]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/vrt] Overhaul extractors (#6244)
[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
c795c39f 69STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
962ffcf8 70# any clients starting with _ cannot be explicitly requested by the user
000c15a4 71INNERTUBE_CLIENTS = {
72 'web': {
73 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
74 'INNERTUBE_CONTEXT': {
75 'client': {
76 'clientName': 'WEB',
a0c830f4 77 'clientVersion': '2.20220801.00.00',
000c15a4 78 }
79 },
80 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
81 },
82 'web_embedded': {
83 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
84 'INNERTUBE_CONTEXT': {
85 'client': {
86 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 87 'clientVersion': '1.20220731.00.00',
000c15a4 88 },
89 },
90 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
91 },
92 'web_music': {
93 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
94 'INNERTUBE_HOST': 'music.youtube.com',
95 'INNERTUBE_CONTEXT': {
96 'client': {
97 'clientName': 'WEB_REMIX',
a0c830f4 98 'clientVersion': '1.20220727.01.00',
000c15a4 99 }
100 },
101 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
102 },
e7e94f2a 103 'web_creator': {
18c7683d 104 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
105 'INNERTUBE_CONTEXT': {
106 'client': {
107 'clientName': 'WEB_CREATOR',
a0c830f4 108 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
109 }
110 },
111 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
112 },
000c15a4 113 'android': {
18c7683d 114 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 115 'INNERTUBE_CONTEXT': {
116 'client': {
117 'clientName': 'ANDROID',
50ac0e54 118 'clientVersion': '17.31.35',
119 'androidSdkVersion': 30,
120 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 121 }
122 },
123 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 124 'REQUIRE_JS_PLAYER': False
000c15a4 125 },
126 'android_embedded': {
18c7683d 127 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 128 'INNERTUBE_CONTEXT': {
129 'client': {
130 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 131 'clientVersion': '17.31.35',
132 'androidSdkVersion': 30,
133 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 134 },
135 },
b6de707d 136 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
137 'REQUIRE_JS_PLAYER': False
000c15a4 138 },
139 'android_music': {
18c7683d 140 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 141 'INNERTUBE_CONTEXT': {
142 'client': {
143 'clientName': 'ANDROID_MUSIC',
a0c830f4 144 'clientVersion': '5.16.51',
50ac0e54 145 'androidSdkVersion': 30,
146 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 147 }
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 150 'REQUIRE_JS_PLAYER': False
000c15a4 151 },
e7e94f2a 152 'android_creator': {
18c7683d 153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
154 'INNERTUBE_CONTEXT': {
155 'client': {
156 'clientName': 'ANDROID_CREATOR',
50ac0e54 157 'clientVersion': '22.30.100',
158 'androidSdkVersion': 30,
159 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
160 },
161 },
b6de707d 162 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
163 'REQUIRE_JS_PLAYER': False
e7e94f2a 164 },
18c7683d 165 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
166 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 167 'ios': {
18c7683d 168 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 169 'INNERTUBE_CONTEXT': {
170 'client': {
171 'clientName': 'IOS',
224b5a35 172 'clientVersion': '17.33.2',
18c7683d 173 'deviceModel': 'iPhone14,3',
224b5a35 174 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 175 }
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_embedded': {
000c15a4 181 'INNERTUBE_CONTEXT': {
182 'client': {
183 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 184 'clientVersion': '17.33.2',
18c7683d 185 'deviceModel': 'iPhone14,3',
224b5a35 186 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 187 },
188 },
b6de707d 189 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
190 'REQUIRE_JS_PLAYER': False
000c15a4 191 },
192 'ios_music': {
18c7683d 193 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 194 'INNERTUBE_CONTEXT': {
195 'client': {
196 'clientName': 'IOS_MUSIC',
224b5a35
SF
197 'clientVersion': '5.21',
198 'deviceModel': 'iPhone14,3',
199 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 200 },
201 },
b6de707d 202 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
203 'REQUIRE_JS_PLAYER': False
000c15a4 204 },
e7e94f2a
D
205 'ios_creator': {
206 'INNERTUBE_CONTEXT': {
207 'client': {
208 'clientName': 'IOS_CREATOR',
224b5a35
SF
209 'clientVersion': '22.33.101',
210 'deviceModel': 'iPhone14,3',
211 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
212 },
213 },
b6de707d 214 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
215 'REQUIRE_JS_PLAYER': False
e7e94f2a 216 },
3619f78d 217 # mweb has 'ultralow' formats
218 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 219 'mweb': {
18c7683d 220 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 221 'INNERTUBE_CONTEXT': {
222 'client': {
223 'clientName': 'MWEB',
a0c830f4 224 'clientVersion': '2.20220801.00.00',
000c15a4 225 }
226 },
227 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
228 },
229 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
230 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
231 'tv_embedded': {
232 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
233 'INNERTUBE_CONTEXT': {
234 'client': {
235 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
236 'clientVersion': '2.0',
237 },
238 },
239 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
240 },
000c15a4 241}
242
243
e7870111
D
244def _split_innertube_client(client_name):
245 variant, *base = client_name.rsplit('.', 1)
246 if base:
247 return variant, base[0], variant
248 base, *variant = client_name.split('_', 1)
249 return client_name, base, variant[0] if variant else None
250
251
c795c39f
L
252def short_client_name(client_name):
253 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
254 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
255
256
000c15a4 257def build_innertube_clients():
2e4cacd0 258 THIRD_PARTY = {
e7870111 259 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 260 }
e7870111 261 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 262 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 263
264 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 265 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 266 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 267 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 268 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 269
e7870111 270 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 271 ytcfg['priority'] = 10 * priority(base_client)
272
e48b3875 273 if not variant:
e7870111
D
274 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
275 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
276 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
277 embedscreen['priority'] -= 3
278 elif variant == 'embedded':
e48b3875 279 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 280 ytcfg['priority'] -= 2
e48b3875 281 else:
000c15a4 282 ytcfg['priority'] -= 3
283
284
285build_innertube_clients()
286
287
c26f9b99 288class BadgeType(enum.Enum):
289 AVAILABILITY_UNLISTED = enum.auto()
290 AVAILABILITY_PRIVATE = enum.auto()
291 AVAILABILITY_PUBLIC = enum.auto()
292 AVAILABILITY_PREMIUM = enum.auto()
293 AVAILABILITY_SUBSCRIPTION = enum.auto()
294 LIVE_NOW = enum.auto()
295
296
de7f3446 297class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 298 """Provide base functions for Youtube extractors"""
e00eb564 299
3462ffa8 300 _RESERVED_NAMES = (
08e29b9f 301 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
182bda88 302 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 303 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 304 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 305
3619f78d 306 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
307
52efa4b3 308 # _NETRC_MACHINE = 'youtube'
3619f78d 309
b2e8bc1b
JMF
310 # If True it will raise an error if no login info is provided
311 _LOGIN_REQUIRED = False
312
d9190e44
RH
313 _INVIDIOUS_SITES = (
314 # invidious-redirect websites
315 r'(?:www\.)?redirect\.invidious\.io',
316 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 317 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
318 r'(?:www\.)?invidious\.pussthecat\.org',
319 r'(?:www\.)?invidious\.zee\.li',
320 r'(?:www\.)?invidious\.ethibox\.fr',
05799a48
RH
321 r'(?:www\.)?iv\.ggtyler\.dev',
322 r'(?:www\.)?inv\.vern\.i2p',
323 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
324 r'(?:www\.)?inv\.riverside\.rocks',
325 r'(?:www\.)?invidious\.silur\.me',
326 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
327 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
328 r'(?:www\.)?invidious\.slipfox\.xyz',
329 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
330 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
331 r'(?:www\.)?invidious\.tiekoetter\.com',
332 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
333 r'(?:www\.)?invidious\.nerdvpn\.de',
334 r'(?:www\.)?invidious\.weblibre\.org',
335 r'(?:www\.)?inv\.odyssey346\.dev',
336 r'(?:www\.)?invidious\.dhusch\.de',
337 r'(?:www\.)?iv\.melmac\.space',
338 r'(?:www\.)?watch\.thekitty\.zone',
339 r'(?:www\.)?invidious\.privacydev\.net',
340 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
341 r'(?:www\.)?invidious\.drivet\.xyz',
342 r'(?:www\.)?vid\.priv\.au',
343 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
344 r'(?:www\.)?inv\.vern\.cc',
345 r'(?:www\.)?invidious\.esmailelbob\.xyz',
346 r'(?:www\.)?invidious\.sethforprivacy\.com',
347 r'(?:www\.)?yt\.oelrichsgarcia\.de',
348 r'(?:www\.)?yt\.artemislena\.eu',
349 r'(?:www\.)?invidious\.flokinet\.to',
350 r'(?:www\.)?invidious\.baczek\.me',
351 r'(?:www\.)?y\.com\.sb',
352 r'(?:www\.)?invidious\.epicsite\.xyz',
353 r'(?:www\.)?invidious\.lidarshield\.cloud',
354 r'(?:www\.)?yt\.funami\.tech',
d9190e44 355 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
356 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
357 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
358 # youtube-dl invidious instances list
359 r'(?:(?:www|no)\.)?invidiou\.sh',
360 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
361 r'(?:www\.)?invidious\.kabi\.tk',
362 r'(?:www\.)?invidious\.mastodon\.host',
363 r'(?:www\.)?invidious\.zapashcanon\.fr',
364 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
365 r'(?:www\.)?invidious\.tinfoil-hat\.net',
366 r'(?:www\.)?invidious\.himiko\.cloud',
367 r'(?:www\.)?invidious\.reallyancient\.tech',
368 r'(?:www\.)?invidious\.tube',
369 r'(?:www\.)?invidiou\.site',
370 r'(?:www\.)?invidious\.site',
371 r'(?:www\.)?invidious\.xyz',
372 r'(?:www\.)?invidious\.nixnet\.xyz',
373 r'(?:www\.)?invidious\.048596\.xyz',
374 r'(?:www\.)?invidious\.drycat\.fr',
375 r'(?:www\.)?inv\.skyn3t\.in',
376 r'(?:www\.)?tube\.poal\.co',
377 r'(?:www\.)?tube\.connect\.cafe',
378 r'(?:www\.)?vid\.wxzm\.sx',
379 r'(?:www\.)?vid\.mint\.lgbt',
380 r'(?:www\.)?vid\.puffyan\.us',
381 r'(?:www\.)?yewtu\.be',
382 r'(?:www\.)?yt\.elukerio\.org',
383 r'(?:www\.)?yt\.lelux\.fi',
384 r'(?:www\.)?invidious\.ggc-project\.de',
385 r'(?:www\.)?yt\.maisputain\.ovh',
386 r'(?:www\.)?ytprivate\.com',
387 r'(?:www\.)?invidious\.13ad\.de',
388 r'(?:www\.)?invidious\.toot\.koeln',
389 r'(?:www\.)?invidious\.fdn\.fr',
390 r'(?:www\.)?watch\.nettohikari\.com',
391 r'(?:www\.)?invidious\.namazso\.eu',
392 r'(?:www\.)?invidious\.silkky\.cloud',
393 r'(?:www\.)?invidious\.exonip\.de',
394 r'(?:www\.)?invidious\.riverside\.rocks',
395 r'(?:www\.)?invidious\.blamefran\.net',
396 r'(?:www\.)?invidious\.moomoo\.de',
397 r'(?:www\.)?ytb\.trom\.tf',
398 r'(?:www\.)?yt\.cyberhost\.uk',
399 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
400 r'(?:www\.)?qklhadlycap4cnod\.onion',
401 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
402 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
403 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
404 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
405 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
406 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
407 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
408 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
409 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
410 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
411 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
412 r'(?:www\.)?piped\.kavin\.rocks',
d1c4f6d4 413 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 414 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 415 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
416 r'(?:www\.)?watch\.whatever\.social',
417 r'(?:www\.)?piped\.garudalinux\.org',
418 r'(?:www\.)?piped\.rivo\.lol',
419 r'(?:www\.)?piped-libre\.kavin\.rocks',
420 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 421 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
422 r'(?:www\.)?il\.ax',
423 r'(?:www\.)?piped\.esmailelbob\.xyz',
424 r'(?:www\.)?piped\.projectsegfau\.lt',
425 r'(?:www\.)?piped\.privacydev\.net',
426 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
427 r'(?:www\.)?piped\.smnz\.de',
428 r'(?:www\.)?piped\.adminforge\.de',
429 r'(?:www\.)?watch\.whatevertinfoil\.de',
430 r'(?:www\.)?piped\.qdi\.fi',
bc87dac7
B
431 r'(?:www\.)?piped\.video',
432 r'(?:www\.)?piped\.aeong\.one',
05799a48
RH
433 r'(?:www\.)?piped\.moomoo\.me',
434 r'(?:www\.)?piped\.chauvet\.pro',
435 r'(?:www\.)?watch\.leptons\.xyz',
436 r'(?:www\.)?pd\.vern\.cc',
437 r'(?:www\.)?piped\.hostux\.net',
438 r'(?:www\.)?piped\.lunar\.icu',
78a78fa7
BG
439 # Hyperpipe instances from https://hyperpipe.codeberg.page/
440 r'(?:www\.)?hyperpipe\.surge\.sh',
441 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
442 r'(?:www\.)?listen\.whatever\.social',
443 r'(?:www\.)?music\.adminforge\.de',
d9190e44
RH
444 )
445
c26f9b99 446 # extracted from account/account_menu ep
447 # XXX: These are the supported YouTube UI and API languages,
448 # which is slightly different from languages supported for translation in YouTube studio
449 _SUPPORTED_LANG_CODES = [
450 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
451 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
452 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
453 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
454 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
455 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
456 ]
457
a057779d 458 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
459
7666b936 460 _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
461 _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
462
463 def ucid_or_none(self, ucid):
464 return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
465
466 def handle_or_none(self, handle):
467 return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
468
469 def handle_from_url(self, url):
470 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
471 url, 'channel handle', default=None)
472
473 def ucid_from_url(self, url):
474 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
475 url, 'channel id', default=None)
476
c26f9b99 477 @functools.cached_property
478 def _preferred_lang(self):
479 """
480 Returns a language code supported by YouTube for the user preferred language.
481 Returns None if no preferred language set.
482 """
483 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
484 if not preferred_lang:
485 return
486 if preferred_lang not in self._SUPPORTED_LANG_CODES:
487 raise ExtractorError(
488 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
489 expected=True)
490 elif preferred_lang != 'en':
491 self.report_warning(
492 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
493 return preferred_lang
494
cce889b9 495 def _initialize_consent(self):
496 cookies = self._get_cookies('https://www.youtube.com/')
497 if cookies.get('__Secure-3PSID'):
498 return
499 consent_id = None
500 consent = cookies.get('CONSENT')
501 if consent:
502 if 'YES' in consent.value:
503 return
504 consent_id = self._search_regex(
505 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
506 if not consent_id:
507 consent_id = random.randint(100, 999)
508 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 509
f3aa3c3f 510 def _initialize_pref(self):
511 cookies = self._get_cookies('https://www.youtube.com/')
512 pref_cookie = cookies.get('PREF')
513 pref = {}
514 if pref_cookie:
515 try:
14f25df2 516 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 517 except ValueError:
518 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 519 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 520 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 521
b2e8bc1b 522 def _real_initialize(self):
f3aa3c3f 523 self._initialize_pref()
cce889b9 524 self._initialize_consent()
a25bca9f 525 self._check_login_required()
526
527 def _check_login_required(self):
24146491 528 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 529 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 530
b7c47b74 531 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
532 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 533
000c15a4 534 def _get_default_ytcfg(self, client='web'):
535 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 536
000c15a4 537 def _get_innertube_host(self, client='web'):
538 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 539
000c15a4 540 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 541 # try_get but with fallback to default ytcfg client values when present
542 _func = lambda y: try_get(y, getter, expected_type)
543 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
544
000c15a4 545 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 546 return self._ytcfg_get_safe(
547 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 548 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 549
000c15a4 550 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 551 return self._ytcfg_get_safe(
552 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 553 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 554
2ae778b8 555 def _select_api_hostname(self, req_api_hostname, default_client=None):
556 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
557 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
558
000c15a4 559 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 560 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 561
000c15a4 562 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 563 context = get_first(
564 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 565 # Enforce language and tz for extraction
566 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 567 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 568 return context
569
cf87314d 570 _SAPISID = None
571
109dd3b2 572 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 573 time_now = round(time.time())
cf87314d 574 if self._SAPISID is None:
575 yt_cookies = self._get_cookies('https://www.youtube.com')
576 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
577 # See: https://github.com/yt-dlp/yt-dlp/issues/393
578 sapisid_cookie = dict_get(
579 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
580 if sapisid_cookie and sapisid_cookie.value:
581 self._SAPISID = sapisid_cookie.value
582 self.write_debug('Extracted SAPISID cookie')
583 # SAPISID cookie is required if not already present
584 if not yt_cookies.get('SAPISID'):
585 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
586 self._set_cookie(
587 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
588 else:
589 self._SAPISID = False
590 if not self._SAPISID:
591 return None
1974e99f 592 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
593 sapisidhash = hashlib.sha1(
86e5f3ed 594 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 595 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
596
597 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 598 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 599 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 600
109dd3b2 601 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 602 data.update(query)
11f9be09 603 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 604 real_headers.update({'content-type': 'application/json'})
605 if headers:
606 real_headers.update(headers)
2ae778b8 607 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
608 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 609 return self._download_json(
2ae778b8 610 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 611 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 612 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 613 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 614
65141660 615 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
616 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 617
99e9e001 618 @staticmethod
619 def _extract_session_index(*data):
620 """
621 Index of current account in account list.
622 See: https://github.com/yt-dlp/yt-dlp/pull/519
623 """
624 for ytcfg in data:
625 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
626 if session_index is not None:
627 return session_index
628
629 # Deprecated?
630 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 631 if ytcfg:
14f25df2 632 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
633 if token:
634 return token
99e9e001 635 if webpage:
636 return self._search_regex(
637 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
638 'identity token', default=None, fatal=False)
a1c5d2ca
M
639
640 @staticmethod
fe93e2c4 641 def _extract_account_syncid(*args):
8ea3f7b9 642 """
643 Extract syncId required to download private playlists of secondary channels
fe93e2c4 644 @params response and/or ytcfg
8ea3f7b9 645 """
fe93e2c4 646 for data in args:
647 # ytcfg includes channel_syncid if on secondary channel
14f25df2 648 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 649 if delegated_sid:
650 return delegated_sid
651 sync_ids = (try_get(
652 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 653 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 654 if len(sync_ids) >= 2 and sync_ids[1]:
655 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
656 # and just "user_syncid||" for primary channel. We only want the channel_syncid
657 return sync_ids[0]
a1c5d2ca 658
ac56cf38 659 @staticmethod
660 def _extract_visitor_data(*args):
661 """
662 Extracts visitorData from an API response or ytcfg
663 Appears to be used to track session state
664 """
9222c381 665 return get_first(
6c73052c 666 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 667 expected_type=str)
ac56cf38 668
2762dbb1 669 @functools.cached_property
99e9e001 670 def is_authenticated(self):
671 return bool(self._generate_sapisidhash_header())
672
11f9be09 673 def extract_ytcfg(self, video_id, webpage):
8c54a305 674 if not webpage:
675 return {}
29f7c58a 676 return self._parse_json(
677 self._search_regex(
678 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 679 default='{}'), video_id, fatal=False) or {}
680
11f9be09 681 def generate_api_headers(
99e9e001 682 self, *, ytcfg=None, account_syncid=None, session_index=None,
683 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
684
2ae778b8 685 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 686 headers = {
14f25df2 687 'X-YouTube-Client-Name': str(
11f9be09 688 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
689 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 690 'Origin': origin,
691 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
692 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 693 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
694 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 695 }
696 if session_index is None:
314ee305 697 session_index = self._extract_session_index(ytcfg)
698 if account_syncid or session_index is not None:
699 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 700
109dd3b2 701 auth = self._generate_sapisidhash_header(origin)
f4f751af 702 if auth is not None:
703 headers['Authorization'] = auth
109dd3b2 704 headers['X-Origin'] = origin
7a32c70d 705 return filter_dict(headers)
29f7c58a 706
a25bca9f 707 def _download_ytcfg(self, client, video_id):
708 url = {
709 'web': 'https://www.youtube.com',
710 'web_music': 'https://music.youtube.com',
711 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
712 }.get(client)
713 if not url:
714 return {}
715 webpage = self._download_webpage(
716 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
717 return self.extract_ytcfg(video_id, webpage) or {}
718
2d6659b9 719 @staticmethod
720 def _build_api_continuation_query(continuation, ctp=None):
721 query = {
722 'continuation': continuation
723 }
724 # TODO: Inconsistency with clickTrackingParams.
725 # Currently we have a fixed ctp contained within context (from ytcfg)
726 # and a ctp in root query for continuation.
727 if ctp:
728 query['clickTracking'] = {'clickTrackingParams': ctp}
729 return query
730
2d6659b9 731 @classmethod
732 def _extract_next_continuation_data(cls, renderer):
733 next_continuation = try_get(
734 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
735 lambda x: x['continuation']['reloadContinuationData']), dict)
736 if not next_continuation:
737 return
738 continuation = next_continuation.get('continuation')
739 if not continuation:
740 return
741 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 742 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 743
744 @classmethod
745 def _extract_continuation_ep_data(cls, continuation_ep: dict):
746 if isinstance(continuation_ep, dict):
747 continuation = try_get(
14f25df2 748 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 749 if not continuation:
750 return
751 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 752 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 753
754 @classmethod
755 def _extract_continuation(cls, renderer):
756 next_continuation = cls._extract_next_continuation_data(renderer)
757 if next_continuation:
758 return next_continuation
fe93e2c4 759
7a32c70d 760 return traverse_obj(renderer, (
761 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
762 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
763 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 764
fe93e2c4 765 @classmethod
766 def _extract_alerts(cls, data):
109dd3b2 767 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
768 if not isinstance(alert_dict, dict):
769 continue
770 for alert in alert_dict.values():
771 alert_type = alert.get('type')
772 if not alert_type:
773 continue
052e1350 774 message = cls._get_text(alert, 'text')
109dd3b2 775 if message:
776 yield alert_type, message
777
c0ac49bc 778 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 779 errors, warnings = [], []
109dd3b2 780 for alert_type, alert_message in alerts:
641ad5d8 781 if alert_type.lower() == 'error' and fatal:
109dd3b2 782 errors.append([alert_type, alert_message])
a057779d 783 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 784 warnings.append([alert_type, alert_message])
785
786 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 787 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 788 if errors:
789 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
790
791 def _extract_and_report_alerts(self, data, *args, **kwargs):
792 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
793
47193e02 794 def _extract_badges(self, renderer: dict):
c26f9b99 795 privacy_icon_map = {
796 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
797 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
798 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC
799 }
800
801 badge_style_map = {
802 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
803 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
804 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW
805 }
806
807 label_map = {
808 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
809 'private': BadgeType.AVAILABILITY_PRIVATE,
810 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
811 'live': BadgeType.LIVE_NOW,
812 'premium': BadgeType.AVAILABILITY_PREMIUM
813 }
814
815 badges = []
6839ae1f 816 for badge in traverse_obj(renderer, ('badges', ..., 'metadataBadgeRenderer')):
c26f9b99 817 badge_type = (
818 privacy_icon_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
819 or badge_style_map.get(traverse_obj(badge, 'style'))
820 )
821 if badge_type:
822 badges.append({'type': badge_type})
823 continue
824
825 # fallback, won't work in some languages
826 label = traverse_obj(badge, 'label', expected_type=str, default='')
827 for match, label_badge_type in label_map.items():
828 if match in label.lower():
829 badges.append({'type': badge_type})
830 continue
831
47193e02 832 return badges
833
c26f9b99 834 @staticmethod
835 def _has_badge(badges, badge_type):
836 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
837
47193e02 838 @staticmethod
052e1350 839 def _get_text(data, *path_list, max_runs=None):
840 for path in path_list or [None]:
841 if path is None:
842 obj = [data]
843 else:
844 obj = traverse_obj(data, path, default=[])
845 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
846 obj = [obj]
847 for item in obj:
14f25df2 848 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 849 if text:
850 return text
851 runs = try_get(item, lambda x: x['runs'], list) or []
852 if not runs and isinstance(item, list):
853 runs = item
854
855 runs = runs[:min(len(runs), max_runs or len(runs))]
6839ae1f 856 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
052e1350 857 if text:
858 return text
47193e02 859
f0d785d3 860 def _get_count(self, data, *path_list):
861 count_text = self._get_text(data, *path_list) or ''
862 count = parse_count(count_text)
863 if count is None:
864 count = str_to_int(
865 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
866 return count
867
a709d873 868 @staticmethod
869 def _extract_thumbnails(data, *path_list):
870 """
871 Extract thumbnails from thumbnails dict
872 @param path_list: path list to level that contains 'thumbnails' key
873 """
874 thumbnails = []
875 for path in path_list or [()]:
6839ae1f 876 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
a709d873 877 thumbnail_url = url_or_none(thumbnail.get('url'))
878 if not thumbnail_url:
879 continue
880 # Sometimes youtube gives a wrong thumbnail URL. See:
881 # https://github.com/yt-dlp/yt-dlp/issues/233
882 # https://github.com/ytdl-org/youtube-dl/issues/28023
883 if 'maxresdefault' in thumbnail_url:
884 thumbnail_url = thumbnail_url.split('?')[0]
885 thumbnails.append({
886 'url': thumbnail_url,
887 'height': int_or_none(thumbnail.get('height')),
888 'width': int_or_none(thumbnail.get('width')),
889 })
890 return thumbnails
891
f3aa3c3f 892 @staticmethod
893 def extract_relative_time(relative_time_text):
894 """
895 Extracts a relative time from string and converts to dt object
f0d785d3 896 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 897 """
f0d785d3 898 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 899 if mobj:
f0d785d3 900 start = mobj.group('start')
901 if start:
902 return datetime_from_str(start)
f3aa3c3f 903 try:
f0d785d3 904 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 905 except ValueError:
906 return None
907
c26f9b99 908 def _parse_time_text(self, text):
909 if not text:
910 return
f3aa3c3f 911 dt = self.extract_relative_time(text)
912 timestamp = None
913 if isinstance(dt, datetime.datetime):
914 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 915
916 if timestamp is None:
917 timestamp = (
918 unified_timestamp(text) or unified_timestamp(
919 self._search_regex(
17322130 920 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 921 text.lower(), 'time text', default=None)))
f0d785d3 922
c26f9b99 923 if text and timestamp is None and self._preferred_lang in (None, 'en'):
924 self.report_warning(
925 f'Cannot parse localized time text "{text}"', only_once=True)
926 return timestamp
f3aa3c3f 927
109dd3b2 928 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
929 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 930 default_client='web'):
be5c1ae8 931 for retry in self.RetryManager():
109dd3b2 932 try:
933 response = self._call_api(
934 ep=ep, fatal=True, headers=headers,
be5c1ae8 935 video_id=item_id, query=query, note=note,
109dd3b2 936 context=self._extract_context(ytcfg, default_client),
937 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 938 api_hostname=api_hostname, default_client=default_client)
109dd3b2 939 except ExtractorError as e:
be5c1ae8 940 if not isinstance(e.cause, network_exceptions):
941 return self._error_or_warning(e, fatal=fatal)
942 elif not isinstance(e.cause, urllib.error.HTTPError):
943 retry.error = e
944 continue
109dd3b2 945
be5c1ae8 946 first_bytes = e.cause.read(512)
947 if not is_html(first_bytes):
948 yt_error = try_get(
949 self._parse_json(
950 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
951 lambda x: x['error']['message'], str)
952 if yt_error:
953 self._report_alerts([('ERROR', yt_error)], fatal=False)
954 # Downloading page may result in intermittent 5xx HTTP error
955 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
956 # We also want to catch all other network exceptions since errors in later pages can be troublesome
957 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
958 if e.cause.code not in (403, 429):
959 retry.error = e
960 continue
961 return self._error_or_warning(e, fatal=fatal)
962
963 try:
964 self._extract_and_report_alerts(response, only_once=True)
965 except ExtractorError as e:
966 # YouTube servers may return errors we want to retry on in a 200 OK response
967 # See: https://github.com/yt-dlp/yt-dlp/issues/839
968 if 'unknown error' in e.msg.lower():
969 retry.error = e
970 continue
971 return self._error_or_warning(e, fatal=fatal)
972 # Youtube sometimes sends incomplete data
973 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
974 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 975 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 976 continue
977
978 return response
109dd3b2 979
9297939e 980 @staticmethod
981 def is_music_url(url):
5b28cef7 982 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
9297939e 983
30a074c2 984 def _extract_video(self, renderer):
985 video_id = renderer.get('videoId')
4dc23a80
M
986
987 reel_header_renderer = traverse_obj(renderer, (
988 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
989 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
990
991 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 992 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
993
994 duration = int_or_none(renderer.get('lengthSeconds'))
995 if duration is None:
996 duration = parse_duration(self._get_text(
997 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 998 if duration is None:
4dc23a80 999 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 1000 duration = parse_duration(self._search_regex(
1001 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
1002 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
1003 video_id, default=None, group='duration'))
1004
f3aa3c3f 1005 channel_id = traverse_obj(
a44ca5a4 1006 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
1007 expected_type=str, get_all=False)
4dc23a80
M
1008 if not channel_id:
1009 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
1010
7666b936 1011 channel_id = self.ucid_or_none(channel_id)
1012
f3aa3c3f 1013 overlay_style = traverse_obj(
a44ca5a4 1014 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
1015 get_all=False, expected_type=str)
f3aa3c3f 1016 badges = self._extract_badges(renderer)
4dc23a80 1017
fd2ad7cb 1018 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 1019 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1020 expected_type=str)) or ''
fd2ad7cb 1021 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 1022 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 1023 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 1024
4dc23a80
M
1025 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1026 or self._get_text(reel_header_renderer, 'timestampText') or '')
1027 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1028
867c66ff
M
1029 live_status = (
1030 'is_upcoming' if scheduled_timestamp is not None
1031 else 'was_live' if 'streamed' in time_text.lower()
1032 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1033 else None)
1034
4dc23a80
M
1035 # videoInfo is a string like '50K views • 10 years ago'.
1036 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1037 view_count = (0 if 'no views' in view_count_text.lower()
1038 else self._get_count({'simpleText': view_count_text}))
1039 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1040
93e12ed7 1041 channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
1042 or self._get_text(reel_header_renderer, 'channelTitleText'))
1043
1044 channel_handle = traverse_obj(renderer, (
1045 'shortBylineText', 'runs', ..., 'navigationEndpoint',
1046 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
1047 expected_type=self.handle_from_url, get_all=False)
30a074c2 1048 return {
39ed931e 1049 '_type': 'url',
30a074c2 1050 'ie_key': YoutubeIE.ie_key(),
1051 'id': video_id,
fd2ad7cb 1052 'url': url,
30a074c2 1053 'title': title,
1054 'description': description,
1055 'duration': duration,
f3aa3c3f 1056 'channel_id': channel_id,
93e12ed7 1057 'channel': channel,
4dc23a80 1058 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
93e12ed7 1059 'uploader': channel,
1060 'uploader_id': channel_handle,
1061 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4dc23a80 1062 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1063 'timestamp': (self._parse_time_text(time_text)
1064 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1065 else None),
f3aa3c3f 1066 'release_timestamp': scheduled_timestamp,
c26f9b99 1067 'availability':
1068 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1069 else self._availability(
1070 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1071 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1072 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1073 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1074 view_count_field: view_count,
e63faa10 1075 'live_status': live_status
30a074c2 1076 }
1077
0c148415 1078
360e1ca5 1079class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1080 IE_DESC = 'YouTube'
cb7dfeea 1081 _VALID_URL = r"""(?x)^
c5e8d7af 1082 (
edb53e2d 1083 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1084 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1085 (?:www\.)?deturl\.com/www\.youtube\.com|
1086 (?:www\.)?pwnyoutube\.com|
1087 (?:www\.)?hooktube\.com|
1088 (?:www\.)?yourepeat\.com|
1089 tube\.majestyc\.net|
1090 %(invidious)s|
1091 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1092 (?:.*?\#/)? # handle anchor (#/) redirect urls
1093 (?: # the various things that can precede the ID:
dad2210c 1094 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1095 |(?: # or the v= param in all its forms
f7000f3a 1096 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1097 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1098 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1099 v=
1100 )
f4b05232 1101 ))
cbaed4bb
S
1102 |(?:
1103 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1104 vid\.plus| # or vid.plus/xxxx
1105 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1106 %(invidious)s
cbaed4bb 1107 )/
edb53e2d 1108 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1109 )
c5e8d7af 1110 )? # all until now is optional -> you can pass the naked ID
201c1459 1111 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1112 (?(1).+)? # if we found the ID, everything can follow
9297939e 1113 (?:\#|$)""" % {
d9190e44 1114 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1115 }
7c6eb424 1116 _EMBED_REGEX = [
1117 r'''(?x)
1118 (?:
0ca0f881 1119 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1120 data-video-url=|
1121 <embed[^>]+?src=|
1122 embedSWF\(?:\s*|
1123 <object[^>]+data=|
1124 new\s+SWFObject\(
1125 )
1126 (["\'])
1127 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1128 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1129 \1''',
1130 # https://wordpress.org/plugins/lazy-load-for-videos/
1131 r'''(?xs)
1132 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1133 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1134 ]
6368e2e6 1135 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1136
e40c758c 1137 _PLAYER_INFO_RE = (
cc2db878 1138 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1139 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$',
545cc85d 1140 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1141 )
2c62dc26 1142 _formats = {
c2d3cb4c 1143 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1144 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1145 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1146 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1147 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1148 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1149 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1150 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1151 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1152 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1153 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1154 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1155 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1156 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1157 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1158 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1159 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1160 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1161
1162
1163 # 3D videos
c2d3cb4c 1164 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1165 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1166 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1167 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1168 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1169 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1170 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1171
96fb5605 1172 # Apple HTTP Live Streaming
11f12195 1173 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1174 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1175 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1176 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1177 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1178 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1179 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1180 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1181
1182 # DASH mp4 video
d23028a8
S
1183 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1184 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1185 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1186 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1187 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1188 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1189 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1190 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1191 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1192 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1193 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1194 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1195
f6f1fc92 1196 # Dash mp4 audio
d23028a8
S
1197 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1198 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1199 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1200 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1201 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1202 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1203 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1204
1205 # Dash webm
d23028a8
S
1206 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1207 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1208 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1209 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1210 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1211 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1212 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1213 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1214 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1215 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1216 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1217 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1218 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1219 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1220 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1221 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1222 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1223 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1224 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1225 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1226 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1227 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1228
1229 # Dash webm audio
d23028a8
S
1230 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1231 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1232
0857baad 1233 # Dash webm audio with opus inside
d23028a8
S
1234 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1235 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1236 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1237
ce6b9a2d
PH
1238 # RTMP (unnamed)
1239 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1240
1241 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1242 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1243 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1244 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1245 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1246 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1247 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1248 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1249 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1250 }
29f7c58a 1251 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1252
fd5c4aab
S
1253 _GEO_BYPASS = False
1254
78caa52a 1255 IE_NAME = 'youtube'
2eb88d95
PH
1256 _TESTS = [
1257 {
2d3d2997 1258 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1259 'info_dict': {
1260 'id': 'BaW_jenozKc',
1261 'ext': 'mp4',
3867038a 1262 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
ff9f925b 1263 'channel': 'Philipp Hagemeister',
dd4c4492
S
1264 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1265 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1266 'upload_date': '20121002',
ff9f925b 1267 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1268 'categories': ['Science & Technology'],
3867038a 1269 'tags': ['youtube-dl'],
556dbe7f 1270 'duration': 10,
dbdaaa23 1271 'view_count': int,
3e7c1224 1272 'like_count': int,
ff9f925b 1273 'availability': 'public',
1274 'playable_in_embed': True,
1275 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1276 'live_status': 'not_live',
1277 'age_limit': 0,
7c80519c 1278 'start_time': 1,
297a564b 1279 'end_time': 9,
12a1b225 1280 'comment_count': int,
7666b936 1281 'channel_follower_count': int,
1282 'uploader': 'Philipp Hagemeister',
1283 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1284 'uploader_id': '@PhilippHagemeister',
5caf30db 1285 'heatmap': 'count:100',
2eb88d95 1286 }
0e853ca4 1287 },
fccd3771 1288 {
4bc3a23e
PH
1289 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1290 'note': 'Embed-only video (#1746)',
1291 'info_dict': {
1292 'id': 'yZIXLfi8CZQ',
1293 'ext': 'mp4',
1294 'upload_date': '20120608',
1295 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1296 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
94bfcd23 1297 'age_limit': 18,
545cc85d 1298 },
1299 'skip': 'Private video',
fccd3771 1300 },
11b56058 1301 {
8bdd16b4 1302 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1303 'note': 'Use the first video ID in the URL',
1304 'info_dict': {
1305 'id': 'BaW_jenozKc',
1306 'ext': 'mp4',
3867038a 1307 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
976ae3ea 1308 'channel': 'Philipp Hagemeister',
1309 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1310 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1311 'upload_date': '20121002',
976ae3ea 1312 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1313 'categories': ['Science & Technology'],
3867038a 1314 'tags': ['youtube-dl'],
556dbe7f 1315 'duration': 10,
dbdaaa23 1316 'view_count': int,
11b56058 1317 'like_count': int,
976ae3ea 1318 'availability': 'public',
1319 'playable_in_embed': True,
1320 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1321 'live_status': 'not_live',
1322 'age_limit': 0,
12a1b225 1323 'comment_count': int,
7666b936 1324 'channel_follower_count': int,
1325 'uploader': 'Philipp Hagemeister',
1326 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1327 'uploader_id': '@PhilippHagemeister',
34a7de29
S
1328 },
1329 'params': {
1330 'skip_download': True,
1331 },
11b56058 1332 },
dd27fd17 1333 {
2d3d2997 1334 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1335 'note': '256k DASH audio (format 141) via DASH manifest',
1336 'info_dict': {
1337 'id': 'a9LDPn-MO4I',
1338 'ext': 'm4a',
1339 'upload_date': '20121002',
4bc3a23e 1340 'description': '',
4bc3a23e 1341 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1342 },
4bc3a23e
PH
1343 'params': {
1344 'youtube_include_dash_manifest': True,
1345 'format': '141',
4919603f 1346 },
de3c7fe0 1347 'skip': 'format 141 not served anymore',
dd27fd17 1348 },
8bdd16b4 1349 # DASH manifest with encrypted signature
1350 {
1351 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1352 'info_dict': {
1353 'id': 'IB3lcPjvWLA',
1354 'ext': 'm4a',
1355 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1356 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1357 'duration': 244,
8bdd16b4 1358 'upload_date': '20131011',
cc2db878 1359 'abr': 129.495,
976ae3ea 1360 'like_count': int,
1361 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1362 'playable_in_embed': True,
1363 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1364 'view_count': int,
1365 'track': 'The Spark',
1366 'live_status': 'not_live',
1367 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1368 'channel': 'Afrojack',
976ae3ea 1369 'tags': 'count:19',
1370 'availability': 'public',
1371 'categories': ['Music'],
1372 'age_limit': 0,
1373 'alt_title': 'The Spark',
7666b936 1374 'channel_follower_count': int,
1375 'uploader': 'Afrojack',
1376 'uploader_url': 'https://www.youtube.com/@Afrojack',
1377 'uploader_id': '@Afrojack',
8bdd16b4 1378 },
1379 'params': {
1380 'youtube_include_dash_manifest': True,
1381 'format': '141/bestaudio[ext=m4a]',
1382 },
1383 },
65c2fde2 1384 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1385 {
65c2fde2 1386 'note': 'Embed allowed age-gate video',
2d3d2997 1387 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1388 'info_dict': {
1389 'id': 'HtVdAasjOgU',
1390 'ext': 'mp4',
1391 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1392 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1393 'duration': 142,
c522adb1 1394 'upload_date': '20140605',
34952f09 1395 'age_limit': 18,
976ae3ea 1396 'categories': ['Gaming'],
1397 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1398 'availability': 'needs_auth',
1399 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1400 'like_count': int,
1401 'channel': 'The Witcher',
1402 'live_status': 'not_live',
1403 'tags': 'count:17',
1404 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1405 'playable_in_embed': True,
1406 'view_count': int,
7666b936 1407 'channel_follower_count': int,
1408 'uploader': 'The Witcher',
1409 'uploader_url': 'https://www.youtube.com/@thewitcher',
1410 'uploader_id': '@thewitcher',
c522adb1
JMF
1411 },
1412 },
65c2fde2 1413 {
1414 'note': 'Age-gate video with embed allowed in public site',
1415 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1416 'info_dict': {
1417 'id': 'HsUATh_Nc2U',
1418 'ext': 'mp4',
1419 'title': 'Godzilla 2 (Official Video)',
1420 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1421 'upload_date': '20200408',
65c2fde2 1422 'age_limit': 18,
976ae3ea 1423 'availability': 'needs_auth',
1424 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
976ae3ea 1425 'channel': 'FlyingKitty',
1426 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1427 'view_count': int,
1428 'categories': ['Entertainment'],
1429 'live_status': 'not_live',
1430 'tags': ['Flyingkitty', 'godzilla 2'],
1431 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1432 'like_count': int,
1433 'duration': 177,
1434 'playable_in_embed': True,
7666b936 1435 'channel_follower_count': int,
1436 'uploader': 'FlyingKitty',
1437 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
1438 'uploader_id': '@FlyingKitty900',
5caf30db 1439 'comment_count': int,
65c2fde2 1440 },
1441 },
1442 {
1443 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1444 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1445 'info_dict': {
1446 'id': 'Tq92D6wQ1mg',
1447 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1448 'ext': 'mp4',
17322130 1449 'upload_date': '20191228',
65c2fde2 1450 'description': 'md5:17eccca93a786d51bc67646756894066',
1451 'age_limit': 18,
976ae3ea 1452 'like_count': int,
1453 'availability': 'needs_auth',
976ae3ea 1454 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1455 'view_count': int,
1456 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1457 'channel': 'Projekt Melody',
1458 'live_status': 'not_live',
1459 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1460 'playable_in_embed': True,
1461 'categories': ['Entertainment'],
1462 'duration': 106,
1463 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1464 'comment_count': int,
7666b936 1465 'channel_follower_count': int,
1466 'uploader': 'Projekt Melody',
1467 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
1468 'uploader_id': '@ProjektMelody',
65c2fde2 1469 },
1470 },
1471 {
1472 'note': 'Non-Agegated non-embeddable video',
1473 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1474 'info_dict': {
1475 'id': 'MeJVWBSsPAY',
1476 'ext': 'mp4',
1477 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
65c2fde2 1478 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1479 'upload_date': '20130730',
976ae3ea 1480 'track': 'Such mich find mich',
1481 'age_limit': 0,
1482 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1483 'like_count': int,
1484 'playable_in_embed': False,
1485 'creator': 'OOMPH!',
1486 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1487 'view_count': int,
1488 'alt_title': 'Such mich find mich',
1489 'duration': 210,
1490 'channel': 'Herr Lurik',
1491 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1492 'categories': ['Music'],
1493 'availability': 'public',
976ae3ea 1494 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1495 'live_status': 'not_live',
1496 'artist': 'OOMPH!',
7666b936 1497 'channel_follower_count': int,
1498 'uploader': 'Herr Lurik',
1499 'uploader_url': 'https://www.youtube.com/@HerrLurik',
1500 'uploader_id': '@HerrLurik',
65c2fde2 1501 },
1502 },
1503 {
1504 'note': 'Non-bypassable age-gated video',
1505 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1506 'only_matching': True,
1507 },
8bdd16b4 1508 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1509 # YouTube Red ad is not captured for creator
1510 {
1511 'url': '__2ABJjxzNo',
1512 'info_dict': {
1513 'id': '__2ABJjxzNo',
1514 'ext': 'mp4',
1515 'duration': 266,
1516 'upload_date': '20100430',
545cc85d 1517 'creator': 'deadmau5',
1518 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1519 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1520 'alt_title': 'Some Chords',
976ae3ea 1521 'availability': 'public',
1522 'tags': 'count:14',
1523 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1524 'view_count': int,
1525 'live_status': 'not_live',
1526 'channel': 'deadmau5',
1527 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1528 'like_count': int,
1529 'track': 'Some Chords',
1530 'artist': 'deadmau5',
1531 'playable_in_embed': True,
1532 'age_limit': 0,
1533 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1534 'categories': ['Music'],
1535 'album': 'Some Chords',
7666b936 1536 'channel_follower_count': int,
1537 'uploader': 'deadmau5',
1538 'uploader_url': 'https://www.youtube.com/@deadmau5',
1539 'uploader_id': '@deadmau5',
8bdd16b4 1540 },
1541 'expected_warnings': [
1542 'DASH manifest missing',
1543 ]
1544 },
067aa17e 1545 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1546 {
1547 'url': 'lqQg6PlCWgI',
1548 'info_dict': {
1549 'id': 'lqQg6PlCWgI',
1550 'ext': 'mp4',
556dbe7f 1551 'duration': 6085,
90227264 1552 'upload_date': '20150827',
12a1b225 1553 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
cbe2bd91 1554 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1555 'like_count': int,
1556 'release_timestamp': 1343767800,
1557 'playable_in_embed': True,
1558 'categories': ['Sports'],
1559 'release_date': '20120731',
1560 'channel': 'Olympics',
1561 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1562 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1563 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1564 'age_limit': 0,
1565 'availability': 'public',
1566 'live_status': 'was_live',
1567 'view_count': int,
1568 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
7666b936 1569 'channel_follower_count': int,
1570 'uploader': 'Olympics',
1571 'uploader_url': 'https://www.youtube.com/@Olympics',
1572 'uploader_id': '@Olympics',
cbe2bd91
PH
1573 },
1574 'params': {
1575 'skip_download': 'requires avconv',
e52a40ab 1576 }
cbe2bd91 1577 },
6271f1ca
PH
1578 # Non-square pixels
1579 {
1580 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1581 'info_dict': {
1582 'id': '_b-2C3KPAM0',
1583 'ext': 'mp4',
1584 'stretched_ratio': 16 / 9.,
556dbe7f 1585 'duration': 85,
6271f1ca 1586 'upload_date': '20110310',
6271f1ca 1587 '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',
6271f1ca 1588 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1589 'playable_in_embed': True,
1590 'channel': '孫ᄋᄅ',
1591 'age_limit': 0,
1592 'tags': 'count:11',
1593 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1594 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1595 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1596 'view_count': int,
1597 'categories': ['People & Blogs'],
1598 'like_count': int,
1599 'live_status': 'not_live',
1600 'availability': 'unlisted',
12a1b225 1601 'comment_count': int,
7666b936 1602 'channel_follower_count': int,
1603 'uploader': '孫ᄋᄅ',
1604 'uploader_url': 'https://www.youtube.com/@AllenMeow',
1605 'uploader_id': '@AllenMeow',
6271f1ca 1606 },
06b491eb
S
1607 },
1608 # url_encoded_fmt_stream_map is empty string
1609 {
1610 'url': 'qEJwOuvDf7I',
1611 'info_dict': {
1612 'id': 'qEJwOuvDf7I',
f57b7835 1613 'ext': 'webm',
06b491eb
S
1614 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1615 'description': '',
1616 'upload_date': '20150404',
06b491eb
S
1617 },
1618 'params': {
1619 'skip_download': 'requires avconv',
e323cf3f
S
1620 },
1621 'skip': 'This live event has ended.',
06b491eb 1622 },
067aa17e 1623 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1624 {
1625 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1626 'info_dict': {
1627 'id': 'FIl7x6_3R5Y',
eb6793ba 1628 'ext': 'webm',
da77d856
S
1629 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1630 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1631 'duration': 220,
da77d856 1632 'upload_date': '20150625',
eb6793ba 1633 'formats': 'mincount:31',
da77d856 1634 },
eb6793ba 1635 'skip': 'not actual anymore',
2ee8f5d8 1636 },
8a1a26ce
YCH
1637 # DASH manifest with segment_list
1638 {
1639 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1640 'md5': '8ce563a1d667b599d21064e982ab9e31',
1641 'info_dict': {
1642 'id': 'CsmdDsKjzN8',
1643 'ext': 'mp4',
17ee98e1 1644 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce 1645 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
8a1a26ce
YCH
1646 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1647 },
1648 'params': {
1649 'youtube_include_dash_manifest': True,
1650 'format': '135', # bestvideo
be49068d
S
1651 },
1652 'skip': 'This live event has ended.',
2ee8f5d8 1653 },
cf7e015f 1654 {
6368e2e6 1655 # Multifeed videos (multiple cameras), URL can be of any Camera
7666b936 1656 # TODO: fix multifeed titles
6368e2e6 1657 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1658 'info_dict': {
6368e2e6 1659 'id': 'zaPI8MvL8pg',
1660 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1661 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1662 },
1663 'playlist': [{
1664 'info_dict': {
6368e2e6 1665 'id': 'j5yGuxZ8lLU',
cf7e015f 1666 'ext': 'mp4',
6368e2e6 1667 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
6368e2e6 1668 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1669 'duration': 10120,
1670 'channel_follower_count': int,
1671 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1672 'availability': 'public',
1673 'playable_in_embed': True,
1674 'upload_date': '20131105',
6368e2e6 1675 'categories': ['Gaming'],
1676 'live_status': 'was_live',
1677 'tags': 'count:24',
1678 'release_timestamp': 1383701910,
1679 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1680 'comment_count': int,
1681 'age_limit': 0,
1682 'like_count': int,
1683 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1684 'channel': 'WiiLikeToPlay',
1685 'view_count': int,
1686 'release_date': '20131106',
7666b936 1687 'uploader': 'WiiLikeToPlay',
1688 'uploader_id': '@WLTP',
1689 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1690 },
1691 }, {
1692 'info_dict': {
6368e2e6 1693 'id': 'zaPI8MvL8pg',
cf7e015f 1694 'ext': 'mp4',
6368e2e6 1695 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
6368e2e6 1696 'availability': 'public',
1697 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1698 'channel': 'WiiLikeToPlay',
6368e2e6 1699 'channel_follower_count': int,
1700 'description': 'md5:563ccbc698b39298481ca3c571169519',
1701 'duration': 10108,
1702 'age_limit': 0,
1703 'like_count': int,
1704 'tags': 'count:24',
1705 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
6368e2e6 1706 'release_timestamp': 1383701915,
1707 'comment_count': int,
1708 'upload_date': '20131105',
1709 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1710 'release_date': '20131106',
1711 'playable_in_embed': True,
1712 'live_status': 'was_live',
1713 'categories': ['Gaming'],
1714 'view_count': int,
7666b936 1715 'uploader': 'WiiLikeToPlay',
1716 'uploader_id': '@WLTP',
1717 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1718 },
1719 }, {
1720 'info_dict': {
6368e2e6 1721 'id': 'R7r3vfO7Hao',
cf7e015f 1722 'ext': 'mp4',
6368e2e6 1723 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1724 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1725 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1726 'like_count': int,
1727 'availability': 'public',
1728 'playable_in_embed': True,
1729 'upload_date': '20131105',
1730 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1731 'channel_follower_count': int,
1732 'tags': 'count:24',
1733 'release_date': '20131106',
6368e2e6 1734 'comment_count': int,
1735 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1736 'channel': 'WiiLikeToPlay',
1737 'categories': ['Gaming'],
1738 'release_timestamp': 1383701914,
1739 'live_status': 'was_live',
1740 'age_limit': 0,
1741 'duration': 10128,
1742 'view_count': int,
7666b936 1743 'uploader': 'WiiLikeToPlay',
1744 'uploader_id': '@WLTP',
1745 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1746 },
1747 }],
6368e2e6 1748 'params': {'skip_download': True},
cbaed4bb 1749 },
f9f49d87 1750 {
067aa17e 1751 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1752 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1753 'info_dict': {
1754 'id': 'gVfLd0zydlo',
1755 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1756 },
1757 'playlist_count': 2,
be49068d 1758 'skip': 'Not multifeed anymore',
f9f49d87 1759 },
cbaed4bb 1760 {
2d3d2997 1761 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1762 'only_matching': True,
0e49d9a6 1763 },
6d4fc66b 1764 {
2d3d2997 1765 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1766 'only_matching': True,
1767 },
0e49d9a6 1768 {
067aa17e 1769 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1770 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1771 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1772 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1773 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1774 'info_dict': {
1775 'id': 'lsguqyKfVQg',
1776 'ext': 'mp4',
1777 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1778 'alt_title': 'Dark Walk',
0e49d9a6 1779 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1780 'duration': 133,
0e49d9a6 1781 'upload_date': '20151119',
11f9be09 1782 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1783 'track': 'Dark Walk',
1784 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1785 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1786 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1787 'categories': ['Film & Animation'],
1788 'view_count': int,
1789 'live_status': 'not_live',
1790 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1791 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1792 'tags': 'count:13',
1793 'availability': 'public',
1794 'channel': 'IronSoulElf',
1795 'playable_in_embed': True,
1796 'like_count': int,
1797 'age_limit': 0,
6c73052c 1798 'channel_follower_count': int
0e49d9a6
LL
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 },
61f92af1 1804 {
067aa17e 1805 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1806 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1807 'only_matching': True,
1808 },
313dfc45
LL
1809 {
1810 # Video with yt:stretch=17:0
1811 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1812 'info_dict': {
1813 'id': 'Q39EVAstoRM',
1814 'ext': 'mp4',
1815 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1816 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1817 'upload_date': '20151107',
313dfc45
LL
1818 },
1819 'params': {
1820 'skip_download': True,
1821 },
be49068d 1822 'skip': 'This video does not exist.',
313dfc45 1823 },
201c1459 1824 {
1825 # Video with incomplete 'yt:stretch=16:'
1826 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1827 'only_matching': True,
1828 },
7caf9830
S
1829 {
1830 # Video licensed under Creative Commons
1831 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1832 'info_dict': {
1833 'id': 'M4gD1WSo5mA',
1834 'ext': 'mp4',
1835 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1836 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1837 'duration': 721,
17322130 1838 'upload_date': '20150128',
7caf9830 1839 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1840 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1841 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1842 'like_count': int,
1843 'age_limit': 0,
1844 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1845 'channel': 'The Berkman Klein Center for Internet & Society',
1846 'availability': 'public',
1847 'view_count': int,
1848 'categories': ['Education'],
1849 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1850 'live_status': 'not_live',
1851 'playable_in_embed': True,
d5d1df8a 1852 'channel_follower_count': int,
1853 'chapters': list,
7666b936 1854 'uploader': 'The Berkman Klein Center for Internet & Society',
1855 'uploader_id': '@BKCHarvard',
1856 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
7caf9830
S
1857 },
1858 'params': {
1859 'skip_download': True,
1860 },
1861 },
fd050249 1862 {
fd050249
S
1863 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1864 'info_dict': {
1865 'id': 'eQcmzGIKrzg',
1866 'ext': 'mp4',
1867 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1868 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1869 'duration': 4060,
17322130 1870 'upload_date': '20151120',
fd050249 1871 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1872 'playable_in_embed': True,
1873 'tags': 'count:12',
1874 'like_count': int,
1875 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1876 'age_limit': 0,
1877 'availability': 'public',
1878 'categories': ['News & Politics'],
1879 'channel': 'Bernie Sanders',
1880 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1881 'view_count': int,
1882 'live_status': 'not_live',
1883 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1884 'comment_count': int,
d5d1df8a 1885 'channel_follower_count': int,
1886 'chapters': list,
7666b936 1887 'uploader': 'Bernie Sanders',
1888 'uploader_url': 'https://www.youtube.com/@BernieSanders',
1889 'uploader_id': '@BernieSanders',
fd050249
S
1890 },
1891 'params': {
1892 'skip_download': True,
1893 },
1894 },
040ac686
S
1895 {
1896 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1897 'only_matching': True,
7f29cf54
S
1898 },
1899 {
067aa17e 1900 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1901 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1902 'only_matching': True,
6496ccb4
S
1903 },
1904 {
1905 # Rental video preview
1906 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1907 'info_dict': {
1908 'id': 'uGpuVWrhIzE',
1909 'ext': 'mp4',
1910 'title': 'Piku - Trailer',
1911 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1912 'upload_date': '20150811',
6496ccb4
S
1913 'license': 'Standard YouTube License',
1914 },
1915 'params': {
1916 'skip_download': True,
1917 },
eb6793ba 1918 'skip': 'This video is not available.',
022a5d66 1919 },
12afdc2a
S
1920 {
1921 # YouTube Red video with episode data
1922 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1923 'info_dict': {
1924 'id': 'iqKdEhx-dD4',
1925 'ext': 'mp4',
1926 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1927 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1928 'duration': 2085,
12afdc2a 1929 'upload_date': '20170118',
12afdc2a
S
1930 'series': 'Mind Field',
1931 'season_number': 1,
1932 'episode_number': 1,
976ae3ea 1933 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1934 'tags': 'count:12',
1935 'view_count': int,
1936 'availability': 'public',
1937 'age_limit': 0,
1938 'channel': 'Vsauce',
1939 'episode': 'Episode 1',
1940 'categories': ['Entertainment'],
1941 'season': 'Season 1',
1942 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1943 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1944 'like_count': int,
1945 'playable_in_embed': True,
1946 'live_status': 'not_live',
7666b936 1947 'channel_follower_count': int,
1948 'uploader': 'Vsauce',
1949 'uploader_url': 'https://www.youtube.com/@Vsauce',
1950 'uploader_id': '@Vsauce',
12afdc2a
S
1951 },
1952 'params': {
1953 'skip_download': True,
1954 },
1955 'expected_warnings': [
1956 'Skipping DASH manifest',
1957 ],
1958 },
c7121fa7
S
1959 {
1960 # The following content has been identified by the YouTube community
1961 # as inappropriate or offensive to some audiences.
1962 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1963 'info_dict': {
1964 'id': '6SJNVb0GnPI',
1965 'ext': 'mp4',
1966 'title': 'Race Differences in Intelligence',
1967 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1968 'duration': 965,
1969 'upload_date': '20140124',
c7121fa7
S
1970 },
1971 'params': {
1972 'skip_download': True,
1973 },
545cc85d 1974 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1975 },
022a5d66
S
1976 {
1977 # itag 212
1978 'url': '1t24XAntNCY',
1979 'only_matching': True,
fd5c4aab
S
1980 },
1981 {
1982 # geo restricted to JP
1983 'url': 'sJL6WA-aGkQ',
1984 'only_matching': True,
1985 },
cd5a74a2
S
1986 {
1987 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1988 'only_matching': True,
1989 },
bc2ca1bb 1990 {
1991 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1992 'only_matching': True,
1993 },
1994 {
1995 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1996 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1997 'only_matching': True,
1998 },
825cd268
RA
1999 {
2000 # DRM protected
2001 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
2002 'only_matching': True,
4fe54c12
S
2003 },
2004 {
2005 # Video with unsupported adaptive stream type formats
2006 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2007 'info_dict': {
2008 'id': 'Z4Vy8R84T1U',
2009 'ext': 'mp4',
2010 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2011 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2012 'duration': 433,
2013 'upload_date': '20130923',
4fe54c12
S
2014 'formats': 'maxcount:10',
2015 },
2016 'params': {
2017 'skip_download': True,
2018 'youtube_include_dash_manifest': False,
2019 },
5429d6a9 2020 'skip': 'not actual anymore',
5caabd3c 2021 },
2022 {
822b9d9c 2023 # Youtube Music Auto-generated description
7666b936 2024 # TODO: fix metadata extraction
5caabd3c 2025 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2026 'info_dict': {
2027 'id': 'MgNrAu2pzNs',
2028 'ext': 'mp4',
2029 'title': 'Voyeur Girl',
2030 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2031 'upload_date': '20190312',
5caabd3c 2032 'artist': 'Stephen',
2033 'track': 'Voyeur Girl',
2034 'album': 'it\'s too much love to know my dear',
2035 'release_date': '20190313',
2036 'release_year': 2019,
976ae3ea 2037 'alt_title': 'Voyeur Girl',
2038 'view_count': int,
976ae3ea 2039 'playable_in_embed': True,
2040 'like_count': int,
2041 'categories': ['Music'],
2042 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
7666b936 2043 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
2044 'uploader': 'Stephen',
976ae3ea 2045 'availability': 'public',
2046 'creator': 'Stephen',
2047 'duration': 169,
2048 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2049 'age_limit': 0,
2050 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2051 'tags': 'count:11',
2052 'live_status': 'not_live',
6c73052c 2053 'channel_follower_count': int
5caabd3c 2054 },
2055 'params': {
2056 'skip_download': True,
2057 },
2058 },
66b48727
RA
2059 {
2060 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2061 'only_matching': True,
2062 },
011e75e6
S
2063 {
2064 # invalid -> valid video id redirection
2065 'url': 'DJztXj2GPfl',
2066 'info_dict': {
2067 'id': 'DJztXj2GPfk',
2068 'ext': 'mp4',
2069 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2070 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2071 'upload_date': '20090125',
011e75e6
S
2072 'artist': 'Panjabi MC',
2073 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2074 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2075 },
2076 'params': {
2077 'skip_download': True,
2078 },
545cc85d 2079 'skip': 'Video unavailable',
ea74e00b
DP
2080 },
2081 {
2082 # empty description results in an empty string
2083 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2084 'info_dict': {
2085 'id': 'x41yOUIvK2k',
2086 'ext': 'mp4',
2087 'title': 'IMG 3456',
2088 'description': '',
2089 'upload_date': '20170613',
976ae3ea 2090 'view_count': int,
2091 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2092 'like_count': int,
2093 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2094 'tags': [],
2095 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2096 'availability': 'public',
2097 'age_limit': 0,
2098 'categories': ['Pets & Animals'],
2099 'duration': 7,
2100 'playable_in_embed': True,
2101 'live_status': 'not_live',
7666b936 2102 'channel': 'l\'Or Vert asbl',
2103 'channel_follower_count': int,
2104 'uploader': 'l\'Or Vert asbl',
2105 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2106 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2107 },
2108 'params': {
2109 'skip_download': True,
2110 },
2111 },
a0566bbf 2112 {
29f7c58a 2113 # with '};' inside yt initial data (see [1])
2114 # see [2] for an example with '};' inside ytInitialPlayerResponse
2115 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2116 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2117 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2118 'info_dict': {
2119 'id': 'CHqg6qOn4no',
2120 'ext': 'mp4',
2121 'title': 'Part 77 Sort a list of simple types in c#',
2122 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2123 'upload_date': '20130831',
976ae3ea 2124 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2125 'like_count': int,
976ae3ea 2126 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2127 'live_status': 'not_live',
2128 'categories': ['Education'],
2129 'availability': 'public',
2130 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2131 'tags': 'count:12',
2132 'playable_in_embed': True,
2133 'age_limit': 0,
2134 'view_count': int,
2135 'duration': 522,
2136 'channel': 'kudvenkat',
12a1b225 2137 'comment_count': int,
d5d1df8a 2138 'channel_follower_count': int,
2139 'chapters': list,
7666b936 2140 'uploader': 'kudvenkat',
2141 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2142 'uploader_id': '@Csharp-video-tutorialsBlogspot',
a0566bbf 2143 },
2144 'params': {
2145 'skip_download': True,
2146 },
2147 },
29f7c58a 2148 {
2149 # another example of '};' in ytInitialData
2150 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2151 'only_matching': True,
2152 },
2153 {
2154 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2155 'only_matching': True,
2156 },
545cc85d 2157 {
cc2db878 2158 # https://github.com/ytdl-org/youtube-dl/pull/28094
2159 'url': 'OtqTfy26tG0',
2160 'info_dict': {
2161 'id': 'OtqTfy26tG0',
2162 'ext': 'mp4',
2163 'title': 'Burn Out',
2164 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2165 'upload_date': '20141120',
cc2db878 2166 'artist': 'The Cinematic Orchestra',
2167 'track': 'Burn Out',
2168 'album': 'Every Day',
976ae3ea 2169 'like_count': int,
2170 'live_status': 'not_live',
2171 'alt_title': 'Burn Out',
2172 'duration': 614,
2173 'age_limit': 0,
2174 'view_count': int,
2175 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2176 'creator': 'The Cinematic Orchestra',
2177 'channel': 'The Cinematic Orchestra',
2178 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2179 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2180 'availability': 'public',
2181 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2182 'categories': ['Music'],
2183 'playable_in_embed': True,
7666b936 2184 'channel_follower_count': int,
2185 'uploader': 'The Cinematic Orchestra',
2186 'comment_count': int,
cc2db878 2187 },
2188 'params': {
2189 'skip_download': True,
2190 },
545cc85d 2191 },
bc2ca1bb 2192 {
2193 # controversial video, only works with bpctr when authenticated with cookies
2194 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2195 'only_matching': True,
2196 },
a1a7907b 2197 {
2198 # controversial video, requires bpctr/contentCheckOk
2199 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2200 'info_dict': {
2201 'id': 'SZJvDhaSDnc',
2202 'ext': 'mp4',
2203 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2204 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2205 'upload_date': '20140716',
976ae3ea 2206 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2207 'duration': 170,
2208 'categories': ['News & Politics'],
976ae3ea 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,
7666b936 2219 'channel_follower_count': int,
2220 'uploader': 'CBS Mornings',
2221 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2222 'uploader_id': '@CBSMornings',
a1a7907b 2223 }
2224 },
f7ad7160 2225 {
2226 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2227 'url': 'cBvYw8_A0vQ',
2228 'info_dict': {
2229 'id': 'cBvYw8_A0vQ',
2230 'ext': 'mp4',
2231 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2232 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2233 'upload_date': '20201120',
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,
7666b936 2246 'channel_follower_count': int,
2247 'uploader': 'Walk around Japan',
2248 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2249 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2250 },
2251 'params': {
2252 'skip_download': True,
2253 },
0fb983f6 2254 }, {
2255 # Has multiple audio streams
2256 'url': 'WaOKSUlf4TM',
2257 'only_matching': True
9297939e 2258 }, {
2259 # Requires Premium: has format 141 when requested using YTM url
2260 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2261 'only_matching': True
2262 }, {
120916da 2263 # multiple subtitles with same lang_code
2264 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2265 'only_matching': True,
109dd3b2 2266 }, {
2267 # Force use android client fallback
2268 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2269 'info_dict': {
2270 'id': 'YOelRv7fMxY',
11f9be09 2271 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2272 'ext': '3gp',
2273 'upload_date': '20210624',
2274 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2275 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2276 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2277 'duration': 596,
2278 'categories': ['Entertainment'],
976ae3ea 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,
7666b936 2290 'uploader': 'colinfurze',
2291 'uploader_url': 'https://www.youtube.com/@colinfurze',
2292 'uploader_id': '@colinfurze',
109dd3b2 2293 },
2294 'params': {
2295 'format': '17', # 3gp format available on android
2296 'extractor_args': {'youtube': {'player_client': ['android']}},
2297 },
120916da 2298 },
109dd3b2 2299 {
2300 # Skip download of additional client configs (remix client config in this case)
2301 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2302 'only_matching': True,
2303 'params': {
2304 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2305 },
8fc54b12 2306 }, {
2307 # shorts
2308 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2309 'only_matching': True,
9222c381 2310 }, {
2311 'note': 'Storyboards',
2312 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2313 'info_dict': {
2314 'id': '5KLPxDtMqe8',
2315 'ext': 'mhtml',
2316 'format_id': 'sb0',
2317 'title': 'Your Brain is Plastic',
9222c381 2318 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2319 'upload_date': '20140324',
976ae3ea 2320 'like_count': int,
2321 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2322 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2323 'view_count': int,
2324 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2325 'playable_in_embed': True,
2326 'tags': 'count:12',
976ae3ea 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,
7666b936 2335 'uploader': 'SciShow',
2336 'uploader_url': 'https://www.youtube.com/@SciShow',
2337 'uploader_id': '@SciShow',
9222c381 2338 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2339 }, {
2340 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2341 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2342 'info_dict': {
2343 'id': '2NUZ8W2llS4',
2344 'ext': 'mp4',
2345 'title': 'The NP that test your phone performance 🙂',
2346 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 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,
7666b936 2362 'channel_follower_count': int,
2363 'uploader': 'Leon Nguyen',
2364 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2365 'uploader_id': '@LeonNguyen',
992f9a73 2366 }
1ff88b7a 2367 }, {
2368 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2369 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2370 'info_dict': {
2371 'id': '2NUZ8W2llS4',
2372 'ext': 'mp4',
2373 'title': 'The NP that test your phone performance 🙂',
2374 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 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,
7666b936 2390 'channel_follower_count': int,
2391 'uploader': 'Leon Nguyen',
2392 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2393 'uploader_id': '@LeonNguyen',
1ff88b7a 2394 },
2395 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2396 }, {
2397 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2398 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2399 'info_dict': {
2400 'id': 'mzZzzBU6lrM',
2401 'ext': 'mp4',
2402 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2403 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 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',
7666b936 2420 'channel_follower_count': int,
2421 'uploader': 'Quackity',
2422 'uploader_id': '@Quackity',
2423 'uploader_url': 'https://www.youtube.com/@Quackity',
992f9a73 2424 }
2425 },
2426 { # continuous livestream. Microformat upload date should be preferred.
2427 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2428 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2429 'info_dict': {
2430 'id': 'kgx4WGK0oNU',
2431 '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}',
2432 'ext': 'mp4',
2433 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2434 'availability': 'public',
2435 'age_limit': 0,
2436 'release_timestamp': 1637975704,
2437 'upload_date': '20210619',
2438 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2439 'live_status': 'is_live',
2440 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2441 'channel': 'Abao in Tokyo',
2442 'channel_follower_count': int,
2443 'release_date': '20211127',
2444 'tags': 'count:39',
2445 'categories': ['People & Blogs'],
2446 'like_count': int,
992f9a73 2447 'view_count': int,
2448 'playable_in_embed': True,
2449 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2450 'concurrent_view_count': int,
7666b936 2451 'uploader': 'Abao in Tokyo',
2452 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2453 'uploader_id': '@abaointokyo',
992f9a73 2454 },
2455 'params': {'skip_download': True}
6e634cbe 2456 }, {
2457 # Story. Requires specific player params to work.
ee27297f 2458 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2459 'info_dict': {
ee27297f 2460 'id': 'vv8qTUWmulI',
6e634cbe 2461 'ext': 'mp4',
ee27297f 2462 'availability': 'unlisted',
2463 'view_count': int,
2464 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2465 'upload_date': '20220526',
2466 'categories': ['Education'],
2467 'title': 'Story',
2468 'channel': 'IT\'S HISTORY',
2469 'description': '',
ee27297f 2470 'duration': 12,
6e634cbe 2471 'playable_in_embed': True,
6e634cbe 2472 'age_limit': 0,
6e634cbe 2473 'live_status': 'not_live',
ee27297f 2474 'tags': [],
2475 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
ee27297f 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',
7666b936 2488 'channel': 'Lesmiscore',
2489 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2490 'age_limit': 0,
ee27297f 2491 'categories': ['Music'],
6e634cbe 2492 'view_count': int,
2493 'description': '',
ee27297f 2494 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2495 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2496 'live_status': 'not_live',
2497 'playable_in_embed': True,
2498 'channel_follower_count': int,
2499 'duration': 6,
2500 'tags': [],
7666b936 2501 'uploader_id': '@lesmiscore',
2502 'uploader': 'Lesmiscore',
2503 'uploader_url': 'https://www.youtube.com/@lesmiscore',
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',
7666b936 2521 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2522 'age_limit': 0,
2523 'duration': 5,
c26f9b99 2524 'live_status': 'not_live',
2525 'upload_date': '20220908',
2526 'categories': ['People & Blogs'],
c26f9b99 2527 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2528 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2529 'uploader_id': '@coletdjnz',
2530 'uploader': 'cole-dlp-test-acc',
c26f9b99 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',
c26f9b99 2545 'view_count': int,
2546 'categories': ['People & Blogs'],
7666b936 2547 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2548 'title': 'dlp test video title translated (fr)',
2549 'availability': 'public',
c26f9b99 2550 'age_limit': 0,
2551 'description': 'dlp test video description translated (fr)',
2552 'playable_in_embed': True,
2553 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2554 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2555 'uploader_id': '@coletdjnz',
2556 'uploader': 'cole-dlp-test-acc',
c26f9b99 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',
a4894d3e 2572 'live_status': 'not_live',
2573 'duration': 937,
2574 'channel_follower_count': int,
2575 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2576 'title': 'Last To Take Hand Off Jet, Keeps It!',
2577 'channel': 'MrBeast',
2578 'playable_in_embed': True,
2579 'view_count': int,
2580 'upload_date': '20221112',
a4894d3e 2581 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2582 'age_limit': 0,
2583 'availability': 'public',
2584 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2585 'like_count': int,
2586 'tags': [],
7666b936 2587 'uploader': 'MrBeast',
2588 'uploader_url': 'https://www.youtube.com/@MrBeast',
2589 'uploader_id': '@MrBeast',
a4894d3e 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',
7666b936 2597 'ext': 'webm',
9bb85699 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',
9bb85699 2604 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2605 'playable_in_embed': True,
2606 'like_count': int,
2607 'categories': ['Entertainment'],
2608 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2609 'age_limit': 18,
2610 'channel': 'Projekt Melody',
9bb85699 2611 'view_count': int,
2612 'availability': 'needs_auth',
2613 'comment_count': int,
2614 'live_status': 'not_live',
9bb85699 2615 'duration': 106,
7666b936 2616 'uploader': 'Projekt Melody',
2617 'uploader_id': '@ProjektMelody',
2618 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 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,
dad2210c 2628 'comment_count': int,
2629 'chapters': 'count:13',
2630 'upload_date': '20221223',
2631 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2632 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2633 'like_count': int,
2634 'release_date': '20221223',
2635 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2636 '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】',
2637 'view_count': int,
2638 'playable_in_embed': True,
2639 'duration': 4438,
2640 'availability': 'public',
2641 'channel_follower_count': int,
2642 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2643 'categories': ['Entertainment'],
2644 'live_status': 'was_live',
2645 'release_timestamp': 1671793345,
2646 'channel': 'さなちゃんねる',
2647 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2648 'uploader': 'さなちゃんねる',
7666b936 2649 'uploader_url': 'https://www.youtube.com/@sana_natori',
2650 'uploader_id': '@sana_natori',
2651 },
2652 },
2653 {
2654 # Fallbacks when webpage and web client is unavailable
2655 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2656 'info_dict': {
2657 'id': 'wSSmNUl9Snw',
2658 'ext': 'mp4',
2659 # 'categories': ['Science & Technology'],
2660 'view_count': int,
2661 'chapters': 'count:2',
2662 'channel': 'Scott Manley',
2663 'like_count': int,
2664 'age_limit': 0,
2665 # 'availability': 'public',
2666 'channel_follower_count': int,
2667 'live_status': 'not_live',
2668 'upload_date': '20170831',
2669 'duration': 682,
2670 'tags': 'count:8',
2671 'uploader_url': 'https://www.youtube.com/@scottmanley',
2672 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2673 'uploader': 'Scott Manley',
2674 'uploader_id': '@scottmanley',
2675 'title': 'The Computer Hack That Saved Apollo 14',
2676 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2677 'thumbnail': r're:^https?://.*\.webp',
2678 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2679 'playable_in_embed': True,
2680 },
2681 'params': {
2682 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2683 },
2684 },
2eb88d95
PH
2685 ]
2686
f2e8dbcc 2687 _WEBPAGE_TESTS = [
2688 # YouTube <object> embed
2689 {
2690 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2691 'md5': '873c81d308b979f0e23ee7e620b312a3',
2692 'info_dict': {
2693 'id': 'msN87y-iEx0',
2694 'ext': 'mp4',
2695 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2696 'upload_date': '20080526',
2697 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2698 'age_limit': 0,
2699 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2700 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2701 'playable_in_embed': True,
2702 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2703 'like_count': int,
2704 'comment_count': int,
2705 'channel': 'Christopher Sykes',
2706 'live_status': 'not_live',
2707 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2708 'availability': 'public',
2709 'duration': 195,
2710 'view_count': int,
2711 'categories': ['Science & Technology'],
2712 'channel_follower_count': int,
7666b936 2713 'uploader': 'Christopher Sykes',
2714 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2715 'uploader_id': '@ChristopherSykesDocumentaries',
f2e8dbcc 2716 },
2717 'params': {
2718 'skip_download': True,
2719 }
2720 },
2721 ]
2722
201c1459 2723 @classmethod
2724 def suitable(cls, url):
4dfbf869 2725 from ..utils import parse_qs
2726
201c1459 2727 qs = parse_qs(url)
2728 if qs.get('list', [None])[0]:
2729 return False
86e5f3ed 2730 return super().suitable(url)
201c1459 2731
e0df6211 2732 def __init__(self, *args, **kwargs):
86e5f3ed 2733 super().__init__(*args, **kwargs)
545cc85d 2734 self._code_cache = {}
83799698 2735 self._player_cache = {}
e0df6211 2736
4d37720a 2737 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2738 lock = threading.Lock()
185bf310 2739 start_time = time.time()
adbc4ec4
THD
2740 formats = [f for f in formats if f.get('is_from_start')]
2741
185bf310 2742 def refetch_manifest(format_id, delay):
2743 nonlocal formats, start_time, is_live
2744 if time.time() <= start_time + delay:
adbc4ec4
THD
2745 return
2746
2747 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2748 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2749 microformats = traverse_obj(
2750 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2751 expected_type=dict)
4d37720a
L
2752 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2753 is_live = live_status == 'is_live'
185bf310 2754 start_time = time.time()
adbc4ec4 2755
185bf310 2756 def mpd_feed(format_id, delay):
adbc4ec4
THD
2757 """
2758 @returns (manifest_url, manifest_stream_number, is_live) or None
2759 """
253ac4ba 2760 for retry in self.RetryManager(fatal=False):
2761 with lock:
2762 refetch_manifest(format_id, delay)
2763
2764 f = next((f for f in formats if f['format_id'] == format_id), None)
2765 if not f:
2766 if not is_live:
2767 retry.error = f'{video_id}: Video is no longer live'
2768 else:
2769 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2770 continue
2771 return f['manifest_url'], f['manifest_stream_number'], is_live
2772 return None
adbc4ec4
THD
2773
2774 for f in formats:
4d37720a
L
2775 f['is_live'] = is_live
2776 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2777 live_start_time, mpd_feed, not is_live and f.copy())
2778 if is_live:
2779 f['fragments'] = gen
2780 f['protocol'] = 'http_dash_segments_generator'
2781 else:
2782 f['fragments'] = LazyList(gen({}))
2783 del f['is_from_start']
adbc4ec4 2784
4d37720a 2785 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2786 FETCH_SPAN, MAX_DURATION = 5, 432000
2787
2788 mpd_url, stream_number, is_live = None, None, True
2789
2790 begin_index = 0
2791 download_start_time = ctx.get('start') or time.time()
2792
2793 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2794 if lack_early_segments:
2795 self.report_warning(bug_reports_message(
2796 'Starting download from the last 120 hours of the live stream since '
2797 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2798 lack_early_segments = True
2799
2800 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2801 fragments, fragment_base_url = None, None
2802
a539f065 2803 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2804 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2805 # Obtain from MPD's maximum seq value
2806 old_mpd_url = mpd_url
185bf310 2807 last_error = ctx.pop('last_error', None)
14f25df2 2808 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2809 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2810 or (mpd_url, stream_number, False))
2811 if not refresh_sequence:
2812 if expire_fast and not is_live:
2813 return False, last_seq
2814 elif old_mpd_url == mpd_url:
2815 return True, last_seq
4d37720a
L
2816 if manifestless_orig_fmt:
2817 fmt_info = manifestless_orig_fmt
2818 else:
2819 try:
2820 fmts, _ = self._extract_mpd_formats_and_subtitles(
2821 mpd_url, None, note=False, errnote=False, fatal=False)
2822 except ExtractorError:
2823 fmts = None
2824 if not fmts:
2825 no_fragment_score += 2
2826 return False, last_seq
2827 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2828 fragments = fmt_info['fragments']
2829 fragment_base_url = fmt_info['fragment_base_url']
2830 assert fragment_base_url
2831
2832 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2833 return True, _last_seq
2834
4d37720a 2835 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2836 while is_live:
2837 fetch_time = time.time()
2838 if no_fragment_score > 30:
2839 return
2840 if last_segment_url:
2841 # Obtain from "X-Head-Seqnum" header value from each segment
2842 try:
2843 urlh = self._request_webpage(
2844 last_segment_url, None, note=False, errnote=False, fatal=False)
2845 except ExtractorError:
2846 urlh = None
2847 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2848 if last_seq is None:
a539f065 2849 no_fragment_score += 2
adbc4ec4
THD
2850 last_segment_url = None
2851 continue
2852 else:
a539f065
LNO
2853 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2854 no_fragment_score += 2
185bf310 2855 if not should_continue:
adbc4ec4
THD
2856 continue
2857
2858 if known_idx > last_seq:
2859 last_segment_url = None
2860 continue
2861
2862 last_seq += 1
2863
2864 if begin_index < 0 and known_idx < 0:
2865 # skip from the start when it's negative value
2866 known_idx = last_seq + begin_index
2867 if lack_early_segments:
2868 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2869 try:
2870 for idx in range(known_idx, last_seq):
2871 # do not update sequence here or you'll get skipped some part of it
a539f065 2872 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2873 if not should_continue:
adbc4ec4
THD
2874 known_idx = idx - 1
2875 raise ExtractorError('breaking out of outer loop')
2876 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2877 yield {
2878 'url': last_segment_url,
36195c44 2879 'fragment_count': last_seq,
adbc4ec4
THD
2880 }
2881 if known_idx == last_seq:
2882 no_fragment_score += 5
2883 else:
2884 no_fragment_score = 0
2885 known_idx = last_seq
2886 except ExtractorError:
2887 continue
2888
4d37720a
L
2889 if manifestless_orig_fmt:
2890 # Stop at the first iteration if running for post-live manifestless;
2891 # fragment count no longer increase since it starts
2892 break
2893
adbc4ec4
THD
2894 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2895
b6de707d 2896 def _extract_player_url(self, *ytcfgs, webpage=None):
2897 player_url = traverse_obj(
2898 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2899 get_all=False, expected_type=str)
11f9be09 2900 if not player_url:
b6de707d 2901 return
60f393e4 2902 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2903
b6de707d 2904 def _download_player_url(self, video_id, fatal=False):
2905 res = self._download_webpage(
2906 'https://www.youtube.com/iframe_api',
2907 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2908 if res:
2909 player_version = self._search_regex(
2910 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2911 if player_version:
2912 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2913
60064c53
PH
2914 def _signature_cache_id(self, example_sig):
2915 """ Return a string representation of a signature """
14f25df2 2916 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2917
e40c758c
S
2918 @classmethod
2919 def _extract_player_info(cls, player_url):
2920 for player_re in cls._PLAYER_INFO_RE:
2921 id_m = re.search(player_re, player_url)
2922 if id_m:
2923 break
2924 else:
c081b35c 2925 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2926 return id_m.group('id')
e40c758c 2927
404f611f 2928 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2929 player_id = self._extract_player_info(player_url)
2930 if player_id not in self._code_cache:
1276a43a 2931 code = self._download_webpage(
109dd3b2 2932 player_url, video_id, fatal=fatal,
2933 note='Downloading player ' + player_id,
2934 errnote='Download of %s failed' % player_url)
1276a43a 2935 if code:
2936 self._code_cache[player_id] = code
404f611f 2937 return self._code_cache.get(player_id)
109dd3b2 2938
e40c758c 2939 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2940 player_id = self._extract_player_info(player_url)
e0df6211 2941
c4417ddb 2942 # Read from filesystem cache
86e5f3ed 2943 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2944 assert os.path.basename(func_id) == func_id
a0e07d31 2945
ae61d108 2946 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2947 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2948
580ce007 2949 if not cache_spec:
2950 code = self._load_player(video_id, player_url)
404f611f 2951 if code:
109dd3b2 2952 res = self._parse_sig_js(code)
ac668111 2953 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2954 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2955 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2956
2957 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2958
60064c53 2959 def _print_sig_code(self, func, example_sig):
404f611f 2960 if not self.get_param('youtube_print_sig_code'):
2961 return
2962
edf3e38e
PH
2963 def gen_sig_code(idxs):
2964 def _genslice(start, end, step):
78caa52a 2965 starts = '' if start == 0 else str(start)
8bcc8756 2966 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2967 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2968 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2969
2970 step = None
7af808a5
PH
2971 # Quelch pyflakes warnings - start will be set when step is set
2972 start = '(Never used)'
edf3e38e
PH
2973 for i, prev in zip(idxs[1:], idxs[:-1]):
2974 if step is not None:
2975 if i - prev == step:
2976 continue
2977 yield _genslice(start, prev, step)
2978 step = None
2979 continue
2980 if i - prev in [-1, 1]:
2981 step = i - prev
2982 start = prev
2983 continue
2984 else:
78caa52a 2985 yield 's[%d]' % prev
edf3e38e 2986 if step is None:
78caa52a 2987 yield 's[%d]' % i
edf3e38e
PH
2988 else:
2989 yield _genslice(start, i, step)
2990
ac668111 2991 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2992 cache_res = func(test_string)
edf3e38e 2993 cache_spec = [ord(c) for c in cache_res]
78caa52a 2994 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2995 signature_id_tuple = '(%s)' % (
14f25df2 2996 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2997 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2998 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2999 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3000
e0df6211
PH
3001 def _parse_sig_js(self, jscode):
3002 funcname = self._search_regex(
abefc03f
S
3003 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3004 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
3005 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3006 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3007 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}\(a,\d+\))?',
31ce6e99 3008 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3009 # Obsolete patterns
4823ec9f 3010 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3011 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3012 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3013 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3014 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3015 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3016 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3017
3018 jsi = JSInterpreter(jscode)
3019 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3020 return lambda s: initial_function([s])
3021
580ce007 3022 def _cached(self, func, *cache_id):
3023 def inner(*args, **kwargs):
3024 if cache_id not in self._player_cache:
3025 try:
3026 self._player_cache[cache_id] = func(*args, **kwargs)
3027 except ExtractorError as e:
3028 self._player_cache[cache_id] = e
3029 except Exception as e:
3030 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3031
3032 ret = self._player_cache[cache_id]
3033 if isinstance(ret, Exception):
3034 raise ret
3035 return ret
3036 return inner
3037
545cc85d 3038 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3039 """Turn the encrypted s field into a working signature"""
580ce007 3040 extract_sig = self._cached(
3041 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3042 func = extract_sig(video_id, player_url, s)
3043 self._print_sig_code(func, s)
3044 return func(s)
404f611f 3045
3046 def _decrypt_nsig(self, s, video_id, player_url):
3047 """Turn the encrypted n field into a working signature"""
3048 if player_url is None:
3049 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3050 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3051
b505e851 3052 try:
3053 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3054 except ExtractorError as e:
3055 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3056 if self.get_param('youtube_print_sig_code'):
3057 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3058
25836db6 3059 try:
3060 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3061 ret = extract_nsig(jsi, func_code)(s)
3062 except JSInterpreter.Exception as e:
3063 try:
992dc6b4 3064 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3065 except ExtractorError:
3066 raise e
3067 self.report_warning(
3068 f'Native nsig extraction failed: Trying with PhantomJS\n'
3069 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3070 self.write_debug(e, only_once=True)
25836db6 3071
3072 args, func_body = func_code
3073 ret = jsi.execute(
3074 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3075 video_id=video_id, note='Executing signature code').strip()
580ce007 3076
3077 self.write_debug(f'Decrypted nsig {s} => {ret}')
3078 return ret
3079
90a1df30 3080 def _extract_n_function_name(self, jscode):
3081 funcname, idx = self._search_regex(
3082 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3083 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3084 if not idx:
3085 return funcname
3086
3087 return json.loads(js_to_json(self._search_regex(
3088 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3089 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3090
580ce007 3091 def _extract_n_function_code(self, video_id, player_url):
404f611f 3092 player_id = self._extract_player_info(player_url)
05deb747 3093 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3094 jscode = func_code or self._load_player(video_id, player_url)
3095 jsi = JSInterpreter(jscode)
404f611f 3096
3097 if func_code:
580ce007 3098 return jsi, player_id, func_code
404f611f 3099
b505e851 3100 func_name = self._extract_n_function_name(jscode)
3101
3102 # For redundancy
3103 func_code = self._search_regex(
3104 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3105 # NB: The end of the regex is intentionally kept strict
3106 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3107 jscode, 'nsig function', group=('var', 'code'), default=None)
3108 if func_code:
3109 func_code = ([func_code[0]], func_code[1])
3110 else:
3111 self.write_debug('Extracting nsig function with jsinterp')
3112 func_code = jsi.extract_function_code(func_name)
3113
580ce007 3114 self.cache.store('youtube-nsig', player_id, func_code)
3115 return jsi, player_id, func_code
3116
3117 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3118 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3119
580ce007 3120 def extract_nsig(s):
25836db6 3121 try:
3122 ret = func([s])
3123 except JSInterpreter.Exception:
3124 raise
3125 except Exception as e:
3126 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3127
f6ca640b 3128 if ret.startswith('enhanced_except_'):
25836db6 3129 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3130 return ret
580ce007 3131
3132 return extract_nsig
e0df6211 3133
109dd3b2 3134 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3135 """
3136 Extract signatureTimestamp (sts)
3137 Required to tell API what sig/player version is in use.
3138 """
3139 sts = None
3140 if isinstance(ytcfg, dict):
3141 sts = int_or_none(ytcfg.get('STS'))
3142
3143 if not sts:
3144 # Attempt to extract from player
3145 if player_url is None:
3146 error_msg = 'Cannot extract signature timestamp without player_url.'
3147 if fatal:
3148 raise ExtractorError(error_msg)
3149 self.report_warning(error_msg)
3150 return
404f611f 3151 code = self._load_player(video_id, player_url, fatal=fatal)
3152 if code:
109dd3b2 3153 sts = int_or_none(self._search_regex(
3154 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3155 'JS player signature timestamp', group='sts', fatal=fatal))
3156 return sts
3157
11f9be09 3158 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3159 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3160 label = 'fully ' if is_full else ''
3161 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3162 expected_type=url_or_none)
3163 if not url:
3164 self.report_warning(f'Unable to mark {label}watched')
3165 return
14f25df2 3166 parsed_url = urllib.parse.urlparse(url)
3167 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3168
3169 # cpn generation algorithm is reverse engineered from base.js.
3170 # In fact it works even with dummy cpn.
3171 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3172 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3173
3174 # # more consistent results setting it to right before the end
3175 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3176
3177 qs.update({
3178 'ver': ['2'],
3179 'cpn': [cpn],
3180 'cmt': video_length,
3181 'el': 'detailpage', # otherwise defaults to "shorts"
3182 })
3183
3184 if is_full:
3185 # these seem to mark watchtime "history" in the real world
3186 # they're required, so send in a single value
3187 qs.update({
5318156f 3188 'st': 0,
06cc8f10
B
3189 'et': video_length,
3190 })
3191
14f25df2 3192 url = urllib.parse.urlunparse(
3193 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3194
3195 self._download_webpage(
3196 url, video_id, f'Marking {label}watched',
3197 'Unable to mark watched', fatal=False)
d77ab8e2 3198
bfd973ec 3199 @classmethod
3200 def _extract_from_webpage(cls, url, webpage):
3201 # Invidious Instances
3202 # https://github.com/yt-dlp/yt-dlp/issues/195
3203 # https://github.com/iv-org/invidious/pull/1730
3204 mobj = re.search(
3205 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3206 webpage)
3207 if mobj:
3208 yield cls.url_result(mobj.group('url'), cls)
3209 raise cls.StopExtraction()
3210
3211 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3212
3213 # lazyYT YouTube embed
bfd973ec 3214 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3215 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3216
3217 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3218 for m in re.findall(r'''(?x)<div[^>]+
3219 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3220 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3221 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3222
97665381
PH
3223 @classmethod
3224 def extract_id(cls, url):
ae61d108 3225 video_id = cls.get_temp_id(url)
3226 if not video_id:
3227 raise ExtractorError(f'Invalid URL: {url}')
3228 return video_id
c5e8d7af 3229
7c365c21 3230 def _extract_chapters_from_json(self, data, duration):
3231 chapter_list = traverse_obj(
3232 data, (
3233 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3234 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3235 ), expected_type=list)
3236
22ccd542 3237 return self._extract_chapters_helper(
7c365c21 3238 chapter_list,
22ccd542 3239 start_function=lambda chapter: float_or_none(
7c365c21 3240 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3241 title_function=lambda chapter: traverse_obj(
7c365c21 3242 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3243 duration=duration)
3244
3245 def _extract_chapters_from_engagement_panel(self, data, duration):
3246 content_list = traverse_obj(
8bdd16b4 3247 data,
7c365c21 3248 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3249 expected_type=list)
052e1350 3250 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3251 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3252
1890fc63 3253 return next(filter(None, (
22ccd542 3254 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3255 chapter_time, chapter_title, duration)
1890fc63 3256 for contents in content_list)), [])
7c365c21 3257
5caf30db
A
3258 def _extract_heatmap_from_player_overlay(self, data):
3259 content_list = traverse_obj(data, (
3260 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', 'decoratedPlayerBarRenderer', 'playerBar',
3261 'multiMarkersPlayerBarRenderer', 'markersMap', ..., 'value', 'heatmap', 'heatmapRenderer', 'heatMarkers', {list}))
3262 return next(filter(None, (
3263 traverse_obj(contents, (..., 'heatMarkerRenderer', {
3264 'start_time': ('timeRangeStartMillis', {functools.partial(float_or_none, scale=1000)}),
3265 'end_time': {lambda x: (x['timeRangeStartMillis'] + x['markerDurationMillis']) / 1000},
3266 'value': ('heatMarkerIntensityScoreNormalized', {float_or_none}),
3267 })) for contents in content_list)), None)
3268
a1c5d2ca
M
3269 def _extract_comment(self, comment_renderer, parent=None):
3270 comment_id = comment_renderer.get('commentId')
3271 if not comment_id:
3272 return
fe93e2c4 3273
c35448b7 3274 info = {
3275 'id': comment_id,
3276 'text': self._get_text(comment_renderer, 'contentText'),
3277 'like_count': self._get_count(comment_renderer, 'voteCount'),
3278 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3279 'author': self._get_text(comment_renderer, 'authorText'),
3280 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3281 'parent': parent or 'root',
3282 }
fe93e2c4 3283
c26f9b99 3284 # Timestamp is an estimate calculated from the current time and time_text
3285 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3286 timestamp = self._parse_time_text(time_text)
3287
c35448b7 3288 info.update({
3289 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3290 '_time_text': time_text,
3291 'timestamp': timestamp,
3292 })
fe93e2c4 3293
c35448b7 3294 info['author_url'] = urljoin(
3295 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3296 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3297 expected_type=str, get_all=False))
a1c5d2ca 3298
c35448b7 3299 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3300 if author_is_uploader is not None:
3301 info['author_is_uploader'] = author_is_uploader
3302
3303 comment_abr = traverse_obj(
3304 comment_renderer, ('actionsButtons', 'commentActionButtonsRenderer'), expected_type=dict)
3305 if comment_abr is not None:
3306 info['is_favorited'] = 'creatorHeart' in comment_abr
3307
3308 comment_ab_icontype = traverse_obj(
3309 comment_renderer, ('authorCommentBadge', 'authorCommentBadgeRenderer', 'icon', 'iconType'))
3310 if comment_ab_icontype is not None:
3311 info['author_is_verified'] = comment_ab_icontype in ('CHECK_CIRCLE_THICK', 'OFFICIAL_ARTIST_BADGE')
3312
3313 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3314 if is_pinned:
3315 info['is_pinned'] = True
3316
3317 return info
a1c5d2ca 3318
46383212 3319 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3320
3321 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3322
3323 def extract_header(contents):
2d6659b9 3324 _continuation = None
3325 for content in contents:
46383212 3326 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3327 expected_comment_count = self._get_count(
3328 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3329
18f8fba7 3330 if expected_comment_count is not None:
46383212 3331 tracker['est_total'] = expected_comment_count
3332 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3333 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3334
3335 sort_menu_item = try_get(
3336 comments_header_renderer,
3337 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3338 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3339
3340 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3341 if not _continuation:
3342 continue
3343
46383212 3344 sort_text = str_or_none(sort_menu_item.get('title'))
3345 if not sort_text:
2d6659b9 3346 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3347 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3348 break
a2160aa4 3349 return _continuation
a1c5d2ca 3350
2d6659b9 3351 def extract_thread(contents):
a1c5d2ca 3352 if not parent:
46383212 3353 tracker['current_page_thread'] = 0
a1c5d2ca 3354 for content in contents:
46383212 3355 if not parent and tracker['total_parent_comments'] >= max_parents:
3356 yield
a1c5d2ca 3357 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3358 comment_renderer = get_first(
3359 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3360 expected_type=dict, default={})
a1c5d2ca 3361
a1c5d2ca
M
3362 comment = self._extract_comment(comment_renderer, parent)
3363 if not comment:
3364 continue
141a8dff 3365 comment_id = comment['id']
c35448b7 3366 if comment.get('is_pinned'):
141a8dff 3367 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3368 # Sometimes YouTube may break and give us infinite looping comments.
3369 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3370 if comment_id in tracker['seen_comment_ids']:
c35448b7 3371 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3372 # Pinned comments may appear a second time in newest first sort
3373 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3374 continue
7f51861b 3375 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3376 yield
3377 else:
3378 tracker['seen_comment_ids'].add(comment['id'])
46383212 3379
3380 tracker['running_total'] += 1
3381 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3382 yield comment
46383212 3383
a1c5d2ca
M
3384 # Attempt to get the replies
3385 comment_replies_renderer = try_get(
3386 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3387
3388 if comment_replies_renderer:
46383212 3389 tracker['current_page_thread'] += 1
a1c5d2ca 3390 comment_entries_iter = self._comment_entries(
99e9e001 3391 comment_replies_renderer, ytcfg, video_id,
46383212 3392 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3393 yield from itertools.islice(comment_entries_iter, min(
3394 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3395
46383212 3396 # Keeps track of counts across recursive calls
3397 if not tracker:
3398 tracker = dict(
3399 running_total=0,
18f8fba7 3400 est_total=None,
46383212 3401 current_page_thread=0,
3402 total_parent_comments=0,
7f51861b 3403 total_reply_comments=0,
141a8dff 3404 seen_comment_ids=set(),
3405 pinned_comment_ids=set()
3406 )
46383212 3407
3408 # TODO: Deprecated
2d6659b9 3409 # YouTube comments have a max depth of 2
46383212 3410 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3411 if max_depth:
da4db748 3412 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3413 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3414 if max_depth == 1 and parent:
3415 return
a1c5d2ca 3416
46383212 3417 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3418 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3419
46383212 3420 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3421
46383212 3422 response = None
6e634cbe 3423 is_forced_continuation = False
2d6659b9 3424 is_first_continuation = parent is None
6e634cbe 3425 if is_first_continuation and not continuation:
3426 # Sometimes you can get comments by generating the continuation yourself,
3427 # even if YouTube initially reports them being disabled - e.g. stories comments.
3428 # Note: if the comment section is actually disabled, YouTube may return a response with
3429 # required check_get_keys missing. So we will disable that check initially in this case.
3430 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3431 is_forced_continuation = True
a1c5d2ca 3432
18f8fba7 3433 continuation_items_path = (
3434 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3435 for page_num in itertools.count(0):
3436 if not continuation:
3437 break
46383212 3438 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3439 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3440 if page_num == 0:
3441 if is_first_continuation:
3442 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3443 else:
2d6659b9 3444 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3445 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3446 else:
3447 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3448 ' ' if parent else '', ' replies' if parent else '',
3449 page_num, comment_prog_str)
18f8fba7 3450
3451 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3452 # Ignore check if YouTube says the comment count is 0.
3453 check_get_keys = None
3454 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3455 check_get_keys = [[*continuation_items_path, ..., (
3456 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3457 try:
3458 response = self._extract_response(
3459 item_id=None, query=continuation,
3460 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3461 check_get_keys=check_get_keys)
e72e48c5
M
3462 except ExtractorError as e:
3463 # Ignore incomplete data error for replies if retries didn't work.
3464 # This is to allow any other parent comments and comment threads to be downloaded.
3465 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3466 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3467 self.report_warning(
3468 'Received incomplete data for a comment reply thread and retrying did not help. '
3469 'Ignoring to let other comments be downloaded.')
3470 else:
3471 raise
6e634cbe 3472 is_forced_continuation = False
2d6659b9 3473 continuation = None
18f8fba7 3474 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3475 if is_first_continuation:
3476 continuation = extract_header(continuation_items)
3477 is_first_continuation = False
2d6659b9 3478 if continuation:
a1c5d2ca 3479 break
46383212 3480 continue
a1c5d2ca 3481
46383212 3482 for entry in extract_thread(continuation_items):
3483 if not entry:
3484 return
3485 yield entry
3486 continuation = self._extract_continuation({'contents': continuation_items})
3487 if continuation:
2d6659b9 3488 break
a1c5d2ca 3489
6e634cbe 3490 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3491 if message and not parent and tracker['running_total'] == 0:
3492 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3493 raise self.CommentsDisabled
6e634cbe 3494
3495 @staticmethod
3496 def _generate_comment_continuation(video_id):
3497 """
3498 Generates initial comment section continuation token from given video id
3499 """
3500 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3501 return base64.b64encode(token.encode()).decode()
3502
a2160aa4 3503 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3504 """Entry for comment extraction"""
2d6659b9 3505 def _real_comment_extract(contents):
aae16f6e 3506 renderer = next((
3507 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3508 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3509 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3510
a2160aa4 3511 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3512 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3513
109dd3b2 3514 @staticmethod
99e9e001 3515 def _get_checkok_params():
3516 return {'contentCheckOk': True, 'racyCheckOk': True}
3517
3518 @classmethod
3519 def _generate_player_context(cls, sts=None):
109dd3b2 3520 context = {
3521 'html5Preference': 'HTML5_PREF_WANTS',
3522 }
3523 if sts is not None:
3524 context['signatureTimestamp'] = sts
3525 return {
3526 'playbackContext': {
3527 'contentPlaybackContext': context
a1a7907b 3528 },
99e9e001 3529 **cls._get_checkok_params()
109dd3b2 3530 }
3531
e7e94f2a
D
3532 @staticmethod
3533 def _is_agegated(player_response):
3534 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3535 return True
e7e94f2a 3536
6839ae1f 3537 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3538 AGE_GATE_REASONS = (
3539 'confirm your age', 'age-restricted', 'inappropriate', # reason
3540 'age_verification_required', 'age_check_required', # status
3541 )
3542 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3543
3544 @staticmethod
3545 def _is_unplayable(player_response):
3546 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3547
50ac0e54 3548 _STORY_PLAYER_PARAMS = '8AEB'
3549
3550 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3551
11f9be09 3552 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3553 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3554 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3555 headers = self.generate_api_headers(
99e9e001 3556 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3557
6e634cbe 3558 yt_query = {
3559 'videoId': video_id,
6e634cbe 3560 }
50ac0e54 3561 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3562 yt_query['params'] = self._STORY_PLAYER_PARAMS
3563
11f9be09 3564 yt_query.update(self._generate_player_context(sts))
3565 return self._extract_response(
3566 item_id=video_id, ep='player', query=yt_query,
379e44ed 3567 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3568 default_client=client,
11f9be09 3569 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3570 ) or None
3571
11f9be09 3572 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3573 requested_clients = []
d0d012d4 3574 default = ['android', 'web']
000c15a4 3575 allowed_clients = sorted(
86e5f3ed 3576 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3577 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3578 for client in self._configuration_arg('player_client'):
3579 if client in allowed_clients:
3580 requested_clients.append(client)
d0d012d4 3581 elif client == 'default':
3582 requested_clients.extend(default)
b4c055ba 3583 elif client == 'all':
3584 requested_clients.extend(allowed_clients)
3585 else:
3586 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3587 if not requested_clients:
d0d012d4 3588 requested_clients = default
cf7e015f 3589
11f9be09 3590 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3591 requested_clients.extend(
e7e94f2a 3592 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3593
11f9be09 3594 return orderedSet(requested_clients)
cf7e015f 3595
50ac0e54 3596 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3597 initial_pr = None
3598 if webpage:
b7c47b74 3599 initial_pr = self._search_json(
3600 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3601
ae729626 3602 all_clients = set(clients)
c0bc527b 3603 clients = clients[::-1]
b6de707d 3604 prs = []
e7e94f2a 3605
ae729626 3606 def append_client(*client_names):
e7870111 3607 """ Append the first client name that exists but not already used """
ae729626 3608 for client_name in client_names:
e7870111
D
3609 actual_client = _split_innertube_client(client_name)[0]
3610 if actual_client in INNERTUBE_CLIENTS:
3611 if actual_client not in all_clients:
ae729626 3612 clients.append(client_name)
e7870111
D
3613 all_clients.add(actual_client)
3614 return
e7e94f2a 3615
379e44ed 3616 # Android player_response does not have microFormats which are needed for
3617 # extraction of some data. So we return the initial_pr with formats
3618 # stripped out even if not requested by the user
3619 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3620 if initial_pr:
3621 pr = dict(initial_pr)
3622 pr['streamingData'] = None
b6de707d 3623 prs.append(pr)
379e44ed 3624
3625 last_error = None
b6de707d 3626 tried_iframe_fallback = False
3627 player_url = None
c0bc527b 3628 while clients:
e7870111 3629 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3630 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3631 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3632 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3633
b6de707d 3634 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3635 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3636 if 'js' in self._configuration_arg('player_skip'):
3637 require_js_player = False
3638 player_url = None
3639
3640 if not player_url and not tried_iframe_fallback and require_js_player:
3641 player_url = self._download_player_url(video_id)
3642 tried_iframe_fallback = True
3643
379e44ed 3644 try:
3645 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3646 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3647 except ExtractorError as e:
3648 if last_error:
3649 self.report_warning(last_error)
3650 last_error = e
3651 continue
3652
11f9be09 3653 if pr:
a3e96421 3654 # YouTube may return a different video player response than expected.
3655 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3656 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3657 if pr_video_id and pr_video_id != video_id:
3658 self.report_warning(
c7dcf0b3 3659 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3660 else:
c795c39f
L
3661 # Save client name for introspection later
3662 name = short_client_name(client)
3663 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3664 sd[STREAMING_DATA_CLIENT_NAME] = name
3665 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3666 f[STREAMING_DATA_CLIENT_NAME] = name
a3e96421 3667 prs.append(pr)
c0bc527b 3668
e7e94f2a 3669 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3670 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3671 append_client(f'{base_client}_creator')
e7e94f2a 3672 elif self._is_agegated(pr):
e7870111
D
3673 if variant == 'tv_embedded':
3674 append_client(f'{base_client}_embedded')
3675 elif not variant:
3676 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3677
379e44ed 3678 if last_error:
b6de707d 3679 if not len(prs):
379e44ed 3680 raise last_error
3681 self.report_warning(last_error)
b6de707d 3682 return prs, player_url
11f9be09 3683
4d37720a
L
3684 def _needs_live_processing(self, live_status, duration):
3685 if (live_status == 'is_live' and self.get_param('live_from_start')
3686 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3687 return live_status
3688
3689 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3690 CHUNK_SIZE = 10 << 20
a4894d3e 3691 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3692 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3693 q = qualities([
2a9c6dcd 3694 # Normally tiny is the smallest video-only formats. But
3695 # audio-only formats with unknown quality may get tagged as tiny
3696 'tiny',
3697 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3698 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3699 ])
6839ae1f 3700 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
86cb9221 3701 all_formats = self._configuration_arg('include_duplicate_formats')
9297939e 3702
e389d172 3703 def build_fragments(f):
3704 return LazyList({
3705 'url': update_url_query(f['url'], {
3706 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3707 })
3708 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3709
545cc85d 3710 for fmt in streaming_formats:
727029c5 3711 if fmt.get('targetDurationSec'):
545cc85d 3712 continue
321bf820 3713
cc2db878 3714 itag = str_or_none(fmt.get('itag'))
9297939e 3715 audio_track = fmt.get('audioTrack') or {}
9bb85699 3716 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3717 if not all_formats:
3718 if stream_id in stream_ids:
3719 continue
9297939e 3720
cc2db878 3721 quality = fmt.get('quality')
2a9c6dcd 3722 height = int_or_none(fmt.get('height'))
d3fc8074 3723 if quality == 'tiny' or not quality:
3724 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3725 # The 3gp format (17) in android client has a quality of "small",
3726 # but is actually worse than other formats
3727 if itag == '17':
3728 quality = 'tiny'
3729 if quality:
3730 if itag:
3731 itag_qualities[itag] = quality
3732 if height:
3733 res_qualities[height] = quality
cc2db878 3734 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3735 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3736 # number of fragment that would subsequently requested with (`&sq=N`)
3737 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3738 continue
3739
545cc85d 3740 fmt_url = fmt.get('url')
3741 if not fmt_url:
14f25df2 3742 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3743 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3744 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3745 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3746 continue
52023f12 3747 try:
3748 fmt_url += '&%s=%s' % (
3749 traverse_obj(sc, ('sp', -1)) or 'signature',
3750 self._decrypt_signature(encrypted_sig, video_id, player_url)
3751 )
3752 except ExtractorError as e:
580ce007 3753 self.report_warning('Signature extraction failed: Some formats may be missing',
3754 video_id=video_id, only_once=True)
52023f12 3755 self.write_debug(e, only_once=True)
201e9eaa 3756 continue
545cc85d 3757
404f611f 3758 query = parse_qs(fmt_url)
3759 throttled = False
b2916526 3760 if query.get('n'):
404f611f 3761 try:
580ce007 3762 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3763 fmt_url = update_url_query(fmt_url, {
580ce007 3764 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3765 })
404f611f 3766 except ExtractorError as e:
25836db6 3767 phantomjs_hint = ''
3768 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3769 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3770 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3771 if player_url:
3772 self.report_warning(
3773 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3774 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3775 self.write_debug(e, only_once=True)
3776 else:
3777 self.report_warning(
3778 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3779 video_id=video_id, only_once=True)
404f611f 3780 throttled = True
3781
0ad92dfb 3782 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3783 language_preference = (
3784 10 if audio_track.get('audioIsDefault') and 10
3785 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3786 else -1)
0ad92dfb 3787 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3788 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3789 # Make sure to avoid false positives with small duration differences.
62b58c09 3790 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3791 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3792 if is_damaged:
0f06bcd7 3793 self.report_warning(
3794 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3795
3796 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
545cc85d 3797 dct = {
3798 'asr': int_or_none(fmt.get('audioSampleRate')),
3799 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3800 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3801 'format_note': join_nonempty(
392389b7 3802 join_nonempty(audio_track.get('displayName'),
3803 language_preference > 0 and ' (default)', delim=''),
404f611f 3804 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
392389b7 3805 fmt.get('isDrc') and 'DRC',
a4166234 3806 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3807 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3808 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3809 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3810 delim=', '),
91e5e839 3811 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3812 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3813 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3814 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3815 'height': height,
9bb85699 3816 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3817 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3818 'tbr': tbr,
545cc85d 3819 'url': fmt_url,
2a9c6dcd 3820 'width': int_or_none(fmt.get('width')),
ab6df717 3821 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3822 'desc' if language_preference < -1 else '') or None,
ab6df717 3823 'language_preference': language_preference,
a405b38f 3824 # Strictly de-prioritize damaged and 3gp formats
3825 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3826 }
60bdb7bd 3827 mime_mobj = re.match(
3828 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3829 if mime_mobj:
3830 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3831 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3832 if itag:
3833 itags[itag].add(('https', dct.get('language')))
3834 stream_ids.append(stream_id)
c9abebb8 3835 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3836 if single_stream and dct.get('ext'):
3837 dct['container'] = dct['ext'] + '_dash'
86cb9221 3838
c6786ff3 3839 if all_formats and dct['filesize']:
86cb9221 3840 yield {
3841 **dct,
3842 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3843 'protocol': 'http_dash_segments',
e389d172 3844 'fragments': build_fragments(dct),
86cb9221 3845 }
86cb9221 3846 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
11f9be09 3847 yield dct
545cc85d 3848
4d37720a
L
3849 needs_live_processing = self._needs_live_processing(live_status, duration)
3850 skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
3851
3852 skip_manifests = set(self._configuration_arg('skip'))
3853 if (not self.get_param('youtube_include_hls_manifest', True)
3854 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3855 or needs_live_processing and skip_bad_formats):
3856 skip_manifests.add('hls')
3857
0f06bcd7 3858 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3859 skip_manifests.add('dash')
3860 if self._configuration_arg('include_live_dash'):
3861 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
3862 'Use include_incomplete_formats extractor argument instead')
3863 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3864 skip_manifests.add('dash')
5d3a0e79 3865
c795c39f 3866 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3867 key = (proto, f.get('language'))
86cb9221 3868 if not all_formats and key in itags[itag]:
a4894d3e 3869 return False
3870 itags[itag].add(key)
3871
86cb9221 3872 if itag and all_formats:
3873 f['format_id'] = f'{itag}-{proto}'
3874 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3875 f['format_id'] = f'{itag}-{proto}'
3876 elif itag:
a0bb6ce5 3877 f['format_id'] = itag
a0bb6ce5 3878
b25cac65 3879 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3880 if f['quality'] == -1 and f.get('height'):
3881 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
c795c39f
L
3882 if self.get_param('verbose'):
3883 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
a0bb6ce5 3884 return True
2a9c6dcd 3885
c646d76f 3886 subtitles = {}
11f9be09 3887 for sd in streaming_data:
c795c39f
L
3888 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3889
4d37720a 3890 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3891 if hls_manifest_url:
4d37720a
L
3892 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3893 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3894 subtitles = self._merge_subtitles(subs, subtitles)
3895 for f in fmts:
c795c39f 3896 if process_manifest_format(f, 'hls', client_name, self._search_regex(
a0bb6ce5 3897 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3898 yield f
545cc85d 3899
4d37720a 3900 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3901 if dash_manifest_url:
c646d76f 3902 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3903 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3904 for f in formats:
c795c39f 3905 if process_manifest_format(f, 'dash', client_name, f['format_id']):
a0bb6ce5 3906 f['filesize'] = int_or_none(self._search_regex(
3907 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3908 if needs_live_processing:
adbc4ec4
THD
3909 f['is_from_start'] = True
3910
a0bb6ce5 3911 yield f
c646d76f 3912 yield subtitles
11f9be09 3913
720c3099 3914 def _extract_storyboard(self, player_responses, duration):
3915 spec = get_first(
3916 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3917 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3918 if not base_url:
720c3099 3919 return
720c3099 3920 L = len(spec) - 1
3921 for i, args in enumerate(spec):
3922 args = args.split('#')
3923 counts = list(map(int_or_none, args[:5]))
3924 if len(args) != 8 or not all(counts):
3925 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3926 continue
3927 width, height, frame_count, cols, rows = counts
3928 N, sigh = args[6:]
3929
3930 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3931 fragment_count = frame_count / (cols * rows)
3932 fragment_duration = duration / fragment_count
3933 yield {
3934 'format_id': f'sb{i}',
3935 'format_note': 'storyboard',
3936 'ext': 'mhtml',
3937 'protocol': 'mhtml',
3938 'acodec': 'none',
3939 'vcodec': 'none',
3940 'url': url,
3941 'width': width,
3942 'height': height,
45e8a04e 3943 'fps': frame_count / duration,
3944 'rows': rows,
3945 'columns': cols,
720c3099 3946 'fragments': [{
b3edc806 3947 'url': url.replace('$M', str(j)),
720c3099 3948 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3949 } for j in range(math.ceil(fragment_count))],
3950 }
3951
adbc4ec4 3952 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3953 webpage = None
3954 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 3955 query = {'bpctr': '9999999999', 'has_verified': '1'}
3956 if smuggled_data.get('is_story'):
3957 query['pp'] = self._STORY_PLAYER_PARAMS
b6de707d 3958 webpage = self._download_webpage(
50ac0e54 3959 webpage_url, video_id, fatal=False, query=query)
11f9be09 3960
3961 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3962
b6de707d 3963 player_responses, player_url = self._extract_player_responses(
11f9be09 3964 self._get_requested_clients(url, smuggled_data),
50ac0e54 3965 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 3966
adbc4ec4
THD
3967 return webpage, master_ytcfg, player_responses, player_url
3968
a1b2d843 3969 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3970 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3971 is_live = get_first(video_details, 'isLive')
3972 if is_live is None:
3973 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
3974 live_content = get_first(video_details, 'isLiveContent')
3975 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
3976 post_live = get_first(video_details, 'isPostLiveDvr')
3977 live_status = ('post_live' if post_live
3978 else 'is_live' if is_live
3979 else 'is_upcoming' if is_upcoming
6678a4f0 3980 else 'was_live' if live_content
3981 else 'not_live' if False in (is_live, live_content)
3982 else None)
6839ae1f 3983 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 3984 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 3985
4d37720a 3986 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
3987
3988 def _real_extract(self, url):
3989 url, smuggled_data = unsmuggle_url(url, {})
3990 video_id = self._match_id(url)
3991
3992 base_url = self.http_scheme() + '//www.youtube.com/'
3993 webpage_url = base_url + 'watch?v=' + video_id
3994
3995 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3996
11f9be09 3997 playability_statuses = traverse_obj(
6839ae1f 3998 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 3999
4000 trailer_video_id = get_first(
4001 playability_statuses,
4002 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4003 expected_type=str)
4004 if trailer_video_id:
4005 return self.url_result(
4006 trailer_video_id, self.ie_key(), trailer_video_id)
4007
4008 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4009 if webpage else (lambda x: None))
4010
6839ae1f 4011 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4012 microformats = traverse_obj(
4013 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4014 expected_type=dict)
c26f9b99 4015
4016 translated_title = self._get_text(microformats, (..., 'title'))
4017 video_title = (self._preferred_lang and translated_title
4018 or get_first(video_details, 'title') # primary
4019 or translated_title
4020 or search_meta(['og:title', 'twitter:title', 'title']))
4021 translated_description = self._get_text(microformats, (..., 'description'))
4022 original_description = get_first(video_details, 'shortDescription')
4023 video_description = (
4024 self._preferred_lang and translated_description
4025 # If original description is blank, it will be an empty string.
4026 # Do not prefer translated description in this case.
4027 or original_description if original_description is not None else translated_description)
11f9be09 4028
d89257f3 4029 multifeed_metadata_list = get_first(
4030 player_responses,
4031 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4032 expected_type=str)
4033 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4034 if self.get_param('noplaylist'):
11f9be09 4035 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4036 else:
4037 entries = []
4038 feed_ids = []
4039 for feed in multifeed_metadata_list.split(','):
4040 # Unquote should take place before split on comma (,) since textual
4041 # fields may contain comma as well (see
4042 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4043 feed_data = urllib.parse.parse_qs(
ac668111 4044 urllib.parse.unquote_plus(feed))
d89257f3 4045
4046 def feed_entry(name):
4047 return try_get(
14f25df2 4048 feed_data, lambda x: x[name][0], str)
d89257f3 4049
4050 feed_id = feed_entry('id')
4051 if not feed_id:
4052 continue
4053 feed_title = feed_entry('title')
4054 title = video_title
4055 if feed_title:
4056 title += ' (%s)' % feed_title
4057 entries.append({
4058 '_type': 'url_transparent',
4059 'ie_key': 'Youtube',
4060 'url': smuggle_url(
4061 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4062 {'force_singlefeed': True}),
4063 'title': title,
4064 })
4065 feed_ids.append(feed_id)
4066 self.to_screen(
4067 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4068 % (', '.join(feed_ids), video_id))
4069 return self.playlist_result(
4070 entries, video_id, video_title, video_description)
11f9be09 4071
9da6612b 4072 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4073 or int_or_none(get_first(microformats, 'lengthSeconds'))
4074 or parse_duration(search_meta('duration')) or None)
a1b2d843 4075
4d37720a
L
4076 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4077 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4078 if live_status == 'post_live':
4079 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4080
545cc85d 4081 if not formats:
11f9be09 4082 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4083 self.report_drm(video_id)
11f9be09 4084 pemr = get_first(
4085 playability_statuses,
4086 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4087 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4088 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4089 if subreason:
545cc85d 4090 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4091 countries = get_first(microformats, 'availableCountries')
545cc85d 4092 if not countries:
4093 regions_allowed = search_meta('regionsAllowed')
4094 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4095 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4096 reason += f'. {subreason}'
545cc85d 4097 if reason:
b7da73eb 4098 self.raise_no_formats(reason, expected=True)
bf1317d2 4099
11f9be09 4100 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4101 if not keywords and webpage:
4102 keywords = [
4103 unescapeHTML(m.group('content'))
4104 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4105 for keyword in keywords:
4106 if keyword.startswith('yt:stretch='):
201c1459 4107 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4108 if mobj:
4109 # NB: float is intentional for forcing float division
4110 w, h = (float(v) for v in mobj.groups())
4111 if w > 0 and h > 0:
4112 ratio = w / h
4113 for f in formats:
4114 if f.get('vcodec') != 'none':
4115 f['stretched_ratio'] = ratio
4116 break
a709d873 4117 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4118 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4119 if thumbnail_url:
4120 thumbnails.append({
4121 'url': thumbnail_url,
ff2751ac 4122 })
fccf5021 4123 original_thumbnails = thumbnails.copy()
4124
0ba692ac 4125 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4126 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4127 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4128 thumbnail_names = [
962ffcf8 4129 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4130 # in resolution, these are not the custom thumbnail. So de-prioritize them
4131 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4132 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4133 ]
cca80fe6 4134 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4135 thumbnails.extend({
4136 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4137 video_id=video_id, name=name, ext=ext,
4d37720a 4138 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4139 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4140 for thumb in thumbnails:
cca80fe6 4141 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4142 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4143 self._remove_duplicate_formats(thumbnails)
fccf5021 4144 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4145
7ea65411 4146 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4147 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4148 get_first(video_details, 'channelId')
4149 or get_first(microformats, 'externalChannelId')
7666b936 4150 or search_meta('channelId')))
7ea65411 4151 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4152
adbc4ec4
THD
4153 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4154 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4155 if not duration and live_end_time and live_start_time:
4156 duration = live_end_time - live_start_time
4157
4d37720a
L
4158 needs_live_processing = self._needs_live_processing(live_status, duration)
4159
4160 def is_bad_format(fmt):
4161 if needs_live_processing and not fmt.get('is_from_start'):
4162 return True
4163 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4164 and fmt.get('protocol') == 'http_dash_segments'):
4165 return True
4166
4167 for fmt in filter(is_bad_format, formats):
4168 fmt['preference'] = (fmt.get('preference') or -1) - 10
4169 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
4170
4171 if needs_live_processing:
4172 self._prepare_live_from_start_formats(
4173 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4174
720c3099 4175 formats.extend(self._extract_storyboard(player_responses, duration))
4176
7666b936 4177 channel_handle = self.handle_from_url(owner_profile_url)
4178
545cc85d 4179 info = {
4180 'id': video_id,
39ca3b5c 4181 'title': video_title,
545cc85d 4182 'formats': formats,
4183 'thumbnails': thumbnails,
fccf5021 4184 # The best thumbnail that we are sure exists. Prevents unnecessary
4185 # URL checking if user don't care about getting the best possible thumbnail
4186 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4187 'description': video_description,
545cc85d 4188 'channel_id': channel_id,
7666b936 4189 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4190 'duration': duration,
4191 'view_count': int_or_none(
11f9be09 4192 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4193 or search_meta('interactionCount')),
11f9be09 4194 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4195 'age_limit': 18 if (
11f9be09 4196 get_first(microformats, 'isFamilySafe') is False
545cc85d 4197 or search_meta('isFamilyFriendly') == 'false'
4198 or search_meta('og:restrictions:age') == '18+') else 0,
4199 'webpage_url': webpage_url,
4200 'categories': [category] if category else None,
4201 'tags': keywords,
11f9be09 4202 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4203 'live_status': live_status,
adbc4ec4 4204 'release_timestamp': live_start_time,
9f14daf2 4205 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4206 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4207 }
b477fc13 4208
c646d76f 4209 subtitles = {}
3944e7af 4210 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4211 if pctr:
ecdc9049 4212 def get_lang_code(track):
4213 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4214 or track.get('languageCode'))
4215
4216 # Converted into dicts to remove duplicates
4217 captions = {
4218 get_lang_code(sub): sub
6839ae1f 4219 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4220 translation_languages = {
4221 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4222 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4223
774d79cc 4224 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4225 lang_subs = container.setdefault(lang_code, [])
545cc85d 4226 for fmt in self._SUBTITLE_FORMATS:
4227 query.update({
4228 'fmt': fmt,
4229 })
4230 lang_subs.append({
4231 'ext': fmt,
60f393e4 4232 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4233 'name': sub_name,
545cc85d 4234 })
7e72694b 4235
07b47084 4236 # NB: Constructing the full subtitle dictionary is slow
4237 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4238 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4239 for lang_code, caption_track in captions.items():
4240 base_url = caption_track.get('baseUrl')
1235d333 4241 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4242 if not base_url:
4243 continue
ecdc9049 4244 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4245 if caption_track.get('kind') != 'asr':
545cc85d 4246 if not lang_code:
4247 continue
4248 process_language(
ecdc9049 4249 subtitles, base_url, lang_code, lang_name, {})
4250 if not caption_track.get('isTranslatable'):
4251 continue
3944e7af 4252 for trans_code, trans_name in translation_languages.items():
4253 if not trans_code:
545cc85d 4254 continue
1235d333 4255 orig_trans_code = trans_code
71eb82d1 4256 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4257 if not get_translated_subs:
18e49408 4258 continue
ecdc9049 4259 trans_code += f'-{lang_code}'
a70635b8 4260 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 4261 # Add an "-orig" label to the original language so that it can be distinguished.
4262 # The subs are returned without "-orig" as well for compatibility
1235d333 4263 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 4264 process_language(
d49669ac 4265 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4266 # Setting tlang=lang returns damaged subtitles.
d49669ac 4267 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4268 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4269
4270 info['automatic_captions'] = automatic_captions
4271 info['subtitles'] = subtitles
7e72694b 4272
14f25df2 4273 parsed_url = urllib.parse.urlparse(url)
545cc85d 4274 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4275 query = urllib.parse.parse_qs(component)
545cc85d 4276 for k, v in query.items():
4277 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4278 d_k += '_time'
4279 if d_k not in info and k in s_ks:
4280 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4281
4282 # Youtube Music Auto-generated description
822b9d9c 4283 if video_description:
1890fc63 4284 mobj = re.search(
4285 r'''(?xs)
4286 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4287 (?P<album>[^\n]+)
4288 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4289 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4290 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4291 .+\nAuto-generated\ by\ YouTube\.\s*$
4292 ''', video_description)
822b9d9c 4293 if mobj:
822b9d9c
RA
4294 release_year = mobj.group('release_year')
4295 release_date = mobj.group('release_date')
4296 if release_date:
4297 release_date = release_date.replace('-', '')
4298 if not release_year:
545cc85d 4299 release_year = release_date[:4]
4300 info.update({
4301 'album': mobj.group('album'.strip()),
4302 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4303 'track': mobj.group('track').strip(),
4304 'release_date': release_date,
cc2db878 4305 'release_year': int_or_none(release_year),
545cc85d 4306 })
7e72694b 4307
545cc85d 4308 initial_data = None
4309 if webpage:
56ba69e4 4310 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4311 if not traverse_obj(initial_data, 'contents'):
4312 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4313 initial_data = None
545cc85d 4314 if not initial_data:
99e9e001 4315 query = {'videoId': video_id}
4316 query.update(self._get_checkok_params())
109dd3b2 4317 initial_data = self._extract_response(
4318 item_id=video_id, ep='next', fatal=False,
607510b9 4319 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4320 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4321 note='Downloading initial data API JSON')
545cc85d 4322
0df111a3 4323 info['comment_count'] = traverse_obj(initial_data, (
4324 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4325 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4326 ), (
4327 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4328 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4329 ), expected_type=self._get_count, get_all=False)
0df111a3 4330
19a03940 4331 try: # This will error if there is no livechat
c60ee3a2 4332 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4333 except (KeyError, IndexError, TypeError):
4334 pass
4335 else:
ecdc9049 4336 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4337 # url is needed to set cookies
4338 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4339 'video_id': video_id,
4340 'ext': 'json',
4d37720a
L
4341 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4342 else 'youtube_live_chat_replay'),
c60ee3a2 4343 }]
545cc85d 4344
4345 if initial_data:
7c365c21 4346 info['chapters'] = (
4347 self._extract_chapters_from_json(initial_data, duration)
4348 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4349 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4350 or None)
545cc85d 4351
5caf30db
A
4352 info['heatmap'] = self._extract_heatmap_from_player_overlay(initial_data)
4353
17322130 4354 contents = traverse_obj(
4355 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4356 expected_type=list, default=[])
4357
4358 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4359 if vpir:
4360 stl = vpir.get('superTitleLink')
4361 if stl:
4362 stl = self._get_text(stl)
4363 if try_get(
4364 vpir,
4365 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4366 info['location'] = stl
4367 else:
affc4fef 4368 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4369 if mobj:
545cc85d 4370 info.update({
17322130 4371 'series': mobj.group(1),
4372 'season_number': int(mobj.group(2)),
4373 'episode_number': int(mobj.group(3)),
545cc85d 4374 })
17322130 4375 for tlb in (try_get(
4376 vpir,
4377 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4378 list) or []):
3ffb2f5b 4379 tbrs = variadic(
4380 traverse_obj(
6839ae1f
SS
4381 tlb, ('toggleButtonRenderer', ...),
4382 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4383 for tbr in tbrs:
4384 for getter, regex in [(
4385 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4386 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4387 lambda x: x['accessibility'],
4388 lambda x: x['accessibilityData']['accessibilityData'],
4389 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4390 label = (try_get(tbr, getter, dict) or {}).get('label')
4391 if label:
4392 mobj = re.match(regex, label)
4393 if mobj:
4394 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4395 break
17322130 4396 sbr_tooltip = try_get(
4397 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4398 if sbr_tooltip:
4399 like_count, dislike_count = sbr_tooltip.split(' / ')
4400 info.update({
4401 'like_count': str_to_int(like_count),
4402 'dislike_count': str_to_int(dislike_count),
4403 })
867c66ff
M
4404 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4405 if vcr:
4406 vc = self._get_count(vcr, 'viewCount')
4407 # Upcoming premieres with waiting count are treated as live here
4408 if vcr.get('isLive'):
4409 info['concurrent_view_count'] = vc
4410 elif info.get('view_count') is None:
4411 info['view_count'] = vc
4412
17322130 4413 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4414 if vsir:
4415 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4416 info.update({
4417 'channel': self._get_text(vor, 'title'),
4418 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4419
7666b936 4420 if not channel_handle:
4421 channel_handle = self.handle_from_url(
4422 traverse_obj(vor, (
4423 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4424 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4425 {str}), get_all=False))
4426
17322130 4427 rows = try_get(
4428 vsir,
4429 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4430 list) or []
4431 multiple_songs = False
4432 for row in rows:
4433 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4434 multiple_songs = True
4435 break
4436 for row in rows:
4437 mrr = row.get('metadataRowRenderer') or {}
4438 mrr_title = mrr.get('title')
4439 if not mrr_title:
4440 continue
4441 mrr_title = self._get_text(mrr, 'title')
4442 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4443 if mrr_title == 'License':
4444 info['license'] = mrr_contents_text
4445 elif not multiple_songs:
4446 if mrr_title == 'Album':
4447 info['album'] = mrr_contents_text
4448 elif mrr_title == 'Artist':
4449 info['artist'] = mrr_contents_text
4450 elif mrr_title == 'Song':
4451 info['track'] = mrr_contents_text
545cc85d 4452
7666b936 4453 info.update({
4454 'uploader': info.get('channel'),
4455 'uploader_id': channel_handle,
4456 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4457 })
17322130 4458 # The upload date for scheduled, live and past live streams / premieres in microformats
4459 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4460 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4461 upload_date = (
4462 unified_strdate(get_first(microformats, 'uploadDate'))
4463 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4464 if not upload_date or (
4d37720a 4465 live_status in ('not_live', None)
1ff88b7a 4466 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4467 ):
c26f9b99 4468 upload_date = strftime_or_none(
4469 self._parse_time_text(self._get_text(vpir, 'dateText')), '%Y%m%d') or upload_date
17322130 4470 info['upload_date'] = upload_date
992f9a73 4471
545cc85d 4472 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4473 v = info.get(s_k)
4474 if v:
4475 info[d_k] = v
b84071c0 4476
c26f9b99 4477 badges = self._extract_badges(traverse_obj(contents, (..., 'videoPrimaryInfoRenderer'), get_all=False))
4478
4479 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4480 or get_first(video_details, 'isPrivate', expected_type=bool))
4481
4482 info['availability'] = (
4483 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4484 else self._availability(
4485 is_private=is_private,
4486 needs_premium=(
4487 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4488 or False if initial_data and is_private is not None else None),
4489 needs_subscription=(
4490 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4491 or False if initial_data and is_private is not None else None),
4492 needs_auth=info['age_limit'] >= 18,
4493 is_unlisted=None if is_private is None else (
4494 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4495 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4496
a2160aa4 4497 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4498
11f9be09 4499 self.mark_watched(video_id, player_responses)
d77ab8e2 4500
545cc85d 4501 return info
c5e8d7af 4502
a61fd4cf 4503
a6213a49 4504class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4505 @staticmethod
4506 def passthrough_smuggled_data(func):
bd7e919a 4507 def _smuggle(info, smuggled_data):
4508 if info.get('_type') not in ('url', 'url_transparent'):
4509 return info
4510 if smuggled_data.get('is_music_url'):
4511 parsed_url = urllib.parse.urlparse(info['url'])
4512 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4513 smuggled_data.pop('is_music_url')
4514 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4515 if smuggled_data:
4516 info['url'] = smuggle_url(info['url'], smuggled_data)
4517 return info
182bda88 4518
4519 @functools.wraps(func)
4520 def wrapper(self, url):
4521 url, smuggled_data = unsmuggle_url(url, {})
4522 if self.is_music_url(url):
4523 smuggled_data['is_music_url'] = True
4524 info_dict = func(self, url, smuggled_data)
bd7e919a 4525 if smuggled_data:
4526 _smuggle(info_dict, smuggled_data)
4527 if info_dict.get('entries'):
a8c754cc 4528 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4529 return info_dict
4530 return wrapper
4531
8bdd16b4 4532 @staticmethod
cd7c66cf 4533 def _extract_basic_item_renderer(item):
4534 # Modified from _extract_grid_item_renderer
201c1459 4535 known_basic_renderers = (
a17526e4 4536 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4537 )
4538 for key, renderer in item.items():
201c1459 4539 if not isinstance(renderer, dict):
cd7c66cf 4540 continue
201c1459 4541 elif key in known_basic_renderers:
4542 return renderer
4543 elif key.startswith('grid') and key.endswith('Renderer'):
4544 return renderer
8bdd16b4 4545
c7335551 4546 def _extract_channel_renderer(self, renderer):
7666b936 4547 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4548 title = self._get_text(renderer, 'title')
7666b936 4549 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
4550 # As of 2023-03-01 YouTube doesn't use the channel handles on these renderers yet.
4551 # However we can expect them to change that in the future.
4552 channel_handle = self.handle_from_url(
4553 traverse_obj(renderer, (
4554 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4555 ('browseEndpoint', 'canonicalBaseUrl')),
4556 {str}), get_all=False))
c7335551
M
4557 return {
4558 '_type': 'url',
4559 'url': channel_url,
4560 'id': channel_id,
4561 'ie_key': YoutubeTabIE.ie_key(),
4562 'channel': title,
7666b936 4563 'uploader': title,
c7335551
M
4564 'channel_id': channel_id,
4565 'channel_url': channel_url,
4566 'title': title,
7666b936 4567 'uploader_id': channel_handle,
4568 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
c7335551
M
4569 'channel_follower_count': self._get_count(renderer, 'subscriberCountText'),
4570 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
4571 'playlist_count': self._get_count(renderer, 'videoCountText'),
4572 'description': self._get_text(renderer, 'descriptionSnippet'),
4573 }
4574
8bdd16b4 4575 def _grid_entries(self, grid_renderer):
4576 for item in grid_renderer['items']:
4577 if not isinstance(item, dict):
39b62db1 4578 continue
cd7c66cf 4579 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4580 if not isinstance(renderer, dict):
4581 continue
052e1350 4582 title = self._get_text(renderer, 'title')
fe93e2c4 4583
8bdd16b4 4584 # playlist
4585 playlist_id = renderer.get('playlistId')
4586 if playlist_id:
4587 yield self.url_result(
4588 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4589 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4590 video_title=title)
201c1459 4591 continue
8bdd16b4 4592 # video
4593 video_id = renderer.get('videoId')
4594 if video_id:
4595 yield self._extract_video(renderer)
201c1459 4596 continue
8bdd16b4 4597 # channel
4598 channel_id = renderer.get('channelId')
4599 if channel_id:
c7335551 4600 yield self._extract_channel_renderer(renderer)
201c1459 4601 continue
4602 # generic endpoint URL support
4603 ep_url = urljoin('https://www.youtube.com/', try_get(
4604 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4605 str))
201c1459 4606 if ep_url:
4607 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4608 if ie.suitable(ep_url):
4609 yield self.url_result(
4610 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4611 break
8bdd16b4 4612
16aa9ea4 4613 def _music_reponsive_list_entry(self, renderer):
4614 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4615 if video_id:
69a40e4a 4616 title = traverse_obj(renderer, (
4617 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4618 'text', 'runs', 0, 'text'))
16aa9ea4 4619 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4620 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4621 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4622 if playlist_id:
4623 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4624 if video_id:
4625 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4626 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4627 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4628 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4629 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4630 if browse_id:
4631 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4632 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4633
3d3dddc9 4634 def _shelf_entries_from_content(self, shelf_renderer):
4635 content = shelf_renderer.get('content')
4636 if not isinstance(content, dict):
8bdd16b4 4637 return
cd7c66cf 4638 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4639 if renderer:
4640 # TODO: add support for nested playlists so each shelf is processed
4641 # as separate playlist
4642 # TODO: this includes only first N items
86e5f3ed 4643 yield from self._grid_entries(renderer)
3d3dddc9 4644 renderer = content.get('horizontalListRenderer')
4645 if renderer:
4646 # TODO
4647 pass
8bdd16b4 4648
29f7c58a 4649 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4650 ep = try_get(
4651 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4652 str)
8bdd16b4 4653 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4654 if shelf_url:
29f7c58a 4655 # Skipping links to another channels, note that checking for
4656 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4657 # will not work
4658 if skip_channels and '/channels?' in shelf_url:
4659 return
052e1350 4660 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4661 yield self.url_result(shelf_url, video_title=title)
4662 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4663 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4664
8bdd16b4 4665 def _playlist_entries(self, video_list_renderer):
4666 for content in video_list_renderer['contents']:
4667 if not isinstance(content, dict):
4668 continue
4669 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4670 if not isinstance(renderer, dict):
4671 continue
4672 video_id = renderer.get('videoId')
4673 if not video_id:
4674 continue
4675 yield self._extract_video(renderer)
07aeced6 4676
3462ffa8 4677 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4678 renderer = traverse_obj(
447afb9e 4679 rich_grid_renderer,
4680 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4681 video_id = renderer.get('videoId')
447afb9e 4682 if video_id:
4683 yield self._extract_video(renderer)
4684 return
4685 playlist_id = renderer.get('playlistId')
4686 if playlist_id:
4687 yield self.url_result(
4688 f'https://www.youtube.com/playlist?list={playlist_id}',
4689 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4690 video_title=self._get_text(renderer, 'title'))
3462ffa8 4691 return
3462ffa8 4692
8bdd16b4 4693 def _video_entry(self, video_renderer):
4694 video_id = video_renderer.get('videoId')
4695 if video_id:
4696 return self._extract_video(video_renderer)
dacb3a86 4697
ad210f4f 4698 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4699 url = urljoin('https://youtube.com', traverse_obj(
4700 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4701 if url:
4702 return self.url_result(
4703 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4704
8bdd16b4 4705 def _post_thread_entries(self, post_thread_renderer):
4706 post_renderer = try_get(
4707 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4708 if not post_renderer:
4709 return
4710 # video attachment
4711 video_renderer = try_get(
895b0931 4712 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4713 video_id = video_renderer.get('videoId')
4714 if video_id:
4715 entry = self._extract_video(video_renderer)
8bdd16b4 4716 if entry:
4717 yield entry
895b0931 4718 # playlist attachment
4719 playlist_id = try_get(
14f25df2 4720 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4721 if playlist_id:
4722 yield self.url_result(
e28f1c0a 4723 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4724 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4725 # inline video links
4726 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4727 for run in runs:
4728 if not isinstance(run, dict):
4729 continue
4730 ep_url = try_get(
14f25df2 4731 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4732 if not ep_url:
4733 continue
4734 if not YoutubeIE.suitable(ep_url):
4735 continue
4736 ep_video_id = YoutubeIE._match_id(ep_url)
4737 if video_id == ep_video_id:
4738 continue
895b0931 4739 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4740
8bdd16b4 4741 def _post_thread_continuation_entries(self, post_thread_continuation):
4742 contents = post_thread_continuation.get('contents')
4743 if not isinstance(contents, list):
4744 return
4745 for content in contents:
4746 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4747 if isinstance(renderer, dict):
4748 yield from self._post_thread_entries(renderer)
8bdd16b4 4749 continue
6b0b0a28 4750 renderer = content.get('videoRenderer')
4751 if isinstance(renderer, dict):
4752 yield self._video_entry(renderer)
07aeced6 4753
39ed931e 4754 r''' # unused
4755 def _rich_grid_entries(self, contents):
4756 for content in contents:
4757 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4758 if video_renderer:
4759 entry = self._video_entry(video_renderer)
4760 if entry:
4761 yield entry
4762 '''
52efa4b3 4763
0a5095fe 4764 def _report_history_entries(self, renderer):
4765 for url in traverse_obj(renderer, (
7a32c70d 4766 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4767 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4768 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4769 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4770
a6213a49 4771 def _extract_entries(self, parent_renderer, continuation_list):
4772 # continuation_list is modified in-place with continuation_list = [continuation_token]
4773 continuation_list[:] = [None]
4774 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4775 for content in contents:
4776 if not isinstance(content, dict):
4777 continue
16aa9ea4 4778 is_renderer = traverse_obj(
4779 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4780 expected_type=dict)
a6213a49 4781 if not is_renderer:
0a5095fe 4782 if content.get('richItemRenderer'):
4783 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4784 yield entry
4785 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4786 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4787 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4788 yield from self._report_history_entries(table)
4789 continuation_list[0] = self._extract_continuation(table)
a6213a49 4790 continue
0a5095fe 4791
a6213a49 4792 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4793 for isr_content in isr_contents:
4794 if not isinstance(isr_content, dict):
8bdd16b4 4795 continue
69184e41 4796
a6213a49 4797 known_renderers = {
4798 'playlistVideoListRenderer': self._playlist_entries,
4799 'gridRenderer': self._grid_entries,
a17526e4 4800 'reelShelfRenderer': self._grid_entries,
4801 'shelfRenderer': self._shelf_entries,
16aa9ea4 4802 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4803 'backstagePostThreadRenderer': self._post_thread_entries,
4804 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4805 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4806 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4807 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4808 }
4809 for key, renderer in isr_content.items():
4810 if key not in known_renderers:
4811 continue
4812 for entry in known_renderers[key](renderer):
4813 if entry:
4814 yield entry
4815 continuation_list[0] = self._extract_continuation(renderer)
4816 break
70d5c17b 4817
4818 if not continuation_list[0]:
a6213a49 4819 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4820
a6213a49 4821 if not continuation_list[0]:
4822 continuation_list[0] = self._extract_continuation(parent_renderer)
4823
4824 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4825 continuation_list = [None]
4826 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4827 tab_content = try_get(tab, lambda x: x['content'], dict)
4828 if not tab_content:
4829 return
3462ffa8 4830 parent_renderer = (
29f7c58a 4831 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4832 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4833 yield from extract_entries(parent_renderer)
3462ffa8 4834 continuation = continuation_list[0]
d069eca7 4835
8bdd16b4 4836 for page_num in itertools.count(1):
4837 if not continuation:
4838 break
99e9e001 4839 headers = self.generate_api_headers(
4840 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4841 response = self._extract_response(
86e5f3ed 4842 item_id=f'{item_id} page {page_num}',
fe93e2c4 4843 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4844 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4845
4846 if not response:
8bdd16b4 4847 break
ac56cf38 4848 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4849 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4850 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4851
a1b535bd 4852 known_renderers = {
e4b98809 4853 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4854 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4855 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4856 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4857 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4858 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4859 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4860 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4861 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4862 'playlistVideoListContinuation': (self._playlist_entries, None),
4863 'gridContinuation': (self._grid_entries, None),
4864 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4865 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4866 }
1fb53b94 4867
4868 continuation_items = traverse_obj(response, (
4869 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4870 'appendContinuationItemsAction', 'continuationItems'
4871 ), 'continuationContents', get_all=False)
4872 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4873
a1b535bd 4874 video_items_renderer = None
1fb53b94 4875 for key in continuation_item.keys():
a1b535bd 4876 if key not in known_renderers:
8bdd16b4 4877 continue
1fb53b94 4878 func, parent_key = known_renderers[key]
4879 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4880 continuation_list = [None]
1fb53b94 4881 yield from func(video_items_renderer)
9ba5705a 4882 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4883
4884 if not video_items_renderer:
a1b535bd 4885 break
9558dcec 4886
8bdd16b4 4887 @staticmethod
7c219ea6 4888 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4889 for tab_renderer in tabs:
4890 if tab_renderer.get('selected'):
4891 return tab_renderer
4892 if fatal:
4893 raise ExtractorError('Unable to find selected tab')
4894
4895 @staticmethod
4896 def _extract_tab_renderers(response):
4897 return traverse_obj(
4898 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4899
ac56cf38 4900 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 4901 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 4902
8bdd16b4 4903 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 4904 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
4905 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
4906
4907 return self.playlist_result(
4908 self._entries(
4909 selected_tab, metadata['id'], ytcfg,
4910 self._extract_account_syncid(ytcfg, data),
4911 self._extract_visitor_data(data, ytcfg)),
4912 **metadata)
39ed931e 4913
bd7e919a 4914 def _extract_metadata_from_tabs(self, item_id, data):
4915 info = {'id': item_id}
4916
4917 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 4918 if metadata_renderer:
7666b936 4919 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 4920 ('channelUrl', {self.ucid_from_url}))
bd7e919a 4921 info.update({
7666b936 4922 'channel': metadata_renderer.get('title'),
4923 'channel_id': channel_id,
bd7e919a 4924 })
7666b936 4925 if info['channel_id']:
4926 info['id'] = info['channel_id']
bd7e919a 4927 else:
4928 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 4929
301d07fc 4930 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4931 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4932 def _get_uncropped(url):
4933 return url_or_none((url or '').split('=')[0] + '=s0')
4934
6141346d 4935 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 4936 if avatar_thumbnails:
4937 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4938 if uncropped_avatar:
4939 avatar_thumbnails.append({
4940 'url': uncropped_avatar,
4941 'id': 'avatar_uncropped',
4942 'preference': 1
4943 })
4944
4945 channel_banners = self._extract_thumbnails(
bd7e919a 4946 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 4947 for banner in channel_banners:
4948 banner['preference'] = -10
4949
4950 if channel_banners:
4951 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4952 if uncropped_banner:
4953 channel_banners.append({
4954 'url': uncropped_banner,
4955 'id': 'banner_uncropped',
4956 'preference': -5
4957 })
4958
bd7e919a 4959 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4960 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4961 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
4962
301d07fc 4963 primary_thumbnails = self._extract_thumbnails(
a17526e4 4964 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
4965 playlist_thumbnails = self._extract_thumbnails(
4966 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4967
bd7e919a 4968 info.update({
4969 'title': (traverse_obj(metadata_renderer, 'title')
4970 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4971 or info['id']),
4972 'availability': self._extract_availability(data),
4973 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4974 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
4975 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
4976 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
4977 })
f0d785d3 4978
7666b936 4979 channel_handle = (
4980 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
4981 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
4982
4983 if channel_handle:
4984 info.update({
4985 'uploader_id': channel_handle,
4986 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4987 })
6141346d
M
4988 # Playlist stats is a text runs array containing [video count, view count, last updated].
4989 # last updated or (view count and last updated) may be missing.
4990 playlist_stats = get_first(
bd7e919a 4991 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
4992
6141346d
M
4993 last_updated_unix = self._parse_time_text(
4994 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
4995 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
bd7e919a 4996 info['modified_date'] = strftime_or_none(last_updated_unix, '%Y%m%d')
6141346d 4997
bd7e919a 4998 info['view_count'] = self._get_count(playlist_stats, 1)
4999 if info['view_count'] is None: # 0 is allowed
5000 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5001 if info['view_count'] is None:
5002 info['view_count'] = self._get_count(data, (
5003 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5004 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5005
5006 info['playlist_count'] = self._get_count(playlist_stats, 0)
5007 if info['playlist_count'] is None: # 0 is allowed
5008 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5009
7666b936 5010 if not info.get('channel_id'):
6141346d 5011 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5012 if not owner: # Deprecated
6141346d
M
5013 owner = traverse_obj(
5014 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5015 ('videoOwner', 'videoOwnerRenderer', 'title'))
5016 owner_text = self._get_text(owner)
5017 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5018 info.update({
7666b936 5019 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5020 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5021 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5022 })
6141346d 5023
bd7e919a 5024 info.update({
7666b936 5025 'uploader': info['channel'],
5026 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5027 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5028 })
7666b936 5029
bd7e919a 5030 return info
73c4ac2c 5031
6e634cbe 5032 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5033 first_id = last_id = response = None
2be71994 5034 for page_num in itertools.count(1):
cd7c66cf 5035 videos = list(self._playlist_entries(playlist))
5036 if not videos:
5037 return
2be71994 5038 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5039 if start >= len(videos):
5040 return
24146491 5041 yield from videos[start:]
2be71994 5042 first_id = first_id or videos[0]['id']
5043 last_id = videos[-1]['id']
79360d99 5044 watch_endpoint = try_get(
5045 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5046 headers = self.generate_api_headers(
5047 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5048 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5049 query = {
5050 'playlistId': playlist_id,
5051 'videoId': watch_endpoint.get('videoId') or last_id,
5052 'index': watch_endpoint.get('index') or len(videos),
5053 'params': watch_endpoint.get('params') or 'OAE%3D'
5054 }
5055 response = self._extract_response(
5056 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5057 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5058 check_get_keys='contents'
5059 )
cd7c66cf 5060 playlist = try_get(
79360d99 5061 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5062
ac56cf38 5063 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5064 title = playlist.get('title') or try_get(
14f25df2 5065 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5066 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5067
5068 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5069 playlist_url = urljoin(url, try_get(
5070 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5071 str))
6e634cbe 5072
5073 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5074 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5075 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5076
5077 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5078 return self.url_result(
5079 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5080 video_title=title)
cd7c66cf 5081
8bdd16b4 5082 return self.playlist_result(
6e634cbe 5083 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5084 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5085
47193e02 5086 def _extract_availability(self, data):
5087 """
5088 Gets the availability of a given playlist/tab.
5089 Note: Unless YouTube tells us explicitly, we do not assume it is public
5090 @param data: response
5091 """
6141346d
M
5092 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5093 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5094 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5095
6141346d 5096 badges = self._extract_badges(sidebar_renderer)
47193e02 5097
5098 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5099 privacy_setting_icon = get_first(
5100 (playlist_header_renderer, sidebar_renderer),
5101 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5102 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5103 expected_type=str)
5104
5105 microformats_is_unlisted = traverse_obj(
5106 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5107
c26f9b99 5108 return (
5109 'public' if (
5110 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5111 or player_header_privacy == 'PUBLIC'
5112 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5113 else self._availability(
5114 is_private=(
5115 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5116 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5117 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5118 is_unlisted=(
5119 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5120 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5121 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5122 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5123 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5124 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5125 needs_auth=False))
47193e02 5126
5127 @staticmethod
5128 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5129 sidebar_renderer = try_get(
5130 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5131 for item in sidebar_renderer:
5132 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5133 if renderer:
5134 return renderer
5135
ac56cf38 5136 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5137 """
6141346d 5138 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5139 """
6141346d
M
5140 is_playlist = bool(traverse_obj(
5141 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5142 if not is_playlist:
47193e02 5143 return
11f9be09 5144 headers = self.generate_api_headers(
99e9e001 5145 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5146 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5147 query = {
6141346d
M
5148 'params': 'wgYCCAA=',
5149 'browseId': f'VL{item_id}'
47193e02 5150 }
5151 return self._extract_response(
5152 item_id=item_id, headers=headers, query=query,
fe93e2c4 5153 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5154 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5155
2762dbb1 5156 @functools.cached_property
a25bca9f 5157 def skip_webpage(self):
5158 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5159
ac56cf38 5160 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5161 webpage, data = None, None
5162 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5163 try:
be5c1ae8 5164 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5165 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5166 except ExtractorError as e:
5167 if isinstance(e.cause, network_exceptions):
14f25df2 5168 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 5169 retry.error = e
5170 continue
5171 self._error_or_warning(e, fatal=fatal)
14fdfea9 5172 break
ac56cf38 5173
be5c1ae8 5174 try:
5175 self._extract_and_report_alerts(data)
5176 except ExtractorError as e:
5177 self._error_or_warning(e, fatal=fatal)
5178 break
ac56cf38 5179
be5c1ae8 5180 # Sometimes youtube returns a webpage with incomplete ytInitialData
5181 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5182 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5183 retry.error = ExtractorError('Incomplete yt initial data received')
5184 continue
ac56cf38 5185
cd7c66cf 5186 return webpage, data
5187
a25bca9f 5188 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5189 """Use if failed to extract ytcfg (and data) from initial webpage"""
5190 if not ytcfg and self.is_authenticated:
5191 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5192 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5193 raise ExtractorError(
5194 f'{msg}. If you are not downloading private content, or '
5195 'your cookies are only for the first account and channel,'
5196 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5197 expected=True)
5198 self.report_warning(msg, only_once=True)
5199
ac56cf38 5200 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5201 data = None
a25bca9f 5202 if not self.skip_webpage:
ac56cf38 5203 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5204 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5205 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5206 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5207 if (url != 'https://www.youtube.com/feed/recommended'
5208 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5209 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5210 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5211 if fatal:
5212 raise ExtractorError(msg, expected=True)
5213 self.report_warning(msg, only_once=True)
ac56cf38 5214 if not data:
a25bca9f 5215 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5216 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5217 return data, ytcfg
5218
5219 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5220 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5221 resolve_response = self._extract_response(
5222 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5223 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5224 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5225 for ep_key, ep in endpoints.items():
5226 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5227 if params:
5228 return self._extract_response(
5229 item_id=item_id, query=params, ep=ep, headers=headers,
5230 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5231 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5232 err_note = 'Failed to resolve url (does the playlist exist?)'
5233 if fatal:
5234 raise ExtractorError(err_note, expected=True)
5235 self.report_warning(err_note, item_id)
5236
a6213a49 5237 _SEARCH_PARAMS = None
5238
af5c1c55 5239 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5240 data = {'query': query}
5241 if params is NO_DEFAULT:
5242 params = self._SEARCH_PARAMS
5243 if params:
5244 data['params'] = params
16aa9ea4 5245
5246 content_keys = (
5247 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5248 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5249 # ytmusic search
5250 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5251 ('continuationContents', ),
5252 )
a25bca9f 5253 display_id = f'query "{query}"'
86e5f3ed 5254 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5255 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5256 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5257
a61fd4cf 5258 continuation_list = [None]
a25bca9f 5259 search = None
a6213a49 5260 for page_num in itertools.count(1):
a61fd4cf 5261 data.update(continuation_list[0] or {})
a25bca9f 5262 headers = self.generate_api_headers(
5263 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5264 search = self._extract_response(
a25bca9f 5265 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5266 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5267 slr_contents = traverse_obj(search, *content_keys)
5268 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5269 if not continuation_list[0]:
a6213a49 5270 break
5271
5272
5273class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5274 IE_DESC = 'YouTube Tabs'
5275 _VALID_URL = r'''(?x:
5276 https?://
b032ff0f 5277 (?!consent\.)(?:\w+\.)?
a6213a49 5278 (?:
5279 youtube(?:kids)?\.com|
5280 %(invidious)s
5281 )/
5282 (?:
5283 (?P<channel_type>channel|c|user|browse)/|
5284 (?P<not_channel>
5285 feed/|hashtag/|
5286 (?:playlist|watch)\?.*?\blist=
5287 )|
5288 (?!(?:%(reserved_names)s)\b) # Direct URLs
5289 )
5290 (?P<id>[^/?\#&]+)
5291 )''' % {
5292 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5293 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5294 }
5295 IE_NAME = 'youtube:tab'
5296
5297 _TESTS = [{
5298 'note': 'playlists, multipage',
5299 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5300 'playlist_mincount': 94,
5301 'info_dict': {
5302 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5303 'title': 'Igor Kleiner - Playlists',
a6213a49 5304 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5305 'uploader': 'Igor Kleiner',
7666b936 5306 'uploader_id': '@IgorDataScience',
5307 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5308 'channel': 'Igor Kleiner',
5309 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5310 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5311 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5312 'channel_follower_count': int
a6213a49 5313 },
5314 }, {
5315 'note': 'playlists, multipage, different order',
5316 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5317 'playlist_mincount': 94,
5318 'info_dict': {
5319 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5320 'title': 'Igor Kleiner - Playlists',
a6213a49 5321 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5322 'uploader': 'Igor Kleiner',
7666b936 5323 'uploader_id': '@IgorDataScience',
5324 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5325 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5326 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5327 'channel': 'Igor Kleiner',
5328 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5329 'channel_follower_count': int
a6213a49 5330 },
5331 }, {
5332 'note': 'playlists, series',
5333 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5334 'playlist_mincount': 5,
5335 'info_dict': {
5336 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5337 'title': '3Blue1Brown - Playlists',
5338 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5339 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5340 'channel': '3Blue1Brown',
5341 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5342 'uploader_id': '@3blue1brown',
5343 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5344 'uploader': '3Blue1Brown',
976ae3ea 5345 'tags': ['Mathematics'],
6c73052c 5346 'channel_follower_count': int
a6213a49 5347 },
5348 }, {
5349 'note': 'playlists, singlepage',
5350 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5351 'playlist_mincount': 4,
5352 'info_dict': {
5353 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5354 'title': 'ThirstForScience - Playlists',
5355 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5356 'uploader': 'ThirstForScience',
7666b936 5357 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5358 'uploader_id': '@ThirstForScience',
976ae3ea 5359 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5360 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5361 'tags': 'count:13',
5362 'channel': 'ThirstForScience',
6c73052c 5363 'channel_follower_count': int
a6213a49 5364 }
5365 }, {
5366 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5367 'only_matching': True,
5368 }, {
5369 'note': 'basic, single video playlist',
5370 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5371 'info_dict': {
a6213a49 5372 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5373 'title': 'youtube-dl public playlist',
976ae3ea 5374 'description': '',
5375 'tags': [],
5376 'view_count': int,
5377 'modified_date': '20201130',
5378 'channel': 'Sergey M.',
5379 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5380 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5381 'availability': 'public',
7666b936 5382 'uploader': 'Sergey M.',
5383 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5384 'uploader_id': '@sergeym.6173',
a6213a49 5385 },
5386 'playlist_count': 1,
5387 }, {
5388 'note': 'empty playlist',
5389 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5390 'info_dict': {
a6213a49 5391 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5392 'title': 'youtube-dl empty playlist',
976ae3ea 5393 'tags': [],
5394 'channel': 'Sergey M.',
5395 'description': '',
5396 'modified_date': '20160902',
5397 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5398 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5399 'availability': 'public',
7666b936 5400 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5401 'uploader_id': '@sergeym.6173',
5402 'uploader': 'Sergey M.',
a6213a49 5403 },
5404 'playlist_count': 0,
5405 }, {
5406 'note': 'Home tab',
5407 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5408 'info_dict': {
5409 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5410 'title': 'lex will - Home',
5411 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5412 'uploader': 'lex will',
7666b936 5413 'uploader_id': '@lexwill718',
976ae3ea 5414 'channel': 'lex will',
5415 'tags': ['bible', 'history', 'prophesy'],
7666b936 5416 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5417 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5418 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5419 'channel_follower_count': int
a6213a49 5420 },
5421 'playlist_mincount': 2,
5422 }, {
5423 'note': 'Videos tab',
5424 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5425 'info_dict': {
5426 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5427 'title': 'lex will - Videos',
5428 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5429 'uploader': 'lex will',
7666b936 5430 'uploader_id': '@lexwill718',
976ae3ea 5431 'tags': ['bible', 'history', 'prophesy'],
5432 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5433 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5434 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5435 'channel': 'lex will',
6c73052c 5436 'channel_follower_count': int
a6213a49 5437 },
5438 'playlist_mincount': 975,
5439 }, {
5440 'note': 'Videos tab, sorted by popular',
5441 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5442 'info_dict': {
5443 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5444 'title': 'lex will - Videos',
5445 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5446 'uploader': 'lex will',
7666b936 5447 'uploader_id': '@lexwill718',
976ae3ea 5448 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5449 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5450 'channel': 'lex will',
5451 'tags': ['bible', 'history', 'prophesy'],
5452 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5453 'channel_follower_count': int
a6213a49 5454 },
5455 'playlist_mincount': 199,
5456 }, {
5457 'note': 'Playlists tab',
5458 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5459 'info_dict': {
5460 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5461 'title': 'lex will - Playlists',
5462 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5463 'uploader': 'lex will',
7666b936 5464 'uploader_id': '@lexwill718',
5465 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5466 'channel': 'lex will',
5467 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5468 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5469 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5470 'channel_follower_count': int
a6213a49 5471 },
5472 'playlist_mincount': 17,
5473 }, {
5474 'note': 'Community tab',
5475 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5476 'info_dict': {
5477 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5478 'title': 'lex will - Community',
5479 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5480 'channel': 'lex will',
5481 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5482 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5483 'tags': ['bible', 'history', 'prophesy'],
7666b936 5484 'channel_follower_count': int,
5485 'uploader_url': 'https://www.youtube.com/@lexwill718',
5486 'uploader_id': '@lexwill718',
5487 'uploader': 'lex will',
a6213a49 5488 },
5489 'playlist_mincount': 18,
5490 }, {
5491 'note': 'Channels tab',
5492 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5493 'info_dict': {
5494 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5495 'title': 'lex will - Channels',
5496 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5497 'channel': 'lex will',
5498 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5499 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5500 'tags': ['bible', 'history', 'prophesy'],
7666b936 5501 'channel_follower_count': int,
5502 'uploader_url': 'https://www.youtube.com/@lexwill718',
5503 'uploader_id': '@lexwill718',
5504 'uploader': 'lex will',
a6213a49 5505 },
5506 'playlist_mincount': 12,
5507 }, {
5508 'note': 'Search tab',
5509 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5510 'playlist_mincount': 40,
5511 'info_dict': {
5512 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5513 'title': '3Blue1Brown - Search - linear algebra',
5514 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5515 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5516 'tags': ['Mathematics'],
5517 'channel': '3Blue1Brown',
5518 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5519 'channel_follower_count': int,
5520 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5521 'uploader_id': '@3blue1brown',
5522 'uploader': '3Blue1Brown',
a6213a49 5523 },
5524 }, {
5525 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5526 'only_matching': True,
5527 }, {
5528 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5529 'only_matching': True,
5530 }, {
5531 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5532 'only_matching': True,
5533 }, {
5534 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5535 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5536 'info_dict': {
5537 'title': '29C3: Not my department',
5538 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5539 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5540 'tags': [],
976ae3ea 5541 'view_count': int,
5542 'modified_date': '20150605',
5543 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5544 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5545 'channel': 'Christiaan008',
c26f9b99 5546 'availability': 'public',
7666b936 5547 'uploader_id': '@ChRiStIaAn008',
5548 'uploader': 'Christiaan008',
5549 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5550 },
5551 'playlist_count': 96,
5552 }, {
5553 'note': 'Large playlist',
5554 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5555 'info_dict': {
5556 'title': 'Uploads from Cauchemar',
5557 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5558 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5559 'tags': [],
5560 'modified_date': r're:\d{8}',
5561 'channel': 'Cauchemar',
976ae3ea 5562 'view_count': int,
5563 'description': '',
5564 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5565 'availability': 'public',
7666b936 5566 'uploader_id': '@Cauchemar89',
5567 'uploader': 'Cauchemar',
5568 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5569 },
5570 'playlist_mincount': 1123,
976ae3ea 5571 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5572 }, {
5573 'note': 'even larger playlist, 8832 videos',
5574 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5575 'only_matching': True,
5576 }, {
5577 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5578 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5579 'info_dict': {
5580 'title': 'Uploads from Interstellar Movie',
5581 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5582 'tags': [],
5583 'view_count': int,
5584 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5585 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5586 'channel': 'Interstellar Movie',
5587 'description': '',
5588 'modified_date': r're:\d{8}',
c26f9b99 5589 'availability': 'public',
7666b936 5590 'uploader_id': '@InterstellarMovie',
5591 'uploader': 'Interstellar Movie',
5592 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5593 },
5594 'playlist_mincount': 21,
5595 }, {
5596 'note': 'Playlist with "show unavailable videos" button',
5597 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5598 'info_dict': {
5599 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5600 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5601 'view_count': int,
5602 'channel': 'Phim Siêu Nhân Nhật Bản',
5603 'tags': [],
976ae3ea 5604 'description': '',
5605 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5606 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5607 'modified_date': r're:\d{8}',
c26f9b99 5608 'availability': 'public',
7666b936 5609 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5610 'uploader_id': '@phimsieunhannhatban',
5611 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5612 },
5613 'playlist_mincount': 200,
976ae3ea 5614 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5615 }, {
5616 'note': 'Playlist with unavailable videos in page 7',
5617 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5618 'info_dict': {
5619 'title': 'Uploads from BlankTV',
5620 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5621 'channel': 'BlankTV',
7666b936 5622 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5623 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5624 'view_count': int,
5625 'tags': [],
976ae3ea 5626 'modified_date': r're:\d{8}',
5627 'description': '',
c26f9b99 5628 'availability': 'public',
7666b936 5629 'uploader_id': '@blanktv',
5630 'uploader': 'BlankTV',
5631 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5632 },
5633 'playlist_mincount': 1000,
976ae3ea 5634 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5635 }, {
5636 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5637 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5638 'info_dict': {
5639 'title': 'Data Analysis with Dr Mike Pound',
5640 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5641 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5642 'tags': [],
5643 'view_count': int,
5644 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5645 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5646 'channel': 'Computerphile',
c26f9b99 5647 'availability': 'public',
6141346d 5648 'modified_date': '20190712',
7666b936 5649 'uploader_id': '@Computerphile',
5650 'uploader': 'Computerphile',
5651 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5652 },
5653 'playlist_mincount': 11,
5654 }, {
5655 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5656 'only_matching': True,
5657 }, {
5658 'note': 'Playlist URL that does not actually serve a playlist',
5659 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5660 'info_dict': {
5661 'id': 'FqZTN594JQw',
5662 'ext': 'webm',
5663 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5664 'upload_date': '20150526',
5665 'license': 'Standard YouTube License',
5666 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5667 'categories': ['People & Blogs'],
5668 'tags': list,
5669 'view_count': int,
5670 'like_count': int,
a6213a49 5671 },
5672 'params': {
5673 'skip_download': True,
5674 },
5675 'skip': 'This video is not available.',
5676 'add_ie': [YoutubeIE.ie_key()],
5677 }, {
5678 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5679 'only_matching': True,
5680 }, {
5681 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5682 'only_matching': True,
5683 }, {
5684 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5685 'info_dict': {
7666b936 5686 'id': 'AlTsmyW4auo', # This will keep changing
a6213a49 5687 'ext': 'mp4',
976ae3ea 5688 'title': str,
a6213a49 5689 'upload_date': r're:\d{8}',
976ae3ea 5690 'description': str,
a6213a49 5691 'categories': ['News & Politics'],
5692 'tags': list,
5693 'like_count': int,
86973308 5694 'release_timestamp': int,
976ae3ea 5695 'channel': 'Sky News',
5696 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5697 'age_limit': 0,
5698 'view_count': int,
86973308 5699 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5700 'playable_in_embed': True,
86973308 5701 'release_date': r're:\d+',
976ae3ea 5702 'availability': 'public',
5703 'live_status': 'is_live',
5704 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5705 'channel_follower_count': int,
5706 'concurrent_view_count': int,
7666b936 5707 'uploader_url': 'https://www.youtube.com/@SkyNews',
5708 'uploader_id': '@SkyNews',
5709 'uploader': 'Sky News',
a6213a49 5710 },
5711 'params': {
5712 'skip_download': True,
5713 },
976ae3ea 5714 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5715 }, {
5716 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5717 'info_dict': {
5718 'id': 'a48o2S1cPoo',
5719 'ext': 'mp4',
5720 'title': 'The Young Turks - Live Main Show',
a6213a49 5721 'upload_date': '20150715',
5722 'license': 'Standard YouTube License',
5723 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5724 'categories': ['News & Politics'],
5725 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5726 'like_count': int,
a6213a49 5727 },
5728 'params': {
5729 'skip_download': True,
5730 },
5731 'only_matching': True,
5732 }, {
5733 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5734 'only_matching': True,
5735 }, {
5736 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5737 'only_matching': True,
5738 }, {
5739 'note': 'A channel that is not live. Should raise error',
5740 'url': 'https://www.youtube.com/user/numberphile/live',
5741 'only_matching': True,
5742 }, {
5743 'url': 'https://www.youtube.com/feed/trending',
5744 'only_matching': True,
5745 }, {
5746 'url': 'https://www.youtube.com/feed/library',
5747 'only_matching': True,
5748 }, {
5749 'url': 'https://www.youtube.com/feed/history',
5750 'only_matching': True,
5751 }, {
5752 'url': 'https://www.youtube.com/feed/subscriptions',
5753 'only_matching': True,
5754 }, {
5755 'url': 'https://www.youtube.com/feed/watch_later',
5756 'only_matching': True,
5757 }, {
5758 'note': 'Recommended - redirects to home page.',
5759 'url': 'https://www.youtube.com/feed/recommended',
5760 'only_matching': True,
5761 }, {
5762 'note': 'inline playlist with not always working continuations',
5763 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5764 'only_matching': True,
5765 }, {
5766 'url': 'https://www.youtube.com/course',
5767 'only_matching': True,
5768 }, {
5769 'url': 'https://www.youtube.com/zsecurity',
5770 'only_matching': True,
5771 }, {
5772 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5773 'only_matching': True,
5774 }, {
5775 'url': 'https://www.youtube.com/TheYoungTurks/live',
5776 'only_matching': True,
5777 }, {
5778 'url': 'https://www.youtube.com/hashtag/cctv9',
5779 'info_dict': {
5780 'id': 'cctv9',
5781 'title': '#cctv9',
976ae3ea 5782 'tags': [],
a6213a49 5783 },
4dc23a80 5784 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5785 }, {
5786 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5787 'only_matching': True,
5788 }, {
5789 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5790 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5791 'only_matching': True
5792 }, {
5793 'note': '/browse/ should redirect to /channel/',
5794 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5795 'only_matching': True
5796 }, {
5797 'note': 'VLPL, should redirect to playlist?list=PL...',
5798 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5799 'info_dict': {
5800 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5801 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5802 'title': 'NCS : All Releases 💿',
7666b936 5803 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5804 'modified_date': r're:\d{8}',
5805 'view_count': int,
5806 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5807 'tags': [],
5808 'channel': 'NoCopyrightSounds',
c26f9b99 5809 'availability': 'public',
7666b936 5810 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5811 'uploader': 'NoCopyrightSounds',
5812 'uploader_id': '@NoCopyrightSounds',
a6213a49 5813 },
5814 'playlist_mincount': 166,
7666b936 5815 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5816 }, {
7666b936 5817 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5818 'note': 'Topic, should redirect to playlist?list=UU...',
5819 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5820 'info_dict': {
5821 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5822 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5823 'tags': [],
5824 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5825 'channel': 'Royalty Free Music - Topic',
5826 'view_count': int,
5827 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5828 'modified_date': r're:\d{8}',
976ae3ea 5829 'description': '',
c26f9b99 5830 'availability': 'public',
7666b936 5831 'uploader': 'Royalty Free Music - Topic',
a6213a49 5832 },
a6213a49 5833 'playlist_mincount': 101,
7666b936 5834 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5835 }, {
86973308
M
5836 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5837 # Treat as a general feed
a6213a49 5838 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5839 'info_dict': {
5840 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5841 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5842 'tags': [],
a6213a49 5843 },
a6213a49 5844 'playlist_mincount': 9,
5845 }, {
5846 'note': 'Youtube music Album',
5847 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5848 'info_dict': {
5849 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5850 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5851 'tags': [],
5852 'view_count': int,
5853 'description': '',
5854 'availability': 'unlisted',
5855 'modified_date': r're:\d{8}',
a6213a49 5856 },
5857 'playlist_count': 50,
7666b936 5858 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5859 }, {
5860 'note': 'unlisted single video playlist',
5861 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5862 'info_dict': {
a6213a49 5863 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5864 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5865 'availability': 'unlisted',
5866 'tags': [],
12a1b225 5867 'modified_date': '20220418',
976ae3ea 5868 'channel': 'colethedj',
5869 'view_count': int,
5870 'description': '',
976ae3ea 5871 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5872 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 5873 'uploader_url': 'https://www.youtube.com/@colethedj1894',
5874 'uploader_id': '@colethedj1894',
5875 'uploader': 'colethedj',
a6213a49 5876 },
93e12ed7 5877 'playlist': [{
5878 'info_dict': {
5879 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
5880 'id': 'BaW_jenozKc',
5881 '_type': 'url',
5882 'ie_key': 'Youtube',
5883 'duration': 10,
5884 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
5885 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
5886 'view_count': int,
5887 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
5888 'channel': 'Philipp Hagemeister',
5889 'uploader_id': '@PhilippHagemeister',
5890 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
5891 'uploader': 'Philipp Hagemeister',
5892 }
5893 }],
a6213a49 5894 'playlist_count': 1,
93e12ed7 5895 'params': {'extract_flat': True},
a6213a49 5896 }, {
5897 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5898 'url': 'https://www.youtube.com/feed/recommended',
5899 'info_dict': {
5900 'id': 'recommended',
5901 'title': 'recommended',
6c73052c 5902 'tags': [],
a6213a49 5903 },
5904 'playlist_mincount': 50,
5905 'params': {
5906 'skip_download': True,
5907 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5908 },
5909 }, {
5910 'note': 'API Fallback: /videos tab, sorted by oldest first',
5911 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5912 'info_dict': {
5913 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5914 'title': 'Cody\'sLab - Videos',
5915 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 5916 'channel': 'Cody\'sLab',
5917 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5918 'tags': [],
5919 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5920 'channel_follower_count': int
a6213a49 5921 },
5922 'playlist_mincount': 650,
5923 'params': {
5924 'skip_download': True,
5925 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5926 },
86973308 5927 'skip': 'Query for sorting no longer works',
a6213a49 5928 }, {
5929 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5930 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5931 'info_dict': {
5932 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5933 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5934 'modified_date': r're:\d{8}',
5935 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5936 'description': '',
5937 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5938 'tags': [],
5939 'channel': 'Royalty Free Music - Topic',
5940 'view_count': int,
c26f9b99 5941 'availability': 'public',
7666b936 5942 'uploader': 'Royalty Free Music - Topic',
a6213a49 5943 },
a6213a49 5944 'playlist_mincount': 101,
5945 'params': {
5946 'skip_download': True,
5947 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5948 },
7666b936 5949 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 5950 }, {
5951 'note': 'non-standard redirect to regional channel',
5952 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5953 'only_matching': True
61d3665d 5954 }, {
5955 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5956 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5957 'info_dict': {
5958 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5959 'modified_date': '20220407',
5960 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5961 'tags': [],
61d3665d 5962 'availability': 'unlisted',
5963 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5964 'channel': 'pukkandan',
5965 'description': 'Test for collaborative playlist',
5966 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5967 'view_count': int,
7666b936 5968 'uploader_url': 'https://www.youtube.com/@pukkandan',
5969 'uploader_id': '@pukkandan',
5970 'uploader': 'pukkandan',
61d3665d 5971 },
5972 'playlist_mincount': 2
c26f9b99 5973 }, {
5974 'note': 'translated tab name',
5975 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5976 'info_dict': {
5977 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5978 'tags': [],
c26f9b99 5979 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 5980 'description': 'test description',
c26f9b99 5981 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 5982 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5983 'channel': 'cole-dlp-test-acc',
7666b936 5984 'uploader_url': 'https://www.youtube.com/@coletdjnz',
5985 'uploader_id': '@coletdjnz',
5986 'uploader': 'cole-dlp-test-acc',
c26f9b99 5987 },
5988 'playlist_mincount': 1,
5989 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
5990 'expected_warnings': ['Preferring "ja"'],
5991 }, {
5992 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5993 'note': 'preferred lang set with playlist with translated video titles',
5994 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5995 'info_dict': {
5996 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5997 'tags': [],
5998 'view_count': int,
5999 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6000 'channel': 'cole-dlp-test-acc',
6001 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6002 'description': 'test',
c26f9b99 6003 'title': 'dlp test playlist',
6004 'availability': 'public',
7666b936 6005 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6006 'uploader_id': '@coletdjnz',
6007 'uploader': 'cole-dlp-test-acc',
c26f9b99 6008 },
6009 'playlist_mincount': 1,
6010 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6011 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6012 }, {
6013 # shorts audio pivot for 2GtVksBMYFM.
6014 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6015 'info_dict': {
6016 'id': 'sfv_audio_pivot',
6017 'title': 'sfv_audio_pivot',
6018 'tags': [],
6019 },
6020 'playlist_mincount': 50,
6021
86973308
M
6022 }, {
6023 # Channel with a real live tab (not to be mistaken with streams tab)
6024 # Do not treat like it should redirect to live stream
6025 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6026 'info_dict': {
6027 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6028 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6029 'tags': [],
6030 },
6031 'playlist_mincount': 20,
6032 }, {
6033 # Tab name is not the same as tab id
6034 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6035 'info_dict': {
6036 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6037 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6038 'tags': [],
6039 },
6040 'playlist_mincount': 8,
6041 }, {
6042 # Home tab id is literally home. Not to get mistaken with featured
6043 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6044 'info_dict': {
6045 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6046 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6047 'tags': [],
6048 },
6049 'playlist_mincount': 8,
6050 }, {
6051 # Should get three playlists for videos, shorts and streams tabs
6052 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6053 'info_dict': {
6054 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6055 'title': 'Polka Ch. 尾丸ポルカ',
6056 'channel_follower_count': int,
6057 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6058 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
7666b936 6059 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
bd7e919a 6060 'channel': 'Polka Ch. 尾丸ポルカ',
6061 'tags': 'count:35',
7666b936 6062 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6063 'uploader': 'Polka Ch. 尾丸ポルカ',
6064 'uploader_id': '@OmaruPolka',
86973308
M
6065 },
6066 'playlist_count': 3,
6067 }, {
6068 # Shorts tab with channel with handle
7666b936 6069 # TODO: fix channel description
86973308
M
6070 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6071 'info_dict': {
6072 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6073 'title': 'Not Just Bikes - Shorts',
6074 'tags': 'count:12',
86973308 6075 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
7666b936 6076 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
86973308 6077 'channel_follower_count': int,
86973308 6078 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6079 'channel': 'Not Just Bikes',
7666b936 6080 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6081 'uploader': 'Not Just Bikes',
6082 'uploader_id': '@NotJustBikes',
86973308
M
6083 },
6084 'playlist_mincount': 10,
6085 }, {
6086 # Streams tab
6087 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6088 'info_dict': {
6089 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6090 'title': '中村悠一 - Live',
6091 'tags': 'count:7',
6092 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6093 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6094 'channel': '中村悠一',
86973308 6095 'channel_follower_count': int,
86973308 6096 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6097 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6098 'uploader_id': '@Yuichi-Nakamura',
6099 'uploader': '中村悠一',
86973308
M
6100 },
6101 'playlist_mincount': 60,
6102 }, {
6103 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6104 # See test_youtube_lists
6105 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6106 'only_matching': True,
6107 }, {
6108 # No uploads and no UCID given. Should fail with no uploads error
6109 # See test_youtube_lists
6110 'url': 'https://www.youtube.com/news',
6111 'only_matching': True
6112 }, {
6113 # No videos tab but has a shorts tab
6114 'url': 'https://www.youtube.com/c/TKFShorts',
6115 'info_dict': {
6116 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6117 'title': 'Shorts Break - Shorts',
7666b936 6118 'tags': 'count:48',
86973308
M
6119 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6120 'channel': 'Shorts Break',
7666b936 6121 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6122 'channel_follower_count': int,
86973308 6123 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6124 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6125 'uploader': 'Shorts Break',
6126 'uploader_id': '@ShortsBreak_Official',
86973308
M
6127 },
6128 'playlist_mincount': 30,
6129 }, {
6130 # Trending Now Tab. tab id is empty
6131 'url': 'https://www.youtube.com/feed/trending',
6132 'info_dict': {
6133 'id': 'trending',
6134 'title': 'trending - Now',
6135 'tags': [],
6136 },
6137 'playlist_mincount': 30,
6138 }, {
6139 # Trending Gaming Tab. tab id is empty
6140 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6141 'info_dict': {
6142 'id': 'trending',
6143 'title': 'trending - Gaming',
6144 'tags': [],
6145 },
6146 'playlist_mincount': 30,
4dc23a80
M
6147 }, {
6148 # Shorts url result in shorts tab
7666b936 6149 # TODO: Fix channel id extraction
4dc23a80
M
6150 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6151 'info_dict': {
6152 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6153 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6154 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6155 'description': 'test description',
6156 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6157 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6158 'tags': [],
7666b936 6159 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6160 'uploader_id': '@coletdjnz',
4dc23a80 6161 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6162 },
6163 'playlist': [{
6164 'info_dict': {
7666b936 6165 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6166 '_type': 'url',
6167 'ie_key': 'Youtube',
6168 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6169 'id': 'sSM9J5YH_60',
4dc23a80 6170 'title': 'SHORT short',
4dc23a80
M
6171 'view_count': int,
6172 'thumbnails': list,
6173 }
6174 }],
6175 'params': {'extract_flat': True},
6176 }, {
6177 # Live video status should be extracted
6178 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6179 'info_dict': {
6180 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6181 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6182 'tags': []
6183 },
6184 'playlist': [{
6185 'info_dict': {
6186 '_type': 'url',
6187 'ie_key': 'Youtube',
6188 'url': 'startswith:https://www.youtube.com/watch?v=',
6189 'id': str,
6190 'title': str,
6191 'live_status': 'is_live',
6192 'channel_id': str,
6193 'channel_url': str,
6194 'concurrent_view_count': int,
6195 'channel': str,
93e12ed7 6196 'uploader': str,
6197 'uploader_url': str,
6198 'uploader_id': str
4dc23a80
M
6199 }
6200 }],
c7335551 6201 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6202 'playlist_mincount': 1
c7335551
M
6203 }, {
6204 # Channel renderer metadata. Contains number of videos on the channel
6205 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6206 'info_dict': {
6207 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6208 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6209 'channel': 'cole-dlp-test-acc',
6210 'description': 'test description',
6211 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6212 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6213 'tags': [],
7666b936 6214 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6215 'uploader_id': '@coletdjnz',
c7335551 6216 'uploader': 'cole-dlp-test-acc',
c7335551
M
6217 },
6218 'playlist': [{
6219 'info_dict': {
6220 '_type': 'url',
6221 'ie_key': 'YoutubeTab',
6222 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6223 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6224 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6225 'title': 'PewDiePie',
6226 'channel': 'PewDiePie',
6227 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6228 'thumbnails': list,
6229 'channel_follower_count': int,
7666b936 6230 'playlist_count': int,
6231 'uploader': 'PewDiePie',
6232 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6233 'uploader_id': '@PewDiePie',
c7335551
M
6234 }
6235 }],
6236 'params': {'extract_flat': True},
31e18355 6237 }, {
6238 'url': 'https://www.youtube.com/@3blue1brown/about',
6239 'info_dict': {
6240 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6241 'tags': ['Mathematics'],
6242 'title': '3Blue1Brown - About',
31e18355 6243 'channel_follower_count': int,
6244 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6245 'channel': '3Blue1Brown',
31e18355 6246 'view_count': int,
6247 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6248 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
7666b936 6249 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6250 'uploader_id': '@3blue1brown',
6251 'uploader': '3Blue1Brown',
31e18355 6252 },
6253 'playlist_count': 0,
447afb9e 6254 }, {
6255 # Podcasts tab, with rich entry playlistRenderers
6256 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6257 'info_dict': {
6258 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6259 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6260 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6261 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6262 'title': '99 Percent Invisible - Podcasts',
6263 'uploader': '99 Percent Invisible',
6264 'channel_follower_count': int,
6265 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6266 'tags': [],
6267 'channel': '99 Percent Invisible',
6268 'uploader_id': '@99percentinvisiblepodcast',
6269 },
6270 'playlist_count': 1,
6271 }, {
6272 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6273 'url': 'https://www.youtube.com/@AHimitsu/releases',
6274 'info_dict': {
6275 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6276 'channel': 'A Himitsu',
6277 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6278 'title': 'A Himitsu - Releases',
6279 'uploader_id': '@AHimitsu',
6280 'uploader': 'A Himitsu',
6281 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6282 'tags': 'count:16',
6283 'description': 'I make music',
6284 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6285 'channel_follower_count': int,
6286 },
6287 'playlist_mincount': 10,
a6213a49 6288 }]
6289
6290 @classmethod
6291 def suitable(cls, url):
86e5f3ed 6292 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6293
86973308
M
6294 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6295
6296 def _get_url_mobj(self, url):
6297 mobj = self._URL_RE.match(url).groupdict()
6298 mobj.update((k, '') for k, v in mobj.items() if v is None)
6299 return mobj
6300
6301 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6302 tab_name = (tab.get('title') or '').lower()
6303 tab_url = urljoin(base_url, traverse_obj(
6304 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6305
bd7e919a 6306 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6307 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6308 if tab_id:
bd7e919a 6309 return {
6310 'TAB_ID_SPONSORSHIPS': 'membership',
6311 }.get(tab_id, tab_id), tab_name
86973308
M
6312
6313 # Fallback to tab name if we cannot get the tab id.
6314 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6315 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6316 if tab_name:
6317 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6318 return {
6319 'home': 'featured',
6320 'live': 'streams',
6321 }.get(tab_name, tab_name), tab_name
6322
6323 def _has_tab(self, tabs, tab_id):
6324 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6325
182bda88 6326 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6327 def _real_extract(self, url, smuggled_data):
cd7c66cf 6328 item_id = self._match_id(url)
14f25df2 6329 url = urllib.parse.urlunparse(
6330 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6331 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6332
86973308
M
6333 mobj = self._get_url_mobj(url)
6334 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6335 if is_channel and smuggled_data.get('is_music_url'):
6336 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6337 return self.url_result(
6338 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6339 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6340 mdata = self._extract_tab_endpoint(
6341 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6342 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6343 get_all=False, expected_type=str)
6344 if not murl:
6345 raise ExtractorError('Failed to resolve album to playlist')
6346 return self.url_result(murl, YoutubeTabIE)
6347 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6348 return self.url_result(
6349 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6350
6351 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6352 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6353 url = f'{pre}/videos{post}'
5b28cef7 6354 if smuggled_data.get('is_music_url'):
6355 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6356
6357 # Handle both video/playlist URLs
201c1459 6358 qs = parse_qs(url)
bd7e919a 6359 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6360 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6361 if not playlist_id:
fe03a6cd 6362 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6363 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6364 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6365 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6366 return self.url_result(
6367 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6368
86973308
M
6369 if not self._yes_playlist(playlist_id, video_id):
6370 return self.url_result(
6371 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6372
bd7e919a 6373 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6374
7c219ea6 6375 # YouTube may provide a non-standard redirect to the regional channel
6376 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6377 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6378 redirect_url = traverse_obj(
6379 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6380 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6381 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6382 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6383 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6384
bd7e919a 6385 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6386 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6387 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6388 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6389 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6390
6391 if not original_tab_id and selected_tab_name:
bd7e919a 6392 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6393 'To download only the videos in a specific tab, pass the tab\'s URL')
6394 if self._has_tab(tabs, 'streams'):
bd7e919a 6395 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6396 if self._has_tab(tabs, 'shorts'):
bd7e919a 6397 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6398 # XXX: Members-only tab should also be extracted
6399
bd7e919a 6400 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6401 # Channel does not have streams, shorts or videos tabs
6402 if item_id[:2] != 'UC':
6403 raise ExtractorError('This channel has no uploads', expected=True)
6404
6405 # Topic channels don't have /videos. Use the equivalent playlist instead
6406 pl_id = f'UU{item_id[2:]}'
6407 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6408 try:
6409 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6410 except ExtractorError:
6411 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6412 else:
86973308
M
6413 item_id, url = pl_id, pl_url
6414 self.to_screen(
6415 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6416
bd7e919a 6417 elif extra_tabs and selected_tab_id != 'videos':
86973308 6418 # When there are shorts/live tabs but not videos tab
bd7e919a 6419 url, data = f'{pre}{post}', None
86973308
M
6420
6421 elif (original_tab_id or 'videos') != selected_tab_id:
6422 if original_tab_id == 'live':
6423 # Live tab should have redirected to the video
6424 # Except in the case the channel has an actual live tab
6425 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6426 raise UserNotLive(video_id=item_id)
86973308
M
6427 elif selected_tab_name:
6428 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6429
6430 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6431 url = f'{pre}{post}'
18db7548 6432
358de58c 6433 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6434 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6435 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6436 self._extract_and_report_alerts(data, only_once=True)
86973308 6437
bd7e919a 6438 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6439 if tabs:
bd7e919a 6440 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6441 entries[0].update({
86973308
M
6442 'extractor_key': YoutubeTabIE.ie_key(),
6443 'extractor': YoutubeTabIE.IE_NAME,
6444 'webpage_url': url,
6445 })
bd7e919a 6446 if self.get_param('playlist_items') == '0':
6447 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6448 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6449 entries.extend(map(self._real_extract, extra_tabs))
6450
6451 if len(entries) == 1:
6452 return entries[0]
6453 elif entries:
6454 metadata = self._extract_metadata_from_tabs(item_id, data)
6455 uploads_url = 'the Uploads (UU) playlist URL'
6456 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6457 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6458 self.to_screen(
6459 'Downloading as multiple playlists, separated by tabs. '
6460 f'To download as a single playlist instead, pass {uploads_url}')
6461 return self.playlist_result(entries, item_id, **metadata)
6462
6463 # Inline playlist
37e57a9f 6464 playlist = traverse_obj(
6465 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6466 if playlist:
ac56cf38 6467 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6468
37e57a9f 6469 video_id = traverse_obj(
6470 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6471 if video_id:
bd7e919a 6472 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6473 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6474 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6475
8bdd16b4 6476 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6477
c5e8d7af 6478
8bdd16b4 6479class YoutubePlaylistIE(InfoExtractor):
96565c7e 6480 IE_DESC = 'YouTube playlists'
8bdd16b4 6481 _VALID_URL = r'''(?x)(?:
6482 (?:https?://)?
6483 (?:\w+\.)?
6484 (?:
6485 (?:
6486 youtube(?:kids)?\.com|
d9190e44 6487 %(invidious)s
8bdd16b4 6488 )
6489 /.*?\?.*?\blist=
6490 )?
6491 (?P<id>%(playlist_id)s)
d9190e44
RH
6492 )''' % {
6493 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6494 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6495 }
8bdd16b4 6496 IE_NAME = 'youtube:playlist'
cdc628a4 6497 _TESTS = [{
8bdd16b4 6498 'note': 'issue #673',
6499 'url': 'PLBB231211A4F62143',
cdc628a4 6500 'info_dict': {
8bdd16b4 6501 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6502 'id': 'PLBB231211A4F62143',
976ae3ea 6503 'uploader': 'Wickman',
7666b936 6504 'uploader_id': '@WickmanVT',
11f9be09 6505 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6506 'view_count': int,
7666b936 6507 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6508 'modified_date': r're:\d{8}',
6509 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6510 'channel': 'Wickman',
6511 'tags': [],
7666b936 6512 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6513 'availability': 'public',
8bdd16b4 6514 },
6515 'playlist_mincount': 29,
6516 }, {
6517 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6518 'info_dict': {
6519 'title': 'YDL_safe_search',
6520 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6521 },
6522 'playlist_count': 2,
6523 'skip': 'This playlist is private',
9558dcec 6524 }, {
8bdd16b4 6525 'note': 'embedded',
6526 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6527 'playlist_count': 4,
9558dcec 6528 'info_dict': {
8bdd16b4 6529 'title': 'JODA15',
6530 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6531 'uploader': 'milan',
7666b936 6532 'uploader_id': '@milan5503',
976ae3ea 6533 'description': '',
6534 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6535 'tags': [],
6536 'modified_date': '20140919',
6537 'view_count': int,
6538 'channel': 'milan',
6539 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6540 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6541 'availability': 'public',
976ae3ea 6542 },
86973308 6543 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6544 }, {
8bdd16b4 6545 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6546 'playlist_mincount': 455,
8bdd16b4 6547 'info_dict': {
6548 'title': '2018 Chinese New Singles (11/6 updated)',
6549 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6550 'uploader': 'LBK',
7666b936 6551 'uploader_id': '@music_king',
11f9be09 6552 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6553 'channel': 'LBK',
6554 'view_count': int,
7666b936 6555 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6556 'tags': [],
7666b936 6557 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6558 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6559 'modified_date': r're:\d{8}',
c26f9b99 6560 'availability': 'public',
976ae3ea 6561 },
6562 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6563 }, {
29f7c58a 6564 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6565 'only_matching': True,
6566 }, {
6567 # music album playlist
6568 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6569 'only_matching': True,
6570 }]
6571
6572 @classmethod
6573 def suitable(cls, url):
201c1459 6574 if YoutubeTabIE.suitable(url):
6575 return False
49a57e70 6576 from ..utils import parse_qs
201c1459 6577 qs = parse_qs(url)
6578 if qs.get('v', [None])[0]:
6579 return False
86e5f3ed 6580 return super().suitable(url)
29f7c58a 6581
6582 def _real_extract(self, url):
6583 playlist_id = self._match_id(url)
46953e7e 6584 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6585 url = update_url_query(
6586 'https://www.youtube.com/playlist',
6587 parse_qs(url) or {'list': playlist_id})
6588 if is_music_url:
6589 url = smuggle_url(url, {'is_music_url': True})
6590 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6591
6592
6593class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6594 IE_DESC = 'youtu.be'
29f7c58a 6595 _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}
6596 _TESTS = [{
8bdd16b4 6597 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6598 'info_dict': {
6599 'id': 'yeWKywCrFtk',
6600 'ext': 'mp4',
6601 'title': 'Small Scale Baler and Braiding Rugs',
6602 'uploader': 'Backus-Page House Museum',
7666b936 6603 'uploader_id': '@backuspagemuseum',
6604 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6605 'upload_date': '20161008',
6606 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6607 'categories': ['Nonprofits & Activism'],
6608 'tags': list,
6609 'like_count': int,
976ae3ea 6610 'age_limit': 0,
6611 'playable_in_embed': True,
7666b936 6612 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6613 'channel': 'Backus-Page House Museum',
6614 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6615 'live_status': 'not_live',
6616 'view_count': int,
6617 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6618 'availability': 'public',
6619 'duration': 59,
12a1b225
A
6620 'comment_count': int,
6621 'channel_follower_count': int
8bdd16b4 6622 },
6623 'params': {
6624 'noplaylist': True,
6625 'skip_download': True,
6626 },
39e7107d 6627 }, {
8bdd16b4 6628 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6629 'only_matching': True,
cdc628a4
PH
6630 }]
6631
8bdd16b4 6632 def _real_extract(self, url):
5ad28e7f 6633 mobj = self._match_valid_url(url)
29f7c58a 6634 video_id = mobj.group('id')
6635 playlist_id = mobj.group('playlist_id')
8bdd16b4 6636 return self.url_result(
29f7c58a 6637 update_url_query('https://www.youtube.com/watch', {
6638 'v': video_id,
6639 'list': playlist_id,
6640 'feature': 'youtu.be',
6641 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6642
6643
b6ce9bb0 6644class YoutubeLivestreamEmbedIE(InfoExtractor):
6645 IE_DESC = 'YouTube livestream embeds'
6646 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6647 _TESTS = [{
6648 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6649 'only_matching': True,
6650 }]
6651
6652 def _real_extract(self, url):
6653 channel_id = self._match_id(url)
6654 return self.url_result(
6655 f'https://www.youtube.com/channel/{channel_id}/live',
6656 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6657
6658
8bdd16b4 6659class YoutubeYtUserIE(InfoExtractor):
96565c7e 6660 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6661 IE_NAME = 'youtube:user'
8bdd16b4 6662 _VALID_URL = r'ytuser:(?P<id>.+)'
6663 _TESTS = [{
6664 'url': 'ytuser:phihag',
6665 'only_matching': True,
6666 }]
6667
6668 def _real_extract(self, url):
6669 user_id = self._match_id(url)
08270da5 6670 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6671
b05654f0 6672
3d3dddc9 6673class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6674 IE_NAME = 'youtube:favorites'
96565c7e 6675 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6676 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6677 _LOGIN_REQUIRED = True
6678 _TESTS = [{
6679 'url': ':ytfav',
6680 'only_matching': True,
6681 }, {
6682 'url': ':ytfavorites',
6683 'only_matching': True,
6684 }]
6685
6686 def _real_extract(self, url):
6687 return self.url_result(
6688 'https://www.youtube.com/playlist?list=LL',
6689 ie=YoutubeTabIE.ie_key())
6690
6691
ca5300c7 6692class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6693 IE_NAME = 'youtube:notif'
6694 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6695 _VALID_URL = r':ytnotif(?:ication)?s?'
6696 _LOGIN_REQUIRED = True
6697 _TESTS = [{
6698 'url': ':ytnotif',
6699 'only_matching': True,
6700 }, {
6701 'url': ':ytnotifications',
6702 'only_matching': True,
6703 }]
6704
6705 def _extract_notification_menu(self, response, continuation_list):
6706 notification_list = traverse_obj(
6707 response,
6708 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6709 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6710 expected_type=list) or []
6711 continuation_list[0] = None
6712 for item in notification_list:
6713 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6714 if entry:
6715 yield entry
6716 continuation = item.get('continuationItemRenderer')
6717 if continuation:
6718 continuation_list[0] = continuation
6719
6720 def _extract_notification_renderer(self, notification):
6721 video_id = traverse_obj(
6722 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6723 url = f'https://www.youtube.com/watch?v={video_id}'
6724 channel_id = None
6725 if not video_id:
6726 browse_ep = traverse_obj(
6727 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6728 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6729 post_id = self._search_regex(
6730 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6731 'post id', default=None)
6732 if not channel_id or not post_id:
6733 return
6734 # The direct /post url redirects to this in the browser
6735 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6736
6737 channel = traverse_obj(
6738 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6739 expected_type=str)
c7a7baaa 6740 notification_title = self._get_text(notification, 'shortMessage')
6741 if notification_title:
6742 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6743 # TODO: handle recommended videos
ca5300c7 6744 title = self._search_regex(
c7a7baaa 6745 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6746 'video title', default=None)
5225df50 6747 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6748 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6749 else None)
ca5300c7 6750 return {
6751 '_type': 'url',
6752 'url': url,
6753 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6754 'video_id': video_id,
6755 'title': title,
6756 'channel_id': channel_id,
6757 'channel': channel,
7666b936 6758 'uploader': channel,
ca5300c7 6759 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6760 'timestamp': timestamp,
ca5300c7 6761 }
6762
6763 def _notification_menu_entries(self, ytcfg):
6764 continuation_list = [None]
6765 response = None
6766 for page in itertools.count(1):
6767 ctoken = traverse_obj(
6768 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6769 response = self._extract_response(
6770 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6771 ep='notification/get_notification_menu', check_get_keys='actions',
6772 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6773 yield from self._extract_notification_menu(response, continuation_list)
6774 if not continuation_list[0]:
6775 break
6776
6777 def _real_extract(self, url):
6778 display_id = 'notifications'
6779 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6780 self._report_playlist_authcheck(ytcfg)
6781 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6782
6783
a6213a49 6784class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6785 IE_DESC = 'YouTube search'
78caa52a 6786 IE_NAME = 'youtube:search'
b05654f0 6787 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6788 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6789 _TESTS = [{
6790 'url': 'ytsearch5:youtube-dl test video',
6791 'playlist_count': 5,
6792 'info_dict': {
6793 'id': 'youtube-dl test video',
6794 'title': 'youtube-dl test video',
6795 }
6796 }]
b05654f0 6797
a61fd4cf 6798
5f7cb91a 6799class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6800 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6801 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6802 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6803 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6804 _TESTS = [{
6805 'url': 'ytsearchdate5:youtube-dl test video',
6806 'playlist_count': 5,
6807 'info_dict': {
6808 'id': 'youtube-dl test video',
6809 'title': 'youtube-dl test video',
6810 }
6811 }]
75dff0ee 6812
c9ae7b95 6813
a6213a49 6814class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6815 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6816 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6817 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6818 _TESTS = [{
6819 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6820 'playlist_mincount': 5,
6821 'info_dict': {
11f9be09 6822 'id': 'youtube-dl test video',
3462ffa8 6823 'title': 'youtube-dl test video',
6824 }
a61fd4cf 6825 }, {
6826 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6827 'playlist_mincount': 5,
6828 'info_dict': {
6829 'id': 'python',
6830 'title': 'python',
6831 }
ad210f4f 6832 }, {
6833 'url': 'https://www.youtube.com/results?search_query=%23cats',
6834 'playlist_mincount': 1,
6835 'info_dict': {
6836 'id': '#cats',
6837 'title': '#cats',
12a1b225
A
6838 # The test suite does not have support for nested playlists
6839 # 'entries': [{
6840 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6841 # 'title': '#cats',
6842 # }],
ad210f4f 6843 },
c7335551
M
6844 }, {
6845 # Channel results
6846 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6847 'info_dict': {
6848 'id': 'kurzgesagt',
6849 'title': 'kurzgesagt',
6850 },
6851 'playlist': [{
6852 'info_dict': {
6853 '_type': 'url',
6854 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6855 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6856 'ie_key': 'YoutubeTab',
6857 'channel': 'Kurzgesagt – In a Nutshell',
6858 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6859 'title': 'Kurzgesagt – In a Nutshell',
6860 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6861 'playlist_count': int, # XXX: should have a way of saying > 1
6862 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 6863 'thumbnails': list,
6864 'uploader_id': '@kurzgesagt',
6865 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
6866 'uploader': 'Kurzgesagt – In a Nutshell',
c7335551
M
6867 }
6868 }],
6869 'params': {'extract_flat': True, 'playlist_items': '1'},
6870 'playlist_mincount': 1,
3462ffa8 6871 }, {
6872 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6873 'only_matching': True,
6874 }]
6875
6876 def _real_extract(self, url):
4dfbf869 6877 qs = parse_qs(url)
386e1dd9 6878 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 6879 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 6880
6881
16aa9ea4 6882class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 6883 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 6884 IE_NAME = 'youtube:music:search_url'
6885 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6886 _TESTS = [{
6887 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6888 'playlist_count': 16,
6889 'info_dict': {
6890 'id': 'royalty free music',
6891 'title': 'royalty free music',
6892 }
6893 }, {
6894 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6895 'playlist_mincount': 30,
6896 'info_dict': {
6897 'id': 'royalty free music - songs',
6898 'title': 'royalty free music - songs',
6899 },
6900 'params': {'extract_flat': 'in_playlist'}
6901 }, {
6902 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6903 'playlist_mincount': 30,
6904 'info_dict': {
6905 'id': 'royalty free music - community playlists',
6906 'title': 'royalty free music - community playlists',
6907 },
6908 'params': {'extract_flat': 'in_playlist'}
6909 }]
6910
6911 _SECTIONS = {
6912 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6913 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6914 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6915 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6916 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6917 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6918 }
6919
6920 def _real_extract(self, url):
6921 qs = parse_qs(url)
6922 query = (qs.get('search_query') or qs.get('q'))[0]
6923 params = qs.get('sp', (None,))[0]
6924 if params:
6925 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
6926 else:
ac668111 6927 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 6928 params = self._SECTIONS.get(section)
6929 if not params:
6930 section = None
6931 title = join_nonempty(query, section, delim=' - ')
af5c1c55 6932 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 6933
6934
182bda88 6935class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 6936 """
25f14e9f 6937 Base class for feed extractors
82d02080 6938 Subclasses must re-define the _FEED_NAME property.
d7ae0639 6939 """
b2e8bc1b 6940 _LOGIN_REQUIRED = True
82d02080 6941 _FEED_NAME = 'feeds'
a25bca9f 6942
6943 def _real_initialize(self):
6944 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 6945
82d02080 6946 @classproperty
d7ae0639 6947 def IE_NAME(self):
82d02080 6948 return f'youtube:{self._FEED_NAME}'
04cc9617 6949
3853309f 6950 def _real_extract(self, url):
3d3dddc9 6951 return self.url_result(
182bda88 6952 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
6953
6954
ef2f3c7f 6955class YoutubeWatchLaterIE(InfoExtractor):
6956 IE_NAME = 'youtube:watchlater'
96565c7e 6957 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 6958 _VALID_URL = r':ytwatchlater'
bc7a9cd8 6959 _TESTS = [{
8bdd16b4 6960 'url': ':ytwatchlater',
bc7a9cd8
S
6961 'only_matching': True,
6962 }]
25f14e9f
S
6963
6964 def _real_extract(self, url):
ef2f3c7f 6965 return self.url_result(
6966 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 6967
6968
25f14e9f 6969class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 6970 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 6971 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 6972 _FEED_NAME = 'recommended'
45db527f 6973 _LOGIN_REQUIRED = False
3d3dddc9 6974 _TESTS = [{
6975 'url': ':ytrec',
6976 'only_matching': True,
6977 }, {
6978 'url': ':ytrecommended',
6979 'only_matching': True,
6980 }, {
6981 'url': 'https://youtube.com',
6982 'only_matching': True,
6983 }]
1ed5b5c9 6984
1ed5b5c9 6985
25f14e9f 6986class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 6987 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 6988 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 6989 _FEED_NAME = 'subscriptions'
3d3dddc9 6990 _TESTS = [{
6991 'url': ':ytsubs',
6992 'only_matching': True,
6993 }, {
6994 'url': ':ytsubscriptions',
6995 'only_matching': True,
6996 }]
1ed5b5c9 6997
1ed5b5c9 6998
25f14e9f 6999class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7000 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7001 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7002 _FEED_NAME = 'history'
3d3dddc9 7003 _TESTS = [{
7004 'url': ':ythistory',
7005 'only_matching': True,
7006 }]
1ed5b5c9
JMF
7007
7008
6e634cbe 7009class YoutubeStoriesIE(InfoExtractor):
7010 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
7011 IE_NAME = 'youtube:stories'
7012 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
7013 _TESTS = [{
7014 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
7015 'only_matching': True,
7016 }]
7017
7018 def _real_extract(self, url):
7019 playlist_id = f'RLTD{self._match_id(url)}'
7020 return self.url_result(
50ac0e54 7021 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 7022 ie=YoutubeTabIE, video_id=playlist_id)
7023
7024
80eb0bd9 7025class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7026 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7027 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7028 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7029 _TESTS = [{
1dd18a88 7030 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7031 'only_matching': True,
7032 }]
7033
7034 @staticmethod
7035 def _generate_audio_pivot_params(video_id):
7036 """
7037 Generates sfv_audio_pivot browse params for this video id
7038 """
7039 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7040 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7041
7042 def _real_extract(self, url):
7043 video_id = self._match_id(url)
7044 return self.url_result(
7045 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7046 ie=YoutubeTabIE)
7047
7048
15870e90
PH
7049class YoutubeTruncatedURLIE(InfoExtractor):
7050 IE_NAME = 'youtube:truncated_url'
7051 IE_DESC = False # Do not list
975d35db 7052 _VALID_URL = r'''(?x)
b95aab84
PH
7053 (?:https?://)?
7054 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7055 (?:watch\?(?:
c4808c60 7056 feature=[a-z_]+|
b95aab84
PH
7057 annotation_id=annotation_[^&]+|
7058 x-yt-cl=[0-9]+|
c1708b89 7059 hl=[^&]*|
287be8c6 7060 t=[0-9]+
b95aab84
PH
7061 )?
7062 |
7063 attribution_link\?a=[^&]+
7064 )
7065 $
975d35db 7066 '''
15870e90 7067
c4808c60 7068 _TESTS = [{
2d3d2997 7069 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7070 'only_matching': True,
dc2fc736 7071 }, {
2d3d2997 7072 'url': 'https://www.youtube.com/watch?',
dc2fc736 7073 'only_matching': True,
b95aab84
PH
7074 }, {
7075 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7076 'only_matching': True,
7077 }, {
7078 'url': 'https://www.youtube.com/watch?feature=foo',
7079 'only_matching': True,
c1708b89
PH
7080 }, {
7081 'url': 'https://www.youtube.com/watch?hl=en-GB',
7082 'only_matching': True,
287be8c6
PH
7083 }, {
7084 'url': 'https://www.youtube.com/watch?t=2372',
7085 'only_matching': True,
c4808c60
PH
7086 }]
7087
15870e90
PH
7088 def _real_extract(self, url):
7089 raise ExtractorError(
78caa52a
PH
7090 'Did you forget to quote the URL? Remember that & is a meta '
7091 'character in most shells, so you want to put the URL in quotes, '
3867038a 7092 'like youtube-dl '
2d3d2997 7093 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7094 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7095 expected=True)
772fd5cc
PH
7096
7097
471d0367 7098class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7099 IE_NAME = 'youtube:clip'
471d0367 7100 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7101 _TESTS = [{
7102 # FIXME: Other metadata should be extracted from the clip, not from the base video
7103 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7104 'info_dict': {
7105 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7106 'ext': 'mp4',
7107 'section_start': 29.0,
7108 'section_end': 39.7,
7109 'duration': 10.7,
12a1b225
A
7110 'age_limit': 0,
7111 'availability': 'public',
7112 'categories': ['Gaming'],
7113 'channel': 'Scott The Woz',
7114 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7115 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7116 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7117 'like_count': int,
7118 'playable_in_embed': True,
7119 'tags': 'count:17',
7120 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7121 'title': 'Mobile Games on Console - Scott The Woz',
7122 'upload_date': '20210920',
7123 'uploader': 'Scott The Woz',
7666b936 7124 'uploader_id': '@ScottTheWoz',
7125 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7126 'view_count': int,
7127 'live_status': 'not_live',
7666b936 7128 'channel_follower_count': int,
7129 'chapters': 'count:20',
471d0367 7130 }
7131 }]
3cd786db 7132
7133 def _real_extract(self, url):
471d0367 7134 clip_id = self._match_id(url)
7135 _, data = self._extract_webpage(url, clip_id)
7136
7137 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7138 if not video_id:
7139 raise ExtractorError('Unable to find video ID')
7140
7141 clip_data = traverse_obj(data, (
7142 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7143 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7144 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7145 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7146
7147 return {
7148 '_type': 'url_transparent',
7149 'url': f'https://www.youtube.com/watch?v={video_id}',
7150 'ie_key': YoutubeIE.ie_key(),
7151 'id': clip_id,
7152 'section_start': int(clip_data['startTimeMs']) / 1000,
7153 'section_end': int(clip_data['endTimeMs']) / 1000,
7154 }
3cd786db 7155
7156
b032ff0f 7157class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7158 IE_NAME = 'youtube:consent'
7159 IE_DESC = False # Do not list
7160 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7161 _TESTS = [{
7162 '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',
7163 'info_dict': {
7164 'id': 'qVv6vCqciTM',
7165 'ext': 'mp4',
7166 'age_limit': 0,
7666b936 7167 'uploader_id': '@sana_natori',
b032ff0f 7168 'comment_count': int,
7169 'chapters': 'count:13',
7170 'upload_date': '20221223',
7171 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7172 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7173 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7174 'like_count': int,
7175 'release_date': '20221223',
7176 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7177 '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】',
7178 'view_count': int,
7179 'playable_in_embed': True,
7180 'duration': 4438,
7181 'availability': 'public',
7182 'channel_follower_count': int,
7183 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7184 'categories': ['Entertainment'],
7185 'live_status': 'was_live',
7186 'release_timestamp': 1671793345,
7187 'channel': 'さなちゃんねる',
7188 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7189 'uploader': 'さなちゃんねる',
7190 },
7191 'add_ie': ['Youtube'],
7192 'params': {'skip_download': 'Youtube'},
7193 }]
7194
7195 def _real_extract(self, url):
7196 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7197 if not redirect_url:
7198 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7199 return self.url_result(redirect_url)
7200
7201
772fd5cc
PH
7202class YoutubeTruncatedIDIE(InfoExtractor):
7203 IE_NAME = 'youtube:truncated_id'
7204 IE_DESC = False # Do not list
b95aab84 7205 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7206
7207 _TESTS = [{
7208 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7209 'only_matching': True,
7210 }]
7211
7212 def _real_extract(self, url):
7213 video_id = self._match_id(url)
7214 raise ExtractorError(
86e5f3ed 7215 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7216 expected=True)