': 'Uploads from Interstellar Movie',
4562 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4563 'uploader': 'Interstellar Movie',
4564 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4565 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4566 'tags': [],
4567 'view_count': int,
4568 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4569 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4570 'channel': 'Interstellar Movie',
4571 'description': '',
4572 'modified_date': r're:\d{8}',
a6213a49 4573 },
4574 'playlist_mincount': 21,
4575 }, {
4576 'note': 'Playlist with "show unavailable videos" button',
4577 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4578 'info_dict': {
4579 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4580 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4581 'uploader': 'Phim Siêu Nhân Nhật Bản',
4582 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4583 'view_count': int,
4584 'channel': 'Phim Siêu Nhân Nhật Bản',
4585 'tags': [],
4586 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4587 'description': '',
4588 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4589 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4590 'modified_date': r're:\d{8}',
a6213a49 4591 },
4592 'playlist_mincount': 200,
976ae3ea 4593 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4594 }, {
4595 'note': 'Playlist with unavailable videos in page 7',
4596 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4597 'info_dict': {
4598 'title': 'Uploads from BlankTV',
4599 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4600 'uploader': 'BlankTV',
4601 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4602 'channel': 'BlankTV',
4603 'channel_url': 'https://www.youtube.com/c/blanktv',
4604 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4605 'view_count': int,
4606 'tags': [],
4607 'uploader_url': 'https://www.youtube.com/c/blanktv',
4608 'modified_date': r're:\d{8}',
4609 'description': '',
a6213a49 4610 },
4611 'playlist_mincount': 1000,
976ae3ea 4612 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4613 }, {
4614 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4615 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4616 'info_dict': {
4617 'title': 'Data Analysis with Dr Mike Pound',
4618 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4619 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4620 'uploader': 'Computerphile',
4621 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4622 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4623 'tags': [],
4624 'view_count': int,
4625 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4626 'channel_url': 'https://www.youtube.com/user/Computerphile',
4627 'channel': 'Computerphile',
a6213a49 4628 },
4629 'playlist_mincount': 11,
4630 }, {
4631 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4632 'only_matching': True,
4633 }, {
4634 'note': 'Playlist URL that does not actually serve a playlist',
4635 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4636 'info_dict': {
4637 'id': 'FqZTN594JQw',
4638 'ext': 'webm',
4639 'title': "Smiley's People 01 detective, Adventure Series, Action",
4640 'uploader': 'STREEM',
4641 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4642 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4643 'upload_date': '20150526',
4644 'license': 'Standard YouTube License',
4645 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4646 'categories': ['People & Blogs'],
4647 'tags': list,
4648 'view_count': int,
4649 'like_count': int,
a6213a49 4650 },
4651 'params': {
4652 'skip_download': True,
4653 },
4654 'skip': 'This video is not available.',
4655 'add_ie': [YoutubeIE.ie_key()],
4656 }, {
4657 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4658 'only_matching': True,
4659 }, {
4660 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4661 'only_matching': True,
4662 }, {
4663 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4664 'info_dict': {
6c73052c 4665 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4666 'ext': 'mp4',
976ae3ea 4667 'title': str,
a6213a49 4668 'uploader': 'Sky News',
4669 'uploader_id': 'skynews',
4670 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4671 'upload_date': r're:\d{8}',
976ae3ea 4672 'description': str,
a6213a49 4673 'categories': ['News & Politics'],
4674 'tags': list,
4675 'like_count': int,
6c73052c 4676 'release_timestamp': 1642502819,
976ae3ea 4677 'channel': 'Sky News',
4678 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4679 'age_limit': 0,
4680 'view_count': int,
6c73052c 4681 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4682 'playable_in_embed': True,
6c73052c 4683 'release_date': '20220118',
976ae3ea 4684 'availability': 'public',
4685 'live_status': 'is_live',
4686 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4687 'channel_follower_count': int
a6213a49 4688 },
4689 'params': {
4690 'skip_download': True,
4691 },
976ae3ea 4692 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4693 }, {
4694 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4695 'info_dict': {
4696 'id': 'a48o2S1cPoo',
4697 'ext': 'mp4',
4698 'title': 'The Young Turks - Live Main Show',
4699 'uploader': 'The Young Turks',
4700 'uploader_id': 'TheYoungTurks',
4701 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4702 'upload_date': '20150715',
4703 'license': 'Standard YouTube License',
4704 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4705 'categories': ['News & Politics'],
4706 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4707 'like_count': int,
a6213a49 4708 },
4709 'params': {
4710 'skip_download': True,
4711 },
4712 'only_matching': True,
4713 }, {
4714 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4715 'only_matching': True,
4716 }, {
4717 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4718 'only_matching': True,
4719 }, {
4720 'note': 'A channel that is not live. Should raise error',
4721 'url': 'https://www.youtube.com/user/numberphile/live',
4722 'only_matching': True,
4723 }, {
4724 'url': 'https://www.youtube.com/feed/trending',
4725 'only_matching': True,
4726 }, {
4727 'url': 'https://www.youtube.com/feed/library',
4728 'only_matching': True,
4729 }, {
4730 'url': 'https://www.youtube.com/feed/history',
4731 'only_matching': True,
4732 }, {
4733 'url': 'https://www.youtube.com/feed/subscriptions',
4734 'only_matching': True,
4735 }, {
4736 'url': 'https://www.youtube.com/feed/watch_later',
4737 'only_matching': True,
4738 }, {
4739 'note': 'Recommended - redirects to home page.',
4740 'url': 'https://www.youtube.com/feed/recommended',
4741 'only_matching': True,
4742 }, {
4743 'note': 'inline playlist with not always working continuations',
4744 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4745 'only_matching': True,
4746 }, {
4747 'url': 'https://www.youtube.com/course',
4748 'only_matching': True,
4749 }, {
4750 'url': 'https://www.youtube.com/zsecurity',
4751 'only_matching': True,
4752 }, {
4753 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4754 'only_matching': True,
4755 }, {
4756 'url': 'https://www.youtube.com/TheYoungTurks/live',
4757 'only_matching': True,
4758 }, {
4759 'url': 'https://www.youtube.com/hashtag/cctv9',
4760 'info_dict': {
4761 'id': 'cctv9',
4762 'title': '#cctv9',
976ae3ea 4763 'tags': [],
a6213a49 4764 },
4765 'playlist_mincount': 350,
4766 }, {
4767 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4768 'only_matching': True,
4769 }, {
4770 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4771 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4772 'only_matching': True
4773 }, {
4774 'note': '/browse/ should redirect to /channel/',
4775 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4776 'only_matching': True
4777 }, {
4778 'note': 'VLPL, should redirect to playlist?list=PL...',
4779 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4780 'info_dict': {
4781 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4782 'uploader': 'NoCopyrightSounds',
4783 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4784 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4785 'title': 'NCS Releases',
976ae3ea 4786 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4787 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4788 'modified_date': r're:\d{8}',
4789 'view_count': int,
4790 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4791 'tags': [],
4792 'channel': 'NoCopyrightSounds',
a6213a49 4793 },
4794 'playlist_mincount': 166,
976ae3ea 4795 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4796 }, {
4797 'note': 'Topic, should redirect to playlist?list=UU...',
4798 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4799 'info_dict': {
4800 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4801 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4802 'title': 'Uploads from Royalty Free Music - Topic',
4803 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4804 'tags': [],
4805 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4806 'channel': 'Royalty Free Music - Topic',
4807 'view_count': int,
4808 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4809 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4810 'modified_date': r're:\d{8}',
4811 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4812 'description': '',
a6213a49 4813 },
4814 'expected_warnings': [
a6213a49 4815 'The URL does not have a videos tab',
976ae3ea 4816 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4817 ],
4818 'playlist_mincount': 101,
4819 }, {
4820 'note': 'Topic without a UU playlist',
4821 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4822 'info_dict': {
4823 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4824 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4825 'tags': [],
a6213a49 4826 },
4827 'expected_warnings': [
976ae3ea 4828 'the playlist redirect gave error',
a6213a49 4829 ],
4830 'playlist_mincount': 9,
4831 }, {
4832 'note': 'Youtube music Album',
4833 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4834 'info_dict': {
4835 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4836 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 4837 'tags': [],
4838 'view_count': int,
4839 'description': '',
4840 'availability': 'unlisted',
4841 'modified_date': r're:\d{8}',
a6213a49 4842 },
4843 'playlist_count': 50,
4844 }, {
4845 'note': 'unlisted single video playlist',
4846 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4847 'info_dict': {
4848 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4849 'uploader': 'colethedj',
4850 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4851 'title': 'yt-dlp unlisted playlist test',
976ae3ea 4852 'availability': 'unlisted',
4853 'tags': [],
4854 'modified_date': '20211208',
4855 'channel': 'colethedj',
4856 'view_count': int,
4857 'description': '',
4858 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4859 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4860 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 4861 },
4862 'playlist_count': 1,
4863 }, {
4864 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4865 'url': 'https://www.youtube.com/feed/recommended',
4866 'info_dict': {
4867 'id': 'recommended',
4868 'title': 'recommended',
6c73052c 4869 'tags': [],
a6213a49 4870 },
4871 'playlist_mincount': 50,
4872 'params': {
4873 'skip_download': True,
4874 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4875 },
4876 }, {
4877 'note': 'API Fallback: /videos tab, sorted by oldest first',
4878 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4879 'info_dict': {
4880 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4881 'title': 'Cody\'sLab - Videos',
4882 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4883 'uploader': 'Cody\'sLab',
4884 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 4885 'channel': 'Cody\'sLab',
4886 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4887 'tags': [],
4888 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4889 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 4890 'channel_follower_count': int
a6213a49 4891 },
4892 'playlist_mincount': 650,
4893 'params': {
4894 'skip_download': True,
4895 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4896 },
4897 }, {
4898 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4899 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4900 'info_dict': {
4901 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4902 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4903 'title': 'Uploads from Royalty Free Music - Topic',
4904 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4905 'modified_date': r're:\d{8}',
4906 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4907 'description': '',
4908 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4909 'tags': [],
4910 'channel': 'Royalty Free Music - Topic',
4911 'view_count': int,
4912 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 4913 },
4914 'expected_warnings': [
976ae3ea 4915 'does not have a videos tab',
4916 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4917 ],
4918 'playlist_mincount': 101,
4919 'params': {
4920 'skip_download': True,
4921 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4922 },
4923 }]
4924
4925 @classmethod
4926 def suitable(cls, url):
4927 return False if YoutubeIE.suitable(url) else super(
4928 YoutubeTabIE, cls).suitable(url)
9297939e 4929
cd7c66cf 4930 def _real_extract(self, url):
9297939e 4931 url, smuggled_data = unsmuggle_url(url, {})
4932 if self.is_music_url(url):
4933 smuggled_data['is_music_url'] = True
fe03a6cd 4934 info_dict = self.__real_extract(url, smuggled_data)
9297939e 4935 if info_dict.get('entries'):
4936 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4937 return info_dict
4938
64f36541 4939 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 4940
4941 def __real_extract(self, url, smuggled_data):
cd7c66cf 4942 item_id = self._match_id(url)
4943 url = compat_urlparse.urlunparse(
4944 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 4945 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 4946
fe03a6cd 4947 def get_mobj(url):
37e57a9f 4948 mobj = self._URL_RE.match(url).groupdict()
07cce701 4949 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 4950 return mobj
4951
37e57a9f 4952 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 4953 # Youtube returns incomplete data if tabname is not lower case
4954 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 4955 if is_channel:
4956 if smuggled_data.get('is_music_url'):
37e57a9f 4957 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 4958 item_id = item_id[2:]
37e57a9f 4959 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
4960 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 4961 mdata = self._extract_tab_endpoint(
37e57a9f 4962 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
4963 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
4964 get_all=False, expected_type=compat_str)
ac56cf38 4965 if not murl:
37e57a9f 4966 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 4967 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 4968 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
4969 pre = f'https://www.youtube.com/channel/{item_id}'
4970
64f36541 4971 original_tab_name = tab
fe03a6cd 4972 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4973 # Home URLs should redirect to /videos/
37e57a9f 4974 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
4975 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 4976 tab = '/videos'
4977
4978 url = ''.join((pre, tab, post))
4979 mobj = get_mobj(url)
cd7c66cf 4980
4981 # Handle both video/playlist URLs
201c1459 4982 qs = parse_qs(url)
37e57a9f 4983 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 4984
fe03a6cd 4985 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 4986 if not playlist_id:
fe03a6cd 4987 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 4988 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 4989 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 4990 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
4991 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 4992 mobj = get_mobj(url)
cd7c66cf 4993
4994 if video_id and playlist_id:
a06916d9 4995 if self.get_param('noplaylist'):
37e57a9f 4996 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
4997 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
4998 ie=YoutubeIE.ie_key(), video_id=video_id)
4999 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5000
ac56cf38 5001 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5002
37e57a9f 5003 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5004 if tabs:
5005 selected_tab = self._extract_selected_tab(tabs)
64f36541 5006 selected_tab_name = selected_tab.get('title', '').lower()
5007 if selected_tab_name == 'home':
5008 selected_tab_name = 'featured'
5009 requested_tab_name = mobj['tab'][1:]
09f1580e 5010 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5011 if requested_tab_name == 'live':
09f1580e 5012 # Live tab should have redirected to the video
5013 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5014 if requested_tab_name not in ('', selected_tab_name):
5015 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5016 if not original_tab_name:
5017 if item_id[:2] == 'UC':
5018 # Topic channels don't have /videos. Use the equivalent playlist instead
5019 pl_id = f'UU{item_id[2:]}'
5020 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5021 try:
5022 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5023 except ExtractorError:
5024 redirect_warning += ' and the playlist redirect gave error'
5025 else:
5026 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5027 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5028 if selected_tab_name and selected_tab_name != requested_tab_name:
5029 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5030 else:
5031 raise ExtractorError(redirect_warning, expected=True)
18db7548 5032
37e57a9f 5033 if redirect_warning:
64f36541 5034 self.to_screen(redirect_warning)
37e57a9f 5035 self.write_debug(f'Final URL: {url}')
18db7548 5036
358de58c 5037 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5038 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5039 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5040 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5041 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5042 if tabs:
ac56cf38 5043 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5044
37e57a9f 5045 playlist = traverse_obj(
5046 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5047 if playlist:
ac56cf38 5048 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5049
37e57a9f 5050 video_id = traverse_obj(
5051 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5052 if video_id:
09f1580e 5053 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5054 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5055 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5056 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5057
8bdd16b4 5058 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5059
c5e8d7af 5060
8bdd16b4 5061class YoutubePlaylistIE(InfoExtractor):
96565c7e 5062 IE_DESC = 'YouTube playlists'
8bdd16b4 5063 _VALID_URL = r'''(?x)(?:
5064 (?:https?://)?
5065 (?:\w+\.)?
5066 (?:
5067 (?:
5068 youtube(?:kids)?\.com|
d9190e44 5069 %(invidious)s
8bdd16b4 5070 )
5071 /.*?\?.*?\blist=
5072 )?
5073 (?P<id>%(playlist_id)s)
d9190e44
RH
5074 )''' % {
5075 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5076 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5077 }
8bdd16b4 5078 IE_NAME = 'youtube:playlist'
cdc628a4 5079 _TESTS = [{
8bdd16b4 5080 'note': 'issue #673',
5081 'url': 'PLBB231211A4F62143',
cdc628a4 5082 'info_dict': {
8bdd16b4 5083 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5084 'id': 'PLBB231211A4F62143',
976ae3ea 5085 'uploader': 'Wickman',
8bdd16b4 5086 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5087 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5088 'view_count': int,
5089 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5090 'modified_date': r're:\d{8}',
5091 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5092 'channel': 'Wickman',
5093 'tags': [],
5094 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5095 },
5096 'playlist_mincount': 29,
5097 }, {
5098 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5099 'info_dict': {
5100 'title': 'YDL_safe_search',
5101 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5102 },
5103 'playlist_count': 2,
5104 'skip': 'This playlist is private',
9558dcec 5105 }, {
8bdd16b4 5106 'note': 'embedded',
5107 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5108 'playlist_count': 4,
9558dcec 5109 'info_dict': {
8bdd16b4 5110 'title': 'JODA15',
5111 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5112 'uploader': 'milan',
5113 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5114 'description': '',
5115 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5116 'tags': [],
5117 'modified_date': '20140919',
5118 'view_count': int,
5119 'channel': 'milan',
5120 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5121 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5122 },
5123 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5124 }, {
8bdd16b4 5125 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5126 'playlist_mincount': 654,
8bdd16b4 5127 'info_dict': {
5128 'title': '2018 Chinese New Singles (11/6 updated)',
5129 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5130 'uploader': 'LBK',
5131 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5132 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5133 'channel': 'LBK',
5134 'view_count': int,
5135 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5136 'tags': [],
5137 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5138 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5139 'modified_date': r're:\d{8}',
5140 },
5141 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5142 }, {
29f7c58a 5143 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5144 'only_matching': True,
5145 }, {
5146 # music album playlist
5147 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5148 'only_matching': True,
5149 }]
5150
5151 @classmethod
5152 def suitable(cls, url):
201c1459 5153 if YoutubeTabIE.suitable(url):
5154 return False
49a57e70 5155 from ..utils import parse_qs
201c1459 5156 qs = parse_qs(url)
5157 if qs.get('v', [None])[0]:
5158 return False
5159 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5160
5161 def _real_extract(self, url):
5162 playlist_id = self._match_id(url)
46953e7e 5163 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5164 url = update_url_query(
5165 'https://www.youtube.com/playlist',
5166 parse_qs(url) or {'list': playlist_id})
5167 if is_music_url:
5168 url = smuggle_url(url, {'is_music_url': True})
5169 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5170
5171
5172class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5173 IE_DESC = 'youtu.be'
29f7c58a 5174 _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}
5175 _TESTS = [{
8bdd16b4 5176 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5177 'info_dict': {
5178 'id': 'yeWKywCrFtk',
5179 'ext': 'mp4',
5180 'title': 'Small Scale Baler and Braiding Rugs',
5181 'uploader': 'Backus-Page House Museum',
5182 'uploader_id': 'backuspagemuseum',
5183 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5184 'upload_date': '20161008',
5185 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5186 'categories': ['Nonprofits & Activism'],
5187 'tags': list,
5188 'like_count': int,
976ae3ea 5189 'age_limit': 0,
5190 'playable_in_embed': True,
5191 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5192 'channel': 'Backus-Page House Museum',
5193 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5194 'live_status': 'not_live',
5195 'view_count': int,
5196 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5197 'availability': 'public',
5198 'duration': 59,
8bdd16b4 5199 },
5200 'params': {
5201 'noplaylist': True,
5202 'skip_download': True,
5203 },
39e7107d 5204 }, {
8bdd16b4 5205 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5206 'only_matching': True,
cdc628a4
PH
5207 }]
5208
8bdd16b4 5209 def _real_extract(self, url):
5ad28e7f 5210 mobj = self._match_valid_url(url)
29f7c58a 5211 video_id = mobj.group('id')
5212 playlist_id = mobj.group('playlist_id')
8bdd16b4 5213 return self.url_result(
29f7c58a 5214 update_url_query('https://www.youtube.com/watch', {
5215 'v': video_id,
5216 'list': playlist_id,
5217 'feature': 'youtu.be',
5218 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5219
5220
b6ce9bb0 5221class YoutubeLivestreamEmbedIE(InfoExtractor):
5222 IE_DESC = 'YouTube livestream embeds'
5223 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5224 _TESTS = [{
5225 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5226 'only_matching': True,
5227 }]
5228
5229 def _real_extract(self, url):
5230 channel_id = self._match_id(url)
5231 return self.url_result(
5232 f'https://www.youtube.com/channel/{channel_id}/live',
5233 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5234
5235
8bdd16b4 5236class YoutubeYtUserIE(InfoExtractor):
96565c7e 5237 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5238 IE_NAME = 'youtube:user'
8bdd16b4 5239 _VALID_URL = r'ytuser:(?P<id>.+)'
5240 _TESTS = [{
5241 'url': 'ytuser:phihag',
5242 'only_matching': True,
5243 }]
5244
5245 def _real_extract(self, url):
5246 user_id = self._match_id(url)
5247 return self.url_result(
c586f9e8 5248 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5249 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5250
b05654f0 5251
3d3dddc9 5252class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5253 IE_NAME = 'youtube:favorites'
96565c7e 5254 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5255 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5256 _LOGIN_REQUIRED = True
5257 _TESTS = [{
5258 'url': ':ytfav',
5259 'only_matching': True,
5260 }, {
5261 'url': ':ytfavorites',
5262 'only_matching': True,
5263 }]
5264
5265 def _real_extract(self, url):
5266 return self.url_result(
5267 'https://www.youtube.com/playlist?list=LL',
5268 ie=YoutubeTabIE.ie_key())
5269
5270
a6213a49 5271class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5272 IE_DESC = 'YouTube search'
78caa52a 5273 IE_NAME = 'youtube:search'
b05654f0 5274 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5275 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
9dd8e46a 5276 _TESTS = []
b05654f0 5277
a61fd4cf 5278
5f7cb91a 5279class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5280 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5281 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5282 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5283 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
75dff0ee 5284
c9ae7b95 5285
a6213a49 5286class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5287 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5288 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5289 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
3462ffa8 5290 _TESTS = [{
5291 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5292 'playlist_mincount': 5,
5293 'info_dict': {
11f9be09 5294 'id': 'youtube-dl test video',
3462ffa8 5295 'title': 'youtube-dl test video',
5296 }
a61fd4cf 5297 }, {
5298 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5299 'playlist_mincount': 5,
5300 'info_dict': {
5301 'id': 'python',
5302 'title': 'python',
5303 }
5304
3462ffa8 5305 }, {
5306 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5307 'only_matching': True,
5308 }]
5309
5310 def _real_extract(self, url):
4dfbf869 5311 qs = parse_qs(url)
386e1dd9 5312 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5313 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5314
5315
5316class YoutubeFeedsInfoExtractor(YoutubeTabIE):
d7ae0639 5317 """
25f14e9f 5318 Base class for feed extractors
3d3dddc9 5319 Subclasses must define the _FEED_NAME property.
d7ae0639 5320 """
b2e8bc1b 5321 _LOGIN_REQUIRED = True
ef2f3c7f 5322 _TESTS = []
d7ae0639
JMF
5323
5324 @property
5325 def IE_NAME(self):
78caa52a 5326 return 'youtube:%s' % self._FEED_NAME
04cc9617 5327
3853309f 5328 def _real_extract(self, url):
3d3dddc9 5329 return self.url_result(
5330 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
5331 ie=YoutubeTabIE.ie_key())
25f14e9f
S
5332
5333
ef2f3c7f 5334class YoutubeWatchLaterIE(InfoExtractor):
5335 IE_NAME = 'youtube:watchlater'
96565c7e 5336 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5337 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5338 _TESTS = [{
8bdd16b4 5339 'url': ':ytwatchlater',
bc7a9cd8
S
5340 'only_matching': True,
5341 }]
25f14e9f
S
5342
5343 def _real_extract(self, url):
ef2f3c7f 5344 return self.url_result(
5345 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5346
5347
25f14e9f 5348class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5349 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5350 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5351 _FEED_NAME = 'recommended'
45db527f 5352 _LOGIN_REQUIRED = False
3d3dddc9 5353 _TESTS = [{
5354 'url': ':ytrec',
5355 'only_matching': True,
5356 }, {
5357 'url': ':ytrecommended',
5358 'only_matching': True,
5359 }, {
5360 'url': 'https://youtube.com',
5361 'only_matching': True,
5362 }]
1ed5b5c9 5363
1ed5b5c9 5364
25f14e9f 5365class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5366 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5367 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5368 _FEED_NAME = 'subscriptions'
3d3dddc9 5369 _TESTS = [{
5370 'url': ':ytsubs',
5371 'only_matching': True,
5372 }, {
5373 'url': ':ytsubscriptions',
5374 'only_matching': True,
5375 }]
1ed5b5c9 5376
1ed5b5c9 5377
25f14e9f 5378class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5379 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5380 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5381 _FEED_NAME = 'history'
3d3dddc9 5382 _TESTS = [{
5383 'url': ':ythistory',
5384 'only_matching': True,
5385 }]
1ed5b5c9
JMF
5386
5387
15870e90
PH
5388class YoutubeTruncatedURLIE(InfoExtractor):
5389 IE_NAME = 'youtube:truncated_url'
5390 IE_DESC = False # Do not list
975d35db 5391 _VALID_URL = r'''(?x)
b95aab84
PH
5392 (?:https?://)?
5393 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5394 (?:watch\?(?:
c4808c60 5395 feature=[a-z_]+|
b95aab84
PH
5396 annotation_id=annotation_[^&]+|
5397 x-yt-cl=[0-9]+|
c1708b89 5398 hl=[^&]*|
287be8c6 5399 t=[0-9]+
b95aab84
PH
5400 )?
5401 |
5402 attribution_link\?a=[^&]+
5403 )
5404 $
975d35db 5405 '''
15870e90 5406
c4808c60 5407 _TESTS = [{
2d3d2997 5408 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5409 'only_matching': True,
dc2fc736 5410 }, {
2d3d2997 5411 'url': 'https://www.youtube.com/watch?',
dc2fc736 5412 'only_matching': True,
b95aab84
PH
5413 }, {
5414 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5415 'only_matching': True,
5416 }, {
5417 'url': 'https://www.youtube.com/watch?feature=foo',
5418 'only_matching': True,
c1708b89
PH
5419 }, {
5420 'url': 'https://www.youtube.com/watch?hl=en-GB',
5421 'only_matching': True,
287be8c6
PH
5422 }, {
5423 'url': 'https://www.youtube.com/watch?t=2372',
5424 'only_matching': True,
c4808c60
PH
5425 }]
5426
15870e90
PH
5427 def _real_extract(self, url):
5428 raise ExtractorError(
78caa52a
PH
5429 'Did you forget to quote the URL? Remember that & is a meta '
5430 'character in most shells, so you want to put the URL in quotes, '
3867038a 5431 'like youtube-dl '
2d3d2997 5432 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5433 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5434 expected=True)
772fd5cc
PH
5435
5436
3cd786db 5437class YoutubeClipIE(InfoExtractor):
5438 IE_NAME = 'youtube:clip'
5439 IE_DESC = False # Do not list
5440 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5441
5442 def _real_extract(self, url):
5443 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5444 return self.url_result(url, 'Generic')
5445
5446
772fd5cc
PH
5447class YoutubeTruncatedIDIE(InfoExtractor):
5448 IE_NAME = 'youtube:truncated_id'
5449 IE_DESC = False # Do not list
b95aab84 5450 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5451
5452 _TESTS = [{
5453 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5454 'only_matching': True,
5455 }]
5456
5457 def _real_extract(self, url):
5458 video_id = self._match_id(url)
5459 raise ExtractorError(
5460 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5461 expected=True)