]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[ie] Do not smuggle `http_headers`
[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
ac668111 18import urllib.parse
c5e8d7af 19
b05654f0 20from .common import InfoExtractor, SearchInfoExtractor
25836db6 21from .openload import PhantomJSwrapper
14f25df2 22from ..compat import functools
545cc85d 23from ..jsinterp import JSInterpreter
3d2623a8 24from ..networking.exceptions import HTTPError, network_exceptions
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,
11f9be09 44 orderedSet,
6310acf5 45 parse_codecs,
49bd8c66 46 parse_count,
7c80519c 47 parse_duration,
7ea65411 48 parse_iso8601,
4dfbf869 49 parse_qs,
dca3ff4a 50 qualities,
3995d37d 51 remove_start,
cf7e015f 52 smuggle_url,
dbdaaa23 53 str_or_none,
c93d53f5 54 str_to_int,
f3aa3c3f 55 strftime_or_none,
7c365c21 56 traverse_obj,
556dbe7f 57 try_get,
c5e8d7af
PH
58 unescapeHTML,
59 unified_strdate,
f0d785d3 60 unified_timestamp,
cf7e015f 61 unsmuggle_url,
8bdd16b4 62 update_url_query,
21c340b8 63 url_or_none,
fe93e2c4 64 urljoin,
7c365c21 65 variadic,
c5e8d7af
PH
66)
67
c795c39f 68STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
962ffcf8 69# any clients starting with _ cannot be explicitly requested by the user
000c15a4 70INNERTUBE_CLIENTS = {
71 'web': {
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
74 'client': {
75 'clientName': 'WEB',
a0c830f4 76 'clientVersion': '2.20220801.00.00',
000c15a4 77 }
78 },
79 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
80 },
81 'web_embedded': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 86 'clientVersion': '1.20220731.00.00',
000c15a4 87 },
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
90 },
91 'web_music': {
92 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
93 'INNERTUBE_HOST': 'music.youtube.com',
94 'INNERTUBE_CONTEXT': {
95 'client': {
96 'clientName': 'WEB_REMIX',
a0c830f4 97 'clientVersion': '1.20220727.01.00',
000c15a4 98 }
99 },
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
101 },
e7e94f2a 102 'web_creator': {
18c7683d 103 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_CREATOR',
a0c830f4 107 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
111 },
000c15a4 112 'android': {
18c7683d 113 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'ANDROID',
50ac0e54 117 'clientVersion': '17.31.35',
118 'androidSdkVersion': 30,
119 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 120 }
121 },
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 123 'REQUIRE_JS_PLAYER': False
000c15a4 124 },
125 'android_embedded': {
18c7683d 126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 127 'INNERTUBE_CONTEXT': {
128 'client': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 130 'clientVersion': '17.31.35',
131 'androidSdkVersion': 30,
132 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 133 },
134 },
b6de707d 135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
000c15a4 137 },
138 'android_music': {
18c7683d 139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 140 'INNERTUBE_CONTEXT': {
141 'client': {
142 'clientName': 'ANDROID_MUSIC',
a0c830f4 143 'clientVersion': '5.16.51',
50ac0e54 144 'androidSdkVersion': 30,
145 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 146 }
147 },
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 149 'REQUIRE_JS_PLAYER': False
000c15a4 150 },
e7e94f2a 151 'android_creator': {
18c7683d 152 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
153 'INNERTUBE_CONTEXT': {
154 'client': {
155 'clientName': 'ANDROID_CREATOR',
50ac0e54 156 'clientVersion': '22.30.100',
157 'androidSdkVersion': 30,
158 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
159 },
160 },
b6de707d 161 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
162 'REQUIRE_JS_PLAYER': False
e7e94f2a 163 },
18c7683d 164 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
165 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 166 'ios': {
18c7683d 167 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS',
224b5a35 171 'clientVersion': '17.33.2',
18c7683d 172 'deviceModel': 'iPhone14,3',
224b5a35 173 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 174 }
175 },
b6de707d 176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
000c15a4 178 },
179 'ios_embedded': {
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 183 'clientVersion': '17.33.2',
18c7683d 184 'deviceModel': 'iPhone14,3',
224b5a35 185 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
191 'ios_music': {
18c7683d 192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
224b5a35
SF
196 'clientVersion': '5.21',
197 'deviceModel': 'iPhone14,3',
198 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 199 },
200 },
b6de707d 201 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
202 'REQUIRE_JS_PLAYER': False
000c15a4 203 },
e7e94f2a
D
204 'ios_creator': {
205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'IOS_CREATOR',
224b5a35
SF
208 'clientVersion': '22.33.101',
209 'deviceModel': 'iPhone14,3',
210 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
211 },
212 },
b6de707d 213 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
214 'REQUIRE_JS_PLAYER': False
e7e94f2a 215 },
3619f78d 216 # mweb has 'ultralow' formats
217 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 218 'mweb': {
18c7683d 219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 220 'INNERTUBE_CONTEXT': {
221 'client': {
222 'clientName': 'MWEB',
a0c830f4 223 'clientVersion': '2.20220801.00.00',
000c15a4 224 }
225 },
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
227 },
228 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
229 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
230 'tv_embedded': {
231 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
232 'INNERTUBE_CONTEXT': {
233 'client': {
234 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
235 'clientVersion': '2.0',
236 },
237 },
238 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
239 },
000c15a4 240}
241
242
e7870111
D
243def _split_innertube_client(client_name):
244 variant, *base = client_name.rsplit('.', 1)
245 if base:
246 return variant, base[0], variant
247 base, *variant = client_name.split('_', 1)
248 return client_name, base, variant[0] if variant else None
249
250
c795c39f
L
251def short_client_name(client_name):
252 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
253 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
254
255
000c15a4 256def build_innertube_clients():
2e4cacd0 257 THIRD_PARTY = {
e7870111 258 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 259 }
1e75d97d 260 BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
2e4cacd0 261 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 262
263 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 264 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 265 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 266 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 267 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 268
e7870111 269 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 270 ytcfg['priority'] = 10 * priority(base_client)
271
e48b3875 272 if not variant:
e7870111
D
273 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
274 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
275 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
276 embedscreen['priority'] -= 3
277 elif variant == 'embedded':
e48b3875 278 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 279 ytcfg['priority'] -= 2
e48b3875 280 else:
000c15a4 281 ytcfg['priority'] -= 3
282
283
284build_innertube_clients()
285
286
c26f9b99 287class BadgeType(enum.Enum):
288 AVAILABILITY_UNLISTED = enum.auto()
289 AVAILABILITY_PRIVATE = enum.auto()
290 AVAILABILITY_PUBLIC = enum.auto()
291 AVAILABILITY_PREMIUM = enum.auto()
292 AVAILABILITY_SUBSCRIPTION = enum.auto()
293 LIVE_NOW = enum.auto()
14a14335 294 VERIFIED = enum.auto()
c26f9b99 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
378ae9f9 499 socs = cookies.get('SOCS')
500 if socs and not socs.value.startswith('CAA'): # not consented
501 return
502 self._set_cookie('.youtube.com', 'SOCS', 'CAI', secure=True) # accept all (required for mixes)
8d81f3e3 503
f3aa3c3f 504 def _initialize_pref(self):
505 cookies = self._get_cookies('https://www.youtube.com/')
506 pref_cookie = cookies.get('PREF')
507 pref = {}
508 if pref_cookie:
509 try:
14f25df2 510 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 511 except ValueError:
512 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 513 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 514 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 515
b2e8bc1b 516 def _real_initialize(self):
f3aa3c3f 517 self._initialize_pref()
cce889b9 518 self._initialize_consent()
a25bca9f 519 self._check_login_required()
520
521 def _check_login_required(self):
24146491 522 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 523 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 524
b7c47b74 525 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
526 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 527
000c15a4 528 def _get_default_ytcfg(self, client='web'):
529 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 530
000c15a4 531 def _get_innertube_host(self, client='web'):
532 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 533
000c15a4 534 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 535 # try_get but with fallback to default ytcfg client values when present
536 _func = lambda y: try_get(y, getter, expected_type)
537 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
538
000c15a4 539 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 540 return self._ytcfg_get_safe(
541 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 542 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 543
000c15a4 544 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 545 return self._ytcfg_get_safe(
546 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 547 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 548
2ae778b8 549 def _select_api_hostname(self, req_api_hostname, default_client=None):
550 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
551 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
552
000c15a4 553 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 554 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 555
000c15a4 556 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 557 context = get_first(
558 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 559 # Enforce language and tz for extraction
560 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 561 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 562 return context
563
cf87314d 564 _SAPISID = None
565
109dd3b2 566 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 567 time_now = round(time.time())
cf87314d 568 if self._SAPISID is None:
569 yt_cookies = self._get_cookies('https://www.youtube.com')
570 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
571 # See: https://github.com/yt-dlp/yt-dlp/issues/393
572 sapisid_cookie = dict_get(
573 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
574 if sapisid_cookie and sapisid_cookie.value:
575 self._SAPISID = sapisid_cookie.value
576 self.write_debug('Extracted SAPISID cookie')
577 # SAPISID cookie is required if not already present
578 if not yt_cookies.get('SAPISID'):
579 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
580 self._set_cookie(
581 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
582 else:
583 self._SAPISID = False
584 if not self._SAPISID:
585 return None
1974e99f 586 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
587 sapisidhash = hashlib.sha1(
86e5f3ed 588 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 589 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
590
591 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 592 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 593 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 594
109dd3b2 595 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 596 data.update(query)
11f9be09 597 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 598 real_headers.update({'content-type': 'application/json'})
599 if headers:
600 real_headers.update(headers)
2ae778b8 601 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
602 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 603 return self._download_json(
2ae778b8 604 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 605 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 606 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 607 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 608
65141660 609 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
610 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 611
99e9e001 612 @staticmethod
613 def _extract_session_index(*data):
614 """
615 Index of current account in account list.
616 See: https://github.com/yt-dlp/yt-dlp/pull/519
617 """
618 for ytcfg in data:
619 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
620 if session_index is not None:
621 return session_index
622
623 # Deprecated?
624 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 625 if ytcfg:
14f25df2 626 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
627 if token:
628 return token
99e9e001 629 if webpage:
630 return self._search_regex(
631 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
632 'identity token', default=None, fatal=False)
a1c5d2ca
M
633
634 @staticmethod
fe93e2c4 635 def _extract_account_syncid(*args):
8ea3f7b9 636 """
637 Extract syncId required to download private playlists of secondary channels
fe93e2c4 638 @params response and/or ytcfg
8ea3f7b9 639 """
fe93e2c4 640 for data in args:
641 # ytcfg includes channel_syncid if on secondary channel
14f25df2 642 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 643 if delegated_sid:
644 return delegated_sid
645 sync_ids = (try_get(
646 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 647 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 648 if len(sync_ids) >= 2 and sync_ids[1]:
649 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
650 # and just "user_syncid||" for primary channel. We only want the channel_syncid
651 return sync_ids[0]
a1c5d2ca 652
ac56cf38 653 @staticmethod
654 def _extract_visitor_data(*args):
655 """
656 Extracts visitorData from an API response or ytcfg
657 Appears to be used to track session state
658 """
9222c381 659 return get_first(
6c73052c 660 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 661 expected_type=str)
ac56cf38 662
2762dbb1 663 @functools.cached_property
99e9e001 664 def is_authenticated(self):
665 return bool(self._generate_sapisidhash_header())
666
11f9be09 667 def extract_ytcfg(self, video_id, webpage):
8c54a305 668 if not webpage:
669 return {}
29f7c58a 670 return self._parse_json(
671 self._search_regex(
672 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 673 default='{}'), video_id, fatal=False) or {}
674
11f9be09 675 def generate_api_headers(
99e9e001 676 self, *, ytcfg=None, account_syncid=None, session_index=None,
677 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
678
2ae778b8 679 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 680 headers = {
14f25df2 681 'X-YouTube-Client-Name': str(
11f9be09 682 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
683 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 684 'Origin': origin,
685 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
686 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 687 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
688 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 689 }
690 if session_index is None:
314ee305 691 session_index = self._extract_session_index(ytcfg)
692 if account_syncid or session_index is not None:
693 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 694
109dd3b2 695 auth = self._generate_sapisidhash_header(origin)
f4f751af 696 if auth is not None:
697 headers['Authorization'] = auth
109dd3b2 698 headers['X-Origin'] = origin
7a32c70d 699 return filter_dict(headers)
29f7c58a 700
a25bca9f 701 def _download_ytcfg(self, client, video_id):
702 url = {
703 'web': 'https://www.youtube.com',
704 'web_music': 'https://music.youtube.com',
705 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
706 }.get(client)
707 if not url:
708 return {}
709 webpage = self._download_webpage(
710 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
711 return self.extract_ytcfg(video_id, webpage) or {}
712
2d6659b9 713 @staticmethod
714 def _build_api_continuation_query(continuation, ctp=None):
715 query = {
716 'continuation': continuation
717 }
718 # TODO: Inconsistency with clickTrackingParams.
719 # Currently we have a fixed ctp contained within context (from ytcfg)
720 # and a ctp in root query for continuation.
721 if ctp:
722 query['clickTracking'] = {'clickTrackingParams': ctp}
723 return query
724
2d6659b9 725 @classmethod
726 def _extract_next_continuation_data(cls, renderer):
727 next_continuation = try_get(
728 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
729 lambda x: x['continuation']['reloadContinuationData']), dict)
730 if not next_continuation:
731 return
732 continuation = next_continuation.get('continuation')
733 if not continuation:
734 return
735 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 736 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 737
738 @classmethod
739 def _extract_continuation_ep_data(cls, continuation_ep: dict):
740 if isinstance(continuation_ep, dict):
741 continuation = try_get(
14f25df2 742 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 743 if not continuation:
744 return
745 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 746 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 747
748 @classmethod
749 def _extract_continuation(cls, renderer):
750 next_continuation = cls._extract_next_continuation_data(renderer)
751 if next_continuation:
752 return next_continuation
fe93e2c4 753
7a32c70d 754 return traverse_obj(renderer, (
755 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
756 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
757 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 758
fe93e2c4 759 @classmethod
760 def _extract_alerts(cls, data):
109dd3b2 761 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
762 if not isinstance(alert_dict, dict):
763 continue
764 for alert in alert_dict.values():
765 alert_type = alert.get('type')
766 if not alert_type:
767 continue
052e1350 768 message = cls._get_text(alert, 'text')
109dd3b2 769 if message:
770 yield alert_type, message
771
c0ac49bc 772 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 773 errors, warnings = [], []
109dd3b2 774 for alert_type, alert_message in alerts:
641ad5d8 775 if alert_type.lower() == 'error' and fatal:
109dd3b2 776 errors.append([alert_type, alert_message])
a057779d 777 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 778 warnings.append([alert_type, alert_message])
779
780 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 781 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 782 if errors:
783 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
784
785 def _extract_and_report_alerts(self, data, *args, **kwargs):
786 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
787
14a14335 788 def _extract_badges(self, badge_list: list):
789 """
790 Extract known BadgeType's from a list of badge renderers.
791 @returns [{'type': BadgeType}]
792 """
793 icon_type_map = {
c26f9b99 794 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
795 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
14a14335 796 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC,
797 'CHECK_CIRCLE_THICK': BadgeType.VERIFIED,
798 'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED,
8213ce28 799 'CHECK': BadgeType.VERIFIED,
c26f9b99 800 }
801
802 badge_style_map = {
803 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
804 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
14a14335 805 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW,
8213ce28 806 'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED,
ad54c913 807 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED,
c26f9b99 808 }
809
810 label_map = {
811 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
812 'private': BadgeType.AVAILABILITY_PRIVATE,
813 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
814 'live': BadgeType.LIVE_NOW,
14a14335 815 'premium': BadgeType.AVAILABILITY_PREMIUM,
8213ce28 816 'verified': BadgeType.VERIFIED,
ad54c913 817 'official artist channel': BadgeType.VERIFIED,
c26f9b99 818 }
819
820 badges = []
14a14335 821 for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))):
c26f9b99 822 badge_type = (
14a14335 823 icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
c26f9b99 824 or badge_style_map.get(traverse_obj(badge, 'style'))
825 )
826 if badge_type:
827 badges.append({'type': badge_type})
828 continue
829
830 # fallback, won't work in some languages
14a14335 831 label = traverse_obj(
832 badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='')
c26f9b99 833 for match, label_badge_type in label_map.items():
834 if match in label.lower():
14a14335 835 badges.append({'type': label_badge_type})
836 break
c26f9b99 837
47193e02 838 return badges
839
c26f9b99 840 @staticmethod
841 def _has_badge(badges, badge_type):
842 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
843
47193e02 844 @staticmethod
052e1350 845 def _get_text(data, *path_list, max_runs=None):
846 for path in path_list or [None]:
847 if path is None:
848 obj = [data]
849 else:
850 obj = traverse_obj(data, path, default=[])
851 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
852 obj = [obj]
853 for item in obj:
14f25df2 854 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 855 if text:
856 return text
857 runs = try_get(item, lambda x: x['runs'], list) or []
858 if not runs and isinstance(item, list):
859 runs = item
860
861 runs = runs[:min(len(runs), max_runs or len(runs))]
6839ae1f 862 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
052e1350 863 if text:
864 return text
47193e02 865
f0d785d3 866 def _get_count(self, data, *path_list):
867 count_text = self._get_text(data, *path_list) or ''
868 count = parse_count(count_text)
869 if count is None:
870 count = str_to_int(
871 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
872 return count
873
a709d873 874 @staticmethod
875 def _extract_thumbnails(data, *path_list):
876 """
877 Extract thumbnails from thumbnails dict
878 @param path_list: path list to level that contains 'thumbnails' key
879 """
880 thumbnails = []
881 for path in path_list or [()]:
6839ae1f 882 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
a709d873 883 thumbnail_url = url_or_none(thumbnail.get('url'))
884 if not thumbnail_url:
885 continue
886 # Sometimes youtube gives a wrong thumbnail URL. See:
887 # https://github.com/yt-dlp/yt-dlp/issues/233
888 # https://github.com/ytdl-org/youtube-dl/issues/28023
889 if 'maxresdefault' in thumbnail_url:
890 thumbnail_url = thumbnail_url.split('?')[0]
891 thumbnails.append({
892 'url': thumbnail_url,
893 'height': int_or_none(thumbnail.get('height')),
894 'width': int_or_none(thumbnail.get('width')),
895 })
896 return thumbnails
897
f3aa3c3f 898 @staticmethod
899 def extract_relative_time(relative_time_text):
900 """
901 Extracts a relative time from string and converts to dt object
2fb35f60 902 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago'
f3aa3c3f 903 """
2fb35f60 904
5ca095cb 905 # XXX: this could be moved to a general function in utils/_utils.py
2fb35f60 906 # The relative time text strings are roughly the same as what
907 # Javascript's Intl.RelativeTimeFormat function generates.
908 # See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat
909 mobj = re.search(
910 r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>sec(?:ond)?|s|min(?:ute)?|h(?:our|r)?|d(?:ay)?|w(?:eek|k)?|mo(?:nth)?|y(?:ear|r)?)s?\s*ago',
911 relative_time_text)
f3aa3c3f 912 if mobj:
f0d785d3 913 start = mobj.group('start')
914 if start:
915 return datetime_from_str(start)
f3aa3c3f 916 try:
f0d785d3 917 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 918 except ValueError:
919 return None
920
c26f9b99 921 def _parse_time_text(self, text):
922 if not text:
923 return
f3aa3c3f 924 dt = self.extract_relative_time(text)
925 timestamp = None
926 if isinstance(dt, datetime.datetime):
927 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 928
929 if timestamp is None:
930 timestamp = (
931 unified_timestamp(text) or unified_timestamp(
932 self._search_regex(
17322130 933 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 934 text.lower(), 'time text', default=None)))
f0d785d3 935
c26f9b99 936 if text and timestamp is None and self._preferred_lang in (None, 'en'):
937 self.report_warning(
938 f'Cannot parse localized time text "{text}"', only_once=True)
939 return timestamp
f3aa3c3f 940
109dd3b2 941 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
942 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 943 default_client='web'):
eb5bdbfa 944 raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE))
945 # Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal.
946 icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete))
947 icd_rm = next(icd_retries)
948 main_retries = iter(self.RetryManager())
949 main_rm = next(main_retries)
feebf6d0
SS
950 # Manual retry loop for multiple RetryManagers
951 # The proper RetryManager MUST be advanced after an error
b634ba74 952 # and its result MUST be checked if the manager is non fatal
feebf6d0 953 while True:
109dd3b2 954 try:
955 response = self._call_api(
956 ep=ep, fatal=True, headers=headers,
be5c1ae8 957 video_id=item_id, query=query, note=note,
109dd3b2 958 context=self._extract_context(ytcfg, default_client),
959 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 960 api_hostname=api_hostname, default_client=default_client)
109dd3b2 961 except ExtractorError as e:
be5c1ae8 962 if not isinstance(e.cause, network_exceptions):
963 return self._error_or_warning(e, fatal=fatal)
3d2623a8 964 elif not isinstance(e.cause, HTTPError):
eb5bdbfa 965 main_rm.error = e
966 next(main_retries)
be5c1ae8 967 continue
109dd3b2 968
3d2623a8 969 first_bytes = e.cause.response.read(512)
be5c1ae8 970 if not is_html(first_bytes):
971 yt_error = try_get(
972 self._parse_json(
3d2623a8 973 self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
be5c1ae8 974 lambda x: x['error']['message'], str)
975 if yt_error:
976 self._report_alerts([('ERROR', yt_error)], fatal=False)
977 # Downloading page may result in intermittent 5xx HTTP error
eb5bdbfa 978 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
be5c1ae8 979 # We also want to catch all other network exceptions since errors in later pages can be troublesome
980 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
3d2623a8 981 if e.cause.status not in (403, 429):
eb5bdbfa 982 main_rm.error = e
983 next(main_retries)
be5c1ae8 984 continue
985 return self._error_or_warning(e, fatal=fatal)
986
987 try:
988 self._extract_and_report_alerts(response, only_once=True)
989 except ExtractorError as e:
eb5bdbfa 990 # YouTube's servers may return errors we want to retry on in a 200 OK response
be5c1ae8 991 # See: https://github.com/yt-dlp/yt-dlp/issues/839
992 if 'unknown error' in e.msg.lower():
eb5bdbfa 993 main_rm.error = e
994 next(main_retries)
be5c1ae8 995 continue
996 return self._error_or_warning(e, fatal=fatal)
997 # Youtube sometimes sends incomplete data
998 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
999 if not traverse_obj(response, *variadic(check_get_keys)):
eb5bdbfa 1000 icd_rm.error = ExtractorError('Incomplete data received', expected=True)
1001 should_retry = next(icd_retries, None)
1002 if not should_retry:
1003 return None
be5c1ae8 1004 continue
1005
1006 return response
109dd3b2 1007
9297939e 1008 @staticmethod
1009 def is_music_url(url):
5b28cef7 1010 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
9297939e 1011
30a074c2 1012 def _extract_video(self, renderer):
1013 video_id = renderer.get('videoId')
4dc23a80
M
1014
1015 reel_header_renderer = traverse_obj(renderer, (
1016 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
1017 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
1018
1019 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 1020 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
1021
1022 duration = int_or_none(renderer.get('lengthSeconds'))
1023 if duration is None:
1024 duration = parse_duration(self._get_text(
1025 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 1026 if duration is None:
4dc23a80 1027 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 1028 duration = parse_duration(self._search_regex(
1029 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
1030 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
1031 video_id, default=None, group='duration'))
1032
f3aa3c3f 1033 channel_id = traverse_obj(
a44ca5a4 1034 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
1035 expected_type=str, get_all=False)
4dc23a80
M
1036 if not channel_id:
1037 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
1038
7666b936 1039 channel_id = self.ucid_or_none(channel_id)
1040
f3aa3c3f 1041 overlay_style = traverse_obj(
a44ca5a4 1042 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
1043 get_all=False, expected_type=str)
14a14335 1044 badges = self._extract_badges(traverse_obj(renderer, 'badges'))
8213ce28 1045 owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
fd2ad7cb 1046 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 1047 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1048 expected_type=str)) or ''
fd2ad7cb 1049 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 1050 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 1051 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 1052
4dc23a80
M
1053 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1054 or self._get_text(reel_header_renderer, 'timestampText') or '')
1055 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1056
867c66ff
M
1057 live_status = (
1058 'is_upcoming' if scheduled_timestamp is not None
1059 else 'was_live' if 'streamed' in time_text.lower()
1060 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1061 else None)
1062
4dc23a80
M
1063 # videoInfo is a string like '50K views • 10 years ago'.
1064 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1065 view_count = (0 if 'no views' in view_count_text.lower()
1066 else self._get_count({'simpleText': view_count_text}))
1067 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1068
93e12ed7 1069 channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
1070 or self._get_text(reel_header_renderer, 'channelTitleText'))
1071
1072 channel_handle = traverse_obj(renderer, (
1073 'shortBylineText', 'runs', ..., 'navigationEndpoint',
1074 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
1075 expected_type=self.handle_from_url, get_all=False)
30a074c2 1076 return {
39ed931e 1077 '_type': 'url',
30a074c2 1078 'ie_key': YoutubeIE.ie_key(),
1079 'id': video_id,
fd2ad7cb 1080 'url': url,
30a074c2 1081 'title': title,
1082 'description': description,
1083 'duration': duration,
f3aa3c3f 1084 'channel_id': channel_id,
93e12ed7 1085 'channel': channel,
4dc23a80 1086 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
93e12ed7 1087 'uploader': channel,
1088 'uploader_id': channel_handle,
1089 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4dc23a80 1090 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1091 'timestamp': (self._parse_time_text(time_text)
1092 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1093 else None),
f3aa3c3f 1094 'release_timestamp': scheduled_timestamp,
c26f9b99 1095 'availability':
1096 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1097 else self._availability(
1098 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1099 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1100 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1101 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1102 view_count_field: view_count,
14a14335 1103 'live_status': live_status,
8213ce28 1104 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
30a074c2 1105 }
1106
0c148415 1107
360e1ca5 1108class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1109 IE_DESC = 'YouTube'
cb7dfeea 1110 _VALID_URL = r"""(?x)^
c5e8d7af 1111 (
edb53e2d 1112 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1113 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1114 (?:www\.)?deturl\.com/www\.youtube\.com|
1115 (?:www\.)?pwnyoutube\.com|
1116 (?:www\.)?hooktube\.com|
1117 (?:www\.)?yourepeat\.com|
1118 tube\.majestyc\.net|
1119 %(invidious)s|
1120 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1121 (?:.*?\#/)? # handle anchor (#/) redirect urls
1122 (?: # the various things that can precede the ID:
dad2210c 1123 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1124 |(?: # or the v= param in all its forms
f7000f3a 1125 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1126 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1127 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1128 v=
1129 )
f4b05232 1130 ))
cbaed4bb
S
1131 |(?:
1132 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1133 vid\.plus| # or vid.plus/xxxx
1134 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1135 %(invidious)s
cbaed4bb 1136 )/
edb53e2d 1137 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1138 )
c5e8d7af 1139 )? # all until now is optional -> you can pass the naked ID
201c1459 1140 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1141 (?(1).+)? # if we found the ID, everything can follow
9297939e 1142 (?:\#|$)""" % {
d9190e44 1143 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1144 }
7c6eb424 1145 _EMBED_REGEX = [
1146 r'''(?x)
1147 (?:
0ca0f881 1148 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1149 data-video-url=|
1150 <embed[^>]+?src=|
1151 embedSWF\(?:\s*|
1152 <object[^>]+data=|
1153 new\s+SWFObject\(
1154 )
1155 (["\'])
1156 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1157 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1158 \1''',
1159 # https://wordpress.org/plugins/lazy-load-for-videos/
1160 r'''(?xs)
1161 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1162 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1163 ]
6368e2e6 1164 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1165
e40c758c 1166 _PLAYER_INFO_RE = (
cc2db878 1167 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1168 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$',
545cc85d 1169 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1170 )
2c62dc26 1171 _formats = {
c2d3cb4c 1172 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1173 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1174 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1175 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1176 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1177 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1178 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1179 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1180 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1181 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1182 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1183 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1184 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1185 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1186 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1187 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1188 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1189 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1190
1191
1192 # 3D videos
c2d3cb4c 1193 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1194 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1195 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1196 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1197 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1198 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1199 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1200
96fb5605 1201 # Apple HTTP Live Streaming
11f12195 1202 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1203 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1204 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1205 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1206 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1207 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1208 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1209 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1210
1211 # DASH mp4 video
d23028a8
S
1212 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1213 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1214 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1215 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1216 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1217 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1218 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1219 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1220 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1221 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1222 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1223 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1224
f6f1fc92 1225 # Dash mp4 audio
d23028a8
S
1226 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1227 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1228 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1229 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1230 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1231 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1232 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1233
1234 # Dash webm
d23028a8
S
1235 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1236 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1237 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1238 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1239 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1240 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1241 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1242 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1243 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1244 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1245 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1246 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1247 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1248 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1249 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1250 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1251 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1252 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1253 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1254 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1255 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1256 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1257
1258 # Dash webm audio
d23028a8
S
1259 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1260 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1261
0857baad 1262 # Dash webm audio with opus inside
d23028a8
S
1263 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1264 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1265 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1266
ce6b9a2d
PH
1267 # RTMP (unnamed)
1268 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1269
1270 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1271 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1272 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1273 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1274 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1275 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1276 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1277 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1278 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1279 }
29f7c58a 1280 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1281
fd5c4aab
S
1282 _GEO_BYPASS = False
1283
78caa52a 1284 IE_NAME = 'youtube'
2eb88d95
PH
1285 _TESTS = [
1286 {
2d3d2997 1287 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1288 'info_dict': {
1289 'id': 'BaW_jenozKc',
1290 'ext': 'mp4',
3867038a 1291 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
ff9f925b 1292 'channel': 'Philipp Hagemeister',
dd4c4492
S
1293 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1294 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1295 'upload_date': '20121002',
ff9f925b 1296 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1297 'categories': ['Science & Technology'],
3867038a 1298 'tags': ['youtube-dl'],
556dbe7f 1299 'duration': 10,
dbdaaa23 1300 'view_count': int,
3e7c1224 1301 'like_count': int,
ff9f925b 1302 'availability': 'public',
1303 'playable_in_embed': True,
1304 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1305 'live_status': 'not_live',
1306 'age_limit': 0,
7c80519c 1307 'start_time': 1,
297a564b 1308 'end_time': 9,
12a1b225 1309 'comment_count': int,
7666b936 1310 'channel_follower_count': int,
1311 'uploader': 'Philipp Hagemeister',
1312 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1313 'uploader_id': '@PhilippHagemeister',
5caf30db 1314 'heatmap': 'count:100',
2eb88d95 1315 }
0e853ca4 1316 },
fccd3771 1317 {
4bc3a23e
PH
1318 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1319 'note': 'Embed-only video (#1746)',
1320 'info_dict': {
1321 'id': 'yZIXLfi8CZQ',
1322 'ext': 'mp4',
1323 'upload_date': '20120608',
1324 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1325 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
94bfcd23 1326 'age_limit': 18,
545cc85d 1327 },
1328 'skip': 'Private video',
fccd3771 1329 },
11b56058 1330 {
8bdd16b4 1331 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1332 'note': 'Use the first video ID in the URL',
1333 'info_dict': {
1334 'id': 'BaW_jenozKc',
1335 'ext': 'mp4',
3867038a 1336 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
976ae3ea 1337 'channel': 'Philipp Hagemeister',
1338 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1339 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1340 'upload_date': '20121002',
976ae3ea 1341 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1342 'categories': ['Science & Technology'],
3867038a 1343 'tags': ['youtube-dl'],
556dbe7f 1344 'duration': 10,
dbdaaa23 1345 'view_count': int,
11b56058 1346 'like_count': int,
976ae3ea 1347 'availability': 'public',
1348 'playable_in_embed': True,
1349 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1350 'live_status': 'not_live',
1351 'age_limit': 0,
12a1b225 1352 'comment_count': int,
7666b936 1353 'channel_follower_count': int,
1354 'uploader': 'Philipp Hagemeister',
1355 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1356 'uploader_id': '@PhilippHagemeister',
14a14335 1357 'heatmap': 'count:100',
34a7de29
S
1358 },
1359 'params': {
1360 'skip_download': True,
1361 },
11b56058 1362 },
dd27fd17 1363 {
2d3d2997 1364 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1365 'note': '256k DASH audio (format 141) via DASH manifest',
1366 'info_dict': {
1367 'id': 'a9LDPn-MO4I',
1368 'ext': 'm4a',
1369 'upload_date': '20121002',
4bc3a23e 1370 'description': '',
4bc3a23e 1371 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1372 },
4bc3a23e
PH
1373 'params': {
1374 'youtube_include_dash_manifest': True,
1375 'format': '141',
4919603f 1376 },
de3c7fe0 1377 'skip': 'format 141 not served anymore',
dd27fd17 1378 },
8bdd16b4 1379 # DASH manifest with encrypted signature
1380 {
1381 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1382 'info_dict': {
1383 'id': 'IB3lcPjvWLA',
1384 'ext': 'm4a',
1385 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1386 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1387 'duration': 244,
8bdd16b4 1388 'upload_date': '20131011',
cc2db878 1389 'abr': 129.495,
976ae3ea 1390 'like_count': int,
1391 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1392 'playable_in_embed': True,
1393 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1394 'view_count': int,
1395 'track': 'The Spark',
1396 'live_status': 'not_live',
1397 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1398 'channel': 'Afrojack',
976ae3ea 1399 'tags': 'count:19',
1400 'availability': 'public',
1401 'categories': ['Music'],
1402 'age_limit': 0,
1403 'alt_title': 'The Spark',
7666b936 1404 'channel_follower_count': int,
1405 'uploader': 'Afrojack',
1406 'uploader_url': 'https://www.youtube.com/@Afrojack',
1407 'uploader_id': '@Afrojack',
8bdd16b4 1408 },
1409 'params': {
1410 'youtube_include_dash_manifest': True,
1411 'format': '141/bestaudio[ext=m4a]',
1412 },
1413 },
65c2fde2 1414 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1415 {
65c2fde2 1416 'note': 'Embed allowed age-gate video',
2d3d2997 1417 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1418 'info_dict': {
1419 'id': 'HtVdAasjOgU',
1420 'ext': 'mp4',
1421 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1422 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1423 'duration': 142,
c522adb1 1424 'upload_date': '20140605',
34952f09 1425 'age_limit': 18,
976ae3ea 1426 'categories': ['Gaming'],
1427 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1428 'availability': 'needs_auth',
1429 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1430 'like_count': int,
1431 'channel': 'The Witcher',
1432 'live_status': 'not_live',
1433 'tags': 'count:17',
1434 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1435 'playable_in_embed': True,
1436 'view_count': int,
7666b936 1437 'channel_follower_count': int,
1438 'uploader': 'The Witcher',
1439 'uploader_url': 'https://www.youtube.com/@thewitcher',
1440 'uploader_id': '@thewitcher',
14a14335 1441 'comment_count': int,
8213ce28 1442 'channel_is_verified': True,
14a14335 1443 'heatmap': 'count:100',
c522adb1
JMF
1444 },
1445 },
65c2fde2 1446 {
1447 'note': 'Age-gate video with embed allowed in public site',
1448 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1449 'info_dict': {
1450 'id': 'HsUATh_Nc2U',
1451 'ext': 'mp4',
1452 'title': 'Godzilla 2 (Official Video)',
1453 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1454 'upload_date': '20200408',
65c2fde2 1455 'age_limit': 18,
976ae3ea 1456 'availability': 'needs_auth',
1457 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
976ae3ea 1458 'channel': 'FlyingKitty',
1459 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1460 'view_count': int,
1461 'categories': ['Entertainment'],
1462 'live_status': 'not_live',
1463 'tags': ['Flyingkitty', 'godzilla 2'],
1464 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1465 'like_count': int,
1466 'duration': 177,
1467 'playable_in_embed': True,
7666b936 1468 'channel_follower_count': int,
1469 'uploader': 'FlyingKitty',
1470 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
1471 'uploader_id': '@FlyingKitty900',
5caf30db 1472 'comment_count': int,
8213ce28 1473 'channel_is_verified': True,
65c2fde2 1474 },
1475 },
1476 {
1477 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1478 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1479 'info_dict': {
1480 'id': 'Tq92D6wQ1mg',
1481 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1482 'ext': 'mp4',
17322130 1483 'upload_date': '20191228',
65c2fde2 1484 'description': 'md5:17eccca93a786d51bc67646756894066',
1485 'age_limit': 18,
976ae3ea 1486 'like_count': int,
1487 'availability': 'needs_auth',
976ae3ea 1488 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1489 'view_count': int,
1490 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1491 'channel': 'Projekt Melody',
1492 'live_status': 'not_live',
1493 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1494 'playable_in_embed': True,
1495 'categories': ['Entertainment'],
1496 'duration': 106,
1497 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1498 'comment_count': int,
7666b936 1499 'channel_follower_count': int,
1500 'uploader': 'Projekt Melody',
1501 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
1502 'uploader_id': '@ProjektMelody',
65c2fde2 1503 },
1504 },
1505 {
1506 'note': 'Non-Agegated non-embeddable video',
1507 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1508 'info_dict': {
1509 'id': 'MeJVWBSsPAY',
1510 'ext': 'mp4',
1511 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
65c2fde2 1512 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1513 'upload_date': '20130730',
976ae3ea 1514 'track': 'Such mich find mich',
1515 'age_limit': 0,
1516 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1517 'like_count': int,
1518 'playable_in_embed': False,
1519 'creator': 'OOMPH!',
1520 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1521 'view_count': int,
1522 'alt_title': 'Such mich find mich',
1523 'duration': 210,
1524 'channel': 'Herr Lurik',
1525 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1526 'categories': ['Music'],
1527 'availability': 'public',
976ae3ea 1528 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1529 'live_status': 'not_live',
1530 'artist': 'OOMPH!',
7666b936 1531 'channel_follower_count': int,
1532 'uploader': 'Herr Lurik',
1533 'uploader_url': 'https://www.youtube.com/@HerrLurik',
1534 'uploader_id': '@HerrLurik',
65c2fde2 1535 },
1536 },
1537 {
1538 'note': 'Non-bypassable age-gated video',
1539 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1540 'only_matching': True,
1541 },
8bdd16b4 1542 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1543 # YouTube Red ad is not captured for creator
1544 {
1545 'url': '__2ABJjxzNo',
1546 'info_dict': {
1547 'id': '__2ABJjxzNo',
1548 'ext': 'mp4',
1549 'duration': 266,
1550 'upload_date': '20100430',
545cc85d 1551 'creator': 'deadmau5',
1552 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1553 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1554 'alt_title': 'Some Chords',
976ae3ea 1555 'availability': 'public',
1556 'tags': 'count:14',
1557 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1558 'view_count': int,
1559 'live_status': 'not_live',
1560 'channel': 'deadmau5',
1561 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1562 'like_count': int,
1563 'track': 'Some Chords',
1564 'artist': 'deadmau5',
1565 'playable_in_embed': True,
1566 'age_limit': 0,
1567 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1568 'categories': ['Music'],
1569 'album': 'Some Chords',
7666b936 1570 'channel_follower_count': int,
1571 'uploader': 'deadmau5',
1572 'uploader_url': 'https://www.youtube.com/@deadmau5',
1573 'uploader_id': '@deadmau5',
8bdd16b4 1574 },
1575 'expected_warnings': [
1576 'DASH manifest missing',
1577 ]
1578 },
067aa17e 1579 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1580 {
1581 'url': 'lqQg6PlCWgI',
1582 'info_dict': {
1583 'id': 'lqQg6PlCWgI',
1584 'ext': 'mp4',
556dbe7f 1585 'duration': 6085,
90227264 1586 'upload_date': '20150827',
12a1b225 1587 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
cbe2bd91 1588 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1589 'like_count': int,
1590 'release_timestamp': 1343767800,
1591 'playable_in_embed': True,
1592 'categories': ['Sports'],
1593 'release_date': '20120731',
1594 'channel': 'Olympics',
1595 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1596 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1597 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1598 'age_limit': 0,
1599 'availability': 'public',
1600 'live_status': 'was_live',
1601 'view_count': int,
1602 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
7666b936 1603 'channel_follower_count': int,
1604 'uploader': 'Olympics',
1605 'uploader_url': 'https://www.youtube.com/@Olympics',
1606 'uploader_id': '@Olympics',
8213ce28 1607 'channel_is_verified': True,
cbe2bd91
PH
1608 },
1609 'params': {
1610 'skip_download': 'requires avconv',
e52a40ab 1611 }
cbe2bd91 1612 },
6271f1ca
PH
1613 # Non-square pixels
1614 {
1615 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1616 'info_dict': {
1617 'id': '_b-2C3KPAM0',
1618 'ext': 'mp4',
1619 'stretched_ratio': 16 / 9.,
556dbe7f 1620 'duration': 85,
6271f1ca 1621 'upload_date': '20110310',
6271f1ca 1622 '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 1623 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1624 'playable_in_embed': True,
1625 'channel': '孫ᄋᄅ',
1626 'age_limit': 0,
1627 'tags': 'count:11',
1628 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1629 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1630 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1631 'view_count': int,
1632 'categories': ['People & Blogs'],
1633 'like_count': int,
1634 'live_status': 'not_live',
1635 'availability': 'unlisted',
12a1b225 1636 'comment_count': int,
7666b936 1637 'channel_follower_count': int,
1638 'uploader': '孫ᄋᄅ',
1639 'uploader_url': 'https://www.youtube.com/@AllenMeow',
1640 'uploader_id': '@AllenMeow',
6271f1ca 1641 },
06b491eb
S
1642 },
1643 # url_encoded_fmt_stream_map is empty string
1644 {
1645 'url': 'qEJwOuvDf7I',
1646 'info_dict': {
1647 'id': 'qEJwOuvDf7I',
f57b7835 1648 'ext': 'webm',
06b491eb
S
1649 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1650 'description': '',
1651 'upload_date': '20150404',
06b491eb
S
1652 },
1653 'params': {
1654 'skip_download': 'requires avconv',
e323cf3f
S
1655 },
1656 'skip': 'This live event has ended.',
06b491eb 1657 },
067aa17e 1658 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1659 {
1660 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1661 'info_dict': {
1662 'id': 'FIl7x6_3R5Y',
eb6793ba 1663 'ext': 'webm',
da77d856
S
1664 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1665 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1666 'duration': 220,
da77d856 1667 'upload_date': '20150625',
eb6793ba 1668 'formats': 'mincount:31',
da77d856 1669 },
eb6793ba 1670 'skip': 'not actual anymore',
2ee8f5d8 1671 },
8a1a26ce
YCH
1672 # DASH manifest with segment_list
1673 {
1674 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1675 'md5': '8ce563a1d667b599d21064e982ab9e31',
1676 'info_dict': {
1677 'id': 'CsmdDsKjzN8',
1678 'ext': 'mp4',
17ee98e1 1679 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce 1680 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
8a1a26ce
YCH
1681 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1682 },
1683 'params': {
1684 'youtube_include_dash_manifest': True,
1685 'format': '135', # bestvideo
be49068d
S
1686 },
1687 'skip': 'This live event has ended.',
2ee8f5d8 1688 },
cf7e015f 1689 {
6368e2e6 1690 # Multifeed videos (multiple cameras), URL can be of any Camera
7666b936 1691 # TODO: fix multifeed titles
6368e2e6 1692 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1693 'info_dict': {
6368e2e6 1694 'id': 'zaPI8MvL8pg',
1695 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1696 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1697 },
1698 'playlist': [{
1699 'info_dict': {
6368e2e6 1700 'id': 'j5yGuxZ8lLU',
cf7e015f 1701 'ext': 'mp4',
6368e2e6 1702 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
6368e2e6 1703 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1704 'duration': 10120,
1705 'channel_follower_count': int,
1706 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1707 'availability': 'public',
1708 'playable_in_embed': True,
1709 'upload_date': '20131105',
6368e2e6 1710 'categories': ['Gaming'],
1711 'live_status': 'was_live',
1712 'tags': 'count:24',
1713 'release_timestamp': 1383701910,
1714 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1715 'comment_count': int,
1716 'age_limit': 0,
1717 'like_count': int,
1718 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1719 'channel': 'WiiLikeToPlay',
1720 'view_count': int,
1721 'release_date': '20131106',
7666b936 1722 'uploader': 'WiiLikeToPlay',
1723 'uploader_id': '@WLTP',
1724 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1725 },
1726 }, {
1727 'info_dict': {
6368e2e6 1728 'id': 'zaPI8MvL8pg',
cf7e015f 1729 'ext': 'mp4',
6368e2e6 1730 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
6368e2e6 1731 'availability': 'public',
1732 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1733 'channel': 'WiiLikeToPlay',
6368e2e6 1734 'channel_follower_count': int,
1735 'description': 'md5:563ccbc698b39298481ca3c571169519',
1736 'duration': 10108,
1737 'age_limit': 0,
1738 'like_count': int,
1739 'tags': 'count:24',
1740 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
6368e2e6 1741 'release_timestamp': 1383701915,
1742 'comment_count': int,
1743 'upload_date': '20131105',
1744 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1745 'release_date': '20131106',
1746 'playable_in_embed': True,
1747 'live_status': 'was_live',
1748 'categories': ['Gaming'],
1749 'view_count': int,
7666b936 1750 'uploader': 'WiiLikeToPlay',
1751 'uploader_id': '@WLTP',
1752 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1753 },
1754 }, {
1755 'info_dict': {
6368e2e6 1756 'id': 'R7r3vfO7Hao',
cf7e015f 1757 'ext': 'mp4',
6368e2e6 1758 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1759 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1760 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1761 'like_count': int,
1762 'availability': 'public',
1763 'playable_in_embed': True,
1764 'upload_date': '20131105',
1765 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1766 'channel_follower_count': int,
1767 'tags': 'count:24',
1768 'release_date': '20131106',
6368e2e6 1769 'comment_count': int,
1770 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1771 'channel': 'WiiLikeToPlay',
1772 'categories': ['Gaming'],
1773 'release_timestamp': 1383701914,
1774 'live_status': 'was_live',
1775 'age_limit': 0,
1776 'duration': 10128,
1777 'view_count': int,
7666b936 1778 'uploader': 'WiiLikeToPlay',
1779 'uploader_id': '@WLTP',
1780 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1781 },
1782 }],
6368e2e6 1783 'params': {'skip_download': True},
cbaed4bb 1784 },
f9f49d87 1785 {
067aa17e 1786 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1787 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1788 'info_dict': {
1789 'id': 'gVfLd0zydlo',
1790 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1791 },
1792 'playlist_count': 2,
be49068d 1793 'skip': 'Not multifeed anymore',
f9f49d87 1794 },
cbaed4bb 1795 {
2d3d2997 1796 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1797 'only_matching': True,
0e49d9a6 1798 },
6d4fc66b 1799 {
2d3d2997 1800 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1801 'only_matching': True,
1802 },
0e49d9a6 1803 {
067aa17e 1804 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1805 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1806 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1807 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1808 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1809 'info_dict': {
1810 'id': 'lsguqyKfVQg',
1811 'ext': 'mp4',
1812 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1813 'alt_title': 'Dark Walk',
0e49d9a6 1814 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1815 'duration': 133,
0e49d9a6 1816 'upload_date': '20151119',
11f9be09 1817 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1818 'track': 'Dark Walk',
1819 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1820 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1821 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1822 'categories': ['Film & Animation'],
1823 'view_count': int,
1824 'live_status': 'not_live',
1825 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1826 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1827 'tags': 'count:13',
1828 'availability': 'public',
1829 'channel': 'IronSoulElf',
1830 'playable_in_embed': True,
1831 'like_count': int,
1832 'age_limit': 0,
6c73052c 1833 'channel_follower_count': int
0e49d9a6
LL
1834 },
1835 'params': {
1836 'skip_download': True,
1837 },
1838 },
61f92af1 1839 {
067aa17e 1840 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1841 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1842 'only_matching': True,
1843 },
313dfc45
LL
1844 {
1845 # Video with yt:stretch=17:0
1846 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1847 'info_dict': {
1848 'id': 'Q39EVAstoRM',
1849 'ext': 'mp4',
1850 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1851 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1852 'upload_date': '20151107',
313dfc45
LL
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
be49068d 1857 'skip': 'This video does not exist.',
313dfc45 1858 },
201c1459 1859 {
1860 # Video with incomplete 'yt:stretch=16:'
1861 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1862 'only_matching': True,
1863 },
7caf9830
S
1864 {
1865 # Video licensed under Creative Commons
1866 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1867 'info_dict': {
1868 'id': 'M4gD1WSo5mA',
1869 'ext': 'mp4',
1870 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1871 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1872 'duration': 721,
17322130 1873 'upload_date': '20150128',
7caf9830 1874 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1875 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1876 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1877 'like_count': int,
1878 'age_limit': 0,
1879 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1880 'channel': 'The Berkman Klein Center for Internet & Society',
1881 'availability': 'public',
1882 'view_count': int,
1883 'categories': ['Education'],
1884 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1885 'live_status': 'not_live',
1886 'playable_in_embed': True,
d5d1df8a 1887 'channel_follower_count': int,
1888 'chapters': list,
7666b936 1889 'uploader': 'The Berkman Klein Center for Internet & Society',
1890 'uploader_id': '@BKCHarvard',
1891 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
7caf9830
S
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 },
fd050249 1897 {
fd050249
S
1898 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1899 'info_dict': {
1900 'id': 'eQcmzGIKrzg',
1901 'ext': 'mp4',
1902 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1903 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1904 'duration': 4060,
17322130 1905 'upload_date': '20151120',
fd050249 1906 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1907 'playable_in_embed': True,
1908 'tags': 'count:12',
1909 'like_count': int,
1910 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1911 'age_limit': 0,
1912 'availability': 'public',
1913 'categories': ['News & Politics'],
1914 'channel': 'Bernie Sanders',
1915 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1916 'view_count': int,
1917 'live_status': 'not_live',
1918 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1919 'comment_count': int,
d5d1df8a 1920 'channel_follower_count': int,
1921 'chapters': list,
7666b936 1922 'uploader': 'Bernie Sanders',
1923 'uploader_url': 'https://www.youtube.com/@BernieSanders',
1924 'uploader_id': '@BernieSanders',
8213ce28 1925 'channel_is_verified': True,
14a14335 1926 'heatmap': 'count:100',
fd050249
S
1927 },
1928 'params': {
1929 'skip_download': True,
1930 },
1931 },
040ac686
S
1932 {
1933 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1934 'only_matching': True,
7f29cf54
S
1935 },
1936 {
067aa17e 1937 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1938 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1939 'only_matching': True,
6496ccb4
S
1940 },
1941 {
1942 # Rental video preview
1943 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1944 'info_dict': {
1945 'id': 'uGpuVWrhIzE',
1946 'ext': 'mp4',
1947 'title': 'Piku - Trailer',
1948 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1949 'upload_date': '20150811',
6496ccb4
S
1950 'license': 'Standard YouTube License',
1951 },
1952 'params': {
1953 'skip_download': True,
1954 },
eb6793ba 1955 'skip': 'This video is not available.',
022a5d66 1956 },
12afdc2a
S
1957 {
1958 # YouTube Red video with episode data
1959 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1960 'info_dict': {
1961 'id': 'iqKdEhx-dD4',
1962 'ext': 'mp4',
1963 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1964 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1965 'duration': 2085,
12afdc2a 1966 'upload_date': '20170118',
12afdc2a
S
1967 'series': 'Mind Field',
1968 'season_number': 1,
1969 'episode_number': 1,
976ae3ea 1970 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1971 'tags': 'count:12',
1972 'view_count': int,
1973 'availability': 'public',
1974 'age_limit': 0,
1975 'channel': 'Vsauce',
1976 'episode': 'Episode 1',
1977 'categories': ['Entertainment'],
1978 'season': 'Season 1',
1979 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1980 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1981 'like_count': int,
1982 'playable_in_embed': True,
1983 'live_status': 'not_live',
7666b936 1984 'channel_follower_count': int,
1985 'uploader': 'Vsauce',
1986 'uploader_url': 'https://www.youtube.com/@Vsauce',
1987 'uploader_id': '@Vsauce',
14a14335 1988 'comment_count': int,
8213ce28 1989 'channel_is_verified': True,
12afdc2a
S
1990 },
1991 'params': {
1992 'skip_download': True,
1993 },
1994 'expected_warnings': [
1995 'Skipping DASH manifest',
1996 ],
1997 },
c7121fa7
S
1998 {
1999 # The following content has been identified by the YouTube community
2000 # as inappropriate or offensive to some audiences.
2001 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
2002 'info_dict': {
2003 'id': '6SJNVb0GnPI',
2004 'ext': 'mp4',
2005 'title': 'Race Differences in Intelligence',
2006 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
2007 'duration': 965,
2008 'upload_date': '20140124',
c7121fa7
S
2009 },
2010 'params': {
2011 'skip_download': True,
2012 },
545cc85d 2013 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 2014 },
022a5d66
S
2015 {
2016 # itag 212
2017 'url': '1t24XAntNCY',
2018 'only_matching': True,
fd5c4aab
S
2019 },
2020 {
2021 # geo restricted to JP
2022 'url': 'sJL6WA-aGkQ',
2023 'only_matching': True,
2024 },
cd5a74a2
S
2025 {
2026 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
2027 'only_matching': True,
2028 },
bc2ca1bb 2029 {
2030 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
2031 'only_matching': True,
2032 },
2033 {
2034 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
2035 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
2036 'only_matching': True,
2037 },
825cd268
RA
2038 {
2039 # DRM protected
2040 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
2041 'only_matching': True,
4fe54c12
S
2042 },
2043 {
2044 # Video with unsupported adaptive stream type formats
2045 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2046 'info_dict': {
2047 'id': 'Z4Vy8R84T1U',
2048 'ext': 'mp4',
2049 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2050 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2051 'duration': 433,
2052 'upload_date': '20130923',
4fe54c12
S
2053 'formats': 'maxcount:10',
2054 },
2055 'params': {
2056 'skip_download': True,
2057 'youtube_include_dash_manifest': False,
2058 },
5429d6a9 2059 'skip': 'not actual anymore',
5caabd3c 2060 },
2061 {
822b9d9c 2062 # Youtube Music Auto-generated description
7666b936 2063 # TODO: fix metadata extraction
5caabd3c 2064 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2065 'info_dict': {
2066 'id': 'MgNrAu2pzNs',
2067 'ext': 'mp4',
2068 'title': 'Voyeur Girl',
2069 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2070 'upload_date': '20190312',
5caabd3c 2071 'artist': 'Stephen',
2072 'track': 'Voyeur Girl',
2073 'album': 'it\'s too much love to know my dear',
2074 'release_date': '20190313',
2075 'release_year': 2019,
976ae3ea 2076 'alt_title': 'Voyeur Girl',
2077 'view_count': int,
976ae3ea 2078 'playable_in_embed': True,
2079 'like_count': int,
2080 'categories': ['Music'],
2081 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
7666b936 2082 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
2083 'uploader': 'Stephen',
976ae3ea 2084 'availability': 'public',
2085 'creator': 'Stephen',
2086 'duration': 169,
2087 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2088 'age_limit': 0,
2089 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2090 'tags': 'count:11',
2091 'live_status': 'not_live',
6c73052c 2092 'channel_follower_count': int
5caabd3c 2093 },
2094 'params': {
2095 'skip_download': True,
2096 },
2097 },
66b48727
RA
2098 {
2099 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2100 'only_matching': True,
2101 },
011e75e6
S
2102 {
2103 # invalid -> valid video id redirection
2104 'url': 'DJztXj2GPfl',
2105 'info_dict': {
2106 'id': 'DJztXj2GPfk',
2107 'ext': 'mp4',
2108 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2109 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2110 'upload_date': '20090125',
011e75e6
S
2111 'artist': 'Panjabi MC',
2112 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2113 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2114 },
2115 'params': {
2116 'skip_download': True,
2117 },
545cc85d 2118 'skip': 'Video unavailable',
ea74e00b
DP
2119 },
2120 {
2121 # empty description results in an empty string
2122 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2123 'info_dict': {
2124 'id': 'x41yOUIvK2k',
2125 'ext': 'mp4',
2126 'title': 'IMG 3456',
2127 'description': '',
2128 'upload_date': '20170613',
976ae3ea 2129 'view_count': int,
2130 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2131 'like_count': int,
2132 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2133 'tags': [],
2134 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2135 'availability': 'public',
2136 'age_limit': 0,
2137 'categories': ['Pets & Animals'],
2138 'duration': 7,
2139 'playable_in_embed': True,
2140 'live_status': 'not_live',
7666b936 2141 'channel': 'l\'Or Vert asbl',
2142 'channel_follower_count': int,
2143 'uploader': 'l\'Or Vert asbl',
2144 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2145 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2146 },
2147 'params': {
2148 'skip_download': True,
2149 },
2150 },
a0566bbf 2151 {
29f7c58a 2152 # with '};' inside yt initial data (see [1])
2153 # see [2] for an example with '};' inside ytInitialPlayerResponse
2154 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2155 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2156 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2157 'info_dict': {
2158 'id': 'CHqg6qOn4no',
2159 'ext': 'mp4',
2160 'title': 'Part 77 Sort a list of simple types in c#',
2161 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2162 'upload_date': '20130831',
976ae3ea 2163 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2164 'like_count': int,
976ae3ea 2165 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2166 'live_status': 'not_live',
2167 'categories': ['Education'],
2168 'availability': 'public',
2169 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2170 'tags': 'count:12',
2171 'playable_in_embed': True,
2172 'age_limit': 0,
2173 'view_count': int,
2174 'duration': 522,
2175 'channel': 'kudvenkat',
12a1b225 2176 'comment_count': int,
d5d1df8a 2177 'channel_follower_count': int,
2178 'chapters': list,
7666b936 2179 'uploader': 'kudvenkat',
2180 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2181 'uploader_id': '@Csharp-video-tutorialsBlogspot',
8213ce28 2182 'channel_is_verified': True,
14a14335 2183 'heatmap': 'count:100',
a0566bbf 2184 },
2185 'params': {
2186 'skip_download': True,
2187 },
2188 },
29f7c58a 2189 {
2190 # another example of '};' in ytInitialData
2191 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2192 'only_matching': True,
2193 },
2194 {
2195 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2196 'only_matching': True,
2197 },
545cc85d 2198 {
cc2db878 2199 # https://github.com/ytdl-org/youtube-dl/pull/28094
2200 'url': 'OtqTfy26tG0',
2201 'info_dict': {
2202 'id': 'OtqTfy26tG0',
2203 'ext': 'mp4',
2204 'title': 'Burn Out',
2205 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2206 'upload_date': '20141120',
cc2db878 2207 'artist': 'The Cinematic Orchestra',
2208 'track': 'Burn Out',
2209 'album': 'Every Day',
976ae3ea 2210 'like_count': int,
2211 'live_status': 'not_live',
2212 'alt_title': 'Burn Out',
2213 'duration': 614,
2214 'age_limit': 0,
2215 'view_count': int,
2216 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2217 'creator': 'The Cinematic Orchestra',
2218 'channel': 'The Cinematic Orchestra',
2219 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2220 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2221 'availability': 'public',
2222 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2223 'categories': ['Music'],
2224 'playable_in_embed': True,
7666b936 2225 'channel_follower_count': int,
2226 'uploader': 'The Cinematic Orchestra',
2227 'comment_count': int,
cc2db878 2228 },
2229 'params': {
2230 'skip_download': True,
2231 },
545cc85d 2232 },
bc2ca1bb 2233 {
2234 # controversial video, only works with bpctr when authenticated with cookies
2235 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2236 'only_matching': True,
2237 },
a1a7907b 2238 {
2239 # controversial video, requires bpctr/contentCheckOk
2240 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2241 'info_dict': {
2242 'id': 'SZJvDhaSDnc',
2243 'ext': 'mp4',
2244 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2245 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2246 'upload_date': '20140716',
976ae3ea 2247 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2248 'duration': 170,
2249 'categories': ['News & Politics'],
976ae3ea 2250 'view_count': int,
2251 'channel': 'CBS Mornings',
2252 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2253 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2254 'age_limit': 18,
2255 'availability': 'needs_auth',
2256 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2257 'like_count': int,
2258 'live_status': 'not_live',
2259 'playable_in_embed': True,
7666b936 2260 'channel_follower_count': int,
2261 'uploader': 'CBS Mornings',
2262 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2263 'uploader_id': '@CBSMornings',
14a14335 2264 'comment_count': int,
8213ce28 2265 'channel_is_verified': True,
a1a7907b 2266 }
2267 },
f7ad7160 2268 {
2269 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2270 'url': 'cBvYw8_A0vQ',
2271 'info_dict': {
2272 'id': 'cBvYw8_A0vQ',
2273 'ext': 'mp4',
2274 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2275 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2276 'upload_date': '20201120',
976ae3ea 2277 'duration': 1456,
2278 'categories': ['Travel & Events'],
2279 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2280 'view_count': int,
2281 'channel': 'Walk around Japan',
2282 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2283 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2284 'age_limit': 0,
2285 'availability': 'public',
2286 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2287 'live_status': 'not_live',
2288 'playable_in_embed': True,
7666b936 2289 'channel_follower_count': int,
2290 'uploader': 'Walk around Japan',
2291 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2292 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2293 },
2294 'params': {
2295 'skip_download': True,
2296 },
0fb983f6 2297 }, {
2298 # Has multiple audio streams
2299 'url': 'WaOKSUlf4TM',
2300 'only_matching': True
9297939e 2301 }, {
2302 # Requires Premium: has format 141 when requested using YTM url
2303 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2304 'only_matching': True
2305 }, {
120916da 2306 # multiple subtitles with same lang_code
2307 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2308 'only_matching': True,
109dd3b2 2309 }, {
2310 # Force use android client fallback
2311 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2312 'info_dict': {
2313 'id': 'YOelRv7fMxY',
11f9be09 2314 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2315 'ext': '3gp',
2316 'upload_date': '20210624',
2317 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2318 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2319 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2320 'duration': 596,
2321 'categories': ['Entertainment'],
976ae3ea 2322 'view_count': int,
2323 'channel': 'colinfurze',
2324 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2325 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2326 'age_limit': 0,
2327 'availability': 'public',
2328 'like_count': int,
2329 'live_status': 'not_live',
2330 'playable_in_embed': True,
d5d1df8a 2331 'channel_follower_count': int,
2332 'chapters': list,
7666b936 2333 'uploader': 'colinfurze',
2334 'uploader_url': 'https://www.youtube.com/@colinfurze',
2335 'uploader_id': '@colinfurze',
14a14335 2336 'comment_count': int,
8213ce28 2337 'channel_is_verified': True,
14a14335 2338 'heatmap': 'count:100',
109dd3b2 2339 },
2340 'params': {
2341 'format': '17', # 3gp format available on android
2342 'extractor_args': {'youtube': {'player_client': ['android']}},
2343 },
120916da 2344 },
109dd3b2 2345 {
2346 # Skip download of additional client configs (remix client config in this case)
2347 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2348 'only_matching': True,
2349 'params': {
2350 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2351 },
8fc54b12 2352 }, {
2353 # shorts
2354 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2355 'only_matching': True,
9222c381 2356 }, {
2357 'note': 'Storyboards',
2358 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2359 'info_dict': {
2360 'id': '5KLPxDtMqe8',
2361 'ext': 'mhtml',
2362 'format_id': 'sb0',
2363 'title': 'Your Brain is Plastic',
9222c381 2364 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2365 'upload_date': '20140324',
976ae3ea 2366 'like_count': int,
2367 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2368 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2369 'view_count': int,
2370 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2371 'playable_in_embed': True,
2372 'tags': 'count:12',
976ae3ea 2373 'availability': 'public',
2374 'channel': 'SciShow',
2375 'live_status': 'not_live',
2376 'duration': 248,
2377 'categories': ['Education'],
2378 'age_limit': 0,
d5d1df8a 2379 'channel_follower_count': int,
2380 'chapters': list,
7666b936 2381 'uploader': 'SciShow',
2382 'uploader_url': 'https://www.youtube.com/@SciShow',
2383 'uploader_id': '@SciShow',
14a14335 2384 'comment_count': int,
8213ce28 2385 'channel_is_verified': True,
14a14335 2386 'heatmap': 'count:100',
9222c381 2387 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2388 }, {
2389 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2390 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2391 'info_dict': {
2392 'id': '2NUZ8W2llS4',
2393 'ext': 'mp4',
2394 'title': 'The NP that test your phone performance 🙂',
2395 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 2396 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2397 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2398 'duration': 21,
2399 'view_count': int,
2400 'age_limit': 0,
2401 'categories': ['Gaming'],
2402 'tags': 'count:23',
2403 'playable_in_embed': True,
2404 'live_status': 'not_live',
2405 'upload_date': '20220103',
2406 'like_count': int,
2407 'availability': 'public',
2408 'channel': 'Leon Nguyen',
2409 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2410 'comment_count': int,
7666b936 2411 'channel_follower_count': int,
2412 'uploader': 'Leon Nguyen',
2413 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2414 'uploader_id': '@LeonNguyen',
14a14335 2415 'heatmap': 'count:100',
992f9a73 2416 }
1ff88b7a 2417 }, {
2418 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2419 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2420 'info_dict': {
2421 'id': '2NUZ8W2llS4',
2422 'ext': 'mp4',
2423 'title': 'The NP that test your phone performance 🙂',
2424 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 2425 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2426 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2427 'duration': 21,
2428 'view_count': int,
2429 'age_limit': 0,
2430 'categories': ['Gaming'],
2431 'tags': 'count:23',
2432 'playable_in_embed': True,
2433 'live_status': 'not_live',
2434 'upload_date': '20220102',
2435 'like_count': int,
2436 'availability': 'public',
2437 'channel': 'Leon Nguyen',
2438 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2439 'comment_count': int,
7666b936 2440 'channel_follower_count': int,
2441 'uploader': 'Leon Nguyen',
2442 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2443 'uploader_id': '@LeonNguyen',
14a14335 2444 'heatmap': 'count:100',
1ff88b7a 2445 },
2446 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2447 }, {
2448 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2449 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2450 'info_dict': {
2451 'id': 'mzZzzBU6lrM',
2452 'ext': 'mp4',
2453 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2454 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 2455 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2456 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2457 'duration': 955,
2458 'view_count': int,
2459 'age_limit': 0,
2460 'categories': ['Entertainment'],
2461 'tags': 'count:26',
2462 'playable_in_embed': True,
2463 'live_status': 'not_live',
2464 'release_timestamp': 1641172509,
2465 'release_date': '20220103',
2466 'upload_date': '20220103',
2467 'like_count': int,
2468 'availability': 'public',
2469 'channel': 'Quackity',
2470 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
7666b936 2471 'channel_follower_count': int,
2472 'uploader': 'Quackity',
2473 'uploader_id': '@Quackity',
2474 'uploader_url': 'https://www.youtube.com/@Quackity',
14a14335 2475 'comment_count': int,
8213ce28 2476 'channel_is_verified': True,
14a14335 2477 'heatmap': 'count:100',
992f9a73 2478 }
2479 },
2480 { # continuous livestream. Microformat upload date should be preferred.
2481 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2482 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2483 'info_dict': {
2484 'id': 'kgx4WGK0oNU',
2485 '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}',
2486 'ext': 'mp4',
2487 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2488 'availability': 'public',
2489 'age_limit': 0,
2490 'release_timestamp': 1637975704,
2491 'upload_date': '20210619',
2492 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2493 'live_status': 'is_live',
2494 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2495 'channel': 'Abao in Tokyo',
2496 'channel_follower_count': int,
2497 'release_date': '20211127',
2498 'tags': 'count:39',
2499 'categories': ['People & Blogs'],
2500 'like_count': int,
992f9a73 2501 'view_count': int,
2502 'playable_in_embed': True,
2503 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2504 'concurrent_view_count': int,
7666b936 2505 'uploader': 'Abao in Tokyo',
2506 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2507 'uploader_id': '@abaointokyo',
992f9a73 2508 },
2509 'params': {'skip_download': True}
ee27297f 2510 }, {
2511 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2512 'info_dict': {
2513 'id': 'tjjjtzRLHvA',
2514 'ext': 'mp4',
2515 'title': 'ハッシュタグ無し };if window.ytcsi',
2516 'upload_date': '20220323',
2517 'like_count': int,
2518 'availability': 'unlisted',
7666b936 2519 'channel': 'Lesmiscore',
2520 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2521 'age_limit': 0,
ee27297f 2522 'categories': ['Music'],
6e634cbe 2523 'view_count': int,
2524 'description': '',
ee27297f 2525 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2526 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2527 'live_status': 'not_live',
2528 'playable_in_embed': True,
2529 'channel_follower_count': int,
2530 'duration': 6,
2531 'tags': [],
7666b936 2532 'uploader_id': '@lesmiscore',
2533 'uploader': 'Lesmiscore',
2534 'uploader_url': 'https://www.youtube.com/@lesmiscore',
6e634cbe 2535 }
c26f9b99 2536 }, {
2537 # Prefer primary title+description language metadata by default
2538 # Do not prefer translated description if primary is empty
2539 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2540 'info_dict': {
2541 'id': 'el3E4MbxRqQ',
2542 'ext': 'mp4',
2543 'title': 'dlp test video 2 - primary sv no desc',
2544 'description': '',
2545 'channel': 'cole-dlp-test-acc',
2546 'tags': [],
2547 'view_count': int,
2548 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2549 'like_count': int,
2550 'playable_in_embed': True,
2551 'availability': 'unlisted',
7666b936 2552 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2553 'age_limit': 0,
2554 'duration': 5,
c26f9b99 2555 'live_status': 'not_live',
2556 'upload_date': '20220908',
2557 'categories': ['People & Blogs'],
c26f9b99 2558 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2559 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2560 'uploader_id': '@coletdjnz',
2561 'uploader': 'cole-dlp-test-acc',
c26f9b99 2562 },
2563 'params': {'skip_download': True}
2564 }, {
2565 # Extractor argument: prefer translated title+description
2566 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2567 'info_dict': {
2568 'id': 'gHKT4uU8Zng',
2569 'ext': 'mp4',
2570 'channel': 'cole-dlp-test-acc',
2571 'tags': [],
2572 'duration': 5,
2573 'live_status': 'not_live',
2574 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2575 'upload_date': '20220728',
c26f9b99 2576 'view_count': int,
2577 'categories': ['People & Blogs'],
7666b936 2578 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2579 'title': 'dlp test video title translated (fr)',
2580 'availability': 'public',
c26f9b99 2581 'age_limit': 0,
2582 'description': 'dlp test video description translated (fr)',
2583 'playable_in_embed': True,
2584 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2585 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2586 'uploader_id': '@coletdjnz',
2587 'uploader': 'cole-dlp-test-acc',
c26f9b99 2588 },
2589 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2590 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2591 }, {
2592 'note': '6 channel audio',
2593 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2594 'only_matching': True,
a4894d3e 2595 }, {
2596 'note': 'Multiple HLS formats with same itag',
2597 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2598 'info_dict': {
2599 'id': 'kX3nB4PpJko',
2600 'ext': 'mp4',
2601 'categories': ['Entertainment'],
2602 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
a4894d3e 2603 'live_status': 'not_live',
2604 'duration': 937,
2605 'channel_follower_count': int,
2606 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2607 'title': 'Last To Take Hand Off Jet, Keeps It!',
2608 'channel': 'MrBeast',
2609 'playable_in_embed': True,
2610 'view_count': int,
2611 'upload_date': '20221112',
a4894d3e 2612 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2613 'age_limit': 0,
2614 'availability': 'public',
2615 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2616 'like_count': int,
2617 'tags': [],
7666b936 2618 'uploader': 'MrBeast',
2619 'uploader_url': 'https://www.youtube.com/@MrBeast',
2620 'uploader_id': '@MrBeast',
14a14335 2621 'comment_count': int,
8213ce28 2622 'channel_is_verified': True,
14a14335 2623 'heatmap': 'count:100',
a4894d3e 2624 },
2625 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2626 }, {
2627 'note': 'Audio formats with Dynamic Range Compression',
2628 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2629 'info_dict': {
2630 'id': 'Tq92D6wQ1mg',
7666b936 2631 'ext': 'webm',
9bb85699 2632 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2633 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2634 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2635 'channel_follower_count': int,
2636 'description': 'md5:17eccca93a786d51bc67646756894066',
2637 'upload_date': '20191228',
9bb85699 2638 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2639 'playable_in_embed': True,
2640 'like_count': int,
2641 'categories': ['Entertainment'],
2642 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2643 'age_limit': 18,
2644 'channel': 'Projekt Melody',
9bb85699 2645 'view_count': int,
2646 'availability': 'needs_auth',
2647 'comment_count': int,
2648 'live_status': 'not_live',
9bb85699 2649 'duration': 106,
7666b936 2650 'uploader': 'Projekt Melody',
2651 'uploader_id': '@ProjektMelody',
2652 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 2653 },
2654 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2655 },
2656 {
2657 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2658 'info_dict': {
2659 'id': 'qVv6vCqciTM',
2660 'ext': 'mp4',
2661 'age_limit': 0,
dad2210c 2662 'comment_count': int,
2663 'chapters': 'count:13',
2664 'upload_date': '20221223',
2665 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2666 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2667 'like_count': int,
2668 'release_date': '20221223',
2669 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2670 '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】',
2671 'view_count': int,
2672 'playable_in_embed': True,
2673 'duration': 4438,
2674 'availability': 'public',
2675 'channel_follower_count': int,
2676 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2677 'categories': ['Entertainment'],
2678 'live_status': 'was_live',
2679 'release_timestamp': 1671793345,
2680 'channel': 'さなちゃんねる',
2681 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2682 'uploader': 'さなちゃんねる',
7666b936 2683 'uploader_url': 'https://www.youtube.com/@sana_natori',
2684 'uploader_id': '@sana_natori',
8213ce28 2685 'channel_is_verified': True,
14a14335 2686 'heatmap': 'count:100',
7666b936 2687 },
2688 },
2689 {
2690 # Fallbacks when webpage and web client is unavailable
2691 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2692 'info_dict': {
2693 'id': 'wSSmNUl9Snw',
2694 'ext': 'mp4',
2695 # 'categories': ['Science & Technology'],
2696 'view_count': int,
2697 'chapters': 'count:2',
2698 'channel': 'Scott Manley',
2699 'like_count': int,
2700 'age_limit': 0,
2701 # 'availability': 'public',
2702 'channel_follower_count': int,
2703 'live_status': 'not_live',
2704 'upload_date': '20170831',
2705 'duration': 682,
2706 'tags': 'count:8',
2707 'uploader_url': 'https://www.youtube.com/@scottmanley',
2708 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2709 'uploader': 'Scott Manley',
2710 'uploader_id': '@scottmanley',
2711 'title': 'The Computer Hack That Saved Apollo 14',
2712 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2713 'thumbnail': r're:^https?://.*\.webp',
2714 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2715 'playable_in_embed': True,
14a14335 2716 'comment_count': int,
8213ce28 2717 'channel_is_verified': True,
14a14335 2718 'heatmap': 'count:100',
7666b936 2719 },
2720 'params': {
2721 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2722 },
2723 },
2eb88d95
PH
2724 ]
2725
f2e8dbcc 2726 _WEBPAGE_TESTS = [
2727 # YouTube <object> embed
2728 {
2729 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2730 'md5': '873c81d308b979f0e23ee7e620b312a3',
2731 'info_dict': {
2732 'id': 'msN87y-iEx0',
2733 'ext': 'mp4',
2734 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2735 'upload_date': '20080526',
2736 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2737 'age_limit': 0,
2738 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2739 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2740 'playable_in_embed': True,
2741 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2742 'like_count': int,
2743 'comment_count': int,
2744 'channel': 'Christopher Sykes',
2745 'live_status': 'not_live',
2746 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2747 'availability': 'public',
2748 'duration': 195,
2749 'view_count': int,
2750 'categories': ['Science & Technology'],
2751 'channel_follower_count': int,
7666b936 2752 'uploader': 'Christopher Sykes',
2753 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2754 'uploader_id': '@ChristopherSykesDocumentaries',
14a14335 2755 'heatmap': 'count:100',
f2e8dbcc 2756 },
2757 'params': {
2758 'skip_download': True,
2759 }
2760 },
2761 ]
2762
201c1459 2763 @classmethod
2764 def suitable(cls, url):
4dfbf869 2765 from ..utils import parse_qs
2766
201c1459 2767 qs = parse_qs(url)
2768 if qs.get('list', [None])[0]:
2769 return False
86e5f3ed 2770 return super().suitable(url)
201c1459 2771
e0df6211 2772 def __init__(self, *args, **kwargs):
86e5f3ed 2773 super().__init__(*args, **kwargs)
545cc85d 2774 self._code_cache = {}
83799698 2775 self._player_cache = {}
e0df6211 2776
4d37720a 2777 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2778 lock = threading.Lock()
185bf310 2779 start_time = time.time()
adbc4ec4
THD
2780 formats = [f for f in formats if f.get('is_from_start')]
2781
185bf310 2782 def refetch_manifest(format_id, delay):
2783 nonlocal formats, start_time, is_live
2784 if time.time() <= start_time + delay:
adbc4ec4
THD
2785 return
2786
2787 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2788 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2789 microformats = traverse_obj(
2790 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2791 expected_type=dict)
4d37720a
L
2792 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2793 is_live = live_status == 'is_live'
185bf310 2794 start_time = time.time()
adbc4ec4 2795
185bf310 2796 def mpd_feed(format_id, delay):
adbc4ec4
THD
2797 """
2798 @returns (manifest_url, manifest_stream_number, is_live) or None
2799 """
253ac4ba 2800 for retry in self.RetryManager(fatal=False):
2801 with lock:
2802 refetch_manifest(format_id, delay)
2803
2804 f = next((f for f in formats if f['format_id'] == format_id), None)
2805 if not f:
2806 if not is_live:
2807 retry.error = f'{video_id}: Video is no longer live'
2808 else:
2809 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2810 continue
2811 return f['manifest_url'], f['manifest_stream_number'], is_live
2812 return None
adbc4ec4
THD
2813
2814 for f in formats:
4d37720a
L
2815 f['is_live'] = is_live
2816 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2817 live_start_time, mpd_feed, not is_live and f.copy())
2818 if is_live:
2819 f['fragments'] = gen
2820 f['protocol'] = 'http_dash_segments_generator'
2821 else:
2822 f['fragments'] = LazyList(gen({}))
2823 del f['is_from_start']
adbc4ec4 2824
4d37720a 2825 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2826 FETCH_SPAN, MAX_DURATION = 5, 432000
2827
2828 mpd_url, stream_number, is_live = None, None, True
2829
2830 begin_index = 0
2831 download_start_time = ctx.get('start') or time.time()
2832
2833 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2834 if lack_early_segments:
2835 self.report_warning(bug_reports_message(
2836 'Starting download from the last 120 hours of the live stream since '
2837 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2838 lack_early_segments = True
2839
2840 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2841 fragments, fragment_base_url = None, None
2842
a539f065 2843 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2844 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2845 # Obtain from MPD's maximum seq value
2846 old_mpd_url = mpd_url
185bf310 2847 last_error = ctx.pop('last_error', None)
3d2623a8 2848 expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
185bf310 2849 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2850 or (mpd_url, stream_number, False))
2851 if not refresh_sequence:
2852 if expire_fast and not is_live:
2853 return False, last_seq
2854 elif old_mpd_url == mpd_url:
2855 return True, last_seq
4d37720a
L
2856 if manifestless_orig_fmt:
2857 fmt_info = manifestless_orig_fmt
2858 else:
2859 try:
2860 fmts, _ = self._extract_mpd_formats_and_subtitles(
2861 mpd_url, None, note=False, errnote=False, fatal=False)
2862 except ExtractorError:
2863 fmts = None
2864 if not fmts:
2865 no_fragment_score += 2
2866 return False, last_seq
2867 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2868 fragments = fmt_info['fragments']
2869 fragment_base_url = fmt_info['fragment_base_url']
2870 assert fragment_base_url
2871
2872 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2873 return True, _last_seq
2874
4d37720a 2875 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2876 while is_live:
2877 fetch_time = time.time()
2878 if no_fragment_score > 30:
2879 return
2880 if last_segment_url:
2881 # Obtain from "X-Head-Seqnum" header value from each segment
2882 try:
2883 urlh = self._request_webpage(
2884 last_segment_url, None, note=False, errnote=False, fatal=False)
2885 except ExtractorError:
2886 urlh = None
2887 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2888 if last_seq is None:
a539f065 2889 no_fragment_score += 2
adbc4ec4
THD
2890 last_segment_url = None
2891 continue
2892 else:
a539f065
LNO
2893 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2894 no_fragment_score += 2
185bf310 2895 if not should_continue:
adbc4ec4
THD
2896 continue
2897
2898 if known_idx > last_seq:
2899 last_segment_url = None
2900 continue
2901
2902 last_seq += 1
2903
2904 if begin_index < 0 and known_idx < 0:
2905 # skip from the start when it's negative value
2906 known_idx = last_seq + begin_index
2907 if lack_early_segments:
2908 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2909 try:
2910 for idx in range(known_idx, last_seq):
2911 # do not update sequence here or you'll get skipped some part of it
a539f065 2912 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2913 if not should_continue:
adbc4ec4
THD
2914 known_idx = idx - 1
2915 raise ExtractorError('breaking out of outer loop')
2916 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2917 yield {
2918 'url': last_segment_url,
36195c44 2919 'fragment_count': last_seq,
adbc4ec4
THD
2920 }
2921 if known_idx == last_seq:
2922 no_fragment_score += 5
2923 else:
2924 no_fragment_score = 0
2925 known_idx = last_seq
2926 except ExtractorError:
2927 continue
2928
4d37720a
L
2929 if manifestless_orig_fmt:
2930 # Stop at the first iteration if running for post-live manifestless;
2931 # fragment count no longer increase since it starts
2932 break
2933
adbc4ec4
THD
2934 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2935
b6de707d 2936 def _extract_player_url(self, *ytcfgs, webpage=None):
2937 player_url = traverse_obj(
2938 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2939 get_all=False, expected_type=str)
11f9be09 2940 if not player_url:
b6de707d 2941 return
60f393e4 2942 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2943
b6de707d 2944 def _download_player_url(self, video_id, fatal=False):
2945 res = self._download_webpage(
2946 'https://www.youtube.com/iframe_api',
2947 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2948 if res:
2949 player_version = self._search_regex(
2950 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2951 if player_version:
2952 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2953
60064c53
PH
2954 def _signature_cache_id(self, example_sig):
2955 """ Return a string representation of a signature """
14f25df2 2956 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2957
e40c758c
S
2958 @classmethod
2959 def _extract_player_info(cls, player_url):
2960 for player_re in cls._PLAYER_INFO_RE:
2961 id_m = re.search(player_re, player_url)
2962 if id_m:
2963 break
2964 else:
c081b35c 2965 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2966 return id_m.group('id')
e40c758c 2967
404f611f 2968 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2969 player_id = self._extract_player_info(player_url)
2970 if player_id not in self._code_cache:
1276a43a 2971 code = self._download_webpage(
109dd3b2 2972 player_url, video_id, fatal=fatal,
2973 note='Downloading player ' + player_id,
2974 errnote='Download of %s failed' % player_url)
1276a43a 2975 if code:
2976 self._code_cache[player_id] = code
404f611f 2977 return self._code_cache.get(player_id)
109dd3b2 2978
e40c758c 2979 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2980 player_id = self._extract_player_info(player_url)
e0df6211 2981
c4417ddb 2982 # Read from filesystem cache
86e5f3ed 2983 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2984 assert os.path.basename(func_id) == func_id
a0e07d31 2985
ae61d108 2986 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2987 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2988
580ce007 2989 if not cache_spec:
2990 code = self._load_player(video_id, player_url)
404f611f 2991 if code:
109dd3b2 2992 res = self._parse_sig_js(code)
ac668111 2993 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2994 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2995 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2996
2997 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2998
60064c53 2999 def _print_sig_code(self, func, example_sig):
404f611f 3000 if not self.get_param('youtube_print_sig_code'):
3001 return
3002
edf3e38e
PH
3003 def gen_sig_code(idxs):
3004 def _genslice(start, end, step):
78caa52a 3005 starts = '' if start == 0 else str(start)
8bcc8756 3006 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 3007 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 3008 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
3009
3010 step = None
7af808a5
PH
3011 # Quelch pyflakes warnings - start will be set when step is set
3012 start = '(Never used)'
edf3e38e
PH
3013 for i, prev in zip(idxs[1:], idxs[:-1]):
3014 if step is not None:
3015 if i - prev == step:
3016 continue
3017 yield _genslice(start, prev, step)
3018 step = None
3019 continue
3020 if i - prev in [-1, 1]:
3021 step = i - prev
3022 start = prev
3023 continue
3024 else:
78caa52a 3025 yield 's[%d]' % prev
edf3e38e 3026 if step is None:
78caa52a 3027 yield 's[%d]' % i
edf3e38e
PH
3028 else:
3029 yield _genslice(start, i, step)
3030
ac668111 3031 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 3032 cache_res = func(test_string)
edf3e38e 3033 cache_spec = [ord(c) for c in cache_res]
78caa52a 3034 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 3035 signature_id_tuple = '(%s)' % (
14f25df2 3036 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 3037 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 3038 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 3039 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3040
e0df6211
PH
3041 def _parse_sig_js(self, jscode):
3042 funcname = self._search_regex(
abefc03f
S
3043 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3044 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
3045 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3046 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3047 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 3048 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3049 # Obsolete patterns
4823ec9f 3050 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3051 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3052 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3053 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3054 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3055 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3056 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3057
3058 jsi = JSInterpreter(jscode)
3059 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3060 return lambda s: initial_function([s])
3061
580ce007 3062 def _cached(self, func, *cache_id):
3063 def inner(*args, **kwargs):
3064 if cache_id not in self._player_cache:
3065 try:
3066 self._player_cache[cache_id] = func(*args, **kwargs)
3067 except ExtractorError as e:
3068 self._player_cache[cache_id] = e
3069 except Exception as e:
3070 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3071
3072 ret = self._player_cache[cache_id]
3073 if isinstance(ret, Exception):
3074 raise ret
3075 return ret
3076 return inner
3077
545cc85d 3078 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3079 """Turn the encrypted s field into a working signature"""
580ce007 3080 extract_sig = self._cached(
3081 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3082 func = extract_sig(video_id, player_url, s)
3083 self._print_sig_code(func, s)
3084 return func(s)
404f611f 3085
3086 def _decrypt_nsig(self, s, video_id, player_url):
3087 """Turn the encrypted n field into a working signature"""
3088 if player_url is None:
3089 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3090 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3091
b505e851 3092 try:
3093 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3094 except ExtractorError as e:
3095 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3096 if self.get_param('youtube_print_sig_code'):
3097 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3098
25836db6 3099 try:
3100 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3101 ret = extract_nsig(jsi, func_code)(s)
3102 except JSInterpreter.Exception as e:
3103 try:
992dc6b4 3104 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3105 except ExtractorError:
3106 raise e
3107 self.report_warning(
3108 f'Native nsig extraction failed: Trying with PhantomJS\n'
3109 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3110 self.write_debug(e, only_once=True)
25836db6 3111
3112 args, func_body = func_code
3113 ret = jsi.execute(
3114 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3115 video_id=video_id, note='Executing signature code').strip()
580ce007 3116
3117 self.write_debug(f'Decrypted nsig {s} => {ret}')
3118 return ret
3119
90a1df30 3120 def _extract_n_function_name(self, jscode):
3121 funcname, idx = self._search_regex(
3122 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3123 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3124 if not idx:
3125 return funcname
3126
3127 return json.loads(js_to_json(self._search_regex(
337734d4 3128 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
90a1df30 3129 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3130
580ce007 3131 def _extract_n_function_code(self, video_id, player_url):
404f611f 3132 player_id = self._extract_player_info(player_url)
05deb747 3133 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3134 jscode = func_code or self._load_player(video_id, player_url)
3135 jsi = JSInterpreter(jscode)
404f611f 3136
3137 if func_code:
580ce007 3138 return jsi, player_id, func_code
404f611f 3139
b505e851 3140 func_name = self._extract_n_function_name(jscode)
3141
3142 # For redundancy
3143 func_code = self._search_regex(
3144 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3145 # NB: The end of the regex is intentionally kept strict
3146 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3147 jscode, 'nsig function', group=('var', 'code'), default=None)
3148 if func_code:
3149 func_code = ([func_code[0]], func_code[1])
3150 else:
3151 self.write_debug('Extracting nsig function with jsinterp')
3152 func_code = jsi.extract_function_code(func_name)
3153
580ce007 3154 self.cache.store('youtube-nsig', player_id, func_code)
3155 return jsi, player_id, func_code
3156
3157 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3158 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3159
580ce007 3160 def extract_nsig(s):
25836db6 3161 try:
3162 ret = func([s])
3163 except JSInterpreter.Exception:
3164 raise
3165 except Exception as e:
3166 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3167
f6ca640b 3168 if ret.startswith('enhanced_except_'):
25836db6 3169 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3170 return ret
580ce007 3171
3172 return extract_nsig
e0df6211 3173
109dd3b2 3174 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3175 """
3176 Extract signatureTimestamp (sts)
3177 Required to tell API what sig/player version is in use.
3178 """
3179 sts = None
3180 if isinstance(ytcfg, dict):
3181 sts = int_or_none(ytcfg.get('STS'))
3182
3183 if not sts:
3184 # Attempt to extract from player
3185 if player_url is None:
3186 error_msg = 'Cannot extract signature timestamp without player_url.'
3187 if fatal:
3188 raise ExtractorError(error_msg)
3189 self.report_warning(error_msg)
3190 return
404f611f 3191 code = self._load_player(video_id, player_url, fatal=fatal)
3192 if code:
109dd3b2 3193 sts = int_or_none(self._search_regex(
3194 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3195 'JS player signature timestamp', group='sts', fatal=fatal))
3196 return sts
3197
11f9be09 3198 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3199 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3200 label = 'fully ' if is_full else ''
3201 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3202 expected_type=url_or_none)
3203 if not url:
3204 self.report_warning(f'Unable to mark {label}watched')
3205 return
14f25df2 3206 parsed_url = urllib.parse.urlparse(url)
3207 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3208
3209 # cpn generation algorithm is reverse engineered from base.js.
3210 # In fact it works even with dummy cpn.
3211 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3212 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3213
3214 # # more consistent results setting it to right before the end
3215 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3216
3217 qs.update({
3218 'ver': ['2'],
3219 'cpn': [cpn],
3220 'cmt': video_length,
3221 'el': 'detailpage', # otherwise defaults to "shorts"
3222 })
3223
3224 if is_full:
3225 # these seem to mark watchtime "history" in the real world
3226 # they're required, so send in a single value
3227 qs.update({
5318156f 3228 'st': 0,
06cc8f10
B
3229 'et': video_length,
3230 })
3231
14f25df2 3232 url = urllib.parse.urlunparse(
3233 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3234
3235 self._download_webpage(
3236 url, video_id, f'Marking {label}watched',
3237 'Unable to mark watched', fatal=False)
d77ab8e2 3238
bfd973ec 3239 @classmethod
3240 def _extract_from_webpage(cls, url, webpage):
3241 # Invidious Instances
3242 # https://github.com/yt-dlp/yt-dlp/issues/195
3243 # https://github.com/iv-org/invidious/pull/1730
3244 mobj = re.search(
3245 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3246 webpage)
3247 if mobj:
3248 yield cls.url_result(mobj.group('url'), cls)
3249 raise cls.StopExtraction()
3250
3251 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3252
3253 # lazyYT YouTube embed
bfd973ec 3254 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3255 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3256
3257 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3258 for m in re.findall(r'''(?x)<div[^>]+
3259 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3260 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3261 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3262
97665381
PH
3263 @classmethod
3264 def extract_id(cls, url):
ae61d108 3265 video_id = cls.get_temp_id(url)
3266 if not video_id:
3267 raise ExtractorError(f'Invalid URL: {url}')
3268 return video_id
c5e8d7af 3269
7c365c21 3270 def _extract_chapters_from_json(self, data, duration):
3271 chapter_list = traverse_obj(
3272 data, (
3273 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3274 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3275 ), expected_type=list)
3276
22ccd542 3277 return self._extract_chapters_helper(
7c365c21 3278 chapter_list,
22ccd542 3279 start_function=lambda chapter: float_or_none(
7c365c21 3280 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3281 title_function=lambda chapter: traverse_obj(
7c365c21 3282 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3283 duration=duration)
3284
3285 def _extract_chapters_from_engagement_panel(self, data, duration):
3286 content_list = traverse_obj(
8bdd16b4 3287 data,
7c365c21 3288 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3289 expected_type=list)
052e1350 3290 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3291 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3292
1890fc63 3293 return next(filter(None, (
22ccd542 3294 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3295 chapter_time, chapter_title, duration)
1890fc63 3296 for contents in content_list)), [])
7c365c21 3297
03e85ea9 3298 def _extract_heatmap(self, data):
3299 return traverse_obj(data, (
3300 'frameworkUpdates', 'entityBatchUpdate', 'mutations',
3301 lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
3302 'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
3303 'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
3304 'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
3305 'value': ('intensityScoreNormalized', {float_or_none}),
3306 })) or None
5caf30db 3307
a1c5d2ca
M
3308 def _extract_comment(self, comment_renderer, parent=None):
3309 comment_id = comment_renderer.get('commentId')
3310 if not comment_id:
3311 return
fe93e2c4 3312
c35448b7 3313 info = {
3314 'id': comment_id,
3315 'text': self._get_text(comment_renderer, 'contentText'),
3316 'like_count': self._get_count(comment_renderer, 'voteCount'),
3317 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3318 'author': self._get_text(comment_renderer, 'authorText'),
3319 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3320 'parent': parent or 'root',
3321 }
fe93e2c4 3322
c26f9b99 3323 # Timestamp is an estimate calculated from the current time and time_text
3324 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3325 timestamp = self._parse_time_text(time_text)
3326
c35448b7 3327 info.update({
3328 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3329 '_time_text': time_text,
3330 'timestamp': timestamp,
3331 })
fe93e2c4 3332
c35448b7 3333 info['author_url'] = urljoin(
3334 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3335 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3336 expected_type=str, get_all=False))
a1c5d2ca 3337
c35448b7 3338 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3339 if author_is_uploader is not None:
3340 info['author_is_uploader'] = author_is_uploader
3341
3342 comment_abr = traverse_obj(
89bed013 3343 comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
c35448b7 3344 if comment_abr is not None:
3345 info['is_favorited'] = 'creatorHeart' in comment_abr
3346
14a14335 3347 badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
3348 if self._has_badge(badges, BadgeType.VERIFIED):
3349 info['author_is_verified'] = True
c35448b7 3350
3351 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3352 if is_pinned:
3353 info['is_pinned'] = True
3354
3355 return info
a1c5d2ca 3356
46383212 3357 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3358
3359 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3360
3361 def extract_header(contents):
2d6659b9 3362 _continuation = None
3363 for content in contents:
46383212 3364 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3365 expected_comment_count = self._get_count(
3366 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3367
18f8fba7 3368 if expected_comment_count is not None:
46383212 3369 tracker['est_total'] = expected_comment_count
3370 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3371 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3372
3373 sort_menu_item = try_get(
3374 comments_header_renderer,
3375 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3376 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3377
3378 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3379 if not _continuation:
3380 continue
3381
46383212 3382 sort_text = str_or_none(sort_menu_item.get('title'))
3383 if not sort_text:
2d6659b9 3384 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3385 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3386 break
a2160aa4 3387 return _continuation
a1c5d2ca 3388
2d6659b9 3389 def extract_thread(contents):
a1c5d2ca 3390 if not parent:
46383212 3391 tracker['current_page_thread'] = 0
a1c5d2ca 3392 for content in contents:
46383212 3393 if not parent and tracker['total_parent_comments'] >= max_parents:
3394 yield
a1c5d2ca 3395 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3396 comment_renderer = get_first(
3397 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3398 expected_type=dict, default={})
a1c5d2ca 3399
a1c5d2ca
M
3400 comment = self._extract_comment(comment_renderer, parent)
3401 if not comment:
3402 continue
141a8dff 3403 comment_id = comment['id']
c35448b7 3404 if comment.get('is_pinned'):
141a8dff 3405 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3406 # Sometimes YouTube may break and give us infinite looping comments.
3407 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3408 if comment_id in tracker['seen_comment_ids']:
c35448b7 3409 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3410 # Pinned comments may appear a second time in newest first sort
3411 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3412 continue
4dc4d847 3413 self.report_warning(
3414 'Detected YouTube comments looping. Stopping comment extraction '
3415 f'{"for this thread" if parent else ""} as we probably cannot get any more.')
7f51861b 3416 yield
3417 else:
3418 tracker['seen_comment_ids'].add(comment['id'])
46383212 3419
3420 tracker['running_total'] += 1
3421 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3422 yield comment
46383212 3423
a1c5d2ca
M
3424 # Attempt to get the replies
3425 comment_replies_renderer = try_get(
3426 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3427
3428 if comment_replies_renderer:
46383212 3429 tracker['current_page_thread'] += 1
a1c5d2ca 3430 comment_entries_iter = self._comment_entries(
99e9e001 3431 comment_replies_renderer, ytcfg, video_id,
46383212 3432 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3433 yield from itertools.islice(comment_entries_iter, min(
3434 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3435
46383212 3436 # Keeps track of counts across recursive calls
3437 if not tracker:
3438 tracker = dict(
3439 running_total=0,
18f8fba7 3440 est_total=None,
46383212 3441 current_page_thread=0,
3442 total_parent_comments=0,
7f51861b 3443 total_reply_comments=0,
141a8dff 3444 seen_comment_ids=set(),
3445 pinned_comment_ids=set()
3446 )
46383212 3447
3448 # TODO: Deprecated
2d6659b9 3449 # YouTube comments have a max depth of 2
46383212 3450 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3451 if max_depth:
da4db748 3452 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3453 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3454 if max_depth == 1 and parent:
3455 return
a1c5d2ca 3456
46383212 3457 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3458 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3459
46383212 3460 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3461
46383212 3462 response = None
6e634cbe 3463 is_forced_continuation = False
2d6659b9 3464 is_first_continuation = parent is None
6e634cbe 3465 if is_first_continuation and not continuation:
3466 # Sometimes you can get comments by generating the continuation yourself,
3467 # even if YouTube initially reports them being disabled - e.g. stories comments.
3468 # Note: if the comment section is actually disabled, YouTube may return a response with
3469 # required check_get_keys missing. So we will disable that check initially in this case.
3470 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3471 is_forced_continuation = True
a1c5d2ca 3472
18f8fba7 3473 continuation_items_path = (
3474 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3475 for page_num in itertools.count(0):
3476 if not continuation:
3477 break
46383212 3478 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3479 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3480 if page_num == 0:
3481 if is_first_continuation:
3482 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3483 else:
2d6659b9 3484 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3485 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3486 else:
3487 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3488 ' ' if parent else '', ' replies' if parent else '',
3489 page_num, comment_prog_str)
18f8fba7 3490
3491 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3492 # Ignore check if YouTube says the comment count is 0.
3493 check_get_keys = None
3494 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3495 check_get_keys = [[*continuation_items_path, ..., (
3496 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3497 try:
3498 response = self._extract_response(
3499 item_id=None, query=continuation,
3500 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3501 check_get_keys=check_get_keys)
e72e48c5
M
3502 except ExtractorError as e:
3503 # Ignore incomplete data error for replies if retries didn't work.
3504 # This is to allow any other parent comments and comment threads to be downloaded.
3505 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
4dc4d847 3506 if 'incomplete data' in str(e).lower() and parent:
3507 if self.get_param('ignoreerrors') in (True, 'only_download'):
3508 self.report_warning(
3509 'Received incomplete data for a comment reply thread and retrying did not help. '
3510 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
3511 return
3512 else:
3513 raise ExtractorError(
3514 'Incomplete data received for comment reply thread. '
3515 'Pass --ignore-errors to ignore and allow rest of comments to download.',
3516 expected=True)
3517 raise
6e634cbe 3518 is_forced_continuation = False
2d6659b9 3519 continuation = None
18f8fba7 3520 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3521 if is_first_continuation:
3522 continuation = extract_header(continuation_items)
3523 is_first_continuation = False
2d6659b9 3524 if continuation:
a1c5d2ca 3525 break
46383212 3526 continue
a1c5d2ca 3527
46383212 3528 for entry in extract_thread(continuation_items):
3529 if not entry:
3530 return
3531 yield entry
3532 continuation = self._extract_continuation({'contents': continuation_items})
3533 if continuation:
2d6659b9 3534 break
a1c5d2ca 3535
6e634cbe 3536 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3537 if message and not parent and tracker['running_total'] == 0:
3538 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3539 raise self.CommentsDisabled
6e634cbe 3540
3541 @staticmethod
3542 def _generate_comment_continuation(video_id):
3543 """
3544 Generates initial comment section continuation token from given video id
3545 """
3546 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3547 return base64.b64encode(token.encode()).decode()
3548
a2160aa4 3549 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3550 """Entry for comment extraction"""
2d6659b9 3551 def _real_comment_extract(contents):
aae16f6e 3552 renderer = next((
3553 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3554 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3555 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3556
a2160aa4 3557 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3558 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3559
109dd3b2 3560 @staticmethod
99e9e001 3561 def _get_checkok_params():
3562 return {'contentCheckOk': True, 'racyCheckOk': True}
3563
3564 @classmethod
3565 def _generate_player_context(cls, sts=None):
109dd3b2 3566 context = {
3567 'html5Preference': 'HTML5_PREF_WANTS',
3568 }
3569 if sts is not None:
3570 context['signatureTimestamp'] = sts
3571 return {
3572 'playbackContext': {
3573 'contentPlaybackContext': context
a1a7907b 3574 },
99e9e001 3575 **cls._get_checkok_params()
109dd3b2 3576 }
3577
e7e94f2a
D
3578 @staticmethod
3579 def _is_agegated(player_response):
3580 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3581 return True
e7e94f2a 3582
6839ae1f 3583 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3584 AGE_GATE_REASONS = (
3585 'confirm your age', 'age-restricted', 'inappropriate', # reason
3586 'age_verification_required', 'age_check_required', # status
3587 )
3588 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3589
3590 @staticmethod
3591 def _is_unplayable(player_response):
3592 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3593
50ac0e54 3594 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3595
11f9be09 3596 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3597 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3598 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3599 headers = self.generate_api_headers(
99e9e001 3600 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3601
6e634cbe 3602 yt_query = {
3603 'videoId': video_id,
6e634cbe 3604 }
90db9a3c 3605 if _split_innertube_client(client)[0] == 'android':
ba06d77a 3606 yt_query['params'] = 'CgIQBg=='
3607
546b2c28 3608 pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 3609 if pp_arg:
3610 yt_query['params'] = pp_arg
50ac0e54 3611
11f9be09 3612 yt_query.update(self._generate_player_context(sts))
3613 return self._extract_response(
3614 item_id=video_id, ep='player', query=yt_query,
379e44ed 3615 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3616 default_client=client,
11f9be09 3617 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3618 ) or None
3619
11f9be09 3620 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3621 requested_clients = []
fd8fcf8f 3622 default = ['ios', 'android', 'web']
000c15a4 3623 allowed_clients = sorted(
86e5f3ed 3624 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3625 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3626 for client in self._configuration_arg('player_client'):
3627 if client in allowed_clients:
3628 requested_clients.append(client)
d0d012d4 3629 elif client == 'default':
3630 requested_clients.extend(default)
b4c055ba 3631 elif client == 'all':
3632 requested_clients.extend(allowed_clients)
3633 else:
3634 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3635 if not requested_clients:
d0d012d4 3636 requested_clients = default
cf7e015f 3637
11f9be09 3638 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3639 requested_clients.extend(
e7e94f2a 3640 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3641
11f9be09 3642 return orderedSet(requested_clients)
cf7e015f 3643
50ac0e54 3644 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3645 initial_pr = None
3646 if webpage:
b7c47b74 3647 initial_pr = self._search_json(
3648 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3649
ae729626 3650 all_clients = set(clients)
c0bc527b 3651 clients = clients[::-1]
b6de707d 3652 prs = []
e7e94f2a 3653
ae729626 3654 def append_client(*client_names):
e7870111 3655 """ Append the first client name that exists but not already used """
ae729626 3656 for client_name in client_names:
e7870111
D
3657 actual_client = _split_innertube_client(client_name)[0]
3658 if actual_client in INNERTUBE_CLIENTS:
3659 if actual_client not in all_clients:
ae729626 3660 clients.append(client_name)
e7870111
D
3661 all_clients.add(actual_client)
3662 return
e7e94f2a 3663
379e44ed 3664 # Android player_response does not have microFormats which are needed for
3665 # extraction of some data. So we return the initial_pr with formats
3666 # stripped out even if not requested by the user
3667 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3668 if initial_pr:
3669 pr = dict(initial_pr)
3670 pr['streamingData'] = None
b6de707d 3671 prs.append(pr)
379e44ed 3672
3673 last_error = None
b6de707d 3674 tried_iframe_fallback = False
3675 player_url = None
c0bc527b 3676 while clients:
e7870111 3677 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3678 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3679 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3680 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3681
b6de707d 3682 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3683 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3684 if 'js' in self._configuration_arg('player_skip'):
3685 require_js_player = False
3686 player_url = None
3687
3688 if not player_url and not tried_iframe_fallback and require_js_player:
3689 player_url = self._download_player_url(video_id)
3690 tried_iframe_fallback = True
3691
379e44ed 3692 try:
3693 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3694 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3695 except ExtractorError as e:
3696 if last_error:
3697 self.report_warning(last_error)
3698 last_error = e
3699 continue
3700
11f9be09 3701 if pr:
a3e96421 3702 # YouTube may return a different video player response than expected.
3703 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3704 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3705 if pr_video_id and pr_video_id != video_id:
3706 self.report_warning(
c7dcf0b3 3707 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3708 else:
c795c39f
L
3709 # Save client name for introspection later
3710 name = short_client_name(client)
3711 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3712 sd[STREAMING_DATA_CLIENT_NAME] = name
3713 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3714 f[STREAMING_DATA_CLIENT_NAME] = name
a3e96421 3715 prs.append(pr)
c0bc527b 3716
e7e94f2a 3717 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3718 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3719 append_client(f'{base_client}_creator')
e7e94f2a 3720 elif self._is_agegated(pr):
e7870111
D
3721 if variant == 'tv_embedded':
3722 append_client(f'{base_client}_embedded')
3723 elif not variant:
3724 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3725
379e44ed 3726 if last_error:
b6de707d 3727 if not len(prs):
379e44ed 3728 raise last_error
3729 self.report_warning(last_error)
b6de707d 3730 return prs, player_url
11f9be09 3731
4d37720a
L
3732 def _needs_live_processing(self, live_status, duration):
3733 if (live_status == 'is_live' and self.get_param('live_from_start')
d949c10c 3734 or live_status == 'post_live' and (duration or 0) > 2 * 3600):
4d37720a
L
3735 return live_status
3736
3737 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3738 CHUNK_SIZE = 10 << 20
a4894d3e 3739 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3740 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3741 q = qualities([
2a9c6dcd 3742 # Normally tiny is the smallest video-only formats. But
3743 # audio-only formats with unknown quality may get tagged as tiny
3744 'tiny',
3745 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3746 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3747 ])
6839ae1f 3748 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
58786a10 3749 format_types = self._configuration_arg('formats')
3750 all_formats = 'duplicate' in format_types
3751 if self._configuration_arg('include_duplicate_formats'):
3752 all_formats = True
3753 self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
3754 'Use formats=duplicate extractor argument instead')
9297939e 3755
e389d172 3756 def build_fragments(f):
3757 return LazyList({
3758 'url': update_url_query(f['url'], {
3759 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3760 })
3761 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3762
545cc85d 3763 for fmt in streaming_formats:
727029c5 3764 if fmt.get('targetDurationSec'):
545cc85d 3765 continue
321bf820 3766
cc2db878 3767 itag = str_or_none(fmt.get('itag'))
9297939e 3768 audio_track = fmt.get('audioTrack') or {}
9bb85699 3769 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3770 if not all_formats:
3771 if stream_id in stream_ids:
3772 continue
9297939e 3773
cc2db878 3774 quality = fmt.get('quality')
2a9c6dcd 3775 height = int_or_none(fmt.get('height'))
d3fc8074 3776 if quality == 'tiny' or not quality:
3777 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3778 # The 3gp format (17) in android client has a quality of "small",
3779 # but is actually worse than other formats
3780 if itag == '17':
3781 quality = 'tiny'
3782 if quality:
3783 if itag:
3784 itag_qualities[itag] = quality
3785 if height:
3786 res_qualities[height] = quality
cc2db878 3787 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3788 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3789 # number of fragment that would subsequently requested with (`&sq=N`)
3790 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3791 continue
3792
545cc85d 3793 fmt_url = fmt.get('url')
3794 if not fmt_url:
14f25df2 3795 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3796 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3797 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3798 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3799 continue
52023f12 3800 try:
3801 fmt_url += '&%s=%s' % (
3802 traverse_obj(sc, ('sp', -1)) or 'signature',
3803 self._decrypt_signature(encrypted_sig, video_id, player_url)
3804 )
3805 except ExtractorError as e:
580ce007 3806 self.report_warning('Signature extraction failed: Some formats may be missing',
3807 video_id=video_id, only_once=True)
52023f12 3808 self.write_debug(e, only_once=True)
201e9eaa 3809 continue
545cc85d 3810
404f611f 3811 query = parse_qs(fmt_url)
3812 throttled = False
b2916526 3813 if query.get('n'):
404f611f 3814 try:
580ce007 3815 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3816 fmt_url = update_url_query(fmt_url, {
580ce007 3817 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3818 })
404f611f 3819 except ExtractorError as e:
25836db6 3820 phantomjs_hint = ''
3821 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3822 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3823 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3824 if player_url:
3825 self.report_warning(
3826 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3827 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3828 self.write_debug(e, only_once=True)
3829 else:
3830 self.report_warning(
3831 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3832 video_id=video_id, only_once=True)
404f611f 3833 throttled = True
3834
0ad92dfb 3835 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3836 language_preference = (
3837 10 if audio_track.get('audioIsDefault') and 10
3838 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3839 else -1)
0ad92dfb 3840 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3841 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3842 # Make sure to avoid false positives with small duration differences.
62b58c09 3843 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3844 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3845 if is_damaged:
0f06bcd7 3846 self.report_warning(
3847 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3848
3849 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
51a07b0d 3850 name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
97afb093 3851 fps = int_or_none(fmt.get('fps')) or 0
545cc85d 3852 dct = {
3853 'asr': int_or_none(fmt.get('audioSampleRate')),
3854 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3855 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3856 'format_note': join_nonempty(
392389b7 3857 join_nonempty(audio_track.get('displayName'),
3858 language_preference > 0 and ' (default)', delim=''),
51a07b0d 3859 name, fmt.get('isDrc') and 'DRC',
a4166234 3860 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3861 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3862 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3863 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3864 delim=', '),
91e5e839 3865 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
51a07b0d 3866 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
3867 + (100 if 'Premium' in name else 0)),
97afb093 3868 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
a4166234 3869 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3870 'height': height,
9bb85699 3871 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3872 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3873 'tbr': tbr,
545cc85d 3874 'url': fmt_url,
2a9c6dcd 3875 'width': int_or_none(fmt.get('width')),
ab6df717 3876 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3877 'desc' if language_preference < -1 else '') or None,
ab6df717 3878 'language_preference': language_preference,
a405b38f 3879 # Strictly de-prioritize damaged and 3gp formats
3880 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3881 }
60bdb7bd 3882 mime_mobj = re.match(
3883 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3884 if mime_mobj:
3885 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3886 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3887 if itag:
3888 itags[itag].add(('https', dct.get('language')))
3889 stream_ids.append(stream_id)
c9abebb8 3890 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3891 if single_stream and dct.get('ext'):
3892 dct['container'] = dct['ext'] + '_dash'
86cb9221 3893
58786a10 3894 if (all_formats or 'dashy' in format_types) and dct['filesize']:
86cb9221 3895 yield {
3896 **dct,
3897 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3898 'protocol': 'http_dash_segments',
e389d172 3899 'fragments': build_fragments(dct),
86cb9221 3900 }
58786a10 3901 if all_formats or 'dashy' not in format_types:
3902 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3903 yield dct
545cc85d 3904
4d37720a 3905 needs_live_processing = self._needs_live_processing(live_status, duration)
58786a10 3906 skip_bad_formats = 'incomplete' not in format_types
3907 if self._configuration_arg('include_incomplete_formats'):
3908 skip_bad_formats = False
3909 self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
3910 'Use formats=incomplete extractor argument instead')
4d37720a
L
3911
3912 skip_manifests = set(self._configuration_arg('skip'))
3913 if (not self.get_param('youtube_include_hls_manifest', True)
3914 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3915 or needs_live_processing and skip_bad_formats):
3916 skip_manifests.add('hls')
3917
0f06bcd7 3918 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3919 skip_manifests.add('dash')
3920 if self._configuration_arg('include_live_dash'):
3921 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
58786a10 3922 'Use formats=incomplete extractor argument instead')
4d37720a
L
3923 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3924 skip_manifests.add('dash')
5d3a0e79 3925
c795c39f 3926 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3927 key = (proto, f.get('language'))
86cb9221 3928 if not all_formats and key in itags[itag]:
a4894d3e 3929 return False
3930 itags[itag].add(key)
3931
86cb9221 3932 if itag and all_formats:
3933 f['format_id'] = f'{itag}-{proto}'
3934 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3935 f['format_id'] = f'{itag}-{proto}'
3936 elif itag:
a0bb6ce5 3937 f['format_id'] = itag
a0bb6ce5 3938
94ed638a 3939 if f.get('source_preference') is None:
3940 f['source_preference'] = -1
3941
1e75d97d 3942 if itag in ('616', '235'):
3943 f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
94ed638a 3944 f['source_preference'] += 100
1e75d97d 3945
b25cac65 3946 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3947 if f['quality'] == -1 and f.get('height'):
3948 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
ad54c913 3949 if self.get_param('verbose') or all_formats:
c795c39f 3950 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
97afb093 3951 if f.get('fps') and f['fps'] <= 1:
3952 del f['fps']
94ed638a 3953
3954 if proto == 'hls' and f.get('has_drm'):
3955 f['has_drm'] = 'maybe'
3956 f['source_preference'] -= 5
a0bb6ce5 3957 return True
2a9c6dcd 3958
c646d76f 3959 subtitles = {}
11f9be09 3960 for sd in streaming_data:
c795c39f
L
3961 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3962
4d37720a 3963 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3964 if hls_manifest_url:
4d37720a
L
3965 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3966 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3967 subtitles = self._merge_subtitles(subs, subtitles)
3968 for f in fmts:
c795c39f 3969 if process_manifest_format(f, 'hls', client_name, self._search_regex(
a0bb6ce5 3970 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3971 yield f
545cc85d 3972
4d37720a 3973 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3974 if dash_manifest_url:
c646d76f 3975 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3976 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3977 for f in formats:
c795c39f 3978 if process_manifest_format(f, 'dash', client_name, f['format_id']):
a0bb6ce5 3979 f['filesize'] = int_or_none(self._search_regex(
3980 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3981 if needs_live_processing:
adbc4ec4
THD
3982 f['is_from_start'] = True
3983
a0bb6ce5 3984 yield f
c646d76f 3985 yield subtitles
11f9be09 3986
720c3099 3987 def _extract_storyboard(self, player_responses, duration):
3988 spec = get_first(
3989 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3990 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3991 if not base_url:
720c3099 3992 return
720c3099 3993 L = len(spec) - 1
3994 for i, args in enumerate(spec):
3995 args = args.split('#')
3996 counts = list(map(int_or_none, args[:5]))
3997 if len(args) != 8 or not all(counts):
3998 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3999 continue
4000 width, height, frame_count, cols, rows = counts
4001 N, sigh = args[6:]
4002
4003 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
4004 fragment_count = frame_count / (cols * rows)
4005 fragment_duration = duration / fragment_count
4006 yield {
4007 'format_id': f'sb{i}',
4008 'format_note': 'storyboard',
4009 'ext': 'mhtml',
4010 'protocol': 'mhtml',
4011 'acodec': 'none',
4012 'vcodec': 'none',
4013 'url': url,
4014 'width': width,
4015 'height': height,
45e8a04e 4016 'fps': frame_count / duration,
4017 'rows': rows,
4018 'columns': cols,
720c3099 4019 'fragments': [{
b3edc806 4020 'url': url.replace('$M', str(j)),
720c3099 4021 'duration': min(fragment_duration, duration - (j * fragment_duration)),
4022 } for j in range(math.ceil(fragment_count))],
4023 }
4024
adbc4ec4 4025 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 4026 webpage = None
4027 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 4028 query = {'bpctr': '9999999999', 'has_verified': '1'}
546b2c28 4029 pp = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 4030 if pp:
4031 query['pp'] = pp
b6de707d 4032 webpage = self._download_webpage(
50ac0e54 4033 webpage_url, video_id, fatal=False, query=query)
11f9be09 4034
4035 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 4036
b6de707d 4037 player_responses, player_url = self._extract_player_responses(
11f9be09 4038 self._get_requested_clients(url, smuggled_data),
50ac0e54 4039 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 4040
adbc4ec4
THD
4041 return webpage, master_ytcfg, player_responses, player_url
4042
a1b2d843 4043 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
4044 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
4045 is_live = get_first(video_details, 'isLive')
4046 if is_live is None:
4047 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
4048 live_content = get_first(video_details, 'isLiveContent')
4049 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
4050 post_live = get_first(video_details, 'isPostLiveDvr')
4051 live_status = ('post_live' if post_live
4052 else 'is_live' if is_live
4053 else 'is_upcoming' if is_upcoming
6678a4f0 4054 else 'was_live' if live_content
4055 else 'not_live' if False in (is_live, live_content)
4056 else None)
6839ae1f 4057 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 4058 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
94ed638a 4059 if all(f.get('has_drm') for f in formats):
4060 # If there are no formats that definitely don't have DRM, all have DRM
4061 for f in formats:
4062 f['has_drm'] = True
adbc4ec4 4063
4d37720a 4064 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
4065
4066 def _real_extract(self, url):
4067 url, smuggled_data = unsmuggle_url(url, {})
4068 video_id = self._match_id(url)
4069
4070 base_url = self.http_scheme() + '//www.youtube.com/'
4071 webpage_url = base_url + 'watch?v=' + video_id
4072
4073 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
4074
11f9be09 4075 playability_statuses = traverse_obj(
6839ae1f 4076 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 4077
4078 trailer_video_id = get_first(
4079 playability_statuses,
4080 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4081 expected_type=str)
4082 if trailer_video_id:
4083 return self.url_result(
4084 trailer_video_id, self.ie_key(), trailer_video_id)
4085
4086 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4087 if webpage else (lambda x: None))
4088
6839ae1f 4089 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4090 microformats = traverse_obj(
4091 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4092 expected_type=dict)
c26f9b99 4093
4094 translated_title = self._get_text(microformats, (..., 'title'))
4095 video_title = (self._preferred_lang and translated_title
4096 or get_first(video_details, 'title') # primary
4097 or translated_title
4098 or search_meta(['og:title', 'twitter:title', 'title']))
4099 translated_description = self._get_text(microformats, (..., 'description'))
4100 original_description = get_first(video_details, 'shortDescription')
4101 video_description = (
4102 self._preferred_lang and translated_description
4103 # If original description is blank, it will be an empty string.
4104 # Do not prefer translated description in this case.
4105 or original_description if original_description is not None else translated_description)
11f9be09 4106
d89257f3 4107 multifeed_metadata_list = get_first(
4108 player_responses,
4109 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4110 expected_type=str)
4111 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4112 if self.get_param('noplaylist'):
11f9be09 4113 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4114 else:
4115 entries = []
4116 feed_ids = []
4117 for feed in multifeed_metadata_list.split(','):
4118 # Unquote should take place before split on comma (,) since textual
4119 # fields may contain comma as well (see
4120 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4121 feed_data = urllib.parse.parse_qs(
ac668111 4122 urllib.parse.unquote_plus(feed))
d89257f3 4123
4124 def feed_entry(name):
4125 return try_get(
14f25df2 4126 feed_data, lambda x: x[name][0], str)
d89257f3 4127
4128 feed_id = feed_entry('id')
4129 if not feed_id:
4130 continue
4131 feed_title = feed_entry('title')
4132 title = video_title
4133 if feed_title:
4134 title += ' (%s)' % feed_title
4135 entries.append({
4136 '_type': 'url_transparent',
4137 'ie_key': 'Youtube',
4138 'url': smuggle_url(
4139 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4140 {'force_singlefeed': True}),
4141 'title': title,
4142 })
4143 feed_ids.append(feed_id)
4144 self.to_screen(
4145 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4146 % (', '.join(feed_ids), video_id))
4147 return self.playlist_result(
4148 entries, video_id, video_title, video_description)
11f9be09 4149
9da6612b 4150 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4151 or int_or_none(get_first(microformats, 'lengthSeconds'))
4152 or parse_duration(search_meta('duration')) or None)
a1b2d843 4153
4d37720a
L
4154 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4155 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4156 if live_status == 'post_live':
4157 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4158
545cc85d 4159 if not formats:
11f9be09 4160 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4161 self.report_drm(video_id)
11f9be09 4162 pemr = get_first(
4163 playability_statuses,
4164 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4165 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4166 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4167 if subreason:
545cc85d 4168 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4169 countries = get_first(microformats, 'availableCountries')
545cc85d 4170 if not countries:
4171 regions_allowed = search_meta('regionsAllowed')
4172 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4173 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4174 reason += f'. {subreason}'
545cc85d 4175 if reason:
b7da73eb 4176 self.raise_no_formats(reason, expected=True)
bf1317d2 4177
11f9be09 4178 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4179 if not keywords and webpage:
4180 keywords = [
4181 unescapeHTML(m.group('content'))
4182 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4183 for keyword in keywords:
4184 if keyword.startswith('yt:stretch='):
201c1459 4185 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4186 if mobj:
4187 # NB: float is intentional for forcing float division
4188 w, h = (float(v) for v in mobj.groups())
4189 if w > 0 and h > 0:
4190 ratio = w / h
4191 for f in formats:
4192 if f.get('vcodec') != 'none':
4193 f['stretched_ratio'] = ratio
4194 break
a709d873 4195 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4196 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4197 if thumbnail_url:
4198 thumbnails.append({
4199 'url': thumbnail_url,
ff2751ac 4200 })
fccf5021 4201 original_thumbnails = thumbnails.copy()
4202
0ba692ac 4203 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4204 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4205 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4206 thumbnail_names = [
962ffcf8 4207 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4208 # in resolution, these are not the custom thumbnail. So de-prioritize them
4209 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4210 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4211 ]
cca80fe6 4212 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4213 thumbnails.extend({
4214 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4215 video_id=video_id, name=name, ext=ext,
4d37720a 4216 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4217 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4218 for thumb in thumbnails:
cca80fe6 4219 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4220 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4221 self._remove_duplicate_formats(thumbnails)
fccf5021 4222 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4223
7ea65411 4224 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4225 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4226 get_first(video_details, 'channelId')
4227 or get_first(microformats, 'externalChannelId')
7666b936 4228 or search_meta('channelId')))
7ea65411 4229 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4230
adbc4ec4
THD
4231 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4232 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4233 if not duration and live_end_time and live_start_time:
4234 duration = live_end_time - live_start_time
4235
4d37720a
L
4236 needs_live_processing = self._needs_live_processing(live_status, duration)
4237
4238 def is_bad_format(fmt):
4239 if needs_live_processing and not fmt.get('is_from_start'):
4240 return True
4241 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4242 and fmt.get('protocol') == 'http_dash_segments'):
4243 return True
4244
4245 for fmt in filter(is_bad_format, formats):
4246 fmt['preference'] = (fmt.get('preference') or -1) - 10
d949c10c 4247 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
4d37720a
L
4248
4249 if needs_live_processing:
4250 self._prepare_live_from_start_formats(
4251 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4252
720c3099 4253 formats.extend(self._extract_storyboard(player_responses, duration))
4254
7666b936 4255 channel_handle = self.handle_from_url(owner_profile_url)
4256
545cc85d 4257 info = {
4258 'id': video_id,
39ca3b5c 4259 'title': video_title,
545cc85d 4260 'formats': formats,
4261 'thumbnails': thumbnails,
fccf5021 4262 # The best thumbnail that we are sure exists. Prevents unnecessary
4263 # URL checking if user don't care about getting the best possible thumbnail
4264 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4265 'description': video_description,
545cc85d 4266 'channel_id': channel_id,
7666b936 4267 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4268 'duration': duration,
4269 'view_count': int_or_none(
11f9be09 4270 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4271 or search_meta('interactionCount')),
11f9be09 4272 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4273 'age_limit': 18 if (
11f9be09 4274 get_first(microformats, 'isFamilySafe') is False
545cc85d 4275 or search_meta('isFamilyFriendly') == 'false'
4276 or search_meta('og:restrictions:age') == '18+') else 0,
4277 'webpage_url': webpage_url,
4278 'categories': [category] if category else None,
4279 'tags': keywords,
11f9be09 4280 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4281 'live_status': live_status,
adbc4ec4 4282 'release_timestamp': live_start_time,
9f14daf2 4283 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4284 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4285 }
b477fc13 4286
c646d76f 4287 subtitles = {}
3944e7af 4288 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4289 if pctr:
ecdc9049 4290 def get_lang_code(track):
4291 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4292 or track.get('languageCode'))
4293
4294 # Converted into dicts to remove duplicates
4295 captions = {
4296 get_lang_code(sub): sub
6839ae1f 4297 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4298 translation_languages = {
4299 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4300 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4301
774d79cc 4302 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4303 lang_subs = container.setdefault(lang_code, [])
545cc85d 4304 for fmt in self._SUBTITLE_FORMATS:
4305 query.update({
4306 'fmt': fmt,
4307 })
4308 lang_subs.append({
4309 'ext': fmt,
60f393e4 4310 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4311 'name': sub_name,
545cc85d 4312 })
7e72694b 4313
07b47084 4314 # NB: Constructing the full subtitle dictionary is slow
4315 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4316 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4317 for lang_code, caption_track in captions.items():
4318 base_url = caption_track.get('baseUrl')
1235d333 4319 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4320 if not base_url:
4321 continue
ecdc9049 4322 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4323 if caption_track.get('kind') != 'asr':
545cc85d 4324 if not lang_code:
4325 continue
4326 process_language(
ecdc9049 4327 subtitles, base_url, lang_code, lang_name, {})
4328 if not caption_track.get('isTranslatable'):
4329 continue
3944e7af 4330 for trans_code, trans_name in translation_languages.items():
4331 if not trans_code:
545cc85d 4332 continue
1235d333 4333 orig_trans_code = trans_code
71eb82d1 4334 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4335 if not get_translated_subs:
18e49408 4336 continue
ecdc9049 4337 trans_code += f'-{lang_code}'
a70635b8 4338 trans_name += format_field(lang_name, None, ' from %s')
1235d333 4339 if lang_code == f'a-{orig_trans_code}':
ff9b0e07 4340 # Set audio language based on original subtitles
4341 for f in formats:
4342 if f.get('acodec') != 'none' and not f.get('language'):
4343 f['language'] = orig_trans_code
4344 # Add an "-orig" label to the original language so that it can be distinguished.
4345 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 4346 process_language(
d49669ac 4347 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4348 # Setting tlang=lang returns damaged subtitles.
d49669ac 4349 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4350 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4351
4352 info['automatic_captions'] = automatic_captions
4353 info['subtitles'] = subtitles
7e72694b 4354
14f25df2 4355 parsed_url = urllib.parse.urlparse(url)
545cc85d 4356 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4357 query = urllib.parse.parse_qs(component)
545cc85d 4358 for k, v in query.items():
4359 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4360 d_k += '_time'
4361 if d_k not in info and k in s_ks:
4362 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4363
4364 # Youtube Music Auto-generated description
71dc18fa
BT
4365 if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
4366 # XXX: Causes catastrophic backtracking if description has "·"
4367 # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
4368 # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
4369 # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
1890fc63 4370 mobj = re.search(
4371 r'''(?xs)
71dc18fa
BT
4372 (?=(?P<track>[^\n·]+))(?P=track)·
4373 (?=(?P<artist>[^\n]+))(?P=artist)\n+
4374 (?=(?P<album>[^\n]+))(?P=album)\n
1890fc63 4375 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4376 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
71dc18fa
BT
4377 (.+?\nArtist\s*:\s*
4378 (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
4379 )?.+\nAuto-generated\ by\ YouTube\.\s*$
1890fc63 4380 ''', video_description)
822b9d9c 4381 if mobj:
822b9d9c
RA
4382 release_year = mobj.group('release_year')
4383 release_date = mobj.group('release_date')
4384 if release_date:
4385 release_date = release_date.replace('-', '')
4386 if not release_year:
545cc85d 4387 release_year = release_date[:4]
4388 info.update({
4389 'album': mobj.group('album'.strip()),
4390 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4391 'track': mobj.group('track').strip(),
4392 'release_date': release_date,
cc2db878 4393 'release_year': int_or_none(release_year),
545cc85d 4394 })
7e72694b 4395
545cc85d 4396 initial_data = None
4397 if webpage:
56ba69e4 4398 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4399 if not traverse_obj(initial_data, 'contents'):
4400 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4401 initial_data = None
545cc85d 4402 if not initial_data:
99e9e001 4403 query = {'videoId': video_id}
4404 query.update(self._get_checkok_params())
109dd3b2 4405 initial_data = self._extract_response(
4406 item_id=video_id, ep='next', fatal=False,
607510b9 4407 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4408 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4409 note='Downloading initial data API JSON')
545cc85d 4410
0df111a3 4411 info['comment_count'] = traverse_obj(initial_data, (
4412 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4413 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4414 ), (
4415 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4416 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4417 ), expected_type=self._get_count, get_all=False)
0df111a3 4418
19a03940 4419 try: # This will error if there is no livechat
c60ee3a2 4420 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4421 except (KeyError, IndexError, TypeError):
4422 pass
4423 else:
ecdc9049 4424 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4425 # url is needed to set cookies
4426 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4427 'video_id': video_id,
4428 'ext': 'json',
4d37720a
L
4429 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4430 else 'youtube_live_chat_replay'),
c60ee3a2 4431 }]
545cc85d 4432
4433 if initial_data:
7c365c21 4434 info['chapters'] = (
4435 self._extract_chapters_from_json(initial_data, duration)
4436 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4437 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4438 or None)
545cc85d 4439
03e85ea9 4440 info['heatmap'] = self._extract_heatmap(initial_data)
5caf30db 4441
17322130 4442 contents = traverse_obj(
4443 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4444 expected_type=list, default=[])
4445
4446 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4447 if vpir:
4448 stl = vpir.get('superTitleLink')
4449 if stl:
4450 stl = self._get_text(stl)
4451 if try_get(
4452 vpir,
4453 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4454 info['location'] = stl
4455 else:
affc4fef 4456 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4457 if mobj:
545cc85d 4458 info.update({
17322130 4459 'series': mobj.group(1),
4460 'season_number': int(mobj.group(2)),
4461 'episode_number': int(mobj.group(3)),
545cc85d 4462 })
17322130 4463 for tlb in (try_get(
4464 vpir,
4465 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4466 list) or []):
3ffb2f5b 4467 tbrs = variadic(
4468 traverse_obj(
6839ae1f
SS
4469 tlb, ('toggleButtonRenderer', ...),
4470 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4471 for tbr in tbrs:
4472 for getter, regex in [(
4473 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4474 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4475 lambda x: x['accessibility'],
4476 lambda x: x['accessibilityData']['accessibilityData'],
4477 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4478 label = (try_get(tbr, getter, dict) or {}).get('label')
4479 if label:
4480 mobj = re.match(regex, label)
4481 if mobj:
4482 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4483 break
17322130 4484 sbr_tooltip = try_get(
4485 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4486 if sbr_tooltip:
4487 like_count, dislike_count = sbr_tooltip.split(' / ')
4488 info.update({
4489 'like_count': str_to_int(like_count),
4490 'dislike_count': str_to_int(dislike_count),
4491 })
867c66ff
M
4492 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4493 if vcr:
4494 vc = self._get_count(vcr, 'viewCount')
4495 # Upcoming premieres with waiting count are treated as live here
4496 if vcr.get('isLive'):
4497 info['concurrent_view_count'] = vc
4498 elif info.get('view_count') is None:
4499 info['view_count'] = vc
4500
17322130 4501 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4502 if vsir:
4503 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4504 info.update({
4505 'channel': self._get_text(vor, 'title'),
4506 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4507
7666b936 4508 if not channel_handle:
4509 channel_handle = self.handle_from_url(
4510 traverse_obj(vor, (
4511 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4512 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4513 {str}), get_all=False))
4514
17322130 4515 rows = try_get(
4516 vsir,
4517 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4518 list) or []
4519 multiple_songs = False
4520 for row in rows:
4521 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4522 multiple_songs = True
4523 break
4524 for row in rows:
4525 mrr = row.get('metadataRowRenderer') or {}
4526 mrr_title = mrr.get('title')
4527 if not mrr_title:
4528 continue
4529 mrr_title = self._get_text(mrr, 'title')
4530 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4531 if mrr_title == 'License':
4532 info['license'] = mrr_contents_text
4533 elif not multiple_songs:
4534 if mrr_title == 'Album':
4535 info['album'] = mrr_contents_text
4536 elif mrr_title == 'Artist':
4537 info['artist'] = mrr_contents_text
4538 elif mrr_title == 'Song':
4539 info['track'] = mrr_contents_text
8213ce28 4540 owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
4541 if self._has_badge(owner_badges, BadgeType.VERIFIED):
4542 info['channel_is_verified'] = True
545cc85d 4543
7666b936 4544 info.update({
4545 'uploader': info.get('channel'),
4546 'uploader_id': channel_handle,
4547 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4548 })
17322130 4549 # The upload date for scheduled, live and past live streams / premieres in microformats
4550 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4551 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4552 upload_date = (
4553 unified_strdate(get_first(microformats, 'uploadDate'))
4554 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4555 if not upload_date or (
4d37720a 4556 live_status in ('not_live', None)
1ff88b7a 4557 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4558 ):
c26f9b99 4559 upload_date = strftime_or_none(
ad54c913 4560 self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
17322130 4561 info['upload_date'] = upload_date
992f9a73 4562
ef79d20d 4563 if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
4564 # Newly uploaded videos' HLS formats are potentially problematic and need to be checked
4565 upload_datetime = datetime_from_str(upload_date).replace(tzinfo=datetime.timezone.utc)
4566 if upload_datetime >= datetime_from_str('today-1day'):
4567 for fmt in info['formats']:
4568 if fmt.get('protocol') == 'm3u8_native':
4569 fmt['__needs_testing'] = True
4570
545cc85d 4571 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4572 v = info.get(s_k)
4573 if v:
4574 info[d_k] = v
b84071c0 4575
14a14335 4576 badges = self._extract_badges(traverse_obj(vpir, 'badges'))
c26f9b99 4577
4578 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4579 or get_first(video_details, 'isPrivate', expected_type=bool))
4580
4581 info['availability'] = (
4582 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4583 else self._availability(
4584 is_private=is_private,
4585 needs_premium=(
4586 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4587 or False if initial_data and is_private is not None else None),
4588 needs_subscription=(
4589 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4590 or False if initial_data and is_private is not None else None),
4591 needs_auth=info['age_limit'] >= 18,
4592 is_unlisted=None if is_private is None else (
4593 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4594 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4595
a2160aa4 4596 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4597
11f9be09 4598 self.mark_watched(video_id, player_responses)
d77ab8e2 4599
545cc85d 4600 return info
c5e8d7af 4601
a61fd4cf 4602
a6213a49 4603class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4604 @staticmethod
4605 def passthrough_smuggled_data(func):
bd7e919a 4606 def _smuggle(info, smuggled_data):
4607 if info.get('_type') not in ('url', 'url_transparent'):
4608 return info
4609 if smuggled_data.get('is_music_url'):
4610 parsed_url = urllib.parse.urlparse(info['url'])
4611 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4612 smuggled_data.pop('is_music_url')
4613 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4614 if smuggled_data:
4615 info['url'] = smuggle_url(info['url'], smuggled_data)
4616 return info
182bda88 4617
4618 @functools.wraps(func)
4619 def wrapper(self, url):
4620 url, smuggled_data = unsmuggle_url(url, {})
4621 if self.is_music_url(url):
4622 smuggled_data['is_music_url'] = True
4623 info_dict = func(self, url, smuggled_data)
bd7e919a 4624 if smuggled_data:
4625 _smuggle(info_dict, smuggled_data)
4626 if info_dict.get('entries'):
a8c754cc 4627 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4628 return info_dict
4629 return wrapper
4630
8bdd16b4 4631 @staticmethod
cd7c66cf 4632 def _extract_basic_item_renderer(item):
4633 # Modified from _extract_grid_item_renderer
201c1459 4634 known_basic_renderers = (
a17526e4 4635 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4636 )
4637 for key, renderer in item.items():
201c1459 4638 if not isinstance(renderer, dict):
cd7c66cf 4639 continue
201c1459 4640 elif key in known_basic_renderers:
4641 return renderer
4642 elif key.startswith('grid') and key.endswith('Renderer'):
4643 return renderer
8bdd16b4 4644
c7335551 4645 def _extract_channel_renderer(self, renderer):
7666b936 4646 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4647 title = self._get_text(renderer, 'title')
7666b936 4648 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
7666b936 4649 channel_handle = self.handle_from_url(
4650 traverse_obj(renderer, (
4651 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4652 ('browseEndpoint', 'canonicalBaseUrl')),
4653 {str}), get_all=False))
14a14335 4654 if not channel_handle:
4655 # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
4656 channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
c7335551
M
4657 return {
4658 '_type': 'url',
4659 'url': channel_url,
4660 'id': channel_id,
4661 'ie_key': YoutubeTabIE.ie_key(),
4662 'channel': title,
7666b936 4663 'uploader': title,
c7335551
M
4664 'channel_id': channel_id,
4665 'channel_url': channel_url,
4666 'title': title,
7666b936 4667 'uploader_id': channel_handle,
4668 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
14a14335 4669 # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
4670 # However, in feed/channels this is set correctly to the subscriber count
4671 'channel_follower_count': traverse_obj(
4672 renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
c7335551 4673 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
14a14335 4674 'playlist_count': (
4675 # videoCountText may be the subscriber count
4676 self._get_count(renderer, 'videoCountText')
4677 if self._get_count(renderer, 'subscriberCountText') is not None else None),
c7335551 4678 'description': self._get_text(renderer, 'descriptionSnippet'),
8213ce28 4679 'channel_is_verified': True if self._has_badge(
4680 self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
c7335551
M
4681 }
4682
8bdd16b4 4683 def _grid_entries(self, grid_renderer):
4684 for item in grid_renderer['items']:
4685 if not isinstance(item, dict):
39b62db1 4686 continue
cd7c66cf 4687 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4688 if not isinstance(renderer, dict):
4689 continue
052e1350 4690 title = self._get_text(renderer, 'title')
fe93e2c4 4691
8bdd16b4 4692 # playlist
4693 playlist_id = renderer.get('playlistId')
4694 if playlist_id:
4695 yield self.url_result(
4696 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4697 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4698 video_title=title)
201c1459 4699 continue
8bdd16b4 4700 # video
4701 video_id = renderer.get('videoId')
4702 if video_id:
4703 yield self._extract_video(renderer)
201c1459 4704 continue
8bdd16b4 4705 # channel
4706 channel_id = renderer.get('channelId')
4707 if channel_id:
c7335551 4708 yield self._extract_channel_renderer(renderer)
201c1459 4709 continue
4710 # generic endpoint URL support
4711 ep_url = urljoin('https://www.youtube.com/', try_get(
4712 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4713 str))
201c1459 4714 if ep_url:
4715 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4716 if ie.suitable(ep_url):
4717 yield self.url_result(
4718 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4719 break
8bdd16b4 4720
16aa9ea4 4721 def _music_reponsive_list_entry(self, renderer):
4722 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4723 if video_id:
69a40e4a 4724 title = traverse_obj(renderer, (
4725 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4726 'text', 'runs', 0, 'text'))
16aa9ea4 4727 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4728 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4729 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4730 if playlist_id:
4731 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4732 if video_id:
4733 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4734 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4735 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4736 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4737 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4738 if browse_id:
4739 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4740 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4741
3d3dddc9 4742 def _shelf_entries_from_content(self, shelf_renderer):
4743 content = shelf_renderer.get('content')
4744 if not isinstance(content, dict):
8bdd16b4 4745 return
cd7c66cf 4746 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4747 if renderer:
4748 # TODO: add support for nested playlists so each shelf is processed
4749 # as separate playlist
4750 # TODO: this includes only first N items
86e5f3ed 4751 yield from self._grid_entries(renderer)
3d3dddc9 4752 renderer = content.get('horizontalListRenderer')
4753 if renderer:
4754 # TODO
4755 pass
8bdd16b4 4756
29f7c58a 4757 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4758 ep = try_get(
4759 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4760 str)
8bdd16b4 4761 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4762 if shelf_url:
29f7c58a 4763 # Skipping links to another channels, note that checking for
4764 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4765 # will not work
4766 if skip_channels and '/channels?' in shelf_url:
4767 return
052e1350 4768 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4769 yield self.url_result(shelf_url, video_title=title)
4770 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4771 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4772
8bdd16b4 4773 def _playlist_entries(self, video_list_renderer):
4774 for content in video_list_renderer['contents']:
4775 if not isinstance(content, dict):
4776 continue
4777 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4778 if not isinstance(renderer, dict):
4779 continue
4780 video_id = renderer.get('videoId')
4781 if not video_id:
4782 continue
4783 yield self._extract_video(renderer)
07aeced6 4784
3462ffa8 4785 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4786 renderer = traverse_obj(
447afb9e 4787 rich_grid_renderer,
4788 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4789 video_id = renderer.get('videoId')
447afb9e 4790 if video_id:
4791 yield self._extract_video(renderer)
4792 return
4793 playlist_id = renderer.get('playlistId')
4794 if playlist_id:
4795 yield self.url_result(
4796 f'https://www.youtube.com/playlist?list={playlist_id}',
4797 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4798 video_title=self._get_text(renderer, 'title'))
3462ffa8 4799 return
3462ffa8 4800
8bdd16b4 4801 def _video_entry(self, video_renderer):
4802 video_id = video_renderer.get('videoId')
4803 if video_id:
4804 return self._extract_video(video_renderer)
dacb3a86 4805
ad210f4f 4806 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4807 url = urljoin('https://youtube.com', traverse_obj(
4808 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4809 if url:
4810 return self.url_result(
4811 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4812
8bdd16b4 4813 def _post_thread_entries(self, post_thread_renderer):
4814 post_renderer = try_get(
4815 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4816 if not post_renderer:
4817 return
4818 # video attachment
4819 video_renderer = try_get(
895b0931 4820 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4821 video_id = video_renderer.get('videoId')
4822 if video_id:
4823 entry = self._extract_video(video_renderer)
8bdd16b4 4824 if entry:
4825 yield entry
895b0931 4826 # playlist attachment
4827 playlist_id = try_get(
14f25df2 4828 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4829 if playlist_id:
4830 yield self.url_result(
e28f1c0a 4831 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4832 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4833 # inline video links
4834 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4835 for run in runs:
4836 if not isinstance(run, dict):
4837 continue
4838 ep_url = try_get(
14f25df2 4839 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4840 if not ep_url:
4841 continue
4842 if not YoutubeIE.suitable(ep_url):
4843 continue
4844 ep_video_id = YoutubeIE._match_id(ep_url)
4845 if video_id == ep_video_id:
4846 continue
895b0931 4847 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4848
8bdd16b4 4849 def _post_thread_continuation_entries(self, post_thread_continuation):
4850 contents = post_thread_continuation.get('contents')
4851 if not isinstance(contents, list):
4852 return
4853 for content in contents:
4854 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4855 if isinstance(renderer, dict):
4856 yield from self._post_thread_entries(renderer)
8bdd16b4 4857 continue
6b0b0a28 4858 renderer = content.get('videoRenderer')
4859 if isinstance(renderer, dict):
4860 yield self._video_entry(renderer)
07aeced6 4861
39ed931e 4862 r''' # unused
4863 def _rich_grid_entries(self, contents):
4864 for content in contents:
4865 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4866 if video_renderer:
4867 entry = self._video_entry(video_renderer)
4868 if entry:
4869 yield entry
4870 '''
52efa4b3 4871
0a5095fe 4872 def _report_history_entries(self, renderer):
4873 for url in traverse_obj(renderer, (
7a32c70d 4874 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4875 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4876 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4877 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4878
a6213a49 4879 def _extract_entries(self, parent_renderer, continuation_list):
4880 # continuation_list is modified in-place with continuation_list = [continuation_token]
4881 continuation_list[:] = [None]
4882 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4883 for content in contents:
4884 if not isinstance(content, dict):
4885 continue
16aa9ea4 4886 is_renderer = traverse_obj(
4887 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4888 expected_type=dict)
a6213a49 4889 if not is_renderer:
0a5095fe 4890 if content.get('richItemRenderer'):
4891 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4892 yield entry
4893 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4894 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4895 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4896 yield from self._report_history_entries(table)
4897 continuation_list[0] = self._extract_continuation(table)
a6213a49 4898 continue
0a5095fe 4899
a6213a49 4900 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4901 for isr_content in isr_contents:
4902 if not isinstance(isr_content, dict):
8bdd16b4 4903 continue
69184e41 4904
a6213a49 4905 known_renderers = {
4906 'playlistVideoListRenderer': self._playlist_entries,
4907 'gridRenderer': self._grid_entries,
a17526e4 4908 'reelShelfRenderer': self._grid_entries,
4909 'shelfRenderer': self._shelf_entries,
16aa9ea4 4910 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4911 'backstagePostThreadRenderer': self._post_thread_entries,
4912 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4913 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4914 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
fcbc9ed7 4915 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
4916 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
a6213a49 4917 }
4918 for key, renderer in isr_content.items():
4919 if key not in known_renderers:
4920 continue
4921 for entry in known_renderers[key](renderer):
4922 if entry:
4923 yield entry
4924 continuation_list[0] = self._extract_continuation(renderer)
4925 break
70d5c17b 4926
4927 if not continuation_list[0]:
a6213a49 4928 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4929
a6213a49 4930 if not continuation_list[0]:
4931 continuation_list[0] = self._extract_continuation(parent_renderer)
4932
4933 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4934 continuation_list = [None]
4935 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4936 tab_content = try_get(tab, lambda x: x['content'], dict)
4937 if not tab_content:
4938 return
3462ffa8 4939 parent_renderer = (
29f7c58a 4940 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4941 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4942 yield from extract_entries(parent_renderer)
3462ffa8 4943 continuation = continuation_list[0]
1ba6fe9d 4944 seen_continuations = set()
8bdd16b4 4945 for page_num in itertools.count(1):
4946 if not continuation:
4947 break
1ba6fe9d 4948 continuation_token = continuation.get('continuation')
4949 if continuation_token is not None and continuation_token in seen_continuations:
4950 self.write_debug('Detected YouTube feed looping - assuming end of feed.')
4951 break
4952 seen_continuations.add(continuation_token)
99e9e001 4953 headers = self.generate_api_headers(
4954 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4955 response = self._extract_response(
86e5f3ed 4956 item_id=f'{item_id} page {page_num}',
fe93e2c4 4957 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4958 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4959
4960 if not response:
8bdd16b4 4961 break
ac56cf38 4962 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4963 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4964 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4965
a1b535bd 4966 known_renderers = {
e4b98809 4967 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4968 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4969 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4970 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4971 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4972 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4973 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4974 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4975 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4976 'playlistVideoListContinuation': (self._playlist_entries, None),
4977 'gridContinuation': (self._grid_entries, None),
4978 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4979 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4980 }
1fb53b94 4981
4982 continuation_items = traverse_obj(response, (
4983 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4984 'appendContinuationItemsAction', 'continuationItems'
4985 ), 'continuationContents', get_all=False)
4986 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4987
a1b535bd 4988 video_items_renderer = None
1fb53b94 4989 for key in continuation_item.keys():
a1b535bd 4990 if key not in known_renderers:
8bdd16b4 4991 continue
1fb53b94 4992 func, parent_key = known_renderers[key]
4993 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4994 continuation_list = [None]
1fb53b94 4995 yield from func(video_items_renderer)
9ba5705a 4996 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4997
4998 if not video_items_renderer:
a1b535bd 4999 break
9558dcec 5000
8bdd16b4 5001 @staticmethod
7c219ea6 5002 def _extract_selected_tab(tabs, fatal=True):
86973308
M
5003 for tab_renderer in tabs:
5004 if tab_renderer.get('selected'):
5005 return tab_renderer
5006 if fatal:
5007 raise ExtractorError('Unable to find selected tab')
5008
5009 @staticmethod
5010 def _extract_tab_renderers(response):
5011 return traverse_obj(
5012 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 5013
ac56cf38 5014 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 5015 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 5016
8bdd16b4 5017 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 5018 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
5019 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
5020
5021 return self.playlist_result(
5022 self._entries(
5023 selected_tab, metadata['id'], ytcfg,
5024 self._extract_account_syncid(ytcfg, data),
5025 self._extract_visitor_data(data, ytcfg)),
5026 **metadata)
39ed931e 5027
bd7e919a 5028 def _extract_metadata_from_tabs(self, item_id, data):
5029 info = {'id': item_id}
5030
5031 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 5032 if metadata_renderer:
7666b936 5033 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 5034 ('channelUrl', {self.ucid_from_url}))
bd7e919a 5035 info.update({
7666b936 5036 'channel': metadata_renderer.get('title'),
5037 'channel_id': channel_id,
bd7e919a 5038 })
7666b936 5039 if info['channel_id']:
5040 info['id'] = info['channel_id']
bd7e919a 5041 else:
5042 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 5043
301d07fc 5044 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
5045 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
5046 def _get_uncropped(url):
5047 return url_or_none((url or '').split('=')[0] + '=s0')
5048
6141346d 5049 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 5050 if avatar_thumbnails:
5051 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
5052 if uncropped_avatar:
5053 avatar_thumbnails.append({
5054 'url': uncropped_avatar,
5055 'id': 'avatar_uncropped',
5056 'preference': 1
5057 })
5058
5059 channel_banners = self._extract_thumbnails(
bd7e919a 5060 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 5061 for banner in channel_banners:
5062 banner['preference'] = -10
5063
5064 if channel_banners:
5065 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
5066 if uncropped_banner:
5067 channel_banners.append({
5068 'url': uncropped_banner,
5069 'id': 'banner_uncropped',
5070 'preference': -5
5071 })
5072
bd7e919a 5073 # Deprecated - remove primary_sidebar_renderer when layout discontinued
5074 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
5075 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
5076
301d07fc 5077 primary_thumbnails = self._extract_thumbnails(
a17526e4 5078 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
5079 playlist_thumbnails = self._extract_thumbnails(
5080 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
5081
bd7e919a 5082 info.update({
5083 'title': (traverse_obj(metadata_renderer, 'title')
5084 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
5085 or info['id']),
5086 'availability': self._extract_availability(data),
5087 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
5088 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
5089 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
5090 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
5091 })
f0d785d3 5092
7666b936 5093 channel_handle = (
5094 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
5095 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
5096
5097 if channel_handle:
5098 info.update({
5099 'uploader_id': channel_handle,
5100 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
5101 })
8213ce28 5102
5103 channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
5104 if self._has_badge(channel_badges, BadgeType.VERIFIED):
5105 info['channel_is_verified'] = True
6141346d
M
5106 # Playlist stats is a text runs array containing [video count, view count, last updated].
5107 # last updated or (view count and last updated) may be missing.
5108 playlist_stats = get_first(
bd7e919a 5109 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
5110
6141346d
M
5111 last_updated_unix = self._parse_time_text(
5112 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
5113 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
ad54c913 5114 info['modified_date'] = strftime_or_none(last_updated_unix)
6141346d 5115
bd7e919a 5116 info['view_count'] = self._get_count(playlist_stats, 1)
5117 if info['view_count'] is None: # 0 is allowed
5118 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5119 if info['view_count'] is None:
5120 info['view_count'] = self._get_count(data, (
5121 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5122 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5123
5124 info['playlist_count'] = self._get_count(playlist_stats, 0)
5125 if info['playlist_count'] is None: # 0 is allowed
5126 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5127
7666b936 5128 if not info.get('channel_id'):
6141346d 5129 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5130 if not owner: # Deprecated
6141346d
M
5131 owner = traverse_obj(
5132 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5133 ('videoOwner', 'videoOwnerRenderer', 'title'))
5134 owner_text = self._get_text(owner)
5135 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5136 info.update({
7666b936 5137 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5138 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5139 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5140 })
6141346d 5141
bd7e919a 5142 info.update({
7666b936 5143 'uploader': info['channel'],
5144 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5145 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5146 })
7666b936 5147
bd7e919a 5148 return info
73c4ac2c 5149
6e634cbe 5150 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5151 first_id = last_id = response = None
2be71994 5152 for page_num in itertools.count(1):
cd7c66cf 5153 videos = list(self._playlist_entries(playlist))
5154 if not videos:
5155 return
2be71994 5156 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5157 if start >= len(videos):
5158 return
24146491 5159 yield from videos[start:]
2be71994 5160 first_id = first_id or videos[0]['id']
5161 last_id = videos[-1]['id']
79360d99 5162 watch_endpoint = try_get(
5163 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5164 headers = self.generate_api_headers(
5165 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5166 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5167 query = {
5168 'playlistId': playlist_id,
5169 'videoId': watch_endpoint.get('videoId') or last_id,
5170 'index': watch_endpoint.get('index') or len(videos),
5171 'params': watch_endpoint.get('params') or 'OAE%3D'
5172 }
5173 response = self._extract_response(
5174 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5175 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5176 check_get_keys='contents'
5177 )
cd7c66cf 5178 playlist = try_get(
79360d99 5179 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5180
ac56cf38 5181 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5182 title = playlist.get('title') or try_get(
14f25df2 5183 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5184 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5185
5186 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5187 playlist_url = urljoin(url, try_get(
5188 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5189 str))
6e634cbe 5190
5191 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5192 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5193 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5194
5195 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5196 return self.url_result(
5197 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5198 video_title=title)
cd7c66cf 5199
8bdd16b4 5200 return self.playlist_result(
6e634cbe 5201 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5202 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5203
47193e02 5204 def _extract_availability(self, data):
5205 """
5206 Gets the availability of a given playlist/tab.
5207 Note: Unless YouTube tells us explicitly, we do not assume it is public
5208 @param data: response
5209 """
6141346d
M
5210 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5211 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5212 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5213
14a14335 5214 badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
47193e02 5215
5216 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5217 privacy_setting_icon = get_first(
5218 (playlist_header_renderer, sidebar_renderer),
5219 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5220 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5221 expected_type=str)
5222
5223 microformats_is_unlisted = traverse_obj(
5224 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5225
c26f9b99 5226 return (
5227 'public' if (
5228 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5229 or player_header_privacy == 'PUBLIC'
5230 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5231 else self._availability(
5232 is_private=(
5233 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5234 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5235 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5236 is_unlisted=(
5237 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5238 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5239 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5240 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5241 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5242 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5243 needs_auth=False))
47193e02 5244
5245 @staticmethod
5246 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5247 sidebar_renderer = try_get(
5248 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5249 for item in sidebar_renderer:
5250 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5251 if renderer:
5252 return renderer
5253
ac56cf38 5254 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5255 """
6141346d 5256 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5257 """
6141346d
M
5258 is_playlist = bool(traverse_obj(
5259 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5260 if not is_playlist:
47193e02 5261 return
11f9be09 5262 headers = self.generate_api_headers(
99e9e001 5263 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5264 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5265 query = {
6141346d
M
5266 'params': 'wgYCCAA=',
5267 'browseId': f'VL{item_id}'
47193e02 5268 }
5269 return self._extract_response(
5270 item_id=item_id, headers=headers, query=query,
fe93e2c4 5271 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5272 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5273
2762dbb1 5274 @functools.cached_property
a25bca9f 5275 def skip_webpage(self):
5276 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5277
ac56cf38 5278 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5279 webpage, data = None, None
5280 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5281 try:
be5c1ae8 5282 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5283 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5284 except ExtractorError as e:
5285 if isinstance(e.cause, network_exceptions):
3d2623a8 5286 if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
be5c1ae8 5287 retry.error = e
5288 continue
5289 self._error_or_warning(e, fatal=fatal)
14fdfea9 5290 break
ac56cf38 5291
be5c1ae8 5292 try:
5293 self._extract_and_report_alerts(data)
5294 except ExtractorError as e:
5295 self._error_or_warning(e, fatal=fatal)
5296 break
ac56cf38 5297
be5c1ae8 5298 # Sometimes youtube returns a webpage with incomplete ytInitialData
5299 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5300 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5301 retry.error = ExtractorError('Incomplete yt initial data received')
5302 continue
ac56cf38 5303
cd7c66cf 5304 return webpage, data
5305
a25bca9f 5306 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5307 """Use if failed to extract ytcfg (and data) from initial webpage"""
5308 if not ytcfg and self.is_authenticated:
5309 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5310 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5311 raise ExtractorError(
5312 f'{msg}. If you are not downloading private content, or '
5313 'your cookies are only for the first account and channel,'
5314 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5315 expected=True)
5316 self.report_warning(msg, only_once=True)
5317
ac56cf38 5318 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5319 data = None
a25bca9f 5320 if not self.skip_webpage:
ac56cf38 5321 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5322 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5323 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5324 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5325 if (url != 'https://www.youtube.com/feed/recommended'
5326 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5327 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5328 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5329 if fatal:
5330 raise ExtractorError(msg, expected=True)
5331 self.report_warning(msg, only_once=True)
ac56cf38 5332 if not data:
a25bca9f 5333 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5334 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5335 return data, ytcfg
5336
5337 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5338 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5339 resolve_response = self._extract_response(
5340 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5341 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5342 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5343 for ep_key, ep in endpoints.items():
5344 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5345 if params:
5346 return self._extract_response(
5347 item_id=item_id, query=params, ep=ep, headers=headers,
5348 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5349 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5350 err_note = 'Failed to resolve url (does the playlist exist?)'
5351 if fatal:
5352 raise ExtractorError(err_note, expected=True)
5353 self.report_warning(err_note, item_id)
5354
a6213a49 5355 _SEARCH_PARAMS = None
5356
af5c1c55 5357 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5358 data = {'query': query}
5359 if params is NO_DEFAULT:
5360 params = self._SEARCH_PARAMS
5361 if params:
5362 data['params'] = params
16aa9ea4 5363
5364 content_keys = (
5365 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5366 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5367 # ytmusic search
5368 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5369 ('continuationContents', ),
5370 )
a25bca9f 5371 display_id = f'query "{query}"'
86e5f3ed 5372 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5373 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5374 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5375
a61fd4cf 5376 continuation_list = [None]
a25bca9f 5377 search = None
a6213a49 5378 for page_num in itertools.count(1):
a61fd4cf 5379 data.update(continuation_list[0] or {})
a25bca9f 5380 headers = self.generate_api_headers(
5381 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5382 search = self._extract_response(
a25bca9f 5383 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5384 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5385 slr_contents = traverse_obj(search, *content_keys)
5386 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5387 if not continuation_list[0]:
a6213a49 5388 break
5389
5390
5391class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5392 IE_DESC = 'YouTube Tabs'
5393 _VALID_URL = r'''(?x:
5394 https?://
b032ff0f 5395 (?!consent\.)(?:\w+\.)?
a6213a49 5396 (?:
5397 youtube(?:kids)?\.com|
5398 %(invidious)s
5399 )/
5400 (?:
5401 (?P<channel_type>channel|c|user|browse)/|
5402 (?P<not_channel>
5403 feed/|hashtag/|
5404 (?:playlist|watch)\?.*?\blist=
5405 )|
5406 (?!(?:%(reserved_names)s)\b) # Direct URLs
5407 )
5408 (?P<id>[^/?\#&]+)
5409 )''' % {
5410 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5411 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5412 }
5413 IE_NAME = 'youtube:tab'
5414
5415 _TESTS = [{
5416 'note': 'playlists, multipage',
5417 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5418 'playlist_mincount': 94,
5419 'info_dict': {
5420 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5421 'title': 'Igor Kleiner - Playlists',
a6213a49 5422 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5423 'uploader': 'Igor Kleiner',
7666b936 5424 'uploader_id': '@IgorDataScience',
5425 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5426 'channel': 'Igor Kleiner',
5427 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5428 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5429 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5430 'channel_follower_count': int
a6213a49 5431 },
5432 }, {
5433 'note': 'playlists, multipage, different order',
5434 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5435 'playlist_mincount': 94,
5436 'info_dict': {
5437 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5438 'title': 'Igor Kleiner - Playlists',
a6213a49 5439 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5440 'uploader': 'Igor Kleiner',
7666b936 5441 'uploader_id': '@IgorDataScience',
5442 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5443 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5444 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5445 'channel': 'Igor Kleiner',
5446 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5447 'channel_follower_count': int
a6213a49 5448 },
5449 }, {
5450 'note': 'playlists, series',
5451 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5452 'playlist_mincount': 5,
5453 'info_dict': {
5454 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5455 'title': '3Blue1Brown - Playlists',
5456 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5457 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5458 'channel': '3Blue1Brown',
5459 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5460 'uploader_id': '@3blue1brown',
5461 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5462 'uploader': '3Blue1Brown',
976ae3ea 5463 'tags': ['Mathematics'],
14a14335 5464 'channel_follower_count': int,
8213ce28 5465 'channel_is_verified': True,
a6213a49 5466 },
5467 }, {
5468 'note': 'playlists, singlepage',
5469 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5470 'playlist_mincount': 4,
5471 'info_dict': {
5472 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5473 'title': 'ThirstForScience - Playlists',
5474 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5475 'uploader': 'ThirstForScience',
7666b936 5476 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5477 'uploader_id': '@ThirstForScience',
976ae3ea 5478 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5479 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5480 'tags': 'count:13',
5481 'channel': 'ThirstForScience',
6c73052c 5482 'channel_follower_count': int
a6213a49 5483 }
5484 }, {
5485 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5486 'only_matching': True,
5487 }, {
5488 'note': 'basic, single video playlist',
5489 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5490 'info_dict': {
a6213a49 5491 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5492 'title': 'youtube-dl public playlist',
976ae3ea 5493 'description': '',
5494 'tags': [],
5495 'view_count': int,
5496 'modified_date': '20201130',
5497 'channel': 'Sergey M.',
5498 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5499 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5500 'availability': 'public',
7666b936 5501 'uploader': 'Sergey M.',
5502 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5503 'uploader_id': '@sergeym.6173',
a6213a49 5504 },
5505 'playlist_count': 1,
5506 }, {
5507 'note': 'empty playlist',
5508 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5509 'info_dict': {
a6213a49 5510 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5511 'title': 'youtube-dl empty playlist',
976ae3ea 5512 'tags': [],
5513 'channel': 'Sergey M.',
5514 'description': '',
5515 'modified_date': '20160902',
5516 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5517 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5518 'availability': 'public',
7666b936 5519 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5520 'uploader_id': '@sergeym.6173',
5521 'uploader': 'Sergey M.',
a6213a49 5522 },
5523 'playlist_count': 0,
5524 }, {
5525 'note': 'Home tab',
5526 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5527 'info_dict': {
5528 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5529 'title': 'lex will - Home',
5530 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5531 'uploader': 'lex will',
7666b936 5532 'uploader_id': '@lexwill718',
976ae3ea 5533 'channel': 'lex will',
5534 'tags': ['bible', 'history', 'prophesy'],
7666b936 5535 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5536 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5537 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5538 'channel_follower_count': int
a6213a49 5539 },
5540 'playlist_mincount': 2,
5541 }, {
5542 'note': 'Videos tab',
5543 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5544 'info_dict': {
5545 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5546 'title': 'lex will - Videos',
5547 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5548 'uploader': 'lex will',
7666b936 5549 'uploader_id': '@lexwill718',
976ae3ea 5550 'tags': ['bible', 'history', 'prophesy'],
5551 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5552 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5553 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5554 'channel': 'lex will',
6c73052c 5555 'channel_follower_count': int
a6213a49 5556 },
5557 'playlist_mincount': 975,
5558 }, {
5559 'note': 'Videos tab, sorted by popular',
5560 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5561 'info_dict': {
5562 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5563 'title': 'lex will - Videos',
5564 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5565 'uploader': 'lex will',
7666b936 5566 'uploader_id': '@lexwill718',
976ae3ea 5567 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5568 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5569 'channel': 'lex will',
5570 'tags': ['bible', 'history', 'prophesy'],
5571 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5572 'channel_follower_count': int
a6213a49 5573 },
5574 'playlist_mincount': 199,
5575 }, {
5576 'note': 'Playlists tab',
5577 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5578 'info_dict': {
5579 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5580 'title': 'lex will - Playlists',
5581 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5582 'uploader': 'lex will',
7666b936 5583 'uploader_id': '@lexwill718',
5584 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5585 'channel': 'lex will',
5586 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5587 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5588 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5589 'channel_follower_count': int
a6213a49 5590 },
5591 'playlist_mincount': 17,
5592 }, {
5593 'note': 'Community tab',
5594 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5595 'info_dict': {
5596 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5597 'title': 'lex will - Community',
5598 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5599 'channel': 'lex will',
5600 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5601 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5602 'tags': ['bible', 'history', 'prophesy'],
7666b936 5603 'channel_follower_count': int,
5604 'uploader_url': 'https://www.youtube.com/@lexwill718',
5605 'uploader_id': '@lexwill718',
5606 'uploader': 'lex will',
a6213a49 5607 },
5608 'playlist_mincount': 18,
5609 }, {
5610 'note': 'Channels tab',
5611 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5612 'info_dict': {
5613 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5614 'title': 'lex will - Channels',
5615 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5616 'channel': 'lex will',
5617 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5618 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5619 'tags': ['bible', 'history', 'prophesy'],
7666b936 5620 'channel_follower_count': int,
5621 'uploader_url': 'https://www.youtube.com/@lexwill718',
5622 'uploader_id': '@lexwill718',
5623 'uploader': 'lex will',
a6213a49 5624 },
5625 'playlist_mincount': 12,
5626 }, {
5627 'note': 'Search tab',
5628 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5629 'playlist_mincount': 40,
5630 'info_dict': {
5631 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5632 'title': '3Blue1Brown - Search - linear algebra',
5633 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5634 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5635 'tags': ['Mathematics'],
5636 'channel': '3Blue1Brown',
5637 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5638 'channel_follower_count': int,
5639 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5640 'uploader_id': '@3blue1brown',
5641 'uploader': '3Blue1Brown',
8213ce28 5642 'channel_is_verified': True,
a6213a49 5643 },
5644 }, {
5645 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5646 'only_matching': True,
5647 }, {
5648 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5649 'only_matching': True,
5650 }, {
5651 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5652 'only_matching': True,
5653 }, {
5654 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5655 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5656 'info_dict': {
5657 'title': '29C3: Not my department',
5658 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5659 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5660 'tags': [],
976ae3ea 5661 'view_count': int,
5662 'modified_date': '20150605',
5663 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5664 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5665 'channel': 'Christiaan008',
c26f9b99 5666 'availability': 'public',
7666b936 5667 'uploader_id': '@ChRiStIaAn008',
5668 'uploader': 'Christiaan008',
5669 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5670 },
5671 'playlist_count': 96,
5672 }, {
5673 'note': 'Large playlist',
5674 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5675 'info_dict': {
5676 'title': 'Uploads from Cauchemar',
5677 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5678 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5679 'tags': [],
5680 'modified_date': r're:\d{8}',
5681 'channel': 'Cauchemar',
976ae3ea 5682 'view_count': int,
5683 'description': '',
5684 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5685 'availability': 'public',
7666b936 5686 'uploader_id': '@Cauchemar89',
5687 'uploader': 'Cauchemar',
5688 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5689 },
5690 'playlist_mincount': 1123,
976ae3ea 5691 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5692 }, {
5693 'note': 'even larger playlist, 8832 videos',
5694 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5695 'only_matching': True,
5696 }, {
5697 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5698 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5699 'info_dict': {
5700 'title': 'Uploads from Interstellar Movie',
5701 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5702 'tags': [],
5703 'view_count': int,
5704 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5705 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5706 'channel': 'Interstellar Movie',
5707 'description': '',
5708 'modified_date': r're:\d{8}',
c26f9b99 5709 'availability': 'public',
7666b936 5710 'uploader_id': '@InterstellarMovie',
5711 'uploader': 'Interstellar Movie',
5712 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5713 },
5714 'playlist_mincount': 21,
5715 }, {
5716 'note': 'Playlist with "show unavailable videos" button',
5717 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5718 'info_dict': {
5719 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5720 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5721 'view_count': int,
5722 'channel': 'Phim Siêu Nhân Nhật Bản',
5723 'tags': [],
976ae3ea 5724 'description': '',
5725 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5726 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5727 'modified_date': r're:\d{8}',
c26f9b99 5728 'availability': 'public',
7666b936 5729 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5730 'uploader_id': '@phimsieunhannhatban',
5731 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5732 },
5733 'playlist_mincount': 200,
976ae3ea 5734 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5735 }, {
5736 'note': 'Playlist with unavailable videos in page 7',
5737 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5738 'info_dict': {
5739 'title': 'Uploads from BlankTV',
5740 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5741 'channel': 'BlankTV',
7666b936 5742 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5743 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5744 'view_count': int,
5745 'tags': [],
976ae3ea 5746 'modified_date': r're:\d{8}',
5747 'description': '',
c26f9b99 5748 'availability': 'public',
7666b936 5749 'uploader_id': '@blanktv',
5750 'uploader': 'BlankTV',
5751 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5752 },
5753 'playlist_mincount': 1000,
976ae3ea 5754 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5755 }, {
5756 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5757 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5758 'info_dict': {
5759 'title': 'Data Analysis with Dr Mike Pound',
5760 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5761 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5762 'tags': [],
5763 'view_count': int,
5764 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5765 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5766 'channel': 'Computerphile',
c26f9b99 5767 'availability': 'public',
6141346d 5768 'modified_date': '20190712',
7666b936 5769 'uploader_id': '@Computerphile',
5770 'uploader': 'Computerphile',
5771 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5772 },
5773 'playlist_mincount': 11,
5774 }, {
5775 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5776 'only_matching': True,
5777 }, {
5778 'note': 'Playlist URL that does not actually serve a playlist',
5779 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5780 'info_dict': {
5781 'id': 'FqZTN594JQw',
5782 'ext': 'webm',
5783 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5784 'upload_date': '20150526',
5785 'license': 'Standard YouTube License',
5786 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5787 'categories': ['People & Blogs'],
5788 'tags': list,
5789 'view_count': int,
5790 'like_count': int,
a6213a49 5791 },
5792 'params': {
5793 'skip_download': True,
5794 },
5795 'skip': 'This video is not available.',
5796 'add_ie': [YoutubeIE.ie_key()],
5797 }, {
5798 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5799 'only_matching': True,
5800 }, {
5801 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5802 'only_matching': True,
5803 }, {
5804 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5805 'info_dict': {
14a14335 5806 'id': 'hGkQjiJLjWQ', # This will keep changing
a6213a49 5807 'ext': 'mp4',
976ae3ea 5808 'title': str,
a6213a49 5809 'upload_date': r're:\d{8}',
976ae3ea 5810 'description': str,
a6213a49 5811 'categories': ['News & Politics'],
5812 'tags': list,
5813 'like_count': int,
86973308 5814 'release_timestamp': int,
976ae3ea 5815 'channel': 'Sky News',
5816 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5817 'age_limit': 0,
5818 'view_count': int,
86973308 5819 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5820 'playable_in_embed': True,
86973308 5821 'release_date': r're:\d+',
976ae3ea 5822 'availability': 'public',
5823 'live_status': 'is_live',
5824 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5825 'channel_follower_count': int,
5826 'concurrent_view_count': int,
7666b936 5827 'uploader_url': 'https://www.youtube.com/@SkyNews',
5828 'uploader_id': '@SkyNews',
5829 'uploader': 'Sky News',
8213ce28 5830 'channel_is_verified': True,
a6213a49 5831 },
5832 'params': {
5833 'skip_download': True,
5834 },
976ae3ea 5835 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5836 }, {
5837 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5838 'info_dict': {
5839 'id': 'a48o2S1cPoo',
5840 'ext': 'mp4',
5841 'title': 'The Young Turks - Live Main Show',
a6213a49 5842 'upload_date': '20150715',
5843 'license': 'Standard YouTube License',
5844 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5845 'categories': ['News & Politics'],
5846 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5847 'like_count': int,
a6213a49 5848 },
5849 'params': {
5850 'skip_download': True,
5851 },
5852 'only_matching': True,
5853 }, {
5854 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5855 'only_matching': True,
5856 }, {
5857 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5858 'only_matching': True,
5859 }, {
5860 'note': 'A channel that is not live. Should raise error',
5861 'url': 'https://www.youtube.com/user/numberphile/live',
5862 'only_matching': True,
5863 }, {
5864 'url': 'https://www.youtube.com/feed/trending',
5865 'only_matching': True,
5866 }, {
5867 'url': 'https://www.youtube.com/feed/library',
5868 'only_matching': True,
5869 }, {
5870 'url': 'https://www.youtube.com/feed/history',
5871 'only_matching': True,
5872 }, {
5873 'url': 'https://www.youtube.com/feed/subscriptions',
5874 'only_matching': True,
5875 }, {
5876 'url': 'https://www.youtube.com/feed/watch_later',
5877 'only_matching': True,
5878 }, {
5879 'note': 'Recommended - redirects to home page.',
5880 'url': 'https://www.youtube.com/feed/recommended',
5881 'only_matching': True,
5882 }, {
5883 'note': 'inline playlist with not always working continuations',
5884 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5885 'only_matching': True,
5886 }, {
5887 'url': 'https://www.youtube.com/course',
5888 'only_matching': True,
5889 }, {
5890 'url': 'https://www.youtube.com/zsecurity',
5891 'only_matching': True,
5892 }, {
5893 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5894 'only_matching': True,
5895 }, {
5896 'url': 'https://www.youtube.com/TheYoungTurks/live',
5897 'only_matching': True,
5898 }, {
5899 'url': 'https://www.youtube.com/hashtag/cctv9',
5900 'info_dict': {
5901 'id': 'cctv9',
5902 'title': '#cctv9',
976ae3ea 5903 'tags': [],
a6213a49 5904 },
4dc23a80 5905 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5906 }, {
5907 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5908 'only_matching': True,
5909 }, {
5910 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5911 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5912 'only_matching': True
5913 }, {
5914 'note': '/browse/ should redirect to /channel/',
5915 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5916 'only_matching': True
5917 }, {
5918 'note': 'VLPL, should redirect to playlist?list=PL...',
5919 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5920 'info_dict': {
5921 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5922 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5923 'title': 'NCS : All Releases 💿',
7666b936 5924 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5925 'modified_date': r're:\d{8}',
5926 'view_count': int,
5927 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5928 'tags': [],
5929 'channel': 'NoCopyrightSounds',
c26f9b99 5930 'availability': 'public',
7666b936 5931 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5932 'uploader': 'NoCopyrightSounds',
5933 'uploader_id': '@NoCopyrightSounds',
a6213a49 5934 },
5935 'playlist_mincount': 166,
7666b936 5936 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5937 }, {
7666b936 5938 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5939 'note': 'Topic, should redirect to playlist?list=UU...',
5940 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5941 'info_dict': {
5942 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5943 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5944 'tags': [],
5945 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5946 'channel': 'Royalty Free Music - Topic',
5947 'view_count': int,
5948 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5949 'modified_date': r're:\d{8}',
976ae3ea 5950 'description': '',
c26f9b99 5951 'availability': 'public',
7666b936 5952 'uploader': 'Royalty Free Music - Topic',
a6213a49 5953 },
a6213a49 5954 'playlist_mincount': 101,
7666b936 5955 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5956 }, {
86973308
M
5957 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5958 # Treat as a general feed
a6213a49 5959 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5960 'info_dict': {
5961 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5962 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5963 'tags': [],
a6213a49 5964 },
a6213a49 5965 'playlist_mincount': 9,
5966 }, {
5967 'note': 'Youtube music Album',
5968 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5969 'info_dict': {
5970 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5971 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5972 'tags': [],
5973 'view_count': int,
5974 'description': '',
5975 'availability': 'unlisted',
5976 'modified_date': r're:\d{8}',
a6213a49 5977 },
5978 'playlist_count': 50,
7666b936 5979 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5980 }, {
5981 'note': 'unlisted single video playlist',
5982 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5983 'info_dict': {
a6213a49 5984 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5985 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5986 'availability': 'unlisted',
5987 'tags': [],
12a1b225 5988 'modified_date': '20220418',
976ae3ea 5989 'channel': 'colethedj',
5990 'view_count': int,
5991 'description': '',
976ae3ea 5992 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5993 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 5994 'uploader_url': 'https://www.youtube.com/@colethedj1894',
5995 'uploader_id': '@colethedj1894',
5996 'uploader': 'colethedj',
a6213a49 5997 },
93e12ed7 5998 'playlist': [{
5999 'info_dict': {
6000 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
6001 'id': 'BaW_jenozKc',
6002 '_type': 'url',
6003 'ie_key': 'Youtube',
6004 'duration': 10,
6005 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
6006 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
6007 'view_count': int,
6008 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
6009 'channel': 'Philipp Hagemeister',
6010 'uploader_id': '@PhilippHagemeister',
6011 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
6012 'uploader': 'Philipp Hagemeister',
6013 }
6014 }],
a6213a49 6015 'playlist_count': 1,
93e12ed7 6016 'params': {'extract_flat': True},
a6213a49 6017 }, {
6018 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
6019 'url': 'https://www.youtube.com/feed/recommended',
6020 'info_dict': {
6021 'id': 'recommended',
6022 'title': 'recommended',
6c73052c 6023 'tags': [],
a6213a49 6024 },
6025 'playlist_mincount': 50,
6026 'params': {
6027 'skip_download': True,
6028 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6029 },
6030 }, {
6031 'note': 'API Fallback: /videos tab, sorted by oldest first',
6032 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
6033 'info_dict': {
6034 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6035 'title': 'Cody\'sLab - Videos',
6036 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 6037 'channel': 'Cody\'sLab',
6038 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6039 'tags': [],
6040 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 6041 'channel_follower_count': int
a6213a49 6042 },
6043 'playlist_mincount': 650,
6044 'params': {
6045 'skip_download': True,
6046 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6047 },
86973308 6048 'skip': 'Query for sorting no longer works',
a6213a49 6049 }, {
6050 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
6051 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
6052 'info_dict': {
6053 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 6054 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 6055 'modified_date': r're:\d{8}',
6056 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
6057 'description': '',
6058 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
6059 'tags': [],
6060 'channel': 'Royalty Free Music - Topic',
6061 'view_count': int,
c26f9b99 6062 'availability': 'public',
7666b936 6063 'uploader': 'Royalty Free Music - Topic',
a6213a49 6064 },
a6213a49 6065 'playlist_mincount': 101,
6066 'params': {
6067 'skip_download': True,
6068 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6069 },
7666b936 6070 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 6071 }, {
6072 'note': 'non-standard redirect to regional channel',
6073 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
6074 'only_matching': True
61d3665d 6075 }, {
6076 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
6077 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6078 'info_dict': {
6079 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6080 'modified_date': '20220407',
6081 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
6082 'tags': [],
61d3665d 6083 'availability': 'unlisted',
6084 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
6085 'channel': 'pukkandan',
6086 'description': 'Test for collaborative playlist',
6087 'title': 'yt-dlp test - collaborative playlist',
12a1b225 6088 'view_count': int,
7666b936 6089 'uploader_url': 'https://www.youtube.com/@pukkandan',
6090 'uploader_id': '@pukkandan',
6091 'uploader': 'pukkandan',
61d3665d 6092 },
6093 'playlist_mincount': 2
c26f9b99 6094 }, {
6095 'note': 'translated tab name',
6096 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
6097 'info_dict': {
6098 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6099 'tags': [],
c26f9b99 6100 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 6101 'description': 'test description',
c26f9b99 6102 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 6103 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6104 'channel': 'cole-dlp-test-acc',
7666b936 6105 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6106 'uploader_id': '@coletdjnz',
6107 'uploader': 'cole-dlp-test-acc',
c26f9b99 6108 },
6109 'playlist_mincount': 1,
6110 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6111 'expected_warnings': ['Preferring "ja"'],
6112 }, {
6113 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
6114 'note': 'preferred lang set with playlist with translated video titles',
6115 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6116 'info_dict': {
6117 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6118 'tags': [],
6119 'view_count': int,
6120 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6121 'channel': 'cole-dlp-test-acc',
6122 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6123 'description': 'test',
c26f9b99 6124 'title': 'dlp test playlist',
6125 'availability': 'public',
7666b936 6126 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6127 'uploader_id': '@coletdjnz',
6128 'uploader': 'cole-dlp-test-acc',
c26f9b99 6129 },
6130 'playlist_mincount': 1,
6131 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6132 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6133 }, {
6134 # shorts audio pivot for 2GtVksBMYFM.
6135 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6136 'info_dict': {
6137 'id': 'sfv_audio_pivot',
6138 'title': 'sfv_audio_pivot',
6139 'tags': [],
6140 },
6141 'playlist_mincount': 50,
6142
86973308
M
6143 }, {
6144 # Channel with a real live tab (not to be mistaken with streams tab)
6145 # Do not treat like it should redirect to live stream
6146 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6147 'info_dict': {
6148 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6149 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6150 'tags': [],
6151 },
6152 'playlist_mincount': 20,
6153 }, {
6154 # Tab name is not the same as tab id
6155 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6156 'info_dict': {
6157 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6158 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6159 'tags': [],
6160 },
6161 'playlist_mincount': 8,
6162 }, {
6163 # Home tab id is literally home. Not to get mistaken with featured
6164 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6165 'info_dict': {
6166 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6167 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6168 'tags': [],
6169 },
6170 'playlist_mincount': 8,
6171 }, {
6172 # Should get three playlists for videos, shorts and streams tabs
6173 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6174 'info_dict': {
6175 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6176 'title': 'Polka Ch. 尾丸ポルカ',
6177 'channel_follower_count': int,
6178 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6179 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
7666b936 6180 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
bd7e919a 6181 'channel': 'Polka Ch. 尾丸ポルカ',
6182 'tags': 'count:35',
7666b936 6183 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6184 'uploader': 'Polka Ch. 尾丸ポルカ',
6185 'uploader_id': '@OmaruPolka',
86973308
M
6186 },
6187 'playlist_count': 3,
6188 }, {
6189 # Shorts tab with channel with handle
7666b936 6190 # TODO: fix channel description
86973308
M
6191 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6192 'info_dict': {
6193 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6194 'title': 'Not Just Bikes - Shorts',
6195 'tags': 'count:12',
86973308 6196 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
7666b936 6197 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
86973308 6198 'channel_follower_count': int,
86973308 6199 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6200 'channel': 'Not Just Bikes',
7666b936 6201 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6202 'uploader': 'Not Just Bikes',
6203 'uploader_id': '@NotJustBikes',
86973308
M
6204 },
6205 'playlist_mincount': 10,
6206 }, {
6207 # Streams tab
6208 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6209 'info_dict': {
6210 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6211 'title': '中村悠一 - Live',
6212 'tags': 'count:7',
6213 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6214 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6215 'channel': '中村悠一',
86973308 6216 'channel_follower_count': int,
86973308 6217 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6218 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6219 'uploader_id': '@Yuichi-Nakamura',
6220 'uploader': '中村悠一',
86973308
M
6221 },
6222 'playlist_mincount': 60,
6223 }, {
6224 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6225 # See test_youtube_lists
6226 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6227 'only_matching': True,
6228 }, {
6229 # No uploads and no UCID given. Should fail with no uploads error
6230 # See test_youtube_lists
6231 'url': 'https://www.youtube.com/news',
6232 'only_matching': True
6233 }, {
6234 # No videos tab but has a shorts tab
6235 'url': 'https://www.youtube.com/c/TKFShorts',
6236 'info_dict': {
6237 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6238 'title': 'Shorts Break - Shorts',
7666b936 6239 'tags': 'count:48',
86973308
M
6240 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6241 'channel': 'Shorts Break',
7666b936 6242 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6243 'channel_follower_count': int,
86973308 6244 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6245 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6246 'uploader': 'Shorts Break',
6247 'uploader_id': '@ShortsBreak_Official',
86973308
M
6248 },
6249 'playlist_mincount': 30,
6250 }, {
6251 # Trending Now Tab. tab id is empty
6252 'url': 'https://www.youtube.com/feed/trending',
6253 'info_dict': {
6254 'id': 'trending',
6255 'title': 'trending - Now',
6256 'tags': [],
6257 },
6258 'playlist_mincount': 30,
6259 }, {
6260 # Trending Gaming Tab. tab id is empty
6261 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6262 'info_dict': {
6263 'id': 'trending',
6264 'title': 'trending - Gaming',
6265 'tags': [],
6266 },
6267 'playlist_mincount': 30,
4dc23a80
M
6268 }, {
6269 # Shorts url result in shorts tab
7666b936 6270 # TODO: Fix channel id extraction
4dc23a80
M
6271 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6272 'info_dict': {
6273 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6274 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6275 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6276 'description': 'test description',
6277 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6278 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6279 'tags': [],
7666b936 6280 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6281 'uploader_id': '@coletdjnz',
4dc23a80 6282 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6283 },
6284 'playlist': [{
6285 'info_dict': {
7666b936 6286 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6287 '_type': 'url',
6288 'ie_key': 'Youtube',
6289 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6290 'id': 'sSM9J5YH_60',
4dc23a80 6291 'title': 'SHORT short',
4dc23a80
M
6292 'view_count': int,
6293 'thumbnails': list,
6294 }
6295 }],
6296 'params': {'extract_flat': True},
6297 }, {
6298 # Live video status should be extracted
6299 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6300 'info_dict': {
6301 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6302 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6303 'tags': []
6304 },
6305 'playlist': [{
6306 'info_dict': {
6307 '_type': 'url',
6308 'ie_key': 'Youtube',
6309 'url': 'startswith:https://www.youtube.com/watch?v=',
6310 'id': str,
6311 'title': str,
6312 'live_status': 'is_live',
6313 'channel_id': str,
6314 'channel_url': str,
6315 'concurrent_view_count': int,
6316 'channel': str,
93e12ed7 6317 'uploader': str,
6318 'uploader_url': str,
14a14335 6319 'uploader_id': str,
8213ce28 6320 'channel_is_verified': bool, # this will keep changing
4dc23a80
M
6321 }
6322 }],
c7335551 6323 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6324 'playlist_mincount': 1
c7335551
M
6325 }, {
6326 # Channel renderer metadata. Contains number of videos on the channel
6327 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6328 'info_dict': {
6329 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6330 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6331 'channel': 'cole-dlp-test-acc',
6332 'description': 'test description',
6333 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6334 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6335 'tags': [],
7666b936 6336 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6337 'uploader_id': '@coletdjnz',
c7335551 6338 'uploader': 'cole-dlp-test-acc',
c7335551
M
6339 },
6340 'playlist': [{
6341 'info_dict': {
6342 '_type': 'url',
6343 'ie_key': 'YoutubeTab',
6344 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6345 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6346 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6347 'title': 'PewDiePie',
6348 'channel': 'PewDiePie',
6349 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6350 'thumbnails': list,
6351 'channel_follower_count': int,
7666b936 6352 'playlist_count': int,
6353 'uploader': 'PewDiePie',
6354 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6355 'uploader_id': '@PewDiePie',
8213ce28 6356 'channel_is_verified': True,
c7335551
M
6357 }
6358 }],
6359 'params': {'extract_flat': True},
31e18355 6360 }, {
6361 'url': 'https://www.youtube.com/@3blue1brown/about',
6362 'info_dict': {
6363 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6364 'tags': ['Mathematics'],
6365 'title': '3Blue1Brown - About',
31e18355 6366 'channel_follower_count': int,
6367 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6368 'channel': '3Blue1Brown',
31e18355 6369 'view_count': int,
6370 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6371 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
7666b936 6372 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6373 'uploader_id': '@3blue1brown',
6374 'uploader': '3Blue1Brown',
8213ce28 6375 'channel_is_verified': True,
31e18355 6376 },
6377 'playlist_count': 0,
447afb9e 6378 }, {
6379 # Podcasts tab, with rich entry playlistRenderers
6380 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6381 'info_dict': {
6382 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6383 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6384 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6385 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6386 'title': '99 Percent Invisible - Podcasts',
6387 'uploader': '99 Percent Invisible',
6388 'channel_follower_count': int,
6389 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6390 'tags': [],
6391 'channel': '99 Percent Invisible',
6392 'uploader_id': '@99percentinvisiblepodcast',
6393 },
6394 'playlist_count': 1,
6395 }, {
6396 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6397 'url': 'https://www.youtube.com/@AHimitsu/releases',
6398 'info_dict': {
6399 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6400 'channel': 'A Himitsu',
6401 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6402 'title': 'A Himitsu - Releases',
6403 'uploader_id': '@AHimitsu',
6404 'uploader': 'A Himitsu',
6405 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6406 'tags': 'count:16',
6407 'description': 'I make music',
6408 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6409 'channel_follower_count': int,
8213ce28 6410 'channel_is_verified': True,
447afb9e 6411 },
6412 'playlist_mincount': 10,
fcbc9ed7 6413 }, {
6414 # Playlist with only shorts, shown as reel renderers
6415 # FIXME: future: YouTube currently doesn't give continuation for this,
6416 # may do in future.
6417 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
6418 'info_dict': {
6419 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
6420 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
6421 'view_count': int,
6422 'uploader_id': '@BangyShorts',
6423 'description': '',
6424 'uploader_url': 'https://www.youtube.com/@BangyShorts',
6425 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
6426 'channel': 'Bangy Shorts',
6427 'uploader': 'Bangy Shorts',
6428 'tags': [],
6429 'availability': 'public',
6430 'modified_date': '20230626',
6431 'title': 'Uploads from Bangy Shorts',
6432 },
6433 'playlist_mincount': 100,
6434 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 6435 }]
6436
6437 @classmethod
6438 def suitable(cls, url):
86e5f3ed 6439 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6440
86973308
M
6441 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6442
6443 def _get_url_mobj(self, url):
6444 mobj = self._URL_RE.match(url).groupdict()
6445 mobj.update((k, '') for k, v in mobj.items() if v is None)
6446 return mobj
6447
6448 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6449 tab_name = (tab.get('title') or '').lower()
6450 tab_url = urljoin(base_url, traverse_obj(
6451 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6452
bd7e919a 6453 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6454 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6455 if tab_id:
bd7e919a 6456 return {
6457 'TAB_ID_SPONSORSHIPS': 'membership',
6458 }.get(tab_id, tab_id), tab_name
86973308
M
6459
6460 # Fallback to tab name if we cannot get the tab id.
6461 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6462 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6463 if tab_name:
6464 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6465 return {
6466 'home': 'featured',
6467 'live': 'streams',
6468 }.get(tab_name, tab_name), tab_name
6469
6470 def _has_tab(self, tabs, tab_id):
6471 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6472
182bda88 6473 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6474 def _real_extract(self, url, smuggled_data):
cd7c66cf 6475 item_id = self._match_id(url)
14f25df2 6476 url = urllib.parse.urlunparse(
6477 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6478 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6479
86973308
M
6480 mobj = self._get_url_mobj(url)
6481 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6482 if is_channel and smuggled_data.get('is_music_url'):
6483 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6484 return self.url_result(
6485 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6486 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6487 mdata = self._extract_tab_endpoint(
6488 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6489 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6490 get_all=False, expected_type=str)
6491 if not murl:
6492 raise ExtractorError('Failed to resolve album to playlist')
6493 return self.url_result(murl, YoutubeTabIE)
6494 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6495 return self.url_result(
6496 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6497
6498 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6499 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6500 url = f'{pre}/videos{post}'
5b28cef7 6501 if smuggled_data.get('is_music_url'):
6502 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6503
6504 # Handle both video/playlist URLs
201c1459 6505 qs = parse_qs(url)
bd7e919a 6506 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6507 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6508 if not playlist_id:
fe03a6cd 6509 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6510 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6511 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6512 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6513 return self.url_result(
6514 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6515
86973308
M
6516 if not self._yes_playlist(playlist_id, video_id):
6517 return self.url_result(
6518 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6519
bd7e919a 6520 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6521
7c219ea6 6522 # YouTube may provide a non-standard redirect to the regional channel
6523 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6524 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6525 redirect_url = traverse_obj(
6526 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6527 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6528 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6529 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6530 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6531
bd7e919a 6532 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6533 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6534 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6535 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6536 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6537
6538 if not original_tab_id and selected_tab_name:
bd7e919a 6539 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6540 'To download only the videos in a specific tab, pass the tab\'s URL')
6541 if self._has_tab(tabs, 'streams'):
bd7e919a 6542 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6543 if self._has_tab(tabs, 'shorts'):
bd7e919a 6544 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6545 # XXX: Members-only tab should also be extracted
6546
bd7e919a 6547 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6548 # Channel does not have streams, shorts or videos tabs
6549 if item_id[:2] != 'UC':
6550 raise ExtractorError('This channel has no uploads', expected=True)
6551
6552 # Topic channels don't have /videos. Use the equivalent playlist instead
6553 pl_id = f'UU{item_id[2:]}'
6554 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6555 try:
6556 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6557 except ExtractorError:
6558 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6559 else:
86973308
M
6560 item_id, url = pl_id, pl_url
6561 self.to_screen(
6562 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6563
bd7e919a 6564 elif extra_tabs and selected_tab_id != 'videos':
86973308 6565 # When there are shorts/live tabs but not videos tab
bd7e919a 6566 url, data = f'{pre}{post}', None
86973308
M
6567
6568 elif (original_tab_id or 'videos') != selected_tab_id:
6569 if original_tab_id == 'live':
6570 # Live tab should have redirected to the video
6571 # Except in the case the channel has an actual live tab
6572 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6573 raise UserNotLive(video_id=item_id)
86973308
M
6574 elif selected_tab_name:
6575 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6576
6577 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6578 url = f'{pre}{post}'
18db7548 6579
358de58c 6580 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6581 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6582 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6583 self._extract_and_report_alerts(data, only_once=True)
86973308 6584
bd7e919a 6585 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6586 if tabs:
bd7e919a 6587 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6588 entries[0].update({
86973308
M
6589 'extractor_key': YoutubeTabIE.ie_key(),
6590 'extractor': YoutubeTabIE.IE_NAME,
6591 'webpage_url': url,
6592 })
bd7e919a 6593 if self.get_param('playlist_items') == '0':
6594 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6595 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6596 entries.extend(map(self._real_extract, extra_tabs))
6597
6598 if len(entries) == 1:
6599 return entries[0]
6600 elif entries:
6601 metadata = self._extract_metadata_from_tabs(item_id, data)
6602 uploads_url = 'the Uploads (UU) playlist URL'
6603 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6604 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6605 self.to_screen(
6606 'Downloading as multiple playlists, separated by tabs. '
6607 f'To download as a single playlist instead, pass {uploads_url}')
6608 return self.playlist_result(entries, item_id, **metadata)
6609
6610 # Inline playlist
37e57a9f 6611 playlist = traverse_obj(
6612 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6613 if playlist:
ac56cf38 6614 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6615
37e57a9f 6616 video_id = traverse_obj(
6617 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6618 if video_id:
bd7e919a 6619 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6620 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6621 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6622
8bdd16b4 6623 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6624
c5e8d7af 6625
8bdd16b4 6626class YoutubePlaylistIE(InfoExtractor):
96565c7e 6627 IE_DESC = 'YouTube playlists'
8bdd16b4 6628 _VALID_URL = r'''(?x)(?:
6629 (?:https?://)?
6630 (?:\w+\.)?
6631 (?:
6632 (?:
6633 youtube(?:kids)?\.com|
d9190e44 6634 %(invidious)s
8bdd16b4 6635 )
6636 /.*?\?.*?\blist=
6637 )?
6638 (?P<id>%(playlist_id)s)
d9190e44
RH
6639 )''' % {
6640 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6641 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6642 }
8bdd16b4 6643 IE_NAME = 'youtube:playlist'
cdc628a4 6644 _TESTS = [{
8bdd16b4 6645 'note': 'issue #673',
6646 'url': 'PLBB231211A4F62143',
cdc628a4 6647 'info_dict': {
8bdd16b4 6648 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6649 'id': 'PLBB231211A4F62143',
976ae3ea 6650 'uploader': 'Wickman',
7666b936 6651 'uploader_id': '@WickmanVT',
11f9be09 6652 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6653 'view_count': int,
7666b936 6654 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6655 'modified_date': r're:\d{8}',
6656 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6657 'channel': 'Wickman',
6658 'tags': [],
7666b936 6659 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6660 'availability': 'public',
8bdd16b4 6661 },
6662 'playlist_mincount': 29,
6663 }, {
6664 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6665 'info_dict': {
6666 'title': 'YDL_safe_search',
6667 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6668 },
6669 'playlist_count': 2,
6670 'skip': 'This playlist is private',
9558dcec 6671 }, {
8bdd16b4 6672 'note': 'embedded',
6673 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6674 'playlist_count': 4,
9558dcec 6675 'info_dict': {
8bdd16b4 6676 'title': 'JODA15',
6677 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6678 'uploader': 'milan',
7666b936 6679 'uploader_id': '@milan5503',
976ae3ea 6680 'description': '',
6681 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6682 'tags': [],
6683 'modified_date': '20140919',
6684 'view_count': int,
6685 'channel': 'milan',
6686 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6687 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6688 'availability': 'public',
976ae3ea 6689 },
86973308 6690 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6691 }, {
8bdd16b4 6692 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6693 'playlist_mincount': 455,
8bdd16b4 6694 'info_dict': {
6695 'title': '2018 Chinese New Singles (11/6 updated)',
6696 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6697 'uploader': 'LBK',
7666b936 6698 'uploader_id': '@music_king',
11f9be09 6699 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6700 'channel': 'LBK',
6701 'view_count': int,
7666b936 6702 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6703 'tags': [],
7666b936 6704 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6705 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6706 'modified_date': r're:\d{8}',
c26f9b99 6707 'availability': 'public',
976ae3ea 6708 },
6709 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6710 }, {
29f7c58a 6711 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6712 'only_matching': True,
6713 }, {
6714 # music album playlist
6715 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6716 'only_matching': True,
6717 }]
6718
6719 @classmethod
6720 def suitable(cls, url):
201c1459 6721 if YoutubeTabIE.suitable(url):
6722 return False
49a57e70 6723 from ..utils import parse_qs
201c1459 6724 qs = parse_qs(url)
6725 if qs.get('v', [None])[0]:
6726 return False
86e5f3ed 6727 return super().suitable(url)
29f7c58a 6728
6729 def _real_extract(self, url):
6730 playlist_id = self._match_id(url)
46953e7e 6731 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6732 url = update_url_query(
6733 'https://www.youtube.com/playlist',
6734 parse_qs(url) or {'list': playlist_id})
6735 if is_music_url:
6736 url = smuggle_url(url, {'is_music_url': True})
6737 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6738
6739
6740class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6741 IE_DESC = 'youtu.be'
29f7c58a 6742 _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}
6743 _TESTS = [{
8bdd16b4 6744 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6745 'info_dict': {
6746 'id': 'yeWKywCrFtk',
6747 'ext': 'mp4',
6748 'title': 'Small Scale Baler and Braiding Rugs',
6749 'uploader': 'Backus-Page House Museum',
7666b936 6750 'uploader_id': '@backuspagemuseum',
6751 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6752 'upload_date': '20161008',
6753 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6754 'categories': ['Nonprofits & Activism'],
6755 'tags': list,
6756 'like_count': int,
976ae3ea 6757 'age_limit': 0,
6758 'playable_in_embed': True,
7666b936 6759 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6760 'channel': 'Backus-Page House Museum',
6761 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6762 'live_status': 'not_live',
6763 'view_count': int,
6764 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6765 'availability': 'public',
6766 'duration': 59,
12a1b225
A
6767 'comment_count': int,
6768 'channel_follower_count': int
8bdd16b4 6769 },
6770 'params': {
6771 'noplaylist': True,
6772 'skip_download': True,
6773 },
39e7107d 6774 }, {
8bdd16b4 6775 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6776 'only_matching': True,
cdc628a4
PH
6777 }]
6778
8bdd16b4 6779 def _real_extract(self, url):
5ad28e7f 6780 mobj = self._match_valid_url(url)
29f7c58a 6781 video_id = mobj.group('id')
6782 playlist_id = mobj.group('playlist_id')
8bdd16b4 6783 return self.url_result(
29f7c58a 6784 update_url_query('https://www.youtube.com/watch', {
6785 'v': video_id,
6786 'list': playlist_id,
6787 'feature': 'youtu.be',
6788 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6789
6790
b6ce9bb0 6791class YoutubeLivestreamEmbedIE(InfoExtractor):
6792 IE_DESC = 'YouTube livestream embeds'
6793 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6794 _TESTS = [{
6795 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6796 'only_matching': True,
6797 }]
6798
6799 def _real_extract(self, url):
6800 channel_id = self._match_id(url)
6801 return self.url_result(
6802 f'https://www.youtube.com/channel/{channel_id}/live',
6803 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6804
6805
8bdd16b4 6806class YoutubeYtUserIE(InfoExtractor):
96565c7e 6807 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6808 IE_NAME = 'youtube:user'
8bdd16b4 6809 _VALID_URL = r'ytuser:(?P<id>.+)'
6810 _TESTS = [{
6811 'url': 'ytuser:phihag',
6812 'only_matching': True,
6813 }]
6814
6815 def _real_extract(self, url):
6816 user_id = self._match_id(url)
08270da5 6817 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6818
b05654f0 6819
3d3dddc9 6820class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6821 IE_NAME = 'youtube:favorites'
96565c7e 6822 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6823 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6824 _LOGIN_REQUIRED = True
6825 _TESTS = [{
6826 'url': ':ytfav',
6827 'only_matching': True,
6828 }, {
6829 'url': ':ytfavorites',
6830 'only_matching': True,
6831 }]
6832
6833 def _real_extract(self, url):
6834 return self.url_result(
6835 'https://www.youtube.com/playlist?list=LL',
6836 ie=YoutubeTabIE.ie_key())
6837
6838
ca5300c7 6839class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6840 IE_NAME = 'youtube:notif'
6841 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6842 _VALID_URL = r':ytnotif(?:ication)?s?'
6843 _LOGIN_REQUIRED = True
6844 _TESTS = [{
6845 'url': ':ytnotif',
6846 'only_matching': True,
6847 }, {
6848 'url': ':ytnotifications',
6849 'only_matching': True,
6850 }]
6851
6852 def _extract_notification_menu(self, response, continuation_list):
6853 notification_list = traverse_obj(
6854 response,
6855 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6856 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6857 expected_type=list) or []
6858 continuation_list[0] = None
6859 for item in notification_list:
6860 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6861 if entry:
6862 yield entry
6863 continuation = item.get('continuationItemRenderer')
6864 if continuation:
6865 continuation_list[0] = continuation
6866
6867 def _extract_notification_renderer(self, notification):
6868 video_id = traverse_obj(
6869 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6870 url = f'https://www.youtube.com/watch?v={video_id}'
6871 channel_id = None
6872 if not video_id:
6873 browse_ep = traverse_obj(
6874 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6875 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6876 post_id = self._search_regex(
6877 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6878 'post id', default=None)
6879 if not channel_id or not post_id:
6880 return
6881 # The direct /post url redirects to this in the browser
6882 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6883
6884 channel = traverse_obj(
6885 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6886 expected_type=str)
c7a7baaa 6887 notification_title = self._get_text(notification, 'shortMessage')
6888 if notification_title:
6889 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6890 # TODO: handle recommended videos
ca5300c7 6891 title = self._search_regex(
c7a7baaa 6892 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6893 'video title', default=None)
5225df50 6894 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6895 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6896 else None)
ca5300c7 6897 return {
6898 '_type': 'url',
6899 'url': url,
6900 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6901 'video_id': video_id,
6902 'title': title,
6903 'channel_id': channel_id,
6904 'channel': channel,
7666b936 6905 'uploader': channel,
ca5300c7 6906 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6907 'timestamp': timestamp,
ca5300c7 6908 }
6909
6910 def _notification_menu_entries(self, ytcfg):
6911 continuation_list = [None]
6912 response = None
6913 for page in itertools.count(1):
6914 ctoken = traverse_obj(
6915 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6916 response = self._extract_response(
6917 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6918 ep='notification/get_notification_menu', check_get_keys='actions',
6919 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6920 yield from self._extract_notification_menu(response, continuation_list)
6921 if not continuation_list[0]:
6922 break
6923
6924 def _real_extract(self, url):
6925 display_id = 'notifications'
6926 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6927 self._report_playlist_authcheck(ytcfg)
6928 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6929
6930
a6213a49 6931class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6932 IE_DESC = 'YouTube search'
78caa52a 6933 IE_NAME = 'youtube:search'
b05654f0 6934 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6935 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6936 _TESTS = [{
6937 'url': 'ytsearch5:youtube-dl test video',
6938 'playlist_count': 5,
6939 'info_dict': {
6940 'id': 'youtube-dl test video',
6941 'title': 'youtube-dl test video',
6942 }
6943 }]
b05654f0 6944
a61fd4cf 6945
5f7cb91a 6946class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6947 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6948 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6949 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6950 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6951 _TESTS = [{
6952 'url': 'ytsearchdate5:youtube-dl test video',
6953 'playlist_count': 5,
6954 'info_dict': {
6955 'id': 'youtube-dl test video',
6956 'title': 'youtube-dl test video',
6957 }
6958 }]
75dff0ee 6959
c9ae7b95 6960
a6213a49 6961class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6962 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6963 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6964 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6965 _TESTS = [{
6966 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6967 'playlist_mincount': 5,
6968 'info_dict': {
11f9be09 6969 'id': 'youtube-dl test video',
3462ffa8 6970 'title': 'youtube-dl test video',
6971 }
a61fd4cf 6972 }, {
6973 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6974 'playlist_mincount': 5,
6975 'info_dict': {
6976 'id': 'python',
6977 'title': 'python',
6978 }
ad210f4f 6979 }, {
6980 'url': 'https://www.youtube.com/results?search_query=%23cats',
6981 'playlist_mincount': 1,
6982 'info_dict': {
6983 'id': '#cats',
6984 'title': '#cats',
12a1b225
A
6985 # The test suite does not have support for nested playlists
6986 # 'entries': [{
6987 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6988 # 'title': '#cats',
6989 # }],
ad210f4f 6990 },
c7335551
M
6991 }, {
6992 # Channel results
6993 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6994 'info_dict': {
6995 'id': 'kurzgesagt',
6996 'title': 'kurzgesagt',
6997 },
6998 'playlist': [{
6999 'info_dict': {
7000 '_type': 'url',
7001 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
7002 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7003 'ie_key': 'YoutubeTab',
7004 'channel': 'Kurzgesagt – In a Nutshell',
7005 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
7006 'title': 'Kurzgesagt – In a Nutshell',
7007 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
14a14335 7008 # No longer available for search as it is set to the handle.
7009 # 'playlist_count': int,
c7335551 7010 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 7011 'thumbnails': list,
7012 'uploader_id': '@kurzgesagt',
7013 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
7014 'uploader': 'Kurzgesagt – In a Nutshell',
8213ce28 7015 'channel_is_verified': True,
14a14335 7016 'channel_follower_count': int,
c7335551
M
7017 }
7018 }],
7019 'params': {'extract_flat': True, 'playlist_items': '1'},
7020 'playlist_mincount': 1,
3462ffa8 7021 }, {
7022 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
7023 'only_matching': True,
7024 }]
7025
7026 def _real_extract(self, url):
4dfbf869 7027 qs = parse_qs(url)
386e1dd9 7028 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 7029 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 7030
7031
16aa9ea4 7032class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 7033 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 7034 IE_NAME = 'youtube:music:search_url'
7035 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
7036 _TESTS = [{
7037 'url': 'https://music.youtube.com/search?q=royalty+free+music',
7038 'playlist_count': 16,
7039 'info_dict': {
7040 'id': 'royalty free music',
7041 'title': 'royalty free music',
7042 }
7043 }, {
7044 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
7045 'playlist_mincount': 30,
7046 'info_dict': {
7047 'id': 'royalty free music - songs',
7048 'title': 'royalty free music - songs',
7049 },
7050 'params': {'extract_flat': 'in_playlist'}
7051 }, {
7052 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
7053 'playlist_mincount': 30,
7054 'info_dict': {
7055 'id': 'royalty free music - community playlists',
7056 'title': 'royalty free music - community playlists',
7057 },
7058 'params': {'extract_flat': 'in_playlist'}
7059 }]
7060
7061 _SECTIONS = {
7062 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
7063 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
7064 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
7065 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
7066 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
7067 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
7068 }
7069
7070 def _real_extract(self, url):
7071 qs = parse_qs(url)
7072 query = (qs.get('search_query') or qs.get('q'))[0]
7073 params = qs.get('sp', (None,))[0]
7074 if params:
7075 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
7076 else:
ac668111 7077 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 7078 params = self._SECTIONS.get(section)
7079 if not params:
7080 section = None
7081 title = join_nonempty(query, section, delim=' - ')
af5c1c55 7082 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 7083
7084
182bda88 7085class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 7086 """
25f14e9f 7087 Base class for feed extractors
82d02080 7088 Subclasses must re-define the _FEED_NAME property.
d7ae0639 7089 """
b2e8bc1b 7090 _LOGIN_REQUIRED = True
82d02080 7091 _FEED_NAME = 'feeds'
a25bca9f 7092
7093 def _real_initialize(self):
7094 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 7095
82d02080 7096 @classproperty
d7ae0639 7097 def IE_NAME(self):
82d02080 7098 return f'youtube:{self._FEED_NAME}'
04cc9617 7099
3853309f 7100 def _real_extract(self, url):
3d3dddc9 7101 return self.url_result(
182bda88 7102 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
7103
7104
ef2f3c7f 7105class YoutubeWatchLaterIE(InfoExtractor):
7106 IE_NAME = 'youtube:watchlater'
96565c7e 7107 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 7108 _VALID_URL = r':ytwatchlater'
bc7a9cd8 7109 _TESTS = [{
8bdd16b4 7110 'url': ':ytwatchlater',
bc7a9cd8
S
7111 'only_matching': True,
7112 }]
25f14e9f
S
7113
7114 def _real_extract(self, url):
ef2f3c7f 7115 return self.url_result(
7116 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 7117
7118
25f14e9f 7119class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 7120 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 7121 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 7122 _FEED_NAME = 'recommended'
45db527f 7123 _LOGIN_REQUIRED = False
3d3dddc9 7124 _TESTS = [{
7125 'url': ':ytrec',
7126 'only_matching': True,
7127 }, {
7128 'url': ':ytrecommended',
7129 'only_matching': True,
7130 }, {
7131 'url': 'https://youtube.com',
7132 'only_matching': True,
7133 }]
1ed5b5c9 7134
1ed5b5c9 7135
25f14e9f 7136class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 7137 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 7138 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 7139 _FEED_NAME = 'subscriptions'
3d3dddc9 7140 _TESTS = [{
7141 'url': ':ytsubs',
7142 'only_matching': True,
7143 }, {
7144 'url': ':ytsubscriptions',
7145 'only_matching': True,
7146 }]
1ed5b5c9 7147
1ed5b5c9 7148
25f14e9f 7149class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7150 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7151 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7152 _FEED_NAME = 'history'
3d3dddc9 7153 _TESTS = [{
7154 'url': ':ythistory',
7155 'only_matching': True,
7156 }]
1ed5b5c9
JMF
7157
7158
80eb0bd9 7159class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7160 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7161 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7162 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7163 _TESTS = [{
1dd18a88 7164 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7165 'only_matching': True,
7166 }]
7167
7168 @staticmethod
7169 def _generate_audio_pivot_params(video_id):
7170 """
7171 Generates sfv_audio_pivot browse params for this video id
7172 """
7173 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7174 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7175
7176 def _real_extract(self, url):
7177 video_id = self._match_id(url)
7178 return self.url_result(
7179 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7180 ie=YoutubeTabIE)
7181
7182
15870e90
PH
7183class YoutubeTruncatedURLIE(InfoExtractor):
7184 IE_NAME = 'youtube:truncated_url'
7185 IE_DESC = False # Do not list
975d35db 7186 _VALID_URL = r'''(?x)
b95aab84
PH
7187 (?:https?://)?
7188 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7189 (?:watch\?(?:
c4808c60 7190 feature=[a-z_]+|
b95aab84
PH
7191 annotation_id=annotation_[^&]+|
7192 x-yt-cl=[0-9]+|
c1708b89 7193 hl=[^&]*|
287be8c6 7194 t=[0-9]+
b95aab84
PH
7195 )?
7196 |
7197 attribution_link\?a=[^&]+
7198 )
7199 $
975d35db 7200 '''
15870e90 7201
c4808c60 7202 _TESTS = [{
2d3d2997 7203 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7204 'only_matching': True,
dc2fc736 7205 }, {
2d3d2997 7206 'url': 'https://www.youtube.com/watch?',
dc2fc736 7207 'only_matching': True,
b95aab84
PH
7208 }, {
7209 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7210 'only_matching': True,
7211 }, {
7212 'url': 'https://www.youtube.com/watch?feature=foo',
7213 'only_matching': True,
c1708b89
PH
7214 }, {
7215 'url': 'https://www.youtube.com/watch?hl=en-GB',
7216 'only_matching': True,
287be8c6
PH
7217 }, {
7218 'url': 'https://www.youtube.com/watch?t=2372',
7219 'only_matching': True,
c4808c60
PH
7220 }]
7221
15870e90
PH
7222 def _real_extract(self, url):
7223 raise ExtractorError(
78caa52a
PH
7224 'Did you forget to quote the URL? Remember that & is a meta '
7225 'character in most shells, so you want to put the URL in quotes, '
3867038a 7226 'like youtube-dl '
2d3d2997 7227 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7228 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7229 expected=True)
772fd5cc
PH
7230
7231
471d0367 7232class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7233 IE_NAME = 'youtube:clip'
471d0367 7234 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7235 _TESTS = [{
7236 # FIXME: Other metadata should be extracted from the clip, not from the base video
7237 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7238 'info_dict': {
7239 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7240 'ext': 'mp4',
7241 'section_start': 29.0,
7242 'section_end': 39.7,
7243 'duration': 10.7,
12a1b225
A
7244 'age_limit': 0,
7245 'availability': 'public',
7246 'categories': ['Gaming'],
7247 'channel': 'Scott The Woz',
7248 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7249 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7250 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7251 'like_count': int,
7252 'playable_in_embed': True,
7253 'tags': 'count:17',
7254 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7255 'title': 'Mobile Games on Console - Scott The Woz',
7256 'upload_date': '20210920',
7257 'uploader': 'Scott The Woz',
7666b936 7258 'uploader_id': '@ScottTheWoz',
7259 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7260 'view_count': int,
7261 'live_status': 'not_live',
7666b936 7262 'channel_follower_count': int,
7263 'chapters': 'count:20',
14a14335 7264 'comment_count': int,
7265 'heatmap': 'count:100',
471d0367 7266 }
7267 }]
3cd786db 7268
7269 def _real_extract(self, url):
471d0367 7270 clip_id = self._match_id(url)
7271 _, data = self._extract_webpage(url, clip_id)
7272
7273 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7274 if not video_id:
7275 raise ExtractorError('Unable to find video ID')
7276
7277 clip_data = traverse_obj(data, (
7278 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7279 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7280 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7281 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7282
7283 return {
7284 '_type': 'url_transparent',
7285 'url': f'https://www.youtube.com/watch?v={video_id}',
7286 'ie_key': YoutubeIE.ie_key(),
7287 'id': clip_id,
7288 'section_start': int(clip_data['startTimeMs']) / 1000,
7289 'section_end': int(clip_data['endTimeMs']) / 1000,
7290 }
3cd786db 7291
7292
b032ff0f 7293class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7294 IE_NAME = 'youtube:consent'
7295 IE_DESC = False # Do not list
7296 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7297 _TESTS = [{
7298 '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',
7299 'info_dict': {
7300 'id': 'qVv6vCqciTM',
7301 'ext': 'mp4',
7302 'age_limit': 0,
7666b936 7303 'uploader_id': '@sana_natori',
b032ff0f 7304 'comment_count': int,
7305 'chapters': 'count:13',
7306 'upload_date': '20221223',
7307 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7308 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7309 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7310 'like_count': int,
7311 'release_date': '20221223',
7312 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7313 '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】',
7314 'view_count': int,
7315 'playable_in_embed': True,
7316 'duration': 4438,
7317 'availability': 'public',
7318 'channel_follower_count': int,
7319 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7320 'categories': ['Entertainment'],
7321 'live_status': 'was_live',
7322 'release_timestamp': 1671793345,
7323 'channel': 'さなちゃんねる',
7324 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7325 'uploader': 'さなちゃんねる',
8213ce28 7326 'channel_is_verified': True,
14a14335 7327 'heatmap': 'count:100',
b032ff0f 7328 },
7329 'add_ie': ['Youtube'],
7330 'params': {'skip_download': 'Youtube'},
7331 }]
7332
7333 def _real_extract(self, url):
7334 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7335 if not redirect_url:
7336 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7337 return self.url_result(redirect_url)
7338
7339
772fd5cc
PH
7340class YoutubeTruncatedIDIE(InfoExtractor):
7341 IE_NAME = 'youtube:truncated_id'
7342 IE_DESC = False # Do not list
b95aab84 7343 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7344
7345 _TESTS = [{
7346 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7347 'only_matching': True,
7348 }]
7349
7350 def _real_extract(self, url):
7351 video_id = self._match_id(url)
7352 raise ExtractorError(
86e5f3ed 7353 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7354 expected=True)