]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[compat] Fix `compat.WINDOWS_VT_MODE`
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
c5e8d7af 16
b05654f0 17from .common import InfoExtractor, SearchInfoExtractor
1890fc63 18from ..compat import functools # isort: split
4bb4a188 19from ..compat import (
edf3e38e 20 compat_chr,
29f7c58a 21 compat_HTTPError,
c5e8d7af 22 compat_parse_qs,
545cc85d 23 compat_str,
7fd002c0 24 compat_urllib_parse_unquote_plus,
15707c7e 25 compat_urllib_parse_urlencode,
7c80519c 26 compat_urllib_parse_urlparse,
7c61bd36 27 compat_urlparse,
4bb4a188 28)
545cc85d 29from ..jsinterp import JSInterpreter
4bb4a188 30from ..utils import (
f8271158 31 NO_DEFAULT,
32 ExtractorError,
720c3099 33 bug_reports_message,
82d02080 34 classproperty,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
2d30521a 39 float_or_none,
11f9be09 40 format_field,
ff91cf74 41 get_first,
dd27fd17 42 int_or_none,
641ad5d8 43 is_html,
34921b43 44 join_nonempty,
48416bc4 45 js_to_json,
94278f72 46 mimetype2ext,
9c0d7f49 47 network_exceptions,
11f9be09 48 orderedSet,
6310acf5 49 parse_codecs,
49bd8c66 50 parse_count,
7c80519c 51 parse_duration,
7ea65411 52 parse_iso8601,
4dfbf869 53 parse_qs,
dca3ff4a 54 qualities,
c0ac49bc 55 remove_end,
3995d37d 56 remove_start,
cf7e015f 57 smuggle_url,
dbdaaa23 58 str_or_none,
c93d53f5 59 str_to_int,
f3aa3c3f 60 strftime_or_none,
7c365c21 61 traverse_obj,
556dbe7f 62 try_get,
c5e8d7af
PH
63 unescapeHTML,
64 unified_strdate,
f0d785d3 65 unified_timestamp,
cf7e015f 66 unsmuggle_url,
8bdd16b4 67 update_url_query,
21c340b8 68 url_or_none,
fe93e2c4 69 urljoin,
7c365c21 70 variadic,
c5e8d7af
PH
71)
72
000c15a4 73# any clients starting with _ cannot be explicity requested by the user
74INNERTUBE_CLIENTS = {
75 'web': {
76 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
77 'INNERTUBE_CONTEXT': {
78 'client': {
79 'clientName': 'WEB',
18c7683d 80 'clientVersion': '2.20211221.00.00',
000c15a4 81 }
82 },
83 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
84 },
85 'web_embedded': {
86 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
87 'INNERTUBE_CONTEXT': {
88 'client': {
89 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 90 'clientVersion': '1.20211215.00.01',
000c15a4 91 },
92 },
93 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
94 },
95 'web_music': {
96 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
97 'INNERTUBE_HOST': 'music.youtube.com',
98 'INNERTUBE_CONTEXT': {
99 'client': {
100 'clientName': 'WEB_REMIX',
18c7683d 101 'clientVersion': '1.20211213.00.00',
000c15a4 102 }
103 },
104 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
105 },
e7e94f2a 106 'web_creator': {
18c7683d 107 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
108 'INNERTUBE_CONTEXT': {
109 'client': {
110 'clientName': 'WEB_CREATOR',
18c7683d 111 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
112 }
113 },
114 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
115 },
000c15a4 116 'android': {
18c7683d 117 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 118 'INNERTUBE_CONTEXT': {
119 'client': {
120 'clientName': 'ANDROID',
18c7683d 121 'clientVersion': '16.49',
000c15a4 122 }
123 },
124 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 125 'REQUIRE_JS_PLAYER': False
000c15a4 126 },
127 'android_embedded': {
18c7683d 128 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 129 'INNERTUBE_CONTEXT': {
130 'client': {
131 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 132 'clientVersion': '16.49',
000c15a4 133 },
134 },
b6de707d 135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
000c15a4 137 },
138 'android_music': {
18c7683d 139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 140 'INNERTUBE_CONTEXT': {
141 'client': {
142 'clientName': 'ANDROID_MUSIC',
18c7683d 143 'clientVersion': '4.57',
000c15a4 144 }
145 },
146 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 147 'REQUIRE_JS_PLAYER': False
000c15a4 148 },
e7e94f2a 149 'android_creator': {
18c7683d 150 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
151 'INNERTUBE_CONTEXT': {
152 'client': {
153 'clientName': 'ANDROID_CREATOR',
18c7683d 154 'clientVersion': '21.47',
e7e94f2a
D
155 },
156 },
b6de707d 157 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
158 'REQUIRE_JS_PLAYER': False
e7e94f2a 159 },
18c7683d 160 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
161 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 162 'ios': {
18c7683d 163 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 164 'INNERTUBE_CONTEXT': {
165 'client': {
166 'clientName': 'IOS',
18c7683d 167 'clientVersion': '16.46',
168 'deviceModel': 'iPhone14,3',
000c15a4 169 }
170 },
b6de707d 171 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
172 'REQUIRE_JS_PLAYER': False
000c15a4 173 },
174 'ios_embedded': {
000c15a4 175 'INNERTUBE_CONTEXT': {
176 'client': {
177 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 178 'clientVersion': '16.46',
179 'deviceModel': 'iPhone14,3',
000c15a4 180 },
181 },
b6de707d 182 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
183 'REQUIRE_JS_PLAYER': False
000c15a4 184 },
185 'ios_music': {
18c7683d 186 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 187 'INNERTUBE_CONTEXT': {
188 'client': {
189 'clientName': 'IOS_MUSIC',
18c7683d 190 'clientVersion': '4.57',
000c15a4 191 },
192 },
b6de707d 193 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
194 'REQUIRE_JS_PLAYER': False
000c15a4 195 },
e7e94f2a
D
196 'ios_creator': {
197 'INNERTUBE_CONTEXT': {
198 'client': {
199 'clientName': 'IOS_CREATOR',
18c7683d 200 'clientVersion': '21.47',
e7e94f2a
D
201 },
202 },
b6de707d 203 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
204 'REQUIRE_JS_PLAYER': False
e7e94f2a 205 },
3619f78d 206 # mweb has 'ultralow' formats
207 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 208 'mweb': {
18c7683d 209 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 210 'INNERTUBE_CONTEXT': {
211 'client': {
212 'clientName': 'MWEB',
18c7683d 213 'clientVersion': '2.20211221.01.00',
000c15a4 214 }
215 },
216 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
217 },
218 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
219 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
220 'tv_embedded': {
221 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
222 'INNERTUBE_CONTEXT': {
223 'client': {
224 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
225 'clientVersion': '2.0',
226 },
227 },
228 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
229 },
000c15a4 230}
231
232
e7870111
D
233def _split_innertube_client(client_name):
234 variant, *base = client_name.rsplit('.', 1)
235 if base:
236 return variant, base[0], variant
237 base, *variant = client_name.split('_', 1)
238 return client_name, base, variant[0] if variant else None
239
240
000c15a4 241def build_innertube_clients():
2e4cacd0 242 THIRD_PARTY = {
e7870111 243 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 244 }
e7870111 245 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 246 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 247
248 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 249 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 250 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 251 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 252 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 253
e7870111 254 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 255 ytcfg['priority'] = 10 * priority(base_client)
256
e48b3875 257 if not variant:
e7870111
D
258 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
259 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
260 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
261 embedscreen['priority'] -= 3
262 elif variant == 'embedded':
e48b3875 263 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 264 ytcfg['priority'] -= 2
e48b3875 265 else:
000c15a4 266 ytcfg['priority'] -= 3
267
268
269build_innertube_clients()
270
271
de7f3446 272class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 273 """Provide base functions for Youtube extractors"""
e00eb564 274
3462ffa8 275 _RESERVED_NAMES = (
3cd786db 276 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 277 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 278 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 279 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 280
3619f78d 281 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
282
52efa4b3 283 # _NETRC_MACHINE = 'youtube'
3619f78d 284
b2e8bc1b
JMF
285 # If True it will raise an error if no login info is provided
286 _LOGIN_REQUIRED = False
287
d9190e44
RH
288 _INVIDIOUS_SITES = (
289 # invidious-redirect websites
290 r'(?:www\.)?redirect\.invidious\.io',
291 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 292 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
293 r'(?:www\.)?invidious\.pussthecat\.org',
294 r'(?:www\.)?invidious\.zee\.li',
295 r'(?:www\.)?invidious\.ethibox\.fr',
296 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
297 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
298 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
299 # youtube-dl invidious instances list
300 r'(?:(?:www|no)\.)?invidiou\.sh',
301 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
302 r'(?:www\.)?invidious\.kabi\.tk',
303 r'(?:www\.)?invidious\.mastodon\.host',
304 r'(?:www\.)?invidious\.zapashcanon\.fr',
305 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
306 r'(?:www\.)?invidious\.tinfoil-hat\.net',
307 r'(?:www\.)?invidious\.himiko\.cloud',
308 r'(?:www\.)?invidious\.reallyancient\.tech',
309 r'(?:www\.)?invidious\.tube',
310 r'(?:www\.)?invidiou\.site',
311 r'(?:www\.)?invidious\.site',
312 r'(?:www\.)?invidious\.xyz',
313 r'(?:www\.)?invidious\.nixnet\.xyz',
314 r'(?:www\.)?invidious\.048596\.xyz',
315 r'(?:www\.)?invidious\.drycat\.fr',
316 r'(?:www\.)?inv\.skyn3t\.in',
317 r'(?:www\.)?tube\.poal\.co',
318 r'(?:www\.)?tube\.connect\.cafe',
319 r'(?:www\.)?vid\.wxzm\.sx',
320 r'(?:www\.)?vid\.mint\.lgbt',
321 r'(?:www\.)?vid\.puffyan\.us',
322 r'(?:www\.)?yewtu\.be',
323 r'(?:www\.)?yt\.elukerio\.org',
324 r'(?:www\.)?yt\.lelux\.fi',
325 r'(?:www\.)?invidious\.ggc-project\.de',
326 r'(?:www\.)?yt\.maisputain\.ovh',
327 r'(?:www\.)?ytprivate\.com',
328 r'(?:www\.)?invidious\.13ad\.de',
329 r'(?:www\.)?invidious\.toot\.koeln',
330 r'(?:www\.)?invidious\.fdn\.fr',
331 r'(?:www\.)?watch\.nettohikari\.com',
332 r'(?:www\.)?invidious\.namazso\.eu',
333 r'(?:www\.)?invidious\.silkky\.cloud',
334 r'(?:www\.)?invidious\.exonip\.de',
335 r'(?:www\.)?invidious\.riverside\.rocks',
336 r'(?:www\.)?invidious\.blamefran\.net',
337 r'(?:www\.)?invidious\.moomoo\.de',
338 r'(?:www\.)?ytb\.trom\.tf',
339 r'(?:www\.)?yt\.cyberhost\.uk',
340 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
341 r'(?:www\.)?qklhadlycap4cnod\.onion',
342 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
343 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
344 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
345 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
346 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
347 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
348 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
349 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
350 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
351 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
352 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
353 r'(?:www\.)?piped\.kavin\.rocks',
354 r'(?:www\.)?piped\.silkky\.cloud',
355 r'(?:www\.)?piped\.tokhmi\.xyz',
356 r'(?:www\.)?piped\.moomoo\.me',
357 r'(?:www\.)?il\.ax',
358 r'(?:www\.)?piped\.syncpundit\.com',
359 r'(?:www\.)?piped\.mha\.fi',
360 r'(?:www\.)?piped\.mint\.lgbt',
361 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
362 )
363
cce889b9 364 def _initialize_consent(self):
365 cookies = self._get_cookies('https://www.youtube.com/')
366 if cookies.get('__Secure-3PSID'):
367 return
368 consent_id = None
369 consent = cookies.get('CONSENT')
370 if consent:
371 if 'YES' in consent.value:
372 return
373 consent_id = self._search_regex(
374 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
375 if not consent_id:
376 consent_id = random.randint(100, 999)
377 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 378
f3aa3c3f 379 def _initialize_pref(self):
380 cookies = self._get_cookies('https://www.youtube.com/')
381 pref_cookie = cookies.get('PREF')
382 pref = {}
383 if pref_cookie:
384 try:
385 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
386 except ValueError:
387 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 388 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 389 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
390
b2e8bc1b 391 def _real_initialize(self):
f3aa3c3f 392 self._initialize_pref()
cce889b9 393 self._initialize_consent()
a25bca9f 394 self._check_login_required()
395
396 def _check_login_required(self):
24146491 397 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 398 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 399
b7c47b74 400 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
401 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 402
000c15a4 403 def _get_default_ytcfg(self, client='web'):
404 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 405
000c15a4 406 def _get_innertube_host(self, client='web'):
407 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 408
000c15a4 409 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 410 # try_get but with fallback to default ytcfg client values when present
411 _func = lambda y: try_get(y, getter, expected_type)
412 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
413
000c15a4 414 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 415 return self._ytcfg_get_safe(
416 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
417 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 418
000c15a4 419 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 420 return self._ytcfg_get_safe(
421 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
422 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 423
2ae778b8 424 def _select_api_hostname(self, req_api_hostname, default_client=None):
425 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
426 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
427
000c15a4 428 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 429 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
430
000c15a4 431 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 432 context = get_first(
433 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 434 # Enforce language and tz for extraction
435 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
436 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 437 return context
438
cf87314d 439 _SAPISID = None
440
109dd3b2 441 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 442 time_now = round(time.time())
cf87314d 443 if self._SAPISID is None:
444 yt_cookies = self._get_cookies('https://www.youtube.com')
445 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
446 # See: https://github.com/yt-dlp/yt-dlp/issues/393
447 sapisid_cookie = dict_get(
448 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
449 if sapisid_cookie and sapisid_cookie.value:
450 self._SAPISID = sapisid_cookie.value
451 self.write_debug('Extracted SAPISID cookie')
452 # SAPISID cookie is required if not already present
453 if not yt_cookies.get('SAPISID'):
454 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
455 self._set_cookie(
456 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
457 else:
458 self._SAPISID = False
459 if not self._SAPISID:
460 return None
1974e99f 461 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
462 sapisidhash = hashlib.sha1(
86e5f3ed 463 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 464 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
465
466 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 467 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 468 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 469
109dd3b2 470 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 471 data.update(query)
11f9be09 472 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 473 real_headers.update({'content-type': 'application/json'})
474 if headers:
475 real_headers.update(headers)
2ae778b8 476 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
477 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 478 return self._download_json(
2ae778b8 479 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 480 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 481 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 482 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 483
65141660 484 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
485 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 486
99e9e001 487 @staticmethod
488 def _extract_session_index(*data):
489 """
490 Index of current account in account list.
491 See: https://github.com/yt-dlp/yt-dlp/pull/519
492 """
493 for ytcfg in data:
494 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
495 if session_index is not None:
496 return session_index
497
498 # Deprecated?
499 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
500 if ytcfg:
501 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
502 if token:
503 return token
99e9e001 504 if webpage:
505 return self._search_regex(
506 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
507 'identity token', default=None, fatal=False)
a1c5d2ca
M
508
509 @staticmethod
fe93e2c4 510 def _extract_account_syncid(*args):
8ea3f7b9 511 """
512 Extract syncId required to download private playlists of secondary channels
fe93e2c4 513 @params response and/or ytcfg
8ea3f7b9 514 """
fe93e2c4 515 for data in args:
516 # ytcfg includes channel_syncid if on secondary channel
517 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
518 if delegated_sid:
519 return delegated_sid
520 sync_ids = (try_get(
521 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 522 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 523 if len(sync_ids) >= 2 and sync_ids[1]:
524 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
525 # and just "user_syncid||" for primary channel. We only want the channel_syncid
526 return sync_ids[0]
a1c5d2ca 527
ac56cf38 528 @staticmethod
529 def _extract_visitor_data(*args):
530 """
531 Extracts visitorData from an API response or ytcfg
532 Appears to be used to track session state
533 """
9222c381 534 return get_first(
6c73052c 535 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 536 expected_type=str)
ac56cf38 537
2762dbb1 538 @functools.cached_property
99e9e001 539 def is_authenticated(self):
540 return bool(self._generate_sapisidhash_header())
541
11f9be09 542 def extract_ytcfg(self, video_id, webpage):
8c54a305 543 if not webpage:
544 return {}
29f7c58a 545 return self._parse_json(
546 self._search_regex(
547 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 548 default='{}'), video_id, fatal=False) or {}
549
11f9be09 550 def generate_api_headers(
99e9e001 551 self, *, ytcfg=None, account_syncid=None, session_index=None,
552 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
553
2ae778b8 554 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 555 headers = {
109dd3b2 556 'X-YouTube-Client-Name': compat_str(
11f9be09 557 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
558 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 559 'Origin': origin,
560 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
561 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 562 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 563 }
564 if session_index is None:
314ee305 565 session_index = self._extract_session_index(ytcfg)
566 if account_syncid or session_index is not None:
567 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 568
109dd3b2 569 auth = self._generate_sapisidhash_header(origin)
f4f751af 570 if auth is not None:
571 headers['Authorization'] = auth
109dd3b2 572 headers['X-Origin'] = origin
99e9e001 573 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 574
a25bca9f 575 def _download_ytcfg(self, client, video_id):
576 url = {
577 'web': 'https://www.youtube.com',
578 'web_music': 'https://music.youtube.com',
579 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
580 }.get(client)
581 if not url:
582 return {}
583 webpage = self._download_webpage(
584 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
585 return self.extract_ytcfg(video_id, webpage) or {}
586
2d6659b9 587 @staticmethod
588 def _build_api_continuation_query(continuation, ctp=None):
589 query = {
590 'continuation': continuation
591 }
592 # TODO: Inconsistency with clickTrackingParams.
593 # Currently we have a fixed ctp contained within context (from ytcfg)
594 # and a ctp in root query for continuation.
595 if ctp:
596 query['clickTracking'] = {'clickTrackingParams': ctp}
597 return query
598
2d6659b9 599 @classmethod
600 def _extract_next_continuation_data(cls, renderer):
601 next_continuation = try_get(
602 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
603 lambda x: x['continuation']['reloadContinuationData']), dict)
604 if not next_continuation:
605 return
606 continuation = next_continuation.get('continuation')
607 if not continuation:
608 return
609 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 610 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 611
612 @classmethod
613 def _extract_continuation_ep_data(cls, continuation_ep: dict):
614 if isinstance(continuation_ep, dict):
615 continuation = try_get(
616 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
617 if not continuation:
618 return
619 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 620 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 621
622 @classmethod
623 def _extract_continuation(cls, renderer):
624 next_continuation = cls._extract_next_continuation_data(renderer)
625 if next_continuation:
626 return next_continuation
fe93e2c4 627
2d6659b9 628 contents = []
629 for key in ('contents', 'items'):
630 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 631
2d6659b9 632 for content in contents:
633 if not isinstance(content, dict):
634 continue
635 continuation_ep = try_get(
636 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
637 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
638 dict)
639 continuation = cls._extract_continuation_ep_data(continuation_ep)
640 if continuation:
641 return continuation
642
fe93e2c4 643 @classmethod
644 def _extract_alerts(cls, data):
109dd3b2 645 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
646 if not isinstance(alert_dict, dict):
647 continue
648 for alert in alert_dict.values():
649 alert_type = alert.get('type')
650 if not alert_type:
651 continue
052e1350 652 message = cls._get_text(alert, 'text')
109dd3b2 653 if message:
654 yield alert_type, message
655
c0ac49bc 656 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 657 errors = []
658 warnings = []
659 for alert_type, alert_message in alerts:
641ad5d8 660 if alert_type.lower() == 'error' and fatal:
109dd3b2 661 errors.append([alert_type, alert_message])
662 else:
663 warnings.append([alert_type, alert_message])
664
665 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 666 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 667 if errors:
668 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
669
670 def _extract_and_report_alerts(self, data, *args, **kwargs):
671 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
672
47193e02 673 def _extract_badges(self, renderer: dict):
674 badges = set()
675 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
676 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
677 if label:
678 badges.add(label.lower())
679 return badges
680
681 @staticmethod
052e1350 682 def _get_text(data, *path_list, max_runs=None):
683 for path in path_list or [None]:
684 if path is None:
685 obj = [data]
686 else:
687 obj = traverse_obj(data, path, default=[])
688 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
689 obj = [obj]
690 for item in obj:
691 text = try_get(item, lambda x: x['simpleText'], compat_str)
692 if text:
693 return text
694 runs = try_get(item, lambda x: x['runs'], list) or []
695 if not runs and isinstance(item, list):
696 runs = item
697
698 runs = runs[:min(len(runs), max_runs or len(runs))]
699 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
700 if text:
701 return text
47193e02 702
f0d785d3 703 def _get_count(self, data, *path_list):
704 count_text = self._get_text(data, *path_list) or ''
705 count = parse_count(count_text)
706 if count is None:
707 count = str_to_int(
708 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
709 return count
710
a709d873 711 @staticmethod
712 def _extract_thumbnails(data, *path_list):
713 """
714 Extract thumbnails from thumbnails dict
715 @param path_list: path list to level that contains 'thumbnails' key
716 """
717 thumbnails = []
718 for path in path_list or [()]:
719 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
720 thumbnail_url = url_or_none(thumbnail.get('url'))
721 if not thumbnail_url:
722 continue
723 # Sometimes youtube gives a wrong thumbnail URL. See:
724 # https://github.com/yt-dlp/yt-dlp/issues/233
725 # https://github.com/ytdl-org/youtube-dl/issues/28023
726 if 'maxresdefault' in thumbnail_url:
727 thumbnail_url = thumbnail_url.split('?')[0]
728 thumbnails.append({
729 'url': thumbnail_url,
730 'height': int_or_none(thumbnail.get('height')),
731 'width': int_or_none(thumbnail.get('width')),
732 })
733 return thumbnails
734
f3aa3c3f 735 @staticmethod
736 def extract_relative_time(relative_time_text):
737 """
738 Extracts a relative time from string and converts to dt object
f0d785d3 739 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 740 """
f0d785d3 741 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 742 if mobj:
f0d785d3 743 start = mobj.group('start')
744 if start:
745 return datetime_from_str(start)
f3aa3c3f 746 try:
f0d785d3 747 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 748 except ValueError:
749 return None
750
751 def _extract_time_text(self, renderer, *path_list):
a25bca9f 752 """@returns (timestamp, time_text)"""
f3aa3c3f 753 text = self._get_text(renderer, *path_list) or ''
754 dt = self.extract_relative_time(text)
755 timestamp = None
756 if isinstance(dt, datetime.datetime):
757 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 758
759 if timestamp is None:
760 timestamp = (
761 unified_timestamp(text) or unified_timestamp(
762 self._search_regex(
17322130 763 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 764 text.lower(), 'time text', default=None)))
f0d785d3 765
f3aa3c3f 766 if text and timestamp is None:
17322130 767 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 768 return timestamp, text
769
109dd3b2 770 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
771 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 772 default_client='web'):
109dd3b2 773 response = None
774 last_error = None
775 count = -1
776 retries = self.get_param('extractor_retries', 3)
777 if check_get_keys is None:
778 check_get_keys = []
779 while count < retries:
780 count += 1
781 if last_error:
c0ac49bc 782 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 783 try:
784 response = self._call_api(
785 ep=ep, fatal=True, headers=headers,
786 video_id=item_id, query=query,
787 context=self._extract_context(ytcfg, default_client),
788 api_key=self._extract_api_key(ytcfg, default_client),
789 api_hostname=api_hostname, default_client=default_client,
790 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
791 except ExtractorError as e:
9c0d7f49 792 if isinstance(e.cause, network_exceptions):
87e8e8a7 793 if isinstance(e.cause, compat_HTTPError):
794 first_bytes = e.cause.read(512)
795 if not is_html(first_bytes):
796 yt_error = try_get(
797 self._parse_json(
798 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
799 lambda x: x['error']['message'], compat_str)
800 if yt_error:
801 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 802 # Downloading page may result in intermittent 5xx HTTP error
803 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 804 # We also want to catch all other network exceptions since errors in later pages can be troublesome
805 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
806 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 807 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 808 if count < retries:
809 continue
109dd3b2 810 if fatal:
811 raise
812 else:
813 self.report_warning(error_to_compat_str(e))
814 return
815
816 else:
109dd3b2 817 try:
ac56cf38 818 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 819 except ExtractorError as e:
c0ac49bc 820 # YouTube servers may return errors we want to retry on in a 200 OK response
821 # See: https://github.com/yt-dlp/yt-dlp/issues/839
822 if 'unknown error' in e.msg.lower():
823 last_error = e.msg
824 continue
109dd3b2 825 if fatal:
826 raise
827 self.report_warning(error_to_compat_str(e))
828 return
829 if not check_get_keys or dict_get(response, check_get_keys):
830 break
831 # Youtube sometimes sends incomplete data
832 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
833 last_error = 'Incomplete data received'
834 if count >= retries:
835 if fatal:
836 raise ExtractorError(last_error)
837 else:
838 self.report_warning(last_error)
839 return
840 return response
841
9297939e 842 @staticmethod
843 def is_music_url(url):
844 return re.match(r'https?://music\.youtube\.com/', url) is not None
845
30a074c2 846 def _extract_video(self, renderer):
847 video_id = renderer.get('videoId')
052e1350 848 title = self._get_text(renderer, 'title')
849 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 850 duration = parse_duration(self._get_text(
851 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 852 if duration is None:
853 duration = parse_duration(self._search_regex(
854 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
855 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
856 video_id, default=None, group='duration'))
857
f0d785d3 858 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 859
052e1350 860 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 861 channel_id = traverse_obj(
a44ca5a4 862 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
863 expected_type=str, get_all=False)
f3aa3c3f 864 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
865 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
866 overlay_style = traverse_obj(
a44ca5a4 867 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
868 get_all=False, expected_type=str)
f3aa3c3f 869 badges = self._extract_badges(renderer)
a709d873 870 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 871 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 872 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
873 expected_type=str)) or ''
fd2ad7cb 874 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 875 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 876 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 877
30a074c2 878 return {
39ed931e 879 '_type': 'url',
30a074c2 880 'ie_key': YoutubeIE.ie_key(),
881 'id': video_id,
fd2ad7cb 882 'url': url,
30a074c2 883 'title': title,
884 'description': description,
885 'duration': duration,
886 'view_count': view_count,
887 'uploader': uploader,
f3aa3c3f 888 'channel_id': channel_id,
a709d873 889 'thumbnails': thumbnails,
a44ca5a4 890 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
891 if self._configuration_arg('approximate_date', ie_key='youtubetab')
892 else None),
f3aa3c3f 893 'live_status': ('is_upcoming' if scheduled_timestamp is not None
894 else 'was_live' if 'streamed' in time_text.lower()
895 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
896 else None),
897 'release_timestamp': scheduled_timestamp,
898 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 899 }
900
0c148415 901
360e1ca5 902class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 903 IE_DESC = 'YouTube'
cb7dfeea 904 _VALID_URL = r"""(?x)^
c5e8d7af 905 (
edb53e2d 906 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 907 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
908 (?:www\.)?deturl\.com/www\.youtube\.com|
909 (?:www\.)?pwnyoutube\.com|
910 (?:www\.)?hooktube\.com|
911 (?:www\.)?yourepeat\.com|
912 tube\.majestyc\.net|
913 %(invidious)s|
914 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
915 (?:.*?\#/)? # handle anchor (#/) redirect urls
916 (?: # the various things that can precede the ID:
b6ce9bb0 917 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 918 |(?: # or the v= param in all its forms
f7000f3a 919 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 920 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 921 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
922 v=
923 )
f4b05232 924 ))
cbaed4bb
S
925 |(?:
926 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
927 vid\.plus| # or vid.plus/xxxx
928 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 929 %(invidious)s
cbaed4bb 930 )/
edb53e2d 931 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 932 )
c5e8d7af 933 )? # all until now is optional -> you can pass the naked ID
201c1459 934 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 935 (?(1).+)? # if we found the ID, everything can follow
9297939e 936 (?:\#|$)""" % {
d9190e44 937 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 938 }
e40c758c 939 _PLAYER_INFO_RE = (
cc2db878 940 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
941 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$',
545cc85d 942 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 943 )
2c62dc26 944 _formats = {
c2d3cb4c 945 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
946 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
947 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
948 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
949 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
950 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
951 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
952 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 953 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 954 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
955 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
956 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
957 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
958 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
959 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 960 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 961 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
962 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 963
964
965 # 3D videos
c2d3cb4c 966 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
967 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
968 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
969 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 970 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
971 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
972 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 973
96fb5605 974 # Apple HTTP Live Streaming
11f12195 975 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 976 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
977 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
978 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
979 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
980 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 981 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
982 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
983
984 # DASH mp4 video
d23028a8
S
985 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
989 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 990 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
991 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
992 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
993 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
994 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
995 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
996 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 997
f6f1fc92 998 # Dash mp4 audio
d23028a8
S
999 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1000 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1001 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1002 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1003 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1004 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1005 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1006
1007 # Dash webm
d23028a8
S
1008 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1009 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1010 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1011 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1012 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1013 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1014 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1015 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1019 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1020 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1023 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1024 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1025 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1026 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1027 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1028 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1029 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1030
1031 # Dash webm audio
d23028a8
S
1032 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1033 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1034
0857baad 1035 # Dash webm audio with opus inside
d23028a8
S
1036 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1037 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1038 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1039
ce6b9a2d
PH
1040 # RTMP (unnamed)
1041 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1042
1043 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1044 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1045 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1046 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1047 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1048 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1049 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1050 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1051 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1052 }
29f7c58a 1053 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1054
fd5c4aab
S
1055 _GEO_BYPASS = False
1056
78caa52a 1057 IE_NAME = 'youtube'
2eb88d95
PH
1058 _TESTS = [
1059 {
2d3d2997 1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1061 'info_dict': {
1062 'id': 'BaW_jenozKc',
1063 'ext': 'mp4',
3867038a 1064 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1065 'uploader': 'Philipp Hagemeister',
1066 'uploader_id': 'phihag',
ec85ded8 1067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1068 'channel': 'Philipp Hagemeister',
dd4c4492
S
1069 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1070 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1071 'upload_date': '20121002',
ff9f925b 1072 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1073 'categories': ['Science & Technology'],
3867038a 1074 'tags': ['youtube-dl'],
556dbe7f 1075 'duration': 10,
dbdaaa23 1076 'view_count': int,
3e7c1224 1077 'like_count': int,
ff9f925b 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,
7c80519c 1083 'start_time': 1,
297a564b 1084 'end_time': 9,
6c73052c 1085 'channel_follower_count': int
2eb88d95 1086 }
0e853ca4 1087 },
fccd3771 1088 {
4bc3a23e
PH
1089 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1090 'note': 'Embed-only video (#1746)',
1091 'info_dict': {
1092 'id': 'yZIXLfi8CZQ',
1093 'ext': 'mp4',
1094 'upload_date': '20120608',
1095 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1096 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1097 'uploader': 'SET India',
94bfcd23 1098 'uploader_id': 'setindia',
ec85ded8 1099 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1100 'age_limit': 18,
545cc85d 1101 },
1102 'skip': 'Private video',
fccd3771 1103 },
11b56058 1104 {
8bdd16b4 1105 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1106 'note': 'Use the first video ID in the URL',
1107 'info_dict': {
1108 'id': 'BaW_jenozKc',
1109 'ext': 'mp4',
3867038a 1110 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1111 'uploader': 'Philipp Hagemeister',
1112 'uploader_id': 'phihag',
ec85ded8 1113 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1114 'channel': 'Philipp Hagemeister',
1115 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1116 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1117 'upload_date': '20121002',
976ae3ea 1118 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1119 'categories': ['Science & Technology'],
3867038a 1120 'tags': ['youtube-dl'],
556dbe7f 1121 'duration': 10,
dbdaaa23 1122 'view_count': int,
11b56058 1123 'like_count': int,
976ae3ea 1124 'availability': 'public',
1125 'playable_in_embed': True,
1126 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1127 'live_status': 'not_live',
1128 'age_limit': 0,
6c73052c 1129 'channel_follower_count': int
34a7de29
S
1130 },
1131 'params': {
1132 'skip_download': True,
1133 },
11b56058 1134 },
dd27fd17 1135 {
2d3d2997 1136 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1137 'note': '256k DASH audio (format 141) via DASH manifest',
1138 'info_dict': {
1139 'id': 'a9LDPn-MO4I',
1140 'ext': 'm4a',
1141 'upload_date': '20121002',
1142 'uploader_id': '8KVIDEO',
ec85ded8 1143 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1144 'description': '',
1145 'uploader': '8KVIDEO',
1146 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1147 },
4bc3a23e
PH
1148 'params': {
1149 'youtube_include_dash_manifest': True,
1150 'format': '141',
4919603f 1151 },
de3c7fe0 1152 'skip': 'format 141 not served anymore',
dd27fd17 1153 },
8bdd16b4 1154 # DASH manifest with encrypted signature
1155 {
1156 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1157 'info_dict': {
1158 'id': 'IB3lcPjvWLA',
1159 'ext': 'm4a',
1160 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1161 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1162 'duration': 244,
1163 'uploader': 'AfrojackVEVO',
1164 'uploader_id': 'AfrojackVEVO',
1165 'upload_date': '20131011',
cc2db878 1166 'abr': 129.495,
976ae3ea 1167 'like_count': int,
1168 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1169 'playable_in_embed': True,
1170 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1171 'view_count': int,
1172 'track': 'The Spark',
1173 'live_status': 'not_live',
1174 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1175 'channel': 'Afrojack',
1176 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1177 'tags': 'count:19',
1178 'availability': 'public',
1179 'categories': ['Music'],
1180 'age_limit': 0,
1181 'alt_title': 'The Spark',
6c73052c 1182 'channel_follower_count': int
8bdd16b4 1183 },
1184 'params': {
1185 'youtube_include_dash_manifest': True,
1186 'format': '141/bestaudio[ext=m4a]',
1187 },
1188 },
65c2fde2 1189 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1190 {
65c2fde2 1191 'note': 'Embed allowed age-gate video',
2d3d2997 1192 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1193 'info_dict': {
1194 'id': 'HtVdAasjOgU',
1195 'ext': 'mp4',
1196 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1197 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1198 'duration': 142,
c522adb1
JMF
1199 'uploader': 'The Witcher',
1200 'uploader_id': 'WitcherGame',
ec85ded8 1201 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1202 'upload_date': '20140605',
34952f09 1203 'age_limit': 18,
976ae3ea 1204 'categories': ['Gaming'],
1205 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1206 'availability': 'needs_auth',
1207 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1208 'like_count': int,
1209 'channel': 'The Witcher',
1210 'live_status': 'not_live',
1211 'tags': 'count:17',
1212 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1213 'playable_in_embed': True,
1214 'view_count': int,
6c73052c 1215 'channel_follower_count': int
c522adb1
JMF
1216 },
1217 },
65c2fde2 1218 {
1219 'note': 'Age-gate video with embed allowed in public site',
1220 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1221 'info_dict': {
1222 'id': 'HsUATh_Nc2U',
1223 'ext': 'mp4',
1224 'title': 'Godzilla 2 (Official Video)',
1225 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1226 'upload_date': '20200408',
1227 'uploader_id': 'FlyingKitty900',
1228 'uploader': 'FlyingKitty',
1229 'age_limit': 18,
976ae3ea 1230 'availability': 'needs_auth',
1231 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1232 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1233 'channel': 'FlyingKitty',
1234 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1235 'view_count': int,
1236 'categories': ['Entertainment'],
1237 'live_status': 'not_live',
1238 'tags': ['Flyingkitty', 'godzilla 2'],
1239 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1240 'like_count': int,
1241 'duration': 177,
1242 'playable_in_embed': True,
6c73052c 1243 'channel_follower_count': int
65c2fde2 1244 },
1245 },
1246 {
1247 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1248 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1249 'info_dict': {
1250 'id': 'Tq92D6wQ1mg',
1251 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1252 'ext': 'mp4',
17322130 1253 'upload_date': '20191228',
65c2fde2 1254 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1255 'uploader': 'Projekt Melody',
1256 'description': 'md5:17eccca93a786d51bc67646756894066',
1257 'age_limit': 18,
976ae3ea 1258 'like_count': int,
1259 'availability': 'needs_auth',
1260 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1261 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1262 'view_count': int,
1263 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1264 'channel': 'Projekt Melody',
1265 'live_status': 'not_live',
1266 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1267 'playable_in_embed': True,
1268 'categories': ['Entertainment'],
1269 'duration': 106,
1270 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1271 'channel_follower_count': int
65c2fde2 1272 },
1273 },
1274 {
1275 'note': 'Non-Agegated non-embeddable video',
1276 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1277 'info_dict': {
1278 'id': 'MeJVWBSsPAY',
1279 'ext': 'mp4',
1280 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1281 'uploader': 'Herr Lurik',
1282 'uploader_id': 'st3in234',
1283 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1284 'upload_date': '20130730',
976ae3ea 1285 'track': 'Such mich find mich',
1286 'age_limit': 0,
1287 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1288 'like_count': int,
1289 'playable_in_embed': False,
1290 'creator': 'OOMPH!',
1291 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1292 'view_count': int,
1293 'alt_title': 'Such mich find mich',
1294 'duration': 210,
1295 'channel': 'Herr Lurik',
1296 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1297 'categories': ['Music'],
1298 'availability': 'public',
1299 'uploader_url': 'http://www.youtube.com/user/st3in234',
1300 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1301 'live_status': 'not_live',
1302 'artist': 'OOMPH!',
6c73052c 1303 'channel_follower_count': int
65c2fde2 1304 },
1305 },
1306 {
1307 'note': 'Non-bypassable age-gated video',
1308 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1309 'only_matching': True,
1310 },
8bdd16b4 1311 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1312 # YouTube Red ad is not captured for creator
1313 {
1314 'url': '__2ABJjxzNo',
1315 'info_dict': {
1316 'id': '__2ABJjxzNo',
1317 'ext': 'mp4',
1318 'duration': 266,
1319 'upload_date': '20100430',
1320 'uploader_id': 'deadmau5',
1321 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1322 'creator': 'deadmau5',
1323 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1324 'uploader': 'deadmau5',
1325 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1326 'alt_title': 'Some Chords',
976ae3ea 1327 'availability': 'public',
1328 'tags': 'count:14',
1329 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1330 'view_count': int,
1331 'live_status': 'not_live',
1332 'channel': 'deadmau5',
1333 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1334 'like_count': int,
1335 'track': 'Some Chords',
1336 'artist': 'deadmau5',
1337 'playable_in_embed': True,
1338 'age_limit': 0,
1339 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1340 'categories': ['Music'],
1341 'album': 'Some Chords',
6c73052c 1342 'channel_follower_count': int
8bdd16b4 1343 },
1344 'expected_warnings': [
1345 'DASH manifest missing',
1346 ]
1347 },
067aa17e 1348 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1349 {
1350 'url': 'lqQg6PlCWgI',
1351 'info_dict': {
1352 'id': 'lqQg6PlCWgI',
1353 'ext': 'mp4',
556dbe7f 1354 'duration': 6085,
90227264 1355 'upload_date': '20150827',
cbe2bd91 1356 'uploader_id': 'olympic',
ec85ded8 1357 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1358 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1359 'uploader': 'Olympics',
cbe2bd91 1360 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1361 'like_count': int,
1362 'release_timestamp': 1343767800,
1363 'playable_in_embed': True,
1364 'categories': ['Sports'],
1365 'release_date': '20120731',
1366 'channel': 'Olympics',
1367 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1368 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1369 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1370 'age_limit': 0,
1371 'availability': 'public',
1372 'live_status': 'was_live',
1373 'view_count': int,
1374 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1375 'channel_follower_count': int
cbe2bd91
PH
1376 },
1377 'params': {
1378 'skip_download': 'requires avconv',
e52a40ab 1379 }
cbe2bd91 1380 },
6271f1ca
PH
1381 # Non-square pixels
1382 {
1383 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1384 'info_dict': {
1385 'id': '_b-2C3KPAM0',
1386 'ext': 'mp4',
1387 'stretched_ratio': 16 / 9.,
556dbe7f 1388 'duration': 85,
6271f1ca
PH
1389 'upload_date': '20110310',
1390 'uploader_id': 'AllenMeow',
ec85ded8 1391 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1392 '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 1393 'uploader': '孫ᄋᄅ',
6271f1ca 1394 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1395 'playable_in_embed': True,
1396 'channel': '孫ᄋᄅ',
1397 'age_limit': 0,
1398 'tags': 'count:11',
1399 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1400 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1401 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1402 'view_count': int,
1403 'categories': ['People & Blogs'],
1404 'like_count': int,
1405 'live_status': 'not_live',
1406 'availability': 'unlisted',
6c73052c 1407 'channel_follower_count': int
6271f1ca 1408 },
06b491eb
S
1409 },
1410 # url_encoded_fmt_stream_map is empty string
1411 {
1412 'url': 'qEJwOuvDf7I',
1413 'info_dict': {
1414 'id': 'qEJwOuvDf7I',
f57b7835 1415 'ext': 'webm',
06b491eb
S
1416 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1417 'description': '',
1418 'upload_date': '20150404',
1419 'uploader_id': 'spbelect',
1420 'uploader': 'Наблюдатели Петербурга',
1421 },
1422 'params': {
1423 'skip_download': 'requires avconv',
e323cf3f
S
1424 },
1425 'skip': 'This live event has ended.',
06b491eb 1426 },
067aa17e 1427 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1428 {
1429 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1430 'info_dict': {
1431 'id': 'FIl7x6_3R5Y',
eb6793ba 1432 'ext': 'webm',
da77d856
S
1433 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1434 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1435 'duration': 220,
da77d856
S
1436 'upload_date': '20150625',
1437 'uploader_id': 'dorappi2000',
ec85ded8 1438 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1439 'uploader': 'dorappi2000',
eb6793ba 1440 'formats': 'mincount:31',
da77d856 1441 },
eb6793ba 1442 'skip': 'not actual anymore',
2ee8f5d8 1443 },
8a1a26ce
YCH
1444 # DASH manifest with segment_list
1445 {
1446 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1447 'md5': '8ce563a1d667b599d21064e982ab9e31',
1448 'info_dict': {
1449 'id': 'CsmdDsKjzN8',
1450 'ext': 'mp4',
17ee98e1 1451 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1452 'uploader': 'Airtek',
1453 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1454 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1455 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1456 },
1457 'params': {
1458 'youtube_include_dash_manifest': True,
1459 'format': '135', # bestvideo
be49068d
S
1460 },
1461 'skip': 'This live event has ended.',
2ee8f5d8 1462 },
cf7e015f
S
1463 {
1464 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1465 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1466 'info_dict': {
545cc85d 1467 'id': 'jvGDaLqkpTg',
1468 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1469 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1470 },
1471 'playlist': [{
1472 'info_dict': {
545cc85d 1473 'id': 'jvGDaLqkpTg',
cf7e015f 1474 'ext': 'mp4',
545cc85d 1475 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1476 'description': 'md5:e03b909557865076822aa169218d6a5d',
1477 'duration': 10643,
1478 'upload_date': '20161111',
1479 'uploader': 'Team PGP',
1480 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1481 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1482 },
1483 }, {
1484 'info_dict': {
545cc85d 1485 'id': '3AKt1R1aDnw',
cf7e015f 1486 'ext': 'mp4',
545cc85d 1487 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1488 'description': 'md5:e03b909557865076822aa169218d6a5d',
1489 'duration': 10991,
1490 'upload_date': '20161111',
1491 'uploader': 'Team PGP',
1492 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1493 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1494 },
1495 }, {
1496 'info_dict': {
545cc85d 1497 'id': 'RtAMM00gpVc',
cf7e015f 1498 'ext': 'mp4',
545cc85d 1499 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1500 'description': 'md5:e03b909557865076822aa169218d6a5d',
1501 'duration': 10995,
1502 'upload_date': '20161111',
1503 'uploader': 'Team PGP',
1504 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1505 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1506 },
1507 }, {
1508 'info_dict': {
545cc85d 1509 'id': '6N2fdlP3C5U',
cf7e015f 1510 'ext': 'mp4',
545cc85d 1511 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1512 'description': 'md5:e03b909557865076822aa169218d6a5d',
1513 'duration': 10990,
1514 'upload_date': '20161111',
1515 'uploader': 'Team PGP',
1516 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1517 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1518 },
1519 }],
1520 'params': {
1521 'skip_download': True,
1522 },
65c2fde2 1523 'skip': 'Not multifeed anymore',
cbaed4bb 1524 },
f9f49d87 1525 {
067aa17e 1526 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1527 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1528 'info_dict': {
1529 'id': 'gVfLd0zydlo',
1530 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1531 },
1532 'playlist_count': 2,
be49068d 1533 'skip': 'Not multifeed anymore',
f9f49d87 1534 },
cbaed4bb 1535 {
2d3d2997 1536 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1537 'only_matching': True,
0e49d9a6 1538 },
6d4fc66b 1539 {
2d3d2997 1540 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1541 'only_matching': True,
1542 },
0e49d9a6 1543 {
067aa17e 1544 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1545 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1546 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1547 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1548 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1549 'info_dict': {
1550 'id': 'lsguqyKfVQg',
1551 'ext': 'mp4',
1552 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1553 'alt_title': 'Dark Walk',
0e49d9a6 1554 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1555 'duration': 133,
0e49d9a6
LL
1556 'upload_date': '20151119',
1557 'uploader_id': 'IronSoulElf',
ec85ded8 1558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1559 'uploader': 'IronSoulElf',
11f9be09 1560 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1561 'track': 'Dark Walk',
1562 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1563 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1564 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1565 'categories': ['Film & Animation'],
1566 'view_count': int,
1567 'live_status': 'not_live',
1568 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1569 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1570 'tags': 'count:13',
1571 'availability': 'public',
1572 'channel': 'IronSoulElf',
1573 'playable_in_embed': True,
1574 'like_count': int,
1575 'age_limit': 0,
6c73052c 1576 'channel_follower_count': int
0e49d9a6
LL
1577 },
1578 'params': {
1579 'skip_download': True,
1580 },
1581 },
61f92af1 1582 {
067aa17e 1583 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1584 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1585 'only_matching': True,
1586 },
313dfc45
LL
1587 {
1588 # Video with yt:stretch=17:0
1589 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1590 'info_dict': {
1591 'id': 'Q39EVAstoRM',
1592 'ext': 'mp4',
1593 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1594 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1595 'upload_date': '20151107',
1596 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1597 'uploader': 'CH GAMER DROID',
1598 },
1599 'params': {
1600 'skip_download': True,
1601 },
be49068d 1602 'skip': 'This video does not exist.',
313dfc45 1603 },
201c1459 1604 {
1605 # Video with incomplete 'yt:stretch=16:'
1606 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1607 'only_matching': True,
1608 },
7caf9830
S
1609 {
1610 # Video licensed under Creative Commons
1611 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1612 'info_dict': {
1613 'id': 'M4gD1WSo5mA',
1614 'ext': 'mp4',
1615 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1616 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1617 'duration': 721,
17322130 1618 'upload_date': '20150128',
7caf9830 1619 'uploader_id': 'BerkmanCenter',
ec85ded8 1620 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1621 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1622 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1623 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1624 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1625 'like_count': int,
1626 'age_limit': 0,
1627 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1628 'channel': 'The Berkman Klein Center for Internet & Society',
1629 'availability': 'public',
1630 'view_count': int,
1631 'categories': ['Education'],
1632 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1633 'live_status': 'not_live',
1634 'playable_in_embed': True,
6c73052c 1635 'channel_follower_count': int
7caf9830
S
1636 },
1637 'params': {
1638 'skip_download': True,
1639 },
1640 },
fd050249
S
1641 {
1642 # Channel-like uploader_url
1643 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1644 'info_dict': {
1645 'id': 'eQcmzGIKrzg',
1646 'ext': 'mp4',
1647 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1648 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1649 'duration': 4060,
17322130 1650 'upload_date': '20151120',
eb6793ba 1651 'uploader': 'Bernie Sanders',
fd050249 1652 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1653 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1654 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1655 'playable_in_embed': True,
1656 'tags': 'count:12',
1657 'like_count': int,
1658 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1659 'age_limit': 0,
1660 'availability': 'public',
1661 'categories': ['News & Politics'],
1662 'channel': 'Bernie Sanders',
1663 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1664 'view_count': int,
1665 'live_status': 'not_live',
1666 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1667 'channel_follower_count': int
fd050249
S
1668 },
1669 'params': {
1670 'skip_download': True,
1671 },
1672 },
040ac686
S
1673 {
1674 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1675 'only_matching': True,
7f29cf54
S
1676 },
1677 {
067aa17e 1678 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1679 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1680 'only_matching': True,
6496ccb4
S
1681 },
1682 {
1683 # Rental video preview
1684 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1685 'info_dict': {
1686 'id': 'uGpuVWrhIzE',
1687 'ext': 'mp4',
1688 'title': 'Piku - Trailer',
1689 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1690 'upload_date': '20150811',
1691 'uploader': 'FlixMatrix',
1692 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1693 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1694 'license': 'Standard YouTube License',
1695 },
1696 'params': {
1697 'skip_download': True,
1698 },
eb6793ba 1699 'skip': 'This video is not available.',
022a5d66 1700 },
12afdc2a
S
1701 {
1702 # YouTube Red video with episode data
1703 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1704 'info_dict': {
1705 'id': 'iqKdEhx-dD4',
1706 'ext': 'mp4',
1707 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1708 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1709 'duration': 2085,
12afdc2a
S
1710 'upload_date': '20170118',
1711 'uploader': 'Vsauce',
1712 'uploader_id': 'Vsauce',
1713 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1714 'series': 'Mind Field',
1715 'season_number': 1,
1716 'episode_number': 1,
976ae3ea 1717 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1718 'tags': 'count:12',
1719 'view_count': int,
1720 'availability': 'public',
1721 'age_limit': 0,
1722 'channel': 'Vsauce',
1723 'episode': 'Episode 1',
1724 'categories': ['Entertainment'],
1725 'season': 'Season 1',
1726 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1727 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1728 'like_count': int,
1729 'playable_in_embed': True,
1730 'live_status': 'not_live',
6c73052c 1731 'channel_follower_count': int
12afdc2a
S
1732 },
1733 'params': {
1734 'skip_download': True,
1735 },
1736 'expected_warnings': [
1737 'Skipping DASH manifest',
1738 ],
1739 },
c7121fa7
S
1740 {
1741 # The following content has been identified by the YouTube community
1742 # as inappropriate or offensive to some audiences.
1743 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1744 'info_dict': {
1745 'id': '6SJNVb0GnPI',
1746 'ext': 'mp4',
1747 'title': 'Race Differences in Intelligence',
1748 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1749 'duration': 965,
1750 'upload_date': '20140124',
1751 'uploader': 'New Century Foundation',
1752 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1753 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1754 },
1755 'params': {
1756 'skip_download': True,
1757 },
545cc85d 1758 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1759 },
022a5d66
S
1760 {
1761 # itag 212
1762 'url': '1t24XAntNCY',
1763 'only_matching': True,
fd5c4aab
S
1764 },
1765 {
1766 # geo restricted to JP
1767 'url': 'sJL6WA-aGkQ',
1768 'only_matching': True,
1769 },
cd5a74a2
S
1770 {
1771 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1772 'only_matching': True,
1773 },
bc2ca1bb 1774 {
1775 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1776 'only_matching': True,
1777 },
1778 {
1779 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1780 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1781 'only_matching': True,
1782 },
825cd268
RA
1783 {
1784 # DRM protected
1785 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1786 'only_matching': True,
4fe54c12
S
1787 },
1788 {
1789 # Video with unsupported adaptive stream type formats
1790 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1791 'info_dict': {
1792 'id': 'Z4Vy8R84T1U',
1793 'ext': 'mp4',
1794 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1795 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1796 'duration': 433,
1797 'upload_date': '20130923',
1798 'uploader': 'Amelia Putri Harwita',
1799 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1800 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1801 'formats': 'maxcount:10',
1802 },
1803 'params': {
1804 'skip_download': True,
1805 'youtube_include_dash_manifest': False,
1806 },
5429d6a9 1807 'skip': 'not actual anymore',
5caabd3c 1808 },
1809 {
822b9d9c 1810 # Youtube Music Auto-generated description
5caabd3c 1811 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1812 'info_dict': {
1813 'id': 'MgNrAu2pzNs',
1814 'ext': 'mp4',
1815 'title': 'Voyeur Girl',
1816 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1817 'upload_date': '20190312',
5429d6a9
S
1818 'uploader': 'Stephen - Topic',
1819 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1820 'artist': 'Stephen',
1821 'track': 'Voyeur Girl',
1822 'album': 'it\'s too much love to know my dear',
1823 'release_date': '20190313',
1824 'release_year': 2019,
976ae3ea 1825 'alt_title': 'Voyeur Girl',
1826 'view_count': int,
1827 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1828 'playable_in_embed': True,
1829 'like_count': int,
1830 'categories': ['Music'],
1831 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1832 'channel': 'Stephen',
1833 'availability': 'public',
1834 'creator': 'Stephen',
1835 'duration': 169,
1836 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1837 'age_limit': 0,
1838 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1839 'tags': 'count:11',
1840 'live_status': 'not_live',
6c73052c 1841 'channel_follower_count': int
5caabd3c 1842 },
1843 'params': {
1844 'skip_download': True,
1845 },
1846 },
66b48727
RA
1847 {
1848 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1849 'only_matching': True,
1850 },
011e75e6
S
1851 {
1852 # invalid -> valid video id redirection
1853 'url': 'DJztXj2GPfl',
1854 'info_dict': {
1855 'id': 'DJztXj2GPfk',
1856 'ext': 'mp4',
1857 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1858 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1859 'upload_date': '20090125',
1860 'uploader': 'Prochorowka',
1861 'uploader_id': 'Prochorowka',
1862 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1863 'artist': 'Panjabi MC',
1864 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1865 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1866 },
1867 'params': {
1868 'skip_download': True,
1869 },
545cc85d 1870 'skip': 'Video unavailable',
ea74e00b
DP
1871 },
1872 {
1873 # empty description results in an empty string
1874 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1875 'info_dict': {
1876 'id': 'x41yOUIvK2k',
1877 'ext': 'mp4',
1878 'title': 'IMG 3456',
1879 'description': '',
1880 'upload_date': '20170613',
1881 'uploader_id': 'ElevageOrVert',
1882 'uploader': 'ElevageOrVert',
976ae3ea 1883 'view_count': int,
1884 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1885 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1886 'like_count': int,
1887 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1888 'tags': [],
1889 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1890 'availability': 'public',
1891 'age_limit': 0,
1892 'categories': ['Pets & Animals'],
1893 'duration': 7,
1894 'playable_in_embed': True,
1895 'live_status': 'not_live',
1896 'channel': 'ElevageOrVert',
6c73052c 1897 'channel_follower_count': int
ea74e00b
DP
1898 },
1899 'params': {
1900 'skip_download': True,
1901 },
1902 },
a0566bbf 1903 {
29f7c58a 1904 # with '};' inside yt initial data (see [1])
1905 # see [2] for an example with '};' inside ytInitialPlayerResponse
1906 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1907 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1908 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1909 'info_dict': {
1910 'id': 'CHqg6qOn4no',
1911 'ext': 'mp4',
1912 'title': 'Part 77 Sort a list of simple types in c#',
1913 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1914 'upload_date': '20130831',
1915 'uploader_id': 'kudvenkat',
1916 'uploader': 'kudvenkat',
976ae3ea 1917 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1918 'like_count': int,
1919 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1920 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1921 'live_status': 'not_live',
1922 'categories': ['Education'],
1923 'availability': 'public',
1924 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1925 'tags': 'count:12',
1926 'playable_in_embed': True,
1927 'age_limit': 0,
1928 'view_count': int,
1929 'duration': 522,
1930 'channel': 'kudvenkat',
6c73052c 1931 'channel_follower_count': int
a0566bbf 1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
1936 },
29f7c58a 1937 {
1938 # another example of '};' in ytInitialData
1939 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1940 'only_matching': True,
1941 },
1942 {
1943 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1944 'only_matching': True,
1945 },
545cc85d 1946 {
cc2db878 1947 # https://github.com/ytdl-org/youtube-dl/pull/28094
1948 'url': 'OtqTfy26tG0',
1949 'info_dict': {
1950 'id': 'OtqTfy26tG0',
1951 'ext': 'mp4',
1952 'title': 'Burn Out',
1953 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1954 'upload_date': '20141120',
1955 'uploader': 'The Cinematic Orchestra - Topic',
1956 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1958 'artist': 'The Cinematic Orchestra',
1959 'track': 'Burn Out',
1960 'album': 'Every Day',
976ae3ea 1961 'like_count': int,
1962 'live_status': 'not_live',
1963 'alt_title': 'Burn Out',
1964 'duration': 614,
1965 'age_limit': 0,
1966 'view_count': int,
1967 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1968 'creator': 'The Cinematic Orchestra',
1969 'channel': 'The Cinematic Orchestra',
1970 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1971 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1972 'availability': 'public',
1973 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1974 'categories': ['Music'],
1975 'playable_in_embed': True,
6c73052c 1976 'channel_follower_count': int
cc2db878 1977 },
1978 'params': {
1979 'skip_download': True,
1980 },
545cc85d 1981 },
bc2ca1bb 1982 {
1983 # controversial video, only works with bpctr when authenticated with cookies
1984 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1985 'only_matching': True,
1986 },
a1a7907b 1987 {
1988 # controversial video, requires bpctr/contentCheckOk
1989 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1990 'info_dict': {
1991 'id': 'SZJvDhaSDnc',
1992 'ext': 'mp4',
1993 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1994 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1995 'uploader': 'CBS Mornings',
11f9be09 1996 'uploader_id': 'CBSThisMorning',
a1a7907b 1997 'upload_date': '20140716',
976ae3ea 1998 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1999 'duration': 170,
2000 'categories': ['News & Politics'],
2001 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2002 'view_count': int,
2003 'channel': 'CBS Mornings',
2004 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2005 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2006 'age_limit': 18,
2007 'availability': 'needs_auth',
2008 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2009 'like_count': int,
2010 'live_status': 'not_live',
2011 'playable_in_embed': True,
6c73052c 2012 'channel_follower_count': int
a1a7907b 2013 }
2014 },
f7ad7160 2015 {
2016 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2017 'url': 'cBvYw8_A0vQ',
2018 'info_dict': {
2019 'id': 'cBvYw8_A0vQ',
2020 'ext': 'mp4',
2021 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2022 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2023 'upload_date': '20201120',
2024 'uploader': 'Walk around Japan',
2025 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2026 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2027 'duration': 1456,
2028 'categories': ['Travel & Events'],
2029 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2030 'view_count': int,
2031 'channel': 'Walk around Japan',
2032 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2033 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2034 'age_limit': 0,
2035 'availability': 'public',
2036 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2037 'live_status': 'not_live',
2038 'playable_in_embed': True,
6c73052c 2039 'channel_follower_count': int
f7ad7160 2040 },
2041 'params': {
2042 'skip_download': True,
2043 },
0fb983f6 2044 }, {
2045 # Has multiple audio streams
2046 'url': 'WaOKSUlf4TM',
2047 'only_matching': True
9297939e 2048 }, {
2049 # Requires Premium: has format 141 when requested using YTM url
2050 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2051 'only_matching': True
2052 }, {
120916da 2053 # multiple subtitles with same lang_code
2054 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2055 'only_matching': True,
109dd3b2 2056 }, {
2057 # Force use android client fallback
2058 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2059 'info_dict': {
2060 'id': 'YOelRv7fMxY',
11f9be09 2061 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2062 'ext': '3gp',
2063 'upload_date': '20210624',
2064 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2065 'uploader': 'colinfurze',
11f9be09 2066 'uploader_id': 'colinfurze',
109dd3b2 2067 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2068 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2069 'duration': 596,
2070 'categories': ['Entertainment'],
2071 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2072 'view_count': int,
2073 'channel': 'colinfurze',
2074 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2075 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2076 'age_limit': 0,
2077 'availability': 'public',
2078 'like_count': int,
2079 'live_status': 'not_live',
2080 'playable_in_embed': True,
6c73052c 2081 'channel_follower_count': int
109dd3b2 2082 },
2083 'params': {
2084 'format': '17', # 3gp format available on android
2085 'extractor_args': {'youtube': {'player_client': ['android']}},
2086 },
120916da 2087 },
109dd3b2 2088 {
2089 # Skip download of additional client configs (remix client config in this case)
2090 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2091 'only_matching': True,
2092 'params': {
2093 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2094 },
8fc54b12 2095 }, {
2096 # shorts
2097 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2098 'only_matching': True,
9222c381 2099 }, {
2100 'note': 'Storyboards',
2101 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2102 'info_dict': {
2103 'id': '5KLPxDtMqe8',
2104 'ext': 'mhtml',
2105 'format_id': 'sb0',
2106 'title': 'Your Brain is Plastic',
2107 'uploader_id': 'scishow',
2108 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2109 'upload_date': '20140324',
2110 'uploader': 'SciShow',
976ae3ea 2111 'like_count': int,
2112 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2113 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2114 'view_count': int,
2115 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2116 'playable_in_embed': True,
2117 'tags': 'count:12',
2118 'uploader_url': 'http://www.youtube.com/user/scishow',
2119 'availability': 'public',
2120 'channel': 'SciShow',
2121 'live_status': 'not_live',
2122 'duration': 248,
2123 'categories': ['Education'],
2124 'age_limit': 0,
6c73052c 2125 'channel_follower_count': int
9222c381 2126 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2127 }, {
2128 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2129 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2130 'info_dict': {
2131 'id': '2NUZ8W2llS4',
2132 'ext': 'mp4',
2133 'title': 'The NP that test your phone performance 🙂',
2134 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2135 'uploader': 'Leon Nguyen',
2136 'uploader_id': 'VNSXIII',
2137 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2138 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2139 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2140 'duration': 21,
2141 'view_count': int,
2142 'age_limit': 0,
2143 'categories': ['Gaming'],
2144 'tags': 'count:23',
2145 'playable_in_embed': True,
2146 'live_status': 'not_live',
2147 'upload_date': '20220103',
2148 'like_count': int,
2149 'availability': 'public',
2150 'channel': 'Leon Nguyen',
2151 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2152 'channel_follower_count': int
2153 }
2154 }, {
2155 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2156 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2157 'info_dict': {
2158 'id': 'mzZzzBU6lrM',
2159 'ext': 'mp4',
2160 'title': 'I Met GeorgeNotFound In Real Life...',
2161 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2162 'uploader': 'Quackity',
2163 'uploader_id': 'QuackityHQ',
2164 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2165 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2166 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2167 'duration': 955,
2168 'view_count': int,
2169 'age_limit': 0,
2170 'categories': ['Entertainment'],
2171 'tags': 'count:26',
2172 'playable_in_embed': True,
2173 'live_status': 'not_live',
2174 'release_timestamp': 1641172509,
2175 'release_date': '20220103',
2176 'upload_date': '20220103',
2177 'like_count': int,
2178 'availability': 'public',
2179 'channel': 'Quackity',
2180 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2181 'channel_follower_count': int
2182 }
2183 },
2184 { # continuous livestream. Microformat upload date should be preferred.
2185 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2186 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2187 'info_dict': {
2188 'id': 'kgx4WGK0oNU',
2189 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2190 'ext': 'mp4',
2191 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2192 'availability': 'public',
2193 'age_limit': 0,
2194 'release_timestamp': 1637975704,
2195 'upload_date': '20210619',
2196 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2197 'live_status': 'is_live',
2198 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2199 'uploader': '阿鲍Abao',
2200 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2201 'channel': 'Abao in Tokyo',
2202 'channel_follower_count': int,
2203 'release_date': '20211127',
2204 'tags': 'count:39',
2205 'categories': ['People & Blogs'],
2206 'like_count': int,
2207 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2208 'view_count': int,
2209 'playable_in_embed': True,
2210 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2211 },
2212 'params': {'skip_download': True}
6e634cbe 2213 }, {
2214 # Story. Requires specific player params to work.
2215 # Note: stories get removed after some period of time
ee27297f 2216 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2217 'info_dict': {
ee27297f 2218 'id': 'vv8qTUWmulI',
6e634cbe 2219 'ext': 'mp4',
ee27297f 2220 'availability': 'unlisted',
2221 'view_count': int,
2222 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2223 'upload_date': '20220526',
2224 'categories': ['Education'],
2225 'title': 'Story',
2226 'channel': 'IT\'S HISTORY',
2227 'description': '',
2228 'uploader_id': 'BlastfromthePast',
2229 'duration': 12,
2230 'uploader': 'IT\'S HISTORY',
6e634cbe 2231 'playable_in_embed': True,
6e634cbe 2232 'age_limit': 0,
6e634cbe 2233 'live_status': 'not_live',
ee27297f 2234 'tags': [],
2235 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2236 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2237 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2238 }
2239 }, {
2240 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2241 'info_dict': {
2242 'id': 'tjjjtzRLHvA',
2243 'ext': 'mp4',
2244 'title': 'ハッシュタグ無し };if window.ytcsi',
2245 'upload_date': '20220323',
2246 'like_count': int,
2247 'availability': 'unlisted',
2248 'channel': 'nao20010128nao',
2249 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2250 'age_limit': 0,
2251 'uploader': 'nao20010128nao',
2252 'uploader_id': 'nao20010128nao',
2253 'categories': ['Music'],
6e634cbe 2254 'view_count': int,
2255 'description': '',
ee27297f 2256 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2257 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2258 'live_status': 'not_live',
2259 'playable_in_embed': True,
2260 'channel_follower_count': int,
2261 'duration': 6,
2262 'tags': [],
2263 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2264 }
2265 }
2eb88d95
PH
2266 ]
2267
201c1459 2268 @classmethod
2269 def suitable(cls, url):
4dfbf869 2270 from ..utils import parse_qs
2271
201c1459 2272 qs = parse_qs(url)
2273 if qs.get('list', [None])[0]:
2274 return False
86e5f3ed 2275 return super().suitable(url)
201c1459 2276
e0df6211 2277 def __init__(self, *args, **kwargs):
86e5f3ed 2278 super().__init__(*args, **kwargs)
545cc85d 2279 self._code_cache = {}
83799698 2280 self._player_cache = {}
e0df6211 2281
adbc4ec4 2282 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2283 lock = threading.Lock()
2284
2285 is_live = True
185bf310 2286 start_time = time.time()
adbc4ec4
THD
2287 formats = [f for f in formats if f.get('is_from_start')]
2288
185bf310 2289 def refetch_manifest(format_id, delay):
2290 nonlocal formats, start_time, is_live
2291 if time.time() <= start_time + delay:
adbc4ec4
THD
2292 return
2293
2294 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2295 video_details = traverse_obj(
2296 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2297 microformats = traverse_obj(
2298 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2299 expected_type=dict, default=[])
2300 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2301 start_time = time.time()
adbc4ec4 2302
185bf310 2303 def mpd_feed(format_id, delay):
adbc4ec4
THD
2304 """
2305 @returns (manifest_url, manifest_stream_number, is_live) or None
2306 """
2307 with lock:
185bf310 2308 refetch_manifest(format_id, delay)
adbc4ec4
THD
2309
2310 f = next((f for f in formats if f['format_id'] == format_id), None)
2311 if not f:
185bf310 2312 if not is_live:
2313 self.to_screen(f'{video_id}: Video is no longer live')
2314 else:
2315 self.report_warning(
2316 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2317 return None
2318 return f['manifest_url'], f['manifest_stream_number'], is_live
2319
2320 for f in formats:
a539f065 2321 f['is_live'] = True
adbc4ec4
THD
2322 f['protocol'] = 'http_dash_segments_generator'
2323 f['fragments'] = functools.partial(
2324 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2325
2326 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2327 FETCH_SPAN, MAX_DURATION = 5, 432000
2328
2329 mpd_url, stream_number, is_live = None, None, True
2330
2331 begin_index = 0
2332 download_start_time = ctx.get('start') or time.time()
2333
2334 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2335 if lack_early_segments:
2336 self.report_warning(bug_reports_message(
2337 'Starting download from the last 120 hours of the live stream since '
2338 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2339 lack_early_segments = True
2340
2341 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2342 fragments, fragment_base_url = None, None
2343
a539f065 2344 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2345 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2346 # Obtain from MPD's maximum seq value
2347 old_mpd_url = mpd_url
185bf310 2348 last_error = ctx.pop('last_error', None)
a539f065 2349 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2350 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2351 or (mpd_url, stream_number, False))
2352 if not refresh_sequence:
2353 if expire_fast and not is_live:
2354 return False, last_seq
2355 elif old_mpd_url == mpd_url:
2356 return True, last_seq
adbc4ec4
THD
2357 try:
2358 fmts, _ = self._extract_mpd_formats_and_subtitles(
2359 mpd_url, None, note=False, errnote=False, fatal=False)
2360 except ExtractorError:
2361 fmts = None
2362 if not fmts:
a539f065 2363 no_fragment_score += 2
adbc4ec4
THD
2364 return False, last_seq
2365 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2366 fragments = fmt_info['fragments']
2367 fragment_base_url = fmt_info['fragment_base_url']
2368 assert fragment_base_url
2369
2370 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2371 return True, _last_seq
2372
2373 while is_live:
2374 fetch_time = time.time()
2375 if no_fragment_score > 30:
2376 return
2377 if last_segment_url:
2378 # Obtain from "X-Head-Seqnum" header value from each segment
2379 try:
2380 urlh = self._request_webpage(
2381 last_segment_url, None, note=False, errnote=False, fatal=False)
2382 except ExtractorError:
2383 urlh = None
2384 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2385 if last_seq is None:
a539f065 2386 no_fragment_score += 2
adbc4ec4
THD
2387 last_segment_url = None
2388 continue
2389 else:
a539f065
LNO
2390 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2391 no_fragment_score += 2
185bf310 2392 if not should_continue:
adbc4ec4
THD
2393 continue
2394
2395 if known_idx > last_seq:
2396 last_segment_url = None
2397 continue
2398
2399 last_seq += 1
2400
2401 if begin_index < 0 and known_idx < 0:
2402 # skip from the start when it's negative value
2403 known_idx = last_seq + begin_index
2404 if lack_early_segments:
2405 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2406 try:
2407 for idx in range(known_idx, last_seq):
2408 # do not update sequence here or you'll get skipped some part of it
a539f065 2409 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2410 if not should_continue:
adbc4ec4
THD
2411 known_idx = idx - 1
2412 raise ExtractorError('breaking out of outer loop')
2413 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2414 yield {
2415 'url': last_segment_url,
36195c44 2416 'fragment_count': last_seq,
adbc4ec4
THD
2417 }
2418 if known_idx == last_seq:
2419 no_fragment_score += 5
2420 else:
2421 no_fragment_score = 0
2422 known_idx = last_seq
2423 except ExtractorError:
2424 continue
2425
2426 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2427
b6de707d 2428 def _extract_player_url(self, *ytcfgs, webpage=None):
2429 player_url = traverse_obj(
2430 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2431 get_all=False, expected_type=compat_str)
11f9be09 2432 if not player_url:
b6de707d 2433 return
60f393e4 2434 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2435
b6de707d 2436 def _download_player_url(self, video_id, fatal=False):
2437 res = self._download_webpage(
2438 'https://www.youtube.com/iframe_api',
2439 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2440 if res:
2441 player_version = self._search_regex(
2442 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2443 if player_version:
2444 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2445
60064c53
PH
2446 def _signature_cache_id(self, example_sig):
2447 """ Return a string representation of a signature """
78caa52a 2448 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2449
e40c758c
S
2450 @classmethod
2451 def _extract_player_info(cls, player_url):
2452 for player_re in cls._PLAYER_INFO_RE:
2453 id_m = re.search(player_re, player_url)
2454 if id_m:
2455 break
2456 else:
c081b35c 2457 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2458 return id_m.group('id')
e40c758c 2459
404f611f 2460 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2461 player_id = self._extract_player_info(player_url)
2462 if player_id not in self._code_cache:
1276a43a 2463 code = self._download_webpage(
109dd3b2 2464 player_url, video_id, fatal=fatal,
2465 note='Downloading player ' + player_id,
2466 errnote='Download of %s failed' % player_url)
1276a43a 2467 if code:
2468 self._code_cache[player_id] = code
404f611f 2469 return self._code_cache.get(player_id)
109dd3b2 2470
e40c758c 2471 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2472 player_id = self._extract_player_info(player_url)
e0df6211 2473
c4417ddb 2474 # Read from filesystem cache
86e5f3ed 2475 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2476 assert os.path.basename(func_id) == func_id
a0e07d31 2477
9809740b 2478 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2479 if cache_spec is not None:
78caa52a 2480 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2481
404f611f 2482 code = self._load_player(video_id, player_url)
2483 if code:
109dd3b2 2484 res = self._parse_sig_js(code)
e0df6211 2485
109dd3b2 2486 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2487 cache_res = res(test_string)
2488 cache_spec = [ord(c) for c in cache_res]
83799698 2489
9809740b 2490 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2491 return res
83799698 2492
60064c53 2493 def _print_sig_code(self, func, example_sig):
404f611f 2494 if not self.get_param('youtube_print_sig_code'):
2495 return
2496
edf3e38e
PH
2497 def gen_sig_code(idxs):
2498 def _genslice(start, end, step):
78caa52a 2499 starts = '' if start == 0 else str(start)
8bcc8756 2500 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2501 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2502 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2503
2504 step = None
7af808a5
PH
2505 # Quelch pyflakes warnings - start will be set when step is set
2506 start = '(Never used)'
edf3e38e
PH
2507 for i, prev in zip(idxs[1:], idxs[:-1]):
2508 if step is not None:
2509 if i - prev == step:
2510 continue
2511 yield _genslice(start, prev, step)
2512 step = None
2513 continue
2514 if i - prev in [-1, 1]:
2515 step = i - prev
2516 start = prev
2517 continue
2518 else:
78caa52a 2519 yield 's[%d]' % prev
edf3e38e 2520 if step is None:
78caa52a 2521 yield 's[%d]' % i
edf3e38e
PH
2522 else:
2523 yield _genslice(start, i, step)
2524
78caa52a 2525 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2526 cache_res = func(test_string)
edf3e38e 2527 cache_spec = [ord(c) for c in cache_res]
78caa52a 2528 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2529 signature_id_tuple = '(%s)' % (
2530 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2531 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2532 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2533 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2534
e0df6211
PH
2535 def _parse_sig_js(self, jscode):
2536 funcname = self._search_regex(
abefc03f
S
2537 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2538 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
2539 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2540 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2541 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}\(a,\d+\)',
2542 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 2543 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2544 # Obsolete patterns
2545 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2546 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2547 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2548 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2549 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2550 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2551 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2552 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2553 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2554
2555 jsi = JSInterpreter(jscode)
2556 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2557 return lambda s: initial_function([s])
2558
545cc85d 2559 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2560 """Turn the encrypted s field into a working signature"""
c8bf86d5 2561 try:
62af3a0e 2562 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2563 if player_id not in self._player_cache:
52023f12 2564 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2565 self._player_cache[player_id] = func
2566 func = self._player_cache[player_id]
404f611f 2567 self._print_sig_code(func, s)
c8bf86d5
PH
2568 return func(s)
2569 except Exception as e:
52023f12 2570 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2571
2572 def _decrypt_nsig(self, s, video_id, player_url):
2573 """Turn the encrypted n field into a working signature"""
2574 if player_url is None:
2575 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2576 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2577
2578 sig_id = ('nsig_value', s)
2579 if sig_id in self._player_cache:
2580 return self._player_cache[sig_id]
2581
2582 try:
2583 player_id = ('nsig', player_url)
2584 if player_id not in self._player_cache:
2585 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2586 func = self._player_cache[player_id]
2587 self._player_cache[sig_id] = func(s)
2588 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2589 return self._player_cache[sig_id]
2590 except Exception as e:
aa9369a2 2591 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2592
2593 def _extract_n_function_name(self, jscode):
48416bc4 2594 nfunc, idx = self._search_regex(
c571b3a6 2595 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2596 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2597 if not idx:
2598 return nfunc
2599 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2600 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2601 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2602
2603 def _extract_n_function(self, video_id, player_url):
2604 player_id = self._extract_player_info(player_url)
9809740b 2605 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2606
2607 if func_code:
2608 jsi = JSInterpreter(func_code)
2609 else:
2610 jscode = self._load_player(video_id, player_url)
2611 funcname = self._extract_n_function_name(jscode)
2612 jsi = JSInterpreter(jscode)
2613 func_code = jsi.extract_function_code(funcname)
9809740b 2614 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2615
2616 if self.get_param('youtube_print_sig_code'):
2617 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2618
2619 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2620
109dd3b2 2621 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2622 """
2623 Extract signatureTimestamp (sts)
2624 Required to tell API what sig/player version is in use.
2625 """
2626 sts = None
2627 if isinstance(ytcfg, dict):
2628 sts = int_or_none(ytcfg.get('STS'))
2629
2630 if not sts:
2631 # Attempt to extract from player
2632 if player_url is None:
2633 error_msg = 'Cannot extract signature timestamp without player_url.'
2634 if fatal:
2635 raise ExtractorError(error_msg)
2636 self.report_warning(error_msg)
2637 return
404f611f 2638 code = self._load_player(video_id, player_url, fatal=fatal)
2639 if code:
109dd3b2 2640 sts = int_or_none(self._search_regex(
2641 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2642 'JS player signature timestamp', group='sts', fatal=fatal))
2643 return sts
2644
11f9be09 2645 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2646 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2647 label = 'fully ' if is_full else ''
2648 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2649 expected_type=url_or_none)
2650 if not url:
2651 self.report_warning(f'Unable to mark {label}watched')
2652 return
2653 parsed_url = compat_urlparse.urlparse(url)
2654 qs = compat_urlparse.parse_qs(parsed_url.query)
2655
2656 # cpn generation algorithm is reverse engineered from base.js.
2657 # In fact it works even with dummy cpn.
2658 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2659 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2660
2661 # # more consistent results setting it to right before the end
2662 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2663
2664 qs.update({
2665 'ver': ['2'],
2666 'cpn': [cpn],
2667 'cmt': video_length,
2668 'el': 'detailpage', # otherwise defaults to "shorts"
2669 })
2670
2671 if is_full:
2672 # these seem to mark watchtime "history" in the real world
2673 # they're required, so send in a single value
2674 qs.update({
2675 'st': video_length,
2676 'et': video_length,
2677 })
2678
2679 url = compat_urlparse.urlunparse(
2680 parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2681
2682 self._download_webpage(
2683 url, video_id, f'Marking {label}watched',
2684 'Unable to mark watched', fatal=False)
d77ab8e2 2685
66c9fa36
S
2686 @staticmethod
2687 def _extract_urls(webpage):
2688 # Embedded YouTube player
2689 entries = [
2690 unescapeHTML(mobj.group('url'))
2691 for mobj in re.finditer(r'''(?x)
2692 (?:
2693 <iframe[^>]+?src=|
2694 data-video-url=|
2695 <embed[^>]+?src=|
2696 embedSWF\(?:\s*|
2697 <object[^>]+data=|
2698 new\s+SWFObject\(
2699 )
2700 (["\'])
2701 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2702 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2703 \1''', webpage)]
2704
2705 # lazyYT YouTube embed
2706 entries.extend(list(map(
2707 unescapeHTML,
2708 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2709
2710 # Wordpress "YouTube Video Importer" plugin
2711 matches = re.findall(r'''(?x)<div[^>]+
2712 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2713 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2714 entries.extend(m[-1] for m in matches)
2715
2716 return entries
2717
2718 @staticmethod
2719 def _extract_url(webpage):
2720 urls = YoutubeIE._extract_urls(webpage)
2721 return urls[0] if urls else None
2722
97665381
PH
2723 @classmethod
2724 def extract_id(cls, url):
2725 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2726 if mobj is None:
69ea8ca4 2727 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2728 return mobj.group('id')
c5e8d7af 2729
7c365c21 2730 def _extract_chapters_from_json(self, data, duration):
2731 chapter_list = traverse_obj(
2732 data, (
2733 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2734 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2735 ), expected_type=list)
2736
2737 return self._extract_chapters(
2738 chapter_list,
2739 chapter_time=lambda chapter: float_or_none(
2740 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2741 chapter_title=lambda chapter: traverse_obj(
2742 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2743 duration=duration)
2744
2745 def _extract_chapters_from_engagement_panel(self, data, duration):
2746 content_list = traverse_obj(
8bdd16b4 2747 data,
7c365c21 2748 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2749 expected_type=list, default=[])
052e1350 2750 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2751 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2752
1890fc63 2753 return next(filter(None, (
2754 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2755 chapter_time, chapter_title, duration)
2756 for contents in content_list)), [])
7c365c21 2757
1890fc63 2758 def _extract_chapters_from_description(self, description, duration):
2759 return self._extract_chapters(
2760 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2761 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2762 duration=duration, strict=False)
84213ea8 2763
1890fc63 2764 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2765 if not duration:
2766 return
2767 chapter_list = [{
2768 'start_time': chapter_time(chapter),
2769 'title': chapter_title(chapter),
2770 } for chapter in chapter_list or []]
2771 if not strict:
2772 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2773
2774 chapters = [{'start_time': 0, 'title': '<Untitled>'}]
2775 for idx, chapter in enumerate(chapter_list):
2776 if chapter['start_time'] is None or not chapter['title']:
2777 self.report_warning(f'Incomplete chapter {idx}')
2778 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2779 chapters[-1]['end_time'] = chapter['start_time']
2780 chapters.append(chapter)
2781 else:
2782 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
2783 chapters[-1]['end_time'] = duration
2784 return chapters if len(chapters) > 1 and chapters[1]['start_time'] else chapters[1:]
84213ea8 2785
a1c5d2ca
M
2786 def _extract_comment(self, comment_renderer, parent=None):
2787 comment_id = comment_renderer.get('commentId')
2788 if not comment_id:
2789 return
fe93e2c4 2790
052e1350 2791 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2792
49bd8c66 2793 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2794 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2795 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2796 author_id = try_get(comment_renderer,
2797 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2798
49bd8c66 2799 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2800 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2801 author_thumbnail = try_get(comment_renderer,
2802 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2803
2804 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2805 is_favorited = 'creatorHeart' in (try_get(
2806 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2807 return {
2808 'id': comment_id,
2809 'text': text,
d92f5d5a 2810 'timestamp': timestamp,
a1c5d2ca
M
2811 'time_text': time_text,
2812 'like_count': votes,
97524332 2813 'is_favorited': is_favorited,
a1c5d2ca
M
2814 'author': author,
2815 'author_id': author_id,
2816 'author_thumbnail': author_thumbnail,
2817 'author_is_uploader': author_is_uploader,
2818 'parent': parent or 'root'
2819 }
2820
46383212 2821 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2822
2823 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2824
2825 def extract_header(contents):
2d6659b9 2826 _continuation = None
2827 for content in contents:
46383212 2828 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2829 expected_comment_count = self._get_count(
2830 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2831
2d6659b9 2832 if expected_comment_count:
46383212 2833 tracker['est_total'] = expected_comment_count
2834 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2835 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2836
2837 sort_menu_item = try_get(
2838 comments_header_renderer,
2839 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2840 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2841
2842 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2843 if not _continuation:
2844 continue
2845
46383212 2846 sort_text = str_or_none(sort_menu_item.get('title'))
2847 if not sort_text:
2d6659b9 2848 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2849 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2850 break
a2160aa4 2851 return _continuation
a1c5d2ca 2852
2d6659b9 2853 def extract_thread(contents):
a1c5d2ca 2854 if not parent:
46383212 2855 tracker['current_page_thread'] = 0
a1c5d2ca 2856 for content in contents:
46383212 2857 if not parent and tracker['total_parent_comments'] >= max_parents:
2858 yield
a1c5d2ca 2859 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2860 comment_renderer = get_first(
2861 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2862 expected_type=dict, default={})
a1c5d2ca 2863
a1c5d2ca
M
2864 comment = self._extract_comment(comment_renderer, parent)
2865 if not comment:
2866 continue
46383212 2867
2868 tracker['running_total'] += 1
2869 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2870 yield comment
46383212 2871
a1c5d2ca
M
2872 # Attempt to get the replies
2873 comment_replies_renderer = try_get(
2874 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2875
2876 if comment_replies_renderer:
46383212 2877 tracker['current_page_thread'] += 1
a1c5d2ca 2878 comment_entries_iter = self._comment_entries(
99e9e001 2879 comment_replies_renderer, ytcfg, video_id,
46383212 2880 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2881 yield from itertools.islice(comment_entries_iter, min(
2882 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2883
46383212 2884 # Keeps track of counts across recursive calls
2885 if not tracker:
2886 tracker = dict(
2887 running_total=0,
2888 est_total=0,
2889 current_page_thread=0,
2890 total_parent_comments=0,
2891 total_reply_comments=0)
2892
2893 # TODO: Deprecated
2d6659b9 2894 # YouTube comments have a max depth of 2
46383212 2895 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2896 if max_depth:
2897 self._downloader.deprecation_warning(
2898 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2899 if max_depth == 1 and parent:
2900 return
a1c5d2ca 2901
46383212 2902 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2903 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2904
46383212 2905 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2906
46383212 2907 response = None
6e634cbe 2908 is_forced_continuation = False
2d6659b9 2909 is_first_continuation = parent is None
6e634cbe 2910 if is_first_continuation and not continuation:
2911 # Sometimes you can get comments by generating the continuation yourself,
2912 # even if YouTube initially reports them being disabled - e.g. stories comments.
2913 # Note: if the comment section is actually disabled, YouTube may return a response with
2914 # required check_get_keys missing. So we will disable that check initially in this case.
2915 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2916 is_forced_continuation = True
a1c5d2ca
M
2917
2918 for page_num in itertools.count(0):
2919 if not continuation:
2920 break
46383212 2921 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2922 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2923 if page_num == 0:
2924 if is_first_continuation:
2925 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2926 else:
2d6659b9 2927 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2928 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2929 else:
2930 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2931 ' ' if parent else '', ' replies' if parent else '',
2932 page_num, comment_prog_str)
2933
2934 response = self._extract_response(
fe93e2c4 2935 item_id=None, query=continuation,
2d6659b9 2936 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2937 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2938 is_forced_continuation = False
46383212 2939 continuation_contents = traverse_obj(
2940 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2941
2d6659b9 2942 continuation = None
46383212 2943 for continuation_section in continuation_contents:
2944 continuation_items = traverse_obj(
2945 continuation_section,
2946 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2947 get_all=False, expected_type=list) or []
2948 if is_first_continuation:
2949 continuation = extract_header(continuation_items)
2950 is_first_continuation = False
2d6659b9 2951 if continuation:
a1c5d2ca 2952 break
46383212 2953 continue
a1c5d2ca 2954
46383212 2955 for entry in extract_thread(continuation_items):
2956 if not entry:
2957 return
2958 yield entry
2959 continuation = self._extract_continuation({'contents': continuation_items})
2960 if continuation:
2d6659b9 2961 break
a1c5d2ca 2962
6e634cbe 2963 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2964 if message and not parent and tracker['running_total'] == 0:
2965 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2966
2967 @staticmethod
2968 def _generate_comment_continuation(video_id):
2969 """
2970 Generates initial comment section continuation token from given video id
2971 """
2972 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2973 return base64.b64encode(token.encode()).decode()
2974
a2160aa4 2975 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2976 """Entry for comment extraction"""
2d6659b9 2977 def _real_comment_extract(contents):
aae16f6e 2978 renderer = next((
2979 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2980 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2981 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2982
a2160aa4 2983 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2984 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2985
109dd3b2 2986 @staticmethod
99e9e001 2987 def _get_checkok_params():
2988 return {'contentCheckOk': True, 'racyCheckOk': True}
2989
2990 @classmethod
2991 def _generate_player_context(cls, sts=None):
109dd3b2 2992 context = {
2993 'html5Preference': 'HTML5_PREF_WANTS',
2994 }
2995 if sts is not None:
2996 context['signatureTimestamp'] = sts
2997 return {
2998 'playbackContext': {
2999 'contentPlaybackContext': context
a1a7907b 3000 },
99e9e001 3001 **cls._get_checkok_params()
109dd3b2 3002 }
3003
e7e94f2a
D
3004 @staticmethod
3005 def _is_agegated(player_response):
3006 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3007 return True
e7e94f2a
D
3008
3009 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3010 AGE_GATE_REASONS = (
3011 'confirm your age', 'age-restricted', 'inappropriate', # reason
3012 'age_verification_required', 'age_check_required', # status
3013 )
3014 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3015
3016 @staticmethod
3017 def _is_unplayable(player_response):
3018 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3019
99e9e001 3020 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3021
11f9be09 3022 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3023 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3024 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3025 headers = self.generate_api_headers(
99e9e001 3026 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3027
6e634cbe 3028 yt_query = {
3029 'videoId': video_id,
3030 'params': '8AEB' # enable stories
3031 }
11f9be09 3032 yt_query.update(self._generate_player_context(sts))
3033 return self._extract_response(
3034 item_id=video_id, ep='player', query=yt_query,
379e44ed 3035 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3036 default_client=client,
11f9be09 3037 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3038 ) or None
3039
11f9be09 3040 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3041 requested_clients = []
d0d012d4 3042 default = ['android', 'web']
000c15a4 3043 allowed_clients = sorted(
86e5f3ed 3044 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3045 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3046 for client in self._configuration_arg('player_client'):
3047 if client in allowed_clients:
3048 requested_clients.append(client)
d0d012d4 3049 elif client == 'default':
3050 requested_clients.extend(default)
b4c055ba 3051 elif client == 'all':
3052 requested_clients.extend(allowed_clients)
3053 else:
3054 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3055 if not requested_clients:
d0d012d4 3056 requested_clients = default
cf7e015f 3057
11f9be09 3058 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3059 requested_clients.extend(
e7e94f2a 3060 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3061
11f9be09 3062 return orderedSet(requested_clients)
cf7e015f 3063
99e9e001 3064 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3065 initial_pr = None
3066 if webpage:
b7c47b74 3067 initial_pr = self._search_json(
3068 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3069
ae729626 3070 all_clients = set(clients)
c0bc527b 3071 clients = clients[::-1]
b6de707d 3072 prs = []
e7e94f2a 3073
ae729626 3074 def append_client(*client_names):
e7870111 3075 """ Append the first client name that exists but not already used """
ae729626 3076 for client_name in client_names:
e7870111
D
3077 actual_client = _split_innertube_client(client_name)[0]
3078 if actual_client in INNERTUBE_CLIENTS:
3079 if actual_client not in all_clients:
ae729626 3080 clients.append(client_name)
e7870111
D
3081 all_clients.add(actual_client)
3082 return
e7e94f2a 3083
379e44ed 3084 # Android player_response does not have microFormats which are needed for
3085 # extraction of some data. So we return the initial_pr with formats
3086 # stripped out even if not requested by the user
3087 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3088 if initial_pr:
3089 pr = dict(initial_pr)
3090 pr['streamingData'] = None
b6de707d 3091 prs.append(pr)
379e44ed 3092
3093 last_error = None
b6de707d 3094 tried_iframe_fallback = False
3095 player_url = None
c0bc527b 3096 while clients:
e7870111 3097 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3098 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3099 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3100 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3101
b6de707d 3102 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3103 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3104 if 'js' in self._configuration_arg('player_skip'):
3105 require_js_player = False
3106 player_url = None
3107
3108 if not player_url and not tried_iframe_fallback and require_js_player:
3109 player_url = self._download_player_url(video_id)
3110 tried_iframe_fallback = True
3111
379e44ed 3112 try:
3113 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3114 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3115 except ExtractorError as e:
3116 if last_error:
3117 self.report_warning(last_error)
3118 last_error = e
3119 continue
3120
11f9be09 3121 if pr:
b6de707d 3122 prs.append(pr)
c0bc527b 3123
e7e94f2a 3124 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3125 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3126 append_client(f'{base_client}_creator')
e7e94f2a 3127 elif self._is_agegated(pr):
e7870111
D
3128 if variant == 'tv_embedded':
3129 append_client(f'{base_client}_embedded')
3130 elif not variant:
3131 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3132
379e44ed 3133 if last_error:
b6de707d 3134 if not len(prs):
379e44ed 3135 raise last_error
3136 self.report_warning(last_error)
b6de707d 3137 return prs, player_url
11f9be09 3138
a1b2d843 3139 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3140 itags, stream_ids = {}, []
2a9c6dcd 3141 itag_qualities, res_qualities = {}, {}
d3fc8074 3142 q = qualities([
2a9c6dcd 3143 # Normally tiny is the smallest video-only formats. But
3144 # audio-only formats with unknown quality may get tagged as tiny
3145 'tiny',
3146 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3147 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3148 ])
11f9be09 3149 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3150
545cc85d 3151 for fmt in streaming_formats:
727029c5 3152 if fmt.get('targetDurationSec'):
545cc85d 3153 continue
321bf820 3154
cc2db878 3155 itag = str_or_none(fmt.get('itag'))
9297939e 3156 audio_track = fmt.get('audioTrack') or {}
3157 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3158 if stream_id in stream_ids:
3159 continue
3160
cc2db878 3161 quality = fmt.get('quality')
2a9c6dcd 3162 height = int_or_none(fmt.get('height'))
d3fc8074 3163 if quality == 'tiny' or not quality:
3164 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3165 # The 3gp format (17) in android client has a quality of "small",
3166 # but is actually worse than other formats
3167 if itag == '17':
3168 quality = 'tiny'
3169 if quality:
3170 if itag:
3171 itag_qualities[itag] = quality
3172 if height:
3173 res_qualities[height] = quality
cc2db878 3174 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3175 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3176 # number of fragment that would subsequently requested with (`&sq=N`)
3177 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3178 continue
3179
545cc85d 3180 fmt_url = fmt.get('url')
3181 if not fmt_url:
3182 sc = compat_parse_qs(fmt.get('signatureCipher'))
3183 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3184 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3185 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3186 continue
52023f12 3187 try:
3188 fmt_url += '&%s=%s' % (
3189 traverse_obj(sc, ('sp', -1)) or 'signature',
3190 self._decrypt_signature(encrypted_sig, video_id, player_url)
3191 )
3192 except ExtractorError as e:
3193 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3194 self.write_debug(e, only_once=True)
201e9eaa 3195 continue
545cc85d 3196
404f611f 3197 query = parse_qs(fmt_url)
3198 throttled = False
b2916526 3199 if query.get('n'):
404f611f 3200 try:
3201 fmt_url = update_url_query(fmt_url, {
3202 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3203 except ExtractorError as e:
aa9369a2 3204 self.report_warning(
1d485a1a 3205 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3206 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3207 self.write_debug(e, only_once=True)
404f611f 3208 throttled = True
3209
545cc85d 3210 if itag:
a0bb6ce5 3211 itags[itag] = 'https'
9297939e 3212 stream_ids.append(stream_id)
3213
0ad92dfb 3214 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3215 language_preference = (
3216 10 if audio_track.get('audioIsDefault') and 10
3217 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3218 else -1)
0ad92dfb 3219 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3220 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3221 # Make sure to avoid false positives with small duration differences.
3222 # Eg: __2ABJjxzNo, ySuUZEjARPY
3223 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3224 if is_damaged:
0f06bcd7 3225 self.report_warning(
3226 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3227 dct = {
3228 'asr': int_or_none(fmt.get('audioSampleRate')),
3229 'filesize': int_or_none(fmt.get('contentLength')),
3230 'format_id': itag,
34921b43 3231 'format_note': join_nonempty(
26e8e044 3232 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3233 ' (default)' if language_preference > 0 else ''),
404f611f 3234 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3235 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3236 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3237 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3238 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3239 'height': height,
dca3ff4a 3240 'quality': q(quality),
727029c5 3241 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3242 'tbr': tbr,
545cc85d 3243 'url': fmt_url,
2a9c6dcd 3244 'width': int_or_none(fmt.get('width')),
ab6df717 3245 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3246 'desc' if language_preference < -1 else ''),
3247 'language_preference': language_preference,
a405b38f 3248 # Strictly de-prioritize damaged and 3gp formats
3249 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3250 }
60bdb7bd 3251 mime_mobj = re.match(
3252 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3253 if mime_mobj:
3254 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3255 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3256 no_audio = dct.get('acodec') == 'none'
3257 no_video = dct.get('vcodec') == 'none'
3258 if no_audio:
3259 dct['vbr'] = tbr
3260 if no_video:
3261 dct['abr'] = tbr
3262 if no_audio or no_video:
545cc85d 3263 dct['downloader_options'] = {
3264 # Youtube throttles chunks >~10M
3265 'http_chunk_size': 10485760,
bf1317d2 3266 }
7c60c33e 3267 if dct.get('ext'):
3268 dct['container'] = dct['ext'] + '_dash'
11f9be09 3269 yield dct
545cc85d 3270
adbc4ec4 3271 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3272 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3273 if not self.get_param('youtube_include_hls_manifest', True):
3274 skip_manifests.append('hls')
0f06bcd7 3275 if not self.get_param('youtube_include_dash_manifest', True):
3276 skip_manifests.append('dash')
adbc4ec4
THD
3277 get_dash = 'dash' not in skip_manifests and (
3278 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3279 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3280
a0bb6ce5 3281 def process_manifest_format(f, proto, itag):
3282 if itag in itags:
3283 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3284 return False
3285 itag = f'{itag}-{proto}'
3286 if itag:
3287 f['format_id'] = itag
3288 itags[itag] = proto
3289
3290 f['quality'] = next((
3291 q(qdict[val])
e339d25a 3292 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3293 if val in qdict), -1)
3294 return True
2a9c6dcd 3295
11f9be09 3296 for sd in streaming_data:
5d3a0e79 3297 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3298 if hls_manifest_url:
2a9c6dcd 3299 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3300 if process_manifest_format(f, 'hls', self._search_regex(
3301 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3302 yield f
545cc85d 3303
5d3a0e79 3304 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3305 if dash_manifest_url:
2a9c6dcd 3306 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3307 if process_manifest_format(f, 'dash', f['format_id']):
3308 f['filesize'] = int_or_none(self._search_regex(
3309 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3310 if live_from_start:
3311 f['is_from_start'] = True
3312
a0bb6ce5 3313 yield f
11f9be09 3314
720c3099 3315 def _extract_storyboard(self, player_responses, duration):
3316 spec = get_first(
3317 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3318 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3319 if not base_url:
720c3099 3320 return
720c3099 3321 L = len(spec) - 1
3322 for i, args in enumerate(spec):
3323 args = args.split('#')
3324 counts = list(map(int_or_none, args[:5]))
3325 if len(args) != 8 or not all(counts):
3326 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3327 continue
3328 width, height, frame_count, cols, rows = counts
3329 N, sigh = args[6:]
3330
3331 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3332 fragment_count = frame_count / (cols * rows)
3333 fragment_duration = duration / fragment_count
3334 yield {
3335 'format_id': f'sb{i}',
3336 'format_note': 'storyboard',
3337 'ext': 'mhtml',
3338 'protocol': 'mhtml',
3339 'acodec': 'none',
3340 'vcodec': 'none',
3341 'url': url,
3342 'width': width,
3343 'height': height,
3344 'fragments': [{
b3edc806 3345 'url': url.replace('$M', str(j)),
720c3099 3346 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3347 } for j in range(math.ceil(fragment_count))],
3348 }
3349
adbc4ec4 3350 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3351 webpage = None
3352 if 'webpage' not in self._configuration_arg('player_skip'):
3353 webpage = self._download_webpage(
6e634cbe 3354 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3355
3356 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3357
b6de707d 3358 player_responses, player_url = self._extract_player_responses(
11f9be09 3359 self._get_requested_clients(url, smuggled_data),
99e9e001 3360 video_id, webpage, master_ytcfg)
11f9be09 3361
adbc4ec4
THD
3362 return webpage, master_ytcfg, player_responses, player_url
3363
a1b2d843 3364 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3365 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3366 is_live = get_first(video_details, 'isLive')
3367 if is_live is None:
3368 is_live = get_first(live_broadcast_details, 'isLiveNow')
3369
3370 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3371 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3372
3373 return live_broadcast_details, is_live, streaming_data, formats
3374
3375 def _real_extract(self, url):
3376 url, smuggled_data = unsmuggle_url(url, {})
3377 video_id = self._match_id(url)
3378
3379 base_url = self.http_scheme() + '//www.youtube.com/'
3380 webpage_url = base_url + 'watch?v=' + video_id
3381
3382 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3383
11f9be09 3384 playability_statuses = traverse_obj(
3385 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3386
3387 trailer_video_id = get_first(
3388 playability_statuses,
3389 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3390 expected_type=str)
3391 if trailer_video_id:
3392 return self.url_result(
3393 trailer_video_id, self.ie_key(), trailer_video_id)
3394
3395 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3396 if webpage else (lambda x: None))
3397
3398 video_details = traverse_obj(
3399 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3400 microformats = traverse_obj(
3401 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3402 expected_type=dict, default=[])
3403 video_title = (
3404 get_first(video_details, 'title')
3405 or self._get_text(microformats, (..., 'title'))
3406 or search_meta(['og:title', 'twitter:title', 'title']))
3407 video_description = get_first(video_details, 'shortDescription')
3408
d89257f3 3409 multifeed_metadata_list = get_first(
3410 player_responses,
3411 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3412 expected_type=str)
3413 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3414 if self.get_param('noplaylist'):
11f9be09 3415 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3416 else:
3417 entries = []
3418 feed_ids = []
3419 for feed in multifeed_metadata_list.split(','):
3420 # Unquote should take place before split on comma (,) since textual
3421 # fields may contain comma as well (see
3422 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3423 feed_data = compat_parse_qs(
3424 compat_urllib_parse_unquote_plus(feed))
3425
3426 def feed_entry(name):
3427 return try_get(
3428 feed_data, lambda x: x[name][0], compat_str)
3429
3430 feed_id = feed_entry('id')
3431 if not feed_id:
3432 continue
3433 feed_title = feed_entry('title')
3434 title = video_title
3435 if feed_title:
3436 title += ' (%s)' % feed_title
3437 entries.append({
3438 '_type': 'url_transparent',
3439 'ie_key': 'Youtube',
3440 'url': smuggle_url(
3441 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3442 {'force_singlefeed': True}),
3443 'title': title,
3444 })
3445 feed_ids.append(feed_id)
3446 self.to_screen(
3447 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3448 % (', '.join(feed_ids), video_id))
3449 return self.playlist_result(
3450 entries, video_id, video_title, video_description)
11f9be09 3451
a1b2d843 3452 duration = int_or_none(
3453 get_first(video_details, 'lengthSeconds')
3454 or get_first(microformats, 'lengthSeconds')
3455 or parse_duration(search_meta('duration'))) or None
3456
829bbd1d 3457 if get_first(video_details, 'isPostLiveDvr'):
3458 self.write_debug('Video is in Post-Live Manifestless mode')
3459 if duration or 0 > 4 * 3600:
3460 self.report_warning(
3461 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3462 'This is a known issue and patches are welcome')
3463
a1b2d843 3464 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3465 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3466
545cc85d 3467 if not formats:
11f9be09 3468 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3469 self.report_drm(video_id)
11f9be09 3470 pemr = get_first(
3471 playability_statuses,
3472 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3473 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3474 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3475 if subreason:
545cc85d 3476 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3477 countries = get_first(microformats, 'availableCountries')
545cc85d 3478 if not countries:
3479 regions_allowed = search_meta('regionsAllowed')
3480 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3481 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3482 reason += f'. {subreason}'
545cc85d 3483 if reason:
b7da73eb 3484 self.raise_no_formats(reason, expected=True)
bf1317d2 3485
11f9be09 3486 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3487 if not keywords and webpage:
3488 keywords = [
3489 unescapeHTML(m.group('content'))
3490 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3491 for keyword in keywords:
3492 if keyword.startswith('yt:stretch='):
201c1459 3493 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3494 if mobj:
3495 # NB: float is intentional for forcing float division
3496 w, h = (float(v) for v in mobj.groups())
3497 if w > 0 and h > 0:
3498 ratio = w / h
3499 for f in formats:
3500 if f.get('vcodec') != 'none':
3501 f['stretched_ratio'] = ratio
3502 break
a709d873 3503 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3504 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3505 if thumbnail_url:
3506 thumbnails.append({
3507 'url': thumbnail_url,
ff2751ac 3508 })
fccf5021 3509 original_thumbnails = thumbnails.copy()
3510
0ba692ac 3511 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3512 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3513 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3514 thumbnail_names = [
bfec31be 3515 # While the *1,*2,*3 thumbnails are just below their correspnding "*default" variants
3516 # in resolution, these are not the custom thumbnail. So de-prioritize them
3517 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3518 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3519 ]
cca80fe6 3520 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3521 thumbnails.extend({
3522 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3523 video_id=video_id, name=name, ext=ext,
3524 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3525 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3526 for thumb in thumbnails:
cca80fe6 3527 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3528 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3529 self._remove_duplicate_formats(thumbnails)
fccf5021 3530 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3531
7ea65411 3532 category = get_first(microformats, 'category') or search_meta('genre')
3533 channel_id = str_or_none(
3534 get_first(video_details, 'channelId')
3535 or get_first(microformats, 'externalChannelId')
3536 or search_meta('channelId'))
7ea65411 3537 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3538
3539 live_content = get_first(video_details, 'isLiveContent')
3540 is_upcoming = get_first(video_details, 'isUpcoming')
3541 if is_live is None:
3542 if is_upcoming or live_content is False:
3543 is_live = False
3544 if is_upcoming is None and (live_content or is_live):
3545 is_upcoming = False
adbc4ec4
THD
3546 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3547 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3548 if not duration and live_end_time and live_start_time:
3549 duration = live_end_time - live_start_time
3550
3551 if is_live and self.get_param('live_from_start'):
3552 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3553
720c3099 3554 formats.extend(self._extract_storyboard(player_responses, duration))
3555
3556 # Source is given priority since formats that throttle are given lower source_preference
3557 # When throttling issue is fully fixed, remove this
3558 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3559
545cc85d 3560 info = {
3561 'id': video_id,
39ca3b5c 3562 'title': video_title,
545cc85d 3563 'formats': formats,
3564 'thumbnails': thumbnails,
fccf5021 3565 # The best thumbnail that we are sure exists. Prevents unnecessary
3566 # URL checking if user don't care about getting the best possible thumbnail
3567 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3568 'description': video_description,
11f9be09 3569 'uploader': get_first(video_details, 'author'),
545cc85d 3570 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3571 'uploader_url': owner_profile_url,
3572 'channel_id': channel_id,
a70635b8 3573 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3574 'duration': duration,
3575 'view_count': int_or_none(
11f9be09 3576 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3577 or search_meta('interactionCount')),
11f9be09 3578 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3579 'age_limit': 18 if (
11f9be09 3580 get_first(microformats, 'isFamilySafe') is False
545cc85d 3581 or search_meta('isFamilyFriendly') == 'false'
3582 or search_meta('og:restrictions:age') == '18+') else 0,
3583 'webpage_url': webpage_url,
3584 'categories': [category] if category else None,
3585 'tags': keywords,
11f9be09 3586 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3587 'is_live': is_live,
3588 'was_live': (False if is_live or is_upcoming or live_content is False
3589 else None if is_live is None or is_upcoming is None
3590 else live_content),
3591 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3592 'release_timestamp': live_start_time,
545cc85d 3593 }
b477fc13 3594
3944e7af 3595 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3596 if pctr:
ecdc9049 3597 def get_lang_code(track):
3598 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3599 or track.get('languageCode'))
3600
3601 # Converted into dicts to remove duplicates
3602 captions = {
3603 get_lang_code(sub): sub
3604 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3605 translation_languages = {
3606 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3607 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3608
774d79cc 3609 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3610 lang_subs = container.setdefault(lang_code, [])
545cc85d 3611 for fmt in self._SUBTITLE_FORMATS:
3612 query.update({
3613 'fmt': fmt,
3614 })
3615 lang_subs.append({
3616 'ext': fmt,
60f393e4 3617 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3618 'name': sub_name,
545cc85d 3619 })
7e72694b 3620
ecdc9049 3621 subtitles, automatic_captions = {}, {}
3622 for lang_code, caption_track in captions.items():
3623 base_url = caption_track.get('baseUrl')
1235d333 3624 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3625 if not base_url:
3626 continue
ecdc9049 3627 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3628 if caption_track.get('kind') != 'asr':
545cc85d 3629 if not lang_code:
3630 continue
3631 process_language(
ecdc9049 3632 subtitles, base_url, lang_code, lang_name, {})
3633 if not caption_track.get('isTranslatable'):
3634 continue
3944e7af 3635 for trans_code, trans_name in translation_languages.items():
3636 if not trans_code:
545cc85d 3637 continue
1235d333 3638 orig_trans_code = trans_code
ecdc9049 3639 if caption_track.get('kind') != 'asr':
18e49408 3640 if 'translated_subs' in self._configuration_arg('skip'):
3641 continue
ecdc9049 3642 trans_code += f'-{lang_code}'
a70635b8 3643 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3644 # Add an "-orig" label to the original language so that it can be distinguished.
3645 # The subs are returned without "-orig" as well for compatibility
1235d333 3646 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3647 process_language(
d49669ac 3648 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3649 # Setting tlang=lang returns damaged subtitles.
d49669ac 3650 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3651 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3652 info['automatic_captions'] = automatic_captions
3653 info['subtitles'] = subtitles
7e72694b 3654
545cc85d 3655 parsed_url = compat_urllib_parse_urlparse(url)
3656 for component in [parsed_url.fragment, parsed_url.query]:
3657 query = compat_parse_qs(component)
3658 for k, v in query.items():
3659 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3660 d_k += '_time'
3661 if d_k not in info and k in s_ks:
3662 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3663
3664 # Youtube Music Auto-generated description
822b9d9c 3665 if video_description:
1890fc63 3666 mobj = re.search(
3667 r'''(?xs)
3668 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3669 (?P<album>[^\n]+)
3670 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3671 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3672 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3673 .+\nAuto-generated\ by\ YouTube\.\s*$
3674 ''', video_description)
822b9d9c 3675 if mobj:
822b9d9c
RA
3676 release_year = mobj.group('release_year')
3677 release_date = mobj.group('release_date')
3678 if release_date:
3679 release_date = release_date.replace('-', '')
3680 if not release_year:
545cc85d 3681 release_year = release_date[:4]
3682 info.update({
3683 'album': mobj.group('album'.strip()),
3684 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3685 'track': mobj.group('track').strip(),
3686 'release_date': release_date,
cc2db878 3687 'release_year': int_or_none(release_year),
545cc85d 3688 })
7e72694b 3689
545cc85d 3690 initial_data = None
3691 if webpage:
56ba69e4 3692 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3693 if not initial_data:
99e9e001 3694 query = {'videoId': video_id}
3695 query.update(self._get_checkok_params())
109dd3b2 3696 initial_data = self._extract_response(
3697 item_id=video_id, ep='next', fatal=False,
99e9e001 3698 ytcfg=master_ytcfg, query=query,
3699 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3700 note='Downloading initial data API JSON')
545cc85d 3701
0df111a3 3702 info['comment_count'] = traverse_obj(initial_data, (
3703 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3704 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3705 ), (
3706 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3707 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3708 ), expected_type=int_or_none, get_all=False)
3709
19a03940 3710 try: # This will error if there is no livechat
c60ee3a2 3711 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3712 except (KeyError, IndexError, TypeError):
3713 pass
3714 else:
ecdc9049 3715 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3716 # url is needed to set cookies
3717 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3718 'video_id': video_id,
3719 'ext': 'json',
f6745c49 3720 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3721 }]
545cc85d 3722
3723 if initial_data:
7c365c21 3724 info['chapters'] = (
3725 self._extract_chapters_from_json(initial_data, duration)
3726 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3727 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3728 or None)
545cc85d 3729
17322130 3730 contents = traverse_obj(
3731 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3732 expected_type=list, default=[])
3733
3734 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3735 if vpir:
3736 stl = vpir.get('superTitleLink')
3737 if stl:
3738 stl = self._get_text(stl)
3739 if try_get(
3740 vpir,
3741 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3742 info['location'] = stl
3743 else:
affc4fef 3744 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3745 if mobj:
545cc85d 3746 info.update({
17322130 3747 'series': mobj.group(1),
3748 'season_number': int(mobj.group(2)),
3749 'episode_number': int(mobj.group(3)),
545cc85d 3750 })
17322130 3751 for tlb in (try_get(
3752 vpir,
3753 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3754 list) or []):
3755 tbr = tlb.get('toggleButtonRenderer') or {}
3756 for getter, regex in [(
3757 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3758 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3759 lambda x: x['accessibility'],
3760 lambda x: x['accessibilityData']['accessibilityData'],
3761 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3762 label = (try_get(tbr, getter, dict) or {}).get('label')
3763 if label:
3764 mobj = re.match(regex, label)
3765 if mobj:
3766 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3767 break
17322130 3768 sbr_tooltip = try_get(
3769 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3770 if sbr_tooltip:
3771 like_count, dislike_count = sbr_tooltip.split(' / ')
3772 info.update({
3773 'like_count': str_to_int(like_count),
3774 'dislike_count': str_to_int(dislike_count),
3775 })
3776 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3777 if vsir:
3778 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3779 info.update({
3780 'channel': self._get_text(vor, 'title'),
3781 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3782
3783 rows = try_get(
3784 vsir,
3785 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3786 list) or []
3787 multiple_songs = False
3788 for row in rows:
3789 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3790 multiple_songs = True
3791 break
3792 for row in rows:
3793 mrr = row.get('metadataRowRenderer') or {}
3794 mrr_title = mrr.get('title')
3795 if not mrr_title:
3796 continue
3797 mrr_title = self._get_text(mrr, 'title')
3798 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3799 if mrr_title == 'License':
3800 info['license'] = mrr_contents_text
3801 elif not multiple_songs:
3802 if mrr_title == 'Album':
3803 info['album'] = mrr_contents_text
3804 elif mrr_title == 'Artist':
3805 info['artist'] = mrr_contents_text
3806 elif mrr_title == 'Song':
3807 info['track'] = mrr_contents_text
545cc85d 3808
3809 fallbacks = {
3810 'channel': 'uploader',
3811 'channel_id': 'uploader_id',
3812 'channel_url': 'uploader_url',
3813 }
992f9a73 3814
17322130 3815 # The upload date for scheduled, live and past live streams / premieres in microformats
3816 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3817 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3818 upload_date = (
3819 unified_strdate(get_first(microformats, 'uploadDate'))
3820 or unified_strdate(search_meta('uploadDate')))
3821 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3822 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3823 info['upload_date'] = upload_date
992f9a73 3824
545cc85d 3825 for to, frm in fallbacks.items():
3826 if not info.get(to):
3827 info[to] = info.get(frm)
3828
3829 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3830 v = info.get(s_k)
3831 if v:
3832 info[d_k] = v
b84071c0 3833
11f9be09 3834 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3835 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3836 is_membersonly = None
b28f8d24 3837 is_premium = None
c224251a
M
3838 if initial_data and is_private is not None:
3839 is_membersonly = False
b28f8d24 3840 is_premium = False
47193e02 3841 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3842 badge_labels = set()
3843 for content in contents:
3844 if not isinstance(content, dict):
3845 continue
3846 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3847 for badge_label in badge_labels:
3848 if badge_label.lower() == 'members only':
3849 is_membersonly = True
3850 elif badge_label.lower() == 'premium':
3851 is_premium = True
3852 elif badge_label.lower() == 'unlisted':
3853 is_unlisted = True
c224251a 3854
c224251a
M
3855 info['availability'] = self._availability(
3856 is_private=is_private,
b28f8d24 3857 needs_premium=is_premium,
c224251a
M
3858 needs_subscription=is_membersonly,
3859 needs_auth=info['age_limit'] >= 18,
3860 is_unlisted=None if is_private is None else is_unlisted)
3861
a2160aa4 3862 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3863
11f9be09 3864 self.mark_watched(video_id, player_responses)
d77ab8e2 3865
545cc85d 3866 return info
c5e8d7af 3867
a61fd4cf 3868
a6213a49 3869class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3870
182bda88 3871 @staticmethod
3872 def passthrough_smuggled_data(func):
3873 def _smuggle(entries, smuggled_data):
3874 for entry in entries:
3875 # TODO: Convert URL to music.youtube instead.
3876 # Do we need to passthrough any other smuggled_data?
3877 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3878 yield entry
3879
3880 @functools.wraps(func)
3881 def wrapper(self, url):
3882 url, smuggled_data = unsmuggle_url(url, {})
3883 if self.is_music_url(url):
3884 smuggled_data['is_music_url'] = True
3885 info_dict = func(self, url, smuggled_data)
3886 if smuggled_data and info_dict.get('entries'):
3887 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3888 return info_dict
3889 return wrapper
3890
a6213a49 3891 def _extract_channel_id(self, webpage):
3892 channel_id = self._html_search_meta(
3893 'channelId', webpage, 'channel id', default=None)
3894 if channel_id:
3895 return channel_id
3896 channel_url = self._html_search_meta(
3897 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3898 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3899 'twitter:app:url:googleplay'), webpage, 'channel url')
3900 return self._search_regex(
3901 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3902 channel_url, 'channel id')
15f6397c 3903
8bdd16b4 3904 @staticmethod
cd7c66cf 3905 def _extract_basic_item_renderer(item):
3906 # Modified from _extract_grid_item_renderer
201c1459 3907 known_basic_renderers = (
a17526e4 3908 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3909 )
3910 for key, renderer in item.items():
201c1459 3911 if not isinstance(renderer, dict):
cd7c66cf 3912 continue
201c1459 3913 elif key in known_basic_renderers:
3914 return renderer
3915 elif key.startswith('grid') and key.endswith('Renderer'):
3916 return renderer
8bdd16b4 3917
8bdd16b4 3918 def _grid_entries(self, grid_renderer):
3919 for item in grid_renderer['items']:
3920 if not isinstance(item, dict):
39b62db1 3921 continue
cd7c66cf 3922 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3923 if not isinstance(renderer, dict):
3924 continue
052e1350 3925 title = self._get_text(renderer, 'title')
fe93e2c4 3926
8bdd16b4 3927 # playlist
3928 playlist_id = renderer.get('playlistId')
3929 if playlist_id:
3930 yield self.url_result(
3931 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3932 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3933 video_title=title)
201c1459 3934 continue
8bdd16b4 3935 # video
3936 video_id = renderer.get('videoId')
3937 if video_id:
3938 yield self._extract_video(renderer)
201c1459 3939 continue
8bdd16b4 3940 # channel
3941 channel_id = renderer.get('channelId')
3942 if channel_id:
8bdd16b4 3943 yield self.url_result(
3944 'https://www.youtube.com/channel/%s' % channel_id,
3945 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3946 continue
3947 # generic endpoint URL support
3948 ep_url = urljoin('https://www.youtube.com/', try_get(
3949 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3950 compat_str))
3951 if ep_url:
3952 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3953 if ie.suitable(ep_url):
3954 yield self.url_result(
3955 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3956 break
8bdd16b4 3957
16aa9ea4 3958 def _music_reponsive_list_entry(self, renderer):
3959 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3960 if video_id:
3961 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3962 ie=YoutubeIE.ie_key(), video_id=video_id)
3963 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3964 if playlist_id:
3965 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3966 if video_id:
3967 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3968 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3969 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3970 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3971 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3972 if browse_id:
3973 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3974 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3975
3d3dddc9 3976 def _shelf_entries_from_content(self, shelf_renderer):
3977 content = shelf_renderer.get('content')
3978 if not isinstance(content, dict):
8bdd16b4 3979 return
cd7c66cf 3980 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3981 if renderer:
3982 # TODO: add support for nested playlists so each shelf is processed
3983 # as separate playlist
3984 # TODO: this includes only first N items
86e5f3ed 3985 yield from self._grid_entries(renderer)
3d3dddc9 3986 renderer = content.get('horizontalListRenderer')
3987 if renderer:
3988 # TODO
3989 pass
8bdd16b4 3990
29f7c58a 3991 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3992 ep = try_get(
3993 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3994 compat_str)
3995 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3996 if shelf_url:
29f7c58a 3997 # Skipping links to another channels, note that checking for
3998 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3999 # will not work
4000 if skip_channels and '/channels?' in shelf_url:
4001 return
052e1350 4002 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4003 yield self.url_result(shelf_url, video_title=title)
4004 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4005 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4006
8bdd16b4 4007 def _playlist_entries(self, video_list_renderer):
4008 for content in video_list_renderer['contents']:
4009 if not isinstance(content, dict):
4010 continue
4011 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4012 if not isinstance(renderer, dict):
4013 continue
4014 video_id = renderer.get('videoId')
4015 if not video_id:
4016 continue
4017 yield self._extract_video(renderer)
07aeced6 4018
3462ffa8 4019 def _rich_entries(self, rich_grid_renderer):
4020 renderer = try_get(
70d5c17b 4021 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4022 video_id = renderer.get('videoId')
4023 if not video_id:
4024 return
4025 yield self._extract_video(renderer)
4026
8bdd16b4 4027 def _video_entry(self, video_renderer):
4028 video_id = video_renderer.get('videoId')
4029 if video_id:
4030 return self._extract_video(video_renderer)
dacb3a86 4031
ad210f4f 4032 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4033 url = urljoin('https://youtube.com', traverse_obj(
4034 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4035 if url:
4036 return self.url_result(
4037 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4038
8bdd16b4 4039 def _post_thread_entries(self, post_thread_renderer):
4040 post_renderer = try_get(
4041 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4042 if not post_renderer:
4043 return
4044 # video attachment
4045 video_renderer = try_get(
895b0931 4046 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4047 video_id = video_renderer.get('videoId')
4048 if video_id:
4049 entry = self._extract_video(video_renderer)
8bdd16b4 4050 if entry:
4051 yield entry
895b0931 4052 # playlist attachment
4053 playlist_id = try_get(
4054 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
4055 if playlist_id:
4056 yield self.url_result(
e28f1c0a 4057 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4058 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4059 # inline video links
4060 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4061 for run in runs:
4062 if not isinstance(run, dict):
4063 continue
4064 ep_url = try_get(
4065 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
4066 if not ep_url:
4067 continue
4068 if not YoutubeIE.suitable(ep_url):
4069 continue
4070 ep_video_id = YoutubeIE._match_id(ep_url)
4071 if video_id == ep_video_id:
4072 continue
895b0931 4073 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4074
8bdd16b4 4075 def _post_thread_continuation_entries(self, post_thread_continuation):
4076 contents = post_thread_continuation.get('contents')
4077 if not isinstance(contents, list):
4078 return
4079 for content in contents:
4080 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4081 if isinstance(renderer, dict):
4082 yield from self._post_thread_entries(renderer)
8bdd16b4 4083 continue
6b0b0a28 4084 renderer = content.get('videoRenderer')
4085 if isinstance(renderer, dict):
4086 yield self._video_entry(renderer)
07aeced6 4087
39ed931e 4088 r''' # unused
4089 def _rich_grid_entries(self, contents):
4090 for content in contents:
4091 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4092 if video_renderer:
4093 entry = self._video_entry(video_renderer)
4094 if entry:
4095 yield entry
4096 '''
52efa4b3 4097
a6213a49 4098 def _extract_entries(self, parent_renderer, continuation_list):
4099 # continuation_list is modified in-place with continuation_list = [continuation_token]
4100 continuation_list[:] = [None]
4101 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4102 for content in contents:
4103 if not isinstance(content, dict):
4104 continue
16aa9ea4 4105 is_renderer = traverse_obj(
4106 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4107 expected_type=dict)
a6213a49 4108 if not is_renderer:
4109 renderer = content.get('richItemRenderer')
4110 if renderer:
4111 for entry in self._rich_entries(renderer):
4112 yield entry
4113 continuation_list[0] = self._extract_continuation(parent_renderer)
4114 continue
4115 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4116 for isr_content in isr_contents:
4117 if not isinstance(isr_content, dict):
8bdd16b4 4118 continue
69184e41 4119
a6213a49 4120 known_renderers = {
4121 'playlistVideoListRenderer': self._playlist_entries,
4122 'gridRenderer': self._grid_entries,
a17526e4 4123 'reelShelfRenderer': self._grid_entries,
4124 'shelfRenderer': self._shelf_entries,
16aa9ea4 4125 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4126 'backstagePostThreadRenderer': self._post_thread_entries,
4127 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4128 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4129 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4130 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4131 }
4132 for key, renderer in isr_content.items():
4133 if key not in known_renderers:
4134 continue
4135 for entry in known_renderers[key](renderer):
4136 if entry:
4137 yield entry
4138 continuation_list[0] = self._extract_continuation(renderer)
4139 break
70d5c17b 4140
4141 if not continuation_list[0]:
a6213a49 4142 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4143
a6213a49 4144 if not continuation_list[0]:
4145 continuation_list[0] = self._extract_continuation(parent_renderer)
4146
4147 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4148 continuation_list = [None]
4149 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4150 tab_content = try_get(tab, lambda x: x['content'], dict)
4151 if not tab_content:
4152 return
3462ffa8 4153 parent_renderer = (
29f7c58a 4154 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4155 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4156 yield from extract_entries(parent_renderer)
3462ffa8 4157 continuation = continuation_list[0]
d069eca7 4158
8bdd16b4 4159 for page_num in itertools.count(1):
4160 if not continuation:
4161 break
99e9e001 4162 headers = self.generate_api_headers(
4163 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4164 response = self._extract_response(
86e5f3ed 4165 item_id=f'{item_id} page {page_num}',
fe93e2c4 4166 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4167 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4168
4169 if not response:
8bdd16b4 4170 break
ac56cf38 4171 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4172 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4173 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4174
69184e41 4175 known_continuation_renderers = {
4176 'playlistVideoListContinuation': self._playlist_entries,
4177 'gridContinuation': self._grid_entries,
4178 'itemSectionContinuation': self._post_thread_continuation_entries,
4179 'sectionListContinuation': extract_entries, # for feeds
4180 }
8bdd16b4 4181 continuation_contents = try_get(
69184e41 4182 response, lambda x: x['continuationContents'], dict) or {}
4183 continuation_renderer = None
4184 for key, value in continuation_contents.items():
4185 if key not in known_continuation_renderers:
3462ffa8 4186 continue
69184e41 4187 continuation_renderer = value
4188 continuation_list = [None]
86e5f3ed 4189 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4190 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4191 break
4192 if continuation_renderer:
4193 continue
c5e8d7af 4194
a1b535bd 4195 known_renderers = {
e4b98809 4196 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4197 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4198 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4199 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4200 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4201 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4202 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4203 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4204 }
cce889b9 4205 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4206 continuation_items = try_get(
cce889b9 4207 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4208 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4209 video_items_renderer = None
4210 for key, value in continuation_item.items():
4211 if key not in known_renderers:
8bdd16b4 4212 continue
a1b535bd 4213 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4214 continuation_list = [None]
86e5f3ed 4215 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4216 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4217 break
4218 if video_items_renderer:
4219 continue
8bdd16b4 4220 break
9558dcec 4221
8bdd16b4 4222 @staticmethod
7c219ea6 4223 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4224 for tab in tabs:
cd684175 4225 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4226 if renderer.get('selected') is True:
4227 return renderer
2b3c2546 4228 else:
7c219ea6 4229 if fatal:
4230 raise ExtractorError('Unable to find selected tab')
b82f815f 4231
61d3665d 4232 def _extract_uploader(self, data):
8bdd16b4 4233 uploader = {}
61d3665d 4234 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4235 owner = try_get(
4236 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4237 if owner:
61d3665d 4238 owner_text = owner.get('text')
4239 uploader['uploader'] = self._search_regex(
4240 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4241 uploader['uploader_id'] = try_get(
4242 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4243 uploader['uploader_url'] = urljoin(
4244 'https://www.youtube.com/',
4245 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4246 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4247
ac56cf38 4248 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4249 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4250 tags = []
b60419c5 4251
8bdd16b4 4252 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4253 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4254 renderer = try_get(
4255 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4256 if renderer:
b60419c5 4257 channel_name = renderer.get('title')
4258 channel_url = renderer.get('channelUrl')
4259 channel_id = renderer.get('externalId')
39ed931e 4260 else:
64c0d954 4261 renderer = try_get(
4262 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4263
8bdd16b4 4264 if renderer:
4265 title = renderer.get('title')
ecc97af3 4266 description = renderer.get('description', '')
b60419c5 4267 playlist_id = channel_id
4268 tags = renderer.get('keywords', '').split()
b60419c5 4269
301d07fc 4270 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4271 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4272 def _get_uncropped(url):
4273 return url_or_none((url or '').split('=')[0] + '=s0')
4274
4275 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4276 if avatar_thumbnails:
4277 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4278 if uncropped_avatar:
4279 avatar_thumbnails.append({
4280 'url': uncropped_avatar,
4281 'id': 'avatar_uncropped',
4282 'preference': 1
4283 })
4284
4285 channel_banners = self._extract_thumbnails(
4286 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4287 for banner in channel_banners:
4288 banner['preference'] = -10
4289
4290 if channel_banners:
4291 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4292 if uncropped_banner:
4293 channel_banners.append({
4294 'url': uncropped_banner,
4295 'id': 'banner_uncropped',
4296 'preference': -5
4297 })
4298
4299 primary_thumbnails = self._extract_thumbnails(
a17526e4 4300 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4301
3462ffa8 4302 if playlist_id is None:
70d5c17b 4303 playlist_id = item_id
f0d785d3 4304
4305 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4306 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4307 if title is None:
f0d785d3 4308 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4309 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4310 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4311
b60419c5 4312 metadata = {
4313 'playlist_id': playlist_id,
4314 'playlist_title': title,
4315 'playlist_description': description,
4316 'uploader': channel_name,
4317 'uploader_id': channel_id,
4318 'uploader_url': channel_url,
301d07fc 4319 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4320 'tags': tags,
f0d785d3 4321 'view_count': self._get_count(playlist_stats, 1),
4322 'availability': self._extract_availability(data),
4323 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4324 'playlist_count': self._get_count(playlist_stats, 0),
4325 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4326 }
4327 if not channel_id:
4328 metadata.update(self._extract_uploader(data))
4329 metadata.update({
4330 'channel': metadata['uploader'],
4331 'channel_id': metadata['uploader_id'],
4332 'channel_url': metadata['uploader_url']})
4333 return self.playlist_result(
d069eca7 4334 self._entries(
ac56cf38 4335 selected_tab, playlist_id, ytcfg,
4336 self._extract_account_syncid(ytcfg, data),
4337 self._extract_visitor_data(data, ytcfg)),
b60419c5 4338 **metadata)
73c4ac2c 4339
6e634cbe 4340 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4341 first_id = last_id = response = None
2be71994 4342 for page_num in itertools.count(1):
cd7c66cf 4343 videos = list(self._playlist_entries(playlist))
4344 if not videos:
4345 return
2be71994 4346 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4347 if start >= len(videos):
4348 return
24146491 4349 yield from videos[start:]
2be71994 4350 first_id = first_id or videos[0]['id']
4351 last_id = videos[-1]['id']
79360d99 4352 watch_endpoint = try_get(
4353 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4354 headers = self.generate_api_headers(
4355 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4356 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4357 query = {
4358 'playlistId': playlist_id,
4359 'videoId': watch_endpoint.get('videoId') or last_id,
4360 'index': watch_endpoint.get('index') or len(videos),
4361 'params': watch_endpoint.get('params') or 'OAE%3D'
4362 }
4363 response = self._extract_response(
4364 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4365 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4366 check_get_keys='contents'
4367 )
cd7c66cf 4368 playlist = try_get(
79360d99 4369 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4370
ac56cf38 4371 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4372 title = playlist.get('title') or try_get(
4373 data, lambda x: x['titleText']['simpleText'], compat_str)
4374 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4375
4376 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4377 playlist_url = urljoin(url, try_get(
4378 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4379 compat_str))
6e634cbe 4380
4381 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4382 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4383 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4384
4385 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4386 return self.url_result(
4387 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4388 video_title=title)
cd7c66cf 4389
8bdd16b4 4390 return self.playlist_result(
6e634cbe 4391 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4392 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4393
47193e02 4394 def _extract_availability(self, data):
4395 """
4396 Gets the availability of a given playlist/tab.
4397 Note: Unless YouTube tells us explicitly, we do not assume it is public
4398 @param data: response
4399 """
4400 is_private = is_unlisted = None
4401 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4402 badge_labels = self._extract_badges(renderer)
4403
4404 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4405 privacy_dropdown_entries = try_get(
4406 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4407 for renderer_dict in privacy_dropdown_entries:
4408 is_selected = try_get(
4409 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4410 if not is_selected:
4411 continue
052e1350 4412 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4413 if label:
4414 badge_labels.add(label.lower())
4415 break
4416
4417 for badge_label in badge_labels:
4418 if badge_label == 'unlisted':
4419 is_unlisted = True
4420 elif badge_label == 'private':
4421 is_private = True
4422 elif badge_label == 'public':
4423 is_unlisted = is_private = False
4424 return self._availability(is_private, False, False, False, is_unlisted)
4425
4426 @staticmethod
4427 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4428 sidebar_renderer = try_get(
4429 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4430 for item in sidebar_renderer:
4431 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4432 if renderer:
4433 return renderer
4434
ac56cf38 4435 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4436 """
4437 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4438 """
5d342002 4439 browse_id = params = None
47193e02 4440 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4441 if not renderer:
4442 return
4443 menu_renderer = try_get(
4444 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4445 for menu_item in menu_renderer:
4446 if not isinstance(menu_item, dict):
358de58c 4447 continue
47193e02 4448 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4449 text = try_get(
4450 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4451 if not text or text.lower() != 'show unavailable videos':
4452 continue
4453 browse_endpoint = try_get(
4454 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4455 browse_id = browse_endpoint.get('browseId')
4456 params = browse_endpoint.get('params')
4457 break
5d342002 4458
11f9be09 4459 headers = self.generate_api_headers(
99e9e001 4460 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4461 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4462 query = {
4463 'params': params or 'wgYCCAA=',
4464 'browseId': browse_id or 'VL%s' % item_id
4465 }
4466 return self._extract_response(
4467 item_id=item_id, headers=headers, query=query,
fe93e2c4 4468 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4469 note='Downloading API JSON with unavailable videos')
358de58c 4470
2762dbb1 4471 @functools.cached_property
a25bca9f 4472 def skip_webpage(self):
4473 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4474
ac56cf38 4475 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4476 retries = self.get_param('extractor_retries', 3)
62bff2c1 4477 count = -1
ac56cf38 4478 webpage = data = last_error = None
14fdfea9 4479 while count < retries:
62bff2c1 4480 count += 1
14fdfea9 4481 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4482 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4483 if last_error:
c705177d 4484 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4485 try:
4486 webpage = self._download_webpage(
4487 url, item_id,
4488 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4489 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4490 except ExtractorError as e:
4491 if isinstance(e.cause, network_exceptions):
4492 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4493 last_error = error_to_compat_str(e.cause or e.msg)
4494 if count < retries:
4495 continue
4496 if fatal:
4497 raise
4498 self.report_warning(error_to_compat_str(e))
14fdfea9 4499 break
ac56cf38 4500 else:
4501 try:
4502 self._extract_and_report_alerts(data)
4503 except ExtractorError as e:
4504 if fatal:
4505 raise
4506 self.report_warning(error_to_compat_str(e))
4507 break
4508
7c219ea6 4509 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4510 break
4511
4512 last_error = 'Incomplete yt initial data received'
4513 if count >= retries:
4514 if fatal:
4515 raise ExtractorError(last_error)
4516 self.report_warning(last_error)
4517 break
4518
cd7c66cf 4519 return webpage, data
4520
a25bca9f 4521 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4522 """Use if failed to extract ytcfg (and data) from initial webpage"""
4523 if not ytcfg and self.is_authenticated:
4524 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4525 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4526 raise ExtractorError(
4527 f'{msg}. If you are not downloading private content, or '
4528 'your cookies are only for the first account and channel,'
4529 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4530 expected=True)
4531 self.report_warning(msg, only_once=True)
4532
ac56cf38 4533 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4534 data = None
a25bca9f 4535 if not self.skip_webpage:
ac56cf38 4536 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4537 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4538 # Reject webpage data if redirected to home page without explicitly requesting
4539 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4540 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4541 if (url != 'https://www.youtube.com/feed/recommended'
4542 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4543 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4544 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4545 if fatal:
4546 raise ExtractorError(msg, expected=True)
4547 self.report_warning(msg, only_once=True)
ac56cf38 4548 if not data:
a25bca9f 4549 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4550 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4551 return data, ytcfg
4552
4553 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4554 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4555 resolve_response = self._extract_response(
4556 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4557 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4558 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4559 for ep_key, ep in endpoints.items():
4560 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4561 if params:
4562 return self._extract_response(
4563 item_id=item_id, query=params, ep=ep, headers=headers,
4564 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4565 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4566 err_note = 'Failed to resolve url (does the playlist exist?)'
4567 if fatal:
4568 raise ExtractorError(err_note, expected=True)
4569 self.report_warning(err_note, item_id)
4570
a6213a49 4571 _SEARCH_PARAMS = None
4572
af5c1c55 4573 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4574 data = {'query': query}
4575 if params is NO_DEFAULT:
4576 params = self._SEARCH_PARAMS
4577 if params:
4578 data['params'] = params
16aa9ea4 4579
4580 content_keys = (
4581 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4582 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4583 # ytmusic search
4584 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4585 ('continuationContents', ),
4586 )
a25bca9f 4587 display_id = f'query "{query}"'
86e5f3ed 4588 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4589 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4590 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4591
a61fd4cf 4592 continuation_list = [None]
a25bca9f 4593 search = None
a6213a49 4594 for page_num in itertools.count(1):
a61fd4cf 4595 data.update(continuation_list[0] or {})
a25bca9f 4596 headers = self.generate_api_headers(
4597 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4598 search = self._extract_response(
a25bca9f 4599 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4600 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4601 slr_contents = traverse_obj(search, *content_keys)
4602 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4603 if not continuation_list[0]:
a6213a49 4604 break
4605
4606
4607class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4608 IE_DESC = 'YouTube Tabs'
4609 _VALID_URL = r'''(?x:
4610 https?://
4611 (?:\w+\.)?
4612 (?:
4613 youtube(?:kids)?\.com|
4614 %(invidious)s
4615 )/
4616 (?:
4617 (?P<channel_type>channel|c|user|browse)/|
4618 (?P<not_channel>
4619 feed/|hashtag/|
4620 (?:playlist|watch)\?.*?\blist=
4621 )|
4622 (?!(?:%(reserved_names)s)\b) # Direct URLs
4623 )
4624 (?P<id>[^/?\#&]+)
4625 )''' % {
4626 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4627 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4628 }
4629 IE_NAME = 'youtube:tab'
4630
4631 _TESTS = [{
4632 'note': 'playlists, multipage',
4633 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4634 'playlist_mincount': 94,
4635 'info_dict': {
4636 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4637 'title': 'Igor Kleiner - Playlists',
a6213a49 4638 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4639 'uploader': 'Igor Kleiner',
a6213a49 4640 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4641 'channel': 'Igor Kleiner',
4642 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4643 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4644 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4645 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4646 'channel_follower_count': int
a6213a49 4647 },
4648 }, {
4649 'note': 'playlists, multipage, different order',
4650 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4651 'playlist_mincount': 94,
4652 'info_dict': {
4653 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4654 'title': 'Igor Kleiner - Playlists',
a6213a49 4655 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4656 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4657 'uploader': 'Igor Kleiner',
4658 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4659 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4660 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4661 'channel': 'Igor Kleiner',
4662 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4663 'channel_follower_count': int
a6213a49 4664 },
4665 }, {
4666 'note': 'playlists, series',
4667 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4668 'playlist_mincount': 5,
4669 'info_dict': {
4670 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4671 'title': '3Blue1Brown - Playlists',
4672 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4673 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4674 'uploader': '3Blue1Brown',
976ae3ea 4675 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4676 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4677 'channel': '3Blue1Brown',
4678 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4679 'tags': ['Mathematics'],
6c73052c 4680 'channel_follower_count': int
a6213a49 4681 },
4682 }, {
4683 'note': 'playlists, singlepage',
4684 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4685 'playlist_mincount': 4,
4686 'info_dict': {
4687 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4688 'title': 'ThirstForScience - Playlists',
4689 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4690 'uploader': 'ThirstForScience',
4691 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4692 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4693 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4694 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4695 'tags': 'count:13',
4696 'channel': 'ThirstForScience',
6c73052c 4697 'channel_follower_count': int
a6213a49 4698 }
4699 }, {
4700 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4701 'only_matching': True,
4702 }, {
4703 'note': 'basic, single video playlist',
4704 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4705 'info_dict': {
4706 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4707 'uploader': 'Sergey M.',
4708 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4709 'title': 'youtube-dl public playlist',
976ae3ea 4710 'description': '',
4711 'tags': [],
4712 'view_count': int,
4713 'modified_date': '20201130',
4714 'channel': 'Sergey M.',
4715 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4716 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4717 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4718 },
4719 'playlist_count': 1,
4720 }, {
4721 'note': 'empty playlist',
4722 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4723 'info_dict': {
4724 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4725 'uploader': 'Sergey M.',
4726 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4727 'title': 'youtube-dl empty playlist',
976ae3ea 4728 'tags': [],
4729 'channel': 'Sergey M.',
4730 'description': '',
4731 'modified_date': '20160902',
4732 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4733 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4734 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4735 },
4736 'playlist_count': 0,
4737 }, {
4738 'note': 'Home tab',
4739 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4740 'info_dict': {
4741 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4742 'title': 'lex will - Home',
4743 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4744 'uploader': 'lex will',
4745 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4746 'channel': 'lex will',
4747 'tags': ['bible', 'history', 'prophesy'],
4748 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4749 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4750 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4751 'channel_follower_count': int
a6213a49 4752 },
4753 'playlist_mincount': 2,
4754 }, {
4755 'note': 'Videos tab',
4756 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4757 'info_dict': {
4758 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4759 'title': 'lex will - Videos',
4760 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4761 'uploader': 'lex will',
4762 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4763 'tags': ['bible', 'history', 'prophesy'],
4764 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4765 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4766 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4767 'channel': 'lex will',
6c73052c 4768 'channel_follower_count': int
a6213a49 4769 },
4770 'playlist_mincount': 975,
4771 }, {
4772 'note': 'Videos tab, sorted by popular',
4773 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4774 'info_dict': {
4775 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4776 'title': 'lex will - Videos',
4777 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4778 'uploader': 'lex will',
4779 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4780 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4781 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4782 'channel': 'lex will',
4783 'tags': ['bible', 'history', 'prophesy'],
4784 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4785 'channel_follower_count': int
a6213a49 4786 },
4787 'playlist_mincount': 199,
4788 }, {
4789 'note': 'Playlists tab',
4790 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4791 'info_dict': {
4792 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4793 'title': 'lex will - Playlists',
4794 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4795 'uploader': 'lex will',
4796 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4797 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4798 'channel': 'lex will',
4799 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4801 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4802 'channel_follower_count': int
a6213a49 4803 },
4804 'playlist_mincount': 17,
4805 }, {
4806 'note': 'Community tab',
4807 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4808 'info_dict': {
4809 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4810 'title': 'lex will - Community',
4811 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4812 'uploader': 'lex will',
4813 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4814 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4815 'channel': 'lex will',
4816 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4817 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4818 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4819 'channel_follower_count': int
a6213a49 4820 },
4821 'playlist_mincount': 18,
4822 }, {
4823 'note': 'Channels tab',
4824 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4825 'info_dict': {
4826 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4827 'title': 'lex will - Channels',
4828 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4829 'uploader': 'lex will',
4830 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4831 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4832 'channel': 'lex will',
4833 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4835 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4836 'channel_follower_count': int
a6213a49 4837 },
4838 'playlist_mincount': 12,
4839 }, {
4840 'note': 'Search tab',
4841 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4842 'playlist_mincount': 40,
4843 'info_dict': {
4844 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4845 'title': '3Blue1Brown - Search - linear algebra',
4846 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4847 'uploader': '3Blue1Brown',
4848 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4849 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4850 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4851 'tags': ['Mathematics'],
4852 'channel': '3Blue1Brown',
4853 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4854 'channel_follower_count': int
a6213a49 4855 },
4856 }, {
4857 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4858 'only_matching': True,
4859 }, {
4860 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4861 'only_matching': True,
4862 }, {
4863 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4864 'only_matching': True,
4865 }, {
4866 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4867 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4868 'info_dict': {
4869 'title': '29C3: Not my department',
4870 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4871 'uploader': 'Christiaan008',
4872 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4873 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4874 'tags': [],
4875 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4876 'view_count': int,
4877 'modified_date': '20150605',
4878 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4879 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4880 'channel': 'Christiaan008',
a6213a49 4881 },
4882 'playlist_count': 96,
4883 }, {
4884 'note': 'Large playlist',
4885 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4886 'info_dict': {
4887 'title': 'Uploads from Cauchemar',
4888 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4889 'uploader': 'Cauchemar',
4890 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4891 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4892 'tags': [],
4893 'modified_date': r're:\d{8}',
4894 'channel': 'Cauchemar',
4895 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4896 'view_count': int,
4897 'description': '',
4898 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4899 },
4900 'playlist_mincount': 1123,
976ae3ea 4901 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4902 }, {
4903 'note': 'even larger playlist, 8832 videos',
4904 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4905 'only_matching': True,
4906 }, {
4907 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4908 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4909 'info_dict': {
4910 'title': 'Uploads from Interstellar Movie',
4911 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4912 'uploader': 'Interstellar Movie',
4913 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4914 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4915 'tags': [],
4916 'view_count': int,
4917 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4918 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4919 'channel': 'Interstellar Movie',
4920 'description': '',
4921 'modified_date': r're:\d{8}',
a6213a49 4922 },
4923 'playlist_mincount': 21,
4924 }, {
4925 'note': 'Playlist with "show unavailable videos" button',
4926 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4927 'info_dict': {
4928 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4929 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4930 'uploader': 'Phim Siêu Nhân Nhật Bản',
4931 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4932 'view_count': int,
4933 'channel': 'Phim Siêu Nhân Nhật Bản',
4934 'tags': [],
4935 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4936 'description': '',
4937 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4938 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4939 'modified_date': r're:\d{8}',
a6213a49 4940 },
4941 'playlist_mincount': 200,
976ae3ea 4942 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4943 }, {
4944 'note': 'Playlist with unavailable videos in page 7',
4945 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4946 'info_dict': {
4947 'title': 'Uploads from BlankTV',
4948 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4949 'uploader': 'BlankTV',
4950 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4951 'channel': 'BlankTV',
4952 'channel_url': 'https://www.youtube.com/c/blanktv',
4953 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4954 'view_count': int,
4955 'tags': [],
4956 'uploader_url': 'https://www.youtube.com/c/blanktv',
4957 'modified_date': r're:\d{8}',
4958 'description': '',
a6213a49 4959 },
4960 'playlist_mincount': 1000,
976ae3ea 4961 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4962 }, {
4963 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4964 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4965 'info_dict': {
4966 'title': 'Data Analysis with Dr Mike Pound',
4967 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4968 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4969 'uploader': 'Computerphile',
4970 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4971 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4972 'tags': [],
4973 'view_count': int,
4974 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4975 'channel_url': 'https://www.youtube.com/user/Computerphile',
4976 'channel': 'Computerphile',
a6213a49 4977 },
4978 'playlist_mincount': 11,
4979 }, {
4980 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4981 'only_matching': True,
4982 }, {
4983 'note': 'Playlist URL that does not actually serve a playlist',
4984 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4985 'info_dict': {
4986 'id': 'FqZTN594JQw',
4987 'ext': 'webm',
4988 'title': "Smiley's People 01 detective, Adventure Series, Action",
4989 'uploader': 'STREEM',
4990 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4991 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4992 'upload_date': '20150526',
4993 'license': 'Standard YouTube License',
4994 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4995 'categories': ['People & Blogs'],
4996 'tags': list,
4997 'view_count': int,
4998 'like_count': int,
a6213a49 4999 },
5000 'params': {
5001 'skip_download': True,
5002 },
5003 'skip': 'This video is not available.',
5004 'add_ie': [YoutubeIE.ie_key()],
5005 }, {
5006 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5007 'only_matching': True,
5008 }, {
5009 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5010 'only_matching': True,
5011 }, {
5012 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5013 'info_dict': {
6c73052c 5014 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 5015 'ext': 'mp4',
976ae3ea 5016 'title': str,
a6213a49 5017 'uploader': 'Sky News',
5018 'uploader_id': 'skynews',
5019 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5020 'upload_date': r're:\d{8}',
976ae3ea 5021 'description': str,
a6213a49 5022 'categories': ['News & Politics'],
5023 'tags': list,
5024 'like_count': int,
6c73052c 5025 'release_timestamp': 1642502819,
976ae3ea 5026 'channel': 'Sky News',
5027 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5028 'age_limit': 0,
5029 'view_count': int,
6c73052c 5030 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5031 'playable_in_embed': True,
6c73052c 5032 'release_date': '20220118',
976ae3ea 5033 'availability': 'public',
5034 'live_status': 'is_live',
5035 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5036 'channel_follower_count': int
a6213a49 5037 },
5038 'params': {
5039 'skip_download': True,
5040 },
976ae3ea 5041 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5042 }, {
5043 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5044 'info_dict': {
5045 'id': 'a48o2S1cPoo',
5046 'ext': 'mp4',
5047 'title': 'The Young Turks - Live Main Show',
5048 'uploader': 'The Young Turks',
5049 'uploader_id': 'TheYoungTurks',
5050 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5051 'upload_date': '20150715',
5052 'license': 'Standard YouTube License',
5053 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5054 'categories': ['News & Politics'],
5055 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5056 'like_count': int,
a6213a49 5057 },
5058 'params': {
5059 'skip_download': True,
5060 },
5061 'only_matching': True,
5062 }, {
5063 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5064 'only_matching': True,
5065 }, {
5066 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5067 'only_matching': True,
5068 }, {
5069 'note': 'A channel that is not live. Should raise error',
5070 'url': 'https://www.youtube.com/user/numberphile/live',
5071 'only_matching': True,
5072 }, {
5073 'url': 'https://www.youtube.com/feed/trending',
5074 'only_matching': True,
5075 }, {
5076 'url': 'https://www.youtube.com/feed/library',
5077 'only_matching': True,
5078 }, {
5079 'url': 'https://www.youtube.com/feed/history',
5080 'only_matching': True,
5081 }, {
5082 'url': 'https://www.youtube.com/feed/subscriptions',
5083 'only_matching': True,
5084 }, {
5085 'url': 'https://www.youtube.com/feed/watch_later',
5086 'only_matching': True,
5087 }, {
5088 'note': 'Recommended - redirects to home page.',
5089 'url': 'https://www.youtube.com/feed/recommended',
5090 'only_matching': True,
5091 }, {
5092 'note': 'inline playlist with not always working continuations',
5093 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5094 'only_matching': True,
5095 }, {
5096 'url': 'https://www.youtube.com/course',
5097 'only_matching': True,
5098 }, {
5099 'url': 'https://www.youtube.com/zsecurity',
5100 'only_matching': True,
5101 }, {
5102 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5103 'only_matching': True,
5104 }, {
5105 'url': 'https://www.youtube.com/TheYoungTurks/live',
5106 'only_matching': True,
5107 }, {
5108 'url': 'https://www.youtube.com/hashtag/cctv9',
5109 'info_dict': {
5110 'id': 'cctv9',
5111 'title': '#cctv9',
976ae3ea 5112 'tags': [],
a6213a49 5113 },
5114 'playlist_mincount': 350,
5115 }, {
5116 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5117 'only_matching': True,
5118 }, {
5119 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5120 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5121 'only_matching': True
5122 }, {
5123 'note': '/browse/ should redirect to /channel/',
5124 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5125 'only_matching': True
5126 }, {
5127 'note': 'VLPL, should redirect to playlist?list=PL...',
5128 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5129 'info_dict': {
5130 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5131 'uploader': 'NoCopyrightSounds',
5132 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5133 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5134 'title': 'NCS Releases',
976ae3ea 5135 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5136 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5137 'modified_date': r're:\d{8}',
5138 'view_count': int,
5139 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5140 'tags': [],
5141 'channel': 'NoCopyrightSounds',
a6213a49 5142 },
5143 'playlist_mincount': 166,
976ae3ea 5144 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5145 }, {
5146 'note': 'Topic, should redirect to playlist?list=UU...',
5147 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5148 'info_dict': {
5149 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5150 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5151 'title': 'Uploads from Royalty Free Music - Topic',
5152 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5153 'tags': [],
5154 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5155 'channel': 'Royalty Free Music - Topic',
5156 'view_count': int,
5157 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5158 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5159 'modified_date': r're:\d{8}',
5160 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5161 'description': '',
a6213a49 5162 },
5163 'expected_warnings': [
a6213a49 5164 'The URL does not have a videos tab',
976ae3ea 5165 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5166 ],
5167 'playlist_mincount': 101,
5168 }, {
5169 'note': 'Topic without a UU playlist',
5170 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5171 'info_dict': {
5172 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5173 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5174 'tags': [],
a6213a49 5175 },
5176 'expected_warnings': [
976ae3ea 5177 'the playlist redirect gave error',
a6213a49 5178 ],
5179 'playlist_mincount': 9,
5180 }, {
5181 'note': 'Youtube music Album',
5182 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5183 'info_dict': {
5184 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5185 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5186 'tags': [],
5187 'view_count': int,
5188 'description': '',
5189 'availability': 'unlisted',
5190 'modified_date': r're:\d{8}',
a6213a49 5191 },
5192 'playlist_count': 50,
5193 }, {
5194 'note': 'unlisted single video playlist',
5195 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5196 'info_dict': {
5197 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5198 'uploader': 'colethedj',
5199 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5200 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5201 'availability': 'unlisted',
5202 'tags': [],
5203 'modified_date': '20211208',
5204 'channel': 'colethedj',
5205 'view_count': int,
5206 'description': '',
5207 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5208 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5209 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5210 },
5211 'playlist_count': 1,
5212 }, {
5213 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5214 'url': 'https://www.youtube.com/feed/recommended',
5215 'info_dict': {
5216 'id': 'recommended',
5217 'title': 'recommended',
6c73052c 5218 'tags': [],
a6213a49 5219 },
5220 'playlist_mincount': 50,
5221 'params': {
5222 'skip_download': True,
5223 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5224 },
5225 }, {
5226 'note': 'API Fallback: /videos tab, sorted by oldest first',
5227 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5228 'info_dict': {
5229 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5230 'title': 'Cody\'sLab - Videos',
5231 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5232 'uploader': 'Cody\'sLab',
5233 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5234 'channel': 'Cody\'sLab',
5235 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5236 'tags': [],
5237 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5238 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5239 'channel_follower_count': int
a6213a49 5240 },
5241 'playlist_mincount': 650,
5242 'params': {
5243 'skip_download': True,
5244 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5245 },
5246 }, {
5247 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5248 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5249 'info_dict': {
5250 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5251 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5252 'title': 'Uploads from Royalty Free Music - Topic',
5253 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5254 'modified_date': r're:\d{8}',
5255 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5256 'description': '',
5257 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5258 'tags': [],
5259 'channel': 'Royalty Free Music - Topic',
5260 'view_count': int,
5261 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5262 },
5263 'expected_warnings': [
976ae3ea 5264 'does not have a videos tab',
5265 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5266 ],
5267 'playlist_mincount': 101,
5268 'params': {
5269 'skip_download': True,
5270 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5271 },
7c219ea6 5272 }, {
5273 'note': 'non-standard redirect to regional channel',
5274 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5275 'only_matching': True
61d3665d 5276 }, {
5277 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5278 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5279 'info_dict': {
5280 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5281 'modified_date': '20220407',
5282 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5283 'tags': [],
5284 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5285 'uploader': 'pukkandan',
5286 'availability': 'unlisted',
5287 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5288 'channel': 'pukkandan',
5289 'description': 'Test for collaborative playlist',
5290 'title': 'yt-dlp test - collaborative playlist',
5291 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5292 },
5293 'playlist_mincount': 2
a6213a49 5294 }]
5295
5296 @classmethod
5297 def suitable(cls, url):
86e5f3ed 5298 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5299
64f36541 5300 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5301
182bda88 5302 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5303 def _real_extract(self, url, smuggled_data):
cd7c66cf 5304 item_id = self._match_id(url)
5305 url = compat_urlparse.urlunparse(
5306 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5307 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5308
fe03a6cd 5309 def get_mobj(url):
37e57a9f 5310 mobj = self._URL_RE.match(url).groupdict()
07cce701 5311 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5312 return mobj
5313
37e57a9f 5314 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5315 # Youtube returns incomplete data if tabname is not lower case
5316 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5317 if is_channel:
5318 if smuggled_data.get('is_music_url'):
37e57a9f 5319 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5320 item_id = item_id[2:]
37e57a9f 5321 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5322 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5323 mdata = self._extract_tab_endpoint(
37e57a9f 5324 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5325 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5326 get_all=False, expected_type=compat_str)
ac56cf38 5327 if not murl:
37e57a9f 5328 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5329 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5330 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5331 pre = f'https://www.youtube.com/channel/{item_id}'
5332
64f36541 5333 original_tab_name = tab
fe03a6cd 5334 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5335 # Home URLs should redirect to /videos/
37e57a9f 5336 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5337 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5338 tab = '/videos'
5339
5340 url = ''.join((pre, tab, post))
5341 mobj = get_mobj(url)
cd7c66cf 5342
5343 # Handle both video/playlist URLs
201c1459 5344 qs = parse_qs(url)
86e5f3ed 5345 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5346
fe03a6cd 5347 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5348 if not playlist_id:
fe03a6cd 5349 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5350 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5351 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5352 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5353 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5354 mobj = get_mobj(url)
cd7c66cf 5355
5356 if video_id and playlist_id:
a06916d9 5357 if self.get_param('noplaylist'):
37e57a9f 5358 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5359 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5360 ie=YoutubeIE.ie_key(), video_id=video_id)
5361 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5362
ac56cf38 5363 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5364
7c219ea6 5365 # YouTube may provide a non-standard redirect to the regional channel
5366 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5367 redirect_url = traverse_obj(
5368 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5369 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5370 redirect_url = ''.join((
5371 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5372 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5373 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5374
37e57a9f 5375 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5376 if tabs:
5377 selected_tab = self._extract_selected_tab(tabs)
64f36541 5378 selected_tab_name = selected_tab.get('title', '').lower()
5379 if selected_tab_name == 'home':
5380 selected_tab_name = 'featured'
5381 requested_tab_name = mobj['tab'][1:]
09f1580e 5382 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5383 if requested_tab_name == 'live':
09f1580e 5384 # Live tab should have redirected to the video
5385 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5386 if requested_tab_name not in ('', selected_tab_name):
5387 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5388 if not original_tab_name:
5389 if item_id[:2] == 'UC':
5390 # Topic channels don't have /videos. Use the equivalent playlist instead
5391 pl_id = f'UU{item_id[2:]}'
5392 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5393 try:
5394 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5395 except ExtractorError:
5396 redirect_warning += ' and the playlist redirect gave error'
5397 else:
5398 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5399 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5400 if selected_tab_name and selected_tab_name != requested_tab_name:
5401 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5402 else:
5403 raise ExtractorError(redirect_warning, expected=True)
18db7548 5404
37e57a9f 5405 if redirect_warning:
64f36541 5406 self.to_screen(redirect_warning)
37e57a9f 5407 self.write_debug(f'Final URL: {url}')
18db7548 5408
358de58c 5409 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5410 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5411 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5412 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5413 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5414 if tabs:
ac56cf38 5415 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5416
37e57a9f 5417 playlist = traverse_obj(
5418 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5419 if playlist:
ac56cf38 5420 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5421
37e57a9f 5422 video_id = traverse_obj(
5423 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5424 if video_id:
09f1580e 5425 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5426 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5427 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5428 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5429
8bdd16b4 5430 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5431
c5e8d7af 5432
8bdd16b4 5433class YoutubePlaylistIE(InfoExtractor):
96565c7e 5434 IE_DESC = 'YouTube playlists'
8bdd16b4 5435 _VALID_URL = r'''(?x)(?:
5436 (?:https?://)?
5437 (?:\w+\.)?
5438 (?:
5439 (?:
5440 youtube(?:kids)?\.com|
d9190e44 5441 %(invidious)s
8bdd16b4 5442 )
5443 /.*?\?.*?\blist=
5444 )?
5445 (?P<id>%(playlist_id)s)
d9190e44
RH
5446 )''' % {
5447 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5448 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5449 }
8bdd16b4 5450 IE_NAME = 'youtube:playlist'
cdc628a4 5451 _TESTS = [{
8bdd16b4 5452 'note': 'issue #673',
5453 'url': 'PLBB231211A4F62143',
cdc628a4 5454 'info_dict': {
8bdd16b4 5455 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5456 'id': 'PLBB231211A4F62143',
976ae3ea 5457 'uploader': 'Wickman',
8bdd16b4 5458 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5459 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5460 'view_count': int,
5461 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5462 'modified_date': r're:\d{8}',
5463 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5464 'channel': 'Wickman',
5465 'tags': [],
5466 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5467 },
5468 'playlist_mincount': 29,
5469 }, {
5470 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5471 'info_dict': {
5472 'title': 'YDL_safe_search',
5473 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5474 },
5475 'playlist_count': 2,
5476 'skip': 'This playlist is private',
9558dcec 5477 }, {
8bdd16b4 5478 'note': 'embedded',
5479 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5480 'playlist_count': 4,
9558dcec 5481 'info_dict': {
8bdd16b4 5482 'title': 'JODA15',
5483 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5484 'uploader': 'milan',
5485 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5486 'description': '',
5487 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5488 'tags': [],
5489 'modified_date': '20140919',
5490 'view_count': int,
5491 'channel': 'milan',
5492 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5493 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5494 },
5495 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5496 }, {
8bdd16b4 5497 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5498 'playlist_mincount': 654,
8bdd16b4 5499 'info_dict': {
5500 'title': '2018 Chinese New Singles (11/6 updated)',
5501 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5502 'uploader': 'LBK',
5503 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5504 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5505 'channel': 'LBK',
5506 'view_count': int,
5507 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5508 'tags': [],
5509 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5510 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5511 'modified_date': r're:\d{8}',
5512 },
5513 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5514 }, {
29f7c58a 5515 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5516 'only_matching': True,
5517 }, {
5518 # music album playlist
5519 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5520 'only_matching': True,
5521 }]
5522
5523 @classmethod
5524 def suitable(cls, url):
201c1459 5525 if YoutubeTabIE.suitable(url):
5526 return False
49a57e70 5527 from ..utils import parse_qs
201c1459 5528 qs = parse_qs(url)
5529 if qs.get('v', [None])[0]:
5530 return False
86e5f3ed 5531 return super().suitable(url)
29f7c58a 5532
5533 def _real_extract(self, url):
5534 playlist_id = self._match_id(url)
46953e7e 5535 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5536 url = update_url_query(
5537 'https://www.youtube.com/playlist',
5538 parse_qs(url) or {'list': playlist_id})
5539 if is_music_url:
5540 url = smuggle_url(url, {'is_music_url': True})
5541 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5542
5543
5544class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5545 IE_DESC = 'youtu.be'
29f7c58a 5546 _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}
5547 _TESTS = [{
8bdd16b4 5548 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5549 'info_dict': {
5550 'id': 'yeWKywCrFtk',
5551 'ext': 'mp4',
5552 'title': 'Small Scale Baler and Braiding Rugs',
5553 'uploader': 'Backus-Page House Museum',
5554 'uploader_id': 'backuspagemuseum',
5555 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5556 'upload_date': '20161008',
5557 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5558 'categories': ['Nonprofits & Activism'],
5559 'tags': list,
5560 'like_count': int,
976ae3ea 5561 'age_limit': 0,
5562 'playable_in_embed': True,
5563 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5564 'channel': 'Backus-Page House Museum',
5565 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5566 'live_status': 'not_live',
5567 'view_count': int,
5568 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5569 'availability': 'public',
5570 'duration': 59,
8bdd16b4 5571 },
5572 'params': {
5573 'noplaylist': True,
5574 'skip_download': True,
5575 },
39e7107d 5576 }, {
8bdd16b4 5577 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5578 'only_matching': True,
cdc628a4
PH
5579 }]
5580
8bdd16b4 5581 def _real_extract(self, url):
5ad28e7f 5582 mobj = self._match_valid_url(url)
29f7c58a 5583 video_id = mobj.group('id')
5584 playlist_id = mobj.group('playlist_id')
8bdd16b4 5585 return self.url_result(
29f7c58a 5586 update_url_query('https://www.youtube.com/watch', {
5587 'v': video_id,
5588 'list': playlist_id,
5589 'feature': 'youtu.be',
5590 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5591
5592
b6ce9bb0 5593class YoutubeLivestreamEmbedIE(InfoExtractor):
5594 IE_DESC = 'YouTube livestream embeds'
5595 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5596 _TESTS = [{
5597 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5598 'only_matching': True,
5599 }]
5600
5601 def _real_extract(self, url):
5602 channel_id = self._match_id(url)
5603 return self.url_result(
5604 f'https://www.youtube.com/channel/{channel_id}/live',
5605 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5606
5607
8bdd16b4 5608class YoutubeYtUserIE(InfoExtractor):
96565c7e 5609 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5610 IE_NAME = 'youtube:user'
8bdd16b4 5611 _VALID_URL = r'ytuser:(?P<id>.+)'
5612 _TESTS = [{
5613 'url': 'ytuser:phihag',
5614 'only_matching': True,
5615 }]
5616
5617 def _real_extract(self, url):
5618 user_id = self._match_id(url)
5619 return self.url_result(
c586f9e8 5620 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5621 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5622
b05654f0 5623
3d3dddc9 5624class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5625 IE_NAME = 'youtube:favorites'
96565c7e 5626 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5627 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5628 _LOGIN_REQUIRED = True
5629 _TESTS = [{
5630 'url': ':ytfav',
5631 'only_matching': True,
5632 }, {
5633 'url': ':ytfavorites',
5634 'only_matching': True,
5635 }]
5636
5637 def _real_extract(self, url):
5638 return self.url_result(
5639 'https://www.youtube.com/playlist?list=LL',
5640 ie=YoutubeTabIE.ie_key())
5641
5642
ca5300c7 5643class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5644 IE_NAME = 'youtube:notif'
5645 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5646 _VALID_URL = r':ytnotif(?:ication)?s?'
5647 _LOGIN_REQUIRED = True
5648 _TESTS = [{
5649 'url': ':ytnotif',
5650 'only_matching': True,
5651 }, {
5652 'url': ':ytnotifications',
5653 'only_matching': True,
5654 }]
5655
5656 def _extract_notification_menu(self, response, continuation_list):
5657 notification_list = traverse_obj(
5658 response,
5659 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5660 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5661 expected_type=list) or []
5662 continuation_list[0] = None
5663 for item in notification_list:
5664 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5665 if entry:
5666 yield entry
5667 continuation = item.get('continuationItemRenderer')
5668 if continuation:
5669 continuation_list[0] = continuation
5670
5671 def _extract_notification_renderer(self, notification):
5672 video_id = traverse_obj(
5673 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5674 url = f'https://www.youtube.com/watch?v={video_id}'
5675 channel_id = None
5676 if not video_id:
5677 browse_ep = traverse_obj(
5678 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5679 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5680 post_id = self._search_regex(
5681 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5682 'post id', default=None)
5683 if not channel_id or not post_id:
5684 return
5685 # The direct /post url redirects to this in the browser
5686 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5687
5688 channel = traverse_obj(
5689 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5690 expected_type=str)
c7a7baaa 5691 notification_title = self._get_text(notification, 'shortMessage')
5692 if notification_title:
5693 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5694 # TODO: handle recommended videos
ca5300c7 5695 title = self._search_regex(
c7a7baaa 5696 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5697 'video title', default=None)
ca5300c7 5698 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5699 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5700 else None)
5701 return {
5702 '_type': 'url',
5703 'url': url,
5704 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5705 'video_id': video_id,
5706 'title': title,
5707 'channel_id': channel_id,
5708 'channel': channel,
5709 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5710 'upload_date': upload_date,
5711 }
5712
5713 def _notification_menu_entries(self, ytcfg):
5714 continuation_list = [None]
5715 response = None
5716 for page in itertools.count(1):
5717 ctoken = traverse_obj(
5718 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5719 response = self._extract_response(
5720 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5721 ep='notification/get_notification_menu', check_get_keys='actions',
5722 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5723 yield from self._extract_notification_menu(response, continuation_list)
5724 if not continuation_list[0]:
5725 break
5726
5727 def _real_extract(self, url):
5728 display_id = 'notifications'
5729 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5730 self._report_playlist_authcheck(ytcfg)
5731 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5732
5733
a6213a49 5734class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5735 IE_DESC = 'YouTube search'
78caa52a 5736 IE_NAME = 'youtube:search'
b05654f0 5737 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5738 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5739 _TESTS = [{
5740 'url': 'ytsearch5:youtube-dl test video',
5741 'playlist_count': 5,
5742 'info_dict': {
5743 'id': 'youtube-dl test video',
5744 'title': 'youtube-dl test video',
5745 }
5746 }]
b05654f0 5747
a61fd4cf 5748
5f7cb91a 5749class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5750 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5751 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5752 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5753 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5754 _TESTS = [{
5755 'url': 'ytsearchdate5:youtube-dl test video',
5756 'playlist_count': 5,
5757 'info_dict': {
5758 'id': 'youtube-dl test video',
5759 'title': 'youtube-dl test video',
5760 }
5761 }]
75dff0ee 5762
c9ae7b95 5763
a6213a49 5764class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5765 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5766 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5767 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5768 _TESTS = [{
5769 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5770 'playlist_mincount': 5,
5771 'info_dict': {
11f9be09 5772 'id': 'youtube-dl test video',
3462ffa8 5773 'title': 'youtube-dl test video',
5774 }
a61fd4cf 5775 }, {
5776 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5777 'playlist_mincount': 5,
5778 'info_dict': {
5779 'id': 'python',
5780 'title': 'python',
5781 }
ad210f4f 5782 }, {
5783 'url': 'https://www.youtube.com/results?search_query=%23cats',
5784 'playlist_mincount': 1,
5785 'info_dict': {
5786 'id': '#cats',
5787 'title': '#cats',
5788 'entries': [{
5789 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5790 'title': '#cats',
5791 }],
5792 },
3462ffa8 5793 }, {
5794 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5795 'only_matching': True,
5796 }]
5797
5798 def _real_extract(self, url):
4dfbf869 5799 qs = parse_qs(url)
386e1dd9 5800 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5801 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5802
5803
16aa9ea4 5804class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5805 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5806 IE_NAME = 'youtube:music:search_url'
5807 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5808 _TESTS = [{
5809 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5810 'playlist_count': 16,
5811 'info_dict': {
5812 'id': 'royalty free music',
5813 'title': 'royalty free music',
5814 }
5815 }, {
5816 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5817 'playlist_mincount': 30,
5818 'info_dict': {
5819 'id': 'royalty free music - songs',
5820 'title': 'royalty free music - songs',
5821 },
5822 'params': {'extract_flat': 'in_playlist'}
5823 }, {
5824 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5825 'playlist_mincount': 30,
5826 'info_dict': {
5827 'id': 'royalty free music - community playlists',
5828 'title': 'royalty free music - community playlists',
5829 },
5830 'params': {'extract_flat': 'in_playlist'}
5831 }]
5832
5833 _SECTIONS = {
5834 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5835 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5836 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5837 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5838 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5839 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5840 }
5841
5842 def _real_extract(self, url):
5843 qs = parse_qs(url)
5844 query = (qs.get('search_query') or qs.get('q'))[0]
5845 params = qs.get('sp', (None,))[0]
5846 if params:
5847 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5848 else:
5849 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5850 params = self._SECTIONS.get(section)
5851 if not params:
5852 section = None
5853 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5854 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5855
5856
182bda88 5857class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5858 """
25f14e9f 5859 Base class for feed extractors
82d02080 5860 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5861 """
b2e8bc1b 5862 _LOGIN_REQUIRED = True
82d02080 5863 _FEED_NAME = 'feeds'
a25bca9f 5864
5865 def _real_initialize(self):
5866 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5867
82d02080 5868 @classproperty
d7ae0639 5869 def IE_NAME(self):
82d02080 5870 return f'youtube:{self._FEED_NAME}'
04cc9617 5871
3853309f 5872 def _real_extract(self, url):
3d3dddc9 5873 return self.url_result(
182bda88 5874 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5875
5876
ef2f3c7f 5877class YoutubeWatchLaterIE(InfoExtractor):
5878 IE_NAME = 'youtube:watchlater'
96565c7e 5879 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5880 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5881 _TESTS = [{
8bdd16b4 5882 'url': ':ytwatchlater',
bc7a9cd8
S
5883 'only_matching': True,
5884 }]
25f14e9f
S
5885
5886 def _real_extract(self, url):
ef2f3c7f 5887 return self.url_result(
5888 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5889
5890
25f14e9f 5891class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5892 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5893 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5894 _FEED_NAME = 'recommended'
45db527f 5895 _LOGIN_REQUIRED = False
3d3dddc9 5896 _TESTS = [{
5897 'url': ':ytrec',
5898 'only_matching': True,
5899 }, {
5900 'url': ':ytrecommended',
5901 'only_matching': True,
5902 }, {
5903 'url': 'https://youtube.com',
5904 'only_matching': True,
5905 }]
1ed5b5c9 5906
1ed5b5c9 5907
25f14e9f 5908class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5909 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5910 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5911 _FEED_NAME = 'subscriptions'
3d3dddc9 5912 _TESTS = [{
5913 'url': ':ytsubs',
5914 'only_matching': True,
5915 }, {
5916 'url': ':ytsubscriptions',
5917 'only_matching': True,
5918 }]
1ed5b5c9 5919
1ed5b5c9 5920
25f14e9f 5921class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5922 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5923 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5924 _FEED_NAME = 'history'
3d3dddc9 5925 _TESTS = [{
5926 'url': ':ythistory',
5927 'only_matching': True,
5928 }]
1ed5b5c9
JMF
5929
5930
6e634cbe 5931class YoutubeStoriesIE(InfoExtractor):
5932 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5933 IE_NAME = 'youtube:stories'
5934 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5935 _TESTS = [{
5936 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5937 'only_matching': True,
5938 }]
5939
5940 def _real_extract(self, url):
5941 playlist_id = f'RLTD{self._match_id(url)}'
5942 return self.url_result(
5943 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5944 ie=YoutubeTabIE, video_id=playlist_id)
5945
5946
15870e90
PH
5947class YoutubeTruncatedURLIE(InfoExtractor):
5948 IE_NAME = 'youtube:truncated_url'
5949 IE_DESC = False # Do not list
975d35db 5950 _VALID_URL = r'''(?x)
b95aab84
PH
5951 (?:https?://)?
5952 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5953 (?:watch\?(?:
c4808c60 5954 feature=[a-z_]+|
b95aab84
PH
5955 annotation_id=annotation_[^&]+|
5956 x-yt-cl=[0-9]+|
c1708b89 5957 hl=[^&]*|
287be8c6 5958 t=[0-9]+
b95aab84
PH
5959 )?
5960 |
5961 attribution_link\?a=[^&]+
5962 )
5963 $
975d35db 5964 '''
15870e90 5965
c4808c60 5966 _TESTS = [{
2d3d2997 5967 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5968 'only_matching': True,
dc2fc736 5969 }, {
2d3d2997 5970 'url': 'https://www.youtube.com/watch?',
dc2fc736 5971 'only_matching': True,
b95aab84
PH
5972 }, {
5973 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5974 'only_matching': True,
5975 }, {
5976 'url': 'https://www.youtube.com/watch?feature=foo',
5977 'only_matching': True,
c1708b89
PH
5978 }, {
5979 'url': 'https://www.youtube.com/watch?hl=en-GB',
5980 'only_matching': True,
287be8c6
PH
5981 }, {
5982 'url': 'https://www.youtube.com/watch?t=2372',
5983 'only_matching': True,
c4808c60
PH
5984 }]
5985
15870e90
PH
5986 def _real_extract(self, url):
5987 raise ExtractorError(
78caa52a
PH
5988 'Did you forget to quote the URL? Remember that & is a meta '
5989 'character in most shells, so you want to put the URL in quotes, '
3867038a 5990 'like youtube-dl '
2d3d2997 5991 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5992 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5993 expected=True)
772fd5cc
PH
5994
5995
471d0367 5996class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 5997 IE_NAME = 'youtube:clip'
471d0367 5998 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
5999 _TESTS = [{
6000 # FIXME: Other metadata should be extracted from the clip, not from the base video
6001 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6002 'info_dict': {
6003 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6004 'ext': 'mp4',
6005 'section_start': 29.0,
6006 'section_end': 39.7,
6007 'duration': 10.7,
6008 }
6009 }]
3cd786db 6010
6011 def _real_extract(self, url):
471d0367 6012 clip_id = self._match_id(url)
6013 _, data = self._extract_webpage(url, clip_id)
6014
6015 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6016 if not video_id:
6017 raise ExtractorError('Unable to find video ID')
6018
6019 clip_data = traverse_obj(data, (
6020 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6021 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6022 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6023 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6024
6025 return {
6026 '_type': 'url_transparent',
6027 'url': f'https://www.youtube.com/watch?v={video_id}',
6028 'ie_key': YoutubeIE.ie_key(),
6029 'id': clip_id,
6030 'section_start': int(clip_data['startTimeMs']) / 1000,
6031 'section_end': int(clip_data['endTimeMs']) / 1000,
6032 }
3cd786db 6033
6034
772fd5cc
PH
6035class YoutubeTruncatedIDIE(InfoExtractor):
6036 IE_NAME = 'youtube:truncated_id'
6037 IE_DESC = False # Do not list
b95aab84 6038 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6039
6040 _TESTS = [{
6041 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6042 'only_matching': True,
6043 }]
6044
6045 def _real_extract(self, url):
6046 video_id = self._match_id(url)
6047 raise ExtractorError(
86e5f3ed 6048 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6049 expected=True)