]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/GoogleDrive] Fix some audio
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
a4894d3e 3import collections
109dd3b2 4import copy
fe93e2c4 5import datetime
c26f9b99 6import enum
a5c56234 7import hashlib
0ca96d48 8import itertools
c5e8d7af 9import json
720c3099 10import math
c4417ddb 11import os.path
d77ab8e2 12import random
c5e8d7af 13import re
46383212 14import sys
f8271158 15import threading
8a784c74 16import time
e0df6211 17import traceback
14f25df2 18import urllib.error
ac668111 19import urllib.parse
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
25836db6 22from .openload import PhantomJSwrapper
14f25df2 23from ..compat import functools
545cc85d 24from ..jsinterp import JSInterpreter
4bb4a188 25from ..utils import (
f8271158 26 NO_DEFAULT,
27 ExtractorError,
4d37720a 28 LazyList,
693f0600 29 UserNotLive,
720c3099 30 bug_reports_message,
82d02080 31 classproperty,
c5e8d7af 32 clean_html,
d92f5d5a 33 datetime_from_str,
11f9be09 34 dict_get,
7a32c70d 35 filter_dict,
2d30521a 36 float_or_none,
11f9be09 37 format_field,
ff91cf74 38 get_first,
dd27fd17 39 int_or_none,
641ad5d8 40 is_html,
34921b43 41 join_nonempty,
48416bc4 42 js_to_json,
94278f72 43 mimetype2ext,
9c0d7f49 44 network_exceptions,
11f9be09 45 orderedSet,
6310acf5 46 parse_codecs,
49bd8c66 47 parse_count,
7c80519c 48 parse_duration,
7ea65411 49 parse_iso8601,
4dfbf869 50 parse_qs,
dca3ff4a 51 qualities,
3995d37d 52 remove_start,
cf7e015f 53 smuggle_url,
dbdaaa23 54 str_or_none,
c93d53f5 55 str_to_int,
f3aa3c3f 56 strftime_or_none,
7c365c21 57 traverse_obj,
556dbe7f 58 try_get,
c5e8d7af
PH
59 unescapeHTML,
60 unified_strdate,
f0d785d3 61 unified_timestamp,
cf7e015f 62 unsmuggle_url,
8bdd16b4 63 update_url_query,
21c340b8 64 url_or_none,
fe93e2c4 65 urljoin,
7c365c21 66 variadic,
c5e8d7af
PH
67)
68
962ffcf8 69# any clients starting with _ cannot be explicitly requested by the user
000c15a4 70INNERTUBE_CLIENTS = {
71 'web': {
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
74 'client': {
75 'clientName': 'WEB',
a0c830f4 76 'clientVersion': '2.20220801.00.00',
000c15a4 77 }
78 },
79 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
80 },
81 'web_embedded': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 86 'clientVersion': '1.20220731.00.00',
000c15a4 87 },
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
90 },
91 'web_music': {
92 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
93 'INNERTUBE_HOST': 'music.youtube.com',
94 'INNERTUBE_CONTEXT': {
95 'client': {
96 'clientName': 'WEB_REMIX',
a0c830f4 97 'clientVersion': '1.20220727.01.00',
000c15a4 98 }
99 },
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
101 },
e7e94f2a 102 'web_creator': {
18c7683d 103 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_CREATOR',
a0c830f4 107 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
111 },
000c15a4 112 'android': {
18c7683d 113 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'ANDROID',
50ac0e54 117 'clientVersion': '17.31.35',
118 'androidSdkVersion': 30,
119 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 120 }
121 },
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 123 'REQUIRE_JS_PLAYER': False
000c15a4 124 },
125 'android_embedded': {
18c7683d 126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 127 'INNERTUBE_CONTEXT': {
128 'client': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 130 'clientVersion': '17.31.35',
131 'androidSdkVersion': 30,
132 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
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',
a0c830f4 143 'clientVersion': '5.16.51',
50ac0e54 144 'androidSdkVersion': 30,
145 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 146 }
147 },
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 149 'REQUIRE_JS_PLAYER': False
000c15a4 150 },
e7e94f2a 151 'android_creator': {
18c7683d 152 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
153 'INNERTUBE_CONTEXT': {
154 'client': {
155 'clientName': 'ANDROID_CREATOR',
50ac0e54 156 'clientVersion': '22.30.100',
157 'androidSdkVersion': 30,
158 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
159 },
160 },
b6de707d 161 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
162 'REQUIRE_JS_PLAYER': False
e7e94f2a 163 },
18c7683d 164 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
165 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 166 'ios': {
18c7683d 167 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS',
224b5a35 171 'clientVersion': '17.33.2',
18c7683d 172 'deviceModel': 'iPhone14,3',
224b5a35 173 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 174 }
175 },
b6de707d 176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
000c15a4 178 },
179 'ios_embedded': {
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 183 'clientVersion': '17.33.2',
18c7683d 184 'deviceModel': 'iPhone14,3',
224b5a35 185 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
191 'ios_music': {
18c7683d 192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
224b5a35
SF
196 'clientVersion': '5.21',
197 'deviceModel': 'iPhone14,3',
198 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 199 },
200 },
b6de707d 201 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
202 'REQUIRE_JS_PLAYER': False
000c15a4 203 },
e7e94f2a
D
204 'ios_creator': {
205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'IOS_CREATOR',
224b5a35
SF
208 'clientVersion': '22.33.101',
209 'deviceModel': 'iPhone14,3',
210 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
211 },
212 },
b6de707d 213 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
214 'REQUIRE_JS_PLAYER': False
e7e94f2a 215 },
3619f78d 216 # mweb has 'ultralow' formats
217 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 218 'mweb': {
18c7683d 219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 220 'INNERTUBE_CONTEXT': {
221 'client': {
222 'clientName': 'MWEB',
a0c830f4 223 'clientVersion': '2.20220801.00.00',
000c15a4 224 }
225 },
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
227 },
228 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
229 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
230 'tv_embedded': {
231 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
232 'INNERTUBE_CONTEXT': {
233 'client': {
234 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
235 'clientVersion': '2.0',
236 },
237 },
238 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
239 },
000c15a4 240}
241
242
e7870111
D
243def _split_innertube_client(client_name):
244 variant, *base = client_name.rsplit('.', 1)
245 if base:
246 return variant, base[0], variant
247 base, *variant = client_name.split('_', 1)
248 return client_name, base, variant[0] if variant else None
249
250
000c15a4 251def build_innertube_clients():
2e4cacd0 252 THIRD_PARTY = {
e7870111 253 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 254 }
e7870111 255 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 256 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 257
258 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 259 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 260 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 261 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 262 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 263
e7870111 264 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 265 ytcfg['priority'] = 10 * priority(base_client)
266
e48b3875 267 if not variant:
e7870111
D
268 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
269 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
270 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
271 embedscreen['priority'] -= 3
272 elif variant == 'embedded':
e48b3875 273 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 274 ytcfg['priority'] -= 2
e48b3875 275 else:
000c15a4 276 ytcfg['priority'] -= 3
277
278
279build_innertube_clients()
280
281
c26f9b99 282class BadgeType(enum.Enum):
283 AVAILABILITY_UNLISTED = enum.auto()
284 AVAILABILITY_PRIVATE = enum.auto()
285 AVAILABILITY_PUBLIC = enum.auto()
286 AVAILABILITY_PREMIUM = enum.auto()
287 AVAILABILITY_SUBSCRIPTION = enum.auto()
288 LIVE_NOW = enum.auto()
289
290
de7f3446 291class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 292 """Provide base functions for Youtube extractors"""
e00eb564 293
3462ffa8 294 _RESERVED_NAMES = (
08e29b9f 295 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
182bda88 296 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 297 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 298 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 299
3619f78d 300 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
301
52efa4b3 302 # _NETRC_MACHINE = 'youtube'
3619f78d 303
b2e8bc1b
JMF
304 # If True it will raise an error if no login info is provided
305 _LOGIN_REQUIRED = False
306
d9190e44
RH
307 _INVIDIOUS_SITES = (
308 # invidious-redirect websites
309 r'(?:www\.)?redirect\.invidious\.io',
310 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 311 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
312 r'(?:www\.)?invidious\.pussthecat\.org',
313 r'(?:www\.)?invidious\.zee\.li',
314 r'(?:www\.)?invidious\.ethibox\.fr',
05799a48
RH
315 r'(?:www\.)?iv\.ggtyler\.dev',
316 r'(?:www\.)?inv\.vern\.i2p',
317 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
318 r'(?:www\.)?inv\.riverside\.rocks',
319 r'(?:www\.)?invidious\.silur\.me',
320 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
321 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
322 r'(?:www\.)?invidious\.slipfox\.xyz',
323 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
324 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
325 r'(?:www\.)?invidious\.tiekoetter\.com',
326 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
327 r'(?:www\.)?invidious\.nerdvpn\.de',
328 r'(?:www\.)?invidious\.weblibre\.org',
329 r'(?:www\.)?inv\.odyssey346\.dev',
330 r'(?:www\.)?invidious\.dhusch\.de',
331 r'(?:www\.)?iv\.melmac\.space',
332 r'(?:www\.)?watch\.thekitty\.zone',
333 r'(?:www\.)?invidious\.privacydev\.net',
334 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
335 r'(?:www\.)?invidious\.drivet\.xyz',
336 r'(?:www\.)?vid\.priv\.au',
337 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
338 r'(?:www\.)?inv\.vern\.cc',
339 r'(?:www\.)?invidious\.esmailelbob\.xyz',
340 r'(?:www\.)?invidious\.sethforprivacy\.com',
341 r'(?:www\.)?yt\.oelrichsgarcia\.de',
342 r'(?:www\.)?yt\.artemislena\.eu',
343 r'(?:www\.)?invidious\.flokinet\.to',
344 r'(?:www\.)?invidious\.baczek\.me',
345 r'(?:www\.)?y\.com\.sb',
346 r'(?:www\.)?invidious\.epicsite\.xyz',
347 r'(?:www\.)?invidious\.lidarshield\.cloud',
348 r'(?:www\.)?yt\.funami\.tech',
d9190e44 349 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
350 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
351 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
352 # youtube-dl invidious instances list
353 r'(?:(?:www|no)\.)?invidiou\.sh',
354 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
355 r'(?:www\.)?invidious\.kabi\.tk',
356 r'(?:www\.)?invidious\.mastodon\.host',
357 r'(?:www\.)?invidious\.zapashcanon\.fr',
358 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
359 r'(?:www\.)?invidious\.tinfoil-hat\.net',
360 r'(?:www\.)?invidious\.himiko\.cloud',
361 r'(?:www\.)?invidious\.reallyancient\.tech',
362 r'(?:www\.)?invidious\.tube',
363 r'(?:www\.)?invidiou\.site',
364 r'(?:www\.)?invidious\.site',
365 r'(?:www\.)?invidious\.xyz',
366 r'(?:www\.)?invidious\.nixnet\.xyz',
367 r'(?:www\.)?invidious\.048596\.xyz',
368 r'(?:www\.)?invidious\.drycat\.fr',
369 r'(?:www\.)?inv\.skyn3t\.in',
370 r'(?:www\.)?tube\.poal\.co',
371 r'(?:www\.)?tube\.connect\.cafe',
372 r'(?:www\.)?vid\.wxzm\.sx',
373 r'(?:www\.)?vid\.mint\.lgbt',
374 r'(?:www\.)?vid\.puffyan\.us',
375 r'(?:www\.)?yewtu\.be',
376 r'(?:www\.)?yt\.elukerio\.org',
377 r'(?:www\.)?yt\.lelux\.fi',
378 r'(?:www\.)?invidious\.ggc-project\.de',
379 r'(?:www\.)?yt\.maisputain\.ovh',
380 r'(?:www\.)?ytprivate\.com',
381 r'(?:www\.)?invidious\.13ad\.de',
382 r'(?:www\.)?invidious\.toot\.koeln',
383 r'(?:www\.)?invidious\.fdn\.fr',
384 r'(?:www\.)?watch\.nettohikari\.com',
385 r'(?:www\.)?invidious\.namazso\.eu',
386 r'(?:www\.)?invidious\.silkky\.cloud',
387 r'(?:www\.)?invidious\.exonip\.de',
388 r'(?:www\.)?invidious\.riverside\.rocks',
389 r'(?:www\.)?invidious\.blamefran\.net',
390 r'(?:www\.)?invidious\.moomoo\.de',
391 r'(?:www\.)?ytb\.trom\.tf',
392 r'(?:www\.)?yt\.cyberhost\.uk',
393 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
394 r'(?:www\.)?qklhadlycap4cnod\.onion',
395 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
396 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
397 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
398 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
399 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
400 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
401 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
402 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
403 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
404 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
405 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
406 r'(?:www\.)?piped\.kavin\.rocks',
d1c4f6d4 407 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 408 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 409 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
410 r'(?:www\.)?watch\.whatever\.social',
411 r'(?:www\.)?piped\.garudalinux\.org',
412 r'(?:www\.)?piped\.rivo\.lol',
413 r'(?:www\.)?piped-libre\.kavin\.rocks',
414 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 415 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
416 r'(?:www\.)?il\.ax',
417 r'(?:www\.)?piped\.esmailelbob\.xyz',
418 r'(?:www\.)?piped\.projectsegfau\.lt',
419 r'(?:www\.)?piped\.privacydev\.net',
420 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
421 r'(?:www\.)?piped\.smnz\.de',
422 r'(?:www\.)?piped\.adminforge\.de',
423 r'(?:www\.)?watch\.whatevertinfoil\.de',
424 r'(?:www\.)?piped\.qdi\.fi',
bc87dac7
B
425 r'(?:www\.)?piped\.video',
426 r'(?:www\.)?piped\.aeong\.one',
05799a48
RH
427 r'(?:www\.)?piped\.moomoo\.me',
428 r'(?:www\.)?piped\.chauvet\.pro',
429 r'(?:www\.)?watch\.leptons\.xyz',
430 r'(?:www\.)?pd\.vern\.cc',
431 r'(?:www\.)?piped\.hostux\.net',
432 r'(?:www\.)?piped\.lunar\.icu',
78a78fa7
BG
433 # Hyperpipe instances from https://hyperpipe.codeberg.page/
434 r'(?:www\.)?hyperpipe\.surge\.sh',
435 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
436 r'(?:www\.)?listen\.whatever\.social',
437 r'(?:www\.)?music\.adminforge\.de',
d9190e44
RH
438 )
439
c26f9b99 440 # extracted from account/account_menu ep
441 # XXX: These are the supported YouTube UI and API languages,
442 # which is slightly different from languages supported for translation in YouTube studio
443 _SUPPORTED_LANG_CODES = [
444 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
445 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
446 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
447 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
448 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
449 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
450 ]
451
a057779d 452 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
453
c26f9b99 454 @functools.cached_property
455 def _preferred_lang(self):
456 """
457 Returns a language code supported by YouTube for the user preferred language.
458 Returns None if no preferred language set.
459 """
460 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
461 if not preferred_lang:
462 return
463 if preferred_lang not in self._SUPPORTED_LANG_CODES:
464 raise ExtractorError(
465 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
466 expected=True)
467 elif preferred_lang != 'en':
468 self.report_warning(
469 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
470 return preferred_lang
471
cce889b9 472 def _initialize_consent(self):
473 cookies = self._get_cookies('https://www.youtube.com/')
474 if cookies.get('__Secure-3PSID'):
475 return
476 consent_id = None
477 consent = cookies.get('CONSENT')
478 if consent:
479 if 'YES' in consent.value:
480 return
481 consent_id = self._search_regex(
482 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
483 if not consent_id:
484 consent_id = random.randint(100, 999)
485 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 486
f3aa3c3f 487 def _initialize_pref(self):
488 cookies = self._get_cookies('https://www.youtube.com/')
489 pref_cookie = cookies.get('PREF')
490 pref = {}
491 if pref_cookie:
492 try:
14f25df2 493 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 494 except ValueError:
495 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 496 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 497 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 498
b2e8bc1b 499 def _real_initialize(self):
f3aa3c3f 500 self._initialize_pref()
cce889b9 501 self._initialize_consent()
a25bca9f 502 self._check_login_required()
503
504 def _check_login_required(self):
24146491 505 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 506 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 507
b7c47b74 508 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
509 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 510
000c15a4 511 def _get_default_ytcfg(self, client='web'):
512 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 513
000c15a4 514 def _get_innertube_host(self, client='web'):
515 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 516
000c15a4 517 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 518 # try_get but with fallback to default ytcfg client values when present
519 _func = lambda y: try_get(y, getter, expected_type)
520 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
521
000c15a4 522 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 523 return self._ytcfg_get_safe(
524 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 525 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 526
000c15a4 527 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 528 return self._ytcfg_get_safe(
529 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 530 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 531
2ae778b8 532 def _select_api_hostname(self, req_api_hostname, default_client=None):
533 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
534 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
535
000c15a4 536 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 537 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 538
000c15a4 539 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 540 context = get_first(
541 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 542 # Enforce language and tz for extraction
543 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 544 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 545 return context
546
cf87314d 547 _SAPISID = None
548
109dd3b2 549 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 550 time_now = round(time.time())
cf87314d 551 if self._SAPISID is None:
552 yt_cookies = self._get_cookies('https://www.youtube.com')
553 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
554 # See: https://github.com/yt-dlp/yt-dlp/issues/393
555 sapisid_cookie = dict_get(
556 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
557 if sapisid_cookie and sapisid_cookie.value:
558 self._SAPISID = sapisid_cookie.value
559 self.write_debug('Extracted SAPISID cookie')
560 # SAPISID cookie is required if not already present
561 if not yt_cookies.get('SAPISID'):
562 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
563 self._set_cookie(
564 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
565 else:
566 self._SAPISID = False
567 if not self._SAPISID:
568 return None
1974e99f 569 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
570 sapisidhash = hashlib.sha1(
86e5f3ed 571 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 572 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
573
574 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 575 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 576 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 577
109dd3b2 578 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 579 data.update(query)
11f9be09 580 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 581 real_headers.update({'content-type': 'application/json'})
582 if headers:
583 real_headers.update(headers)
2ae778b8 584 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
585 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 586 return self._download_json(
2ae778b8 587 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 588 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 589 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 590 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 591
65141660 592 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
593 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 594
99e9e001 595 @staticmethod
596 def _extract_session_index(*data):
597 """
598 Index of current account in account list.
599 See: https://github.com/yt-dlp/yt-dlp/pull/519
600 """
601 for ytcfg in data:
602 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
603 if session_index is not None:
604 return session_index
605
606 # Deprecated?
607 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 608 if ytcfg:
14f25df2 609 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
610 if token:
611 return token
99e9e001 612 if webpage:
613 return self._search_regex(
614 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
615 'identity token', default=None, fatal=False)
a1c5d2ca
M
616
617 @staticmethod
fe93e2c4 618 def _extract_account_syncid(*args):
8ea3f7b9 619 """
620 Extract syncId required to download private playlists of secondary channels
fe93e2c4 621 @params response and/or ytcfg
8ea3f7b9 622 """
fe93e2c4 623 for data in args:
624 # ytcfg includes channel_syncid if on secondary channel
14f25df2 625 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 626 if delegated_sid:
627 return delegated_sid
628 sync_ids = (try_get(
629 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 630 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 631 if len(sync_ids) >= 2 and sync_ids[1]:
632 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
633 # and just "user_syncid||" for primary channel. We only want the channel_syncid
634 return sync_ids[0]
a1c5d2ca 635
ac56cf38 636 @staticmethod
637 def _extract_visitor_data(*args):
638 """
639 Extracts visitorData from an API response or ytcfg
640 Appears to be used to track session state
641 """
9222c381 642 return get_first(
6c73052c 643 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 644 expected_type=str)
ac56cf38 645
2762dbb1 646 @functools.cached_property
99e9e001 647 def is_authenticated(self):
648 return bool(self._generate_sapisidhash_header())
649
11f9be09 650 def extract_ytcfg(self, video_id, webpage):
8c54a305 651 if not webpage:
652 return {}
29f7c58a 653 return self._parse_json(
654 self._search_regex(
655 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 656 default='{}'), video_id, fatal=False) or {}
657
11f9be09 658 def generate_api_headers(
99e9e001 659 self, *, ytcfg=None, account_syncid=None, session_index=None,
660 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
661
2ae778b8 662 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 663 headers = {
14f25df2 664 'X-YouTube-Client-Name': str(
11f9be09 665 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
666 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 667 'Origin': origin,
668 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
669 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 670 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
671 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 672 }
673 if session_index is None:
314ee305 674 session_index = self._extract_session_index(ytcfg)
675 if account_syncid or session_index is not None:
676 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 677
109dd3b2 678 auth = self._generate_sapisidhash_header(origin)
f4f751af 679 if auth is not None:
680 headers['Authorization'] = auth
109dd3b2 681 headers['X-Origin'] = origin
7a32c70d 682 return filter_dict(headers)
29f7c58a 683
a25bca9f 684 def _download_ytcfg(self, client, video_id):
685 url = {
686 'web': 'https://www.youtube.com',
687 'web_music': 'https://music.youtube.com',
688 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
689 }.get(client)
690 if not url:
691 return {}
692 webpage = self._download_webpage(
693 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
694 return self.extract_ytcfg(video_id, webpage) or {}
695
2d6659b9 696 @staticmethod
697 def _build_api_continuation_query(continuation, ctp=None):
698 query = {
699 'continuation': continuation
700 }
701 # TODO: Inconsistency with clickTrackingParams.
702 # Currently we have a fixed ctp contained within context (from ytcfg)
703 # and a ctp in root query for continuation.
704 if ctp:
705 query['clickTracking'] = {'clickTrackingParams': ctp}
706 return query
707
2d6659b9 708 @classmethod
709 def _extract_next_continuation_data(cls, renderer):
710 next_continuation = try_get(
711 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
712 lambda x: x['continuation']['reloadContinuationData']), dict)
713 if not next_continuation:
714 return
715 continuation = next_continuation.get('continuation')
716 if not continuation:
717 return
718 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 719 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 720
721 @classmethod
722 def _extract_continuation_ep_data(cls, continuation_ep: dict):
723 if isinstance(continuation_ep, dict):
724 continuation = try_get(
14f25df2 725 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 726 if not continuation:
727 return
728 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 729 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 730
731 @classmethod
732 def _extract_continuation(cls, renderer):
733 next_continuation = cls._extract_next_continuation_data(renderer)
734 if next_continuation:
735 return next_continuation
fe93e2c4 736
7a32c70d 737 return traverse_obj(renderer, (
738 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
739 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
740 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 741
fe93e2c4 742 @classmethod
743 def _extract_alerts(cls, data):
109dd3b2 744 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
745 if not isinstance(alert_dict, dict):
746 continue
747 for alert in alert_dict.values():
748 alert_type = alert.get('type')
749 if not alert_type:
750 continue
052e1350 751 message = cls._get_text(alert, 'text')
109dd3b2 752 if message:
753 yield alert_type, message
754
c0ac49bc 755 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 756 errors, warnings = [], []
109dd3b2 757 for alert_type, alert_message in alerts:
641ad5d8 758 if alert_type.lower() == 'error' and fatal:
109dd3b2 759 errors.append([alert_type, alert_message])
a057779d 760 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 761 warnings.append([alert_type, alert_message])
762
763 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 764 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 765 if errors:
766 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
767
768 def _extract_and_report_alerts(self, data, *args, **kwargs):
769 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
770
47193e02 771 def _extract_badges(self, renderer: dict):
c26f9b99 772 privacy_icon_map = {
773 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
774 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
775 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
776 }
777
778 badge_style_map = {
779 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
780 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
781 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
782 }
783
784 label_map = {
785 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
786 'private': BadgeType.AVAILABILITY_PRIVATE,
787 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
788 'live': BadgeType.LIVE_NOW,
789 'premium': BadgeType.AVAILABILITY_PREMIUM
790 }
791
792 badges = []
6839ae1f 793 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')):
c26f9b99 794 badge_type = (
795 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
796 or badge_style_map.get(traverse_obj(badge, 'style'))
797 )
798 if badge_type:
799 badges.append({'type': badge_type})
800 continue
801
802 # fallback, won't work in some languages
803 label = traverse_obj(badge, 'label', expected_type=str, default='')
804 for match, label_badge_type in label_map.items():
805 if match in label.lower():
806 badges.append({'type': badge_type})
807 continue
808
47193e02 809 return badges
810
c26f9b99 811 @staticmethod
812 def _has_badge(badges, badge_type):
813 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
814
47193e02 815 @staticmethod
052e1350 816 def _get_text(data, *path_list, max_runs=None):
817 for path in path_list or [None]:
818 if path is None:
819 obj = [data]
820 else:
821 obj = traverse_obj(data, path, default=[])
822 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
823 obj = [obj]
824 for item in obj:
14f25df2 825 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 826 if text:
827 return text
828 runs = try_get(item, lambda x: x['runs'], list) or []
829 if not runs and isinstance(item, list):
830 runs = item
831
832 runs = runs[:min(len(runs), max_runs or len(runs))]
6839ae1f 833 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
052e1350 834 if text:
835 return text
47193e02 836
f0d785d3 837 def _get_count(self, data, *path_list):
838 count_text = self._get_text(data, *path_list) or ''
839 count = parse_count(count_text)
840 if count is None:
841 count = str_to_int(
842 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
843 return count
844
a709d873 845 @staticmethod
846 def _extract_thumbnails(data, *path_list):
847 """
848 Extract thumbnails from thumbnails dict
849 @param path_list: path list to level that contains 'thumbnails' key
850 """
851 thumbnails = []
852 for path in path_list or [()]:
6839ae1f 853 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
a709d873 854 thumbnail_url = url_or_none(thumbnail.get('url'))
855 if not thumbnail_url:
856 continue
857 # Sometimes youtube gives a wrong thumbnail URL. See:
858 # https://github.com/yt-dlp/yt-dlp/issues/233
859 # https://github.com/ytdl-org/youtube-dl/issues/28023
860 if 'maxresdefault' in thumbnail_url:
861 thumbnail_url = thumbnail_url.split('?')[0]
862 thumbnails.append({
863 'url': thumbnail_url,
864 'height': int_or_none(thumbnail.get('height')),
865 'width': int_or_none(thumbnail.get('width')),
866 })
867 return thumbnails
868
f3aa3c3f 869 @staticmethod
870 def extract_relative_time(relative_time_text):
871 """
872 Extracts a relative time from string and converts to dt object
f0d785d3 873 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 874 """
f0d785d3 875 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 876 if mobj:
f0d785d3 877 start = mobj.group('start')
878 if start:
879 return datetime_from_str(start)
f3aa3c3f 880 try:
f0d785d3 881 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 882 except ValueError:
883 return None
884
c26f9b99 885 def _parse_time_text(self, text):
886 if not text:
887 return
f3aa3c3f 888 dt = self.extract_relative_time(text)
889 timestamp = None
890 if isinstance(dt, datetime.datetime):
891 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 892
893 if timestamp is None:
894 timestamp = (
895 unified_timestamp(text) or unified_timestamp(
896 self._search_regex(
17322130 897 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 898 text.lower(), 'time text', default=None)))
f0d785d3 899
c26f9b99 900 if text and timestamp is None and self._preferred_lang in (None, 'en'):
901 self.report_warning(
902 f'Cannot parse localized time text "{text}"', only_once=True)
903 return timestamp
f3aa3c3f 904
109dd3b2 905 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
906 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 907 default_client='web'):
be5c1ae8 908 for retry in self.RetryManager():
109dd3b2 909 try:
910 response = self._call_api(
911 ep=ep, fatal=True, headers=headers,
be5c1ae8 912 video_id=item_id, query=query, note=note,
109dd3b2 913 context=self._extract_context(ytcfg, default_client),
914 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 915 api_hostname=api_hostname, default_client=default_client)
109dd3b2 916 except ExtractorError as e:
be5c1ae8 917 if not isinstance(e.cause, network_exceptions):
918 return self._error_or_warning(e, fatal=fatal)
919 elif not isinstance(e.cause, urllib.error.HTTPError):
920 retry.error = e
921 continue
109dd3b2 922
be5c1ae8 923 first_bytes = e.cause.read(512)
924 if not is_html(first_bytes):
925 yt_error = try_get(
926 self._parse_json(
927 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
928 lambda x: x['error']['message'], str)
929 if yt_error:
930 self._report_alerts([('ERROR', yt_error)], fatal=False)
931 # Downloading page may result in intermittent 5xx HTTP error
932 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
933 # We also want to catch all other network exceptions since errors in later pages can be troublesome
934 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
935 if e.cause.code not in (403, 429):
936 retry.error = e
937 continue
938 return self._error_or_warning(e, fatal=fatal)
939
940 try:
941 self._extract_and_report_alerts(response, only_once=True)
942 except ExtractorError as e:
943 # YouTube servers may return errors we want to retry on in a 200 OK response
944 # See: https://github.com/yt-dlp/yt-dlp/issues/839
945 if 'unknown error' in e.msg.lower():
946 retry.error = e
947 continue
948 return self._error_or_warning(e, fatal=fatal)
949 # Youtube sometimes sends incomplete data
950 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
951 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 952 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 953 continue
954
955 return response
109dd3b2 956
9297939e 957 @staticmethod
958 def is_music_url(url):
959 return re.match(r'https?://music\.youtube\.com/', url) is not None
960
30a074c2 961 def _extract_video(self, renderer):
962 video_id = renderer.get('videoId')
4dc23a80
M
963
964 reel_header_renderer = traverse_obj(renderer, (
965 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
966 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
967
968 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 969 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
970
971 duration = int_or_none(renderer.get('lengthSeconds'))
972 if duration is None:
973 duration = parse_duration(self._get_text(
974 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 975 if duration is None:
4dc23a80 976 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 977 duration = parse_duration(self._search_regex(
978 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
979 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
980 video_id, default=None, group='duration'))
981
f3aa3c3f 982 channel_id = traverse_obj(
a44ca5a4 983 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
984 expected_type=str, get_all=False)
4dc23a80
M
985 if not channel_id:
986 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
987
f3aa3c3f 988 overlay_style = traverse_obj(
a44ca5a4 989 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
990 get_all=False, expected_type=str)
f3aa3c3f 991 badges = self._extract_badges(renderer)
4dc23a80 992
fd2ad7cb 993 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 994 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
995 expected_type=str)) or ''
fd2ad7cb 996 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 997 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 998 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 999
4dc23a80
M
1000 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1001 or self._get_text(reel_header_renderer, 'timestampText') or '')
1002 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1003
867c66ff
M
1004 live_status = (
1005 'is_upcoming' if scheduled_timestamp is not None
1006 else 'was_live' if 'streamed' in time_text.lower()
1007 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1008 else None)
1009
4dc23a80
M
1010 # videoInfo is a string like '50K views • 10 years ago'.
1011 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1012 view_count = (0 if 'no views' in view_count_text.lower()
1013 else self._get_count({'simpleText': view_count_text}))
1014 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1015
30a074c2 1016 return {
39ed931e 1017 '_type': 'url',
30a074c2 1018 'ie_key': YoutubeIE.ie_key(),
1019 'id': video_id,
fd2ad7cb 1020 'url': url,
30a074c2 1021 'title': title,
1022 'description': description,
1023 'duration': duration,
f3aa3c3f 1024 'channel_id': channel_id,
4dc23a80
M
1025 'channel': (self._get_text(renderer, 'ownerText', 'shortBylineText')
1026 or self._get_text(reel_header_renderer, 'channelTitleText')),
1027 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
1028 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1029 'timestamp': (self._parse_time_text(time_text)
1030 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1031 else None),
f3aa3c3f 1032 'release_timestamp': scheduled_timestamp,
c26f9b99 1033 'availability':
1034 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1035 else self._availability(
1036 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1037 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1038 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1039 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1040 view_count_field: view_count,
e63faa10 1041 'live_status': live_status
30a074c2 1042 }
1043
0c148415 1044
360e1ca5 1045class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1046 IE_DESC = 'YouTube'
cb7dfeea 1047 _VALID_URL = r"""(?x)^
c5e8d7af 1048 (
edb53e2d 1049 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1050 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1051 (?:www\.)?deturl\.com/www\.youtube\.com|
1052 (?:www\.)?pwnyoutube\.com|
1053 (?:www\.)?hooktube\.com|
1054 (?:www\.)?yourepeat\.com|
1055 tube\.majestyc\.net|
1056 %(invidious)s|
1057 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1058 (?:.*?\#/)? # handle anchor (#/) redirect urls
1059 (?: # the various things that can precede the ID:
dad2210c 1060 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1061 |(?: # or the v= param in all its forms
f7000f3a 1062 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1063 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1064 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1065 v=
1066 )
f4b05232 1067 ))
cbaed4bb
S
1068 |(?:
1069 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1070 vid\.plus| # or vid.plus/xxxx
1071 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1072 %(invidious)s
cbaed4bb 1073 )/
edb53e2d 1074 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1075 )
c5e8d7af 1076 )? # all until now is optional -> you can pass the naked ID
201c1459 1077 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1078 (?(1).+)? # if we found the ID, everything can follow
9297939e 1079 (?:\#|$)""" % {
d9190e44 1080 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1081 }
7c6eb424 1082 _EMBED_REGEX = [
1083 r'''(?x)
1084 (?:
0ca0f881 1085 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1086 data-video-url=|
1087 <embed[^>]+?src=|
1088 embedSWF\(?:\s*|
1089 <object[^>]+data=|
1090 new\s+SWFObject\(
1091 )
1092 (["\'])
1093 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1094 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1095 \1''',
1096 # https://wordpress.org/plugins/lazy-load-for-videos/
1097 r'''(?xs)
1098 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1099 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1100 ]
6368e2e6 1101 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1102
e40c758c 1103 _PLAYER_INFO_RE = (
cc2db878 1104 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1105 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$',
545cc85d 1106 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1107 )
2c62dc26 1108 _formats = {
c2d3cb4c 1109 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1110 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1111 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1112 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1113 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1114 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1115 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1116 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1117 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1118 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1119 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1120 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1121 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1122 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1123 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1124 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1125 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1126 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1127
1128
1129 # 3D videos
c2d3cb4c 1130 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1131 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1132 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1133 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1134 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1135 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1136 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1137
96fb5605 1138 # Apple HTTP Live Streaming
11f12195 1139 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1140 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1141 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1142 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1143 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1144 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1145 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1146 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1147
1148 # DASH mp4 video
d23028a8
S
1149 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1150 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1151 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1152 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1153 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1154 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1155 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1156 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1157 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1158 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1159 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1160 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1161
f6f1fc92 1162 # Dash mp4 audio
d23028a8
S
1163 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1164 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1165 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1166 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1167 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1168 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1169 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1170
1171 # Dash webm
d23028a8
S
1172 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1173 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1174 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1175 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1176 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1177 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1178 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1179 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1180 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1181 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1182 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1183 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1184 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1185 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1186 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1187 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1188 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1189 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1190 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1191 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1192 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1193 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1194
1195 # Dash webm audio
d23028a8
S
1196 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1197 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1198
0857baad 1199 # Dash webm audio with opus inside
d23028a8
S
1200 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1201 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1202 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1203
ce6b9a2d
PH
1204 # RTMP (unnamed)
1205 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1206
1207 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1208 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1209 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1210 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1211 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1212 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1213 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1214 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1215 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1216 }
29f7c58a 1217 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1218
fd5c4aab
S
1219 _GEO_BYPASS = False
1220
78caa52a 1221 IE_NAME = 'youtube'
2eb88d95
PH
1222 _TESTS = [
1223 {
2d3d2997 1224 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1225 'info_dict': {
1226 'id': 'BaW_jenozKc',
1227 'ext': 'mp4',
3867038a 1228 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1229 'uploader': 'Philipp Hagemeister',
1230 'uploader_id': 'phihag',
ec85ded8 1231 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1232 'channel': 'Philipp Hagemeister',
dd4c4492
S
1233 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1234 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1235 'upload_date': '20121002',
ff9f925b 1236 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1237 'categories': ['Science & Technology'],
3867038a 1238 'tags': ['youtube-dl'],
556dbe7f 1239 'duration': 10,
dbdaaa23 1240 'view_count': int,
3e7c1224 1241 'like_count': int,
ff9f925b 1242 'availability': 'public',
1243 'playable_in_embed': True,
1244 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1245 'live_status': 'not_live',
1246 'age_limit': 0,
7c80519c 1247 'start_time': 1,
297a564b 1248 'end_time': 9,
12a1b225 1249 'comment_count': int,
6c73052c 1250 'channel_follower_count': int
2eb88d95 1251 }
0e853ca4 1252 },
fccd3771 1253 {
4bc3a23e
PH
1254 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1255 'note': 'Embed-only video (#1746)',
1256 'info_dict': {
1257 'id': 'yZIXLfi8CZQ',
1258 'ext': 'mp4',
1259 'upload_date': '20120608',
1260 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1261 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1262 'uploader': 'SET India',
94bfcd23 1263 'uploader_id': 'setindia',
ec85ded8 1264 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1265 'age_limit': 18,
545cc85d 1266 },
1267 'skip': 'Private video',
fccd3771 1268 },
11b56058 1269 {
8bdd16b4 1270 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1271 'note': 'Use the first video ID in the URL',
1272 'info_dict': {
1273 'id': 'BaW_jenozKc',
1274 'ext': 'mp4',
3867038a 1275 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1276 'uploader': 'Philipp Hagemeister',
1277 'uploader_id': 'phihag',
ec85ded8 1278 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1279 'channel': 'Philipp Hagemeister',
1280 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1281 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1282 'upload_date': '20121002',
976ae3ea 1283 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1284 'categories': ['Science & Technology'],
3867038a 1285 'tags': ['youtube-dl'],
556dbe7f 1286 'duration': 10,
dbdaaa23 1287 'view_count': int,
11b56058 1288 'like_count': int,
976ae3ea 1289 'availability': 'public',
1290 'playable_in_embed': True,
1291 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1292 'live_status': 'not_live',
1293 'age_limit': 0,
12a1b225 1294 'comment_count': int,
6c73052c 1295 'channel_follower_count': int
34a7de29
S
1296 },
1297 'params': {
1298 'skip_download': True,
1299 },
11b56058 1300 },
dd27fd17 1301 {
2d3d2997 1302 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1303 'note': '256k DASH audio (format 141) via DASH manifest',
1304 'info_dict': {
1305 'id': 'a9LDPn-MO4I',
1306 'ext': 'm4a',
1307 'upload_date': '20121002',
1308 'uploader_id': '8KVIDEO',
ec85ded8 1309 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1310 'description': '',
1311 'uploader': '8KVIDEO',
1312 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1313 },
4bc3a23e
PH
1314 'params': {
1315 'youtube_include_dash_manifest': True,
1316 'format': '141',
4919603f 1317 },
de3c7fe0 1318 'skip': 'format 141 not served anymore',
dd27fd17 1319 },
8bdd16b4 1320 # DASH manifest with encrypted signature
1321 {
1322 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1323 'info_dict': {
1324 'id': 'IB3lcPjvWLA',
1325 'ext': 'm4a',
1326 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1327 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1328 'duration': 244,
1329 'uploader': 'AfrojackVEVO',
1330 'uploader_id': 'AfrojackVEVO',
1331 'upload_date': '20131011',
cc2db878 1332 'abr': 129.495,
976ae3ea 1333 'like_count': int,
1334 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1335 'playable_in_embed': True,
1336 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1337 'view_count': int,
1338 'track': 'The Spark',
1339 'live_status': 'not_live',
1340 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1341 'channel': 'Afrojack',
1342 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1343 'tags': 'count:19',
1344 'availability': 'public',
1345 'categories': ['Music'],
1346 'age_limit': 0,
1347 'alt_title': 'The Spark',
6c73052c 1348 'channel_follower_count': int
8bdd16b4 1349 },
1350 'params': {
1351 'youtube_include_dash_manifest': True,
1352 'format': '141/bestaudio[ext=m4a]',
1353 },
1354 },
65c2fde2 1355 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1356 {
65c2fde2 1357 'note': 'Embed allowed age-gate video',
2d3d2997 1358 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1359 'info_dict': {
1360 'id': 'HtVdAasjOgU',
1361 'ext': 'mp4',
1362 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1363 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1364 'duration': 142,
c522adb1
JMF
1365 'uploader': 'The Witcher',
1366 'uploader_id': 'WitcherGame',
ec85ded8 1367 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1368 'upload_date': '20140605',
34952f09 1369 'age_limit': 18,
976ae3ea 1370 'categories': ['Gaming'],
1371 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1372 'availability': 'needs_auth',
1373 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1374 'like_count': int,
1375 'channel': 'The Witcher',
1376 'live_status': 'not_live',
1377 'tags': 'count:17',
1378 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1379 'playable_in_embed': True,
1380 'view_count': int,
6c73052c 1381 'channel_follower_count': int
c522adb1
JMF
1382 },
1383 },
65c2fde2 1384 {
1385 'note': 'Age-gate video with embed allowed in public site',
1386 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1387 'info_dict': {
1388 'id': 'HsUATh_Nc2U',
1389 'ext': 'mp4',
1390 'title': 'Godzilla 2 (Official Video)',
1391 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1392 'upload_date': '20200408',
1393 'uploader_id': 'FlyingKitty900',
1394 'uploader': 'FlyingKitty',
1395 'age_limit': 18,
976ae3ea 1396 'availability': 'needs_auth',
1397 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1398 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1399 'channel': 'FlyingKitty',
1400 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1401 'view_count': int,
1402 'categories': ['Entertainment'],
1403 'live_status': 'not_live',
1404 'tags': ['Flyingkitty', 'godzilla 2'],
1405 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1406 'like_count': int,
1407 'duration': 177,
1408 'playable_in_embed': True,
6c73052c 1409 'channel_follower_count': int
65c2fde2 1410 },
1411 },
1412 {
1413 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1414 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1415 'info_dict': {
1416 'id': 'Tq92D6wQ1mg',
1417 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1418 'ext': 'mp4',
17322130 1419 'upload_date': '20191228',
65c2fde2 1420 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1421 'uploader': 'Projekt Melody',
1422 'description': 'md5:17eccca93a786d51bc67646756894066',
1423 'age_limit': 18,
976ae3ea 1424 'like_count': int,
1425 'availability': 'needs_auth',
1426 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1427 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1428 'view_count': int,
1429 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1430 'channel': 'Projekt Melody',
1431 'live_status': 'not_live',
1432 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1433 'playable_in_embed': True,
1434 'categories': ['Entertainment'],
1435 'duration': 106,
1436 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1437 'comment_count': int,
6c73052c 1438 'channel_follower_count': int
65c2fde2 1439 },
1440 },
1441 {
1442 'note': 'Non-Agegated non-embeddable video',
1443 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1444 'info_dict': {
1445 'id': 'MeJVWBSsPAY',
1446 'ext': 'mp4',
1447 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1448 'uploader': 'Herr Lurik',
1449 'uploader_id': 'st3in234',
1450 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1451 'upload_date': '20130730',
976ae3ea 1452 'track': 'Such mich find mich',
1453 'age_limit': 0,
1454 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1455 'like_count': int,
1456 'playable_in_embed': False,
1457 'creator': 'OOMPH!',
1458 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1459 'view_count': int,
1460 'alt_title': 'Such mich find mich',
1461 'duration': 210,
1462 'channel': 'Herr Lurik',
1463 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1464 'categories': ['Music'],
1465 'availability': 'public',
1466 'uploader_url': 'http://www.youtube.com/user/st3in234',
1467 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1468 'live_status': 'not_live',
1469 'artist': 'OOMPH!',
6c73052c 1470 'channel_follower_count': int
65c2fde2 1471 },
1472 },
1473 {
1474 'note': 'Non-bypassable age-gated video',
1475 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1476 'only_matching': True,
1477 },
8bdd16b4 1478 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1479 # YouTube Red ad is not captured for creator
1480 {
1481 'url': '__2ABJjxzNo',
1482 'info_dict': {
1483 'id': '__2ABJjxzNo',
1484 'ext': 'mp4',
1485 'duration': 266,
1486 'upload_date': '20100430',
1487 'uploader_id': 'deadmau5',
1488 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1489 'creator': 'deadmau5',
1490 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1491 'uploader': 'deadmau5',
1492 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1493 'alt_title': 'Some Chords',
976ae3ea 1494 'availability': 'public',
1495 'tags': 'count:14',
1496 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1497 'view_count': int,
1498 'live_status': 'not_live',
1499 'channel': 'deadmau5',
1500 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1501 'like_count': int,
1502 'track': 'Some Chords',
1503 'artist': 'deadmau5',
1504 'playable_in_embed': True,
1505 'age_limit': 0,
1506 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1507 'categories': ['Music'],
1508 'album': 'Some Chords',
6c73052c 1509 'channel_follower_count': int
8bdd16b4 1510 },
1511 'expected_warnings': [
1512 'DASH manifest missing',
1513 ]
1514 },
067aa17e 1515 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1516 {
1517 'url': 'lqQg6PlCWgI',
1518 'info_dict': {
1519 'id': 'lqQg6PlCWgI',
1520 'ext': 'mp4',
556dbe7f 1521 'duration': 6085,
90227264 1522 'upload_date': '20150827',
cbe2bd91 1523 'uploader_id': 'olympic',
ec85ded8 1524 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1525 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1526 'uploader': 'Olympics',
cbe2bd91 1527 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1528 'like_count': int,
1529 'release_timestamp': 1343767800,
1530 'playable_in_embed': True,
1531 'categories': ['Sports'],
1532 'release_date': '20120731',
1533 'channel': 'Olympics',
1534 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1535 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1536 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1537 'age_limit': 0,
1538 'availability': 'public',
1539 'live_status': 'was_live',
1540 'view_count': int,
1541 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1542 'channel_follower_count': int
cbe2bd91
PH
1543 },
1544 'params': {
1545 'skip_download': 'requires avconv',
e52a40ab 1546 }
cbe2bd91 1547 },
6271f1ca
PH
1548 # Non-square pixels
1549 {
1550 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1551 'info_dict': {
1552 'id': '_b-2C3KPAM0',
1553 'ext': 'mp4',
1554 'stretched_ratio': 16 / 9.,
556dbe7f 1555 'duration': 85,
6271f1ca
PH
1556 'upload_date': '20110310',
1557 'uploader_id': 'AllenMeow',
ec85ded8 1558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1559 '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 1560 'uploader': '孫ᄋᄅ',
6271f1ca 1561 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1562 'playable_in_embed': True,
1563 'channel': '孫ᄋᄅ',
1564 'age_limit': 0,
1565 'tags': 'count:11',
1566 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1567 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1568 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1569 'view_count': int,
1570 'categories': ['People & Blogs'],
1571 'like_count': int,
1572 'live_status': 'not_live',
1573 'availability': 'unlisted',
12a1b225 1574 'comment_count': int,
6c73052c 1575 'channel_follower_count': int
6271f1ca 1576 },
06b491eb
S
1577 },
1578 # url_encoded_fmt_stream_map is empty string
1579 {
1580 'url': 'qEJwOuvDf7I',
1581 'info_dict': {
1582 'id': 'qEJwOuvDf7I',
f57b7835 1583 'ext': 'webm',
06b491eb
S
1584 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1585 'description': '',
1586 'upload_date': '20150404',
1587 'uploader_id': 'spbelect',
1588 'uploader': 'Наблюдатели Петербурга',
1589 },
1590 'params': {
1591 'skip_download': 'requires avconv',
e323cf3f
S
1592 },
1593 'skip': 'This live event has ended.',
06b491eb 1594 },
067aa17e 1595 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1596 {
1597 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1598 'info_dict': {
1599 'id': 'FIl7x6_3R5Y',
eb6793ba 1600 'ext': 'webm',
da77d856
S
1601 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1602 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1603 'duration': 220,
da77d856
S
1604 'upload_date': '20150625',
1605 'uploader_id': 'dorappi2000',
ec85ded8 1606 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1607 'uploader': 'dorappi2000',
eb6793ba 1608 'formats': 'mincount:31',
da77d856 1609 },
eb6793ba 1610 'skip': 'not actual anymore',
2ee8f5d8 1611 },
8a1a26ce
YCH
1612 # DASH manifest with segment_list
1613 {
1614 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1615 'md5': '8ce563a1d667b599d21064e982ab9e31',
1616 'info_dict': {
1617 'id': 'CsmdDsKjzN8',
1618 'ext': 'mp4',
17ee98e1 1619 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1620 'uploader': 'Airtek',
1621 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1622 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1623 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1624 },
1625 'params': {
1626 'youtube_include_dash_manifest': True,
1627 'format': '135', # bestvideo
be49068d
S
1628 },
1629 'skip': 'This live event has ended.',
2ee8f5d8 1630 },
cf7e015f 1631 {
6368e2e6 1632 # Multifeed videos (multiple cameras), URL can be of any Camera
1633 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1634 'info_dict': {
6368e2e6 1635 'id': 'zaPI8MvL8pg',
1636 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1637 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1638 },
1639 'playlist': [{
1640 'info_dict': {
6368e2e6 1641 'id': 'j5yGuxZ8lLU',
cf7e015f 1642 'ext': 'mp4',
6368e2e6 1643 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
1644 'uploader': 'WiiLikeToPlay',
1645 'description': 'md5:563ccbc698b39298481ca3c571169519',
1646 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1647 'duration': 10120,
1648 'channel_follower_count': int,
1649 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1650 'availability': 'public',
1651 'playable_in_embed': True,
1652 'upload_date': '20131105',
1653 'uploader_id': 'WiiRikeToPray',
1654 'categories': ['Gaming'],
1655 'live_status': 'was_live',
1656 'tags': 'count:24',
1657 'release_timestamp': 1383701910,
1658 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1659 'comment_count': int,
1660 'age_limit': 0,
1661 'like_count': int,
1662 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1663 'channel': 'WiiLikeToPlay',
1664 'view_count': int,
1665 'release_date': '20131106',
cf7e015f
S
1666 },
1667 }, {
1668 'info_dict': {
6368e2e6 1669 'id': 'zaPI8MvL8pg',
cf7e015f 1670 'ext': 'mp4',
6368e2e6 1671 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
1672 'uploader_id': 'WiiRikeToPray',
1673 'availability': 'public',
1674 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1675 'channel': 'WiiLikeToPlay',
1676 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1677 'channel_follower_count': int,
1678 'description': 'md5:563ccbc698b39298481ca3c571169519',
1679 'duration': 10108,
1680 'age_limit': 0,
1681 'like_count': int,
1682 'tags': 'count:24',
1683 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1684 'uploader': 'WiiLikeToPlay',
1685 'release_timestamp': 1383701915,
1686 'comment_count': int,
1687 'upload_date': '20131105',
1688 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1689 'release_date': '20131106',
1690 'playable_in_embed': True,
1691 'live_status': 'was_live',
1692 'categories': ['Gaming'],
1693 'view_count': int,
cf7e015f
S
1694 },
1695 }, {
1696 'info_dict': {
6368e2e6 1697 'id': 'R7r3vfO7Hao',
cf7e015f 1698 'ext': 'mp4',
6368e2e6 1699 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1700 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1701 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1702 'like_count': int,
1703 'availability': 'public',
1704 'playable_in_embed': True,
1705 'upload_date': '20131105',
1706 'description': 'md5:563ccbc698b39298481ca3c571169519',
1707 'uploader_id': 'WiiRikeToPray',
1708 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1709 'channel_follower_count': int,
1710 'tags': 'count:24',
1711 'release_date': '20131106',
1712 'uploader': 'WiiLikeToPlay',
1713 'comment_count': int,
1714 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1715 'channel': 'WiiLikeToPlay',
1716 'categories': ['Gaming'],
1717 'release_timestamp': 1383701914,
1718 'live_status': 'was_live',
1719 'age_limit': 0,
1720 'duration': 10128,
1721 'view_count': int,
cf7e015f
S
1722 },
1723 }],
6368e2e6 1724 'params': {'skip_download': True},
cbaed4bb 1725 },
f9f49d87 1726 {
067aa17e 1727 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1728 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1729 'info_dict': {
1730 'id': 'gVfLd0zydlo',
1731 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1732 },
1733 'playlist_count': 2,
be49068d 1734 'skip': 'Not multifeed anymore',
f9f49d87 1735 },
cbaed4bb 1736 {
2d3d2997 1737 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1738 'only_matching': True,
0e49d9a6 1739 },
6d4fc66b 1740 {
2d3d2997 1741 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1742 'only_matching': True,
1743 },
0e49d9a6 1744 {
067aa17e 1745 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1746 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1747 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1748 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1749 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1750 'info_dict': {
1751 'id': 'lsguqyKfVQg',
1752 'ext': 'mp4',
1753 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1754 'alt_title': 'Dark Walk',
0e49d9a6 1755 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1756 'duration': 133,
0e49d9a6
LL
1757 'upload_date': '20151119',
1758 'uploader_id': 'IronSoulElf',
ec85ded8 1759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1760 'uploader': 'IronSoulElf',
11f9be09 1761 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1762 'track': 'Dark Walk',
1763 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1764 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1765 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1766 'categories': ['Film & Animation'],
1767 'view_count': int,
1768 'live_status': 'not_live',
1769 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1770 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1771 'tags': 'count:13',
1772 'availability': 'public',
1773 'channel': 'IronSoulElf',
1774 'playable_in_embed': True,
1775 'like_count': int,
1776 'age_limit': 0,
6c73052c 1777 'channel_follower_count': int
0e49d9a6
LL
1778 },
1779 'params': {
1780 'skip_download': True,
1781 },
1782 },
61f92af1 1783 {
067aa17e 1784 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1785 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1786 'only_matching': True,
1787 },
313dfc45
LL
1788 {
1789 # Video with yt:stretch=17:0
1790 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1791 'info_dict': {
1792 'id': 'Q39EVAstoRM',
1793 'ext': 'mp4',
1794 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1795 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1796 'upload_date': '20151107',
1797 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1798 'uploader': 'CH GAMER DROID',
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
be49068d 1803 'skip': 'This video does not exist.',
313dfc45 1804 },
201c1459 1805 {
1806 # Video with incomplete 'yt:stretch=16:'
1807 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1808 'only_matching': True,
1809 },
7caf9830
S
1810 {
1811 # Video licensed under Creative Commons
1812 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1813 'info_dict': {
1814 'id': 'M4gD1WSo5mA',
1815 'ext': 'mp4',
1816 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1817 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1818 'duration': 721,
17322130 1819 'upload_date': '20150128',
7caf9830 1820 'uploader_id': 'BerkmanCenter',
ec85ded8 1821 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1822 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1823 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1824 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1825 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1826 'like_count': int,
1827 'age_limit': 0,
1828 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1829 'channel': 'The Berkman Klein Center for Internet & Society',
1830 'availability': 'public',
1831 'view_count': int,
1832 'categories': ['Education'],
1833 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1834 'live_status': 'not_live',
1835 'playable_in_embed': True,
12a1b225 1836 'comment_count': int,
d5d1df8a 1837 'channel_follower_count': int,
1838 'chapters': list,
7caf9830
S
1839 },
1840 'params': {
1841 'skip_download': True,
1842 },
1843 },
fd050249
S
1844 {
1845 # Channel-like uploader_url
1846 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1847 'info_dict': {
1848 'id': 'eQcmzGIKrzg',
1849 'ext': 'mp4',
1850 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1851 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1852 'duration': 4060,
17322130 1853 'upload_date': '20151120',
eb6793ba 1854 'uploader': 'Bernie Sanders',
fd050249 1855 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1857 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1858 'playable_in_embed': True,
1859 'tags': 'count:12',
1860 'like_count': int,
1861 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1862 'age_limit': 0,
1863 'availability': 'public',
1864 'categories': ['News & Politics'],
1865 'channel': 'Bernie Sanders',
1866 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1867 'view_count': int,
1868 'live_status': 'not_live',
1869 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1870 'comment_count': int,
d5d1df8a 1871 'channel_follower_count': int,
1872 'chapters': list,
fd050249
S
1873 },
1874 'params': {
1875 'skip_download': True,
1876 },
1877 },
040ac686
S
1878 {
1879 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1880 'only_matching': True,
7f29cf54
S
1881 },
1882 {
067aa17e 1883 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1884 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1885 'only_matching': True,
6496ccb4
S
1886 },
1887 {
1888 # Rental video preview
1889 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1890 'info_dict': {
1891 'id': 'uGpuVWrhIzE',
1892 'ext': 'mp4',
1893 'title': 'Piku - Trailer',
1894 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1895 'upload_date': '20150811',
1896 'uploader': 'FlixMatrix',
1897 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1898 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1899 'license': 'Standard YouTube License',
1900 },
1901 'params': {
1902 'skip_download': True,
1903 },
eb6793ba 1904 'skip': 'This video is not available.',
022a5d66 1905 },
12afdc2a
S
1906 {
1907 # YouTube Red video with episode data
1908 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1909 'info_dict': {
1910 'id': 'iqKdEhx-dD4',
1911 'ext': 'mp4',
1912 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1913 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1914 'duration': 2085,
12afdc2a
S
1915 'upload_date': '20170118',
1916 'uploader': 'Vsauce',
1917 'uploader_id': 'Vsauce',
1918 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1919 'series': 'Mind Field',
1920 'season_number': 1,
1921 'episode_number': 1,
976ae3ea 1922 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1923 'tags': 'count:12',
1924 'view_count': int,
1925 'availability': 'public',
1926 'age_limit': 0,
1927 'channel': 'Vsauce',
1928 'episode': 'Episode 1',
1929 'categories': ['Entertainment'],
1930 'season': 'Season 1',
1931 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1932 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1933 'like_count': int,
1934 'playable_in_embed': True,
1935 'live_status': 'not_live',
6c73052c 1936 'channel_follower_count': int
12afdc2a
S
1937 },
1938 'params': {
1939 'skip_download': True,
1940 },
1941 'expected_warnings': [
1942 'Skipping DASH manifest',
1943 ],
1944 },
c7121fa7
S
1945 {
1946 # The following content has been identified by the YouTube community
1947 # as inappropriate or offensive to some audiences.
1948 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1949 'info_dict': {
1950 'id': '6SJNVb0GnPI',
1951 'ext': 'mp4',
1952 'title': 'Race Differences in Intelligence',
1953 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1954 'duration': 965,
1955 'upload_date': '20140124',
1956 'uploader': 'New Century Foundation',
1957 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1958 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1959 },
1960 'params': {
1961 'skip_download': True,
1962 },
545cc85d 1963 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1964 },
022a5d66
S
1965 {
1966 # itag 212
1967 'url': '1t24XAntNCY',
1968 'only_matching': True,
fd5c4aab
S
1969 },
1970 {
1971 # geo restricted to JP
1972 'url': 'sJL6WA-aGkQ',
1973 'only_matching': True,
1974 },
cd5a74a2
S
1975 {
1976 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1977 'only_matching': True,
1978 },
bc2ca1bb 1979 {
1980 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1981 'only_matching': True,
1982 },
1983 {
1984 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1985 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1986 'only_matching': True,
1987 },
825cd268
RA
1988 {
1989 # DRM protected
1990 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1991 'only_matching': True,
4fe54c12
S
1992 },
1993 {
1994 # Video with unsupported adaptive stream type formats
1995 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1996 'info_dict': {
1997 'id': 'Z4Vy8R84T1U',
1998 'ext': 'mp4',
1999 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2000 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2001 'duration': 433,
2002 'upload_date': '20130923',
2003 'uploader': 'Amelia Putri Harwita',
2004 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
2005 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
2006 'formats': 'maxcount:10',
2007 },
2008 'params': {
2009 'skip_download': True,
2010 'youtube_include_dash_manifest': False,
2011 },
5429d6a9 2012 'skip': 'not actual anymore',
5caabd3c 2013 },
2014 {
822b9d9c 2015 # Youtube Music Auto-generated description
5caabd3c 2016 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2017 'info_dict': {
2018 'id': 'MgNrAu2pzNs',
2019 'ext': 'mp4',
2020 'title': 'Voyeur Girl',
2021 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2022 'upload_date': '20190312',
5429d6a9
S
2023 'uploader': 'Stephen - Topic',
2024 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 2025 'artist': 'Stephen',
2026 'track': 'Voyeur Girl',
2027 'album': 'it\'s too much love to know my dear',
2028 'release_date': '20190313',
2029 'release_year': 2019,
976ae3ea 2030 'alt_title': 'Voyeur Girl',
2031 'view_count': int,
2032 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2033 'playable_in_embed': True,
2034 'like_count': int,
2035 'categories': ['Music'],
2036 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2037 'channel': 'Stephen',
2038 'availability': 'public',
2039 'creator': 'Stephen',
2040 'duration': 169,
2041 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2042 'age_limit': 0,
2043 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2044 'tags': 'count:11',
2045 'live_status': 'not_live',
6c73052c 2046 'channel_follower_count': int
5caabd3c 2047 },
2048 'params': {
2049 'skip_download': True,
2050 },
2051 },
66b48727
RA
2052 {
2053 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2054 'only_matching': True,
2055 },
011e75e6
S
2056 {
2057 # invalid -> valid video id redirection
2058 'url': 'DJztXj2GPfl',
2059 'info_dict': {
2060 'id': 'DJztXj2GPfk',
2061 'ext': 'mp4',
2062 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2063 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2064 'upload_date': '20090125',
2065 'uploader': 'Prochorowka',
2066 'uploader_id': 'Prochorowka',
2067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
2068 'artist': 'Panjabi MC',
2069 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2070 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2071 },
2072 'params': {
2073 'skip_download': True,
2074 },
545cc85d 2075 'skip': 'Video unavailable',
ea74e00b
DP
2076 },
2077 {
2078 # empty description results in an empty string
2079 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2080 'info_dict': {
2081 'id': 'x41yOUIvK2k',
2082 'ext': 'mp4',
2083 'title': 'IMG 3456',
2084 'description': '',
2085 'upload_date': '20170613',
2086 'uploader_id': 'ElevageOrVert',
2087 'uploader': 'ElevageOrVert',
976ae3ea 2088 'view_count': int,
2089 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2090 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2091 'like_count': int,
2092 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2093 'tags': [],
2094 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2095 'availability': 'public',
2096 'age_limit': 0,
2097 'categories': ['Pets & Animals'],
2098 'duration': 7,
2099 'playable_in_embed': True,
2100 'live_status': 'not_live',
2101 'channel': 'ElevageOrVert',
6c73052c 2102 'channel_follower_count': int
ea74e00b
DP
2103 },
2104 'params': {
2105 'skip_download': True,
2106 },
2107 },
a0566bbf 2108 {
29f7c58a 2109 # with '};' inside yt initial data (see [1])
2110 # see [2] for an example with '};' inside ytInitialPlayerResponse
2111 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2112 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2113 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2114 'info_dict': {
2115 'id': 'CHqg6qOn4no',
2116 'ext': 'mp4',
2117 'title': 'Part 77 Sort a list of simple types in c#',
2118 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2119 'upload_date': '20130831',
2120 'uploader_id': 'kudvenkat',
2121 'uploader': 'kudvenkat',
976ae3ea 2122 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2123 'like_count': int,
2124 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2125 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2126 'live_status': 'not_live',
2127 'categories': ['Education'],
2128 'availability': 'public',
2129 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2130 'tags': 'count:12',
2131 'playable_in_embed': True,
2132 'age_limit': 0,
2133 'view_count': int,
2134 'duration': 522,
2135 'channel': 'kudvenkat',
12a1b225 2136 'comment_count': int,
d5d1df8a 2137 'channel_follower_count': int,
2138 'chapters': list,
a0566bbf 2139 },
2140 'params': {
2141 'skip_download': True,
2142 },
2143 },
29f7c58a 2144 {
2145 # another example of '};' in ytInitialData
2146 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2147 'only_matching': True,
2148 },
2149 {
2150 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2151 'only_matching': True,
2152 },
545cc85d 2153 {
cc2db878 2154 # https://github.com/ytdl-org/youtube-dl/pull/28094
2155 'url': 'OtqTfy26tG0',
2156 'info_dict': {
2157 'id': 'OtqTfy26tG0',
2158 'ext': 'mp4',
2159 'title': 'Burn Out',
2160 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2161 'upload_date': '20141120',
2162 'uploader': 'The Cinematic Orchestra - Topic',
2163 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2164 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2165 'artist': 'The Cinematic Orchestra',
2166 'track': 'Burn Out',
2167 'album': 'Every Day',
976ae3ea 2168 'like_count': int,
2169 'live_status': 'not_live',
2170 'alt_title': 'Burn Out',
2171 'duration': 614,
2172 'age_limit': 0,
2173 'view_count': int,
2174 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2175 'creator': 'The Cinematic Orchestra',
2176 'channel': 'The Cinematic Orchestra',
2177 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2178 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2179 'availability': 'public',
2180 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2181 'categories': ['Music'],
2182 'playable_in_embed': True,
6c73052c 2183 'channel_follower_count': int
cc2db878 2184 },
2185 'params': {
2186 'skip_download': True,
2187 },
545cc85d 2188 },
bc2ca1bb 2189 {
2190 # controversial video, only works with bpctr when authenticated with cookies
2191 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2192 'only_matching': True,
2193 },
a1a7907b 2194 {
2195 # controversial video, requires bpctr/contentCheckOk
2196 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2197 'info_dict': {
2198 'id': 'SZJvDhaSDnc',
2199 'ext': 'mp4',
2200 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2201 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 2202 'uploader': 'CBS Mornings',
11f9be09 2203 'uploader_id': 'CBSThisMorning',
a1a7907b 2204 'upload_date': '20140716',
976ae3ea 2205 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2206 'duration': 170,
2207 'categories': ['News & Politics'],
2208 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2209 'view_count': int,
2210 'channel': 'CBS Mornings',
2211 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2212 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2213 'age_limit': 18,
2214 'availability': 'needs_auth',
2215 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2216 'like_count': int,
2217 'live_status': 'not_live',
2218 'playable_in_embed': True,
6c73052c 2219 'channel_follower_count': int
a1a7907b 2220 }
2221 },
f7ad7160 2222 {
2223 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2224 'url': 'cBvYw8_A0vQ',
2225 'info_dict': {
2226 'id': 'cBvYw8_A0vQ',
2227 'ext': 'mp4',
2228 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2229 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2230 'upload_date': '20201120',
2231 'uploader': 'Walk around Japan',
2232 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2233 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2234 'duration': 1456,
2235 'categories': ['Travel & Events'],
2236 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2237 'view_count': int,
2238 'channel': 'Walk around Japan',
2239 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2240 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2241 'age_limit': 0,
2242 'availability': 'public',
2243 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2244 'live_status': 'not_live',
2245 'playable_in_embed': True,
6c73052c 2246 'channel_follower_count': int
f7ad7160 2247 },
2248 'params': {
2249 'skip_download': True,
2250 },
0fb983f6 2251 }, {
2252 # Has multiple audio streams
2253 'url': 'WaOKSUlf4TM',
2254 'only_matching': True
9297939e 2255 }, {
2256 # Requires Premium: has format 141 when requested using YTM url
2257 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2258 'only_matching': True
2259 }, {
120916da 2260 # multiple subtitles with same lang_code
2261 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2262 'only_matching': True,
109dd3b2 2263 }, {
2264 # Force use android client fallback
2265 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2266 'info_dict': {
2267 'id': 'YOelRv7fMxY',
11f9be09 2268 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2269 'ext': '3gp',
2270 'upload_date': '20210624',
2271 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2272 'uploader': 'colinfurze',
11f9be09 2273 'uploader_id': 'colinfurze',
109dd3b2 2274 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2275 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2276 'duration': 596,
2277 'categories': ['Entertainment'],
2278 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2279 'view_count': int,
2280 'channel': 'colinfurze',
2281 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2282 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2283 'age_limit': 0,
2284 'availability': 'public',
2285 'like_count': int,
2286 'live_status': 'not_live',
2287 'playable_in_embed': True,
d5d1df8a 2288 'channel_follower_count': int,
2289 'chapters': list,
109dd3b2 2290 },
2291 'params': {
2292 'format': '17', # 3gp format available on android
2293 'extractor_args': {'youtube': {'player_client': ['android']}},
2294 },
120916da 2295 },
109dd3b2 2296 {
2297 # Skip download of additional client configs (remix client config in this case)
2298 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2299 'only_matching': True,
2300 'params': {
2301 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2302 },
8fc54b12 2303 }, {
2304 # shorts
2305 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2306 'only_matching': True,
9222c381 2307 }, {
2308 'note': 'Storyboards',
2309 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2310 'info_dict': {
2311 'id': '5KLPxDtMqe8',
2312 'ext': 'mhtml',
2313 'format_id': 'sb0',
2314 'title': 'Your Brain is Plastic',
2315 'uploader_id': 'scishow',
2316 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2317 'upload_date': '20140324',
2318 'uploader': 'SciShow',
976ae3ea 2319 'like_count': int,
2320 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2321 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2322 'view_count': int,
2323 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2324 'playable_in_embed': True,
2325 'tags': 'count:12',
2326 'uploader_url': 'http://www.youtube.com/user/scishow',
2327 'availability': 'public',
2328 'channel': 'SciShow',
2329 'live_status': 'not_live',
2330 'duration': 248,
2331 'categories': ['Education'],
2332 'age_limit': 0,
d5d1df8a 2333 'channel_follower_count': int,
2334 'chapters': list,
9222c381 2335 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2336 }, {
2337 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2338 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2339 'info_dict': {
2340 'id': '2NUZ8W2llS4',
2341 'ext': 'mp4',
2342 'title': 'The NP that test your phone performance 🙂',
2343 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2344 'uploader': 'Leon Nguyen',
2345 'uploader_id': 'VNSXIII',
2346 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2347 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2348 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2349 'duration': 21,
2350 'view_count': int,
2351 'age_limit': 0,
2352 'categories': ['Gaming'],
2353 'tags': 'count:23',
2354 'playable_in_embed': True,
2355 'live_status': 'not_live',
2356 'upload_date': '20220103',
2357 'like_count': int,
2358 'availability': 'public',
2359 'channel': 'Leon Nguyen',
2360 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2361 'comment_count': int,
992f9a73 2362 'channel_follower_count': int
2363 }
1ff88b7a 2364 }, {
2365 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2366 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2367 'info_dict': {
2368 'id': '2NUZ8W2llS4',
2369 'ext': 'mp4',
2370 'title': 'The NP that test your phone performance 🙂',
2371 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2372 'uploader': 'Leon Nguyen',
2373 'uploader_id': 'VNSXIII',
2374 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2375 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2376 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2377 'duration': 21,
2378 'view_count': int,
2379 'age_limit': 0,
2380 'categories': ['Gaming'],
2381 'tags': 'count:23',
2382 'playable_in_embed': True,
2383 'live_status': 'not_live',
2384 'upload_date': '20220102',
2385 'like_count': int,
2386 'availability': 'public',
2387 'channel': 'Leon Nguyen',
2388 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2389 'comment_count': int,
2390 'channel_follower_count': int
2391 },
2392 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2393 }, {
2394 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2395 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2396 'info_dict': {
2397 'id': 'mzZzzBU6lrM',
2398 'ext': 'mp4',
2399 'title': 'I Met GeorgeNotFound In Real Life...',
2400 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2401 'uploader': 'Quackity',
2402 'uploader_id': 'QuackityHQ',
2403 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2404 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2405 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2406 'duration': 955,
2407 'view_count': int,
2408 'age_limit': 0,
2409 'categories': ['Entertainment'],
2410 'tags': 'count:26',
2411 'playable_in_embed': True,
2412 'live_status': 'not_live',
2413 'release_timestamp': 1641172509,
2414 'release_date': '20220103',
2415 'upload_date': '20220103',
2416 'like_count': int,
2417 'availability': 'public',
2418 'channel': 'Quackity',
2419 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2420 'channel_follower_count': int
2421 }
2422 },
2423 { # continuous livestream. Microformat upload date should be preferred.
2424 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2425 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2426 'info_dict': {
2427 'id': 'kgx4WGK0oNU',
2428 '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}',
2429 'ext': 'mp4',
2430 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2431 'availability': 'public',
2432 'age_limit': 0,
2433 'release_timestamp': 1637975704,
2434 'upload_date': '20210619',
2435 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2436 'live_status': 'is_live',
2437 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2438 'uploader': '阿鲍Abao',
2439 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2440 'channel': 'Abao in Tokyo',
2441 'channel_follower_count': int,
2442 'release_date': '20211127',
2443 'tags': 'count:39',
2444 'categories': ['People & Blogs'],
2445 'like_count': int,
2446 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2447 'view_count': int,
2448 'playable_in_embed': True,
2449 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2450 'concurrent_view_count': int,
992f9a73 2451 },
2452 'params': {'skip_download': True}
6e634cbe 2453 }, {
2454 # Story. Requires specific player params to work.
ee27297f 2455 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2456 'info_dict': {
ee27297f 2457 'id': 'vv8qTUWmulI',
6e634cbe 2458 'ext': 'mp4',
ee27297f 2459 'availability': 'unlisted',
2460 'view_count': int,
2461 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2462 'upload_date': '20220526',
2463 'categories': ['Education'],
2464 'title': 'Story',
2465 'channel': 'IT\'S HISTORY',
2466 'description': '',
2467 'uploader_id': 'BlastfromthePast',
2468 'duration': 12,
2469 'uploader': 'IT\'S HISTORY',
6e634cbe 2470 'playable_in_embed': True,
6e634cbe 2471 'age_limit': 0,
6e634cbe 2472 'live_status': 'not_live',
ee27297f 2473 'tags': [],
2474 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2475 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2476 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2477 },
2478 'skip': 'stories get removed after some period of time',
ee27297f 2479 }, {
2480 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2481 'info_dict': {
2482 'id': 'tjjjtzRLHvA',
2483 'ext': 'mp4',
2484 'title': 'ハッシュタグ無し };if window.ytcsi',
2485 'upload_date': '20220323',
2486 'like_count': int,
2487 'availability': 'unlisted',
2488 'channel': 'nao20010128nao',
2489 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2490 'age_limit': 0,
2491 'uploader': 'nao20010128nao',
2492 'uploader_id': 'nao20010128nao',
2493 'categories': ['Music'],
6e634cbe 2494 'view_count': int,
2495 'description': '',
ee27297f 2496 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2497 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2498 'live_status': 'not_live',
2499 'playable_in_embed': True,
2500 'channel_follower_count': int,
2501 'duration': 6,
2502 'tags': [],
2503 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2504 }
c26f9b99 2505 }, {
2506 # Prefer primary title+description language metadata by default
2507 # Do not prefer translated description if primary is empty
2508 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2509 'info_dict': {
2510 'id': 'el3E4MbxRqQ',
2511 'ext': 'mp4',
2512 'title': 'dlp test video 2 - primary sv no desc',
2513 'description': '',
2514 'channel': 'cole-dlp-test-acc',
2515 'tags': [],
2516 'view_count': int,
2517 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2518 'like_count': int,
2519 'playable_in_embed': True,
2520 'availability': 'unlisted',
2521 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2522 'age_limit': 0,
2523 'duration': 5,
2524 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2525 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2526 'live_status': 'not_live',
2527 'upload_date': '20220908',
2528 'categories': ['People & Blogs'],
2529 'uploader': 'cole-dlp-test-acc',
2530 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2531 },
2532 'params': {'skip_download': True}
2533 }, {
2534 # Extractor argument: prefer translated title+description
2535 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2536 'info_dict': {
2537 'id': 'gHKT4uU8Zng',
2538 'ext': 'mp4',
2539 'channel': 'cole-dlp-test-acc',
2540 'tags': [],
2541 'duration': 5,
2542 'live_status': 'not_live',
2543 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2544 'upload_date': '20220728',
2545 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2546 'view_count': int,
2547 'categories': ['People & Blogs'],
2548 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2549 'title': 'dlp test video title translated (fr)',
2550 'availability': 'public',
2551 'uploader': 'cole-dlp-test-acc',
2552 'age_limit': 0,
2553 'description': 'dlp test video description translated (fr)',
2554 'playable_in_embed': True,
2555 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2556 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2557 },
2558 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2559 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2560 }, {
2561 'note': '6 channel audio',
2562 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2563 'only_matching': True,
a4894d3e 2564 }, {
2565 'note': 'Multiple HLS formats with same itag',
2566 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2567 'info_dict': {
2568 'id': 'kX3nB4PpJko',
2569 'ext': 'mp4',
2570 'categories': ['Entertainment'],
2571 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
2572 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
2573 'live_status': 'not_live',
2574 'duration': 937,
2575 'channel_follower_count': int,
2576 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2577 'title': 'Last To Take Hand Off Jet, Keeps It!',
2578 'channel': 'MrBeast',
2579 'playable_in_embed': True,
2580 'view_count': int,
2581 'upload_date': '20221112',
2582 'uploader': 'MrBeast',
2583 'uploader_id': 'MrBeast6000',
2584 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2585 'age_limit': 0,
2586 'availability': 'public',
2587 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2588 'like_count': int,
2589 'tags': [],
2590 },
2591 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2592 }, {
2593 'note': 'Audio formats with Dynamic Range Compression',
2594 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2595 'info_dict': {
2596 'id': 'Tq92D6wQ1mg',
2597 'ext': 'weba',
2598 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2599 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2600 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2601 'channel_follower_count': int,
2602 'description': 'md5:17eccca93a786d51bc67646756894066',
2603 'upload_date': '20191228',
2604 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2605 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2606 'playable_in_embed': True,
2607 'like_count': int,
2608 'categories': ['Entertainment'],
2609 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2610 'age_limit': 18,
2611 'channel': 'Projekt Melody',
2612 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2613 'view_count': int,
2614 'availability': 'needs_auth',
2615 'comment_count': int,
2616 'live_status': 'not_live',
2617 'uploader': 'Projekt Melody',
2618 'duration': 106,
2619 },
2620 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2621 },
2622 {
2623 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2624 'info_dict': {
2625 'id': 'qVv6vCqciTM',
2626 'ext': 'mp4',
2627 'age_limit': 0,
2628 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2629 'comment_count': int,
2630 'chapters': 'count:13',
2631 'upload_date': '20221223',
2632 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2633 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2634 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2635 'like_count': int,
2636 'release_date': '20221223',
2637 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2638 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
2639 'view_count': int,
2640 'playable_in_embed': True,
2641 'duration': 4438,
2642 'availability': 'public',
2643 'channel_follower_count': int,
2644 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2645 'categories': ['Entertainment'],
2646 'live_status': 'was_live',
2647 'release_timestamp': 1671793345,
2648 'channel': 'さなちゃんねる',
2649 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2650 'uploader': 'さなちゃんねる',
2651 },
2652 },
2eb88d95
PH
2653 ]
2654
f2e8dbcc 2655 _WEBPAGE_TESTS = [
2656 # YouTube <object> embed
2657 {
2658 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2659 'md5': '873c81d308b979f0e23ee7e620b312a3',
2660 'info_dict': {
2661 'id': 'msN87y-iEx0',
2662 'ext': 'mp4',
2663 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2664 'upload_date': '20080526',
2665 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2666 'uploader': 'Christopher Sykes',
2667 'uploader_id': 'ChristopherJSykes',
2668 'age_limit': 0,
2669 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2670 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2671 'playable_in_embed': True,
2672 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2673 'like_count': int,
2674 'comment_count': int,
2675 'channel': 'Christopher Sykes',
2676 'live_status': 'not_live',
2677 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2678 'availability': 'public',
2679 'duration': 195,
2680 'view_count': int,
2681 'categories': ['Science & Technology'],
2682 'channel_follower_count': int,
2683 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2684 },
2685 'params': {
2686 'skip_download': True,
2687 }
2688 },
2689 ]
2690
201c1459 2691 @classmethod
2692 def suitable(cls, url):
4dfbf869 2693 from ..utils import parse_qs
2694
201c1459 2695 qs = parse_qs(url)
2696 if qs.get('list', [None])[0]:
2697 return False
86e5f3ed 2698 return super().suitable(url)
201c1459 2699
e0df6211 2700 def __init__(self, *args, **kwargs):
86e5f3ed 2701 super().__init__(*args, **kwargs)
545cc85d 2702 self._code_cache = {}
83799698 2703 self._player_cache = {}
e0df6211 2704
4d37720a 2705 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2706 lock = threading.Lock()
185bf310 2707 start_time = time.time()
adbc4ec4
THD
2708 formats = [f for f in formats if f.get('is_from_start')]
2709
185bf310 2710 def refetch_manifest(format_id, delay):
2711 nonlocal formats, start_time, is_live
2712 if time.time() <= start_time + delay:
adbc4ec4
THD
2713 return
2714
2715 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2716 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2717 microformats = traverse_obj(
2718 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2719 expected_type=dict)
4d37720a
L
2720 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2721 is_live = live_status == 'is_live'
185bf310 2722 start_time = time.time()
adbc4ec4 2723
185bf310 2724 def mpd_feed(format_id, delay):
adbc4ec4
THD
2725 """
2726 @returns (manifest_url, manifest_stream_number, is_live) or None
2727 """
253ac4ba 2728 for retry in self.RetryManager(fatal=False):
2729 with lock:
2730 refetch_manifest(format_id, delay)
2731
2732 f = next((f for f in formats if f['format_id'] == format_id), None)
2733 if not f:
2734 if not is_live:
2735 retry.error = f'{video_id}: Video is no longer live'
2736 else:
2737 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2738 continue
2739 return f['manifest_url'], f['manifest_stream_number'], is_live
2740 return None
adbc4ec4
THD
2741
2742 for f in formats:
4d37720a
L
2743 f['is_live'] = is_live
2744 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2745 live_start_time, mpd_feed, not is_live and f.copy())
2746 if is_live:
2747 f['fragments'] = gen
2748 f['protocol'] = 'http_dash_segments_generator'
2749 else:
2750 f['fragments'] = LazyList(gen({}))
2751 del f['is_from_start']
adbc4ec4 2752
4d37720a 2753 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2754 FETCH_SPAN, MAX_DURATION = 5, 432000
2755
2756 mpd_url, stream_number, is_live = None, None, True
2757
2758 begin_index = 0
2759 download_start_time = ctx.get('start') or time.time()
2760
2761 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2762 if lack_early_segments:
2763 self.report_warning(bug_reports_message(
2764 'Starting download from the last 120 hours of the live stream since '
2765 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2766 lack_early_segments = True
2767
2768 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2769 fragments, fragment_base_url = None, None
2770
a539f065 2771 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2772 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2773 # Obtain from MPD's maximum seq value
2774 old_mpd_url = mpd_url
185bf310 2775 last_error = ctx.pop('last_error', None)
14f25df2 2776 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2777 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2778 or (mpd_url, stream_number, False))
2779 if not refresh_sequence:
2780 if expire_fast and not is_live:
2781 return False, last_seq
2782 elif old_mpd_url == mpd_url:
2783 return True, last_seq
4d37720a
L
2784 if manifestless_orig_fmt:
2785 fmt_info = manifestless_orig_fmt
2786 else:
2787 try:
2788 fmts, _ = self._extract_mpd_formats_and_subtitles(
2789 mpd_url, None, note=False, errnote=False, fatal=False)
2790 except ExtractorError:
2791 fmts = None
2792 if not fmts:
2793 no_fragment_score += 2
2794 return False, last_seq
2795 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2796 fragments = fmt_info['fragments']
2797 fragment_base_url = fmt_info['fragment_base_url']
2798 assert fragment_base_url
2799
2800 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2801 return True, _last_seq
2802
4d37720a 2803 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2804 while is_live:
2805 fetch_time = time.time()
2806 if no_fragment_score > 30:
2807 return
2808 if last_segment_url:
2809 # Obtain from "X-Head-Seqnum" header value from each segment
2810 try:
2811 urlh = self._request_webpage(
2812 last_segment_url, None, note=False, errnote=False, fatal=False)
2813 except ExtractorError:
2814 urlh = None
2815 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2816 if last_seq is None:
a539f065 2817 no_fragment_score += 2
adbc4ec4
THD
2818 last_segment_url = None
2819 continue
2820 else:
a539f065
LNO
2821 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2822 no_fragment_score += 2
185bf310 2823 if not should_continue:
adbc4ec4
THD
2824 continue
2825
2826 if known_idx > last_seq:
2827 last_segment_url = None
2828 continue
2829
2830 last_seq += 1
2831
2832 if begin_index < 0 and known_idx < 0:
2833 # skip from the start when it's negative value
2834 known_idx = last_seq + begin_index
2835 if lack_early_segments:
2836 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2837 try:
2838 for idx in range(known_idx, last_seq):
2839 # do not update sequence here or you'll get skipped some part of it
a539f065 2840 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2841 if not should_continue:
adbc4ec4
THD
2842 known_idx = idx - 1
2843 raise ExtractorError('breaking out of outer loop')
2844 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2845 yield {
2846 'url': last_segment_url,
36195c44 2847 'fragment_count': last_seq,
adbc4ec4
THD
2848 }
2849 if known_idx == last_seq:
2850 no_fragment_score += 5
2851 else:
2852 no_fragment_score = 0
2853 known_idx = last_seq
2854 except ExtractorError:
2855 continue
2856
4d37720a
L
2857 if manifestless_orig_fmt:
2858 # Stop at the first iteration if running for post-live manifestless;
2859 # fragment count no longer increase since it starts
2860 break
2861
adbc4ec4
THD
2862 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2863
b6de707d 2864 def _extract_player_url(self, *ytcfgs, webpage=None):
2865 player_url = traverse_obj(
2866 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2867 get_all=False, expected_type=str)
11f9be09 2868 if not player_url:
b6de707d 2869 return
60f393e4 2870 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2871
b6de707d 2872 def _download_player_url(self, video_id, fatal=False):
2873 res = self._download_webpage(
2874 'https://www.youtube.com/iframe_api',
2875 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2876 if res:
2877 player_version = self._search_regex(
2878 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2879 if player_version:
2880 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2881
60064c53
PH
2882 def _signature_cache_id(self, example_sig):
2883 """ Return a string representation of a signature """
14f25df2 2884 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2885
e40c758c
S
2886 @classmethod
2887 def _extract_player_info(cls, player_url):
2888 for player_re in cls._PLAYER_INFO_RE:
2889 id_m = re.search(player_re, player_url)
2890 if id_m:
2891 break
2892 else:
c081b35c 2893 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2894 return id_m.group('id')
e40c758c 2895
404f611f 2896 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2897 player_id = self._extract_player_info(player_url)
2898 if player_id not in self._code_cache:
1276a43a 2899 code = self._download_webpage(
109dd3b2 2900 player_url, video_id, fatal=fatal,
2901 note='Downloading player ' + player_id,
2902 errnote='Download of %s failed' % player_url)
1276a43a 2903 if code:
2904 self._code_cache[player_id] = code
404f611f 2905 return self._code_cache.get(player_id)
109dd3b2 2906
e40c758c 2907 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2908 player_id = self._extract_player_info(player_url)
e0df6211 2909
c4417ddb 2910 # Read from filesystem cache
86e5f3ed 2911 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2912 assert os.path.basename(func_id) == func_id
a0e07d31 2913
ae61d108 2914 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2915 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2916
580ce007 2917 if not cache_spec:
2918 code = self._load_player(video_id, player_url)
404f611f 2919 if code:
109dd3b2 2920 res = self._parse_sig_js(code)
ac668111 2921 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2922 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2923 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2924
2925 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2926
60064c53 2927 def _print_sig_code(self, func, example_sig):
404f611f 2928 if not self.get_param('youtube_print_sig_code'):
2929 return
2930
edf3e38e
PH
2931 def gen_sig_code(idxs):
2932 def _genslice(start, end, step):
78caa52a 2933 starts = '' if start == 0 else str(start)
8bcc8756 2934 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2935 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2936 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2937
2938 step = None
7af808a5
PH
2939 # Quelch pyflakes warnings - start will be set when step is set
2940 start = '(Never used)'
edf3e38e
PH
2941 for i, prev in zip(idxs[1:], idxs[:-1]):
2942 if step is not None:
2943 if i - prev == step:
2944 continue
2945 yield _genslice(start, prev, step)
2946 step = None
2947 continue
2948 if i - prev in [-1, 1]:
2949 step = i - prev
2950 start = prev
2951 continue
2952 else:
78caa52a 2953 yield 's[%d]' % prev
edf3e38e 2954 if step is None:
78caa52a 2955 yield 's[%d]' % i
edf3e38e
PH
2956 else:
2957 yield _genslice(start, i, step)
2958
ac668111 2959 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2960 cache_res = func(test_string)
edf3e38e 2961 cache_spec = [ord(c) for c in cache_res]
78caa52a 2962 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2963 signature_id_tuple = '(%s)' % (
14f25df2 2964 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2965 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2966 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2967 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2968
e0df6211
PH
2969 def _parse_sig_js(self, jscode):
2970 funcname = self._search_regex(
abefc03f
S
2971 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2972 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
2973 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2974 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2975 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}\(a,\d+\)',
2976 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 2977 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2978 # Obsolete patterns
2979 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2980 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2981 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2982 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2983 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2984 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2985 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2986 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2987 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2988
2989 jsi = JSInterpreter(jscode)
2990 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2991 return lambda s: initial_function([s])
2992
580ce007 2993 def _cached(self, func, *cache_id):
2994 def inner(*args, **kwargs):
2995 if cache_id not in self._player_cache:
2996 try:
2997 self._player_cache[cache_id] = func(*args, **kwargs)
2998 except ExtractorError as e:
2999 self._player_cache[cache_id] = e
3000 except Exception as e:
3001 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3002
3003 ret = self._player_cache[cache_id]
3004 if isinstance(ret, Exception):
3005 raise ret
3006 return ret
3007 return inner
3008
545cc85d 3009 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3010 """Turn the encrypted s field into a working signature"""
580ce007 3011 extract_sig = self._cached(
3012 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3013 func = extract_sig(video_id, player_url, s)
3014 self._print_sig_code(func, s)
3015 return func(s)
404f611f 3016
3017 def _decrypt_nsig(self, s, video_id, player_url):
3018 """Turn the encrypted n field into a working signature"""
3019 if player_url is None:
3020 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3021 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3022
b505e851 3023 try:
3024 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3025 except ExtractorError as e:
3026 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3027 if self.get_param('youtube_print_sig_code'):
3028 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3029
25836db6 3030 try:
3031 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3032 ret = extract_nsig(jsi, func_code)(s)
3033 except JSInterpreter.Exception as e:
3034 try:
992dc6b4 3035 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3036 except ExtractorError:
3037 raise e
3038 self.report_warning(
3039 f'Native nsig extraction failed: Trying with PhantomJS\n'
3040 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3041 self.write_debug(e, only_once=True)
25836db6 3042
3043 args, func_body = func_code
3044 ret = jsi.execute(
3045 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3046 video_id=video_id, note='Executing signature code').strip()
580ce007 3047
3048 self.write_debug(f'Decrypted nsig {s} => {ret}')
3049 return ret
3050
90a1df30 3051 def _extract_n_function_name(self, jscode):
3052 funcname, idx = self._search_regex(
3053 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3054 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3055 if not idx:
3056 return funcname
3057
3058 return json.loads(js_to_json(self._search_regex(
3059 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3060 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3061
580ce007 3062 def _extract_n_function_code(self, video_id, player_url):
404f611f 3063 player_id = self._extract_player_info(player_url)
05deb747 3064 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3065 jscode = func_code or self._load_player(video_id, player_url)
3066 jsi = JSInterpreter(jscode)
404f611f 3067
3068 if func_code:
580ce007 3069 return jsi, player_id, func_code
404f611f 3070
b505e851 3071 func_name = self._extract_n_function_name(jscode)
3072
3073 # For redundancy
3074 func_code = self._search_regex(
3075 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3076 # NB: The end of the regex is intentionally kept strict
3077 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3078 jscode, 'nsig function', group=('var', 'code'), default=None)
3079 if func_code:
3080 func_code = ([func_code[0]], func_code[1])
3081 else:
3082 self.write_debug('Extracting nsig function with jsinterp')
3083 func_code = jsi.extract_function_code(func_name)
3084
580ce007 3085 self.cache.store('youtube-nsig', player_id, func_code)
3086 return jsi, player_id, func_code
3087
3088 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3089 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3090
580ce007 3091 def extract_nsig(s):
25836db6 3092 try:
3093 ret = func([s])
3094 except JSInterpreter.Exception:
3095 raise
3096 except Exception as e:
3097 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3098
f6ca640b 3099 if ret.startswith('enhanced_except_'):
25836db6 3100 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3101 return ret
580ce007 3102
3103 return extract_nsig
e0df6211 3104
109dd3b2 3105 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3106 """
3107 Extract signatureTimestamp (sts)
3108 Required to tell API what sig/player version is in use.
3109 """
3110 sts = None
3111 if isinstance(ytcfg, dict):
3112 sts = int_or_none(ytcfg.get('STS'))
3113
3114 if not sts:
3115 # Attempt to extract from player
3116 if player_url is None:
3117 error_msg = 'Cannot extract signature timestamp without player_url.'
3118 if fatal:
3119 raise ExtractorError(error_msg)
3120 self.report_warning(error_msg)
3121 return
404f611f 3122 code = self._load_player(video_id, player_url, fatal=fatal)
3123 if code:
109dd3b2 3124 sts = int_or_none(self._search_regex(
3125 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3126 'JS player signature timestamp', group='sts', fatal=fatal))
3127 return sts
3128
11f9be09 3129 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3130 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3131 label = 'fully ' if is_full else ''
3132 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3133 expected_type=url_or_none)
3134 if not url:
3135 self.report_warning(f'Unable to mark {label}watched')
3136 return
14f25df2 3137 parsed_url = urllib.parse.urlparse(url)
3138 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3139
3140 # cpn generation algorithm is reverse engineered from base.js.
3141 # In fact it works even with dummy cpn.
3142 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3143 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3144
3145 # # more consistent results setting it to right before the end
3146 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3147
3148 qs.update({
3149 'ver': ['2'],
3150 'cpn': [cpn],
3151 'cmt': video_length,
3152 'el': 'detailpage', # otherwise defaults to "shorts"
3153 })
3154
3155 if is_full:
3156 # these seem to mark watchtime "history" in the real world
3157 # they're required, so send in a single value
3158 qs.update({
5318156f 3159 'st': 0,
06cc8f10
B
3160 'et': video_length,
3161 })
3162
14f25df2 3163 url = urllib.parse.urlunparse(
3164 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3165
3166 self._download_webpage(
3167 url, video_id, f'Marking {label}watched',
3168 'Unable to mark watched', fatal=False)
d77ab8e2 3169
bfd973ec 3170 @classmethod
3171 def _extract_from_webpage(cls, url, webpage):
3172 # Invidious Instances
3173 # https://github.com/yt-dlp/yt-dlp/issues/195
3174 # https://github.com/iv-org/invidious/pull/1730
3175 mobj = re.search(
3176 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3177 webpage)
3178 if mobj:
3179 yield cls.url_result(mobj.group('url'), cls)
3180 raise cls.StopExtraction()
3181
3182 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3183
3184 # lazyYT YouTube embed
bfd973ec 3185 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3186 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3187
3188 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3189 for m in re.findall(r'''(?x)<div[^>]+
3190 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3191 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3192 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3193
97665381
PH
3194 @classmethod
3195 def extract_id(cls, url):
ae61d108 3196 video_id = cls.get_temp_id(url)
3197 if not video_id:
3198 raise ExtractorError(f'Invalid URL: {url}')
3199 return video_id
c5e8d7af 3200
7c365c21 3201 def _extract_chapters_from_json(self, data, duration):
3202 chapter_list = traverse_obj(
3203 data, (
3204 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3205 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3206 ), expected_type=list)
3207
3208 return self._extract_chapters(
3209 chapter_list,
3210 chapter_time=lambda chapter: float_or_none(
3211 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3212 chapter_title=lambda chapter: traverse_obj(
3213 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3214 duration=duration)
3215
3216 def _extract_chapters_from_engagement_panel(self, data, duration):
3217 content_list = traverse_obj(
8bdd16b4 3218 data,
7c365c21 3219 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3220 expected_type=list)
052e1350 3221 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3222 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3223
1890fc63 3224 return next(filter(None, (
3225 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3226 chapter_time, chapter_title, duration)
3227 for contents in content_list)), [])
7c365c21 3228
1890fc63 3229 def _extract_chapters_from_description(self, description, duration):
2e30b46f 3230 duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
3231 sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
1890fc63 3232 return self._extract_chapters(
2e30b46f 3233 re.findall(sep_re % (duration_re, r'.+?'), description or ''),
1890fc63 3234 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2e30b46f 3235 duration=duration, strict=False) or self._extract_chapters(
3236 re.findall(sep_re % (r'.+?', duration_re), description or ''),
3237 chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
1890fc63 3238 duration=duration, strict=False)
84213ea8 3239
1890fc63 3240 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3241 if not duration:
3242 return
3243 chapter_list = [{
3244 'start_time': chapter_time(chapter),
3245 'title': chapter_title(chapter),
3246 } for chapter in chapter_list or []]
3247 if not strict:
3248 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3249
a3976e07 3250 chapters = [{'start_time': 0}]
1890fc63 3251 for idx, chapter in enumerate(chapter_list):
a3976e07 3252 if chapter['start_time'] is None:
1890fc63 3253 self.report_warning(f'Incomplete chapter {idx}')
3254 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 3255 chapters.append(chapter)
709ee214 3256 elif chapter not in chapters:
3257 self.report_warning(
3258 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
a3976e07 3259 return chapters[1:]
84213ea8 3260
a1c5d2ca
M
3261 def _extract_comment(self, comment_renderer, parent=None):
3262 comment_id = comment_renderer.get('commentId')
3263 if not comment_id:
3264 return
fe93e2c4 3265
052e1350 3266 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 3267
c26f9b99 3268 # Timestamp is an estimate calculated from the current time and time_text
3269 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3270 timestamp = self._parse_time_text(time_text)
3271
052e1350 3272 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 3273 author_id = try_get(comment_renderer,
14f25df2 3274 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 3275
49bd8c66 3276 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 3277 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 3278 author_thumbnail = try_get(comment_renderer,
14f25df2 3279 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
3280
3281 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 3282 is_favorited = 'creatorHeart' in (try_get(
3283 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
3284 return {
3285 'id': comment_id,
3286 'text': text,
d92f5d5a 3287 'timestamp': timestamp,
a1c5d2ca
M
3288 'time_text': time_text,
3289 'like_count': votes,
97524332 3290 'is_favorited': is_favorited,
a1c5d2ca
M
3291 'author': author,
3292 'author_id': author_id,
3293 'author_thumbnail': author_thumbnail,
3294 'author_is_uploader': author_is_uploader,
3295 'parent': parent or 'root'
3296 }
3297
46383212 3298 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3299
3300 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3301
3302 def extract_header(contents):
2d6659b9 3303 _continuation = None
3304 for content in contents:
46383212 3305 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3306 expected_comment_count = self._get_count(
3307 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3308
2d6659b9 3309 if expected_comment_count:
46383212 3310 tracker['est_total'] = expected_comment_count
3311 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3312 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3313
3314 sort_menu_item = try_get(
3315 comments_header_renderer,
3316 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3317 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3318
3319 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3320 if not _continuation:
3321 continue
3322
46383212 3323 sort_text = str_or_none(sort_menu_item.get('title'))
3324 if not sort_text:
2d6659b9 3325 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3326 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3327 break
a2160aa4 3328 return _continuation
a1c5d2ca 3329
2d6659b9 3330 def extract_thread(contents):
a1c5d2ca 3331 if not parent:
46383212 3332 tracker['current_page_thread'] = 0
a1c5d2ca 3333 for content in contents:
46383212 3334 if not parent and tracker['total_parent_comments'] >= max_parents:
3335 yield
a1c5d2ca 3336 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3337 comment_renderer = get_first(
3338 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3339 expected_type=dict, default={})
a1c5d2ca 3340
a1c5d2ca
M
3341 comment = self._extract_comment(comment_renderer, parent)
3342 if not comment:
3343 continue
46383212 3344
3345 tracker['running_total'] += 1
3346 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3347 yield comment
46383212 3348
a1c5d2ca
M
3349 # Attempt to get the replies
3350 comment_replies_renderer = try_get(
3351 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3352
3353 if comment_replies_renderer:
46383212 3354 tracker['current_page_thread'] += 1
a1c5d2ca 3355 comment_entries_iter = self._comment_entries(
99e9e001 3356 comment_replies_renderer, ytcfg, video_id,
46383212 3357 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3358 yield from itertools.islice(comment_entries_iter, min(
3359 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3360
46383212 3361 # Keeps track of counts across recursive calls
3362 if not tracker:
3363 tracker = dict(
3364 running_total=0,
3365 est_total=0,
3366 current_page_thread=0,
3367 total_parent_comments=0,
3368 total_reply_comments=0)
3369
3370 # TODO: Deprecated
2d6659b9 3371 # YouTube comments have a max depth of 2
46383212 3372 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3373 if max_depth:
da4db748 3374 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3375 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3376 if max_depth == 1 and parent:
3377 return
a1c5d2ca 3378
46383212 3379 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3380 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3381
46383212 3382 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3383
46383212 3384 response = None
6e634cbe 3385 is_forced_continuation = False
2d6659b9 3386 is_first_continuation = parent is None
6e634cbe 3387 if is_first_continuation and not continuation:
3388 # Sometimes you can get comments by generating the continuation yourself,
3389 # even if YouTube initially reports them being disabled - e.g. stories comments.
3390 # Note: if the comment section is actually disabled, YouTube may return a response with
3391 # required check_get_keys missing. So we will disable that check initially in this case.
3392 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3393 is_forced_continuation = True
a1c5d2ca
M
3394
3395 for page_num in itertools.count(0):
3396 if not continuation:
3397 break
46383212 3398 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3399 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 3400 if page_num == 0:
3401 if is_first_continuation:
3402 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3403 else:
2d6659b9 3404 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3405 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3406 else:
3407 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3408 ' ' if parent else '', ' replies' if parent else '',
3409 page_num, comment_prog_str)
e72e48c5
M
3410 try:
3411 response = self._extract_response(
3412 item_id=None, query=continuation,
3413 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3414 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3415 except ExtractorError as e:
3416 # Ignore incomplete data error for replies if retries didn't work.
3417 # This is to allow any other parent comments and comment threads to be downloaded.
3418 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3419 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3420 self.report_warning(
3421 'Received incomplete data for a comment reply thread and retrying did not help. '
3422 'Ignoring to let other comments be downloaded.')
3423 else:
3424 raise
6e634cbe 3425 is_forced_continuation = False
46383212 3426 continuation_contents = traverse_obj(
3427 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 3428
2d6659b9 3429 continuation = None
46383212 3430 for continuation_section in continuation_contents:
3431 continuation_items = traverse_obj(
3432 continuation_section,
3433 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3434 get_all=False, expected_type=list) or []
3435 if is_first_continuation:
3436 continuation = extract_header(continuation_items)
3437 is_first_continuation = False
2d6659b9 3438 if continuation:
a1c5d2ca 3439 break
46383212 3440 continue
a1c5d2ca 3441
46383212 3442 for entry in extract_thread(continuation_items):
3443 if not entry:
3444 return
3445 yield entry
3446 continuation = self._extract_continuation({'contents': continuation_items})
3447 if continuation:
2d6659b9 3448 break
a1c5d2ca 3449
6e634cbe 3450 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3451 if message and not parent and tracker['running_total'] == 0:
3452 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3453 raise self.CommentsDisabled
6e634cbe 3454
3455 @staticmethod
3456 def _generate_comment_continuation(video_id):
3457 """
3458 Generates initial comment section continuation token from given video id
3459 """
3460 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3461 return base64.b64encode(token.encode()).decode()
3462
a2160aa4 3463 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3464 """Entry for comment extraction"""
2d6659b9 3465 def _real_comment_extract(contents):
aae16f6e 3466 renderer = next((
3467 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3468 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3469 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3470
a2160aa4 3471 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3472 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3473
109dd3b2 3474 @staticmethod
99e9e001 3475 def _get_checkok_params():
3476 return {'contentCheckOk': True, 'racyCheckOk': True}
3477
3478 @classmethod
3479 def _generate_player_context(cls, sts=None):
109dd3b2 3480 context = {
3481 'html5Preference': 'HTML5_PREF_WANTS',
3482 }
3483 if sts is not None:
3484 context['signatureTimestamp'] = sts
3485 return {
3486 'playbackContext': {
3487 'contentPlaybackContext': context
a1a7907b 3488 },
99e9e001 3489 **cls._get_checkok_params()
109dd3b2 3490 }
3491
e7e94f2a
D
3492 @staticmethod
3493 def _is_agegated(player_response):
3494 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3495 return True
e7e94f2a 3496
6839ae1f 3497 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3498 AGE_GATE_REASONS = (
3499 'confirm your age', 'age-restricted', 'inappropriate', # reason
3500 'age_verification_required', 'age_check_required', # status
3501 )
3502 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3503
3504 @staticmethod
3505 def _is_unplayable(player_response):
3506 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3507
50ac0e54 3508 _STORY_PLAYER_PARAMS = '8AEB'
3509
3510 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3511
11f9be09 3512 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3513 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3514 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3515 headers = self.generate_api_headers(
99e9e001 3516 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3517
6e634cbe 3518 yt_query = {
3519 'videoId': video_id,
6e634cbe 3520 }
50ac0e54 3521 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3522 yt_query['params'] = self._STORY_PLAYER_PARAMS
3523
11f9be09 3524 yt_query.update(self._generate_player_context(sts))
3525 return self._extract_response(
3526 item_id=video_id, ep='player', query=yt_query,
379e44ed 3527 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3528 default_client=client,
11f9be09 3529 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3530 ) or None
3531
11f9be09 3532 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3533 requested_clients = []
d0d012d4 3534 default = ['android', 'web']
000c15a4 3535 allowed_clients = sorted(
86e5f3ed 3536 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3537 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3538 for client in self._configuration_arg('player_client'):
3539 if client in allowed_clients:
3540 requested_clients.append(client)
d0d012d4 3541 elif client == 'default':
3542 requested_clients.extend(default)
b4c055ba 3543 elif client == 'all':
3544 requested_clients.extend(allowed_clients)
3545 else:
3546 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3547 if not requested_clients:
d0d012d4 3548 requested_clients = default
cf7e015f 3549
11f9be09 3550 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3551 requested_clients.extend(
e7e94f2a 3552 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3553
11f9be09 3554 return orderedSet(requested_clients)
cf7e015f 3555
50ac0e54 3556 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3557 initial_pr = None
3558 if webpage:
b7c47b74 3559 initial_pr = self._search_json(
3560 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3561
ae729626 3562 all_clients = set(clients)
c0bc527b 3563 clients = clients[::-1]
b6de707d 3564 prs = []
e7e94f2a 3565
ae729626 3566 def append_client(*client_names):
e7870111 3567 """ Append the first client name that exists but not already used """
ae729626 3568 for client_name in client_names:
e7870111
D
3569 actual_client = _split_innertube_client(client_name)[0]
3570 if actual_client in INNERTUBE_CLIENTS:
3571 if actual_client not in all_clients:
ae729626 3572 clients.append(client_name)
e7870111
D
3573 all_clients.add(actual_client)
3574 return
e7e94f2a 3575
379e44ed 3576 # Android player_response does not have microFormats which are needed for
3577 # extraction of some data. So we return the initial_pr with formats
3578 # stripped out even if not requested by the user
3579 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3580 if initial_pr:
3581 pr = dict(initial_pr)
3582 pr['streamingData'] = None
b6de707d 3583 prs.append(pr)
379e44ed 3584
3585 last_error = None
b6de707d 3586 tried_iframe_fallback = False
3587 player_url = None
c0bc527b 3588 while clients:
e7870111 3589 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3590 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3591 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3592 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3593
b6de707d 3594 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3595 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3596 if 'js' in self._configuration_arg('player_skip'):
3597 require_js_player = False
3598 player_url = None
3599
3600 if not player_url and not tried_iframe_fallback and require_js_player:
3601 player_url = self._download_player_url(video_id)
3602 tried_iframe_fallback = True
3603
379e44ed 3604 try:
3605 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3606 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3607 except ExtractorError as e:
3608 if last_error:
3609 self.report_warning(last_error)
3610 last_error = e
3611 continue
3612
11f9be09 3613 if pr:
a3e96421 3614 # YouTube may return a different video player response than expected.
3615 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3616 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3617 if pr_video_id and pr_video_id != video_id:
3618 self.report_warning(
c7dcf0b3 3619 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3620 else:
3621 prs.append(pr)
c0bc527b 3622
e7e94f2a 3623 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3624 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3625 append_client(f'{base_client}_creator')
e7e94f2a 3626 elif self._is_agegated(pr):
e7870111
D
3627 if variant == 'tv_embedded':
3628 append_client(f'{base_client}_embedded')
3629 elif not variant:
3630 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3631
379e44ed 3632 if last_error:
b6de707d 3633 if not len(prs):
379e44ed 3634 raise last_error
3635 self.report_warning(last_error)
b6de707d 3636 return prs, player_url
11f9be09 3637
4d37720a
L
3638 def _needs_live_processing(self, live_status, duration):
3639 if (live_status == 'is_live' and self.get_param('live_from_start')
3640 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3641 return live_status
3642
3643 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
a4894d3e 3644 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3645 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3646 q = qualities([
2a9c6dcd 3647 # Normally tiny is the smallest video-only formats. But
3648 # audio-only formats with unknown quality may get tagged as tiny
3649 'tiny',
3650 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3651 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3652 ])
6839ae1f 3653 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
9297939e 3654
545cc85d 3655 for fmt in streaming_formats:
727029c5 3656 if fmt.get('targetDurationSec'):
545cc85d 3657 continue
321bf820 3658
cc2db878 3659 itag = str_or_none(fmt.get('itag'))
9297939e 3660 audio_track = fmt.get('audioTrack') or {}
9bb85699 3661 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
9297939e 3662 if stream_id in stream_ids:
3663 continue
3664
cc2db878 3665 quality = fmt.get('quality')
2a9c6dcd 3666 height = int_or_none(fmt.get('height'))
d3fc8074 3667 if quality == 'tiny' or not quality:
3668 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3669 # The 3gp format (17) in android client has a quality of "small",
3670 # but is actually worse than other formats
3671 if itag == '17':
3672 quality = 'tiny'
3673 if quality:
3674 if itag:
3675 itag_qualities[itag] = quality
3676 if height:
3677 res_qualities[height] = quality
cc2db878 3678 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3679 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3680 # number of fragment that would subsequently requested with (`&sq=N`)
3681 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3682 continue
3683
545cc85d 3684 fmt_url = fmt.get('url')
3685 if not fmt_url:
14f25df2 3686 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3687 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3688 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3689 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3690 continue
52023f12 3691 try:
3692 fmt_url += '&%s=%s' % (
3693 traverse_obj(sc, ('sp', -1)) or 'signature',
3694 self._decrypt_signature(encrypted_sig, video_id, player_url)
3695 )
3696 except ExtractorError as e:
580ce007 3697 self.report_warning('Signature extraction failed: Some formats may be missing',
3698 video_id=video_id, only_once=True)
52023f12 3699 self.write_debug(e, only_once=True)
201e9eaa 3700 continue
545cc85d 3701
404f611f 3702 query = parse_qs(fmt_url)
3703 throttled = False
b2916526 3704 if query.get('n'):
404f611f 3705 try:
580ce007 3706 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3707 fmt_url = update_url_query(fmt_url, {
580ce007 3708 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3709 })
404f611f 3710 except ExtractorError as e:
25836db6 3711 phantomjs_hint = ''
3712 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3713 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3714 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3715 if player_url:
3716 self.report_warning(
3717 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3718 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3719 self.write_debug(e, only_once=True)
3720 else:
3721 self.report_warning(
3722 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3723 video_id=video_id, only_once=True)
404f611f 3724 throttled = True
3725
0ad92dfb 3726 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3727 language_preference = (
3728 10 if audio_track.get('audioIsDefault') and 10
3729 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3730 else -1)
0ad92dfb 3731 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3732 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3733 # Make sure to avoid false positives with small duration differences.
62b58c09 3734 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3735 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3736 if is_damaged:
0f06bcd7 3737 self.report_warning(
3738 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3739 dct = {
3740 'asr': int_or_none(fmt.get('audioSampleRate')),
3741 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3742 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3743 'format_note': join_nonempty(
26e8e044 3744 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3745 ' (default)' if language_preference > 0 else ''),
404f611f 3746 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
9bb85699 3747 'DRC' if fmt.get('isDrc') else None,
a4166234 3748 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3749 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3750 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3751 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3752 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3753 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3754 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3755 'height': height,
9bb85699 3756 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3757 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3758 'tbr': tbr,
545cc85d 3759 'url': fmt_url,
2a9c6dcd 3760 'width': int_or_none(fmt.get('width')),
ab6df717 3761 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3762 'desc' if language_preference < -1 else '') or None,
ab6df717 3763 'language_preference': language_preference,
a405b38f 3764 # Strictly de-prioritize damaged and 3gp formats
3765 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3766 }
60bdb7bd 3767 mime_mobj = re.match(
3768 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3769 if mime_mobj:
3770 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3771 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3772 no_audio = dct.get('acodec') == 'none'
3773 no_video = dct.get('vcodec') == 'none'
3774 if no_audio:
3775 dct['vbr'] = tbr
3776 if no_video:
3777 dct['abr'] = tbr
3778 if no_audio or no_video:
545cc85d 3779 dct['downloader_options'] = {
3780 # Youtube throttles chunks >~10M
3781 'http_chunk_size': 10485760,
bf1317d2 3782 }
7c60c33e 3783 if dct.get('ext'):
3784 dct['container'] = dct['ext'] + '_dash'
a4894d3e 3785
3786 if itag:
3787 itags[itag].add(('https', dct.get('language')))
3788 stream_ids.append(stream_id)
11f9be09 3789 yield dct
545cc85d 3790
4d37720a
L
3791 needs_live_processing = self._needs_live_processing(live_status, duration)
3792 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3793
3794 skip_manifests = set(self._configuration_arg('skip'))
3795 if (not self.get_param('youtube_include_hls_manifest', True)
3796 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3797 or needs_live_processing and skip_bad_formats):
3798 skip_manifests.add('hls')
3799
0f06bcd7 3800 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3801 skip_manifests.add('dash')
3802 if self._configuration_arg('include_live_dash'):
3803 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3804 'Use include_incomplete_formats extractor argument instead')
3805 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3806 skip_manifests.add('dash')
5d3a0e79 3807
a0bb6ce5 3808 def process_manifest_format(f, proto, itag):
a4894d3e 3809 key = (proto, f.get('language'))
3810 if key in itags[itag]:
3811 return False
3812 itags[itag].add(key)
3813
3814 if any(p != proto for p, _ in itags[itag]):
3815 f['format_id'] = f'{itag}-{proto}'
3816 elif itag:
a0bb6ce5 3817 f['format_id'] = itag
a0bb6ce5 3818
b25cac65 3819 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3820 if f['quality'] == -1 and f.get('height'):
3821 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3822 return True
2a9c6dcd 3823
c646d76f 3824 subtitles = {}
11f9be09 3825 for sd in streaming_data:
4d37720a 3826 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3827 if hls_manifest_url:
4d37720a
L
3828 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3829 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3830 subtitles = self._merge_subtitles(subs, subtitles)
3831 for f in fmts:
a0bb6ce5 3832 if process_manifest_format(f, 'hls', self._search_regex(
3833 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3834 yield f
545cc85d 3835
4d37720a 3836 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3837 if dash_manifest_url:
c646d76f 3838 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3839 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3840 for f in formats:
a0bb6ce5 3841 if process_manifest_format(f, 'dash', f['format_id']):
3842 f['filesize'] = int_or_none(self._search_regex(
3843 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3844 if needs_live_processing:
adbc4ec4
THD
3845 f['is_from_start'] = True
3846
a0bb6ce5 3847 yield f
c646d76f 3848 yield subtitles
11f9be09 3849
720c3099 3850 def _extract_storyboard(self, player_responses, duration):
3851 spec = get_first(
3852 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3853 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3854 if not base_url:
720c3099 3855 return
720c3099 3856 L = len(spec) - 1
3857 for i, args in enumerate(spec):
3858 args = args.split('#')
3859 counts = list(map(int_or_none, args[:5]))
3860 if len(args) != 8 or not all(counts):
3861 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3862 continue
3863 width, height, frame_count, cols, rows = counts
3864 N, sigh = args[6:]
3865
3866 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3867 fragment_count = frame_count / (cols * rows)
3868 fragment_duration = duration / fragment_count
3869 yield {
3870 'format_id': f'sb{i}',
3871 'format_note': 'storyboard',
3872 'ext': 'mhtml',
3873 'protocol': 'mhtml',
3874 'acodec': 'none',
3875 'vcodec': 'none',
3876 'url': url,
3877 'width': width,
3878 'height': height,
45e8a04e 3879 'fps': frame_count / duration,
3880 'rows': rows,
3881 'columns': cols,
720c3099 3882 'fragments': [{
b3edc806 3883 'url': url.replace('$M', str(j)),
720c3099 3884 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3885 } for j in range(math.ceil(fragment_count))],
3886 }
3887
adbc4ec4 3888 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3889 webpage = None
3890 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3891 query = {'bpctr': '9999999999', 'has_verified': '1'}
3892 if smuggled_data.get('is_story'):
3893 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3894 webpage = self._download_webpage(
50ac0e54 3895 webpage_url, video_id, fatal=False, query=query)
11f9be09 3896
3897 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3898
b6de707d 3899 player_responses, player_url = self._extract_player_responses(
11f9be09 3900 self._get_requested_clients(url, smuggled_data),
50ac0e54 3901 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3902
adbc4ec4
THD
3903 return webpage, master_ytcfg, player_responses, player_url
3904
a1b2d843 3905 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3906 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3907 is_live = get_first(video_details, 'isLive')
3908 if is_live is None:
3909 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3910 live_content = get_first(video_details, 'isLiveContent')
3911 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3912 post_live = get_first(video_details, 'isPostLiveDvr')
3913 live_status = ('post_live' if post_live
3914 else 'is_live' if is_live
3915 else 'is_upcoming' if is_upcoming
6678a4f0 3916 else 'was_live' if live_content
3917 else 'not_live' if False in (is_live, live_content)
3918 else None)
6839ae1f 3919 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 3920 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3921
4d37720a 3922 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3923
3924 def _real_extract(self, url):
3925 url, smuggled_data = unsmuggle_url(url, {})
3926 video_id = self._match_id(url)
3927
3928 base_url = self.http_scheme() + '//www.youtube.com/'
3929 webpage_url = base_url + 'watch?v=' + video_id
3930
3931 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3932
11f9be09 3933 playability_statuses = traverse_obj(
6839ae1f 3934 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 3935
3936 trailer_video_id = get_first(
3937 playability_statuses,
3938 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3939 expected_type=str)
3940 if trailer_video_id:
3941 return self.url_result(
3942 trailer_video_id, self.ie_key(), trailer_video_id)
3943
3944 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3945 if webpage else (lambda x: None))
3946
6839ae1f 3947 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 3948 microformats = traverse_obj(
3949 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 3950 expected_type=dict)
c26f9b99 3951
3952 translated_title = self._get_text(microformats, (..., 'title'))
3953 video_title = (self._preferred_lang and translated_title
3954 or get_first(video_details, 'title') # primary
3955 or translated_title
3956 or search_meta(['og:title', 'twitter:title', 'title']))
3957 translated_description = self._get_text(microformats, (..., 'description'))
3958 original_description = get_first(video_details, 'shortDescription')
3959 video_description = (
3960 self._preferred_lang and translated_description
3961 # If original description is blank, it will be an empty string.
3962 # Do not prefer translated description in this case.
3963 or original_description if original_description is not None else translated_description)
11f9be09 3964
d89257f3 3965 multifeed_metadata_list = get_first(
3966 player_responses,
3967 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3968 expected_type=str)
3969 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3970 if self.get_param('noplaylist'):
11f9be09 3971 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3972 else:
3973 entries = []
3974 feed_ids = []
3975 for feed in multifeed_metadata_list.split(','):
3976 # Unquote should take place before split on comma (,) since textual
3977 # fields may contain comma as well (see
3978 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3979 feed_data = urllib.parse.parse_qs(
ac668111 3980 urllib.parse.unquote_plus(feed))
d89257f3 3981
3982 def feed_entry(name):
3983 return try_get(
14f25df2 3984 feed_data, lambda x: x[name][0], str)
d89257f3 3985
3986 feed_id = feed_entry('id')
3987 if not feed_id:
3988 continue
3989 feed_title = feed_entry('title')
3990 title = video_title
3991 if feed_title:
3992 title += ' (%s)' % feed_title
3993 entries.append({
3994 '_type': 'url_transparent',
3995 'ie_key': 'Youtube',
3996 'url': smuggle_url(
3997 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3998 {'force_singlefeed': True}),
3999 'title': title,
4000 })
4001 feed_ids.append(feed_id)
4002 self.to_screen(
4003 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4004 % (', '.join(feed_ids), video_id))
4005 return self.playlist_result(
4006 entries, video_id, video_title, video_description)
11f9be09 4007
9da6612b 4008 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4009 or int_or_none(get_first(microformats, 'lengthSeconds'))
4010 or parse_duration(search_meta('duration')) or None)
a1b2d843 4011
4d37720a
L
4012 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4013 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4014 if live_status == 'post_live':
4015 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4016
545cc85d 4017 if not formats:
11f9be09 4018 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4019 self.report_drm(video_id)
11f9be09 4020 pemr = get_first(
4021 playability_statuses,
4022 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4023 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4024 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4025 if subreason:
545cc85d 4026 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4027 countries = get_first(microformats, 'availableCountries')
545cc85d 4028 if not countries:
4029 regions_allowed = search_meta('regionsAllowed')
4030 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4031 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4032 reason += f'. {subreason}'
545cc85d 4033 if reason:
b7da73eb 4034 self.raise_no_formats(reason, expected=True)
bf1317d2 4035
11f9be09 4036 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4037 if not keywords and webpage:
4038 keywords = [
4039 unescapeHTML(m.group('content'))
4040 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4041 for keyword in keywords:
4042 if keyword.startswith('yt:stretch='):
201c1459 4043 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4044 if mobj:
4045 # NB: float is intentional for forcing float division
4046 w, h = (float(v) for v in mobj.groups())
4047 if w > 0 and h > 0:
4048 ratio = w / h
4049 for f in formats:
4050 if f.get('vcodec') != 'none':
4051 f['stretched_ratio'] = ratio
4052 break
a709d873 4053 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4054 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4055 if thumbnail_url:
4056 thumbnails.append({
4057 'url': thumbnail_url,
ff2751ac 4058 })
fccf5021 4059 original_thumbnails = thumbnails.copy()
4060
0ba692ac 4061 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4062 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4063 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4064 thumbnail_names = [
962ffcf8 4065 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4066 # in resolution, these are not the custom thumbnail. So de-prioritize them
4067 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4068 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4069 ]
cca80fe6 4070 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4071 thumbnails.extend({
4072 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4073 video_id=video_id, name=name, ext=ext,
4d37720a 4074 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4075 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4076 for thumb in thumbnails:
cca80fe6 4077 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4078 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4079 self._remove_duplicate_formats(thumbnails)
fccf5021 4080 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4081
7ea65411 4082 category = get_first(microformats, 'category') or search_meta('genre')
4083 channel_id = str_or_none(
4084 get_first(video_details, 'channelId')
4085 or get_first(microformats, 'externalChannelId')
4086 or search_meta('channelId'))
7ea65411 4087 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4088
adbc4ec4
THD
4089 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4090 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4091 if not duration and live_end_time and live_start_time:
4092 duration = live_end_time - live_start_time
4093
4d37720a
L
4094 needs_live_processing = self._needs_live_processing(live_status, duration)
4095
4096 def is_bad_format(fmt):
4097 if needs_live_processing and not fmt.get('is_from_start'):
4098 return True
4099 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4100 and fmt.get('protocol') == 'http_dash_segments'):
4101 return True
4102
4103 for fmt in filter(is_bad_format, formats):
4104 fmt['preference'] = (fmt.get('preference') or -1) - 10
4105 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4106
4107 if needs_live_processing:
4108 self._prepare_live_from_start_formats(
4109 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4110
720c3099 4111 formats.extend(self._extract_storyboard(player_responses, duration))
4112
545cc85d 4113 info = {
4114 'id': video_id,
39ca3b5c 4115 'title': video_title,
545cc85d 4116 'formats': formats,
4117 'thumbnails': thumbnails,
fccf5021 4118 # The best thumbnail that we are sure exists. Prevents unnecessary
4119 # URL checking if user don't care about getting the best possible thumbnail
4120 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4121 'description': video_description,
11f9be09 4122 'uploader': get_first(video_details, 'author'),
c61cf091 4123 'uploader_id': self._search_regex(r'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url, 'uploader id', default=None),
545cc85d 4124 'uploader_url': owner_profile_url,
4125 'channel_id': channel_id,
a70635b8 4126 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 4127 'duration': duration,
4128 'view_count': int_or_none(
11f9be09 4129 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4130 or search_meta('interactionCount')),
11f9be09 4131 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4132 'age_limit': 18 if (
11f9be09 4133 get_first(microformats, 'isFamilySafe') is False
545cc85d 4134 or search_meta('isFamilyFriendly') == 'false'
4135 or search_meta('og:restrictions:age') == '18+') else 0,
4136 'webpage_url': webpage_url,
4137 'categories': [category] if category else None,
4138 'tags': keywords,
11f9be09 4139 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4140 'live_status': live_status,
adbc4ec4 4141 'release_timestamp': live_start_time,
9f14daf2 4142 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4143 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4144 }
b477fc13 4145
c646d76f 4146 subtitles = {}
3944e7af 4147 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4148 if pctr:
ecdc9049 4149 def get_lang_code(track):
4150 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4151 or track.get('languageCode'))
4152
4153 # Converted into dicts to remove duplicates
4154 captions = {
4155 get_lang_code(sub): sub
6839ae1f 4156 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4157 translation_languages = {
4158 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4159 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4160
774d79cc 4161 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4162 lang_subs = container.setdefault(lang_code, [])
545cc85d 4163 for fmt in self._SUBTITLE_FORMATS:
4164 query.update({
4165 'fmt': fmt,
4166 })
4167 lang_subs.append({
4168 'ext': fmt,
60f393e4 4169 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4170 'name': sub_name,
545cc85d 4171 })
7e72694b 4172
07b47084 4173 # NB: Constructing the full subtitle dictionary is slow
4174 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4175 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4176 for lang_code, caption_track in captions.items():
4177 base_url = caption_track.get('baseUrl')
1235d333 4178 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4179 if not base_url:
4180 continue
ecdc9049 4181 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4182 if caption_track.get('kind') != 'asr':
545cc85d 4183 if not lang_code:
4184 continue
4185 process_language(
ecdc9049 4186 subtitles, base_url, lang_code, lang_name, {})
4187 if not caption_track.get('isTranslatable'):
4188 continue
3944e7af 4189 for trans_code, trans_name in translation_languages.items():
4190 if not trans_code:
545cc85d 4191 continue
1235d333 4192 orig_trans_code = trans_code
71eb82d1 4193 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4194 if not get_translated_subs:
18e49408 4195 continue
ecdc9049 4196 trans_code += f'-{lang_code}'
a70635b8 4197 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 4198 # Add an "-orig" label to the original language so that it can be distinguished.
4199 # The subs are returned without "-orig" as well for compatibility
1235d333 4200 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 4201 process_language(
d49669ac 4202 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4203 # Setting tlang=lang returns damaged subtitles.
d49669ac 4204 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4205 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4206
4207 info['automatic_captions'] = automatic_captions
4208 info['subtitles'] = subtitles
7e72694b 4209
14f25df2 4210 parsed_url = urllib.parse.urlparse(url)
545cc85d 4211 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4212 query = urllib.parse.parse_qs(component)
545cc85d 4213 for k, v in query.items():
4214 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4215 d_k += '_time'
4216 if d_k not in info and k in s_ks:
4217 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4218
4219 # Youtube Music Auto-generated description
822b9d9c 4220 if video_description:
1890fc63 4221 mobj = re.search(
4222 r'''(?xs)
4223 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4224 (?P<album>[^\n]+)
4225 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4226 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4227 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4228 .+\nAuto-generated\ by\ YouTube\.\s*$
4229 ''', video_description)
822b9d9c 4230 if mobj:
822b9d9c
RA
4231 release_year = mobj.group('release_year')
4232 release_date = mobj.group('release_date')
4233 if release_date:
4234 release_date = release_date.replace('-', '')
4235 if not release_year:
545cc85d 4236 release_year = release_date[:4]
4237 info.update({
4238 'album': mobj.group('album'.strip()),
4239 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4240 'track': mobj.group('track').strip(),
4241 'release_date': release_date,
cc2db878 4242 'release_year': int_or_none(release_year),
545cc85d 4243 })
7e72694b 4244
545cc85d 4245 initial_data = None
4246 if webpage:
56ba69e4 4247 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 4248 if not initial_data:
99e9e001 4249 query = {'videoId': video_id}
4250 query.update(self._get_checkok_params())
109dd3b2 4251 initial_data = self._extract_response(
4252 item_id=video_id, ep='next', fatal=False,
99e9e001 4253 ytcfg=master_ytcfg, query=query,
4254 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4255 note='Downloading initial data API JSON')
545cc85d 4256
0df111a3 4257 info['comment_count'] = traverse_obj(initial_data, (
4258 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4259 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4260 ), (
4261 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4262 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4263 ), expected_type=int_or_none, get_all=False)
4264
19a03940 4265 try: # This will error if there is no livechat
c60ee3a2 4266 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4267 except (KeyError, IndexError, TypeError):
4268 pass
4269 else:
ecdc9049 4270 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4271 # url is needed to set cookies
4272 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4273 'video_id': video_id,
4274 'ext': 'json',
4d37720a
L
4275 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4276 else 'youtube_live_chat_replay'),
c60ee3a2 4277 }]
545cc85d 4278
4279 if initial_data:
7c365c21 4280 info['chapters'] = (
4281 self._extract_chapters_from_json(initial_data, duration)
4282 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4283 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4284 or None)
545cc85d 4285
17322130 4286 contents = traverse_obj(
4287 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4288 expected_type=list, default=[])
4289
4290 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4291 if vpir:
4292 stl = vpir.get('superTitleLink')
4293 if stl:
4294 stl = self._get_text(stl)
4295 if try_get(
4296 vpir,
4297 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4298 info['location'] = stl
4299 else:
affc4fef 4300 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4301 if mobj:
545cc85d 4302 info.update({
17322130 4303 'series': mobj.group(1),
4304 'season_number': int(mobj.group(2)),
4305 'episode_number': int(mobj.group(3)),
545cc85d 4306 })
17322130 4307 for tlb in (try_get(
4308 vpir,
4309 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4310 list) or []):
3ffb2f5b 4311 tbrs = variadic(
4312 traverse_obj(
6839ae1f
SS
4313 tlb, ('toggleButtonRenderer', ...),
4314 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4315 for tbr in tbrs:
4316 for getter, regex in [(
4317 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4318 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4319 lambda x: x['accessibility'],
4320 lambda x: x['accessibilityData']['accessibilityData'],
4321 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4322 label = (try_get(tbr, getter, dict) or {}).get('label')
4323 if label:
4324 mobj = re.match(regex, label)
4325 if mobj:
4326 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4327 break
17322130 4328 sbr_tooltip = try_get(
4329 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4330 if sbr_tooltip:
4331 like_count, dislike_count = sbr_tooltip.split(' / ')
4332 info.update({
4333 'like_count': str_to_int(like_count),
4334 'dislike_count': str_to_int(dislike_count),
4335 })
867c66ff
M
4336 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4337 if vcr:
4338 vc = self._get_count(vcr, 'viewCount')
4339 # Upcoming premieres with waiting count are treated as live here
4340 if vcr.get('isLive'):
4341 info['concurrent_view_count'] = vc
4342 elif info.get('view_count') is None:
4343 info['view_count'] = vc
4344
17322130 4345 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4346 if vsir:
4347 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4348 info.update({
4349 'channel': self._get_text(vor, 'title'),
4350 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4351
4352 rows = try_get(
4353 vsir,
4354 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4355 list) or []
4356 multiple_songs = False
4357 for row in rows:
4358 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4359 multiple_songs = True
4360 break
4361 for row in rows:
4362 mrr = row.get('metadataRowRenderer') or {}
4363 mrr_title = mrr.get('title')
4364 if not mrr_title:
4365 continue
4366 mrr_title = self._get_text(mrr, 'title')
4367 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4368 if mrr_title == 'License':
4369 info['license'] = mrr_contents_text
4370 elif not multiple_songs:
4371 if mrr_title == 'Album':
4372 info['album'] = mrr_contents_text
4373 elif mrr_title == 'Artist':
4374 info['artist'] = mrr_contents_text
4375 elif mrr_title == 'Song':
4376 info['track'] = mrr_contents_text
545cc85d 4377
4378 fallbacks = {
4379 'channel': 'uploader',
4380 'channel_id': 'uploader_id',
4381 'channel_url': 'uploader_url',
4382 }
992f9a73 4383
17322130 4384 # The upload date for scheduled, live and past live streams / premieres in microformats
4385 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4386 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4387 upload_date = (
4388 unified_strdate(get_first(microformats, 'uploadDate'))
4389 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4390 if not upload_date or (
4d37720a 4391 live_status in ('not_live', None)
1ff88b7a 4392 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4393 ):
c26f9b99 4394 upload_date = strftime_or_none(
4395 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4396 info['upload_date'] = upload_date
992f9a73 4397
545cc85d 4398 for to, frm in fallbacks.items():
4399 if not info.get(to):
4400 info[to] = info.get(frm)
4401
4402 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4403 v = info.get(s_k)
4404 if v:
4405 info[d_k] = v
b84071c0 4406
c26f9b99 4407 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4408
4409 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4410 or get_first(video_details, 'isPrivate', expected_type=bool))
4411
4412 info['availability'] = (
4413 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4414 else self._availability(
4415 is_private=is_private,
4416 needs_premium=(
4417 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4418 or False if initial_data and is_private is not None else None),
4419 needs_subscription=(
4420 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4421 or False if initial_data and is_private is not None else None),
4422 needs_auth=info['age_limit'] >= 18,
4423 is_unlisted=None if is_private is None else (
4424 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4425 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4426
a2160aa4 4427 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4428
11f9be09 4429 self.mark_watched(video_id, player_responses)
d77ab8e2 4430
545cc85d 4431 return info
c5e8d7af 4432
a61fd4cf 4433
a6213a49 4434class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4435 @staticmethod
4436 def passthrough_smuggled_data(func):
bd7e919a 4437 def _smuggle(info, smuggled_data):
4438 if info.get('_type') not in ('url', 'url_transparent'):
4439 return info
4440 if smuggled_data.get('is_music_url'):
4441 parsed_url = urllib.parse.urlparse(info['url'])
4442 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4443 smuggled_data.pop('is_music_url')
4444 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4445 if smuggled_data:
4446 info['url'] = smuggle_url(info['url'], smuggled_data)
4447 return info
182bda88 4448
4449 @functools.wraps(func)
4450 def wrapper(self, url):
4451 url, smuggled_data = unsmuggle_url(url, {})
4452 if self.is_music_url(url):
4453 smuggled_data['is_music_url'] = True
4454 info_dict = func(self, url, smuggled_data)
bd7e919a 4455 if smuggled_data:
4456 _smuggle(info_dict, smuggled_data)
4457 if info_dict.get('entries'):
a8c754cc 4458 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4459 return info_dict
4460 return wrapper
4461
8bdd16b4 4462 @staticmethod
cd7c66cf 4463 def _extract_basic_item_renderer(item):
4464 # Modified from _extract_grid_item_renderer
201c1459 4465 known_basic_renderers = (
a17526e4 4466 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4467 )
4468 for key, renderer in item.items():
201c1459 4469 if not isinstance(renderer, dict):
cd7c66cf 4470 continue
201c1459 4471 elif key in known_basic_renderers:
4472 return renderer
4473 elif key.startswith('grid') and key.endswith('Renderer'):
4474 return renderer
8bdd16b4 4475
c7335551
M
4476 def _extract_channel_renderer(self, renderer):
4477 channel_id = renderer['channelId']
4478 title = self._get_text(renderer, 'title')
4479 channel_url = f'https://www.youtube.com/channel/{channel_id}'
4480 return {
4481 '_type': 'url',
4482 'url': channel_url,
4483 'id': channel_id,
4484 'ie_key': YoutubeTabIE.ie_key(),
4485 'channel': title,
4486 'channel_id': channel_id,
4487 'channel_url': channel_url,
4488 'title': title,
4489 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4490 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4491 'playlist_count': self._get_count(renderer, 'videoCountText'),
4492 'description': self._get_text(renderer, 'descriptionSnippet'),
4493 }
4494
8bdd16b4 4495 def _grid_entries(self, grid_renderer):
4496 for item in grid_renderer['items']:
4497 if not isinstance(item, dict):
39b62db1 4498 continue
cd7c66cf 4499 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4500 if not isinstance(renderer, dict):
4501 continue
052e1350 4502 title = self._get_text(renderer, 'title')
fe93e2c4 4503
8bdd16b4 4504 # playlist
4505 playlist_id = renderer.get('playlistId')
4506 if playlist_id:
4507 yield self.url_result(
4508 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4509 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4510 video_title=title)
201c1459 4511 continue
8bdd16b4 4512 # video
4513 video_id = renderer.get('videoId')
4514 if video_id:
4515 yield self._extract_video(renderer)
201c1459 4516 continue
8bdd16b4 4517 # channel
4518 channel_id = renderer.get('channelId')
4519 if channel_id:
c7335551 4520 yield self._extract_channel_renderer(renderer)
201c1459 4521 continue
4522 # generic endpoint URL support
4523 ep_url = urljoin('https://www.youtube.com/', try_get(
4524 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4525 str))
201c1459 4526 if ep_url:
4527 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4528 if ie.suitable(ep_url):
4529 yield self.url_result(
4530 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4531 break
8bdd16b4 4532
16aa9ea4 4533 def _music_reponsive_list_entry(self, renderer):
4534 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4535 if video_id:
4536 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4537 ie=YoutubeIE.ie_key(), video_id=video_id)
4538 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4539 if playlist_id:
4540 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4541 if video_id:
4542 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4543 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4544 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4545 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4546 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4547 if browse_id:
4548 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4549 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4550
3d3dddc9 4551 def _shelf_entries_from_content(self, shelf_renderer):
4552 content = shelf_renderer.get('content')
4553 if not isinstance(content, dict):
8bdd16b4 4554 return
cd7c66cf 4555 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4556 if renderer:
4557 # TODO: add support for nested playlists so each shelf is processed
4558 # as separate playlist
4559 # TODO: this includes only first N items
86e5f3ed 4560 yield from self._grid_entries(renderer)
3d3dddc9 4561 renderer = content.get('horizontalListRenderer')
4562 if renderer:
4563 # TODO
4564 pass
8bdd16b4 4565
29f7c58a 4566 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4567 ep = try_get(
4568 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4569 str)
8bdd16b4 4570 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4571 if shelf_url:
29f7c58a 4572 # Skipping links to another channels, note that checking for
4573 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4574 # will not work
4575 if skip_channels and '/channels?' in shelf_url:
4576 return
052e1350 4577 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4578 yield self.url_result(shelf_url, video_title=title)
4579 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4580 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4581
8bdd16b4 4582 def _playlist_entries(self, video_list_renderer):
4583 for content in video_list_renderer['contents']:
4584 if not isinstance(content, dict):
4585 continue
4586 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4587 if not isinstance(renderer, dict):
4588 continue
4589 video_id = renderer.get('videoId')
4590 if not video_id:
4591 continue
4592 yield self._extract_video(renderer)
07aeced6 4593
3462ffa8 4594 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4595 renderer = traverse_obj(
4596 rich_grid_renderer, ('content', ('videoRenderer', 'reelItemRenderer')), get_all=False) or {}
3462ffa8 4597 video_id = renderer.get('videoId')
4598 if not video_id:
4599 return
4600 yield self._extract_video(renderer)
4601
8bdd16b4 4602 def _video_entry(self, video_renderer):
4603 video_id = video_renderer.get('videoId')
4604 if video_id:
4605 return self._extract_video(video_renderer)
dacb3a86 4606
ad210f4f 4607 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4608 url = urljoin('https://youtube.com', traverse_obj(
4609 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4610 if url:
4611 return self.url_result(
4612 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4613
8bdd16b4 4614 def _post_thread_entries(self, post_thread_renderer):
4615 post_renderer = try_get(
4616 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4617 if not post_renderer:
4618 return
4619 # video attachment
4620 video_renderer = try_get(
895b0931 4621 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4622 video_id = video_renderer.get('videoId')
4623 if video_id:
4624 entry = self._extract_video(video_renderer)
8bdd16b4 4625 if entry:
4626 yield entry
895b0931 4627 # playlist attachment
4628 playlist_id = try_get(
14f25df2 4629 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4630 if playlist_id:
4631 yield self.url_result(
e28f1c0a 4632 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4633 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4634 # inline video links
4635 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4636 for run in runs:
4637 if not isinstance(run, dict):
4638 continue
4639 ep_url = try_get(
14f25df2 4640 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4641 if not ep_url:
4642 continue
4643 if not YoutubeIE.suitable(ep_url):
4644 continue
4645 ep_video_id = YoutubeIE._match_id(ep_url)
4646 if video_id == ep_video_id:
4647 continue
895b0931 4648 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4649
8bdd16b4 4650 def _post_thread_continuation_entries(self, post_thread_continuation):
4651 contents = post_thread_continuation.get('contents')
4652 if not isinstance(contents, list):
4653 return
4654 for content in contents:
4655 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4656 if isinstance(renderer, dict):
4657 yield from self._post_thread_entries(renderer)
8bdd16b4 4658 continue
6b0b0a28 4659 renderer = content.get('videoRenderer')
4660 if isinstance(renderer, dict):
4661 yield self._video_entry(renderer)
07aeced6 4662
39ed931e 4663 r''' # unused
4664 def _rich_grid_entries(self, contents):
4665 for content in contents:
4666 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4667 if video_renderer:
4668 entry = self._video_entry(video_renderer)
4669 if entry:
4670 yield entry
4671 '''
52efa4b3 4672
0a5095fe 4673 def _report_history_entries(self, renderer):
4674 for url in traverse_obj(renderer, (
7a32c70d 4675 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4676 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4677 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4678 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4679
a6213a49 4680 def _extract_entries(self, parent_renderer, continuation_list):
4681 # continuation_list is modified in-place with continuation_list = [continuation_token]
4682 continuation_list[:] = [None]
4683 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4684 for content in contents:
4685 if not isinstance(content, dict):
4686 continue
16aa9ea4 4687 is_renderer = traverse_obj(
4688 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4689 expected_type=dict)
a6213a49 4690 if not is_renderer:
0a5095fe 4691 if content.get('richItemRenderer'):
4692 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4693 yield entry
4694 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4695 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4696 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4697 yield from self._report_history_entries(table)
4698 continuation_list[0] = self._extract_continuation(table)
a6213a49 4699 continue
0a5095fe 4700
a6213a49 4701 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4702 for isr_content in isr_contents:
4703 if not isinstance(isr_content, dict):
8bdd16b4 4704 continue
69184e41 4705
a6213a49 4706 known_renderers = {
4707 'playlistVideoListRenderer': self._playlist_entries,
4708 'gridRenderer': self._grid_entries,
a17526e4 4709 'reelShelfRenderer': self._grid_entries,
4710 'shelfRenderer': self._shelf_entries,
16aa9ea4 4711 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4712 'backstagePostThreadRenderer': self._post_thread_entries,
4713 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4714 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4715 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4716 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4717 }
4718 for key, renderer in isr_content.items():
4719 if key not in known_renderers:
4720 continue
4721 for entry in known_renderers[key](renderer):
4722 if entry:
4723 yield entry
4724 continuation_list[0] = self._extract_continuation(renderer)
4725 break
70d5c17b 4726
4727 if not continuation_list[0]:
a6213a49 4728 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4729
a6213a49 4730 if not continuation_list[0]:
4731 continuation_list[0] = self._extract_continuation(parent_renderer)
4732
4733 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4734 continuation_list = [None]
4735 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4736 tab_content = try_get(tab, lambda x: x['content'], dict)
4737 if not tab_content:
4738 return
3462ffa8 4739 parent_renderer = (
29f7c58a 4740 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4741 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4742 yield from extract_entries(parent_renderer)
3462ffa8 4743 continuation = continuation_list[0]
d069eca7 4744
8bdd16b4 4745 for page_num in itertools.count(1):
4746 if not continuation:
4747 break
99e9e001 4748 headers = self.generate_api_headers(
4749 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4750 response = self._extract_response(
86e5f3ed 4751 item_id=f'{item_id} page {page_num}',
fe93e2c4 4752 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4753 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4754
4755 if not response:
8bdd16b4 4756 break
ac56cf38 4757 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4758 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4759 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4760
a1b535bd 4761 known_renderers = {
e4b98809 4762 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4763 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4764 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4765 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4766 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4767 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4768 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4769 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4770 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4771 'playlistVideoListContinuation': (self._playlist_entries, None),
4772 'gridContinuation': (self._grid_entries, None),
4773 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4774 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4775 }
1fb53b94 4776
4777 continuation_items = traverse_obj(response, (
4778 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4779 'appendContinuationItemsAction', 'continuationItems'
4780 ), 'continuationContents', get_all=False)
4781 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4782
a1b535bd 4783 video_items_renderer = None
1fb53b94 4784 for key in continuation_item.keys():
a1b535bd 4785 if key not in known_renderers:
8bdd16b4 4786 continue
1fb53b94 4787 func, parent_key = known_renderers[key]
4788 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4789 continuation_list = [None]
1fb53b94 4790 yield from func(video_items_renderer)
9ba5705a 4791 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4792
4793 if not video_items_renderer:
a1b535bd 4794 break
9558dcec 4795
8bdd16b4 4796 @staticmethod
7c219ea6 4797 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4798 for tab_renderer in tabs:
4799 if tab_renderer.get('selected'):
4800 return tab_renderer
4801 if fatal:
4802 raise ExtractorError('Unable to find selected tab')
4803
4804 @staticmethod
4805 def _extract_tab_renderers(response):
4806 return traverse_obj(
4807 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4808
ac56cf38 4809 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 4810 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 4811
8bdd16b4 4812 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 4813 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4814 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4815
4816 return self.playlist_result(
4817 self._entries(
4818 selected_tab, metadata['id'], ytcfg,
4819 self._extract_account_syncid(ytcfg, data),
4820 self._extract_visitor_data(data, ytcfg)),
4821 **metadata)
39ed931e 4822
bd7e919a 4823 def _extract_metadata_from_tabs(self, item_id, data):
4824 info = {'id': item_id}
4825
4826 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 4827 if metadata_renderer:
bd7e919a 4828 info.update({
4829 'uploader': metadata_renderer.get('title'),
4830 'uploader_id': metadata_renderer.get('externalId'),
4831 'uploader_url': metadata_renderer.get('channelUrl'),
4832 })
4833 if info['uploader_id']:
4834 info['id'] = info['uploader_id']
4835 else:
4836 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 4837
301d07fc 4838 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4839 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4840 def _get_uncropped(url):
4841 return url_or_none((url or '').split('=')[0] + '=s0')
4842
6141346d 4843 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 4844 if avatar_thumbnails:
4845 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4846 if uncropped_avatar:
4847 avatar_thumbnails.append({
4848 'url': uncropped_avatar,
4849 'id': 'avatar_uncropped',
4850 'preference': 1
4851 })
4852
4853 channel_banners = self._extract_thumbnails(
bd7e919a 4854 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 4855 for banner in channel_banners:
4856 banner['preference'] = -10
4857
4858 if channel_banners:
4859 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4860 if uncropped_banner:
4861 channel_banners.append({
4862 'url': uncropped_banner,
4863 'id': 'banner_uncropped',
4864 'preference': -5
4865 })
4866
bd7e919a 4867 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4868 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4869 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4870
301d07fc 4871 primary_thumbnails = self._extract_thumbnails(
a17526e4 4872 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
4873 playlist_thumbnails = self._extract_thumbnails(
4874 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4875
bd7e919a 4876 info.update({
4877 'title': (traverse_obj(metadata_renderer, 'title')
4878 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4879 or info['id']),
4880 'availability': self._extract_availability(data),
4881 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4882 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4883 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4884 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4885 })
f0d785d3 4886
6141346d
M
4887 # Playlist stats is a text runs array containing [video count, view count, last updated].
4888 # last updated or (view count and last updated) may be missing.
4889 playlist_stats = get_first(
bd7e919a 4890 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4891
6141346d
M
4892 last_updated_unix = self._parse_time_text(
4893 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4894 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
bd7e919a 4895 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
6141346d 4896
bd7e919a 4897 info['view_count'] = self._get_count(playlist_stats, 1)
4898 if info['view_count'] is None: # 0 is allowed
4899 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
4900
4901 info['playlist_count'] = self._get_count(playlist_stats, 0)
4902 if info['playlist_count'] is None: # 0 is allowed
4903 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
4904
4905 if not info.get('uploader_id'):
6141346d 4906 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 4907 if not owner: # Deprecated
6141346d
M
4908 owner = traverse_obj(
4909 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
4910 ('videoOwner', 'videoOwnerRenderer', 'title'))
4911 owner_text = self._get_text(owner)
4912 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 4913 info.update({
6141346d
M
4914 'uploader': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
4915 'uploader_id': browse_ep.get('browseId'),
4916 'uploader_url': urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))
bd7e919a 4917 })
6141346d 4918
bd7e919a 4919 info.update({
4920 'channel': info['uploader'],
4921 'channel_id': info['uploader_id'],
4922 'channel_url': info['uploader_url']
4923 })
4924 return info
73c4ac2c 4925
6e634cbe 4926 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4927 first_id = last_id = response = None
2be71994 4928 for page_num in itertools.count(1):
cd7c66cf 4929 videos = list(self._playlist_entries(playlist))
4930 if not videos:
4931 return
2be71994 4932 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4933 if start >= len(videos):
4934 return
24146491 4935 yield from videos[start:]
2be71994 4936 first_id = first_id or videos[0]['id']
4937 last_id = videos[-1]['id']
79360d99 4938 watch_endpoint = try_get(
4939 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4940 headers = self.generate_api_headers(
4941 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4942 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4943 query = {
4944 'playlistId': playlist_id,
4945 'videoId': watch_endpoint.get('videoId') or last_id,
4946 'index': watch_endpoint.get('index') or len(videos),
4947 'params': watch_endpoint.get('params') or 'OAE%3D'
4948 }
4949 response = self._extract_response(
4950 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4951 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4952 check_get_keys='contents'
4953 )
cd7c66cf 4954 playlist = try_get(
79360d99 4955 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4956
ac56cf38 4957 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4958 title = playlist.get('title') or try_get(
14f25df2 4959 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4960 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4961
4962 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4963 playlist_url = urljoin(url, try_get(
4964 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4965 str))
6e634cbe 4966
4967 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4968 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4969 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4970
4971 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4972 return self.url_result(
4973 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4974 video_title=title)
cd7c66cf 4975
8bdd16b4 4976 return self.playlist_result(
6e634cbe 4977 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4978 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4979
47193e02 4980 def _extract_availability(self, data):
4981 """
4982 Gets the availability of a given playlist/tab.
4983 Note: Unless YouTube tells us explicitly, we do not assume it is public
4984 @param data: response
4985 """
6141346d
M
4986 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4987 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
4988 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 4989
6141346d 4990 badges = self._extract_badges(sidebar_renderer)
47193e02 4991
4992 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
4993 privacy_setting_icon = get_first(
4994 (playlist_header_renderer, sidebar_renderer),
4995 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4996 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4997 expected_type=str)
4998
4999 microformats_is_unlisted = traverse_obj(
5000 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5001
c26f9b99 5002 return (
5003 'public' if (
5004 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5005 or player_header_privacy == 'PUBLIC'
5006 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5007 else self._availability(
5008 is_private=(
5009 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5010 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5011 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5012 is_unlisted=(
5013 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5014 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5015 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5016 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5017 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5018 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5019 needs_auth=False))
47193e02 5020
5021 @staticmethod
5022 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5023 sidebar_renderer = try_get(
5024 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5025 for item in sidebar_renderer:
5026 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5027 if renderer:
5028 return renderer
5029
ac56cf38 5030 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5031 """
6141346d 5032 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5033 """
6141346d
M
5034 is_playlist = bool(traverse_obj(
5035 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5036 if not is_playlist:
47193e02 5037 return
11f9be09 5038 headers = self.generate_api_headers(
99e9e001 5039 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5040 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5041 query = {
6141346d
M
5042 'params': 'wgYCCAA=',
5043 'browseId': f'VL{item_id}'
47193e02 5044 }
5045 return self._extract_response(
5046 item_id=item_id, headers=headers, query=query,
fe93e2c4 5047 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5048 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5049
2762dbb1 5050 @functools.cached_property
a25bca9f 5051 def skip_webpage(self):
5052 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5053
ac56cf38 5054 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5055 webpage, data = None, None
5056 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5057 try:
be5c1ae8 5058 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5059 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5060 except ExtractorError as e:
5061 if isinstance(e.cause, network_exceptions):
14f25df2 5062 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 5063 retry.error = e
5064 continue
5065 self._error_or_warning(e, fatal=fatal)
14fdfea9 5066 break
ac56cf38 5067
be5c1ae8 5068 try:
5069 self._extract_and_report_alerts(data)
5070 except ExtractorError as e:
5071 self._error_or_warning(e, fatal=fatal)
5072 break
ac56cf38 5073
be5c1ae8 5074 # Sometimes youtube returns a webpage with incomplete ytInitialData
5075 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5076 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5077 retry.error = ExtractorError('Incomplete yt initial data received')
5078 continue
ac56cf38 5079
cd7c66cf 5080 return webpage, data
5081
a25bca9f 5082 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5083 """Use if failed to extract ytcfg (and data) from initial webpage"""
5084 if not ytcfg and self.is_authenticated:
5085 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5086 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5087 raise ExtractorError(
5088 f'{msg}. If you are not downloading private content, or '
5089 'your cookies are only for the first account and channel,'
5090 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5091 expected=True)
5092 self.report_warning(msg, only_once=True)
5093
ac56cf38 5094 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5095 data = None
a25bca9f 5096 if not self.skip_webpage:
ac56cf38 5097 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5098 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5099 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5100 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5101 if (url != 'https://www.youtube.com/feed/recommended'
5102 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5103 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5104 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5105 if fatal:
5106 raise ExtractorError(msg, expected=True)
5107 self.report_warning(msg, only_once=True)
ac56cf38 5108 if not data:
a25bca9f 5109 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5110 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5111 return data, ytcfg
5112
5113 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5114 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5115 resolve_response = self._extract_response(
5116 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5117 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5118 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5119 for ep_key, ep in endpoints.items():
5120 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5121 if params:
5122 return self._extract_response(
5123 item_id=item_id, query=params, ep=ep, headers=headers,
5124 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5125 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5126 err_note = 'Failed to resolve url (does the playlist exist?)'
5127 if fatal:
5128 raise ExtractorError(err_note, expected=True)
5129 self.report_warning(err_note, item_id)
5130
a6213a49 5131 _SEARCH_PARAMS = None
5132
af5c1c55 5133 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5134 data = {'query': query}
5135 if params is NO_DEFAULT:
5136 params = self._SEARCH_PARAMS
5137 if params:
5138 data['params'] = params
16aa9ea4 5139
5140 content_keys = (
5141 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5142 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5143 # ytmusic search
5144 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5145 ('continuationContents', ),
5146 )
a25bca9f 5147 display_id = f'query "{query}"'
86e5f3ed 5148 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5149 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5150 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5151
a61fd4cf 5152 continuation_list = [None]
a25bca9f 5153 search = None
a6213a49 5154 for page_num in itertools.count(1):
a61fd4cf 5155 data.update(continuation_list[0] or {})
a25bca9f 5156 headers = self.generate_api_headers(
5157 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5158 search = self._extract_response(
a25bca9f 5159 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5160 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5161 slr_contents = traverse_obj(search, *content_keys)
5162 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5163 if not continuation_list[0]:
a6213a49 5164 break
5165
5166
5167class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5168 IE_DESC = 'YouTube Tabs'
5169 _VALID_URL = r'''(?x:
5170 https?://
b032ff0f 5171 (?!consent\.)(?:\w+\.)?
a6213a49 5172 (?:
5173 youtube(?:kids)?\.com|
5174 %(invidious)s
5175 )/
5176 (?:
5177 (?P<channel_type>channel|c|user|browse)/|
5178 (?P<not_channel>
5179 feed/|hashtag/|
5180 (?:playlist|watch)\?.*?\blist=
5181 )|
5182 (?!(?:%(reserved_names)s)\b) # Direct URLs
5183 )
5184 (?P<id>[^/?\#&]+)
5185 )''' % {
5186 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5187 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5188 }
5189 IE_NAME = 'youtube:tab'
5190
5191 _TESTS = [{
5192 'note': 'playlists, multipage',
5193 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5194 'playlist_mincount': 94,
5195 'info_dict': {
5196 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5197 'title': 'Igor Kleiner - Playlists',
a6213a49 5198 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5199 'uploader': 'Igor Kleiner',
a6213a49 5200 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5201 'channel': 'Igor Kleiner',
5202 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5203 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5204 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5205 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5206 'channel_follower_count': int
a6213a49 5207 },
5208 }, {
5209 'note': 'playlists, multipage, different order',
5210 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5211 'playlist_mincount': 94,
5212 'info_dict': {
5213 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5214 'title': 'Igor Kleiner - Playlists',
a6213a49 5215 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5216 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5217 'uploader': 'Igor Kleiner',
5218 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5219 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5220 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5221 'channel': 'Igor Kleiner',
5222 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5223 'channel_follower_count': int
a6213a49 5224 },
5225 }, {
5226 'note': 'playlists, series',
5227 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5228 'playlist_mincount': 5,
5229 'info_dict': {
5230 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5231 'title': '3Blue1Brown - Playlists',
5232 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5233 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5234 'uploader': '3Blue1Brown',
976ae3ea 5235 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5236 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5237 'channel': '3Blue1Brown',
5238 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5239 'tags': ['Mathematics'],
6c73052c 5240 'channel_follower_count': int
a6213a49 5241 },
5242 }, {
5243 'note': 'playlists, singlepage',
5244 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5245 'playlist_mincount': 4,
5246 'info_dict': {
5247 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5248 'title': 'ThirstForScience - Playlists',
5249 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5250 'uploader': 'ThirstForScience',
5251 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5252 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5253 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5254 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5255 'tags': 'count:13',
5256 'channel': 'ThirstForScience',
6c73052c 5257 'channel_follower_count': int
a6213a49 5258 }
5259 }, {
5260 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5261 'only_matching': True,
5262 }, {
5263 'note': 'basic, single video playlist',
5264 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5265 'info_dict': {
5266 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5267 'uploader': 'Sergey M.',
5268 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5269 'title': 'youtube-dl public playlist',
976ae3ea 5270 'description': '',
5271 'tags': [],
5272 'view_count': int,
5273 'modified_date': '20201130',
5274 'channel': 'Sergey M.',
5275 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5276 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5277 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5278 'availability': 'public',
a6213a49 5279 },
5280 'playlist_count': 1,
5281 }, {
5282 'note': 'empty playlist',
5283 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5284 'info_dict': {
5285 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5286 'uploader': 'Sergey M.',
5287 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5288 'title': 'youtube-dl empty playlist',
976ae3ea 5289 'tags': [],
5290 'channel': 'Sergey M.',
5291 'description': '',
5292 'modified_date': '20160902',
5293 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5294 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5295 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5296 'availability': 'public',
a6213a49 5297 },
5298 'playlist_count': 0,
5299 }, {
5300 'note': 'Home tab',
5301 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5302 'info_dict': {
5303 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5304 'title': 'lex will - Home',
5305 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5306 'uploader': 'lex will',
5307 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5308 'channel': 'lex will',
5309 'tags': ['bible', 'history', 'prophesy'],
5310 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5311 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5312 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5313 'channel_follower_count': int
a6213a49 5314 },
5315 'playlist_mincount': 2,
5316 }, {
5317 'note': 'Videos tab',
5318 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5319 'info_dict': {
5320 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5321 'title': 'lex will - Videos',
5322 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5323 'uploader': 'lex will',
5324 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5325 'tags': ['bible', 'history', 'prophesy'],
5326 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5327 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5328 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5329 'channel': 'lex will',
6c73052c 5330 'channel_follower_count': int
a6213a49 5331 },
5332 'playlist_mincount': 975,
5333 }, {
5334 'note': 'Videos tab, sorted by popular',
5335 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5336 'info_dict': {
5337 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5338 'title': 'lex will - Videos',
5339 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5340 'uploader': 'lex will',
5341 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5342 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5343 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5344 'channel': 'lex will',
5345 'tags': ['bible', 'history', 'prophesy'],
5346 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5347 'channel_follower_count': int
a6213a49 5348 },
5349 'playlist_mincount': 199,
5350 }, {
5351 'note': 'Playlists tab',
5352 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5353 'info_dict': {
5354 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5355 'title': 'lex will - Playlists',
5356 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5357 'uploader': 'lex will',
5358 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5359 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5360 'channel': 'lex will',
5361 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5362 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5363 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5364 'channel_follower_count': int
a6213a49 5365 },
5366 'playlist_mincount': 17,
5367 }, {
5368 'note': 'Community tab',
5369 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5370 'info_dict': {
5371 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5372 'title': 'lex will - Community',
5373 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5374 'uploader': 'lex will',
5375 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5376 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5377 'channel': 'lex will',
5378 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5379 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5380 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5381 'channel_follower_count': int
a6213a49 5382 },
5383 'playlist_mincount': 18,
5384 }, {
5385 'note': 'Channels tab',
5386 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5387 'info_dict': {
5388 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5389 'title': 'lex will - Channels',
5390 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5391 'uploader': 'lex will',
5392 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 5393 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5394 'channel': 'lex will',
5395 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5396 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5397 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5398 'channel_follower_count': int
a6213a49 5399 },
5400 'playlist_mincount': 12,
5401 }, {
5402 'note': 'Search tab',
5403 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5404 'playlist_mincount': 40,
5405 'info_dict': {
5406 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5407 'title': '3Blue1Brown - Search - linear algebra',
5408 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5409 'uploader': '3Blue1Brown',
5410 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5411 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5412 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5413 'tags': ['Mathematics'],
5414 'channel': '3Blue1Brown',
5415 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 5416 'channel_follower_count': int
a6213a49 5417 },
5418 }, {
5419 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5420 'only_matching': True,
5421 }, {
5422 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5423 'only_matching': True,
5424 }, {
5425 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5426 'only_matching': True,
5427 }, {
5428 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5429 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5430 'info_dict': {
5431 'title': '29C3: Not my department',
5432 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5433 'uploader': 'Christiaan008',
5434 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5435 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5436 'tags': [],
5437 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5438 'view_count': int,
5439 'modified_date': '20150605',
5440 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5441 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5442 'channel': 'Christiaan008',
c26f9b99 5443 'availability': 'public',
a6213a49 5444 },
5445 'playlist_count': 96,
5446 }, {
5447 'note': 'Large playlist',
5448 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5449 'info_dict': {
5450 'title': 'Uploads from Cauchemar',
5451 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5452 'uploader': 'Cauchemar',
5453 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5454 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5455 'tags': [],
5456 'modified_date': r're:\d{8}',
5457 'channel': 'Cauchemar',
5458 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5459 'view_count': int,
5460 'description': '',
5461 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5462 'availability': 'public',
a6213a49 5463 },
5464 'playlist_mincount': 1123,
976ae3ea 5465 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5466 }, {
5467 'note': 'even larger playlist, 8832 videos',
5468 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5469 'only_matching': True,
5470 }, {
5471 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5472 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5473 'info_dict': {
5474 'title': 'Uploads from Interstellar Movie',
5475 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5476 'uploader': 'Interstellar Movie',
5477 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5478 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5479 'tags': [],
5480 'view_count': int,
5481 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5482 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5483 'channel': 'Interstellar Movie',
5484 'description': '',
5485 'modified_date': r're:\d{8}',
c26f9b99 5486 'availability': 'public',
a6213a49 5487 },
5488 'playlist_mincount': 21,
5489 }, {
5490 'note': 'Playlist with "show unavailable videos" button',
5491 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5492 'info_dict': {
5493 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5494 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5495 'uploader': 'Phim Siêu Nhân Nhật Bản',
5496 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5497 'view_count': int,
5498 'channel': 'Phim Siêu Nhân Nhật Bản',
5499 'tags': [],
5500 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5501 'description': '',
5502 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5503 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5504 'modified_date': r're:\d{8}',
c26f9b99 5505 'availability': 'public',
a6213a49 5506 },
5507 'playlist_mincount': 200,
976ae3ea 5508 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5509 }, {
5510 'note': 'Playlist with unavailable videos in page 7',
5511 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5512 'info_dict': {
5513 'title': 'Uploads from BlankTV',
5514 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5515 'uploader': 'BlankTV',
5516 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5517 'channel': 'BlankTV',
5518 'channel_url': 'https://www.youtube.com/c/blanktv',
5519 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5520 'view_count': int,
5521 'tags': [],
5522 'uploader_url': 'https://www.youtube.com/c/blanktv',
5523 'modified_date': r're:\d{8}',
5524 'description': '',
c26f9b99 5525 'availability': 'public',
a6213a49 5526 },
5527 'playlist_mincount': 1000,
976ae3ea 5528 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5529 }, {
5530 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5531 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5532 'info_dict': {
5533 'title': 'Data Analysis with Dr Mike Pound',
5534 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5535 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5536 'uploader': 'Computerphile',
5537 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5538 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5539 'tags': [],
5540 'view_count': int,
5541 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5542 'channel_url': 'https://www.youtube.com/user/Computerphile',
5543 'channel': 'Computerphile',
c26f9b99 5544 'availability': 'public',
6141346d 5545 'modified_date': '20190712',
a6213a49 5546 },
5547 'playlist_mincount': 11,
5548 }, {
5549 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5550 'only_matching': True,
5551 }, {
5552 'note': 'Playlist URL that does not actually serve a playlist',
5553 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5554 'info_dict': {
5555 'id': 'FqZTN594JQw',
5556 'ext': 'webm',
5557 'title': "Smiley's People 01 detective, Adventure Series, Action",
5558 'uploader': 'STREEM',
5559 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5560 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5561 'upload_date': '20150526',
5562 'license': 'Standard YouTube License',
5563 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5564 'categories': ['People & Blogs'],
5565 'tags': list,
5566 'view_count': int,
5567 'like_count': int,
a6213a49 5568 },
5569 'params': {
5570 'skip_download': True,
5571 },
5572 'skip': 'This video is not available.',
5573 'add_ie': [YoutubeIE.ie_key()],
5574 }, {
5575 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5576 'only_matching': True,
5577 }, {
5578 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5579 'only_matching': True,
5580 }, {
5581 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5582 'info_dict': {
12a1b225 5583 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5584 'ext': 'mp4',
976ae3ea 5585 'title': str,
a6213a49 5586 'uploader': 'Sky News',
5587 'uploader_id': 'skynews',
5588 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5589 'upload_date': r're:\d{8}',
976ae3ea 5590 'description': str,
a6213a49 5591 'categories': ['News & Politics'],
5592 'tags': list,
5593 'like_count': int,
86973308 5594 'release_timestamp': int,
976ae3ea 5595 'channel': 'Sky News',
5596 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5597 'age_limit': 0,
5598 'view_count': int,
86973308 5599 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5600 'playable_in_embed': True,
86973308 5601 'release_date': r're:\d+',
976ae3ea 5602 'availability': 'public',
5603 'live_status': 'is_live',
5604 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5605 'channel_follower_count': int,
5606 'concurrent_view_count': int,
a6213a49 5607 },
5608 'params': {
5609 'skip_download': True,
5610 },
976ae3ea 5611 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5612 }, {
5613 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5614 'info_dict': {
5615 'id': 'a48o2S1cPoo',
5616 'ext': 'mp4',
5617 'title': 'The Young Turks - Live Main Show',
5618 'uploader': 'The Young Turks',
5619 'uploader_id': 'TheYoungTurks',
5620 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5621 'upload_date': '20150715',
5622 'license': 'Standard YouTube License',
5623 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5624 'categories': ['News & Politics'],
5625 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5626 'like_count': int,
a6213a49 5627 },
5628 'params': {
5629 'skip_download': True,
5630 },
5631 'only_matching': True,
5632 }, {
5633 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5634 'only_matching': True,
5635 }, {
5636 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5637 'only_matching': True,
5638 }, {
5639 'note': 'A channel that is not live. Should raise error',
5640 'url': 'https://www.youtube.com/user/numberphile/live',
5641 'only_matching': True,
5642 }, {
5643 'url': 'https://www.youtube.com/feed/trending',
5644 'only_matching': True,
5645 }, {
5646 'url': 'https://www.youtube.com/feed/library',
5647 'only_matching': True,
5648 }, {
5649 'url': 'https://www.youtube.com/feed/history',
5650 'only_matching': True,
5651 }, {
5652 'url': 'https://www.youtube.com/feed/subscriptions',
5653 'only_matching': True,
5654 }, {
5655 'url': 'https://www.youtube.com/feed/watch_later',
5656 'only_matching': True,
5657 }, {
5658 'note': 'Recommended - redirects to home page.',
5659 'url': 'https://www.youtube.com/feed/recommended',
5660 'only_matching': True,
5661 }, {
5662 'note': 'inline playlist with not always working continuations',
5663 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5664 'only_matching': True,
5665 }, {
5666 'url': 'https://www.youtube.com/course',
5667 'only_matching': True,
5668 }, {
5669 'url': 'https://www.youtube.com/zsecurity',
5670 'only_matching': True,
5671 }, {
5672 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5673 'only_matching': True,
5674 }, {
5675 'url': 'https://www.youtube.com/TheYoungTurks/live',
5676 'only_matching': True,
5677 }, {
5678 'url': 'https://www.youtube.com/hashtag/cctv9',
5679 'info_dict': {
5680 'id': 'cctv9',
5681 'title': '#cctv9',
976ae3ea 5682 'tags': [],
a6213a49 5683 },
4dc23a80 5684 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5685 }, {
5686 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5687 'only_matching': True,
5688 }, {
5689 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5690 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5691 'only_matching': True
5692 }, {
5693 'note': '/browse/ should redirect to /channel/',
5694 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5695 'only_matching': True
5696 }, {
5697 'note': 'VLPL, should redirect to playlist?list=PL...',
5698 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5699 'info_dict': {
5700 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5701 'uploader': 'NoCopyrightSounds',
5702 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5703 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5704 'title': 'NCS : All Releases 💿',
976ae3ea 5705 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5706 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5707 'modified_date': r're:\d{8}',
5708 'view_count': int,
5709 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5710 'tags': [],
5711 'channel': 'NoCopyrightSounds',
c26f9b99 5712 'availability': 'public',
a6213a49 5713 },
5714 'playlist_mincount': 166,
976ae3ea 5715 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5716 }, {
5717 'note': 'Topic, should redirect to playlist?list=UU...',
5718 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5719 'info_dict': {
5720 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5721 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5722 'title': 'Uploads from Royalty Free Music - Topic',
5723 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5724 'tags': [],
5725 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5726 'channel': 'Royalty Free Music - Topic',
5727 'view_count': int,
5728 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5729 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5730 'modified_date': r're:\d{8}',
5731 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5732 'description': '',
c26f9b99 5733 'availability': 'public',
a6213a49 5734 },
a6213a49 5735 'playlist_mincount': 101,
5736 }, {
86973308
M
5737 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5738 # Treat as a general feed
a6213a49 5739 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5740 'info_dict': {
5741 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5742 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5743 'tags': [],
a6213a49 5744 },
a6213a49 5745 'playlist_mincount': 9,
5746 }, {
5747 'note': 'Youtube music Album',
5748 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5749 'info_dict': {
5750 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5751 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5752 'tags': [],
5753 'view_count': int,
5754 'description': '',
5755 'availability': 'unlisted',
5756 'modified_date': r're:\d{8}',
a6213a49 5757 },
5758 'playlist_count': 50,
5759 }, {
5760 'note': 'unlisted single video playlist',
5761 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5762 'info_dict': {
5763 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5764 'uploader': 'colethedj',
5765 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5766 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5767 'availability': 'unlisted',
5768 'tags': [],
12a1b225 5769 'modified_date': '20220418',
976ae3ea 5770 'channel': 'colethedj',
5771 'view_count': int,
5772 'description': '',
5773 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5774 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5775 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5776 },
5777 'playlist_count': 1,
5778 }, {
5779 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5780 'url': 'https://www.youtube.com/feed/recommended',
5781 'info_dict': {
5782 'id': 'recommended',
5783 'title': 'recommended',
6c73052c 5784 'tags': [],
a6213a49 5785 },
5786 'playlist_mincount': 50,
5787 'params': {
5788 'skip_download': True,
5789 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5790 },
5791 }, {
5792 'note': 'API Fallback: /videos tab, sorted by oldest first',
5793 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5794 'info_dict': {
5795 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5796 'title': 'Cody\'sLab - Videos',
5797 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5798 'uploader': 'Cody\'sLab',
5799 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5800 'channel': 'Cody\'sLab',
5801 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5802 'tags': [],
5803 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5804 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5805 'channel_follower_count': int
a6213a49 5806 },
5807 'playlist_mincount': 650,
5808 'params': {
5809 'skip_download': True,
5810 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5811 },
86973308 5812 'skip': 'Query for sorting no longer works',
a6213a49 5813 }, {
5814 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5815 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5816 'info_dict': {
5817 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5818 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5819 'title': 'Uploads from Royalty Free Music - Topic',
5820 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5821 'modified_date': r're:\d{8}',
5822 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5823 'description': '',
5824 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5825 'tags': [],
5826 'channel': 'Royalty Free Music - Topic',
5827 'view_count': int,
5828 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
c26f9b99 5829 'availability': 'public',
a6213a49 5830 },
a6213a49 5831 'playlist_mincount': 101,
5832 'params': {
5833 'skip_download': True,
5834 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5835 },
7c219ea6 5836 }, {
5837 'note': 'non-standard redirect to regional channel',
5838 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5839 'only_matching': True
61d3665d 5840 }, {
5841 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5842 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5843 'info_dict': {
5844 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5845 'modified_date': '20220407',
5846 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5847 'tags': [],
5848 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5849 'uploader': 'pukkandan',
5850 'availability': 'unlisted',
5851 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5852 'channel': 'pukkandan',
5853 'description': 'Test for collaborative playlist',
5854 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5855 'view_count': int,
61d3665d 5856 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5857 },
5858 'playlist_mincount': 2
c26f9b99 5859 }, {
5860 'note': 'translated tab name',
5861 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5862 'info_dict': {
5863 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5864 'tags': [],
5865 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5866 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 5867 'description': 'test description',
c26f9b99 5868 'title': 'cole-dlp-test-acc - 再生リスト',
5869 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5870 'uploader': 'cole-dlp-test-acc',
5871 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5872 'channel': 'cole-dlp-test-acc',
5873 },
5874 'playlist_mincount': 1,
5875 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5876 'expected_warnings': ['Preferring "ja"'],
5877 }, {
5878 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5879 'note': 'preferred lang set with playlist with translated video titles',
5880 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5881 'info_dict': {
5882 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5883 'tags': [],
5884 'view_count': int,
5885 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5886 'uploader': 'cole-dlp-test-acc',
5887 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5888 'channel': 'cole-dlp-test-acc',
5889 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5890 'description': 'test',
5891 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5892 'title': 'dlp test playlist',
5893 'availability': 'public',
5894 },
5895 'playlist_mincount': 1,
5896 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5897 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 5898 }, {
5899 # shorts audio pivot for 2GtVksBMYFM.
5900 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5901 'info_dict': {
5902 'id': 'sfv_audio_pivot',
5903 'title': 'sfv_audio_pivot',
5904 'tags': [],
5905 },
5906 'playlist_mincount': 50,
5907
86973308
M
5908 }, {
5909 # Channel with a real live tab (not to be mistaken with streams tab)
5910 # Do not treat like it should redirect to live stream
5911 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5912 'info_dict': {
5913 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5914 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5915 'tags': [],
5916 },
5917 'playlist_mincount': 20,
5918 }, {
5919 # Tab name is not the same as tab id
5920 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5921 'info_dict': {
5922 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5923 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5924 'tags': [],
5925 },
5926 'playlist_mincount': 8,
5927 }, {
5928 # Home tab id is literally home. Not to get mistaken with featured
5929 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5930 'info_dict': {
5931 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5932 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5933 'tags': [],
5934 },
5935 'playlist_mincount': 8,
5936 }, {
5937 # Should get three playlists for videos, shorts and streams tabs
5938 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5939 'info_dict': {
5940 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 5941 'title': 'Polka Ch. 尾丸ポルカ',
5942 'channel_follower_count': int,
5943 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5944 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5945 'uploader': 'Polka Ch. 尾丸ポルカ',
5946 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5947 'channel': 'Polka Ch. 尾丸ポルカ',
5948 'tags': 'count:35',
5949 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5950 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
86973308
M
5951 },
5952 'playlist_count': 3,
5953 }, {
5954 # Shorts tab with channel with handle
5955 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5956 'info_dict': {
5957 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5958 'title': 'Not Just Bikes - Shorts',
5959 'tags': 'count:12',
5960 'uploader': 'Not Just Bikes',
5961 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5962 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5963 'channel_follower_count': int,
5964 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5965 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5966 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5967 'channel': 'Not Just Bikes',
5968 },
5969 'playlist_mincount': 10,
5970 }, {
5971 # Streams tab
5972 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5973 'info_dict': {
5974 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5975 'title': '中村悠一 - Live',
5976 'tags': 'count:7',
5977 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5978 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5979 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5980 'channel': '中村悠一',
5981 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5982 'channel_follower_count': int,
5983 'uploader': '中村悠一',
5984 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5985 },
5986 'playlist_mincount': 60,
5987 }, {
5988 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5989 # See test_youtube_lists
5990 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5991 'only_matching': True,
5992 }, {
5993 # No uploads and no UCID given. Should fail with no uploads error
5994 # See test_youtube_lists
5995 'url': 'https://www.youtube.com/news',
5996 'only_matching': True
5997 }, {
5998 # No videos tab but has a shorts tab
5999 'url': 'https://www.youtube.com/c/TKFShorts',
6000 'info_dict': {
6001 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6002 'title': 'Shorts Break - Shorts',
6003 'tags': 'count:32',
6004 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6005 'channel': 'Shorts Break',
6006 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
6007 'uploader': 'Shorts Break',
6008 'channel_follower_count': int,
6009 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6010 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6011 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
6012 },
6013 'playlist_mincount': 30,
6014 }, {
6015 # Trending Now Tab. tab id is empty
6016 'url': 'https://www.youtube.com/feed/trending',
6017 'info_dict': {
6018 'id': 'trending',
6019 'title': 'trending - Now',
6020 'tags': [],
6021 },
6022 'playlist_mincount': 30,
6023 }, {
6024 # Trending Gaming Tab. tab id is empty
6025 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6026 'info_dict': {
6027 'id': 'trending',
6028 'title': 'trending - Gaming',
6029 'tags': [],
6030 },
6031 'playlist_mincount': 30,
4dc23a80
M
6032 }, {
6033 # Shorts url result in shorts tab
6034 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6035 'info_dict': {
6036 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6037 'title': 'cole-dlp-test-acc - Shorts',
6038 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6039 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6040 'description': 'test description',
6041 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6042 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6043 'tags': [],
6044 'uploader': 'cole-dlp-test-acc',
6045 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6046
6047 },
6048 'playlist': [{
6049 'info_dict': {
6050 '_type': 'url',
6051 'ie_key': 'Youtube',
6052 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6053 'id': 'sSM9J5YH_60',
6054 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6055 'title': 'SHORT short',
6056 'channel': 'cole-dlp-test-acc',
6057 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6058 'view_count': int,
6059 'thumbnails': list,
6060 }
6061 }],
6062 'params': {'extract_flat': True},
6063 }, {
6064 # Live video status should be extracted
6065 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6066 'info_dict': {
6067 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6068 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6069 'tags': []
6070 },
6071 'playlist': [{
6072 'info_dict': {
6073 '_type': 'url',
6074 'ie_key': 'Youtube',
6075 'url': 'startswith:https://www.youtube.com/watch?v=',
6076 'id': str,
6077 'title': str,
6078 'live_status': 'is_live',
6079 'channel_id': str,
6080 'channel_url': str,
6081 'concurrent_view_count': int,
6082 'channel': str,
6083 }
6084 }],
c7335551 6085 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6086 'playlist_mincount': 1
c7335551
M
6087 }, {
6088 # Channel renderer metadata. Contains number of videos on the channel
6089 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6090 'info_dict': {
6091 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6092 'title': 'cole-dlp-test-acc - Channels',
6093 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6094 'channel': 'cole-dlp-test-acc',
6095 'description': 'test description',
6096 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6097 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6098 'tags': [],
6099 'uploader': 'cole-dlp-test-acc',
6100 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6101
6102 },
6103 'playlist': [{
6104 'info_dict': {
6105 '_type': 'url',
6106 'ie_key': 'YoutubeTab',
6107 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6108 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6109 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6110 'title': 'PewDiePie',
6111 'channel': 'PewDiePie',
6112 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6113 'thumbnails': list,
6114 'channel_follower_count': int,
6115 'playlist_count': int
6116 }
6117 }],
6118 'params': {'extract_flat': True},
a6213a49 6119 }]
6120
6121 @classmethod
6122 def suitable(cls, url):
86e5f3ed 6123 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6124
86973308
M
6125 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6126
6127 def _get_url_mobj(self, url):
6128 mobj = self._URL_RE.match(url).groupdict()
6129 mobj.update((k, '') for k, v in mobj.items() if v is None)
6130 return mobj
6131
6132 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6133 tab_name = (tab.get('title') or '').lower()
6134 tab_url = urljoin(base_url, traverse_obj(
6135 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6136
bd7e919a 6137 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6138 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6139 if tab_id:
bd7e919a 6140 return {
6141 'TAB_ID_SPONSORSHIPS': 'membership',
6142 }.get(tab_id, tab_id), tab_name
86973308
M
6143
6144 # Fallback to tab name if we cannot get the tab id.
6145 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6146 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6147 if tab_name:
6148 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6149 return {
6150 'home': 'featured',
6151 'live': 'streams',
6152 }.get(tab_name, tab_name), tab_name
6153
6154 def _has_tab(self, tabs, tab_id):
6155 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6156
182bda88 6157 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6158 def _real_extract(self, url, smuggled_data):
cd7c66cf 6159 item_id = self._match_id(url)
14f25df2 6160 url = urllib.parse.urlunparse(
6161 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6162 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6163
86973308
M
6164 mobj = self._get_url_mobj(url)
6165 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6166 if is_channel and smuggled_data.get('is_music_url'):
6167 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6168 return self.url_result(
6169 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6170 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6171 mdata = self._extract_tab_endpoint(
6172 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6173 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6174 get_all=False, expected_type=str)
6175 if not murl:
6176 raise ExtractorError('Failed to resolve album to playlist')
6177 return self.url_result(murl, YoutubeTabIE)
6178 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6179 return self.url_result(
6180 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6181
6182 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6183 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6184 url = f'{pre}/videos{post}'
cd7c66cf 6185
6186 # Handle both video/playlist URLs
201c1459 6187 qs = parse_qs(url)
bd7e919a 6188 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6189 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6190 if not playlist_id:
fe03a6cd 6191 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6192 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6193 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6194 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6195 return self.url_result(
6196 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6197
86973308
M
6198 if not self._yes_playlist(playlist_id, video_id):
6199 return self.url_result(
6200 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6201
bd7e919a 6202 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6203
7c219ea6 6204 # YouTube may provide a non-standard redirect to the regional channel
6205 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6206 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6207 redirect_url = traverse_obj(
6208 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6209 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6210 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6211 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6212 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6213
bd7e919a 6214 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6215 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6216 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6217 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6218 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6219
6220 if not original_tab_id and selected_tab_name:
bd7e919a 6221 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6222 'To download only the videos in a specific tab, pass the tab\'s URL')
6223 if self._has_tab(tabs, 'streams'):
bd7e919a 6224 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6225 if self._has_tab(tabs, 'shorts'):
bd7e919a 6226 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6227 # XXX: Members-only tab should also be extracted
6228
bd7e919a 6229 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6230 # Channel does not have streams, shorts or videos tabs
6231 if item_id[:2] != 'UC':
6232 raise ExtractorError('This channel has no uploads', expected=True)
6233
6234 # Topic channels don't have /videos. Use the equivalent playlist instead
6235 pl_id = f'UU{item_id[2:]}'
6236 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6237 try:
6238 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6239 except ExtractorError:
6240 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6241 else:
86973308
M
6242 item_id, url = pl_id, pl_url
6243 self.to_screen(
6244 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6245
bd7e919a 6246 elif extra_tabs and selected_tab_id != 'videos':
86973308 6247 # When there are shorts/live tabs but not videos tab
bd7e919a 6248 url, data = f'{pre}{post}', None
86973308
M
6249
6250 elif (original_tab_id or 'videos') != selected_tab_id:
6251 if original_tab_id == 'live':
6252 # Live tab should have redirected to the video
6253 # Except in the case the channel has an actual live tab
6254 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6255 raise UserNotLive(video_id=item_id)
86973308
M
6256 elif selected_tab_name:
6257 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6258
6259 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6260 url = f'{pre}{post}'
18db7548 6261
358de58c 6262 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6263 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6264 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6265 self._extract_and_report_alerts(data, only_once=True)
86973308 6266
bd7e919a 6267 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6268 if tabs:
bd7e919a 6269 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6270 entries[0].update({
86973308
M
6271 'extractor_key': YoutubeTabIE.ie_key(),
6272 'extractor': YoutubeTabIE.IE_NAME,
6273 'webpage_url': url,
6274 })
bd7e919a 6275 if self.get_param('playlist_items') == '0':
6276 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6277 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6278 entries.extend(map(self._real_extract, extra_tabs))
6279
6280 if len(entries) == 1:
6281 return entries[0]
6282 elif entries:
6283 metadata = self._extract_metadata_from_tabs(item_id, data)
6284 uploads_url = 'the Uploads (UU) playlist URL'
6285 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6286 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6287 self.to_screen(
6288 'Downloading as multiple playlists, separated by tabs. '
6289 f'To download as a single playlist instead, pass {uploads_url}')
6290 return self.playlist_result(entries, item_id, **metadata)
6291
6292 # Inline playlist
37e57a9f 6293 playlist = traverse_obj(
6294 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6295 if playlist:
ac56cf38 6296 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6297
37e57a9f 6298 video_id = traverse_obj(
6299 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6300 if video_id:
bd7e919a 6301 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6302 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6303 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6304
8bdd16b4 6305 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6306
c5e8d7af 6307
8bdd16b4 6308class YoutubePlaylistIE(InfoExtractor):
96565c7e 6309 IE_DESC = 'YouTube playlists'
8bdd16b4 6310 _VALID_URL = r'''(?x)(?:
6311 (?:https?://)?
6312 (?:\w+\.)?
6313 (?:
6314 (?:
6315 youtube(?:kids)?\.com|
d9190e44 6316 %(invidious)s
8bdd16b4 6317 )
6318 /.*?\?.*?\blist=
6319 )?
6320 (?P<id>%(playlist_id)s)
d9190e44
RH
6321 )''' % {
6322 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6323 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6324 }
8bdd16b4 6325 IE_NAME = 'youtube:playlist'
cdc628a4 6326 _TESTS = [{
8bdd16b4 6327 'note': 'issue #673',
6328 'url': 'PLBB231211A4F62143',
cdc628a4 6329 'info_dict': {
8bdd16b4 6330 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6331 'id': 'PLBB231211A4F62143',
976ae3ea 6332 'uploader': 'Wickman',
8bdd16b4 6333 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 6334 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6335 'view_count': int,
86973308 6336 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
976ae3ea 6337 'modified_date': r're:\d{8}',
6338 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6339 'channel': 'Wickman',
6340 'tags': [],
86973308
M
6341 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6342 'availability': 'public',
8bdd16b4 6343 },
6344 'playlist_mincount': 29,
6345 }, {
6346 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6347 'info_dict': {
6348 'title': 'YDL_safe_search',
6349 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6350 },
6351 'playlist_count': 2,
6352 'skip': 'This playlist is private',
9558dcec 6353 }, {
8bdd16b4 6354 'note': 'embedded',
6355 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6356 'playlist_count': 4,
9558dcec 6357 'info_dict': {
8bdd16b4 6358 'title': 'JODA15',
6359 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6360 'uploader': 'milan',
6361 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 6362 'description': '',
6363 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6364 'tags': [],
6365 'modified_date': '20140919',
6366 'view_count': int,
6367 'channel': 'milan',
6368 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6369 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
c26f9b99 6370 'availability': 'public',
976ae3ea 6371 },
86973308 6372 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6373 }, {
8bdd16b4 6374 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6375 'playlist_mincount': 455,
8bdd16b4 6376 'info_dict': {
6377 'title': '2018 Chinese New Singles (11/6 updated)',
6378 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6379 'uploader': 'LBK',
6380 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 6381 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6382 'channel': 'LBK',
6383 'view_count': int,
6384 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6385 'tags': [],
6386 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6387 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6388 'modified_date': r're:\d{8}',
c26f9b99 6389 'availability': 'public',
976ae3ea 6390 },
6391 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6392 }, {
29f7c58a 6393 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6394 'only_matching': True,
6395 }, {
6396 # music album playlist
6397 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6398 'only_matching': True,
6399 }]
6400
6401 @classmethod
6402 def suitable(cls, url):
201c1459 6403 if YoutubeTabIE.suitable(url):
6404 return False
49a57e70 6405 from ..utils import parse_qs
201c1459 6406 qs = parse_qs(url)
6407 if qs.get('v', [None])[0]:
6408 return False
86e5f3ed 6409 return super().suitable(url)
29f7c58a 6410
6411 def _real_extract(self, url):
6412 playlist_id = self._match_id(url)
46953e7e 6413 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6414 url = update_url_query(
6415 'https://www.youtube.com/playlist',
6416 parse_qs(url) or {'list': playlist_id})
6417 if is_music_url:
6418 url = smuggle_url(url, {'is_music_url': True})
6419 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6420
6421
6422class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6423 IE_DESC = 'youtu.be'
29f7c58a 6424 _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}
6425 _TESTS = [{
8bdd16b4 6426 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6427 'info_dict': {
6428 'id': 'yeWKywCrFtk',
6429 'ext': 'mp4',
6430 'title': 'Small Scale Baler and Braiding Rugs',
6431 'uploader': 'Backus-Page House Museum',
6432 'uploader_id': 'backuspagemuseum',
6433 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6434 'upload_date': '20161008',
6435 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6436 'categories': ['Nonprofits & Activism'],
6437 'tags': list,
6438 'like_count': int,
976ae3ea 6439 'age_limit': 0,
6440 'playable_in_embed': True,
6441 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6442 'channel': 'Backus-Page House Museum',
6443 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6444 'live_status': 'not_live',
6445 'view_count': int,
6446 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6447 'availability': 'public',
6448 'duration': 59,
12a1b225
A
6449 'comment_count': int,
6450 'channel_follower_count': int
8bdd16b4 6451 },
6452 'params': {
6453 'noplaylist': True,
6454 'skip_download': True,
6455 },
39e7107d 6456 }, {
8bdd16b4 6457 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6458 'only_matching': True,
cdc628a4
PH
6459 }]
6460
8bdd16b4 6461 def _real_extract(self, url):
5ad28e7f 6462 mobj = self._match_valid_url(url)
29f7c58a 6463 video_id = mobj.group('id')
6464 playlist_id = mobj.group('playlist_id')
8bdd16b4 6465 return self.url_result(
29f7c58a 6466 update_url_query('https://www.youtube.com/watch', {
6467 'v': video_id,
6468 'list': playlist_id,
6469 'feature': 'youtu.be',
6470 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6471
6472
b6ce9bb0 6473class YoutubeLivestreamEmbedIE(InfoExtractor):
6474 IE_DESC = 'YouTube livestream embeds'
6475 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6476 _TESTS = [{
6477 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6478 'only_matching': True,
6479 }]
6480
6481 def _real_extract(self, url):
6482 channel_id = self._match_id(url)
6483 return self.url_result(
6484 f'https://www.youtube.com/channel/{channel_id}/live',
6485 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6486
6487
8bdd16b4 6488class YoutubeYtUserIE(InfoExtractor):
96565c7e 6489 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6490 IE_NAME = 'youtube:user'
8bdd16b4 6491 _VALID_URL = r'ytuser:(?P<id>.+)'
6492 _TESTS = [{
6493 'url': 'ytuser:phihag',
6494 'only_matching': True,
6495 }]
6496
6497 def _real_extract(self, url):
6498 user_id = self._match_id(url)
08270da5 6499 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6500
b05654f0 6501
3d3dddc9 6502class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6503 IE_NAME = 'youtube:favorites'
96565c7e 6504 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6505 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6506 _LOGIN_REQUIRED = True
6507 _TESTS = [{
6508 'url': ':ytfav',
6509 'only_matching': True,
6510 }, {
6511 'url': ':ytfavorites',
6512 'only_matching': True,
6513 }]
6514
6515 def _real_extract(self, url):
6516 return self.url_result(
6517 'https://www.youtube.com/playlist?list=LL',
6518 ie=YoutubeTabIE.ie_key())
6519
6520
ca5300c7 6521class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6522 IE_NAME = 'youtube:notif'
6523 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6524 _VALID_URL = r':ytnotif(?:ication)?s?'
6525 _LOGIN_REQUIRED = True
6526 _TESTS = [{
6527 'url': ':ytnotif',
6528 'only_matching': True,
6529 }, {
6530 'url': ':ytnotifications',
6531 'only_matching': True,
6532 }]
6533
6534 def _extract_notification_menu(self, response, continuation_list):
6535 notification_list = traverse_obj(
6536 response,
6537 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6538 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6539 expected_type=list) or []
6540 continuation_list[0] = None
6541 for item in notification_list:
6542 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6543 if entry:
6544 yield entry
6545 continuation = item.get('continuationItemRenderer')
6546 if continuation:
6547 continuation_list[0] = continuation
6548
6549 def _extract_notification_renderer(self, notification):
6550 video_id = traverse_obj(
6551 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6552 url = f'https://www.youtube.com/watch?v={video_id}'
6553 channel_id = None
6554 if not video_id:
6555 browse_ep = traverse_obj(
6556 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
6557 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
6558 post_id = self._search_regex(
6559 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6560 'post id', default=None)
6561 if not channel_id or not post_id:
6562 return
6563 # The direct /post url redirects to this in the browser
6564 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6565
6566 channel = traverse_obj(
6567 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6568 expected_type=str)
c7a7baaa 6569 notification_title = self._get_text(notification, 'shortMessage')
6570 if notification_title:
6571 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6572 # TODO: handle recommended videos
ca5300c7 6573 title = self._search_regex(
c7a7baaa 6574 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6575 'video title', default=None)
5225df50 6576 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6577 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6578 else None)
ca5300c7 6579 return {
6580 '_type': 'url',
6581 'url': url,
6582 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6583 'video_id': video_id,
6584 'title': title,
6585 'channel_id': channel_id,
6586 'channel': channel,
6587 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6588 'timestamp': timestamp,
ca5300c7 6589 }
6590
6591 def _notification_menu_entries(self, ytcfg):
6592 continuation_list = [None]
6593 response = None
6594 for page in itertools.count(1):
6595 ctoken = traverse_obj(
6596 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6597 response = self._extract_response(
6598 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6599 ep='notification/get_notification_menu', check_get_keys='actions',
6600 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6601 yield from self._extract_notification_menu(response, continuation_list)
6602 if not continuation_list[0]:
6603 break
6604
6605 def _real_extract(self, url):
6606 display_id = 'notifications'
6607 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6608 self._report_playlist_authcheck(ytcfg)
6609 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6610
6611
a6213a49 6612class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6613 IE_DESC = 'YouTube search'
78caa52a 6614 IE_NAME = 'youtube:search'
b05654f0 6615 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6616 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6617 _TESTS = [{
6618 'url': 'ytsearch5:youtube-dl test video',
6619 'playlist_count': 5,
6620 'info_dict': {
6621 'id': 'youtube-dl test video',
6622 'title': 'youtube-dl test video',
6623 }
6624 }]
b05654f0 6625
a61fd4cf 6626
5f7cb91a 6627class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6628 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6629 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6630 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6631 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6632 _TESTS = [{
6633 'url': 'ytsearchdate5:youtube-dl test video',
6634 'playlist_count': 5,
6635 'info_dict': {
6636 'id': 'youtube-dl test video',
6637 'title': 'youtube-dl test video',
6638 }
6639 }]
75dff0ee 6640
c9ae7b95 6641
a6213a49 6642class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6643 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6644 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6645 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6646 _TESTS = [{
6647 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6648 'playlist_mincount': 5,
6649 'info_dict': {
11f9be09 6650 'id': 'youtube-dl test video',
3462ffa8 6651 'title': 'youtube-dl test video',
6652 }
a61fd4cf 6653 }, {
6654 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6655 'playlist_mincount': 5,
6656 'info_dict': {
6657 'id': 'python',
6658 'title': 'python',
6659 }
ad210f4f 6660 }, {
6661 'url': 'https://www.youtube.com/results?search_query=%23cats',
6662 'playlist_mincount': 1,
6663 'info_dict': {
6664 'id': '#cats',
6665 'title': '#cats',
12a1b225
A
6666 # The test suite does not have support for nested playlists
6667 # 'entries': [{
6668 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6669 # 'title': '#cats',
6670 # }],
ad210f4f 6671 },
c7335551
M
6672 }, {
6673 # Channel results
6674 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6675 'info_dict': {
6676 'id': 'kurzgesagt',
6677 'title': 'kurzgesagt',
6678 },
6679 'playlist': [{
6680 'info_dict': {
6681 '_type': 'url',
6682 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6683 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6684 'ie_key': 'YoutubeTab',
6685 'channel': 'Kurzgesagt – In a Nutshell',
6686 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6687 'title': 'Kurzgesagt – In a Nutshell',
6688 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6689 'playlist_count': int, # XXX: should have a way of saying > 1
6690 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6691 'thumbnails': list
6692 }
6693 }],
6694 'params': {'extract_flat': True, 'playlist_items': '1'},
6695 'playlist_mincount': 1,
3462ffa8 6696 }, {
6697 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6698 'only_matching': True,
6699 }]
6700
6701 def _real_extract(self, url):
4dfbf869 6702 qs = parse_qs(url)
386e1dd9 6703 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6704 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6705
6706
16aa9ea4 6707class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6708 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6709 IE_NAME = 'youtube:music:search_url'
6710 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6711 _TESTS = [{
6712 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6713 'playlist_count': 16,
6714 'info_dict': {
6715 'id': 'royalty free music',
6716 'title': 'royalty free music',
6717 }
6718 }, {
6719 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6720 'playlist_mincount': 30,
6721 'info_dict': {
6722 'id': 'royalty free music - songs',
6723 'title': 'royalty free music - songs',
6724 },
6725 'params': {'extract_flat': 'in_playlist'}
6726 }, {
6727 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6728 'playlist_mincount': 30,
6729 'info_dict': {
6730 'id': 'royalty free music - community playlists',
6731 'title': 'royalty free music - community playlists',
6732 },
6733 'params': {'extract_flat': 'in_playlist'}
6734 }]
6735
6736 _SECTIONS = {
6737 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6738 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6739 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6740 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6741 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6742 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6743 }
6744
6745 def _real_extract(self, url):
6746 qs = parse_qs(url)
6747 query = (qs.get('search_query') or qs.get('q'))[0]
6748 params = qs.get('sp', (None,))[0]
6749 if params:
6750 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6751 else:
ac668111 6752 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6753 params = self._SECTIONS.get(section)
6754 if not params:
6755 section = None
6756 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6757 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6758
6759
182bda88 6760class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6761 """
25f14e9f 6762 Base class for feed extractors
82d02080 6763 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6764 """
b2e8bc1b 6765 _LOGIN_REQUIRED = True
82d02080 6766 _FEED_NAME = 'feeds'
a25bca9f 6767
6768 def _real_initialize(self):
6769 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6770
82d02080 6771 @classproperty
d7ae0639 6772 def IE_NAME(self):
82d02080 6773 return f'youtube:{self._FEED_NAME}'
04cc9617 6774
3853309f 6775 def _real_extract(self, url):
3d3dddc9 6776 return self.url_result(
182bda88 6777 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6778
6779
ef2f3c7f 6780class YoutubeWatchLaterIE(InfoExtractor):
6781 IE_NAME = 'youtube:watchlater'
96565c7e 6782 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6783 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6784 _TESTS = [{
8bdd16b4 6785 'url': ':ytwatchlater',
bc7a9cd8
S
6786 'only_matching': True,
6787 }]
25f14e9f
S
6788
6789 def _real_extract(self, url):
ef2f3c7f 6790 return self.url_result(
6791 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6792
6793
25f14e9f 6794class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6795 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6796 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6797 _FEED_NAME = 'recommended'
45db527f 6798 _LOGIN_REQUIRED = False
3d3dddc9 6799 _TESTS = [{
6800 'url': ':ytrec',
6801 'only_matching': True,
6802 }, {
6803 'url': ':ytrecommended',
6804 'only_matching': True,
6805 }, {
6806 'url': 'https://youtube.com',
6807 'only_matching': True,
6808 }]
1ed5b5c9 6809
1ed5b5c9 6810
25f14e9f 6811class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6812 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6813 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6814 _FEED_NAME = 'subscriptions'
3d3dddc9 6815 _TESTS = [{
6816 'url': ':ytsubs',
6817 'only_matching': True,
6818 }, {
6819 'url': ':ytsubscriptions',
6820 'only_matching': True,
6821 }]
1ed5b5c9 6822
1ed5b5c9 6823
25f14e9f 6824class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 6825 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 6826 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 6827 _FEED_NAME = 'history'
3d3dddc9 6828 _TESTS = [{
6829 'url': ':ythistory',
6830 'only_matching': True,
6831 }]
1ed5b5c9
JMF
6832
6833
6e634cbe 6834class YoutubeStoriesIE(InfoExtractor):
6835 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
6836 IE_NAME = 'youtube:stories'
6837 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6838 _TESTS = [{
6839 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6840 'only_matching': True,
6841 }]
6842
6843 def _real_extract(self, url):
6844 playlist_id = f'RLTD{self._match_id(url)}'
6845 return self.url_result(
50ac0e54 6846 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 6847 ie=YoutubeTabIE, video_id=playlist_id)
6848
6849
80eb0bd9 6850class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 6851 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 6852 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 6853 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 6854 _TESTS = [{
1dd18a88 6855 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 6856 'only_matching': True,
6857 }]
6858
6859 @staticmethod
6860 def _generate_audio_pivot_params(video_id):
6861 """
6862 Generates sfv_audio_pivot browse params for this video id
6863 """
6864 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
6865 return urllib.parse.quote(base64.b64encode(pb_params).decode())
6866
6867 def _real_extract(self, url):
6868 video_id = self._match_id(url)
6869 return self.url_result(
6870 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6871 ie=YoutubeTabIE)
6872
6873
15870e90
PH
6874class YoutubeTruncatedURLIE(InfoExtractor):
6875 IE_NAME = 'youtube:truncated_url'
6876 IE_DESC = False # Do not list
975d35db 6877 _VALID_URL = r'''(?x)
b95aab84
PH
6878 (?:https?://)?
6879 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6880 (?:watch\?(?:
c4808c60 6881 feature=[a-z_]+|
b95aab84
PH
6882 annotation_id=annotation_[^&]+|
6883 x-yt-cl=[0-9]+|
c1708b89 6884 hl=[^&]*|
287be8c6 6885 t=[0-9]+
b95aab84
PH
6886 )?
6887 |
6888 attribution_link\?a=[^&]+
6889 )
6890 $
975d35db 6891 '''
15870e90 6892
c4808c60 6893 _TESTS = [{
2d3d2997 6894 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6895 'only_matching': True,
dc2fc736 6896 }, {
2d3d2997 6897 'url': 'https://www.youtube.com/watch?',
dc2fc736 6898 'only_matching': True,
b95aab84
PH
6899 }, {
6900 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6901 'only_matching': True,
6902 }, {
6903 'url': 'https://www.youtube.com/watch?feature=foo',
6904 'only_matching': True,
c1708b89
PH
6905 }, {
6906 'url': 'https://www.youtube.com/watch?hl=en-GB',
6907 'only_matching': True,
287be8c6
PH
6908 }, {
6909 'url': 'https://www.youtube.com/watch?t=2372',
6910 'only_matching': True,
c4808c60
PH
6911 }]
6912
15870e90
PH
6913 def _real_extract(self, url):
6914 raise ExtractorError(
78caa52a
PH
6915 'Did you forget to quote the URL? Remember that & is a meta '
6916 'character in most shells, so you want to put the URL in quotes, '
3867038a 6917 'like youtube-dl '
2d3d2997 6918 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6919 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6920 expected=True)
772fd5cc
PH
6921
6922
471d0367 6923class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6924 IE_NAME = 'youtube:clip'
471d0367 6925 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6926 _TESTS = [{
6927 # FIXME: Other metadata should be extracted from the clip, not from the base video
6928 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6929 'info_dict': {
6930 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6931 'ext': 'mp4',
6932 'section_start': 29.0,
6933 'section_end': 39.7,
6934 'duration': 10.7,
12a1b225
A
6935 'age_limit': 0,
6936 'availability': 'public',
6937 'categories': ['Gaming'],
6938 'channel': 'Scott The Woz',
6939 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6940 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6941 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6942 'like_count': int,
6943 'playable_in_embed': True,
6944 'tags': 'count:17',
6945 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6946 'title': 'Mobile Games on Console - Scott The Woz',
6947 'upload_date': '20210920',
6948 'uploader': 'Scott The Woz',
6949 'uploader_id': 'scottthewoz',
6950 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6951 'view_count': int,
6952 'live_status': 'not_live',
6953 'channel_follower_count': int
471d0367 6954 }
6955 }]
3cd786db 6956
6957 def _real_extract(self, url):
471d0367 6958 clip_id = self._match_id(url)
6959 _, data = self._extract_webpage(url, clip_id)
6960
6961 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6962 if not video_id:
6963 raise ExtractorError('Unable to find video ID')
6964
6965 clip_data = traverse_obj(data, (
6966 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6967 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6968 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6969 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6970
6971 return {
6972 '_type': 'url_transparent',
6973 'url': f'https://www.youtube.com/watch?v={video_id}',
6974 'ie_key': YoutubeIE.ie_key(),
6975 'id': clip_id,
6976 'section_start': int(clip_data['startTimeMs']) / 1000,
6977 'section_end': int(clip_data['endTimeMs']) / 1000,
6978 }
3cd786db 6979
6980
b032ff0f 6981class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
6982 IE_NAME = 'youtube:consent'
6983 IE_DESC = False # Do not list
6984 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
6985 _TESTS = [{
6986 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1',
6987 'info_dict': {
6988 'id': 'qVv6vCqciTM',
6989 'ext': 'mp4',
6990 'age_limit': 0,
6991 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
6992 'comment_count': int,
6993 'chapters': 'count:13',
6994 'upload_date': '20221223',
6995 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
6996 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
6997 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
6998 'like_count': int,
6999 'release_date': '20221223',
7000 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7001 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
7002 'view_count': int,
7003 'playable_in_embed': True,
7004 'duration': 4438,
7005 'availability': 'public',
7006 'channel_follower_count': int,
7007 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7008 'categories': ['Entertainment'],
7009 'live_status': 'was_live',
7010 'release_timestamp': 1671793345,
7011 'channel': 'さなちゃんねる',
7012 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7013 'uploader': 'さなちゃんねる',
7014 },
7015 'add_ie': ['Youtube'],
7016 'params': {'skip_download': 'Youtube'},
7017 }]
7018
7019 def _real_extract(self, url):
7020 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7021 if not redirect_url:
7022 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7023 return self.url_result(redirect_url)
7024
7025
772fd5cc
PH
7026class YoutubeTruncatedIDIE(InfoExtractor):
7027 IE_NAME = 'youtube:truncated_id'
7028 IE_DESC = False # Do not list
b95aab84 7029 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7030
7031 _TESTS = [{
7032 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7033 'only_matching': True,
7034 }]
7035
7036 def _real_extract(self, url):
7037 video_id = self._match_id(url)
7038 raise ExtractorError(
86e5f3ed 7039 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7040 expected=True)