]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[ie/duboku] Fix m3u8 formats extraction (#9161)
[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',
413d3675 117 'clientVersion': '18.11.34',
50ac0e54 118 'androidSdkVersion': 30,
413d3675 119 'userAgent': 'com.google.android.youtube/18.11.34 (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',
413d3675 130 'clientVersion': '18.11.34',
50ac0e54 131 'androidSdkVersion': 30,
413d3675 132 'userAgent': 'com.google.android.youtube/18.11.34 (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',
413d3675 171 'clientVersion': '18.11.34',
18c7683d 172 'deviceModel': 'iPhone14,3',
413d3675 173 'userAgent': 'com.google.ios.youtube/18.11.34 (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',
413d3675 183 'clientVersion': '18.11.34',
18c7683d 184 'deviceModel': 'iPhone14,3',
413d3675 185 'userAgent': 'com.google.ios.youtube/18.11.34 (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',
6a9c7a2b 431 r'(?:(?:www|cf)\.)?piped\.video',
bc87dac7 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',
104a7b5a
L
2071 'artists': ['Stephen'],
2072 'creators': ['Stephen'],
5caabd3c 2073 'track': 'Voyeur Girl',
2074 'album': 'it\'s too much love to know my dear',
2075 'release_date': '20190313',
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',
976ae3ea 2085 'duration': 169,
2086 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2087 'age_limit': 0,
2088 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2089 'tags': 'count:11',
2090 'live_status': 'not_live',
6c73052c 2091 'channel_follower_count': int
5caabd3c 2092 },
2093 'params': {
2094 'skip_download': True,
2095 },
2096 },
66b48727
RA
2097 {
2098 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2099 'only_matching': True,
2100 },
011e75e6
S
2101 {
2102 # invalid -> valid video id redirection
2103 'url': 'DJztXj2GPfl',
2104 'info_dict': {
2105 'id': 'DJztXj2GPfk',
2106 'ext': 'mp4',
2107 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2108 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2109 'upload_date': '20090125',
011e75e6
S
2110 'artist': 'Panjabi MC',
2111 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2112 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2113 },
2114 'params': {
2115 'skip_download': True,
2116 },
545cc85d 2117 'skip': 'Video unavailable',
ea74e00b
DP
2118 },
2119 {
2120 # empty description results in an empty string
2121 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2122 'info_dict': {
2123 'id': 'x41yOUIvK2k',
2124 'ext': 'mp4',
2125 'title': 'IMG 3456',
2126 'description': '',
2127 'upload_date': '20170613',
976ae3ea 2128 'view_count': int,
2129 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2130 'like_count': int,
2131 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2132 'tags': [],
2133 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2134 'availability': 'public',
2135 'age_limit': 0,
2136 'categories': ['Pets & Animals'],
2137 'duration': 7,
2138 'playable_in_embed': True,
2139 'live_status': 'not_live',
7666b936 2140 'channel': 'l\'Or Vert asbl',
2141 'channel_follower_count': int,
2142 'uploader': 'l\'Or Vert asbl',
2143 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2144 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2145 },
2146 'params': {
2147 'skip_download': True,
2148 },
2149 },
a0566bbf 2150 {
29f7c58a 2151 # with '};' inside yt initial data (see [1])
2152 # see [2] for an example with '};' inside ytInitialPlayerResponse
2153 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2154 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2155 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2156 'info_dict': {
2157 'id': 'CHqg6qOn4no',
2158 'ext': 'mp4',
2159 'title': 'Part 77 Sort a list of simple types in c#',
2160 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2161 'upload_date': '20130831',
976ae3ea 2162 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2163 'like_count': int,
976ae3ea 2164 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2165 'live_status': 'not_live',
2166 'categories': ['Education'],
2167 'availability': 'public',
2168 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2169 'tags': 'count:12',
2170 'playable_in_embed': True,
2171 'age_limit': 0,
2172 'view_count': int,
2173 'duration': 522,
2174 'channel': 'kudvenkat',
12a1b225 2175 'comment_count': int,
d5d1df8a 2176 'channel_follower_count': int,
2177 'chapters': list,
7666b936 2178 'uploader': 'kudvenkat',
2179 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2180 'uploader_id': '@Csharp-video-tutorialsBlogspot',
8213ce28 2181 'channel_is_verified': True,
14a14335 2182 'heatmap': 'count:100',
a0566bbf 2183 },
2184 'params': {
2185 'skip_download': True,
2186 },
2187 },
29f7c58a 2188 {
2189 # another example of '};' in ytInitialData
2190 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2191 'only_matching': True,
2192 },
2193 {
2194 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2195 'only_matching': True,
2196 },
545cc85d 2197 {
cc2db878 2198 # https://github.com/ytdl-org/youtube-dl/pull/28094
2199 'url': 'OtqTfy26tG0',
2200 'info_dict': {
2201 'id': 'OtqTfy26tG0',
2202 'ext': 'mp4',
2203 'title': 'Burn Out',
2204 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2205 'upload_date': '20141120',
cc2db878 2206 'artist': 'The Cinematic Orchestra',
2207 'track': 'Burn Out',
2208 'album': 'Every Day',
976ae3ea 2209 'like_count': int,
2210 'live_status': 'not_live',
2211 'alt_title': 'Burn Out',
2212 'duration': 614,
2213 'age_limit': 0,
2214 'view_count': int,
2215 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2216 'creator': 'The Cinematic Orchestra',
2217 'channel': 'The Cinematic Orchestra',
2218 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2219 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2220 'availability': 'public',
2221 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2222 'categories': ['Music'],
2223 'playable_in_embed': True,
7666b936 2224 'channel_follower_count': int,
2225 'uploader': 'The Cinematic Orchestra',
2226 'comment_count': int,
cc2db878 2227 },
2228 'params': {
2229 'skip_download': True,
2230 },
545cc85d 2231 },
bc2ca1bb 2232 {
2233 # controversial video, only works with bpctr when authenticated with cookies
2234 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2235 'only_matching': True,
2236 },
a1a7907b 2237 {
2238 # controversial video, requires bpctr/contentCheckOk
2239 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2240 'info_dict': {
2241 'id': 'SZJvDhaSDnc',
2242 'ext': 'mp4',
2243 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2244 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2245 'upload_date': '20140716',
976ae3ea 2246 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2247 'duration': 170,
2248 'categories': ['News & Politics'],
976ae3ea 2249 'view_count': int,
2250 'channel': 'CBS Mornings',
2251 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2252 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2253 'age_limit': 18,
2254 'availability': 'needs_auth',
2255 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2256 'like_count': int,
2257 'live_status': 'not_live',
2258 'playable_in_embed': True,
7666b936 2259 'channel_follower_count': int,
2260 'uploader': 'CBS Mornings',
2261 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2262 'uploader_id': '@CBSMornings',
14a14335 2263 'comment_count': int,
8213ce28 2264 'channel_is_verified': True,
a1a7907b 2265 }
2266 },
f7ad7160 2267 {
2268 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2269 'url': 'cBvYw8_A0vQ',
2270 'info_dict': {
2271 'id': 'cBvYw8_A0vQ',
2272 'ext': 'mp4',
2273 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2274 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2275 'upload_date': '20201120',
976ae3ea 2276 'duration': 1456,
2277 'categories': ['Travel & Events'],
2278 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2279 'view_count': int,
2280 'channel': 'Walk around Japan',
2281 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2282 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2283 'age_limit': 0,
2284 'availability': 'public',
2285 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2286 'live_status': 'not_live',
2287 'playable_in_embed': True,
7666b936 2288 'channel_follower_count': int,
2289 'uploader': 'Walk around Japan',
2290 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2291 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2292 },
2293 'params': {
2294 'skip_download': True,
2295 },
0fb983f6 2296 }, {
2297 # Has multiple audio streams
2298 'url': 'WaOKSUlf4TM',
2299 'only_matching': True
9297939e 2300 }, {
2301 # Requires Premium: has format 141 when requested using YTM url
2302 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2303 'only_matching': True
2304 }, {
120916da 2305 # multiple subtitles with same lang_code
2306 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2307 'only_matching': True,
109dd3b2 2308 }, {
2309 # Force use android client fallback
2310 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2311 'info_dict': {
2312 'id': 'YOelRv7fMxY',
11f9be09 2313 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2314 'ext': '3gp',
2315 'upload_date': '20210624',
2316 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2317 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2318 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2319 'duration': 596,
2320 'categories': ['Entertainment'],
976ae3ea 2321 'view_count': int,
2322 'channel': 'colinfurze',
2323 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2324 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2325 'age_limit': 0,
2326 'availability': 'public',
2327 'like_count': int,
2328 'live_status': 'not_live',
2329 'playable_in_embed': True,
d5d1df8a 2330 'channel_follower_count': int,
2331 'chapters': list,
7666b936 2332 'uploader': 'colinfurze',
2333 'uploader_url': 'https://www.youtube.com/@colinfurze',
2334 'uploader_id': '@colinfurze',
14a14335 2335 'comment_count': int,
8213ce28 2336 'channel_is_verified': True,
14a14335 2337 'heatmap': 'count:100',
109dd3b2 2338 },
2339 'params': {
2340 'format': '17', # 3gp format available on android
2341 'extractor_args': {'youtube': {'player_client': ['android']}},
2342 },
120916da 2343 },
109dd3b2 2344 {
2345 # Skip download of additional client configs (remix client config in this case)
2346 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2347 'only_matching': True,
2348 'params': {
2349 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2350 },
8fc54b12 2351 }, {
2352 # shorts
2353 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2354 'only_matching': True,
9222c381 2355 }, {
2356 'note': 'Storyboards',
2357 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2358 'info_dict': {
2359 'id': '5KLPxDtMqe8',
2360 'ext': 'mhtml',
2361 'format_id': 'sb0',
2362 'title': 'Your Brain is Plastic',
9222c381 2363 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2364 'upload_date': '20140324',
976ae3ea 2365 'like_count': int,
2366 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2367 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2368 'view_count': int,
2369 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2370 'playable_in_embed': True,
2371 'tags': 'count:12',
976ae3ea 2372 'availability': 'public',
2373 'channel': 'SciShow',
2374 'live_status': 'not_live',
2375 'duration': 248,
2376 'categories': ['Education'],
2377 'age_limit': 0,
d5d1df8a 2378 'channel_follower_count': int,
2379 'chapters': list,
7666b936 2380 'uploader': 'SciShow',
2381 'uploader_url': 'https://www.youtube.com/@SciShow',
2382 'uploader_id': '@SciShow',
14a14335 2383 'comment_count': int,
8213ce28 2384 'channel_is_verified': True,
14a14335 2385 'heatmap': 'count:100',
9222c381 2386 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2387 }, {
2388 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2389 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2390 'info_dict': {
2391 'id': '2NUZ8W2llS4',
2392 'ext': 'mp4',
2393 'title': 'The NP that test your phone performance 🙂',
2394 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 2395 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2396 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2397 'duration': 21,
2398 'view_count': int,
2399 'age_limit': 0,
2400 'categories': ['Gaming'],
2401 'tags': 'count:23',
2402 'playable_in_embed': True,
2403 'live_status': 'not_live',
2404 'upload_date': '20220103',
2405 'like_count': int,
2406 'availability': 'public',
2407 'channel': 'Leon Nguyen',
2408 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2409 'comment_count': int,
7666b936 2410 'channel_follower_count': int,
2411 'uploader': 'Leon Nguyen',
2412 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2413 'uploader_id': '@LeonNguyen',
14a14335 2414 'heatmap': 'count:100',
992f9a73 2415 }
1ff88b7a 2416 }, {
2417 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2418 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2419 'info_dict': {
2420 'id': '2NUZ8W2llS4',
2421 'ext': 'mp4',
2422 'title': 'The NP that test your phone performance 🙂',
2423 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 2424 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2425 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2426 'duration': 21,
2427 'view_count': int,
2428 'age_limit': 0,
2429 'categories': ['Gaming'],
2430 'tags': 'count:23',
2431 'playable_in_embed': True,
2432 'live_status': 'not_live',
2433 'upload_date': '20220102',
2434 'like_count': int,
2435 'availability': 'public',
2436 'channel': 'Leon Nguyen',
2437 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2438 'comment_count': int,
7666b936 2439 'channel_follower_count': int,
2440 'uploader': 'Leon Nguyen',
2441 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2442 'uploader_id': '@LeonNguyen',
14a14335 2443 'heatmap': 'count:100',
1ff88b7a 2444 },
2445 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2446 }, {
2447 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2448 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2449 'info_dict': {
2450 'id': 'mzZzzBU6lrM',
2451 'ext': 'mp4',
2452 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2453 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 2454 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2455 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2456 'duration': 955,
2457 'view_count': int,
2458 'age_limit': 0,
2459 'categories': ['Entertainment'],
2460 'tags': 'count:26',
2461 'playable_in_embed': True,
2462 'live_status': 'not_live',
2463 'release_timestamp': 1641172509,
2464 'release_date': '20220103',
2465 'upload_date': '20220103',
2466 'like_count': int,
2467 'availability': 'public',
2468 'channel': 'Quackity',
2469 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
7666b936 2470 'channel_follower_count': int,
2471 'uploader': 'Quackity',
2472 'uploader_id': '@Quackity',
2473 'uploader_url': 'https://www.youtube.com/@Quackity',
14a14335 2474 'comment_count': int,
8213ce28 2475 'channel_is_verified': True,
14a14335 2476 'heatmap': 'count:100',
992f9a73 2477 }
2478 },
2479 { # continuous livestream. Microformat upload date should be preferred.
2480 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2481 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2482 'info_dict': {
2483 'id': 'kgx4WGK0oNU',
2484 '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}',
2485 'ext': 'mp4',
2486 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2487 'availability': 'public',
2488 'age_limit': 0,
2489 'release_timestamp': 1637975704,
2490 'upload_date': '20210619',
2491 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2492 'live_status': 'is_live',
2493 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2494 'channel': 'Abao in Tokyo',
2495 'channel_follower_count': int,
2496 'release_date': '20211127',
2497 'tags': 'count:39',
2498 'categories': ['People & Blogs'],
2499 'like_count': int,
992f9a73 2500 'view_count': int,
2501 'playable_in_embed': True,
2502 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2503 'concurrent_view_count': int,
7666b936 2504 'uploader': 'Abao in Tokyo',
2505 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2506 'uploader_id': '@abaointokyo',
992f9a73 2507 },
2508 'params': {'skip_download': True}
ee27297f 2509 }, {
2510 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2511 'info_dict': {
2512 'id': 'tjjjtzRLHvA',
2513 'ext': 'mp4',
2514 'title': 'ハッシュタグ無し };if window.ytcsi',
2515 'upload_date': '20220323',
2516 'like_count': int,
2517 'availability': 'unlisted',
7666b936 2518 'channel': 'Lesmiscore',
2519 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2520 'age_limit': 0,
ee27297f 2521 'categories': ['Music'],
6e634cbe 2522 'view_count': int,
2523 'description': '',
ee27297f 2524 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2525 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2526 'live_status': 'not_live',
2527 'playable_in_embed': True,
2528 'channel_follower_count': int,
2529 'duration': 6,
2530 'tags': [],
7666b936 2531 'uploader_id': '@lesmiscore',
2532 'uploader': 'Lesmiscore',
2533 'uploader_url': 'https://www.youtube.com/@lesmiscore',
6e634cbe 2534 }
c26f9b99 2535 }, {
2536 # Prefer primary title+description language metadata by default
2537 # Do not prefer translated description if primary is empty
2538 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2539 'info_dict': {
2540 'id': 'el3E4MbxRqQ',
2541 'ext': 'mp4',
2542 'title': 'dlp test video 2 - primary sv no desc',
2543 'description': '',
2544 'channel': 'cole-dlp-test-acc',
2545 'tags': [],
2546 'view_count': int,
2547 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2548 'like_count': int,
2549 'playable_in_embed': True,
2550 'availability': 'unlisted',
7666b936 2551 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2552 'age_limit': 0,
2553 'duration': 5,
c26f9b99 2554 'live_status': 'not_live',
2555 'upload_date': '20220908',
2556 'categories': ['People & Blogs'],
c26f9b99 2557 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2558 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2559 'uploader_id': '@coletdjnz',
2560 'uploader': 'cole-dlp-test-acc',
c26f9b99 2561 },
2562 'params': {'skip_download': True}
2563 }, {
2564 # Extractor argument: prefer translated title+description
2565 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2566 'info_dict': {
2567 'id': 'gHKT4uU8Zng',
2568 'ext': 'mp4',
2569 'channel': 'cole-dlp-test-acc',
2570 'tags': [],
2571 'duration': 5,
2572 'live_status': 'not_live',
2573 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2574 'upload_date': '20220728',
c26f9b99 2575 'view_count': int,
2576 'categories': ['People & Blogs'],
7666b936 2577 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2578 'title': 'dlp test video title translated (fr)',
2579 'availability': 'public',
c26f9b99 2580 'age_limit': 0,
2581 'description': 'dlp test video description translated (fr)',
2582 'playable_in_embed': True,
2583 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2584 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2585 'uploader_id': '@coletdjnz',
2586 'uploader': 'cole-dlp-test-acc',
c26f9b99 2587 },
2588 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2589 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2590 }, {
2591 'note': '6 channel audio',
2592 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2593 'only_matching': True,
a4894d3e 2594 }, {
2595 'note': 'Multiple HLS formats with same itag',
2596 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2597 'info_dict': {
2598 'id': 'kX3nB4PpJko',
2599 'ext': 'mp4',
2600 'categories': ['Entertainment'],
2601 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
a4894d3e 2602 'live_status': 'not_live',
2603 'duration': 937,
2604 'channel_follower_count': int,
2605 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2606 'title': 'Last To Take Hand Off Jet, Keeps It!',
2607 'channel': 'MrBeast',
2608 'playable_in_embed': True,
2609 'view_count': int,
2610 'upload_date': '20221112',
a4894d3e 2611 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2612 'age_limit': 0,
2613 'availability': 'public',
2614 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2615 'like_count': int,
2616 'tags': [],
7666b936 2617 'uploader': 'MrBeast',
2618 'uploader_url': 'https://www.youtube.com/@MrBeast',
2619 'uploader_id': '@MrBeast',
14a14335 2620 'comment_count': int,
8213ce28 2621 'channel_is_verified': True,
14a14335 2622 'heatmap': 'count:100',
a4894d3e 2623 },
2624 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2625 }, {
2626 'note': 'Audio formats with Dynamic Range Compression',
2627 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2628 'info_dict': {
2629 'id': 'Tq92D6wQ1mg',
7666b936 2630 'ext': 'webm',
9bb85699 2631 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2632 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2633 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2634 'channel_follower_count': int,
2635 'description': 'md5:17eccca93a786d51bc67646756894066',
2636 'upload_date': '20191228',
9bb85699 2637 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2638 'playable_in_embed': True,
2639 'like_count': int,
2640 'categories': ['Entertainment'],
2641 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2642 'age_limit': 18,
2643 'channel': 'Projekt Melody',
9bb85699 2644 'view_count': int,
2645 'availability': 'needs_auth',
2646 'comment_count': int,
2647 'live_status': 'not_live',
9bb85699 2648 'duration': 106,
7666b936 2649 'uploader': 'Projekt Melody',
2650 'uploader_id': '@ProjektMelody',
2651 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 2652 },
2653 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2654 },
2655 {
2656 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2657 'info_dict': {
2658 'id': 'qVv6vCqciTM',
2659 'ext': 'mp4',
2660 'age_limit': 0,
dad2210c 2661 'comment_count': int,
2662 'chapters': 'count:13',
2663 'upload_date': '20221223',
2664 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2665 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2666 'like_count': int,
2667 'release_date': '20221223',
2668 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2669 '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】',
2670 'view_count': int,
2671 'playable_in_embed': True,
2672 'duration': 4438,
2673 'availability': 'public',
2674 'channel_follower_count': int,
2675 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2676 'categories': ['Entertainment'],
2677 'live_status': 'was_live',
2678 'release_timestamp': 1671793345,
2679 'channel': 'さなちゃんねる',
2680 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2681 'uploader': 'さなちゃんねる',
7666b936 2682 'uploader_url': 'https://www.youtube.com/@sana_natori',
2683 'uploader_id': '@sana_natori',
8213ce28 2684 'channel_is_verified': True,
14a14335 2685 'heatmap': 'count:100',
7666b936 2686 },
2687 },
2688 {
2689 # Fallbacks when webpage and web client is unavailable
2690 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2691 'info_dict': {
2692 'id': 'wSSmNUl9Snw',
2693 'ext': 'mp4',
2694 # 'categories': ['Science & Technology'],
2695 'view_count': int,
2696 'chapters': 'count:2',
2697 'channel': 'Scott Manley',
2698 'like_count': int,
2699 'age_limit': 0,
2700 # 'availability': 'public',
2701 'channel_follower_count': int,
2702 'live_status': 'not_live',
2703 'upload_date': '20170831',
2704 'duration': 682,
2705 'tags': 'count:8',
2706 'uploader_url': 'https://www.youtube.com/@scottmanley',
2707 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2708 'uploader': 'Scott Manley',
2709 'uploader_id': '@scottmanley',
2710 'title': 'The Computer Hack That Saved Apollo 14',
2711 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2712 'thumbnail': r're:^https?://.*\.webp',
2713 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2714 'playable_in_embed': True,
14a14335 2715 'comment_count': int,
8213ce28 2716 'channel_is_verified': True,
14a14335 2717 'heatmap': 'count:100',
7666b936 2718 },
2719 'params': {
2720 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2721 },
2722 },
2eb88d95
PH
2723 ]
2724
f2e8dbcc 2725 _WEBPAGE_TESTS = [
2726 # YouTube <object> embed
2727 {
2728 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2729 'md5': '873c81d308b979f0e23ee7e620b312a3',
2730 'info_dict': {
2731 'id': 'msN87y-iEx0',
2732 'ext': 'mp4',
2733 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2734 'upload_date': '20080526',
2735 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2736 'age_limit': 0,
2737 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2738 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2739 'playable_in_embed': True,
2740 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2741 'like_count': int,
2742 'comment_count': int,
2743 'channel': 'Christopher Sykes',
2744 'live_status': 'not_live',
2745 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2746 'availability': 'public',
2747 'duration': 195,
2748 'view_count': int,
2749 'categories': ['Science & Technology'],
2750 'channel_follower_count': int,
7666b936 2751 'uploader': 'Christopher Sykes',
2752 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2753 'uploader_id': '@ChristopherSykesDocumentaries',
14a14335 2754 'heatmap': 'count:100',
f2e8dbcc 2755 },
2756 'params': {
2757 'skip_download': True,
2758 }
2759 },
2760 ]
2761
201c1459 2762 @classmethod
2763 def suitable(cls, url):
4dfbf869 2764 from ..utils import parse_qs
2765
201c1459 2766 qs = parse_qs(url)
2767 if qs.get('list', [None])[0]:
2768 return False
86e5f3ed 2769 return super().suitable(url)
201c1459 2770
e0df6211 2771 def __init__(self, *args, **kwargs):
86e5f3ed 2772 super().__init__(*args, **kwargs)
545cc85d 2773 self._code_cache = {}
83799698 2774 self._player_cache = {}
e0df6211 2775
4d37720a 2776 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2777 lock = threading.Lock()
185bf310 2778 start_time = time.time()
adbc4ec4
THD
2779 formats = [f for f in formats if f.get('is_from_start')]
2780
185bf310 2781 def refetch_manifest(format_id, delay):
2782 nonlocal formats, start_time, is_live
2783 if time.time() <= start_time + delay:
adbc4ec4
THD
2784 return
2785
2786 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2787 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2788 microformats = traverse_obj(
2789 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2790 expected_type=dict)
4d37720a
L
2791 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2792 is_live = live_status == 'is_live'
185bf310 2793 start_time = time.time()
adbc4ec4 2794
185bf310 2795 def mpd_feed(format_id, delay):
adbc4ec4
THD
2796 """
2797 @returns (manifest_url, manifest_stream_number, is_live) or None
2798 """
253ac4ba 2799 for retry in self.RetryManager(fatal=False):
2800 with lock:
2801 refetch_manifest(format_id, delay)
2802
2803 f = next((f for f in formats if f['format_id'] == format_id), None)
2804 if not f:
2805 if not is_live:
2806 retry.error = f'{video_id}: Video is no longer live'
2807 else:
2808 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2809 continue
2810 return f['manifest_url'], f['manifest_stream_number'], is_live
2811 return None
adbc4ec4
THD
2812
2813 for f in formats:
4d37720a
L
2814 f['is_live'] = is_live
2815 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2816 live_start_time, mpd_feed, not is_live and f.copy())
2817 if is_live:
2818 f['fragments'] = gen
2819 f['protocol'] = 'http_dash_segments_generator'
2820 else:
2821 f['fragments'] = LazyList(gen({}))
2822 del f['is_from_start']
adbc4ec4 2823
4d37720a 2824 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2825 FETCH_SPAN, MAX_DURATION = 5, 432000
2826
2827 mpd_url, stream_number, is_live = None, None, True
2828
2829 begin_index = 0
2830 download_start_time = ctx.get('start') or time.time()
2831
2832 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2833 if lack_early_segments:
2834 self.report_warning(bug_reports_message(
2835 'Starting download from the last 120 hours of the live stream since '
2836 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2837 lack_early_segments = True
2838
2839 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2840 fragments, fragment_base_url = None, None
2841
a539f065 2842 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2843 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2844 # Obtain from MPD's maximum seq value
2845 old_mpd_url = mpd_url
185bf310 2846 last_error = ctx.pop('last_error', None)
3d2623a8 2847 expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
185bf310 2848 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2849 or (mpd_url, stream_number, False))
2850 if not refresh_sequence:
2851 if expire_fast and not is_live:
2852 return False, last_seq
2853 elif old_mpd_url == mpd_url:
2854 return True, last_seq
4d37720a
L
2855 if manifestless_orig_fmt:
2856 fmt_info = manifestless_orig_fmt
2857 else:
2858 try:
2859 fmts, _ = self._extract_mpd_formats_and_subtitles(
2860 mpd_url, None, note=False, errnote=False, fatal=False)
2861 except ExtractorError:
2862 fmts = None
2863 if not fmts:
2864 no_fragment_score += 2
2865 return False, last_seq
2866 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2867 fragments = fmt_info['fragments']
2868 fragment_base_url = fmt_info['fragment_base_url']
2869 assert fragment_base_url
2870
2871 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2872 return True, _last_seq
2873
4d37720a 2874 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2875 while is_live:
2876 fetch_time = time.time()
2877 if no_fragment_score > 30:
2878 return
2879 if last_segment_url:
2880 # Obtain from "X-Head-Seqnum" header value from each segment
2881 try:
2882 urlh = self._request_webpage(
2883 last_segment_url, None, note=False, errnote=False, fatal=False)
2884 except ExtractorError:
2885 urlh = None
2886 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2887 if last_seq is None:
a539f065 2888 no_fragment_score += 2
adbc4ec4
THD
2889 last_segment_url = None
2890 continue
2891 else:
a539f065
LNO
2892 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2893 no_fragment_score += 2
185bf310 2894 if not should_continue:
adbc4ec4
THD
2895 continue
2896
2897 if known_idx > last_seq:
2898 last_segment_url = None
2899 continue
2900
2901 last_seq += 1
2902
2903 if begin_index < 0 and known_idx < 0:
2904 # skip from the start when it's negative value
2905 known_idx = last_seq + begin_index
2906 if lack_early_segments:
2907 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2908 try:
2909 for idx in range(known_idx, last_seq):
2910 # do not update sequence here or you'll get skipped some part of it
a539f065 2911 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2912 if not should_continue:
adbc4ec4
THD
2913 known_idx = idx - 1
2914 raise ExtractorError('breaking out of outer loop')
2915 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2916 yield {
2917 'url': last_segment_url,
36195c44 2918 'fragment_count': last_seq,
adbc4ec4
THD
2919 }
2920 if known_idx == last_seq:
2921 no_fragment_score += 5
2922 else:
2923 no_fragment_score = 0
2924 known_idx = last_seq
2925 except ExtractorError:
2926 continue
2927
4d37720a
L
2928 if manifestless_orig_fmt:
2929 # Stop at the first iteration if running for post-live manifestless;
2930 # fragment count no longer increase since it starts
2931 break
2932
adbc4ec4
THD
2933 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2934
b6de707d 2935 def _extract_player_url(self, *ytcfgs, webpage=None):
2936 player_url = traverse_obj(
2937 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2938 get_all=False, expected_type=str)
11f9be09 2939 if not player_url:
b6de707d 2940 return
60f393e4 2941 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2942
b6de707d 2943 def _download_player_url(self, video_id, fatal=False):
2944 res = self._download_webpage(
2945 'https://www.youtube.com/iframe_api',
2946 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2947 if res:
2948 player_version = self._search_regex(
2949 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2950 if player_version:
2951 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2952
60064c53
PH
2953 def _signature_cache_id(self, example_sig):
2954 """ Return a string representation of a signature """
14f25df2 2955 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2956
e40c758c
S
2957 @classmethod
2958 def _extract_player_info(cls, player_url):
2959 for player_re in cls._PLAYER_INFO_RE:
2960 id_m = re.search(player_re, player_url)
2961 if id_m:
2962 break
2963 else:
c081b35c 2964 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2965 return id_m.group('id')
e40c758c 2966
404f611f 2967 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2968 player_id = self._extract_player_info(player_url)
2969 if player_id not in self._code_cache:
1276a43a 2970 code = self._download_webpage(
109dd3b2 2971 player_url, video_id, fatal=fatal,
2972 note='Downloading player ' + player_id,
2973 errnote='Download of %s failed' % player_url)
1276a43a 2974 if code:
2975 self._code_cache[player_id] = code
404f611f 2976 return self._code_cache.get(player_id)
109dd3b2 2977
e40c758c 2978 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2979 player_id = self._extract_player_info(player_url)
e0df6211 2980
c4417ddb 2981 # Read from filesystem cache
86e5f3ed 2982 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2983 assert os.path.basename(func_id) == func_id
a0e07d31 2984
ae61d108 2985 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2986 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2987
580ce007 2988 if not cache_spec:
2989 code = self._load_player(video_id, player_url)
404f611f 2990 if code:
109dd3b2 2991 res = self._parse_sig_js(code)
ac668111 2992 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2993 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2994 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2995
2996 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2997
60064c53 2998 def _print_sig_code(self, func, example_sig):
404f611f 2999 if not self.get_param('youtube_print_sig_code'):
3000 return
3001
edf3e38e
PH
3002 def gen_sig_code(idxs):
3003 def _genslice(start, end, step):
78caa52a 3004 starts = '' if start == 0 else str(start)
8bcc8756 3005 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 3006 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 3007 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
3008
3009 step = None
7af808a5
PH
3010 # Quelch pyflakes warnings - start will be set when step is set
3011 start = '(Never used)'
edf3e38e
PH
3012 for i, prev in zip(idxs[1:], idxs[:-1]):
3013 if step is not None:
3014 if i - prev == step:
3015 continue
3016 yield _genslice(start, prev, step)
3017 step = None
3018 continue
3019 if i - prev in [-1, 1]:
3020 step = i - prev
3021 start = prev
3022 continue
3023 else:
78caa52a 3024 yield 's[%d]' % prev
edf3e38e 3025 if step is None:
78caa52a 3026 yield 's[%d]' % i
edf3e38e
PH
3027 else:
3028 yield _genslice(start, i, step)
3029
ac668111 3030 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 3031 cache_res = func(test_string)
edf3e38e 3032 cache_spec = [ord(c) for c in cache_res]
78caa52a 3033 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 3034 signature_id_tuple = '(%s)' % (
14f25df2 3035 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 3036 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 3037 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 3038 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3039
e0df6211
PH
3040 def _parse_sig_js(self, jscode):
3041 funcname = self._search_regex(
abefc03f
S
3042 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3043 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
3044 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3045 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3046 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 3047 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3048 # Obsolete patterns
4823ec9f 3049 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3050 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3051 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3052 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3053 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3054 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3055 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3056
3057 jsi = JSInterpreter(jscode)
3058 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3059 return lambda s: initial_function([s])
3060
580ce007 3061 def _cached(self, func, *cache_id):
3062 def inner(*args, **kwargs):
3063 if cache_id not in self._player_cache:
3064 try:
3065 self._player_cache[cache_id] = func(*args, **kwargs)
3066 except ExtractorError as e:
3067 self._player_cache[cache_id] = e
3068 except Exception as e:
3069 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3070
3071 ret = self._player_cache[cache_id]
3072 if isinstance(ret, Exception):
3073 raise ret
3074 return ret
3075 return inner
3076
545cc85d 3077 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3078 """Turn the encrypted s field into a working signature"""
580ce007 3079 extract_sig = self._cached(
3080 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3081 func = extract_sig(video_id, player_url, s)
3082 self._print_sig_code(func, s)
3083 return func(s)
404f611f 3084
3085 def _decrypt_nsig(self, s, video_id, player_url):
3086 """Turn the encrypted n field into a working signature"""
3087 if player_url is None:
3088 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3089 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3090
b505e851 3091 try:
3092 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3093 except ExtractorError as e:
3094 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3095 if self.get_param('youtube_print_sig_code'):
3096 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3097
25836db6 3098 try:
3099 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3100 ret = extract_nsig(jsi, func_code)(s)
3101 except JSInterpreter.Exception as e:
3102 try:
992dc6b4 3103 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3104 except ExtractorError:
3105 raise e
3106 self.report_warning(
3107 f'Native nsig extraction failed: Trying with PhantomJS\n'
3108 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3109 self.write_debug(e, only_once=True)
25836db6 3110
3111 args, func_body = func_code
3112 ret = jsi.execute(
3113 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3114 video_id=video_id, note='Executing signature code').strip()
580ce007 3115
3116 self.write_debug(f'Decrypted nsig {s} => {ret}')
3117 return ret
3118
90a1df30 3119 def _extract_n_function_name(self, jscode):
3120 funcname, idx = self._search_regex(
3121 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3122 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3123 if not idx:
3124 return funcname
3125
3126 return json.loads(js_to_json(self._search_regex(
337734d4 3127 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
90a1df30 3128 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3129
580ce007 3130 def _extract_n_function_code(self, video_id, player_url):
404f611f 3131 player_id = self._extract_player_info(player_url)
05deb747 3132 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3133 jscode = func_code or self._load_player(video_id, player_url)
3134 jsi = JSInterpreter(jscode)
404f611f 3135
3136 if func_code:
580ce007 3137 return jsi, player_id, func_code
404f611f 3138
b505e851 3139 func_name = self._extract_n_function_name(jscode)
3140
3141 # For redundancy
3142 func_code = self._search_regex(
3143 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3144 # NB: The end of the regex is intentionally kept strict
3145 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3146 jscode, 'nsig function', group=('var', 'code'), default=None)
3147 if func_code:
3148 func_code = ([func_code[0]], func_code[1])
3149 else:
3150 self.write_debug('Extracting nsig function with jsinterp')
3151 func_code = jsi.extract_function_code(func_name)
3152
580ce007 3153 self.cache.store('youtube-nsig', player_id, func_code)
3154 return jsi, player_id, func_code
3155
3156 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3157 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3158
580ce007 3159 def extract_nsig(s):
25836db6 3160 try:
3161 ret = func([s])
3162 except JSInterpreter.Exception:
3163 raise
3164 except Exception as e:
3165 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3166
f6ca640b 3167 if ret.startswith('enhanced_except_'):
25836db6 3168 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3169 return ret
580ce007 3170
3171 return extract_nsig
e0df6211 3172
109dd3b2 3173 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3174 """
3175 Extract signatureTimestamp (sts)
3176 Required to tell API what sig/player version is in use.
3177 """
3178 sts = None
3179 if isinstance(ytcfg, dict):
3180 sts = int_or_none(ytcfg.get('STS'))
3181
3182 if not sts:
3183 # Attempt to extract from player
3184 if player_url is None:
3185 error_msg = 'Cannot extract signature timestamp without player_url.'
3186 if fatal:
3187 raise ExtractorError(error_msg)
3188 self.report_warning(error_msg)
3189 return
404f611f 3190 code = self._load_player(video_id, player_url, fatal=fatal)
3191 if code:
109dd3b2 3192 sts = int_or_none(self._search_regex(
3193 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3194 'JS player signature timestamp', group='sts', fatal=fatal))
3195 return sts
3196
11f9be09 3197 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3198 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3199 label = 'fully ' if is_full else ''
3200 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3201 expected_type=url_or_none)
3202 if not url:
3203 self.report_warning(f'Unable to mark {label}watched')
3204 return
14f25df2 3205 parsed_url = urllib.parse.urlparse(url)
3206 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3207
3208 # cpn generation algorithm is reverse engineered from base.js.
3209 # In fact it works even with dummy cpn.
3210 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3211 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3212
3213 # # more consistent results setting it to right before the end
3214 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3215
3216 qs.update({
3217 'ver': ['2'],
3218 'cpn': [cpn],
3219 'cmt': video_length,
3220 'el': 'detailpage', # otherwise defaults to "shorts"
3221 })
3222
3223 if is_full:
3224 # these seem to mark watchtime "history" in the real world
3225 # they're required, so send in a single value
3226 qs.update({
5318156f 3227 'st': 0,
06cc8f10
B
3228 'et': video_length,
3229 })
3230
14f25df2 3231 url = urllib.parse.urlunparse(
3232 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3233
3234 self._download_webpage(
3235 url, video_id, f'Marking {label}watched',
3236 'Unable to mark watched', fatal=False)
d77ab8e2 3237
bfd973ec 3238 @classmethod
3239 def _extract_from_webpage(cls, url, webpage):
3240 # Invidious Instances
3241 # https://github.com/yt-dlp/yt-dlp/issues/195
3242 # https://github.com/iv-org/invidious/pull/1730
3243 mobj = re.search(
3244 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3245 webpage)
3246 if mobj:
3247 yield cls.url_result(mobj.group('url'), cls)
3248 raise cls.StopExtraction()
3249
3250 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3251
3252 # lazyYT YouTube embed
bfd973ec 3253 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3254 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3255
3256 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3257 for m in re.findall(r'''(?x)<div[^>]+
3258 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3259 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3260 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3261
97665381
PH
3262 @classmethod
3263 def extract_id(cls, url):
ae61d108 3264 video_id = cls.get_temp_id(url)
3265 if not video_id:
3266 raise ExtractorError(f'Invalid URL: {url}')
3267 return video_id
c5e8d7af 3268
7c365c21 3269 def _extract_chapters_from_json(self, data, duration):
3270 chapter_list = traverse_obj(
3271 data, (
3272 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3273 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3274 ), expected_type=list)
3275
22ccd542 3276 return self._extract_chapters_helper(
7c365c21 3277 chapter_list,
22ccd542 3278 start_function=lambda chapter: float_or_none(
7c365c21 3279 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3280 title_function=lambda chapter: traverse_obj(
7c365c21 3281 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3282 duration=duration)
3283
3284 def _extract_chapters_from_engagement_panel(self, data, duration):
3285 content_list = traverse_obj(
8bdd16b4 3286 data,
7c365c21 3287 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3288 expected_type=list)
052e1350 3289 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3290 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3291
1890fc63 3292 return next(filter(None, (
22ccd542 3293 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3294 chapter_time, chapter_title, duration)
1890fc63 3295 for contents in content_list)), [])
7c365c21 3296
03e85ea9 3297 def _extract_heatmap(self, data):
3298 return traverse_obj(data, (
3299 'frameworkUpdates', 'entityBatchUpdate', 'mutations',
3300 lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
3301 'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
3302 'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
3303 'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
3304 'value': ('intensityScoreNormalized', {float_or_none}),
3305 })) or None
5caf30db 3306
a1c5d2ca
M
3307 def _extract_comment(self, comment_renderer, parent=None):
3308 comment_id = comment_renderer.get('commentId')
3309 if not comment_id:
3310 return
fe93e2c4 3311
c35448b7 3312 info = {
3313 'id': comment_id,
3314 'text': self._get_text(comment_renderer, 'contentText'),
3315 'like_count': self._get_count(comment_renderer, 'voteCount'),
3316 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3317 'author': self._get_text(comment_renderer, 'authorText'),
3318 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3319 'parent': parent or 'root',
3320 }
fe93e2c4 3321
c26f9b99 3322 # Timestamp is an estimate calculated from the current time and time_text
3323 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3324 timestamp = self._parse_time_text(time_text)
3325
c35448b7 3326 info.update({
3327 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3328 '_time_text': time_text,
3329 'timestamp': timestamp,
3330 })
fe93e2c4 3331
c35448b7 3332 info['author_url'] = urljoin(
3333 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3334 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3335 expected_type=str, get_all=False))
a1c5d2ca 3336
c35448b7 3337 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3338 if author_is_uploader is not None:
3339 info['author_is_uploader'] = author_is_uploader
3340
3341 comment_abr = traverse_obj(
89bed013 3342 comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
c35448b7 3343 if comment_abr is not None:
3344 info['is_favorited'] = 'creatorHeart' in comment_abr
3345
14a14335 3346 badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
3347 if self._has_badge(badges, BadgeType.VERIFIED):
3348 info['author_is_verified'] = True
c35448b7 3349
3350 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3351 if is_pinned:
3352 info['is_pinned'] = True
3353
3354 return info
a1c5d2ca 3355
46383212 3356 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3357
3358 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3359
3360 def extract_header(contents):
2d6659b9 3361 _continuation = None
3362 for content in contents:
46383212 3363 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3364 expected_comment_count = self._get_count(
3365 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3366
18f8fba7 3367 if expected_comment_count is not None:
46383212 3368 tracker['est_total'] = expected_comment_count
3369 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3370 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3371
3372 sort_menu_item = try_get(
3373 comments_header_renderer,
3374 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3375 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3376
3377 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3378 if not _continuation:
3379 continue
3380
46383212 3381 sort_text = str_or_none(sort_menu_item.get('title'))
3382 if not sort_text:
2d6659b9 3383 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3384 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3385 break
a2160aa4 3386 return _continuation
a1c5d2ca 3387
2d6659b9 3388 def extract_thread(contents):
a1c5d2ca 3389 if not parent:
46383212 3390 tracker['current_page_thread'] = 0
a1c5d2ca 3391 for content in contents:
46383212 3392 if not parent and tracker['total_parent_comments'] >= max_parents:
3393 yield
a1c5d2ca 3394 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3395 comment_renderer = get_first(
3396 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3397 expected_type=dict, default={})
a1c5d2ca 3398
a1c5d2ca
M
3399 comment = self._extract_comment(comment_renderer, parent)
3400 if not comment:
3401 continue
141a8dff 3402 comment_id = comment['id']
c35448b7 3403 if comment.get('is_pinned'):
141a8dff 3404 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3405 # Sometimes YouTube may break and give us infinite looping comments.
3406 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3407 if comment_id in tracker['seen_comment_ids']:
c35448b7 3408 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3409 # Pinned comments may appear a second time in newest first sort
3410 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3411 continue
4dc4d847 3412 self.report_warning(
3413 'Detected YouTube comments looping. Stopping comment extraction '
3414 f'{"for this thread" if parent else ""} as we probably cannot get any more.')
7f51861b 3415 yield
3416 else:
3417 tracker['seen_comment_ids'].add(comment['id'])
46383212 3418
3419 tracker['running_total'] += 1
3420 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3421 yield comment
46383212 3422
a1c5d2ca
M
3423 # Attempt to get the replies
3424 comment_replies_renderer = try_get(
3425 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3426
3427 if comment_replies_renderer:
46383212 3428 tracker['current_page_thread'] += 1
a1c5d2ca 3429 comment_entries_iter = self._comment_entries(
99e9e001 3430 comment_replies_renderer, ytcfg, video_id,
46383212 3431 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3432 yield from itertools.islice(comment_entries_iter, min(
3433 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3434
46383212 3435 # Keeps track of counts across recursive calls
3436 if not tracker:
3437 tracker = dict(
3438 running_total=0,
18f8fba7 3439 est_total=None,
46383212 3440 current_page_thread=0,
3441 total_parent_comments=0,
7f51861b 3442 total_reply_comments=0,
141a8dff 3443 seen_comment_ids=set(),
3444 pinned_comment_ids=set()
3445 )
46383212 3446
3447 # TODO: Deprecated
2d6659b9 3448 # YouTube comments have a max depth of 2
46383212 3449 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3450 if max_depth:
da4db748 3451 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3452 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3453 if max_depth == 1 and parent:
3454 return
a1c5d2ca 3455
46383212 3456 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3457 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3458
46383212 3459 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3460
46383212 3461 response = None
6e634cbe 3462 is_forced_continuation = False
2d6659b9 3463 is_first_continuation = parent is None
6e634cbe 3464 if is_first_continuation and not continuation:
3465 # Sometimes you can get comments by generating the continuation yourself,
3466 # even if YouTube initially reports them being disabled - e.g. stories comments.
3467 # Note: if the comment section is actually disabled, YouTube may return a response with
3468 # required check_get_keys missing. So we will disable that check initially in this case.
3469 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3470 is_forced_continuation = True
a1c5d2ca 3471
18f8fba7 3472 continuation_items_path = (
3473 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3474 for page_num in itertools.count(0):
3475 if not continuation:
3476 break
46383212 3477 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3478 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3479 if page_num == 0:
3480 if is_first_continuation:
3481 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3482 else:
2d6659b9 3483 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3484 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3485 else:
3486 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3487 ' ' if parent else '', ' replies' if parent else '',
3488 page_num, comment_prog_str)
18f8fba7 3489
3490 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3491 # Ignore check if YouTube says the comment count is 0.
3492 check_get_keys = None
3493 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3494 check_get_keys = [[*continuation_items_path, ..., (
3495 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3496 try:
3497 response = self._extract_response(
3498 item_id=None, query=continuation,
3499 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3500 check_get_keys=check_get_keys)
e72e48c5
M
3501 except ExtractorError as e:
3502 # Ignore incomplete data error for replies if retries didn't work.
3503 # This is to allow any other parent comments and comment threads to be downloaded.
3504 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
4dc4d847 3505 if 'incomplete data' in str(e).lower() and parent:
3506 if self.get_param('ignoreerrors') in (True, 'only_download'):
3507 self.report_warning(
3508 'Received incomplete data for a comment reply thread and retrying did not help. '
3509 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
3510 return
3511 else:
3512 raise ExtractorError(
3513 'Incomplete data received for comment reply thread. '
3514 'Pass --ignore-errors to ignore and allow rest of comments to download.',
3515 expected=True)
3516 raise
6e634cbe 3517 is_forced_continuation = False
2d6659b9 3518 continuation = None
18f8fba7 3519 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3520 if is_first_continuation:
3521 continuation = extract_header(continuation_items)
3522 is_first_continuation = False
2d6659b9 3523 if continuation:
a1c5d2ca 3524 break
46383212 3525 continue
a1c5d2ca 3526
46383212 3527 for entry in extract_thread(continuation_items):
3528 if not entry:
3529 return
3530 yield entry
3531 continuation = self._extract_continuation({'contents': continuation_items})
3532 if continuation:
2d6659b9 3533 break
a1c5d2ca 3534
6e634cbe 3535 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3536 if message and not parent and tracker['running_total'] == 0:
3537 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3538 raise self.CommentsDisabled
6e634cbe 3539
3540 @staticmethod
3541 def _generate_comment_continuation(video_id):
3542 """
3543 Generates initial comment section continuation token from given video id
3544 """
3545 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3546 return base64.b64encode(token.encode()).decode()
3547
a2160aa4 3548 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3549 """Entry for comment extraction"""
2d6659b9 3550 def _real_comment_extract(contents):
aae16f6e 3551 renderer = next((
3552 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3553 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3554 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3555
a2160aa4 3556 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3557 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3558
109dd3b2 3559 @staticmethod
99e9e001 3560 def _get_checkok_params():
3561 return {'contentCheckOk': True, 'racyCheckOk': True}
3562
3563 @classmethod
3564 def _generate_player_context(cls, sts=None):
109dd3b2 3565 context = {
3566 'html5Preference': 'HTML5_PREF_WANTS',
3567 }
3568 if sts is not None:
3569 context['signatureTimestamp'] = sts
3570 return {
3571 'playbackContext': {
3572 'contentPlaybackContext': context
a1a7907b 3573 },
99e9e001 3574 **cls._get_checkok_params()
109dd3b2 3575 }
3576
e7e94f2a
D
3577 @staticmethod
3578 def _is_agegated(player_response):
3579 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3580 return True
e7e94f2a 3581
6839ae1f 3582 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3583 AGE_GATE_REASONS = (
3584 'confirm your age', 'age-restricted', 'inappropriate', # reason
3585 'age_verification_required', 'age_check_required', # status
3586 )
3587 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3588
3589 @staticmethod
3590 def _is_unplayable(player_response):
3591 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3592
50ac0e54 3593 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3594
11f9be09 3595 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3596 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3597 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3598 headers = self.generate_api_headers(
99e9e001 3599 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3600
6e634cbe 3601 yt_query = {
3602 'videoId': video_id,
6e634cbe 3603 }
90db9a3c 3604 if _split_innertube_client(client)[0] == 'android':
ba06d77a 3605 yt_query['params'] = 'CgIQBg=='
3606
546b2c28 3607 pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 3608 if pp_arg:
3609 yt_query['params'] = pp_arg
50ac0e54 3610
11f9be09 3611 yt_query.update(self._generate_player_context(sts))
3612 return self._extract_response(
3613 item_id=video_id, ep='player', query=yt_query,
379e44ed 3614 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3615 default_client=client,
11f9be09 3616 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3617 ) or None
3618
11f9be09 3619 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3620 requested_clients = []
fd8fcf8f 3621 default = ['ios', 'android', 'web']
000c15a4 3622 allowed_clients = sorted(
86e5f3ed 3623 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3624 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3625 for client in self._configuration_arg('player_client'):
3626 if client in allowed_clients:
3627 requested_clients.append(client)
d0d012d4 3628 elif client == 'default':
3629 requested_clients.extend(default)
b4c055ba 3630 elif client == 'all':
3631 requested_clients.extend(allowed_clients)
3632 else:
3633 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3634 if not requested_clients:
d0d012d4 3635 requested_clients = default
cf7e015f 3636
11f9be09 3637 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3638 requested_clients.extend(
e7e94f2a 3639 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3640
11f9be09 3641 return orderedSet(requested_clients)
cf7e015f 3642
5eedc208
SS
3643 def _invalid_player_response(self, pr, video_id):
3644 # YouTube may return a different video player response than expected.
3645 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3646 if (pr_id := traverse_obj(pr, ('videoDetails', 'videoId'))) != video_id:
3647 return pr_id
3648
50ac0e54 3649 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3650 initial_pr = None
3651 if webpage:
b7c47b74 3652 initial_pr = self._search_json(
3653 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3654
5eedc208
SS
3655 prs = []
3656 if initial_pr and not self._invalid_player_response(initial_pr, video_id):
3657 # Android player_response does not have microFormats which are needed for
3658 # extraction of some data. So we return the initial_pr with formats
3659 # stripped out even if not requested by the user
3660 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3661 prs.append({**initial_pr, 'streamingData': None})
3662
ae729626 3663 all_clients = set(clients)
c0bc527b 3664 clients = clients[::-1]
e7e94f2a 3665
ae729626 3666 def append_client(*client_names):
e7870111 3667 """ Append the first client name that exists but not already used """
ae729626 3668 for client_name in client_names:
e7870111
D
3669 actual_client = _split_innertube_client(client_name)[0]
3670 if actual_client in INNERTUBE_CLIENTS:
3671 if actual_client not in all_clients:
ae729626 3672 clients.append(client_name)
e7870111
D
3673 all_clients.add(actual_client)
3674 return
e7e94f2a 3675
b6de707d 3676 tried_iframe_fallback = False
3677 player_url = None
5eedc208 3678 skipped_clients = {}
c0bc527b 3679 while clients:
e7870111 3680 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3681 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3682 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3683 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3684
b6de707d 3685 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3686 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3687 if 'js' in self._configuration_arg('player_skip'):
3688 require_js_player = False
3689 player_url = None
3690
3691 if not player_url and not tried_iframe_fallback and require_js_player:
3692 player_url = self._download_player_url(video_id)
3693 tried_iframe_fallback = True
3694
379e44ed 3695 try:
3696 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3697 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3698 except ExtractorError as e:
5eedc208 3699 self.report_warning(e)
379e44ed 3700 continue
3701
5eedc208
SS
3702 if pr_id := self._invalid_player_response(pr, video_id):
3703 skipped_clients[client] = pr_id
3704 elif pr:
3705 # Save client name for introspection later
3706 name = short_client_name(client)
3707 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3708 sd[STREAMING_DATA_CLIENT_NAME] = name
3709 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3710 f[STREAMING_DATA_CLIENT_NAME] = name
3711 prs.append(pr)
c0bc527b 3712
e7e94f2a 3713 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3714 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3715 append_client(f'{base_client}_creator')
e7e94f2a 3716 elif self._is_agegated(pr):
e7870111
D
3717 if variant == 'tv_embedded':
3718 append_client(f'{base_client}_embedded')
3719 elif not variant:
3720 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3721
5eedc208
SS
3722 if skipped_clients:
3723 self.report_warning(
3724 f'Skipping player responses from {"/".join(skipped_clients)} clients '
3725 f'(got player responses for video "{"/".join(set(skipped_clients.values()))}" instead of "{video_id}")')
3726 if not prs:
3727 raise ExtractorError(
3728 'All player responses are invalid. Your IP is likely being blocked by Youtube', expected=True)
3729 elif not prs:
3730 raise ExtractorError('Failed to extract any player response')
b6de707d 3731 return prs, player_url
11f9be09 3732
4d37720a
L
3733 def _needs_live_processing(self, live_status, duration):
3734 if (live_status == 'is_live' and self.get_param('live_from_start')
d949c10c 3735 or live_status == 'post_live' and (duration or 0) > 2 * 3600):
4d37720a
L
3736 return live_status
3737
3738 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3739 CHUNK_SIZE = 10 << 20
a4894d3e 3740 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3741 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3742 q = qualities([
2a9c6dcd 3743 # Normally tiny is the smallest video-only formats. But
3744 # audio-only formats with unknown quality may get tagged as tiny
3745 'tiny',
3746 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3747 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3748 ])
6839ae1f 3749 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
58786a10 3750 format_types = self._configuration_arg('formats')
3751 all_formats = 'duplicate' in format_types
3752 if self._configuration_arg('include_duplicate_formats'):
3753 all_formats = True
3754 self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
3755 'Use formats=duplicate extractor argument instead')
9297939e 3756
e389d172 3757 def build_fragments(f):
3758 return LazyList({
3759 'url': update_url_query(f['url'], {
3760 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3761 })
3762 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3763
545cc85d 3764 for fmt in streaming_formats:
727029c5 3765 if fmt.get('targetDurationSec'):
545cc85d 3766 continue
321bf820 3767
cc2db878 3768 itag = str_or_none(fmt.get('itag'))
9297939e 3769 audio_track = fmt.get('audioTrack') or {}
9bb85699 3770 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3771 if not all_formats:
3772 if stream_id in stream_ids:
3773 continue
9297939e 3774
cc2db878 3775 quality = fmt.get('quality')
2a9c6dcd 3776 height = int_or_none(fmt.get('height'))
d3fc8074 3777 if quality == 'tiny' or not quality:
3778 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3779 # The 3gp format (17) in android client has a quality of "small",
3780 # but is actually worse than other formats
3781 if itag == '17':
3782 quality = 'tiny'
3783 if quality:
3784 if itag:
3785 itag_qualities[itag] = quality
3786 if height:
3787 res_qualities[height] = quality
cc2db878 3788 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3789 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3790 # number of fragment that would subsequently requested with (`&sq=N`)
3791 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3792 continue
3793
545cc85d 3794 fmt_url = fmt.get('url')
3795 if not fmt_url:
14f25df2 3796 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3797 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3798 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3799 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3800 continue
52023f12 3801 try:
3802 fmt_url += '&%s=%s' % (
3803 traverse_obj(sc, ('sp', -1)) or 'signature',
3804 self._decrypt_signature(encrypted_sig, video_id, player_url)
3805 )
3806 except ExtractorError as e:
580ce007 3807 self.report_warning('Signature extraction failed: Some formats may be missing',
3808 video_id=video_id, only_once=True)
52023f12 3809 self.write_debug(e, only_once=True)
201e9eaa 3810 continue
545cc85d 3811
404f611f 3812 query = parse_qs(fmt_url)
3813 throttled = False
b2916526 3814 if query.get('n'):
404f611f 3815 try:
580ce007 3816 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3817 fmt_url = update_url_query(fmt_url, {
580ce007 3818 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3819 })
404f611f 3820 except ExtractorError as e:
25836db6 3821 phantomjs_hint = ''
3822 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3823 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3824 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3825 if player_url:
3826 self.report_warning(
3827 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3828 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3829 self.write_debug(e, only_once=True)
3830 else:
3831 self.report_warning(
3832 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3833 video_id=video_id, only_once=True)
404f611f 3834 throttled = True
3835
0ad92dfb 3836 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3837 language_preference = (
3838 10 if audio_track.get('audioIsDefault') and 10
3839 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3840 else -1)
0ad92dfb 3841 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3842 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3843 # Make sure to avoid false positives with small duration differences.
62b58c09 3844 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3845 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3846 if is_damaged:
0f06bcd7 3847 self.report_warning(
3848 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3849
3850 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
51a07b0d 3851 name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
97afb093 3852 fps = int_or_none(fmt.get('fps')) or 0
545cc85d 3853 dct = {
3854 'asr': int_or_none(fmt.get('audioSampleRate')),
3855 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3856 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3857 'format_note': join_nonempty(
392389b7 3858 join_nonempty(audio_track.get('displayName'),
3859 language_preference > 0 and ' (default)', delim=''),
51a07b0d 3860 name, fmt.get('isDrc') and 'DRC',
a4166234 3861 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3862 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3863 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3864 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3865 delim=', '),
91e5e839 3866 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
51a07b0d 3867 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
3868 + (100 if 'Premium' in name else 0)),
97afb093 3869 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
a4166234 3870 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3871 'height': height,
9bb85699 3872 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3873 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3874 'tbr': tbr,
545cc85d 3875 'url': fmt_url,
2a9c6dcd 3876 'width': int_or_none(fmt.get('width')),
ab6df717 3877 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3878 'desc' if language_preference < -1 else '') or None,
ab6df717 3879 'language_preference': language_preference,
a405b38f 3880 # Strictly de-prioritize damaged and 3gp formats
3881 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3882 }
60bdb7bd 3883 mime_mobj = re.match(
3884 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3885 if mime_mobj:
3886 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3887 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3888 if itag:
3889 itags[itag].add(('https', dct.get('language')))
3890 stream_ids.append(stream_id)
c9abebb8 3891 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3892 if single_stream and dct.get('ext'):
3893 dct['container'] = dct['ext'] + '_dash'
86cb9221 3894
58786a10 3895 if (all_formats or 'dashy' in format_types) and dct['filesize']:
86cb9221 3896 yield {
3897 **dct,
3898 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3899 'protocol': 'http_dash_segments',
e389d172 3900 'fragments': build_fragments(dct),
86cb9221 3901 }
58786a10 3902 if all_formats or 'dashy' not in format_types:
3903 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3904 yield dct
545cc85d 3905
4d37720a 3906 needs_live_processing = self._needs_live_processing(live_status, duration)
58786a10 3907 skip_bad_formats = 'incomplete' not in format_types
3908 if self._configuration_arg('include_incomplete_formats'):
3909 skip_bad_formats = False
3910 self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
3911 'Use formats=incomplete extractor argument instead')
4d37720a
L
3912
3913 skip_manifests = set(self._configuration_arg('skip'))
3914 if (not self.get_param('youtube_include_hls_manifest', True)
3915 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3916 or needs_live_processing and skip_bad_formats):
3917 skip_manifests.add('hls')
3918
0f06bcd7 3919 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3920 skip_manifests.add('dash')
3921 if self._configuration_arg('include_live_dash'):
3922 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
58786a10 3923 'Use formats=incomplete extractor argument instead')
4d37720a
L
3924 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3925 skip_manifests.add('dash')
5d3a0e79 3926
c795c39f 3927 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3928 key = (proto, f.get('language'))
86cb9221 3929 if not all_formats and key in itags[itag]:
a4894d3e 3930 return False
3931 itags[itag].add(key)
3932
86cb9221 3933 if itag and all_formats:
3934 f['format_id'] = f'{itag}-{proto}'
3935 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3936 f['format_id'] = f'{itag}-{proto}'
3937 elif itag:
a0bb6ce5 3938 f['format_id'] = itag
a0bb6ce5 3939
94ed638a 3940 if f.get('source_preference') is None:
3941 f['source_preference'] = -1
3942
1e75d97d 3943 if itag in ('616', '235'):
3944 f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
94ed638a 3945 f['source_preference'] += 100
1e75d97d 3946
b25cac65 3947 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3948 if f['quality'] == -1 and f.get('height'):
3949 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
ad54c913 3950 if self.get_param('verbose') or all_formats:
c795c39f 3951 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
97afb093 3952 if f.get('fps') and f['fps'] <= 1:
3953 del f['fps']
94ed638a 3954
3955 if proto == 'hls' and f.get('has_drm'):
3956 f['has_drm'] = 'maybe'
3957 f['source_preference'] -= 5
a0bb6ce5 3958 return True
2a9c6dcd 3959
c646d76f 3960 subtitles = {}
11f9be09 3961 for sd in streaming_data:
c795c39f
L
3962 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3963
4d37720a 3964 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3965 if hls_manifest_url:
4d37720a
L
3966 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3967 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3968 subtitles = self._merge_subtitles(subs, subtitles)
3969 for f in fmts:
c795c39f 3970 if process_manifest_format(f, 'hls', client_name, self._search_regex(
a0bb6ce5 3971 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3972 yield f
545cc85d 3973
4d37720a 3974 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3975 if dash_manifest_url:
c646d76f 3976 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3977 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3978 for f in formats:
c795c39f 3979 if process_manifest_format(f, 'dash', client_name, f['format_id']):
a0bb6ce5 3980 f['filesize'] = int_or_none(self._search_regex(
3981 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3982 if needs_live_processing:
adbc4ec4
THD
3983 f['is_from_start'] = True
3984
a0bb6ce5 3985 yield f
c646d76f 3986 yield subtitles
11f9be09 3987
720c3099 3988 def _extract_storyboard(self, player_responses, duration):
3989 spec = get_first(
3990 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3991 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3992 if not base_url:
720c3099 3993 return
720c3099 3994 L = len(spec) - 1
3995 for i, args in enumerate(spec):
3996 args = args.split('#')
3997 counts = list(map(int_or_none, args[:5]))
3998 if len(args) != 8 or not all(counts):
3999 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
4000 continue
4001 width, height, frame_count, cols, rows = counts
4002 N, sigh = args[6:]
4003
4004 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
4005 fragment_count = frame_count / (cols * rows)
4006 fragment_duration = duration / fragment_count
4007 yield {
4008 'format_id': f'sb{i}',
4009 'format_note': 'storyboard',
4010 'ext': 'mhtml',
4011 'protocol': 'mhtml',
4012 'acodec': 'none',
4013 'vcodec': 'none',
4014 'url': url,
4015 'width': width,
4016 'height': height,
45e8a04e 4017 'fps': frame_count / duration,
4018 'rows': rows,
4019 'columns': cols,
720c3099 4020 'fragments': [{
b3edc806 4021 'url': url.replace('$M', str(j)),
720c3099 4022 'duration': min(fragment_duration, duration - (j * fragment_duration)),
4023 } for j in range(math.ceil(fragment_count))],
4024 }
4025
adbc4ec4 4026 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 4027 webpage = None
4028 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 4029 query = {'bpctr': '9999999999', 'has_verified': '1'}
546b2c28 4030 pp = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 4031 if pp:
4032 query['pp'] = pp
b6de707d 4033 webpage = self._download_webpage(
50ac0e54 4034 webpage_url, video_id, fatal=False, query=query)
11f9be09 4035
4036 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 4037
b6de707d 4038 player_responses, player_url = self._extract_player_responses(
11f9be09 4039 self._get_requested_clients(url, smuggled_data),
50ac0e54 4040 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 4041
adbc4ec4
THD
4042 return webpage, master_ytcfg, player_responses, player_url
4043
a1b2d843 4044 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
4045 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
4046 is_live = get_first(video_details, 'isLive')
4047 if is_live is None:
4048 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
4049 live_content = get_first(video_details, 'isLiveContent')
4050 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
4051 post_live = get_first(video_details, 'isPostLiveDvr')
4052 live_status = ('post_live' if post_live
4053 else 'is_live' if is_live
4054 else 'is_upcoming' if is_upcoming
6678a4f0 4055 else 'was_live' if live_content
4056 else 'not_live' if False in (is_live, live_content)
4057 else None)
6839ae1f 4058 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 4059 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
94ed638a 4060 if all(f.get('has_drm') for f in formats):
4061 # If there are no formats that definitely don't have DRM, all have DRM
4062 for f in formats:
4063 f['has_drm'] = True
adbc4ec4 4064
4d37720a 4065 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
4066
4067 def _real_extract(self, url):
4068 url, smuggled_data = unsmuggle_url(url, {})
4069 video_id = self._match_id(url)
4070
4071 base_url = self.http_scheme() + '//www.youtube.com/'
4072 webpage_url = base_url + 'watch?v=' + video_id
4073
4074 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
4075
11f9be09 4076 playability_statuses = traverse_obj(
6839ae1f 4077 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 4078
4079 trailer_video_id = get_first(
4080 playability_statuses,
4081 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4082 expected_type=str)
4083 if trailer_video_id:
4084 return self.url_result(
4085 trailer_video_id, self.ie_key(), trailer_video_id)
4086
4087 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4088 if webpage else (lambda x: None))
4089
6839ae1f 4090 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4091 microformats = traverse_obj(
4092 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4093 expected_type=dict)
c26f9b99 4094
4095 translated_title = self._get_text(microformats, (..., 'title'))
4096 video_title = (self._preferred_lang and translated_title
4097 or get_first(video_details, 'title') # primary
4098 or translated_title
4099 or search_meta(['og:title', 'twitter:title', 'title']))
4100 translated_description = self._get_text(microformats, (..., 'description'))
4101 original_description = get_first(video_details, 'shortDescription')
4102 video_description = (
4103 self._preferred_lang and translated_description
4104 # If original description is blank, it will be an empty string.
4105 # Do not prefer translated description in this case.
4106 or original_description if original_description is not None else translated_description)
11f9be09 4107
d89257f3 4108 multifeed_metadata_list = get_first(
4109 player_responses,
4110 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4111 expected_type=str)
4112 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4113 if self.get_param('noplaylist'):
11f9be09 4114 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4115 else:
4116 entries = []
4117 feed_ids = []
4118 for feed in multifeed_metadata_list.split(','):
4119 # Unquote should take place before split on comma (,) since textual
4120 # fields may contain comma as well (see
4121 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4122 feed_data = urllib.parse.parse_qs(
ac668111 4123 urllib.parse.unquote_plus(feed))
d89257f3 4124
4125 def feed_entry(name):
4126 return try_get(
14f25df2 4127 feed_data, lambda x: x[name][0], str)
d89257f3 4128
4129 feed_id = feed_entry('id')
4130 if not feed_id:
4131 continue
4132 feed_title = feed_entry('title')
4133 title = video_title
4134 if feed_title:
4135 title += ' (%s)' % feed_title
4136 entries.append({
4137 '_type': 'url_transparent',
4138 'ie_key': 'Youtube',
4139 'url': smuggle_url(
4140 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4141 {'force_singlefeed': True}),
4142 'title': title,
4143 })
4144 feed_ids.append(feed_id)
4145 self.to_screen(
4146 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4147 % (', '.join(feed_ids), video_id))
4148 return self.playlist_result(
4149 entries, video_id, video_title, video_description)
11f9be09 4150
9da6612b 4151 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4152 or int_or_none(get_first(microformats, 'lengthSeconds'))
4153 or parse_duration(search_meta('duration')) or None)
a1b2d843 4154
4d37720a
L
4155 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4156 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4157 if live_status == 'post_live':
4158 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4159
545cc85d 4160 if not formats:
11f9be09 4161 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4162 self.report_drm(video_id)
11f9be09 4163 pemr = get_first(
4164 playability_statuses,
4165 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4166 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4167 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4168 if subreason:
545cc85d 4169 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4170 countries = get_first(microformats, 'availableCountries')
545cc85d 4171 if not countries:
4172 regions_allowed = search_meta('regionsAllowed')
4173 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4174 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4175 reason += f'. {subreason}'
545cc85d 4176 if reason:
b7da73eb 4177 self.raise_no_formats(reason, expected=True)
bf1317d2 4178
11f9be09 4179 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4180 if not keywords and webpage:
4181 keywords = [
4182 unescapeHTML(m.group('content'))
4183 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4184 for keyword in keywords:
4185 if keyword.startswith('yt:stretch='):
201c1459 4186 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4187 if mobj:
4188 # NB: float is intentional for forcing float division
4189 w, h = (float(v) for v in mobj.groups())
4190 if w > 0 and h > 0:
4191 ratio = w / h
4192 for f in formats:
4193 if f.get('vcodec') != 'none':
4194 f['stretched_ratio'] = ratio
4195 break
a709d873 4196 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4197 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4198 if thumbnail_url:
4199 thumbnails.append({
4200 'url': thumbnail_url,
ff2751ac 4201 })
fccf5021 4202 original_thumbnails = thumbnails.copy()
4203
0ba692ac 4204 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4205 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4206 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4207 thumbnail_names = [
962ffcf8 4208 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4209 # in resolution, these are not the custom thumbnail. So de-prioritize them
4210 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4211 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4212 ]
cca80fe6 4213 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4214 thumbnails.extend({
4215 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4216 video_id=video_id, name=name, ext=ext,
4d37720a 4217 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4218 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4219 for thumb in thumbnails:
cca80fe6 4220 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4221 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4222 self._remove_duplicate_formats(thumbnails)
fccf5021 4223 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4224
7ea65411 4225 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4226 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4227 get_first(video_details, 'channelId')
4228 or get_first(microformats, 'externalChannelId')
7666b936 4229 or search_meta('channelId')))
7ea65411 4230 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4231
adbc4ec4
THD
4232 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4233 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4234 if not duration and live_end_time and live_start_time:
4235 duration = live_end_time - live_start_time
4236
4d37720a
L
4237 needs_live_processing = self._needs_live_processing(live_status, duration)
4238
4239 def is_bad_format(fmt):
4240 if needs_live_processing and not fmt.get('is_from_start'):
4241 return True
4242 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4243 and fmt.get('protocol') == 'http_dash_segments'):
4244 return True
4245
4246 for fmt in filter(is_bad_format, formats):
4247 fmt['preference'] = (fmt.get('preference') or -1) - 10
d949c10c 4248 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
4d37720a
L
4249
4250 if needs_live_processing:
4251 self._prepare_live_from_start_formats(
4252 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4253
720c3099 4254 formats.extend(self._extract_storyboard(player_responses, duration))
4255
7666b936 4256 channel_handle = self.handle_from_url(owner_profile_url)
4257
545cc85d 4258 info = {
4259 'id': video_id,
39ca3b5c 4260 'title': video_title,
545cc85d 4261 'formats': formats,
4262 'thumbnails': thumbnails,
fccf5021 4263 # The best thumbnail that we are sure exists. Prevents unnecessary
4264 # URL checking if user don't care about getting the best possible thumbnail
4265 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4266 'description': video_description,
545cc85d 4267 'channel_id': channel_id,
7666b936 4268 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4269 'duration': duration,
4270 'view_count': int_or_none(
11f9be09 4271 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4272 or search_meta('interactionCount')),
11f9be09 4273 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4274 'age_limit': 18 if (
11f9be09 4275 get_first(microformats, 'isFamilySafe') is False
545cc85d 4276 or search_meta('isFamilyFriendly') == 'false'
4277 or search_meta('og:restrictions:age') == '18+') else 0,
4278 'webpage_url': webpage_url,
4279 'categories': [category] if category else None,
4280 'tags': keywords,
11f9be09 4281 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4282 'live_status': live_status,
adbc4ec4 4283 'release_timestamp': live_start_time,
9f14daf2 4284 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4285 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4286 }
b477fc13 4287
c646d76f 4288 subtitles = {}
3944e7af 4289 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4290 if pctr:
ecdc9049 4291 def get_lang_code(track):
4292 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4293 or track.get('languageCode'))
4294
4295 # Converted into dicts to remove duplicates
4296 captions = {
4297 get_lang_code(sub): sub
6839ae1f 4298 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4299 translation_languages = {
4300 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4301 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4302
774d79cc 4303 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4304 lang_subs = container.setdefault(lang_code, [])
545cc85d 4305 for fmt in self._SUBTITLE_FORMATS:
4306 query.update({
4307 'fmt': fmt,
4308 })
4309 lang_subs.append({
4310 'ext': fmt,
60f393e4 4311 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4312 'name': sub_name,
545cc85d 4313 })
7e72694b 4314
07b47084 4315 # NB: Constructing the full subtitle dictionary is slow
4316 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4317 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4318 for lang_code, caption_track in captions.items():
4319 base_url = caption_track.get('baseUrl')
1235d333 4320 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4321 if not base_url:
4322 continue
ecdc9049 4323 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4324 if caption_track.get('kind') != 'asr':
545cc85d 4325 if not lang_code:
4326 continue
4327 process_language(
ecdc9049 4328 subtitles, base_url, lang_code, lang_name, {})
4329 if not caption_track.get('isTranslatable'):
4330 continue
3944e7af 4331 for trans_code, trans_name in translation_languages.items():
4332 if not trans_code:
545cc85d 4333 continue
1235d333 4334 orig_trans_code = trans_code
71eb82d1 4335 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4336 if not get_translated_subs:
18e49408 4337 continue
ecdc9049 4338 trans_code += f'-{lang_code}'
a70635b8 4339 trans_name += format_field(lang_name, None, ' from %s')
1235d333 4340 if lang_code == f'a-{orig_trans_code}':
ff9b0e07 4341 # Set audio language based on original subtitles
4342 for f in formats:
4343 if f.get('acodec') != 'none' and not f.get('language'):
4344 f['language'] = orig_trans_code
4345 # Add an "-orig" label to the original language so that it can be distinguished.
4346 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 4347 process_language(
d49669ac 4348 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4349 # Setting tlang=lang returns damaged subtitles.
d49669ac 4350 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4351 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4352
4353 info['automatic_captions'] = automatic_captions
4354 info['subtitles'] = subtitles
7e72694b 4355
14f25df2 4356 parsed_url = urllib.parse.urlparse(url)
545cc85d 4357 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4358 query = urllib.parse.parse_qs(component)
545cc85d 4359 for k, v in query.items():
4360 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4361 d_k += '_time'
4362 if d_k not in info and k in s_ks:
4363 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4364
4365 # Youtube Music Auto-generated description
71dc18fa
BT
4366 if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
4367 # XXX: Causes catastrophic backtracking if description has "·"
4368 # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
4369 # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
4370 # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
1890fc63 4371 mobj = re.search(
4372 r'''(?xs)
71dc18fa
BT
4373 (?=(?P<track>[^\n·]+))(?P=track)·
4374 (?=(?P<artist>[^\n]+))(?P=artist)\n+
4375 (?=(?P<album>[^\n]+))(?P=album)\n
1890fc63 4376 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4377 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
71dc18fa
BT
4378 (.+?\nArtist\s*:\s*
4379 (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
4380 )?.+\nAuto-generated\ by\ YouTube\.\s*$
1890fc63 4381 ''', video_description)
822b9d9c 4382 if mobj:
822b9d9c
RA
4383 release_year = mobj.group('release_year')
4384 release_date = mobj.group('release_date')
4385 if release_date:
4386 release_date = release_date.replace('-', '')
4387 if not release_year:
545cc85d 4388 release_year = release_date[:4]
4389 info.update({
4390 'album': mobj.group('album'.strip()),
104a7b5a
L
4391 'artists': ([a] if (a := mobj.group('clean_artist'))
4392 else [a.strip() for a in mobj.group('artist').split('·')]),
545cc85d 4393 'track': mobj.group('track').strip(),
4394 'release_date': release_date,
cc2db878 4395 'release_year': int_or_none(release_year),
545cc85d 4396 })
7e72694b 4397
545cc85d 4398 initial_data = None
4399 if webpage:
56ba69e4 4400 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4401 if not traverse_obj(initial_data, 'contents'):
4402 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4403 initial_data = None
545cc85d 4404 if not initial_data:
99e9e001 4405 query = {'videoId': video_id}
4406 query.update(self._get_checkok_params())
109dd3b2 4407 initial_data = self._extract_response(
4408 item_id=video_id, ep='next', fatal=False,
607510b9 4409 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4410 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4411 note='Downloading initial data API JSON')
545cc85d 4412
0df111a3 4413 info['comment_count'] = traverse_obj(initial_data, (
4414 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4415 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4416 ), (
4417 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4418 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4419 ), expected_type=self._get_count, get_all=False)
0df111a3 4420
19a03940 4421 try: # This will error if there is no livechat
c60ee3a2 4422 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4423 except (KeyError, IndexError, TypeError):
4424 pass
4425 else:
ecdc9049 4426 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4427 # url is needed to set cookies
4428 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4429 'video_id': video_id,
4430 'ext': 'json',
4d37720a
L
4431 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4432 else 'youtube_live_chat_replay'),
c60ee3a2 4433 }]
545cc85d 4434
4435 if initial_data:
7c365c21 4436 info['chapters'] = (
4437 self._extract_chapters_from_json(initial_data, duration)
4438 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4439 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4440 or None)
545cc85d 4441
03e85ea9 4442 info['heatmap'] = self._extract_heatmap(initial_data)
5caf30db 4443
17322130 4444 contents = traverse_obj(
4445 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4446 expected_type=list, default=[])
4447
4448 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4449 if vpir:
4450 stl = vpir.get('superTitleLink')
4451 if stl:
4452 stl = self._get_text(stl)
4453 if try_get(
4454 vpir,
4455 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4456 info['location'] = stl
4457 else:
affc4fef 4458 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4459 if mobj:
545cc85d 4460 info.update({
17322130 4461 'series': mobj.group(1),
4462 'season_number': int(mobj.group(2)),
4463 'episode_number': int(mobj.group(3)),
545cc85d 4464 })
17322130 4465 for tlb in (try_get(
4466 vpir,
4467 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4468 list) or []):
3ffb2f5b 4469 tbrs = variadic(
4470 traverse_obj(
6839ae1f
SS
4471 tlb, ('toggleButtonRenderer', ...),
4472 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4473 for tbr in tbrs:
4474 for getter, regex in [(
4475 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4476 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4477 lambda x: x['accessibility'],
4478 lambda x: x['accessibilityData']['accessibilityData'],
4479 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4480 label = (try_get(tbr, getter, dict) or {}).get('label')
4481 if label:
4482 mobj = re.match(regex, label)
4483 if mobj:
4484 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4485 break
6b5d93b0
PG
4486
4487 info['like_count'] = traverse_obj(vpir, (
4488 'videoActions', 'menuRenderer', 'topLevelButtons', ...,
4489 'segmentedLikeDislikeButtonViewModel', 'likeButtonViewModel', 'likeButtonViewModel',
4490 'toggleButtonViewModel', 'toggleButtonViewModel', 'defaultButtonViewModel',
4491 'buttonViewModel', 'accessibilityText', {parse_count}), get_all=False)
4492
867c66ff
M
4493 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4494 if vcr:
4495 vc = self._get_count(vcr, 'viewCount')
4496 # Upcoming premieres with waiting count are treated as live here
4497 if vcr.get('isLive'):
4498 info['concurrent_view_count'] = vc
4499 elif info.get('view_count') is None:
4500 info['view_count'] = vc
4501
17322130 4502 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4503 if vsir:
4504 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4505 info.update({
4506 'channel': self._get_text(vor, 'title'),
4507 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4508
7666b936 4509 if not channel_handle:
4510 channel_handle = self.handle_from_url(
4511 traverse_obj(vor, (
4512 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4513 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4514 {str}), get_all=False))
4515
17322130 4516 rows = try_get(
4517 vsir,
4518 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4519 list) or []
4520 multiple_songs = False
4521 for row in rows:
4522 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4523 multiple_songs = True
4524 break
4525 for row in rows:
4526 mrr = row.get('metadataRowRenderer') or {}
4527 mrr_title = mrr.get('title')
4528 if not mrr_title:
4529 continue
4530 mrr_title = self._get_text(mrr, 'title')
4531 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4532 if mrr_title == 'License':
4533 info['license'] = mrr_contents_text
4534 elif not multiple_songs:
4535 if mrr_title == 'Album':
4536 info['album'] = mrr_contents_text
4537 elif mrr_title == 'Artist':
104a7b5a 4538 info['artists'] = [mrr_contents_text] if mrr_contents_text else None
17322130 4539 elif mrr_title == 'Song':
4540 info['track'] = mrr_contents_text
8213ce28 4541 owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
4542 if self._has_badge(owner_badges, BadgeType.VERIFIED):
4543 info['channel_is_verified'] = True
545cc85d 4544
7666b936 4545 info.update({
4546 'uploader': info.get('channel'),
4547 'uploader_id': channel_handle,
4548 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4549 })
17322130 4550 # The upload date for scheduled, live and past live streams / premieres in microformats
4551 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4552 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4553 upload_date = (
4554 unified_strdate(get_first(microformats, 'uploadDate'))
4555 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4556 if not upload_date or (
4d37720a 4557 live_status in ('not_live', None)
1ff88b7a 4558 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4559 ):
c26f9b99 4560 upload_date = strftime_or_none(
ad54c913 4561 self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
17322130 4562 info['upload_date'] = upload_date
992f9a73 4563
ef79d20d 4564 if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
4565 # Newly uploaded videos' HLS formats are potentially problematic and need to be checked
4566 upload_datetime = datetime_from_str(upload_date).replace(tzinfo=datetime.timezone.utc)
bb5a54e6 4567 if upload_datetime >= datetime_from_str('today-2days'):
ef79d20d 4568 for fmt in info['formats']:
4569 if fmt.get('protocol') == 'm3u8_native':
4570 fmt['__needs_testing'] = True
4571
104a7b5a 4572 for s_k, d_k in [('artists', 'creators'), ('track', 'alt_title')]:
545cc85d 4573 v = info.get(s_k)
4574 if v:
4575 info[d_k] = v
b84071c0 4576
14a14335 4577 badges = self._extract_badges(traverse_obj(vpir, 'badges'))
c26f9b99 4578
4579 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4580 or get_first(video_details, 'isPrivate', expected_type=bool))
4581
4582 info['availability'] = (
4583 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4584 else self._availability(
4585 is_private=is_private,
4586 needs_premium=(
4587 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4588 or False if initial_data and is_private is not None else None),
4589 needs_subscription=(
4590 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4591 or False if initial_data and is_private is not None else None),
4592 needs_auth=info['age_limit'] >= 18,
4593 is_unlisted=None if is_private is None else (
4594 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4595 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4596
a2160aa4 4597 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4598
11f9be09 4599 self.mark_watched(video_id, player_responses)
d77ab8e2 4600
545cc85d 4601 return info
c5e8d7af 4602
a61fd4cf 4603
a6213a49 4604class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4605 @staticmethod
4606 def passthrough_smuggled_data(func):
bd7e919a 4607 def _smuggle(info, smuggled_data):
4608 if info.get('_type') not in ('url', 'url_transparent'):
4609 return info
4610 if smuggled_data.get('is_music_url'):
4611 parsed_url = urllib.parse.urlparse(info['url'])
4612 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4613 smuggled_data.pop('is_music_url')
4614 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4615 if smuggled_data:
4616 info['url'] = smuggle_url(info['url'], smuggled_data)
4617 return info
182bda88 4618
4619 @functools.wraps(func)
4620 def wrapper(self, url):
4621 url, smuggled_data = unsmuggle_url(url, {})
4622 if self.is_music_url(url):
4623 smuggled_data['is_music_url'] = True
4624 info_dict = func(self, url, smuggled_data)
bd7e919a 4625 if smuggled_data:
4626 _smuggle(info_dict, smuggled_data)
4627 if info_dict.get('entries'):
a8c754cc 4628 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4629 return info_dict
4630 return wrapper
4631
8bdd16b4 4632 @staticmethod
cd7c66cf 4633 def _extract_basic_item_renderer(item):
4634 # Modified from _extract_grid_item_renderer
201c1459 4635 known_basic_renderers = (
a17526e4 4636 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4637 )
4638 for key, renderer in item.items():
201c1459 4639 if not isinstance(renderer, dict):
cd7c66cf 4640 continue
201c1459 4641 elif key in known_basic_renderers:
4642 return renderer
4643 elif key.startswith('grid') and key.endswith('Renderer'):
4644 return renderer
8bdd16b4 4645
c7335551 4646 def _extract_channel_renderer(self, renderer):
7666b936 4647 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4648 title = self._get_text(renderer, 'title')
7666b936 4649 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
7666b936 4650 channel_handle = self.handle_from_url(
4651 traverse_obj(renderer, (
4652 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4653 ('browseEndpoint', 'canonicalBaseUrl')),
4654 {str}), get_all=False))
14a14335 4655 if not channel_handle:
4656 # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
4657 channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
c7335551
M
4658 return {
4659 '_type': 'url',
4660 'url': channel_url,
4661 'id': channel_id,
4662 'ie_key': YoutubeTabIE.ie_key(),
4663 'channel': title,
7666b936 4664 'uploader': title,
c7335551
M
4665 'channel_id': channel_id,
4666 'channel_url': channel_url,
4667 'title': title,
7666b936 4668 'uploader_id': channel_handle,
4669 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
14a14335 4670 # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
4671 # However, in feed/channels this is set correctly to the subscriber count
4672 'channel_follower_count': traverse_obj(
4673 renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
c7335551 4674 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
14a14335 4675 'playlist_count': (
4676 # videoCountText may be the subscriber count
4677 self._get_count(renderer, 'videoCountText')
4678 if self._get_count(renderer, 'subscriberCountText') is not None else None),
c7335551 4679 'description': self._get_text(renderer, 'descriptionSnippet'),
8213ce28 4680 'channel_is_verified': True if self._has_badge(
4681 self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
c7335551
M
4682 }
4683
8bdd16b4 4684 def _grid_entries(self, grid_renderer):
4685 for item in grid_renderer['items']:
4686 if not isinstance(item, dict):
39b62db1 4687 continue
cd7c66cf 4688 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4689 if not isinstance(renderer, dict):
4690 continue
052e1350 4691 title = self._get_text(renderer, 'title')
fe93e2c4 4692
8bdd16b4 4693 # playlist
4694 playlist_id = renderer.get('playlistId')
4695 if playlist_id:
4696 yield self.url_result(
4697 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4698 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4699 video_title=title)
201c1459 4700 continue
8bdd16b4 4701 # video
4702 video_id = renderer.get('videoId')
4703 if video_id:
4704 yield self._extract_video(renderer)
201c1459 4705 continue
8bdd16b4 4706 # channel
4707 channel_id = renderer.get('channelId')
4708 if channel_id:
c7335551 4709 yield self._extract_channel_renderer(renderer)
201c1459 4710 continue
4711 # generic endpoint URL support
4712 ep_url = urljoin('https://www.youtube.com/', try_get(
4713 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4714 str))
201c1459 4715 if ep_url:
4716 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4717 if ie.suitable(ep_url):
4718 yield self.url_result(
4719 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4720 break
8bdd16b4 4721
16aa9ea4 4722 def _music_reponsive_list_entry(self, renderer):
4723 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4724 if video_id:
69a40e4a 4725 title = traverse_obj(renderer, (
4726 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4727 'text', 'runs', 0, 'text'))
16aa9ea4 4728 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4729 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4730 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4731 if playlist_id:
4732 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4733 if video_id:
4734 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4735 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4736 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4737 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4738 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4739 if browse_id:
4740 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4741 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4742
3d3dddc9 4743 def _shelf_entries_from_content(self, shelf_renderer):
4744 content = shelf_renderer.get('content')
4745 if not isinstance(content, dict):
8bdd16b4 4746 return
cd7c66cf 4747 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4748 if renderer:
4749 # TODO: add support for nested playlists so each shelf is processed
4750 # as separate playlist
4751 # TODO: this includes only first N items
86e5f3ed 4752 yield from self._grid_entries(renderer)
3d3dddc9 4753 renderer = content.get('horizontalListRenderer')
4754 if renderer:
4755 # TODO
4756 pass
8bdd16b4 4757
29f7c58a 4758 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4759 ep = try_get(
4760 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4761 str)
8bdd16b4 4762 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4763 if shelf_url:
29f7c58a 4764 # Skipping links to another channels, note that checking for
4765 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4766 # will not work
4767 if skip_channels and '/channels?' in shelf_url:
4768 return
052e1350 4769 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4770 yield self.url_result(shelf_url, video_title=title)
4771 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4772 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4773
8bdd16b4 4774 def _playlist_entries(self, video_list_renderer):
4775 for content in video_list_renderer['contents']:
4776 if not isinstance(content, dict):
4777 continue
4778 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4779 if not isinstance(renderer, dict):
4780 continue
4781 video_id = renderer.get('videoId')
4782 if not video_id:
4783 continue
4784 yield self._extract_video(renderer)
07aeced6 4785
3462ffa8 4786 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4787 renderer = traverse_obj(
447afb9e 4788 rich_grid_renderer,
4789 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4790 video_id = renderer.get('videoId')
447afb9e 4791 if video_id:
4792 yield self._extract_video(renderer)
4793 return
4794 playlist_id = renderer.get('playlistId')
4795 if playlist_id:
4796 yield self.url_result(
4797 f'https://www.youtube.com/playlist?list={playlist_id}',
4798 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4799 video_title=self._get_text(renderer, 'title'))
3462ffa8 4800 return
3462ffa8 4801
8bdd16b4 4802 def _video_entry(self, video_renderer):
4803 video_id = video_renderer.get('videoId')
4804 if video_id:
4805 return self._extract_video(video_renderer)
dacb3a86 4806
ad210f4f 4807 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4808 url = urljoin('https://youtube.com', traverse_obj(
4809 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4810 if url:
4811 return self.url_result(
4812 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4813
8bdd16b4 4814 def _post_thread_entries(self, post_thread_renderer):
4815 post_renderer = try_get(
4816 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4817 if not post_renderer:
4818 return
4819 # video attachment
4820 video_renderer = try_get(
895b0931 4821 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4822 video_id = video_renderer.get('videoId')
4823 if video_id:
4824 entry = self._extract_video(video_renderer)
8bdd16b4 4825 if entry:
4826 yield entry
895b0931 4827 # playlist attachment
4828 playlist_id = try_get(
14f25df2 4829 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4830 if playlist_id:
4831 yield self.url_result(
e28f1c0a 4832 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4833 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4834 # inline video links
4835 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4836 for run in runs:
4837 if not isinstance(run, dict):
4838 continue
4839 ep_url = try_get(
14f25df2 4840 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4841 if not ep_url:
4842 continue
4843 if not YoutubeIE.suitable(ep_url):
4844 continue
4845 ep_video_id = YoutubeIE._match_id(ep_url)
4846 if video_id == ep_video_id:
4847 continue
895b0931 4848 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4849
8bdd16b4 4850 def _post_thread_continuation_entries(self, post_thread_continuation):
4851 contents = post_thread_continuation.get('contents')
4852 if not isinstance(contents, list):
4853 return
4854 for content in contents:
4855 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4856 if isinstance(renderer, dict):
4857 yield from self._post_thread_entries(renderer)
8bdd16b4 4858 continue
6b0b0a28 4859 renderer = content.get('videoRenderer')
4860 if isinstance(renderer, dict):
4861 yield self._video_entry(renderer)
07aeced6 4862
39ed931e 4863 r''' # unused
4864 def _rich_grid_entries(self, contents):
4865 for content in contents:
4866 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4867 if video_renderer:
4868 entry = self._video_entry(video_renderer)
4869 if entry:
4870 yield entry
4871 '''
52efa4b3 4872
0a5095fe 4873 def _report_history_entries(self, renderer):
4874 for url in traverse_obj(renderer, (
7a32c70d 4875 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4876 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4877 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4878 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4879
a6213a49 4880 def _extract_entries(self, parent_renderer, continuation_list):
4881 # continuation_list is modified in-place with continuation_list = [continuation_token]
4882 continuation_list[:] = [None]
4883 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4884 for content in contents:
4885 if not isinstance(content, dict):
4886 continue
16aa9ea4 4887 is_renderer = traverse_obj(
4888 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4889 expected_type=dict)
a6213a49 4890 if not is_renderer:
0a5095fe 4891 if content.get('richItemRenderer'):
4892 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4893 yield entry
4894 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4895 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4896 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4897 yield from self._report_history_entries(table)
4898 continuation_list[0] = self._extract_continuation(table)
a6213a49 4899 continue
0a5095fe 4900
a6213a49 4901 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4902 for isr_content in isr_contents:
4903 if not isinstance(isr_content, dict):
8bdd16b4 4904 continue
69184e41 4905
a6213a49 4906 known_renderers = {
4907 'playlistVideoListRenderer': self._playlist_entries,
4908 'gridRenderer': self._grid_entries,
a17526e4 4909 'reelShelfRenderer': self._grid_entries,
4910 'shelfRenderer': self._shelf_entries,
16aa9ea4 4911 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4912 'backstagePostThreadRenderer': self._post_thread_entries,
4913 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4914 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4915 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
fcbc9ed7 4916 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
4917 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
a6213a49 4918 }
4919 for key, renderer in isr_content.items():
4920 if key not in known_renderers:
4921 continue
4922 for entry in known_renderers[key](renderer):
4923 if entry:
4924 yield entry
4925 continuation_list[0] = self._extract_continuation(renderer)
4926 break
70d5c17b 4927
4928 if not continuation_list[0]:
a6213a49 4929 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4930
a6213a49 4931 if not continuation_list[0]:
4932 continuation_list[0] = self._extract_continuation(parent_renderer)
4933
4934 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4935 continuation_list = [None]
4936 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4937 tab_content = try_get(tab, lambda x: x['content'], dict)
4938 if not tab_content:
4939 return
3462ffa8 4940 parent_renderer = (
29f7c58a 4941 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4942 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4943 yield from extract_entries(parent_renderer)
3462ffa8 4944 continuation = continuation_list[0]
1ba6fe9d 4945 seen_continuations = set()
8bdd16b4 4946 for page_num in itertools.count(1):
4947 if not continuation:
4948 break
1ba6fe9d 4949 continuation_token = continuation.get('continuation')
4950 if continuation_token is not None and continuation_token in seen_continuations:
4951 self.write_debug('Detected YouTube feed looping - assuming end of feed.')
4952 break
4953 seen_continuations.add(continuation_token)
99e9e001 4954 headers = self.generate_api_headers(
4955 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4956 response = self._extract_response(
86e5f3ed 4957 item_id=f'{item_id} page {page_num}',
fe93e2c4 4958 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4959 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4960
4961 if not response:
8bdd16b4 4962 break
ac56cf38 4963 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4964 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4965 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4966
a1b535bd 4967 known_renderers = {
e4b98809 4968 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4969 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4970 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4971 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4972 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4973 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4974 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4975 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4976 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4977 'playlistVideoListContinuation': (self._playlist_entries, None),
4978 'gridContinuation': (self._grid_entries, None),
4979 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4980 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4981 }
1fb53b94 4982
4983 continuation_items = traverse_obj(response, (
4984 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4985 'appendContinuationItemsAction', 'continuationItems'
4986 ), 'continuationContents', get_all=False)
4987 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4988
a1b535bd 4989 video_items_renderer = None
1fb53b94 4990 for key in continuation_item.keys():
a1b535bd 4991 if key not in known_renderers:
8bdd16b4 4992 continue
1fb53b94 4993 func, parent_key = known_renderers[key]
4994 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4995 continuation_list = [None]
1fb53b94 4996 yield from func(video_items_renderer)
9ba5705a 4997 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4998
4999 if not video_items_renderer:
a1b535bd 5000 break
9558dcec 5001
8bdd16b4 5002 @staticmethod
7c219ea6 5003 def _extract_selected_tab(tabs, fatal=True):
86973308
M
5004 for tab_renderer in tabs:
5005 if tab_renderer.get('selected'):
5006 return tab_renderer
5007 if fatal:
5008 raise ExtractorError('Unable to find selected tab')
5009
5010 @staticmethod
5011 def _extract_tab_renderers(response):
5012 return traverse_obj(
5013 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 5014
ac56cf38 5015 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 5016 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 5017
8bdd16b4 5018 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 5019 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
5020 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
5021
5022 return self.playlist_result(
5023 self._entries(
5024 selected_tab, metadata['id'], ytcfg,
5025 self._extract_account_syncid(ytcfg, data),
5026 self._extract_visitor_data(data, ytcfg)),
5027 **metadata)
39ed931e 5028
bd7e919a 5029 def _extract_metadata_from_tabs(self, item_id, data):
5030 info = {'id': item_id}
5031
5032 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 5033 if metadata_renderer:
7666b936 5034 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 5035 ('channelUrl', {self.ucid_from_url}))
bd7e919a 5036 info.update({
7666b936 5037 'channel': metadata_renderer.get('title'),
5038 'channel_id': channel_id,
bd7e919a 5039 })
7666b936 5040 if info['channel_id']:
5041 info['id'] = info['channel_id']
bd7e919a 5042 else:
5043 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 5044
301d07fc 5045 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
5046 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
5047 def _get_uncropped(url):
5048 return url_or_none((url or '').split('=')[0] + '=s0')
5049
6141346d 5050 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 5051 if avatar_thumbnails:
5052 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
5053 if uncropped_avatar:
5054 avatar_thumbnails.append({
5055 'url': uncropped_avatar,
5056 'id': 'avatar_uncropped',
5057 'preference': 1
5058 })
5059
5060 channel_banners = self._extract_thumbnails(
bd7e919a 5061 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 5062 for banner in channel_banners:
5063 banner['preference'] = -10
5064
5065 if channel_banners:
5066 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
5067 if uncropped_banner:
5068 channel_banners.append({
5069 'url': uncropped_banner,
5070 'id': 'banner_uncropped',
5071 'preference': -5
5072 })
5073
bd7e919a 5074 # Deprecated - remove primary_sidebar_renderer when layout discontinued
5075 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
5076 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
5077
301d07fc 5078 primary_thumbnails = self._extract_thumbnails(
a17526e4 5079 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
5080 playlist_thumbnails = self._extract_thumbnails(
5081 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
5082
bd7e919a 5083 info.update({
5084 'title': (traverse_obj(metadata_renderer, 'title')
5085 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
5086 or info['id']),
5087 'availability': self._extract_availability(data),
5088 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
5089 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
5090 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
5091 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
5092 })
f0d785d3 5093
7666b936 5094 channel_handle = (
5095 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
5096 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
5097
5098 if channel_handle:
5099 info.update({
5100 'uploader_id': channel_handle,
5101 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
5102 })
8213ce28 5103
5104 channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
5105 if self._has_badge(channel_badges, BadgeType.VERIFIED):
5106 info['channel_is_verified'] = True
6141346d
M
5107 # Playlist stats is a text runs array containing [video count, view count, last updated].
5108 # last updated or (view count and last updated) may be missing.
5109 playlist_stats = get_first(
bd7e919a 5110 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
5111
6141346d
M
5112 last_updated_unix = self._parse_time_text(
5113 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
5114 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
ad54c913 5115 info['modified_date'] = strftime_or_none(last_updated_unix)
6141346d 5116
bd7e919a 5117 info['view_count'] = self._get_count(playlist_stats, 1)
5118 if info['view_count'] is None: # 0 is allowed
5119 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5120 if info['view_count'] is None:
5121 info['view_count'] = self._get_count(data, (
5122 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5123 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5124
5125 info['playlist_count'] = self._get_count(playlist_stats, 0)
5126 if info['playlist_count'] is None: # 0 is allowed
5127 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5128
7666b936 5129 if not info.get('channel_id'):
6141346d 5130 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5131 if not owner: # Deprecated
6141346d
M
5132 owner = traverse_obj(
5133 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5134 ('videoOwner', 'videoOwnerRenderer', 'title'))
5135 owner_text = self._get_text(owner)
5136 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5137 info.update({
7666b936 5138 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5139 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5140 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5141 })
6141346d 5142
bd7e919a 5143 info.update({
7666b936 5144 'uploader': info['channel'],
5145 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5146 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5147 })
7666b936 5148
bd7e919a 5149 return info
73c4ac2c 5150
6e634cbe 5151 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5152 first_id = last_id = response = None
2be71994 5153 for page_num in itertools.count(1):
cd7c66cf 5154 videos = list(self._playlist_entries(playlist))
5155 if not videos:
5156 return
2be71994 5157 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5158 if start >= len(videos):
5159 return
24146491 5160 yield from videos[start:]
2be71994 5161 first_id = first_id or videos[0]['id']
5162 last_id = videos[-1]['id']
79360d99 5163 watch_endpoint = try_get(
5164 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5165 headers = self.generate_api_headers(
5166 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5167 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5168 query = {
5169 'playlistId': playlist_id,
5170 'videoId': watch_endpoint.get('videoId') or last_id,
5171 'index': watch_endpoint.get('index') or len(videos),
5172 'params': watch_endpoint.get('params') or 'OAE%3D'
5173 }
5174 response = self._extract_response(
5175 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5176 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5177 check_get_keys='contents'
5178 )
cd7c66cf 5179 playlist = try_get(
79360d99 5180 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5181
ac56cf38 5182 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5183 title = playlist.get('title') or try_get(
14f25df2 5184 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5185 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5186
5187 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5188 playlist_url = urljoin(url, try_get(
5189 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5190 str))
6e634cbe 5191
5192 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5193 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5194 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5195
5196 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5197 return self.url_result(
5198 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5199 video_title=title)
cd7c66cf 5200
8bdd16b4 5201 return self.playlist_result(
6e634cbe 5202 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5203 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5204
47193e02 5205 def _extract_availability(self, data):
5206 """
5207 Gets the availability of a given playlist/tab.
5208 Note: Unless YouTube tells us explicitly, we do not assume it is public
5209 @param data: response
5210 """
6141346d
M
5211 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5212 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5213 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5214
14a14335 5215 badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
47193e02 5216
5217 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5218 privacy_setting_icon = get_first(
5219 (playlist_header_renderer, sidebar_renderer),
5220 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5221 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5222 expected_type=str)
5223
5224 microformats_is_unlisted = traverse_obj(
5225 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5226
c26f9b99 5227 return (
5228 'public' if (
5229 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5230 or player_header_privacy == 'PUBLIC'
5231 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5232 else self._availability(
5233 is_private=(
5234 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5235 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5236 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5237 is_unlisted=(
5238 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5239 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5240 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5241 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5242 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5243 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5244 needs_auth=False))
47193e02 5245
5246 @staticmethod
5247 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5248 sidebar_renderer = try_get(
5249 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5250 for item in sidebar_renderer:
5251 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5252 if renderer:
5253 return renderer
5254
ac56cf38 5255 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5256 """
6141346d 5257 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5258 """
6141346d
M
5259 is_playlist = bool(traverse_obj(
5260 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5261 if not is_playlist:
47193e02 5262 return
11f9be09 5263 headers = self.generate_api_headers(
99e9e001 5264 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5265 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5266 query = {
6141346d
M
5267 'params': 'wgYCCAA=',
5268 'browseId': f'VL{item_id}'
47193e02 5269 }
5270 return self._extract_response(
5271 item_id=item_id, headers=headers, query=query,
fe93e2c4 5272 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5273 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5274
2762dbb1 5275 @functools.cached_property
a25bca9f 5276 def skip_webpage(self):
5277 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5278
ac56cf38 5279 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5280 webpage, data = None, None
5281 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5282 try:
be5c1ae8 5283 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5284 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5285 except ExtractorError as e:
5286 if isinstance(e.cause, network_exceptions):
3d2623a8 5287 if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
be5c1ae8 5288 retry.error = e
5289 continue
5290 self._error_or_warning(e, fatal=fatal)
14fdfea9 5291 break
ac56cf38 5292
be5c1ae8 5293 try:
5294 self._extract_and_report_alerts(data)
5295 except ExtractorError as e:
5296 self._error_or_warning(e, fatal=fatal)
5297 break
ac56cf38 5298
be5c1ae8 5299 # Sometimes youtube returns a webpage with incomplete ytInitialData
5300 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5301 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5302 retry.error = ExtractorError('Incomplete yt initial data received')
f9fb3ce8 5303 data = None
be5c1ae8 5304 continue
ac56cf38 5305
cd7c66cf 5306 return webpage, data
5307
a25bca9f 5308 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5309 """Use if failed to extract ytcfg (and data) from initial webpage"""
5310 if not ytcfg and self.is_authenticated:
5311 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5312 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5313 raise ExtractorError(
5314 f'{msg}. If you are not downloading private content, or '
5315 'your cookies are only for the first account and channel,'
5316 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5317 expected=True)
5318 self.report_warning(msg, only_once=True)
5319
ac56cf38 5320 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5321 data = None
a25bca9f 5322 if not self.skip_webpage:
ac56cf38 5323 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5324 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5325 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5326 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5327 if (url != 'https://www.youtube.com/feed/recommended'
5328 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5329 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5330 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5331 if fatal:
5332 raise ExtractorError(msg, expected=True)
5333 self.report_warning(msg, only_once=True)
ac56cf38 5334 if not data:
a25bca9f 5335 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5336 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5337 return data, ytcfg
5338
5339 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5340 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5341 resolve_response = self._extract_response(
5342 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5343 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5344 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5345 for ep_key, ep in endpoints.items():
5346 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5347 if params:
5348 return self._extract_response(
5349 item_id=item_id, query=params, ep=ep, headers=headers,
5350 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5351 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5352 err_note = 'Failed to resolve url (does the playlist exist?)'
5353 if fatal:
5354 raise ExtractorError(err_note, expected=True)
5355 self.report_warning(err_note, item_id)
5356
a6213a49 5357 _SEARCH_PARAMS = None
5358
af5c1c55 5359 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5360 data = {'query': query}
5361 if params is NO_DEFAULT:
5362 params = self._SEARCH_PARAMS
5363 if params:
5364 data['params'] = params
16aa9ea4 5365
5366 content_keys = (
5367 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5368 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5369 # ytmusic search
5370 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5371 ('continuationContents', ),
5372 )
a25bca9f 5373 display_id = f'query "{query}"'
86e5f3ed 5374 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5375 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5376 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5377
a61fd4cf 5378 continuation_list = [None]
a25bca9f 5379 search = None
a6213a49 5380 for page_num in itertools.count(1):
a61fd4cf 5381 data.update(continuation_list[0] or {})
a25bca9f 5382 headers = self.generate_api_headers(
5383 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5384 search = self._extract_response(
a25bca9f 5385 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5386 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5387 slr_contents = traverse_obj(search, *content_keys)
5388 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5389 if not continuation_list[0]:
a6213a49 5390 break
5391
5392
5393class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5394 IE_DESC = 'YouTube Tabs'
5395 _VALID_URL = r'''(?x:
5396 https?://
b032ff0f 5397 (?!consent\.)(?:\w+\.)?
a6213a49 5398 (?:
5399 youtube(?:kids)?\.com|
5400 %(invidious)s
5401 )/
5402 (?:
5403 (?P<channel_type>channel|c|user|browse)/|
5404 (?P<not_channel>
5405 feed/|hashtag/|
5406 (?:playlist|watch)\?.*?\blist=
5407 )|
5408 (?!(?:%(reserved_names)s)\b) # Direct URLs
5409 )
5410 (?P<id>[^/?\#&]+)
5411 )''' % {
5412 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5413 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5414 }
5415 IE_NAME = 'youtube:tab'
5416
5417 _TESTS = [{
5418 'note': 'playlists, multipage',
5419 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5420 'playlist_mincount': 94,
5421 'info_dict': {
5422 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5423 'title': 'Igor Kleiner - Playlists',
a6213a49 5424 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5425 'uploader': 'Igor Kleiner',
7666b936 5426 'uploader_id': '@IgorDataScience',
5427 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5428 'channel': 'Igor Kleiner',
5429 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5430 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5431 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5432 'channel_follower_count': int
a6213a49 5433 },
5434 }, {
5435 'note': 'playlists, multipage, different order',
5436 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5437 'playlist_mincount': 94,
5438 'info_dict': {
5439 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5440 'title': 'Igor Kleiner - Playlists',
a6213a49 5441 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5442 'uploader': 'Igor Kleiner',
7666b936 5443 'uploader_id': '@IgorDataScience',
5444 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5445 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5446 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5447 'channel': 'Igor Kleiner',
5448 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5449 'channel_follower_count': int
a6213a49 5450 },
5451 }, {
5452 'note': 'playlists, series',
5453 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5454 'playlist_mincount': 5,
5455 'info_dict': {
5456 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5457 'title': '3Blue1Brown - Playlists',
5458 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5459 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5460 'channel': '3Blue1Brown',
5461 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5462 'uploader_id': '@3blue1brown',
5463 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5464 'uploader': '3Blue1Brown',
976ae3ea 5465 'tags': ['Mathematics'],
14a14335 5466 'channel_follower_count': int,
8213ce28 5467 'channel_is_verified': True,
a6213a49 5468 },
5469 }, {
5470 'note': 'playlists, singlepage',
5471 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5472 'playlist_mincount': 4,
5473 'info_dict': {
5474 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5475 'title': 'ThirstForScience - Playlists',
5476 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5477 'uploader': 'ThirstForScience',
7666b936 5478 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5479 'uploader_id': '@ThirstForScience',
976ae3ea 5480 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5481 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5482 'tags': 'count:13',
5483 'channel': 'ThirstForScience',
6c73052c 5484 'channel_follower_count': int
a6213a49 5485 }
5486 }, {
5487 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5488 'only_matching': True,
5489 }, {
5490 'note': 'basic, single video playlist',
5491 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5492 'info_dict': {
a6213a49 5493 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5494 'title': 'youtube-dl public playlist',
976ae3ea 5495 'description': '',
5496 'tags': [],
5497 'view_count': int,
5498 'modified_date': '20201130',
5499 'channel': 'Sergey M.',
5500 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5501 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5502 'availability': 'public',
7666b936 5503 'uploader': 'Sergey M.',
5504 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5505 'uploader_id': '@sergeym.6173',
a6213a49 5506 },
5507 'playlist_count': 1,
5508 }, {
5509 'note': 'empty playlist',
5510 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5511 'info_dict': {
a6213a49 5512 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5513 'title': 'youtube-dl empty playlist',
976ae3ea 5514 'tags': [],
5515 'channel': 'Sergey M.',
5516 'description': '',
5517 'modified_date': '20160902',
5518 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5519 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5520 'availability': 'public',
7666b936 5521 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5522 'uploader_id': '@sergeym.6173',
5523 'uploader': 'Sergey M.',
a6213a49 5524 },
5525 'playlist_count': 0,
5526 }, {
5527 'note': 'Home tab',
5528 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5529 'info_dict': {
5530 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5531 'title': 'lex will - Home',
5532 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5533 'uploader': 'lex will',
7666b936 5534 'uploader_id': '@lexwill718',
976ae3ea 5535 'channel': 'lex will',
5536 'tags': ['bible', 'history', 'prophesy'],
7666b936 5537 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5538 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5539 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5540 'channel_follower_count': int
a6213a49 5541 },
5542 'playlist_mincount': 2,
5543 }, {
5544 'note': 'Videos tab',
5545 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5546 'info_dict': {
5547 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5548 'title': 'lex will - Videos',
5549 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5550 'uploader': 'lex will',
7666b936 5551 'uploader_id': '@lexwill718',
976ae3ea 5552 'tags': ['bible', 'history', 'prophesy'],
5553 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5554 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5555 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5556 'channel': 'lex will',
6c73052c 5557 'channel_follower_count': int
a6213a49 5558 },
5559 'playlist_mincount': 975,
5560 }, {
5561 'note': 'Videos tab, sorted by popular',
5562 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5563 'info_dict': {
5564 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5565 'title': 'lex will - Videos',
5566 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5567 'uploader': 'lex will',
7666b936 5568 'uploader_id': '@lexwill718',
976ae3ea 5569 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5570 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5571 'channel': 'lex will',
5572 'tags': ['bible', 'history', 'prophesy'],
5573 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5574 'channel_follower_count': int
a6213a49 5575 },
5576 'playlist_mincount': 199,
5577 }, {
5578 'note': 'Playlists tab',
5579 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5580 'info_dict': {
5581 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5582 'title': 'lex will - Playlists',
5583 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5584 'uploader': 'lex will',
7666b936 5585 'uploader_id': '@lexwill718',
5586 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5587 'channel': 'lex will',
5588 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5589 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5590 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5591 'channel_follower_count': int
a6213a49 5592 },
5593 'playlist_mincount': 17,
5594 }, {
5595 'note': 'Community tab',
5596 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5597 'info_dict': {
5598 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5599 'title': 'lex will - Community',
5600 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5601 'channel': 'lex will',
5602 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5603 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5604 'tags': ['bible', 'history', 'prophesy'],
7666b936 5605 'channel_follower_count': int,
5606 'uploader_url': 'https://www.youtube.com/@lexwill718',
5607 'uploader_id': '@lexwill718',
5608 'uploader': 'lex will',
a6213a49 5609 },
5610 'playlist_mincount': 18,
5611 }, {
5612 'note': 'Channels tab',
5613 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5614 'info_dict': {
5615 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5616 'title': 'lex will - Channels',
5617 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5618 'channel': 'lex will',
5619 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5620 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5621 'tags': ['bible', 'history', 'prophesy'],
7666b936 5622 'channel_follower_count': int,
5623 'uploader_url': 'https://www.youtube.com/@lexwill718',
5624 'uploader_id': '@lexwill718',
5625 'uploader': 'lex will',
a6213a49 5626 },
5627 'playlist_mincount': 12,
5628 }, {
5629 'note': 'Search tab',
5630 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5631 'playlist_mincount': 40,
5632 'info_dict': {
5633 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5634 'title': '3Blue1Brown - Search - linear algebra',
5635 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5636 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5637 'tags': ['Mathematics'],
5638 'channel': '3Blue1Brown',
5639 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5640 'channel_follower_count': int,
5641 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5642 'uploader_id': '@3blue1brown',
5643 'uploader': '3Blue1Brown',
8213ce28 5644 'channel_is_verified': True,
a6213a49 5645 },
5646 }, {
5647 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5648 'only_matching': True,
5649 }, {
5650 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5651 'only_matching': True,
5652 }, {
5653 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5654 'only_matching': True,
5655 }, {
5656 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5657 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5658 'info_dict': {
5659 'title': '29C3: Not my department',
5660 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5661 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5662 'tags': [],
976ae3ea 5663 'view_count': int,
5664 'modified_date': '20150605',
5665 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5666 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5667 'channel': 'Christiaan008',
c26f9b99 5668 'availability': 'public',
7666b936 5669 'uploader_id': '@ChRiStIaAn008',
5670 'uploader': 'Christiaan008',
5671 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5672 },
5673 'playlist_count': 96,
5674 }, {
5675 'note': 'Large playlist',
5676 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5677 'info_dict': {
5678 'title': 'Uploads from Cauchemar',
5679 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5680 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5681 'tags': [],
5682 'modified_date': r're:\d{8}',
5683 'channel': 'Cauchemar',
976ae3ea 5684 'view_count': int,
5685 'description': '',
5686 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5687 'availability': 'public',
7666b936 5688 'uploader_id': '@Cauchemar89',
5689 'uploader': 'Cauchemar',
5690 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5691 },
5692 'playlist_mincount': 1123,
976ae3ea 5693 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5694 }, {
5695 'note': 'even larger playlist, 8832 videos',
5696 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5697 'only_matching': True,
5698 }, {
5699 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5700 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5701 'info_dict': {
5702 'title': 'Uploads from Interstellar Movie',
5703 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5704 'tags': [],
5705 'view_count': int,
5706 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5707 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5708 'channel': 'Interstellar Movie',
5709 'description': '',
5710 'modified_date': r're:\d{8}',
c26f9b99 5711 'availability': 'public',
7666b936 5712 'uploader_id': '@InterstellarMovie',
5713 'uploader': 'Interstellar Movie',
5714 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5715 },
5716 'playlist_mincount': 21,
5717 }, {
5718 'note': 'Playlist with "show unavailable videos" button',
5719 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5720 'info_dict': {
5721 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5722 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5723 'view_count': int,
5724 'channel': 'Phim Siêu Nhân Nhật Bản',
5725 'tags': [],
976ae3ea 5726 'description': '',
5727 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5728 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5729 'modified_date': r're:\d{8}',
c26f9b99 5730 'availability': 'public',
7666b936 5731 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5732 'uploader_id': '@phimsieunhannhatban',
5733 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5734 },
5735 'playlist_mincount': 200,
976ae3ea 5736 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5737 }, {
5738 'note': 'Playlist with unavailable videos in page 7',
5739 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5740 'info_dict': {
5741 'title': 'Uploads from BlankTV',
5742 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5743 'channel': 'BlankTV',
7666b936 5744 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5745 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5746 'view_count': int,
5747 'tags': [],
976ae3ea 5748 'modified_date': r're:\d{8}',
5749 'description': '',
c26f9b99 5750 'availability': 'public',
7666b936 5751 'uploader_id': '@blanktv',
5752 'uploader': 'BlankTV',
5753 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5754 },
5755 'playlist_mincount': 1000,
976ae3ea 5756 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5757 }, {
5758 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5759 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5760 'info_dict': {
5761 'title': 'Data Analysis with Dr Mike Pound',
5762 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5763 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5764 'tags': [],
5765 'view_count': int,
5766 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5767 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5768 'channel': 'Computerphile',
c26f9b99 5769 'availability': 'public',
6141346d 5770 'modified_date': '20190712',
7666b936 5771 'uploader_id': '@Computerphile',
5772 'uploader': 'Computerphile',
5773 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5774 },
5775 'playlist_mincount': 11,
5776 }, {
5777 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5778 'only_matching': True,
5779 }, {
5780 'note': 'Playlist URL that does not actually serve a playlist',
5781 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5782 'info_dict': {
5783 'id': 'FqZTN594JQw',
5784 'ext': 'webm',
5785 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5786 'upload_date': '20150526',
5787 'license': 'Standard YouTube License',
5788 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5789 'categories': ['People & Blogs'],
5790 'tags': list,
5791 'view_count': int,
5792 'like_count': int,
a6213a49 5793 },
5794 'params': {
5795 'skip_download': True,
5796 },
5797 'skip': 'This video is not available.',
5798 'add_ie': [YoutubeIE.ie_key()],
5799 }, {
5800 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5801 'only_matching': True,
5802 }, {
5803 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5804 'only_matching': True,
5805 }, {
5806 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5807 'info_dict': {
14a14335 5808 'id': 'hGkQjiJLjWQ', # This will keep changing
a6213a49 5809 'ext': 'mp4',
976ae3ea 5810 'title': str,
a6213a49 5811 'upload_date': r're:\d{8}',
976ae3ea 5812 'description': str,
a6213a49 5813 'categories': ['News & Politics'],
5814 'tags': list,
5815 'like_count': int,
86973308 5816 'release_timestamp': int,
976ae3ea 5817 'channel': 'Sky News',
5818 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5819 'age_limit': 0,
5820 'view_count': int,
86973308 5821 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5822 'playable_in_embed': True,
86973308 5823 'release_date': r're:\d+',
976ae3ea 5824 'availability': 'public',
5825 'live_status': 'is_live',
5826 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5827 'channel_follower_count': int,
5828 'concurrent_view_count': int,
7666b936 5829 'uploader_url': 'https://www.youtube.com/@SkyNews',
5830 'uploader_id': '@SkyNews',
5831 'uploader': 'Sky News',
8213ce28 5832 'channel_is_verified': True,
a6213a49 5833 },
5834 'params': {
5835 'skip_download': True,
5836 },
976ae3ea 5837 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5838 }, {
5839 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5840 'info_dict': {
5841 'id': 'a48o2S1cPoo',
5842 'ext': 'mp4',
5843 'title': 'The Young Turks - Live Main Show',
a6213a49 5844 'upload_date': '20150715',
5845 'license': 'Standard YouTube License',
5846 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5847 'categories': ['News & Politics'],
5848 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5849 'like_count': int,
a6213a49 5850 },
5851 'params': {
5852 'skip_download': True,
5853 },
5854 'only_matching': True,
5855 }, {
5856 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5857 'only_matching': True,
5858 }, {
5859 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5860 'only_matching': True,
5861 }, {
5862 'note': 'A channel that is not live. Should raise error',
5863 'url': 'https://www.youtube.com/user/numberphile/live',
5864 'only_matching': True,
5865 }, {
5866 'url': 'https://www.youtube.com/feed/trending',
5867 'only_matching': True,
5868 }, {
5869 'url': 'https://www.youtube.com/feed/library',
5870 'only_matching': True,
5871 }, {
5872 'url': 'https://www.youtube.com/feed/history',
5873 'only_matching': True,
5874 }, {
5875 'url': 'https://www.youtube.com/feed/subscriptions',
5876 'only_matching': True,
5877 }, {
5878 'url': 'https://www.youtube.com/feed/watch_later',
5879 'only_matching': True,
5880 }, {
5881 'note': 'Recommended - redirects to home page.',
5882 'url': 'https://www.youtube.com/feed/recommended',
5883 'only_matching': True,
5884 }, {
5885 'note': 'inline playlist with not always working continuations',
5886 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5887 'only_matching': True,
5888 }, {
5889 'url': 'https://www.youtube.com/course',
5890 'only_matching': True,
5891 }, {
5892 'url': 'https://www.youtube.com/zsecurity',
5893 'only_matching': True,
5894 }, {
5895 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5896 'only_matching': True,
5897 }, {
5898 'url': 'https://www.youtube.com/TheYoungTurks/live',
5899 'only_matching': True,
5900 }, {
5901 'url': 'https://www.youtube.com/hashtag/cctv9',
5902 'info_dict': {
5903 'id': 'cctv9',
5904 'title': '#cctv9',
976ae3ea 5905 'tags': [],
a6213a49 5906 },
4dc23a80 5907 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5908 }, {
5909 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5910 'only_matching': True,
5911 }, {
5912 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5913 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5914 'only_matching': True
5915 }, {
5916 'note': '/browse/ should redirect to /channel/',
5917 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5918 'only_matching': True
5919 }, {
5920 'note': 'VLPL, should redirect to playlist?list=PL...',
5921 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5922 'info_dict': {
5923 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5924 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5925 'title': 'NCS : All Releases 💿',
7666b936 5926 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5927 'modified_date': r're:\d{8}',
5928 'view_count': int,
5929 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5930 'tags': [],
5931 'channel': 'NoCopyrightSounds',
c26f9b99 5932 'availability': 'public',
7666b936 5933 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5934 'uploader': 'NoCopyrightSounds',
5935 'uploader_id': '@NoCopyrightSounds',
a6213a49 5936 },
5937 'playlist_mincount': 166,
7666b936 5938 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5939 }, {
7666b936 5940 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5941 'note': 'Topic, should redirect to playlist?list=UU...',
5942 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5943 'info_dict': {
5944 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5945 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5946 'tags': [],
5947 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5948 'channel': 'Royalty Free Music - Topic',
5949 'view_count': int,
5950 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5951 'modified_date': r're:\d{8}',
976ae3ea 5952 'description': '',
c26f9b99 5953 'availability': 'public',
7666b936 5954 'uploader': 'Royalty Free Music - Topic',
a6213a49 5955 },
a6213a49 5956 'playlist_mincount': 101,
7666b936 5957 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5958 }, {
86973308
M
5959 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5960 # Treat as a general feed
a6213a49 5961 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5962 'info_dict': {
5963 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5964 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5965 'tags': [],
a6213a49 5966 },
a6213a49 5967 'playlist_mincount': 9,
5968 }, {
5969 'note': 'Youtube music Album',
5970 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5971 'info_dict': {
5972 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5973 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5974 'tags': [],
5975 'view_count': int,
5976 'description': '',
5977 'availability': 'unlisted',
5978 'modified_date': r're:\d{8}',
a6213a49 5979 },
5980 'playlist_count': 50,
7666b936 5981 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5982 }, {
5983 'note': 'unlisted single video playlist',
5984 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5985 'info_dict': {
a6213a49 5986 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5987 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5988 'availability': 'unlisted',
5989 'tags': [],
12a1b225 5990 'modified_date': '20220418',
976ae3ea 5991 'channel': 'colethedj',
5992 'view_count': int,
5993 'description': '',
976ae3ea 5994 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5995 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 5996 'uploader_url': 'https://www.youtube.com/@colethedj1894',
5997 'uploader_id': '@colethedj1894',
5998 'uploader': 'colethedj',
a6213a49 5999 },
93e12ed7 6000 'playlist': [{
6001 'info_dict': {
6002 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
6003 'id': 'BaW_jenozKc',
6004 '_type': 'url',
6005 'ie_key': 'Youtube',
6006 'duration': 10,
6007 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
6008 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
6009 'view_count': int,
6010 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
6011 'channel': 'Philipp Hagemeister',
6012 'uploader_id': '@PhilippHagemeister',
6013 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
6014 'uploader': 'Philipp Hagemeister',
6015 }
6016 }],
a6213a49 6017 'playlist_count': 1,
93e12ed7 6018 'params': {'extract_flat': True},
a6213a49 6019 }, {
6020 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
6021 'url': 'https://www.youtube.com/feed/recommended',
6022 'info_dict': {
6023 'id': 'recommended',
6024 'title': 'recommended',
6c73052c 6025 'tags': [],
a6213a49 6026 },
6027 'playlist_mincount': 50,
6028 'params': {
6029 'skip_download': True,
6030 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6031 },
6032 }, {
6033 'note': 'API Fallback: /videos tab, sorted by oldest first',
6034 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
6035 'info_dict': {
6036 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6037 'title': 'Cody\'sLab - Videos',
6038 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 6039 'channel': 'Cody\'sLab',
6040 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6041 'tags': [],
6042 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 6043 'channel_follower_count': int
a6213a49 6044 },
6045 'playlist_mincount': 650,
6046 'params': {
6047 'skip_download': True,
6048 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6049 },
86973308 6050 'skip': 'Query for sorting no longer works',
a6213a49 6051 }, {
6052 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
6053 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
6054 'info_dict': {
6055 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 6056 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 6057 'modified_date': r're:\d{8}',
6058 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
6059 'description': '',
6060 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
6061 'tags': [],
6062 'channel': 'Royalty Free Music - Topic',
6063 'view_count': int,
c26f9b99 6064 'availability': 'public',
7666b936 6065 'uploader': 'Royalty Free Music - Topic',
a6213a49 6066 },
a6213a49 6067 'playlist_mincount': 101,
6068 'params': {
6069 'skip_download': True,
6070 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6071 },
7666b936 6072 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 6073 }, {
6074 'note': 'non-standard redirect to regional channel',
6075 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
6076 'only_matching': True
61d3665d 6077 }, {
6078 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
6079 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6080 'info_dict': {
6081 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6082 'modified_date': '20220407',
6083 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
6084 'tags': [],
61d3665d 6085 'availability': 'unlisted',
6086 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
6087 'channel': 'pukkandan',
6088 'description': 'Test for collaborative playlist',
6089 'title': 'yt-dlp test - collaborative playlist',
12a1b225 6090 'view_count': int,
7666b936 6091 'uploader_url': 'https://www.youtube.com/@pukkandan',
6092 'uploader_id': '@pukkandan',
6093 'uploader': 'pukkandan',
61d3665d 6094 },
6095 'playlist_mincount': 2
c26f9b99 6096 }, {
6097 'note': 'translated tab name',
6098 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
6099 'info_dict': {
6100 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6101 'tags': [],
c26f9b99 6102 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 6103 'description': 'test description',
c26f9b99 6104 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 6105 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6106 'channel': 'cole-dlp-test-acc',
7666b936 6107 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6108 'uploader_id': '@coletdjnz',
6109 'uploader': 'cole-dlp-test-acc',
c26f9b99 6110 },
6111 'playlist_mincount': 1,
6112 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6113 'expected_warnings': ['Preferring "ja"'],
6114 }, {
6115 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
6116 'note': 'preferred lang set with playlist with translated video titles',
6117 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6118 'info_dict': {
6119 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6120 'tags': [],
6121 'view_count': int,
6122 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6123 'channel': 'cole-dlp-test-acc',
6124 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6125 'description': 'test',
c26f9b99 6126 'title': 'dlp test playlist',
6127 'availability': 'public',
7666b936 6128 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6129 'uploader_id': '@coletdjnz',
6130 'uploader': 'cole-dlp-test-acc',
c26f9b99 6131 },
6132 'playlist_mincount': 1,
6133 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6134 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6135 }, {
6136 # shorts audio pivot for 2GtVksBMYFM.
6137 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6138 'info_dict': {
6139 'id': 'sfv_audio_pivot',
6140 'title': 'sfv_audio_pivot',
6141 'tags': [],
6142 },
6143 'playlist_mincount': 50,
6144
86973308
M
6145 }, {
6146 # Channel with a real live tab (not to be mistaken with streams tab)
6147 # Do not treat like it should redirect to live stream
6148 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6149 'info_dict': {
6150 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6151 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6152 'tags': [],
6153 },
6154 'playlist_mincount': 20,
6155 }, {
6156 # Tab name is not the same as tab id
6157 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6158 'info_dict': {
6159 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6160 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6161 'tags': [],
6162 },
6163 'playlist_mincount': 8,
6164 }, {
6165 # Home tab id is literally home. Not to get mistaken with featured
6166 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6167 'info_dict': {
6168 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6169 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6170 'tags': [],
6171 },
6172 'playlist_mincount': 8,
6173 }, {
6174 # Should get three playlists for videos, shorts and streams tabs
6175 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6176 'info_dict': {
6177 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6178 'title': 'Polka Ch. 尾丸ポルカ',
6179 'channel_follower_count': int,
6180 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6181 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
7666b936 6182 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
bd7e919a 6183 'channel': 'Polka Ch. 尾丸ポルカ',
6184 'tags': 'count:35',
7666b936 6185 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6186 'uploader': 'Polka Ch. 尾丸ポルカ',
6187 'uploader_id': '@OmaruPolka',
86973308
M
6188 },
6189 'playlist_count': 3,
6190 }, {
6191 # Shorts tab with channel with handle
7666b936 6192 # TODO: fix channel description
86973308
M
6193 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6194 'info_dict': {
6195 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6196 'title': 'Not Just Bikes - Shorts',
6197 'tags': 'count:12',
86973308 6198 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
7666b936 6199 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
86973308 6200 'channel_follower_count': int,
86973308 6201 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6202 'channel': 'Not Just Bikes',
7666b936 6203 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6204 'uploader': 'Not Just Bikes',
6205 'uploader_id': '@NotJustBikes',
86973308
M
6206 },
6207 'playlist_mincount': 10,
6208 }, {
6209 # Streams tab
6210 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6211 'info_dict': {
6212 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6213 'title': '中村悠一 - Live',
6214 'tags': 'count:7',
6215 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6216 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6217 'channel': '中村悠一',
86973308 6218 'channel_follower_count': int,
86973308 6219 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6220 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6221 'uploader_id': '@Yuichi-Nakamura',
6222 'uploader': '中村悠一',
86973308
M
6223 },
6224 'playlist_mincount': 60,
6225 }, {
6226 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6227 # See test_youtube_lists
6228 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6229 'only_matching': True,
6230 }, {
6231 # No uploads and no UCID given. Should fail with no uploads error
6232 # See test_youtube_lists
6233 'url': 'https://www.youtube.com/news',
6234 'only_matching': True
6235 }, {
6236 # No videos tab but has a shorts tab
6237 'url': 'https://www.youtube.com/c/TKFShorts',
6238 'info_dict': {
6239 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6240 'title': 'Shorts Break - Shorts',
7666b936 6241 'tags': 'count:48',
86973308
M
6242 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6243 'channel': 'Shorts Break',
7666b936 6244 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6245 'channel_follower_count': int,
86973308 6246 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6247 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6248 'uploader': 'Shorts Break',
6249 'uploader_id': '@ShortsBreak_Official',
86973308
M
6250 },
6251 'playlist_mincount': 30,
6252 }, {
6253 # Trending Now Tab. tab id is empty
6254 'url': 'https://www.youtube.com/feed/trending',
6255 'info_dict': {
6256 'id': 'trending',
6257 'title': 'trending - Now',
6258 'tags': [],
6259 },
6260 'playlist_mincount': 30,
6261 }, {
6262 # Trending Gaming Tab. tab id is empty
6263 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6264 'info_dict': {
6265 'id': 'trending',
6266 'title': 'trending - Gaming',
6267 'tags': [],
6268 },
6269 'playlist_mincount': 30,
4dc23a80
M
6270 }, {
6271 # Shorts url result in shorts tab
7666b936 6272 # TODO: Fix channel id extraction
4dc23a80
M
6273 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6274 'info_dict': {
6275 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6276 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6277 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6278 'description': 'test description',
6279 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6280 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6281 'tags': [],
7666b936 6282 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6283 'uploader_id': '@coletdjnz',
4dc23a80 6284 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6285 },
6286 'playlist': [{
6287 'info_dict': {
7666b936 6288 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6289 '_type': 'url',
6290 'ie_key': 'Youtube',
6291 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6292 'id': 'sSM9J5YH_60',
4dc23a80 6293 'title': 'SHORT short',
4dc23a80
M
6294 'view_count': int,
6295 'thumbnails': list,
6296 }
6297 }],
6298 'params': {'extract_flat': True},
6299 }, {
6300 # Live video status should be extracted
6301 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6302 'info_dict': {
6303 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6304 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6305 'tags': []
6306 },
6307 'playlist': [{
6308 'info_dict': {
6309 '_type': 'url',
6310 'ie_key': 'Youtube',
6311 'url': 'startswith:https://www.youtube.com/watch?v=',
6312 'id': str,
6313 'title': str,
6314 'live_status': 'is_live',
6315 'channel_id': str,
6316 'channel_url': str,
6317 'concurrent_view_count': int,
6318 'channel': str,
93e12ed7 6319 'uploader': str,
6320 'uploader_url': str,
14a14335 6321 'uploader_id': str,
8213ce28 6322 'channel_is_verified': bool, # this will keep changing
4dc23a80
M
6323 }
6324 }],
c7335551 6325 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6326 'playlist_mincount': 1
c7335551
M
6327 }, {
6328 # Channel renderer metadata. Contains number of videos on the channel
6329 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6330 'info_dict': {
6331 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6332 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6333 'channel': 'cole-dlp-test-acc',
6334 'description': 'test description',
6335 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6336 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6337 'tags': [],
7666b936 6338 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6339 'uploader_id': '@coletdjnz',
c7335551 6340 'uploader': 'cole-dlp-test-acc',
c7335551
M
6341 },
6342 'playlist': [{
6343 'info_dict': {
6344 '_type': 'url',
6345 'ie_key': 'YoutubeTab',
6346 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6347 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6348 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6349 'title': 'PewDiePie',
6350 'channel': 'PewDiePie',
6351 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6352 'thumbnails': list,
6353 'channel_follower_count': int,
7666b936 6354 'playlist_count': int,
6355 'uploader': 'PewDiePie',
6356 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6357 'uploader_id': '@PewDiePie',
8213ce28 6358 'channel_is_verified': True,
c7335551
M
6359 }
6360 }],
6361 'params': {'extract_flat': True},
31e18355 6362 }, {
6363 'url': 'https://www.youtube.com/@3blue1brown/about',
6364 'info_dict': {
6365 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6366 'tags': ['Mathematics'],
6367 'title': '3Blue1Brown - About',
31e18355 6368 'channel_follower_count': int,
6369 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6370 'channel': '3Blue1Brown',
31e18355 6371 'view_count': int,
6372 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6373 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
7666b936 6374 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6375 'uploader_id': '@3blue1brown',
6376 'uploader': '3Blue1Brown',
8213ce28 6377 'channel_is_verified': True,
31e18355 6378 },
6379 'playlist_count': 0,
447afb9e 6380 }, {
6381 # Podcasts tab, with rich entry playlistRenderers
6382 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6383 'info_dict': {
6384 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6385 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6386 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6387 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6388 'title': '99 Percent Invisible - Podcasts',
6389 'uploader': '99 Percent Invisible',
6390 'channel_follower_count': int,
6391 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6392 'tags': [],
6393 'channel': '99 Percent Invisible',
6394 'uploader_id': '@99percentinvisiblepodcast',
6395 },
6396 'playlist_count': 1,
6397 }, {
6398 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6399 'url': 'https://www.youtube.com/@AHimitsu/releases',
6400 'info_dict': {
6401 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6402 'channel': 'A Himitsu',
6403 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6404 'title': 'A Himitsu - Releases',
6405 'uploader_id': '@AHimitsu',
6406 'uploader': 'A Himitsu',
6407 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6408 'tags': 'count:16',
6409 'description': 'I make music',
6410 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6411 'channel_follower_count': int,
8213ce28 6412 'channel_is_verified': True,
447afb9e 6413 },
6414 'playlist_mincount': 10,
fcbc9ed7 6415 }, {
6416 # Playlist with only shorts, shown as reel renderers
6417 # FIXME: future: YouTube currently doesn't give continuation for this,
6418 # may do in future.
6419 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
6420 'info_dict': {
6421 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
6422 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
6423 'view_count': int,
6424 'uploader_id': '@BangyShorts',
6425 'description': '',
6426 'uploader_url': 'https://www.youtube.com/@BangyShorts',
6427 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
6428 'channel': 'Bangy Shorts',
6429 'uploader': 'Bangy Shorts',
6430 'tags': [],
6431 'availability': 'public',
6432 'modified_date': '20230626',
6433 'title': 'Uploads from Bangy Shorts',
6434 },
6435 'playlist_mincount': 100,
6436 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 6437 }]
6438
6439 @classmethod
6440 def suitable(cls, url):
86e5f3ed 6441 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6442
86973308
M
6443 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6444
6445 def _get_url_mobj(self, url):
6446 mobj = self._URL_RE.match(url).groupdict()
6447 mobj.update((k, '') for k, v in mobj.items() if v is None)
6448 return mobj
6449
6450 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6451 tab_name = (tab.get('title') or '').lower()
6452 tab_url = urljoin(base_url, traverse_obj(
6453 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6454
bd7e919a 6455 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6456 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6457 if tab_id:
bd7e919a 6458 return {
6459 'TAB_ID_SPONSORSHIPS': 'membership',
6460 }.get(tab_id, tab_id), tab_name
86973308
M
6461
6462 # Fallback to tab name if we cannot get the tab id.
6463 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6464 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6465 if tab_name:
6466 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6467 return {
6468 'home': 'featured',
6469 'live': 'streams',
6470 }.get(tab_name, tab_name), tab_name
6471
6472 def _has_tab(self, tabs, tab_id):
6473 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6474
044886c2 6475 def _empty_playlist(self, item_id, data):
6476 return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data))
6477
182bda88 6478 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6479 def _real_extract(self, url, smuggled_data):
cd7c66cf 6480 item_id = self._match_id(url)
14f25df2 6481 url = urllib.parse.urlunparse(
6482 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6483 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6484
86973308
M
6485 mobj = self._get_url_mobj(url)
6486 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6487 if is_channel and smuggled_data.get('is_music_url'):
6488 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6489 return self.url_result(
6490 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6491 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6492 mdata = self._extract_tab_endpoint(
6493 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6494 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6495 get_all=False, expected_type=str)
6496 if not murl:
6497 raise ExtractorError('Failed to resolve album to playlist')
6498 return self.url_result(murl, YoutubeTabIE)
6499 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6500 return self.url_result(
6501 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6502
6503 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6504 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6505 url = f'{pre}/videos{post}'
5b28cef7 6506 if smuggled_data.get('is_music_url'):
6507 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6508
6509 # Handle both video/playlist URLs
201c1459 6510 qs = parse_qs(url)
bd7e919a 6511 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6512 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6513 if not playlist_id:
fe03a6cd 6514 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6515 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6516 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6517 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6518 return self.url_result(
6519 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6520
86973308
M
6521 if not self._yes_playlist(playlist_id, video_id):
6522 return self.url_result(
6523 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6524
bd7e919a 6525 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6526
7c219ea6 6527 # YouTube may provide a non-standard redirect to the regional channel
6528 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6529 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6530 redirect_url = traverse_obj(
6531 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6532 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6533 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6534 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6535 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6536
bd7e919a 6537 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6538 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6539 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6540 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6541 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6542
044886c2 6543 # /about is no longer a tab
6544 if original_tab_id == 'about':
6545 return self._empty_playlist(item_id, data)
6546
86973308 6547 if not original_tab_id and selected_tab_name:
bd7e919a 6548 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6549 'To download only the videos in a specific tab, pass the tab\'s URL')
6550 if self._has_tab(tabs, 'streams'):
bd7e919a 6551 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6552 if self._has_tab(tabs, 'shorts'):
bd7e919a 6553 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6554 # XXX: Members-only tab should also be extracted
6555
bd7e919a 6556 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6557 # Channel does not have streams, shorts or videos tabs
6558 if item_id[:2] != 'UC':
044886c2 6559 return self._empty_playlist(item_id, data)
86973308
M
6560
6561 # Topic channels don't have /videos. Use the equivalent playlist instead
6562 pl_id = f'UU{item_id[2:]}'
6563 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6564 try:
6565 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6566 except ExtractorError:
044886c2 6567 return self._empty_playlist(item_id, data)
64f36541 6568 else:
86973308
M
6569 item_id, url = pl_id, pl_url
6570 self.to_screen(
6571 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6572
bd7e919a 6573 elif extra_tabs and selected_tab_id != 'videos':
86973308 6574 # When there are shorts/live tabs but not videos tab
bd7e919a 6575 url, data = f'{pre}{post}', None
86973308
M
6576
6577 elif (original_tab_id or 'videos') != selected_tab_id:
6578 if original_tab_id == 'live':
6579 # Live tab should have redirected to the video
6580 # Except in the case the channel has an actual live tab
6581 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6582 raise UserNotLive(video_id=item_id)
86973308
M
6583 elif selected_tab_name:
6584 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6585
6586 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6587 url = f'{pre}{post}'
18db7548 6588
358de58c 6589 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6590 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6591 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6592 self._extract_and_report_alerts(data, only_once=True)
86973308 6593
bd7e919a 6594 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6595 if tabs:
bd7e919a 6596 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6597 entries[0].update({
86973308
M
6598 'extractor_key': YoutubeTabIE.ie_key(),
6599 'extractor': YoutubeTabIE.IE_NAME,
6600 'webpage_url': url,
6601 })
bd7e919a 6602 if self.get_param('playlist_items') == '0':
6603 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6604 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6605 entries.extend(map(self._real_extract, extra_tabs))
6606
6607 if len(entries) == 1:
6608 return entries[0]
6609 elif entries:
6610 metadata = self._extract_metadata_from_tabs(item_id, data)
6611 uploads_url = 'the Uploads (UU) playlist URL'
6612 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6613 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6614 self.to_screen(
6615 'Downloading as multiple playlists, separated by tabs. '
6616 f'To download as a single playlist instead, pass {uploads_url}')
6617 return self.playlist_result(entries, item_id, **metadata)
6618
6619 # Inline playlist
37e57a9f 6620 playlist = traverse_obj(
6621 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6622 if playlist:
ac56cf38 6623 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6624
37e57a9f 6625 video_id = traverse_obj(
6626 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6627 if video_id:
bd7e919a 6628 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6629 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6630 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6631
8bdd16b4 6632 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6633
c5e8d7af 6634
8bdd16b4 6635class YoutubePlaylistIE(InfoExtractor):
96565c7e 6636 IE_DESC = 'YouTube playlists'
8bdd16b4 6637 _VALID_URL = r'''(?x)(?:
6638 (?:https?://)?
6639 (?:\w+\.)?
6640 (?:
6641 (?:
6642 youtube(?:kids)?\.com|
d9190e44 6643 %(invidious)s
8bdd16b4 6644 )
6645 /.*?\?.*?\blist=
6646 )?
6647 (?P<id>%(playlist_id)s)
d9190e44
RH
6648 )''' % {
6649 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6650 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6651 }
8bdd16b4 6652 IE_NAME = 'youtube:playlist'
cdc628a4 6653 _TESTS = [{
8bdd16b4 6654 'note': 'issue #673',
6655 'url': 'PLBB231211A4F62143',
cdc628a4 6656 'info_dict': {
8bdd16b4 6657 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6658 'id': 'PLBB231211A4F62143',
976ae3ea 6659 'uploader': 'Wickman',
7666b936 6660 'uploader_id': '@WickmanVT',
11f9be09 6661 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6662 'view_count': int,
7666b936 6663 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6664 'modified_date': r're:\d{8}',
6665 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6666 'channel': 'Wickman',
6667 'tags': [],
7666b936 6668 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6669 'availability': 'public',
8bdd16b4 6670 },
6671 'playlist_mincount': 29,
6672 }, {
6673 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6674 'info_dict': {
6675 'title': 'YDL_safe_search',
6676 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6677 },
6678 'playlist_count': 2,
6679 'skip': 'This playlist is private',
9558dcec 6680 }, {
8bdd16b4 6681 'note': 'embedded',
6682 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6683 'playlist_count': 4,
9558dcec 6684 'info_dict': {
8bdd16b4 6685 'title': 'JODA15',
6686 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6687 'uploader': 'milan',
7666b936 6688 'uploader_id': '@milan5503',
976ae3ea 6689 'description': '',
6690 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6691 'tags': [],
6692 'modified_date': '20140919',
6693 'view_count': int,
6694 'channel': 'milan',
6695 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6696 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6697 'availability': 'public',
976ae3ea 6698 },
b012271d 6699 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden', 'Retrying', 'Giving up'],
cdc628a4 6700 }, {
8bdd16b4 6701 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6702 'playlist_mincount': 455,
8bdd16b4 6703 'info_dict': {
6704 'title': '2018 Chinese New Singles (11/6 updated)',
6705 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6706 'uploader': 'LBK',
7666b936 6707 'uploader_id': '@music_king',
11f9be09 6708 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6709 'channel': 'LBK',
6710 'view_count': int,
7666b936 6711 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6712 'tags': [],
7666b936 6713 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6714 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6715 'modified_date': r're:\d{8}',
c26f9b99 6716 'availability': 'public',
976ae3ea 6717 },
6718 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6719 }, {
29f7c58a 6720 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6721 'only_matching': True,
6722 }, {
6723 # music album playlist
6724 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6725 'only_matching': True,
6726 }]
6727
6728 @classmethod
6729 def suitable(cls, url):
201c1459 6730 if YoutubeTabIE.suitable(url):
6731 return False
49a57e70 6732 from ..utils import parse_qs
201c1459 6733 qs = parse_qs(url)
6734 if qs.get('v', [None])[0]:
6735 return False
86e5f3ed 6736 return super().suitable(url)
29f7c58a 6737
6738 def _real_extract(self, url):
6739 playlist_id = self._match_id(url)
46953e7e 6740 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6741 url = update_url_query(
6742 'https://www.youtube.com/playlist',
6743 parse_qs(url) or {'list': playlist_id})
6744 if is_music_url:
6745 url = smuggle_url(url, {'is_music_url': True})
6746 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6747
6748
6749class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6750 IE_DESC = 'youtu.be'
29f7c58a 6751 _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}
6752 _TESTS = [{
8bdd16b4 6753 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6754 'info_dict': {
6755 'id': 'yeWKywCrFtk',
6756 'ext': 'mp4',
6757 'title': 'Small Scale Baler and Braiding Rugs',
6758 'uploader': 'Backus-Page House Museum',
7666b936 6759 'uploader_id': '@backuspagemuseum',
6760 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6761 'upload_date': '20161008',
6762 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6763 'categories': ['Nonprofits & Activism'],
6764 'tags': list,
6765 'like_count': int,
976ae3ea 6766 'age_limit': 0,
6767 'playable_in_embed': True,
7666b936 6768 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6769 'channel': 'Backus-Page House Museum',
6770 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6771 'live_status': 'not_live',
6772 'view_count': int,
6773 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6774 'availability': 'public',
6775 'duration': 59,
12a1b225
A
6776 'comment_count': int,
6777 'channel_follower_count': int
8bdd16b4 6778 },
6779 'params': {
6780 'noplaylist': True,
6781 'skip_download': True,
6782 },
39e7107d 6783 }, {
8bdd16b4 6784 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6785 'only_matching': True,
cdc628a4
PH
6786 }]
6787
8bdd16b4 6788 def _real_extract(self, url):
5ad28e7f 6789 mobj = self._match_valid_url(url)
29f7c58a 6790 video_id = mobj.group('id')
6791 playlist_id = mobj.group('playlist_id')
8bdd16b4 6792 return self.url_result(
29f7c58a 6793 update_url_query('https://www.youtube.com/watch', {
6794 'v': video_id,
6795 'list': playlist_id,
6796 'feature': 'youtu.be',
6797 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6798
6799
b6ce9bb0 6800class YoutubeLivestreamEmbedIE(InfoExtractor):
6801 IE_DESC = 'YouTube livestream embeds'
6802 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6803 _TESTS = [{
6804 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6805 'only_matching': True,
6806 }]
6807
6808 def _real_extract(self, url):
6809 channel_id = self._match_id(url)
6810 return self.url_result(
6811 f'https://www.youtube.com/channel/{channel_id}/live',
6812 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6813
6814
8bdd16b4 6815class YoutubeYtUserIE(InfoExtractor):
96565c7e 6816 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6817 IE_NAME = 'youtube:user'
8bdd16b4 6818 _VALID_URL = r'ytuser:(?P<id>.+)'
6819 _TESTS = [{
6820 'url': 'ytuser:phihag',
6821 'only_matching': True,
6822 }]
6823
6824 def _real_extract(self, url):
6825 user_id = self._match_id(url)
08270da5 6826 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6827
b05654f0 6828
3d3dddc9 6829class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6830 IE_NAME = 'youtube:favorites'
96565c7e 6831 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6832 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6833 _LOGIN_REQUIRED = True
6834 _TESTS = [{
6835 'url': ':ytfav',
6836 'only_matching': True,
6837 }, {
6838 'url': ':ytfavorites',
6839 'only_matching': True,
6840 }]
6841
6842 def _real_extract(self, url):
6843 return self.url_result(
6844 'https://www.youtube.com/playlist?list=LL',
6845 ie=YoutubeTabIE.ie_key())
6846
6847
ca5300c7 6848class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6849 IE_NAME = 'youtube:notif'
6850 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6851 _VALID_URL = r':ytnotif(?:ication)?s?'
6852 _LOGIN_REQUIRED = True
6853 _TESTS = [{
6854 'url': ':ytnotif',
6855 'only_matching': True,
6856 }, {
6857 'url': ':ytnotifications',
6858 'only_matching': True,
6859 }]
6860
6861 def _extract_notification_menu(self, response, continuation_list):
6862 notification_list = traverse_obj(
6863 response,
6864 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6865 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6866 expected_type=list) or []
6867 continuation_list[0] = None
6868 for item in notification_list:
6869 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6870 if entry:
6871 yield entry
6872 continuation = item.get('continuationItemRenderer')
6873 if continuation:
6874 continuation_list[0] = continuation
6875
6876 def _extract_notification_renderer(self, notification):
6877 video_id = traverse_obj(
6878 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6879 url = f'https://www.youtube.com/watch?v={video_id}'
6880 channel_id = None
6881 if not video_id:
6882 browse_ep = traverse_obj(
6883 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6884 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6885 post_id = self._search_regex(
6886 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6887 'post id', default=None)
6888 if not channel_id or not post_id:
6889 return
6890 # The direct /post url redirects to this in the browser
6891 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6892
6893 channel = traverse_obj(
6894 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6895 expected_type=str)
c7a7baaa 6896 notification_title = self._get_text(notification, 'shortMessage')
6897 if notification_title:
6898 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6899 # TODO: handle recommended videos
ca5300c7 6900 title = self._search_regex(
c7a7baaa 6901 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6902 'video title', default=None)
5225df50 6903 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6904 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6905 else None)
ca5300c7 6906 return {
6907 '_type': 'url',
6908 'url': url,
6909 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6910 'video_id': video_id,
6911 'title': title,
6912 'channel_id': channel_id,
6913 'channel': channel,
7666b936 6914 'uploader': channel,
ca5300c7 6915 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6916 'timestamp': timestamp,
ca5300c7 6917 }
6918
6919 def _notification_menu_entries(self, ytcfg):
6920 continuation_list = [None]
6921 response = None
6922 for page in itertools.count(1):
6923 ctoken = traverse_obj(
6924 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6925 response = self._extract_response(
6926 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6927 ep='notification/get_notification_menu', check_get_keys='actions',
6928 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6929 yield from self._extract_notification_menu(response, continuation_list)
6930 if not continuation_list[0]:
6931 break
6932
6933 def _real_extract(self, url):
6934 display_id = 'notifications'
6935 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6936 self._report_playlist_authcheck(ytcfg)
6937 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6938
6939
a6213a49 6940class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6941 IE_DESC = 'YouTube search'
78caa52a 6942 IE_NAME = 'youtube:search'
b05654f0 6943 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6944 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6945 _TESTS = [{
6946 'url': 'ytsearch5:youtube-dl test video',
6947 'playlist_count': 5,
6948 'info_dict': {
6949 'id': 'youtube-dl test video',
6950 'title': 'youtube-dl test video',
6951 }
6952 }]
b05654f0 6953
a61fd4cf 6954
5f7cb91a 6955class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6956 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6957 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6958 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6959 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6960 _TESTS = [{
6961 'url': 'ytsearchdate5:youtube-dl test video',
6962 'playlist_count': 5,
6963 'info_dict': {
6964 'id': 'youtube-dl test video',
6965 'title': 'youtube-dl test video',
6966 }
6967 }]
75dff0ee 6968
c9ae7b95 6969
a6213a49 6970class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6971 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6972 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6973 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6974 _TESTS = [{
6975 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6976 'playlist_mincount': 5,
6977 'info_dict': {
11f9be09 6978 'id': 'youtube-dl test video',
3462ffa8 6979 'title': 'youtube-dl test video',
6980 }
a61fd4cf 6981 }, {
6982 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6983 'playlist_mincount': 5,
6984 'info_dict': {
6985 'id': 'python',
6986 'title': 'python',
6987 }
ad210f4f 6988 }, {
6989 'url': 'https://www.youtube.com/results?search_query=%23cats',
6990 'playlist_mincount': 1,
6991 'info_dict': {
6992 'id': '#cats',
6993 'title': '#cats',
12a1b225
A
6994 # The test suite does not have support for nested playlists
6995 # 'entries': [{
6996 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6997 # 'title': '#cats',
6998 # }],
ad210f4f 6999 },
c7335551
M
7000 }, {
7001 # Channel results
7002 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
7003 'info_dict': {
7004 'id': 'kurzgesagt',
7005 'title': 'kurzgesagt',
7006 },
7007 'playlist': [{
7008 'info_dict': {
7009 '_type': 'url',
7010 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
7011 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7012 'ie_key': 'YoutubeTab',
7013 'channel': 'Kurzgesagt – In a Nutshell',
7014 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
7015 'title': 'Kurzgesagt – In a Nutshell',
7016 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
14a14335 7017 # No longer available for search as it is set to the handle.
7018 # 'playlist_count': int,
c7335551 7019 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 7020 'thumbnails': list,
7021 'uploader_id': '@kurzgesagt',
7022 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
7023 'uploader': 'Kurzgesagt – In a Nutshell',
8213ce28 7024 'channel_is_verified': True,
14a14335 7025 'channel_follower_count': int,
c7335551
M
7026 }
7027 }],
7028 'params': {'extract_flat': True, 'playlist_items': '1'},
7029 'playlist_mincount': 1,
3462ffa8 7030 }, {
7031 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
7032 'only_matching': True,
7033 }]
7034
7035 def _real_extract(self, url):
4dfbf869 7036 qs = parse_qs(url)
386e1dd9 7037 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 7038 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 7039
7040
16aa9ea4 7041class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 7042 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 7043 IE_NAME = 'youtube:music:search_url'
7044 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
7045 _TESTS = [{
7046 'url': 'https://music.youtube.com/search?q=royalty+free+music',
7047 'playlist_count': 16,
7048 'info_dict': {
7049 'id': 'royalty free music',
7050 'title': 'royalty free music',
7051 }
7052 }, {
7053 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
7054 'playlist_mincount': 30,
7055 'info_dict': {
7056 'id': 'royalty free music - songs',
7057 'title': 'royalty free music - songs',
7058 },
7059 'params': {'extract_flat': 'in_playlist'}
7060 }, {
7061 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
7062 'playlist_mincount': 30,
7063 'info_dict': {
7064 'id': 'royalty free music - community playlists',
7065 'title': 'royalty free music - community playlists',
7066 },
7067 'params': {'extract_flat': 'in_playlist'}
7068 }]
7069
7070 _SECTIONS = {
7071 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
7072 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
7073 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
7074 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
7075 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
7076 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
7077 }
7078
7079 def _real_extract(self, url):
7080 qs = parse_qs(url)
7081 query = (qs.get('search_query') or qs.get('q'))[0]
7082 params = qs.get('sp', (None,))[0]
7083 if params:
7084 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
7085 else:
ac668111 7086 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 7087 params = self._SECTIONS.get(section)
7088 if not params:
7089 section = None
7090 title = join_nonempty(query, section, delim=' - ')
af5c1c55 7091 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 7092
7093
182bda88 7094class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 7095 """
25f14e9f 7096 Base class for feed extractors
82d02080 7097 Subclasses must re-define the _FEED_NAME property.
d7ae0639 7098 """
b2e8bc1b 7099 _LOGIN_REQUIRED = True
82d02080 7100 _FEED_NAME = 'feeds'
a25bca9f 7101
7102 def _real_initialize(self):
7103 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 7104
82d02080 7105 @classproperty
d7ae0639 7106 def IE_NAME(self):
82d02080 7107 return f'youtube:{self._FEED_NAME}'
04cc9617 7108
3853309f 7109 def _real_extract(self, url):
3d3dddc9 7110 return self.url_result(
182bda88 7111 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
7112
7113
ef2f3c7f 7114class YoutubeWatchLaterIE(InfoExtractor):
7115 IE_NAME = 'youtube:watchlater'
96565c7e 7116 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 7117 _VALID_URL = r':ytwatchlater'
bc7a9cd8 7118 _TESTS = [{
8bdd16b4 7119 'url': ':ytwatchlater',
bc7a9cd8
S
7120 'only_matching': True,
7121 }]
25f14e9f
S
7122
7123 def _real_extract(self, url):
ef2f3c7f 7124 return self.url_result(
7125 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 7126
7127
25f14e9f 7128class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 7129 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 7130 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 7131 _FEED_NAME = 'recommended'
45db527f 7132 _LOGIN_REQUIRED = False
3d3dddc9 7133 _TESTS = [{
7134 'url': ':ytrec',
7135 'only_matching': True,
7136 }, {
7137 'url': ':ytrecommended',
7138 'only_matching': True,
7139 }, {
7140 'url': 'https://youtube.com',
7141 'only_matching': True,
7142 }]
1ed5b5c9 7143
1ed5b5c9 7144
25f14e9f 7145class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 7146 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 7147 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 7148 _FEED_NAME = 'subscriptions'
3d3dddc9 7149 _TESTS = [{
7150 'url': ':ytsubs',
7151 'only_matching': True,
7152 }, {
7153 'url': ':ytsubscriptions',
7154 'only_matching': True,
7155 }]
1ed5b5c9 7156
1ed5b5c9 7157
25f14e9f 7158class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7159 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7160 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7161 _FEED_NAME = 'history'
3d3dddc9 7162 _TESTS = [{
7163 'url': ':ythistory',
7164 'only_matching': True,
7165 }]
1ed5b5c9
JMF
7166
7167
80eb0bd9 7168class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7169 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7170 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7171 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7172 _TESTS = [{
1dd18a88 7173 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7174 'only_matching': True,
7175 }]
7176
7177 @staticmethod
7178 def _generate_audio_pivot_params(video_id):
7179 """
7180 Generates sfv_audio_pivot browse params for this video id
7181 """
7182 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7183 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7184
7185 def _real_extract(self, url):
7186 video_id = self._match_id(url)
7187 return self.url_result(
7188 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7189 ie=YoutubeTabIE)
7190
7191
15870e90
PH
7192class YoutubeTruncatedURLIE(InfoExtractor):
7193 IE_NAME = 'youtube:truncated_url'
7194 IE_DESC = False # Do not list
975d35db 7195 _VALID_URL = r'''(?x)
b95aab84
PH
7196 (?:https?://)?
7197 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7198 (?:watch\?(?:
c4808c60 7199 feature=[a-z_]+|
b95aab84
PH
7200 annotation_id=annotation_[^&]+|
7201 x-yt-cl=[0-9]+|
c1708b89 7202 hl=[^&]*|
287be8c6 7203 t=[0-9]+
b95aab84
PH
7204 )?
7205 |
7206 attribution_link\?a=[^&]+
7207 )
7208 $
975d35db 7209 '''
15870e90 7210
c4808c60 7211 _TESTS = [{
2d3d2997 7212 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7213 'only_matching': True,
dc2fc736 7214 }, {
2d3d2997 7215 'url': 'https://www.youtube.com/watch?',
dc2fc736 7216 'only_matching': True,
b95aab84
PH
7217 }, {
7218 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7219 'only_matching': True,
7220 }, {
7221 'url': 'https://www.youtube.com/watch?feature=foo',
7222 'only_matching': True,
c1708b89
PH
7223 }, {
7224 'url': 'https://www.youtube.com/watch?hl=en-GB',
7225 'only_matching': True,
287be8c6
PH
7226 }, {
7227 'url': 'https://www.youtube.com/watch?t=2372',
7228 'only_matching': True,
c4808c60
PH
7229 }]
7230
15870e90
PH
7231 def _real_extract(self, url):
7232 raise ExtractorError(
78caa52a
PH
7233 'Did you forget to quote the URL? Remember that & is a meta '
7234 'character in most shells, so you want to put the URL in quotes, '
3867038a 7235 'like youtube-dl '
2d3d2997 7236 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7237 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7238 expected=True)
772fd5cc
PH
7239
7240
471d0367 7241class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7242 IE_NAME = 'youtube:clip'
471d0367 7243 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7244 _TESTS = [{
7245 # FIXME: Other metadata should be extracted from the clip, not from the base video
7246 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7247 'info_dict': {
7248 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7249 'ext': 'mp4',
7250 'section_start': 29.0,
7251 'section_end': 39.7,
7252 'duration': 10.7,
12a1b225
A
7253 'age_limit': 0,
7254 'availability': 'public',
7255 'categories': ['Gaming'],
7256 'channel': 'Scott The Woz',
7257 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7258 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7259 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7260 'like_count': int,
7261 'playable_in_embed': True,
7262 'tags': 'count:17',
7263 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7264 'title': 'Mobile Games on Console - Scott The Woz',
7265 'upload_date': '20210920',
7266 'uploader': 'Scott The Woz',
7666b936 7267 'uploader_id': '@ScottTheWoz',
7268 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7269 'view_count': int,
7270 'live_status': 'not_live',
7666b936 7271 'channel_follower_count': int,
7272 'chapters': 'count:20',
14a14335 7273 'comment_count': int,
7274 'heatmap': 'count:100',
471d0367 7275 }
7276 }]
3cd786db 7277
7278 def _real_extract(self, url):
471d0367 7279 clip_id = self._match_id(url)
7280 _, data = self._extract_webpage(url, clip_id)
7281
7282 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7283 if not video_id:
7284 raise ExtractorError('Unable to find video ID')
7285
7286 clip_data = traverse_obj(data, (
7287 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7288 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7289 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7290 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7291
7292 return {
7293 '_type': 'url_transparent',
7294 'url': f'https://www.youtube.com/watch?v={video_id}',
7295 'ie_key': YoutubeIE.ie_key(),
7296 'id': clip_id,
7297 'section_start': int(clip_data['startTimeMs']) / 1000,
7298 'section_end': int(clip_data['endTimeMs']) / 1000,
7299 }
3cd786db 7300
7301
b032ff0f 7302class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7303 IE_NAME = 'youtube:consent'
7304 IE_DESC = False # Do not list
7305 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7306 _TESTS = [{
7307 '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',
7308 'info_dict': {
7309 'id': 'qVv6vCqciTM',
7310 'ext': 'mp4',
7311 'age_limit': 0,
7666b936 7312 'uploader_id': '@sana_natori',
b032ff0f 7313 'comment_count': int,
7314 'chapters': 'count:13',
7315 'upload_date': '20221223',
7316 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7317 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7318 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7319 'like_count': int,
7320 'release_date': '20221223',
7321 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7322 '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】',
7323 'view_count': int,
7324 'playable_in_embed': True,
7325 'duration': 4438,
7326 'availability': 'public',
7327 'channel_follower_count': int,
7328 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7329 'categories': ['Entertainment'],
7330 'live_status': 'was_live',
7331 'release_timestamp': 1671793345,
7332 'channel': 'さなちゃんねる',
7333 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7334 'uploader': 'さなちゃんねる',
8213ce28 7335 'channel_is_verified': True,
14a14335 7336 'heatmap': 'count:100',
b032ff0f 7337 },
7338 'add_ie': ['Youtube'],
7339 'params': {'skip_download': 'Youtube'},
7340 }]
7341
7342 def _real_extract(self, url):
7343 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7344 if not redirect_url:
7345 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7346 return self.url_result(redirect_url)
7347
7348
772fd5cc
PH
7349class YoutubeTruncatedIDIE(InfoExtractor):
7350 IE_NAME = 'youtube:truncated_id'
7351 IE_DESC = False # Do not list
b95aab84 7352 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7353
7354 _TESTS = [{
7355 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7356 'only_matching': True,
7357 }]
7358
7359 def _real_extract(self, url):
7360 video_id = self._match_id(url)
7361 raise ExtractorError(
86e5f3ed 7362 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7363 expected=True)